├── .gitignore ├── Chapter02 ├── .gitignore ├── 01_agent_anatomy.py ├── 02_cartpole_random.py ├── 03_random_action_wrapper.py └── 04_cartpole_random_monitor.py ├── Chapter03 ├── 01_modules.py ├── 02_tensorboard.py ├── 03_atari_gan.py └── 04_atari_gan_ignite.py ├── Chapter04 ├── 01_cartpole.py ├── 02_frozenlake_naive.py ├── 03_frozenlake_tweaked.py └── 04_frozenlake_nonslippery.py ├── Chapter05 ├── 01_frozenlake_v_iteration.py └── 02_frozenlake_q_iteration.py ├── Chapter06 ├── 01_frozenlake_q_learning.py ├── 02_dqn_pong.py ├── 03_dqn_play.py └── lib │ ├── __init__.py │ ├── dqn_model.py │ └── wrappers.py ├── Chapter07 ├── 01_actions.py ├── 02_agents.py ├── 03_exp_sources.py ├── 04_replay_buf.py ├── 05_target_net.py ├── 06_cartpole.py └── lib.py ├── Chapter08 ├── 01_dqn_basic.py ├── 02_dqn_n_steps.py ├── 03_dqn_double.py ├── 04_dqn_noisy_net.py ├── 05_dqn_prio_replay.py ├── 06_dqn_dueling.py ├── 07_dqn_distrib.py ├── 08_dqn_rainbow.py ├── adhoc │ ├── commute.py │ └── distr_test.py ├── bench │ ├── prio_buffer_bench.py │ └── simple_buffer_bench.py └── lib │ ├── __init__.py │ ├── common.py │ ├── dqn_extra.py │ └── dqn_model.py ├── Chapter09 ├── .gitignore ├── 00_slow_grads.py ├── 01_baseline.py ├── 02_n_envs.py ├── 03_parallel.py ├── 04_wrappers_n_env.py ├── 04_wrappers_parallel.py ├── attic │ ├── 02_env_steps.py │ └── 03_parallel_orig.py ├── img │ ├── 01_orig_tb.png │ ├── 02_steps-tb.png │ ├── 03-serial-blocks.png │ ├── 03_serial.png │ └── 04_parallel.png └── lib │ ├── __init__.py │ ├── __pycache__ │ ├── __init__.cpython-311.pyc │ ├── common.cpython-311.pyc │ └── dqn_model.cpython-311.pyc │ ├── atari_wrappers.py │ ├── common.py │ └── dqn_model.py ├── Chapter10 ├── .gitignore ├── conftest.py ├── data │ ├── ch10-small-quotes.tgz │ └── unpack_data.sh ├── lib │ ├── __init__.py │ ├── common.py │ ├── data.py │ ├── environ.py │ ├── models.py │ └── validation.py ├── run_model.py ├── tests │ ├── test_data.py │ └── test_environ.py ├── train_model.py └── train_model_conv.py ├── Chapter11 ├── .gitignore ├── 01_cartpole_dqn.py ├── 02_cartpole_reinforce.py ├── 03_cartpole_reinforce_baseline.py ├── 04_cartpole_pg.py ├── 05_pong_pg.py ├── 05_pong_pg_tune.py └── lib │ ├── __init__.py │ └── common.py ├── Chapter12 ├── .gitignore ├── 01_cartpole_pg.py ├── 02_pong_a2c.py ├── 02_pong_a2c_tune.py ├── 03_a3c_grad.py └── lib │ ├── __init__.py │ └── common.py ├── Chapter13 ├── adhoc │ ├── hf_t1.py │ ├── hf_t2.py │ ├── lc_t1.py │ └── openai_check.py ├── chatgpt_auto.py ├── chatgpt_interactive.py ├── conftest.py ├── games │ ├── .gitignore │ └── make_games.sh ├── lib │ ├── __init__.py │ ├── common.py │ ├── model.py │ └── preproc.py ├── pytest.ini ├── requirements.txt ├── tests │ ├── __init__.py │ └── test_preproc.py ├── train_basic.py ├── train_preproc.py └── train_tr.py ├── Chapter14 ├── .gitignore ├── adhoc │ ├── 01_wob_create.py │ ├── 02_act_clicks.py │ ├── 03_clicker.py │ ├── 04_load_demo.py │ ├── 05_join_obs.py │ ├── 06_save_traj.py │ └── 06_save_traj_vec.py ├── demos │ ├── click-dialog │ │ ├── click-dialog_0421165244.json │ │ ├── click-dialog_0421165247.json │ │ ├── click-dialog_0421165250.json │ │ ├── click-dialog_0421165253.json │ │ ├── click-dialog_0421165255.json │ │ ├── click-dialog_0421165258.json │ │ ├── click-dialog_0421165300.json │ │ ├── click-dialog_0421165303.json │ │ ├── click-dialog_0421165306.json │ │ ├── click-dialog_0421165308.json │ │ ├── click-dialog_0421165311.json │ │ ├── click-dialog_0421165313.json │ │ ├── click-dialog_0421165316.json │ │ ├── click-dialog_0421165318.json │ │ ├── click-dialog_0421165320.json │ │ └── click-dialog_0421165323.json │ ├── click-tab │ │ ├── click-tab_0426161308.json │ │ ├── click-tab_0426161312.json │ │ ├── click-tab_0426161315.json │ │ ├── click-tab_0426161318.json │ │ ├── click-tab_0426161321.json │ │ ├── click-tab_0426161324.json │ │ ├── click-tab_0426161327.json │ │ ├── click-tab_0426161330.json │ │ ├── click-tab_0426161334.json │ │ ├── click-tab_0426161338.json │ │ ├── click-tab_0426161341.json │ │ ├── click-tab_0426161345.json │ │ ├── click-tab_0426161348.json │ │ ├── click-tab_0426161350.json │ │ └── click-tab_0426161353.json │ ├── count-sides │ │ ├── count-sides_0423161944.json │ │ ├── count-sides_0423161949.json │ │ ├── count-sides_0423161952.json │ │ ├── count-sides_0423161955.json │ │ ├── count-sides_0423161958.json │ │ ├── count-sides_0423162002.json │ │ ├── count-sides_0423162006.json │ │ ├── count-sides_0423162010.json │ │ ├── count-sides_0423162012.json │ │ ├── count-sides_0423162017.json │ │ ├── count-sides_0423162021.json │ │ ├── count-sides_0423162025.json │ │ ├── count-sides_0423162029.json │ │ ├── count-sides_0423162032.json │ │ ├── count-sides_0423162034.json │ │ ├── count-sides_0423162036.json │ │ ├── count-sides_0423162041.json │ │ ├── count-sides_0423162045.json │ │ ├── count-sides_0423162049.json │ │ ├── count-sides_0423162053.json │ │ ├── count-sides_0423162057.json │ │ ├── count-sides_0423162100.json │ │ ├── count-sides_0423162103.json │ │ ├── count-sides_0423162107.json │ │ └── count-sides_0423162110.json │ └── tic-tac-toe │ │ ├── tic-tac-toe_0423220647.json │ │ ├── tic-tac-toe_0423220653.json │ │ ├── tic-tac-toe_0423220658.json │ │ ├── tic-tac-toe_0423220704.json │ │ ├── tic-tac-toe_0423220710.json │ │ ├── tic-tac-toe_0423220718.json │ │ ├── tic-tac-toe_0423220724.json │ │ ├── tic-tac-toe_0423220730.json │ │ ├── tic-tac-toe_0423220737.json │ │ ├── tic-tac-toe_0423220744.json │ │ ├── tic-tac-toe_0423220749.json │ │ ├── tic-tac-toe_0423220754.json │ │ ├── tic-tac-toe_0423220801.json │ │ ├── tic-tac-toe_0423220805.json │ │ ├── tic-tac-toe_0423220812.json │ │ ├── tic-tac-toe_0423220818.json │ │ ├── tic-tac-toe_0423220823.json │ │ ├── tic-tac-toe_0423220828.json │ │ ├── tic-tac-toe_0423220835.json │ │ ├── tic-tac-toe_0423220839.json │ │ ├── tic-tac-toe_0423220843.json │ │ ├── tic-tac-toe_0423220847.json │ │ ├── tic-tac-toe_0423220852.json │ │ ├── tic-tac-toe_0423220856.json │ │ ├── tic-tac-toe_0423220902.json │ │ ├── tic-tac-toe_0423220905.json │ │ └── tic-tac-toe_0423220912.json ├── lib │ ├── common.py │ ├── demos.py │ ├── model.py │ └── wob.py ├── record_demo.py ├── requirements.txt ├── wob_click_mm_play.py ├── wob_click_mm_train.py ├── wob_click_play.py └── wob_click_train.py ├── Chapter15 ├── 01_check_env.py ├── 02_train_a2c.py ├── 03_play_a2c.py ├── 04_train_ddpg.py ├── 05_play_ddpg.py ├── 06_train_d4pg.py ├── lib │ ├── __init__.py │ ├── common.py │ └── model.py └── requirements.txt ├── Chapter16 ├── 01_train_a2c.py ├── 02_play.py ├── 03_train_ppo.py ├── 04_train_trpo.py ├── 05_train_acktr.py ├── 06_train_sac.py ├── lib │ ├── __init__.py │ ├── common.py │ ├── kfac.py │ ├── model.py │ └── trpo.py └── requirements.txt ├── Chapter17 ├── .gitignore ├── 01_cartpole_es.py ├── 02_cheetah_es.py ├── 03_cartpole_ga.py ├── 04_cheetah_ga.py └── lib │ ├── __init__.py │ └── common.py ├── Chapter18 ├── atari_dqn.py ├── atari_ppo.py ├── lib │ ├── __init__.py │ ├── common.py │ ├── dqn_extra.py │ └── ppo.py ├── mcar_dqn.py ├── mcar_ppo.py ├── riverswim.py └── tests │ ├── __init__.py │ └── test_ppo.py ├── Chapter19 ├── .gitignore ├── 01_a2c.py ├── 01_play.py ├── 02_label_ui.py ├── 03_reward_train.py ├── adhoc │ ├── obs_to_gif.py │ └── rw_model.py ├── lib │ ├── __init__.py │ ├── common.py │ ├── rlhf.py │ └── ui_tools.py └── requirements.txt ├── Chapter20 ├── .gitignore ├── lib │ ├── __init__.py │ ├── game.py │ ├── mcts.py │ ├── model.py │ └── muzero.py ├── play-mu.py ├── play.py ├── telegram-bot.py ├── tests │ ├── __init__.py │ ├── test_game.py │ ├── test_model.py │ └── test_muzero.py ├── tournament │ ├── 2ed │ │ ├── charts.ipynb │ │ ├── final-short.png │ │ ├── final.csv │ │ ├── final.svg │ │ ├── final.txt │ │ ├── final_plot.ipynb │ │ ├── semi-0.txt │ │ ├── semi-1.txt │ │ ├── semi-2.txt │ │ ├── semi-3.txt │ │ ├── semi-4.txt │ │ ├── semi-5.txt │ │ ├── semi-6.txt │ │ ├── semi-7.txt │ │ ├── semi-8.txt │ │ ├── semi-9.txt │ │ ├── semi-common.png │ │ └── semi-scores.png │ └── 3ed │ │ ├── .ipynb_checkpoints │ │ ├── charts-checkpoint.ipynb │ │ └── charts-mu-checkpoint.ipynb │ │ ├── charts-mu.ipynb │ │ ├── charts.ipynb │ │ ├── final.sh │ │ ├── final_plot.ipynb │ │ ├── mu-t5-6-res2.txt │ │ ├── mu-v1-wins.csv │ │ ├── semi-v1.txt │ │ ├── semi-v2.txt │ │ ├── v1-wins.csv │ │ └── v2-wins.csv ├── train-mu.py └── train.py ├── Chapter21 ├── .gitignore ├── csvs │ ├── 2ed │ │ ├── README.md │ │ ├── c2x2-paper-d200-t1-v2.csv │ │ ├── c2x2-paper-d200-t1.csv │ │ ├── c2x2-zero-goal-d200-t1-v2.csv │ │ ├── c2x2-zero-goal-d200-t1.csv │ │ ├── c3x3-paper-d200-t1-v2.csv │ │ ├── c3x3-paper-d200-t1.csv │ │ ├── c3x3-zero-goal-d200-no-decay-v2.csv │ │ ├── c3x3-zero-goal-d200-no-decay.csv │ │ ├── c3x3-zero-goal-d200-t1-v2.csv │ │ ├── c3x3-zero-goal-d200-t1.csv │ │ ├── c3x3 │ │ │ ├── c3-paper-d20-1.93e-1.csv │ │ │ ├── c3-zg-d20-noweight-no-decay=5.501e-1.csv │ │ │ ├── c3-zg-d20-noweight-no-decay=5.61e-1.csv │ │ │ ├── c3-zg-d20-noweight-no-decay=6.43e-1.csv │ │ │ ├── c3-zg-d20-noweight-no-decay=7.29e-1.csv │ │ │ ├── c3-zg-d20-noweight-no-decay=chp100k.csv │ │ │ ├── c3-zg-d20-noweight-no-decay=chp64k.csv │ │ │ ├── c3-zg-d20-noweight.csv │ │ │ └── c3-zg-d20.csv │ │ ├── t3-c2x2-mcts-c=0.01.csv │ │ ├── t3-c2x2-mcts-c=0.1.csv │ │ ├── t3-c2x2-mcts-c=1.csv │ │ ├── t3-c2x2-mcts-c=10.csv │ │ ├── t3-c2x2-mcts-c=100.csv │ │ ├── t3-c2x2-mcts-c=1000.csv │ │ ├── t3-c2x2-mcts-c=100000.csv │ │ ├── t3.1-c2x2-mcts-c=1.csv │ │ ├── t3.1-c2x2-mcts-c=10.csv │ │ ├── t3.1-c2x2-mcts-c=100-steps=100k.csv │ │ ├── t3.1-c2x2-mcts-c=100-steps=60k.csv │ │ ├── t3.1-c2x2-mcts-c=100.csv │ │ ├── t3.1-c2x2-mcts-c=1000.csv │ │ ├── t3.1-c2x2-mcts-c=10000.csv │ │ ├── t4-c2x2-mcts-c=10-steps=100k.csv │ │ ├── t4-c2x2-mcts-c=10-steps=200k.csv │ │ ├── t4-c2x2-mcts-c=10-steps=500k.csv │ │ ├── t4-c2x2-mcts-c=100-steps=100k-b10.csv │ │ ├── t4-c2x2-mcts-c=100-steps=100k-b100.csv │ │ ├── t4-c2x2-mcts-c=100-steps=100k.csv │ │ ├── t5-c2x2-1.0366e-01.csv │ │ ├── t5-c2x2-3.0742e-02.csv │ │ ├── t5-c2x2-6.0737e-02.csv │ │ ├── t6-c2x2-nu=1.csv │ │ ├── t6-c2x2-nu=10.csv │ │ ├── t6-c2x2-nu=1000.csv │ │ └── t7-best-paper-1.8184e-1.csv │ └── 3ed │ │ ├── 2x2-paper.csv │ │ ├── 2x2-zg-chpt-17k.csv │ │ ├── 3x3-paper.csv │ │ └── 3x3-zg-chpt-26k.csv ├── cubes_tests │ ├── 2ed │ │ ├── cube2x2_d3.txt │ │ ├── cube2x2_d4.txt │ │ ├── cube2x2_d5.txt │ │ ├── cube2x2_d6.txt │ │ ├── cube3x3_d10.txt │ │ ├── cube3x3_d1000.txt │ │ ├── cube3x3_d15.txt │ │ ├── cube3x3_d3.txt │ │ └── cube3x3_d3_norepeat.txt │ └── 3ed │ │ ├── 2x2-d1-50.txt │ │ └── 3x3-d1-50.txt ├── docs │ └── Notes.md ├── gen_cubes.py ├── ini │ ├── README.md │ ├── cube2x2-paper-d200.ini │ ├── cube2x2-zero-goal-d200.ini │ ├── cube3x3-paper-d20.ini │ ├── cube3x3-paper-d200.ini │ ├── cube3x3-zero-goal-d20-noweight.ini │ ├── cube3x3-zero-goal-d20.ini │ ├── cube3x3-zero-goal-d200-slow-decay.ini │ └── cube3x3-zero-goal-d200.ini ├── libcube │ ├── conf.py │ ├── cubes │ │ ├── __init__.py │ │ ├── _common.py │ │ ├── _env.py │ │ ├── cube2x2.py │ │ └── cube3x3.py │ ├── mcts.py │ └── model.py ├── models │ ├── .gitattributes │ └── 3ed │ │ ├── 2x2-paper │ │ └── best_3.2572e-02.dat │ │ ├── 2x2-zg │ │ └── chpt_017000.dat │ │ ├── 3x3-paper │ │ └── best_3.1818e-02.dat │ │ └── 3x3-zg │ │ └── chpt_026400.dat ├── nbs │ ├── 2ed │ │ ├── 01_paper-vs-zero_goal.ipynb │ │ ├── 02_fix_steps_limit.ipynb │ │ ├── 03_mcts_tuning.ipynb │ │ ├── 04_mcts_C-extra-data.ipynb │ │ ├── 05_batch_search.ipynb │ │ ├── 06_compare_models.ipynb │ │ └── 07_article_figs.ipynb │ └── 3ed │ │ └── 07_article_figs.ipynb ├── requirements.txt ├── run_tests.sh ├── solver.py ├── tests │ ├── __init__.py │ └── libcube │ │ ├── __init__.py │ │ └── cubes │ │ ├── __init__.py │ │ ├── test_cube2x2.py │ │ └── test_cube3x3.py ├── train.py └── train_debug.py ├── Chapter22 ├── .gitignore ├── battle_dqn.py ├── battle_play.py ├── forest_both_dqn.py ├── forest_both_play.py ├── forest_random.py ├── forest_tigers_dqn.py ├── forest_tigers_play.py ├── lib │ ├── __init__.py │ ├── common.py │ ├── data.py │ └── model.py └── requirements.txt ├── LICENSE ├── README.md ├── requirements.txt └── tools ├── avg_csv.py ├── ch12 ├── norm_dist.py └── norm_dist.svg └── plot.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/.gitignore -------------------------------------------------------------------------------- /Chapter02/.gitignore: -------------------------------------------------------------------------------- 1 | video -------------------------------------------------------------------------------- /Chapter02/01_agent_anatomy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter02/01_agent_anatomy.py -------------------------------------------------------------------------------- /Chapter02/02_cartpole_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter02/02_cartpole_random.py -------------------------------------------------------------------------------- /Chapter02/03_random_action_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter02/03_random_action_wrapper.py -------------------------------------------------------------------------------- /Chapter02/04_cartpole_random_monitor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter02/04_cartpole_random_monitor.py -------------------------------------------------------------------------------- /Chapter03/01_modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter03/01_modules.py -------------------------------------------------------------------------------- /Chapter03/02_tensorboard.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter03/02_tensorboard.py -------------------------------------------------------------------------------- /Chapter03/03_atari_gan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter03/03_atari_gan.py -------------------------------------------------------------------------------- /Chapter03/04_atari_gan_ignite.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter03/04_atari_gan_ignite.py -------------------------------------------------------------------------------- /Chapter04/01_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter04/01_cartpole.py -------------------------------------------------------------------------------- /Chapter04/02_frozenlake_naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter04/02_frozenlake_naive.py -------------------------------------------------------------------------------- /Chapter04/03_frozenlake_tweaked.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter04/03_frozenlake_tweaked.py -------------------------------------------------------------------------------- /Chapter04/04_frozenlake_nonslippery.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter04/04_frozenlake_nonslippery.py -------------------------------------------------------------------------------- /Chapter05/01_frozenlake_v_iteration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter05/01_frozenlake_v_iteration.py -------------------------------------------------------------------------------- /Chapter05/02_frozenlake_q_iteration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter05/02_frozenlake_q_iteration.py -------------------------------------------------------------------------------- /Chapter06/01_frozenlake_q_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter06/01_frozenlake_q_learning.py -------------------------------------------------------------------------------- /Chapter06/02_dqn_pong.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter06/02_dqn_pong.py -------------------------------------------------------------------------------- /Chapter06/03_dqn_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter06/03_dqn_play.py -------------------------------------------------------------------------------- /Chapter06/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter06/lib/dqn_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter06/lib/dqn_model.py -------------------------------------------------------------------------------- /Chapter06/lib/wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter06/lib/wrappers.py -------------------------------------------------------------------------------- /Chapter07/01_actions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter07/01_actions.py -------------------------------------------------------------------------------- /Chapter07/02_agents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter07/02_agents.py -------------------------------------------------------------------------------- /Chapter07/03_exp_sources.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter07/03_exp_sources.py -------------------------------------------------------------------------------- /Chapter07/04_replay_buf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter07/04_replay_buf.py -------------------------------------------------------------------------------- /Chapter07/05_target_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter07/05_target_net.py -------------------------------------------------------------------------------- /Chapter07/06_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter07/06_cartpole.py -------------------------------------------------------------------------------- /Chapter07/lib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter07/lib.py -------------------------------------------------------------------------------- /Chapter08/01_dqn_basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/01_dqn_basic.py -------------------------------------------------------------------------------- /Chapter08/02_dqn_n_steps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/02_dqn_n_steps.py -------------------------------------------------------------------------------- /Chapter08/03_dqn_double.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/03_dqn_double.py -------------------------------------------------------------------------------- /Chapter08/04_dqn_noisy_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/04_dqn_noisy_net.py -------------------------------------------------------------------------------- /Chapter08/05_dqn_prio_replay.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/05_dqn_prio_replay.py -------------------------------------------------------------------------------- /Chapter08/06_dqn_dueling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/06_dqn_dueling.py -------------------------------------------------------------------------------- /Chapter08/07_dqn_distrib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/07_dqn_distrib.py -------------------------------------------------------------------------------- /Chapter08/08_dqn_rainbow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/08_dqn_rainbow.py -------------------------------------------------------------------------------- /Chapter08/adhoc/commute.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/adhoc/commute.py -------------------------------------------------------------------------------- /Chapter08/adhoc/distr_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/adhoc/distr_test.py -------------------------------------------------------------------------------- /Chapter08/bench/prio_buffer_bench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/bench/prio_buffer_bench.py -------------------------------------------------------------------------------- /Chapter08/bench/simple_buffer_bench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/bench/simple_buffer_bench.py -------------------------------------------------------------------------------- /Chapter08/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter08/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/lib/common.py -------------------------------------------------------------------------------- /Chapter08/lib/dqn_extra.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/lib/dqn_extra.py -------------------------------------------------------------------------------- /Chapter08/lib/dqn_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter08/lib/dqn_model.py -------------------------------------------------------------------------------- /Chapter09/.gitignore: -------------------------------------------------------------------------------- 1 | runs 2 | res 3 | -------------------------------------------------------------------------------- /Chapter09/00_slow_grads.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/00_slow_grads.py -------------------------------------------------------------------------------- /Chapter09/01_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/01_baseline.py -------------------------------------------------------------------------------- /Chapter09/02_n_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/02_n_envs.py -------------------------------------------------------------------------------- /Chapter09/03_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/03_parallel.py -------------------------------------------------------------------------------- /Chapter09/04_wrappers_n_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/04_wrappers_n_env.py -------------------------------------------------------------------------------- /Chapter09/04_wrappers_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/04_wrappers_parallel.py -------------------------------------------------------------------------------- /Chapter09/attic/02_env_steps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/attic/02_env_steps.py -------------------------------------------------------------------------------- /Chapter09/attic/03_parallel_orig.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/attic/03_parallel_orig.py -------------------------------------------------------------------------------- /Chapter09/img/01_orig_tb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/img/01_orig_tb.png -------------------------------------------------------------------------------- /Chapter09/img/02_steps-tb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/img/02_steps-tb.png -------------------------------------------------------------------------------- /Chapter09/img/03-serial-blocks.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/img/03-serial-blocks.png -------------------------------------------------------------------------------- /Chapter09/img/03_serial.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/img/03_serial.png -------------------------------------------------------------------------------- /Chapter09/img/04_parallel.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/img/04_parallel.png -------------------------------------------------------------------------------- /Chapter09/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter09/lib/__pycache__/__init__.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/lib/__pycache__/__init__.cpython-311.pyc -------------------------------------------------------------------------------- /Chapter09/lib/__pycache__/common.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/lib/__pycache__/common.cpython-311.pyc -------------------------------------------------------------------------------- /Chapter09/lib/__pycache__/dqn_model.cpython-311.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/lib/__pycache__/dqn_model.cpython-311.pyc -------------------------------------------------------------------------------- /Chapter09/lib/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/lib/atari_wrappers.py -------------------------------------------------------------------------------- /Chapter09/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/lib/common.py -------------------------------------------------------------------------------- /Chapter09/lib/dqn_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter09/lib/dqn_model.py -------------------------------------------------------------------------------- /Chapter10/.gitignore: -------------------------------------------------------------------------------- 1 | *.csv 2 | saves 3 | res 4 | -------------------------------------------------------------------------------- /Chapter10/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/conftest.py -------------------------------------------------------------------------------- /Chapter10/data/ch10-small-quotes.tgz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/data/ch10-small-quotes.tgz -------------------------------------------------------------------------------- /Chapter10/data/unpack_data.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | tar xvf ch10-small-quotes.tgz 3 | -------------------------------------------------------------------------------- /Chapter10/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter10/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/lib/common.py -------------------------------------------------------------------------------- /Chapter10/lib/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/lib/data.py -------------------------------------------------------------------------------- /Chapter10/lib/environ.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/lib/environ.py -------------------------------------------------------------------------------- /Chapter10/lib/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/lib/models.py -------------------------------------------------------------------------------- /Chapter10/lib/validation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/lib/validation.py -------------------------------------------------------------------------------- /Chapter10/run_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/run_model.py -------------------------------------------------------------------------------- /Chapter10/tests/test_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/tests/test_data.py -------------------------------------------------------------------------------- /Chapter10/tests/test_environ.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/tests/test_environ.py -------------------------------------------------------------------------------- /Chapter10/train_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/train_model.py -------------------------------------------------------------------------------- /Chapter10/train_model_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter10/train_model_conv.py -------------------------------------------------------------------------------- /Chapter11/.gitignore: -------------------------------------------------------------------------------- 1 | res 2 | -------------------------------------------------------------------------------- /Chapter11/01_cartpole_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter11/01_cartpole_dqn.py -------------------------------------------------------------------------------- /Chapter11/02_cartpole_reinforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter11/02_cartpole_reinforce.py -------------------------------------------------------------------------------- /Chapter11/03_cartpole_reinforce_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter11/03_cartpole_reinforce_baseline.py -------------------------------------------------------------------------------- /Chapter11/04_cartpole_pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter11/04_cartpole_pg.py -------------------------------------------------------------------------------- /Chapter11/05_pong_pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter11/05_pong_pg.py -------------------------------------------------------------------------------- /Chapter11/05_pong_pg_tune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter11/05_pong_pg_tune.py -------------------------------------------------------------------------------- /Chapter11/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter11/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter11/lib/common.py -------------------------------------------------------------------------------- /Chapter12/.gitignore: -------------------------------------------------------------------------------- 1 | runs_arch 2 | -------------------------------------------------------------------------------- /Chapter12/01_cartpole_pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter12/01_cartpole_pg.py -------------------------------------------------------------------------------- /Chapter12/02_pong_a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter12/02_pong_a2c.py -------------------------------------------------------------------------------- /Chapter12/02_pong_a2c_tune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter12/02_pong_a2c_tune.py -------------------------------------------------------------------------------- /Chapter12/03_a3c_grad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter12/03_a3c_grad.py -------------------------------------------------------------------------------- /Chapter12/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter12/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter12/lib/common.py -------------------------------------------------------------------------------- /Chapter13/adhoc/hf_t1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/adhoc/hf_t1.py -------------------------------------------------------------------------------- /Chapter13/adhoc/hf_t2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/adhoc/hf_t2.py -------------------------------------------------------------------------------- /Chapter13/adhoc/lc_t1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/adhoc/lc_t1.py -------------------------------------------------------------------------------- /Chapter13/adhoc/openai_check.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/adhoc/openai_check.py -------------------------------------------------------------------------------- /Chapter13/chatgpt_auto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/chatgpt_auto.py -------------------------------------------------------------------------------- /Chapter13/chatgpt_interactive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/chatgpt_interactive.py -------------------------------------------------------------------------------- /Chapter13/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/conftest.py -------------------------------------------------------------------------------- /Chapter13/games/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/games/.gitignore -------------------------------------------------------------------------------- /Chapter13/games/make_games.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/games/make_games.sh -------------------------------------------------------------------------------- /Chapter13/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter13/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/lib/common.py -------------------------------------------------------------------------------- /Chapter13/lib/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/lib/model.py -------------------------------------------------------------------------------- /Chapter13/lib/preproc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/lib/preproc.py -------------------------------------------------------------------------------- /Chapter13/pytest.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/pytest.ini -------------------------------------------------------------------------------- /Chapter13/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/requirements.txt -------------------------------------------------------------------------------- /Chapter13/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter13/tests/test_preproc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/tests/test_preproc.py -------------------------------------------------------------------------------- /Chapter13/train_basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/train_basic.py -------------------------------------------------------------------------------- /Chapter13/train_preproc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/train_preproc.py -------------------------------------------------------------------------------- /Chapter13/train_tr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter13/train_tr.py -------------------------------------------------------------------------------- /Chapter14/.gitignore: -------------------------------------------------------------------------------- 1 | out -------------------------------------------------------------------------------- /Chapter14/adhoc/01_wob_create.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/adhoc/01_wob_create.py -------------------------------------------------------------------------------- /Chapter14/adhoc/02_act_clicks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/adhoc/02_act_clicks.py -------------------------------------------------------------------------------- /Chapter14/adhoc/03_clicker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/adhoc/03_clicker.py -------------------------------------------------------------------------------- /Chapter14/adhoc/04_load_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/adhoc/04_load_demo.py -------------------------------------------------------------------------------- /Chapter14/adhoc/05_join_obs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/adhoc/05_join_obs.py -------------------------------------------------------------------------------- /Chapter14/adhoc/06_save_traj.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/adhoc/06_save_traj.py -------------------------------------------------------------------------------- /Chapter14/adhoc/06_save_traj_vec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/adhoc/06_save_traj_vec.py -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165244.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165244.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165247.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165247.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165250.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165250.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165253.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165253.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165255.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165255.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165258.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165258.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165300.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165300.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165303.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165303.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165306.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165306.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165308.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165308.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165311.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165311.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165313.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165313.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165316.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165316.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165318.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165318.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165320.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165320.json -------------------------------------------------------------------------------- /Chapter14/demos/click-dialog/click-dialog_0421165323.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-dialog/click-dialog_0421165323.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161308.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161308.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161312.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161312.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161315.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161315.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161318.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161318.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161321.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161321.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161324.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161324.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161327.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161327.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161330.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161330.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161334.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161334.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161338.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161338.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161341.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161341.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161345.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161345.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161348.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161348.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161350.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161350.json -------------------------------------------------------------------------------- /Chapter14/demos/click-tab/click-tab_0426161353.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/click-tab/click-tab_0426161353.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423161944.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423161944.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423161949.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423161949.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423161952.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423161952.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423161955.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423161955.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423161958.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423161958.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162002.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162002.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162006.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162006.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162010.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162010.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162012.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162012.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162017.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162017.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162021.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162021.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162025.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162025.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162029.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162029.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162032.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162032.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162034.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162034.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162036.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162036.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162041.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162041.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162045.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162045.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162049.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162049.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162053.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162053.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162057.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162057.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162100.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162100.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162103.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162103.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162107.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162107.json -------------------------------------------------------------------------------- /Chapter14/demos/count-sides/count-sides_0423162110.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/count-sides/count-sides_0423162110.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220647.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220647.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220653.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220653.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220658.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220658.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220704.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220704.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220710.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220710.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220718.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220718.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220724.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220724.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220730.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220730.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220737.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220737.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220744.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220744.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220749.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220749.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220754.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220754.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220801.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220801.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220805.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220805.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220812.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220812.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220818.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220818.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220823.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220823.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220828.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220828.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220835.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220835.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220839.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220839.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220843.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220843.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220847.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220847.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220852.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220852.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220856.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220856.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220902.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220902.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220905.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220905.json -------------------------------------------------------------------------------- /Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220912.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/demos/tic-tac-toe/tic-tac-toe_0423220912.json -------------------------------------------------------------------------------- /Chapter14/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/lib/common.py -------------------------------------------------------------------------------- /Chapter14/lib/demos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/lib/demos.py -------------------------------------------------------------------------------- /Chapter14/lib/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/lib/model.py -------------------------------------------------------------------------------- /Chapter14/lib/wob.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/lib/wob.py -------------------------------------------------------------------------------- /Chapter14/record_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/record_demo.py -------------------------------------------------------------------------------- /Chapter14/requirements.txt: -------------------------------------------------------------------------------- 1 | miniwob==1.0 2 | nltk==3.8.1 3 | bottle==0.12.25 4 | -------------------------------------------------------------------------------- /Chapter14/wob_click_mm_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/wob_click_mm_play.py -------------------------------------------------------------------------------- /Chapter14/wob_click_mm_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/wob_click_mm_train.py -------------------------------------------------------------------------------- /Chapter14/wob_click_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/wob_click_play.py -------------------------------------------------------------------------------- /Chapter14/wob_click_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter14/wob_click_train.py -------------------------------------------------------------------------------- /Chapter15/01_check_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter15/01_check_env.py -------------------------------------------------------------------------------- /Chapter15/02_train_a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter15/02_train_a2c.py -------------------------------------------------------------------------------- /Chapter15/03_play_a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter15/03_play_a2c.py -------------------------------------------------------------------------------- /Chapter15/04_train_ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter15/04_train_ddpg.py -------------------------------------------------------------------------------- /Chapter15/05_play_ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter15/05_play_ddpg.py -------------------------------------------------------------------------------- /Chapter15/06_train_d4pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter15/06_train_d4pg.py -------------------------------------------------------------------------------- /Chapter15/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter15/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter15/lib/common.py -------------------------------------------------------------------------------- /Chapter15/lib/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter15/lib/model.py -------------------------------------------------------------------------------- /Chapter15/requirements.txt: -------------------------------------------------------------------------------- 1 | pybullet==3.2.6 2 | gym==0.25.1 3 | numpy<2 -------------------------------------------------------------------------------- /Chapter16/01_train_a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/01_train_a2c.py -------------------------------------------------------------------------------- /Chapter16/02_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/02_play.py -------------------------------------------------------------------------------- /Chapter16/03_train_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/03_train_ppo.py -------------------------------------------------------------------------------- /Chapter16/04_train_trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/04_train_trpo.py -------------------------------------------------------------------------------- /Chapter16/05_train_acktr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/05_train_acktr.py -------------------------------------------------------------------------------- /Chapter16/06_train_sac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/06_train_sac.py -------------------------------------------------------------------------------- /Chapter16/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter16/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/lib/common.py -------------------------------------------------------------------------------- /Chapter16/lib/kfac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/lib/kfac.py -------------------------------------------------------------------------------- /Chapter16/lib/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/lib/model.py -------------------------------------------------------------------------------- /Chapter16/lib/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter16/lib/trpo.py -------------------------------------------------------------------------------- /Chapter16/requirements.txt: -------------------------------------------------------------------------------- 1 | gymnasium[mujoco]==0.29.0 -------------------------------------------------------------------------------- /Chapter17/.gitignore: -------------------------------------------------------------------------------- 1 | res 2 | -------------------------------------------------------------------------------- /Chapter17/01_cartpole_es.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter17/01_cartpole_es.py -------------------------------------------------------------------------------- /Chapter17/02_cheetah_es.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter17/02_cheetah_es.py -------------------------------------------------------------------------------- /Chapter17/03_cartpole_ga.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter17/03_cartpole_ga.py -------------------------------------------------------------------------------- /Chapter17/04_cheetah_ga.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter17/04_cheetah_ga.py -------------------------------------------------------------------------------- /Chapter17/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter17/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter17/lib/common.py -------------------------------------------------------------------------------- /Chapter18/atari_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter18/atari_dqn.py -------------------------------------------------------------------------------- /Chapter18/atari_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter18/atari_ppo.py -------------------------------------------------------------------------------- /Chapter18/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter18/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter18/lib/common.py -------------------------------------------------------------------------------- /Chapter18/lib/dqn_extra.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter18/lib/dqn_extra.py -------------------------------------------------------------------------------- /Chapter18/lib/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter18/lib/ppo.py -------------------------------------------------------------------------------- /Chapter18/mcar_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter18/mcar_dqn.py -------------------------------------------------------------------------------- /Chapter18/mcar_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter18/mcar_ppo.py -------------------------------------------------------------------------------- /Chapter18/riverswim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter18/riverswim.py -------------------------------------------------------------------------------- /Chapter18/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter18/tests/test_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter18/tests/test_ppo.py -------------------------------------------------------------------------------- /Chapter19/.gitignore: -------------------------------------------------------------------------------- 1 | db* 2 | *.dat 3 | rec* 4 | -------------------------------------------------------------------------------- /Chapter19/01_a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter19/01_a2c.py -------------------------------------------------------------------------------- /Chapter19/01_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter19/01_play.py -------------------------------------------------------------------------------- /Chapter19/02_label_ui.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter19/02_label_ui.py -------------------------------------------------------------------------------- /Chapter19/03_reward_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter19/03_reward_train.py -------------------------------------------------------------------------------- /Chapter19/adhoc/obs_to_gif.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter19/adhoc/obs_to_gif.py -------------------------------------------------------------------------------- /Chapter19/adhoc/rw_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter19/adhoc/rw_model.py -------------------------------------------------------------------------------- /Chapter19/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter19/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter19/lib/common.py -------------------------------------------------------------------------------- /Chapter19/lib/rlhf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter19/lib/rlhf.py -------------------------------------------------------------------------------- /Chapter19/lib/ui_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter19/lib/ui_tools.py -------------------------------------------------------------------------------- /Chapter19/requirements.txt: -------------------------------------------------------------------------------- 1 | nicegui==1.4.26 2 | -------------------------------------------------------------------------------- /Chapter20/.gitignore: -------------------------------------------------------------------------------- 1 | res 2 | -------------------------------------------------------------------------------- /Chapter20/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter20/lib/game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/lib/game.py -------------------------------------------------------------------------------- /Chapter20/lib/mcts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/lib/mcts.py -------------------------------------------------------------------------------- /Chapter20/lib/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/lib/model.py -------------------------------------------------------------------------------- /Chapter20/lib/muzero.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/lib/muzero.py -------------------------------------------------------------------------------- /Chapter20/play-mu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/play-mu.py -------------------------------------------------------------------------------- /Chapter20/play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/play.py -------------------------------------------------------------------------------- /Chapter20/telegram-bot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/telegram-bot.py -------------------------------------------------------------------------------- /Chapter20/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter20/tests/test_game.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tests/test_game.py -------------------------------------------------------------------------------- /Chapter20/tests/test_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tests/test_model.py -------------------------------------------------------------------------------- /Chapter20/tests/test_muzero.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tests/test_muzero.py -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/charts.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/charts.ipynb -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/final-short.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/final-short.png -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/final.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/final.csv -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/final.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/final.svg -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/final.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/final.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/final_plot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/final_plot.ipynb -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-0.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-0.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-1.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-2.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-3.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-4.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-4.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-5.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-5.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-6.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-6.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-7.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-7.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-8.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-8.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-9.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-9.txt -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-common.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-common.png -------------------------------------------------------------------------------- /Chapter20/tournament/2ed/semi-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/2ed/semi-scores.png -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/.ipynb_checkpoints/charts-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/.ipynb_checkpoints/charts-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/.ipynb_checkpoints/charts-mu-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/.ipynb_checkpoints/charts-mu-checkpoint.ipynb -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/charts-mu.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/charts-mu.ipynb -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/charts.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/charts.ipynb -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/final.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/final.sh -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/final_plot.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/final_plot.ipynb -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/mu-t5-6-res2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/mu-t5-6-res2.txt -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/mu-v1-wins.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/mu-v1-wins.csv -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/semi-v1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/semi-v1.txt -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/semi-v2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/semi-v2.txt -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/v1-wins.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/v1-wins.csv -------------------------------------------------------------------------------- /Chapter20/tournament/3ed/v2-wins.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/tournament/3ed/v2-wins.csv -------------------------------------------------------------------------------- /Chapter20/train-mu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/train-mu.py -------------------------------------------------------------------------------- /Chapter20/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter20/train.py -------------------------------------------------------------------------------- /Chapter21/.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | runs 3 | saves 4 | *.png 5 | .ipynb_checkpoints 6 | *.log 7 | -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/README.md -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c2x2-paper-d200-t1-v2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c2x2-paper-d200-t1-v2.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c2x2-paper-d200-t1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c2x2-paper-d200-t1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c2x2-zero-goal-d200-t1-v2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c2x2-zero-goal-d200-t1-v2.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c2x2-zero-goal-d200-t1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c2x2-zero-goal-d200-t1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3-paper-d200-t1-v2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3-paper-d200-t1-v2.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3-paper-d200-t1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3-paper-d200-t1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3-zero-goal-d200-no-decay-v2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3-zero-goal-d200-no-decay-v2.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3-zero-goal-d200-no-decay.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3-zero-goal-d200-no-decay.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3-zero-goal-d200-t1-v2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3-zero-goal-d200-t1-v2.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3-zero-goal-d200-t1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3-zero-goal-d200-t1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3/c3-paper-d20-1.93e-1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3/c3-paper-d20-1.93e-1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=5.501e-1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=5.501e-1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=5.61e-1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=5.61e-1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=6.43e-1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=6.43e-1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=7.29e-1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=7.29e-1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=chp100k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=chp100k.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=chp64k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight-no-decay=chp64k.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3/c3-zg-d20-noweight.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/c3x3/c3-zg-d20.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/c3x3/c3-zg-d20.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3-c2x2-mcts-c=0.01.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3-c2x2-mcts-c=0.01.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3-c2x2-mcts-c=0.1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3-c2x2-mcts-c=0.1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3-c2x2-mcts-c=1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3-c2x2-mcts-c=1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3-c2x2-mcts-c=10.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3-c2x2-mcts-c=10.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3-c2x2-mcts-c=100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3-c2x2-mcts-c=100.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3-c2x2-mcts-c=1000.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3-c2x2-mcts-c=1000.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3-c2x2-mcts-c=100000.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3-c2x2-mcts-c=100000.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=10.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=10.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=100-steps=100k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=100-steps=100k.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=100-steps=60k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=100-steps=60k.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=100.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=1000.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=1000.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=10000.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t3.1-c2x2-mcts-c=10000.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t4-c2x2-mcts-c=10-steps=100k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t4-c2x2-mcts-c=10-steps=100k.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t4-c2x2-mcts-c=10-steps=200k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t4-c2x2-mcts-c=10-steps=200k.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t4-c2x2-mcts-c=10-steps=500k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t4-c2x2-mcts-c=10-steps=500k.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t4-c2x2-mcts-c=100-steps=100k-b10.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t4-c2x2-mcts-c=100-steps=100k-b10.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t4-c2x2-mcts-c=100-steps=100k-b100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t4-c2x2-mcts-c=100-steps=100k-b100.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t4-c2x2-mcts-c=100-steps=100k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t4-c2x2-mcts-c=100-steps=100k.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t5-c2x2-1.0366e-01.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t5-c2x2-1.0366e-01.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t5-c2x2-3.0742e-02.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t5-c2x2-3.0742e-02.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t5-c2x2-6.0737e-02.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t5-c2x2-6.0737e-02.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t6-c2x2-nu=1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t6-c2x2-nu=1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t6-c2x2-nu=10.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t6-c2x2-nu=10.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t6-c2x2-nu=1000.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t6-c2x2-nu=1000.csv -------------------------------------------------------------------------------- /Chapter21/csvs/2ed/t7-best-paper-1.8184e-1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/2ed/t7-best-paper-1.8184e-1.csv -------------------------------------------------------------------------------- /Chapter21/csvs/3ed/2x2-paper.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/3ed/2x2-paper.csv -------------------------------------------------------------------------------- /Chapter21/csvs/3ed/2x2-zg-chpt-17k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/3ed/2x2-zg-chpt-17k.csv -------------------------------------------------------------------------------- /Chapter21/csvs/3ed/3x3-paper.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/3ed/3x3-paper.csv -------------------------------------------------------------------------------- /Chapter21/csvs/3ed/3x3-zg-chpt-26k.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/csvs/3ed/3x3-zg-chpt-26k.csv -------------------------------------------------------------------------------- /Chapter21/cubes_tests/2ed/cube2x2_d3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/2ed/cube2x2_d3.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/2ed/cube2x2_d4.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/2ed/cube2x2_d4.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/2ed/cube2x2_d5.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/2ed/cube2x2_d5.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/2ed/cube2x2_d6.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/2ed/cube2x2_d6.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/2ed/cube3x3_d10.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/2ed/cube3x3_d10.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/2ed/cube3x3_d1000.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/2ed/cube3x3_d1000.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/2ed/cube3x3_d15.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/2ed/cube3x3_d15.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/2ed/cube3x3_d3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/2ed/cube3x3_d3.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/2ed/cube3x3_d3_norepeat.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/2ed/cube3x3_d3_norepeat.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/3ed/2x2-d1-50.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/3ed/2x2-d1-50.txt -------------------------------------------------------------------------------- /Chapter21/cubes_tests/3ed/3x3-d1-50.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/cubes_tests/3ed/3x3-d1-50.txt -------------------------------------------------------------------------------- /Chapter21/docs/Notes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/docs/Notes.md -------------------------------------------------------------------------------- /Chapter21/gen_cubes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/gen_cubes.py -------------------------------------------------------------------------------- /Chapter21/ini/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/ini/README.md -------------------------------------------------------------------------------- /Chapter21/ini/cube2x2-paper-d200.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/ini/cube2x2-paper-d200.ini -------------------------------------------------------------------------------- /Chapter21/ini/cube2x2-zero-goal-d200.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/ini/cube2x2-zero-goal-d200.ini -------------------------------------------------------------------------------- /Chapter21/ini/cube3x3-paper-d20.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/ini/cube3x3-paper-d20.ini -------------------------------------------------------------------------------- /Chapter21/ini/cube3x3-paper-d200.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/ini/cube3x3-paper-d200.ini -------------------------------------------------------------------------------- /Chapter21/ini/cube3x3-zero-goal-d20-noweight.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/ini/cube3x3-zero-goal-d20-noweight.ini -------------------------------------------------------------------------------- /Chapter21/ini/cube3x3-zero-goal-d20.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/ini/cube3x3-zero-goal-d20.ini -------------------------------------------------------------------------------- /Chapter21/ini/cube3x3-zero-goal-d200-slow-decay.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/ini/cube3x3-zero-goal-d200-slow-decay.ini -------------------------------------------------------------------------------- /Chapter21/ini/cube3x3-zero-goal-d200.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/ini/cube3x3-zero-goal-d200.ini -------------------------------------------------------------------------------- /Chapter21/libcube/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/libcube/conf.py -------------------------------------------------------------------------------- /Chapter21/libcube/cubes/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/libcube/cubes/__init__.py -------------------------------------------------------------------------------- /Chapter21/libcube/cubes/_common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/libcube/cubes/_common.py -------------------------------------------------------------------------------- /Chapter21/libcube/cubes/_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/libcube/cubes/_env.py -------------------------------------------------------------------------------- /Chapter21/libcube/cubes/cube2x2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/libcube/cubes/cube2x2.py -------------------------------------------------------------------------------- /Chapter21/libcube/cubes/cube3x3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/libcube/cubes/cube3x3.py -------------------------------------------------------------------------------- /Chapter21/libcube/mcts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/libcube/mcts.py -------------------------------------------------------------------------------- /Chapter21/libcube/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/libcube/model.py -------------------------------------------------------------------------------- /Chapter21/models/.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/models/.gitattributes -------------------------------------------------------------------------------- /Chapter21/models/3ed/2x2-paper/best_3.2572e-02.dat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/models/3ed/2x2-paper/best_3.2572e-02.dat -------------------------------------------------------------------------------- /Chapter21/models/3ed/2x2-zg/chpt_017000.dat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/models/3ed/2x2-zg/chpt_017000.dat -------------------------------------------------------------------------------- /Chapter21/models/3ed/3x3-paper/best_3.1818e-02.dat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/models/3ed/3x3-paper/best_3.1818e-02.dat -------------------------------------------------------------------------------- /Chapter21/models/3ed/3x3-zg/chpt_026400.dat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/models/3ed/3x3-zg/chpt_026400.dat -------------------------------------------------------------------------------- /Chapter21/nbs/2ed/01_paper-vs-zero_goal.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/nbs/2ed/01_paper-vs-zero_goal.ipynb -------------------------------------------------------------------------------- /Chapter21/nbs/2ed/02_fix_steps_limit.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/nbs/2ed/02_fix_steps_limit.ipynb -------------------------------------------------------------------------------- /Chapter21/nbs/2ed/03_mcts_tuning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/nbs/2ed/03_mcts_tuning.ipynb -------------------------------------------------------------------------------- /Chapter21/nbs/2ed/04_mcts_C-extra-data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/nbs/2ed/04_mcts_C-extra-data.ipynb -------------------------------------------------------------------------------- /Chapter21/nbs/2ed/05_batch_search.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/nbs/2ed/05_batch_search.ipynb -------------------------------------------------------------------------------- /Chapter21/nbs/2ed/06_compare_models.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/nbs/2ed/06_compare_models.ipynb -------------------------------------------------------------------------------- /Chapter21/nbs/2ed/07_article_figs.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/nbs/2ed/07_article_figs.ipynb -------------------------------------------------------------------------------- /Chapter21/nbs/3ed/07_article_figs.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/nbs/3ed/07_article_figs.ipynb -------------------------------------------------------------------------------- /Chapter21/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/requirements.txt -------------------------------------------------------------------------------- /Chapter21/run_tests.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/run_tests.sh -------------------------------------------------------------------------------- /Chapter21/solver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/solver.py -------------------------------------------------------------------------------- /Chapter21/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter21/tests/libcube/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter21/tests/libcube/cubes/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter21/tests/libcube/cubes/test_cube2x2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/tests/libcube/cubes/test_cube2x2.py -------------------------------------------------------------------------------- /Chapter21/tests/libcube/cubes/test_cube3x3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/tests/libcube/cubes/test_cube3x3.py -------------------------------------------------------------------------------- /Chapter21/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/train.py -------------------------------------------------------------------------------- /Chapter21/train_debug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter21/train_debug.py -------------------------------------------------------------------------------- /Chapter22/.gitignore: -------------------------------------------------------------------------------- 1 | render 2 | -------------------------------------------------------------------------------- /Chapter22/battle_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/battle_dqn.py -------------------------------------------------------------------------------- /Chapter22/battle_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/battle_play.py -------------------------------------------------------------------------------- /Chapter22/forest_both_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/forest_both_dqn.py -------------------------------------------------------------------------------- /Chapter22/forest_both_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/forest_both_play.py -------------------------------------------------------------------------------- /Chapter22/forest_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/forest_random.py -------------------------------------------------------------------------------- /Chapter22/forest_tigers_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/forest_tigers_dqn.py -------------------------------------------------------------------------------- /Chapter22/forest_tigers_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/forest_tigers_play.py -------------------------------------------------------------------------------- /Chapter22/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chapter22/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/lib/common.py -------------------------------------------------------------------------------- /Chapter22/lib/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/lib/data.py -------------------------------------------------------------------------------- /Chapter22/lib/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/Chapter22/lib/model.py -------------------------------------------------------------------------------- /Chapter22/requirements.txt: -------------------------------------------------------------------------------- 1 | magent2==0.3.3 -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/README.md -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/requirements.txt -------------------------------------------------------------------------------- /tools/avg_csv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/tools/avg_csv.py -------------------------------------------------------------------------------- /tools/ch12/norm_dist.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/tools/ch12/norm_dist.py -------------------------------------------------------------------------------- /tools/ch12/norm_dist.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/tools/ch12/norm_dist.svg -------------------------------------------------------------------------------- /tools/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-Third-Edition/HEAD/tools/plot.py --------------------------------------------------------------------------------