├── .gitignore ├── 1-grid-world ├── 1-policy-iteration │ ├── environment.py │ └── policy_iteration.py ├── 2-value-iteration │ ├── environment.py │ └── value_iteration.py ├── 3-monte-carlo │ ├── environment.py │ └── mc_agent.py ├── 4-sarsa │ ├── .python-version │ ├── environment.py │ └── sarsa_agent.py ├── 5-q-learning │ ├── .python-version │ ├── environment.py │ └── q_learning_agent.py ├── 6-deep-sarsa │ ├── deep_sarsa_agent.py │ ├── environment.py │ ├── save_graph │ │ └── deep_sarsa_trained.png │ └── save_model │ │ └── deep_sarsa_trained.h5 ├── 7-reinforce │ ├── environment.py │ ├── reinforce_agent.py │ ├── save_graph │ │ └── reinforce_trained.png │ └── save_model │ │ └── reinforce_trained.h5 ├── README.md ├── gridworld.png ├── gridworld_changing.png └── img │ ├── circle.png │ ├── down.png │ ├── left.png │ ├── rectangle.png │ ├── right.png │ ├── triangle.png │ └── up.png ├── 2-cartpole ├── 1-dqn │ ├── SumTree.py │ ├── cartpole_dqn.py │ ├── cartpole_only_per.py │ ├── save_graph │ │ └── Cartpole_DQN.png │ └── save_model │ │ └── cartpole_dqn.h5 ├── 2-double-dqn │ ├── cartpole_ddqn.py │ ├── save_graph │ │ └── cartpole_ddqn.png │ └── save_model │ │ └── cartpole_ddqn.h5 ├── 3-reinforce │ ├── cartpole_reinforce.py │ ├── save_graph │ │ └── cartpole_reinforce.png │ └── save_model │ │ └── cartpole_reinforce.h5 ├── 4-actor-critic │ ├── cartpole_a2c.py │ ├── save_graph │ │ └── cartpole_a2c.png │ └── save_model │ │ ├── cartpole_actor.h5 │ │ └── cartpole_critic.h5 ├── 5-a3c │ ├── cartpole_a3c.py │ └── save_model │ │ ├── Cartpole_A3C_actor.h5 │ │ └── Cartpole_A3C_critic.h5 ├── LICENSE ├── README.md └── cartpole.png ├── 3-atari ├── 1-breakout │ ├── breakout_a3c.py │ ├── breakout_ddqn.py │ ├── breakout_dqn.py │ ├── breakout_dueling_ddqn.py │ ├── play_a3c_model.py │ ├── play_dqn_model.py │ ├── save_model │ │ ├── breakout_a3c_1_actor.h5 │ │ ├── breakout_a3c_1_critic.h5 │ │ ├── breakout_a3c_2_actor.h5 │ │ ├── breakout_a3c_2_critic.h5 │ │ ├── breakout_a3c_3_actor.h5 │ │ ├── breakout_a3c_3_critic.h5 │ │ ├── breakout_a3c_4_actor.h5 │ │ ├── breakout_a3c_4_critic.h5 │ │ ├── breakout_a3c_5_actor.h5 │ │ ├── breakout_a3c_5_critic.h5 │ │ ├── breakout_dqn.h5 │ │ ├── breakout_dqn_1.h5 │ │ ├── breakout_dqn_2.h5 │ │ ├── breakout_dqn_3.h5 │ │ ├── breakout_dqn_4.h5 │ │ └── breakout_dqn_5.h5 │ └── summary │ │ ├── breakout_a3c │ │ └── events.out.tfevents.1497264638 │ │ └── breakout_dqn │ │ └── events.out.tfevents.1496968668.young-System-Product-Name ├── 2-pong │ ├── README.md │ ├── assets │ │ ├── pg.gif │ │ └── score.png │ ├── pong_a3c.py │ ├── pong_reinforce.py │ └── save_model │ │ └── pong_reinforce.h5 └── LICENSE ├── 4-gym └── 1-mountaincar │ ├── mountaincar_dqn.py │ └── save_model │ └── MountainCar_DQN.h5 ├── LICENSE ├── README.md ├── images └── Reinforcement-Learning.png ├── requirements.txt └── wiki ├── how-to-windows.md ├── img ├── how-to-windows.png ├── link-env-with-pychar-1.png ├── link-env-with-pychar-2.png └── link-env-with-pychar.png ├── install_guide_osx+ubuntu.md └── rlcode_image ├── cartpole_exam.png ├── console_hello_world.png ├── default_config.png ├── file_setting.png ├── hello_world_ubuntu.png ├── openai_github.png ├── project_interpreter.png ├── pycham_new_project.png ├── pycharm_community.png ├── pycharm_drag.png ├── pycharm_init.png ├── python3_terminal.jpg ├── python_download.png ├── python_installed.png ├── python_intalled.png ├── rl_book_hello_world.png ├── rl_book_project.png ├── rl_book_venv.png ├── rl_book_virtualenv.png ├── rlcode_book_directory.png ├── rlcode_project.png ├── run_hello_world.png ├── sh_pycharm.sh.png └── terminal_rlcode_book.png /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/.gitignore -------------------------------------------------------------------------------- /1-grid-world/1-policy-iteration/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/1-policy-iteration/environment.py -------------------------------------------------------------------------------- /1-grid-world/1-policy-iteration/policy_iteration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/1-policy-iteration/policy_iteration.py -------------------------------------------------------------------------------- /1-grid-world/2-value-iteration/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/2-value-iteration/environment.py -------------------------------------------------------------------------------- /1-grid-world/2-value-iteration/value_iteration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/2-value-iteration/value_iteration.py -------------------------------------------------------------------------------- /1-grid-world/3-monte-carlo/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/3-monte-carlo/environment.py -------------------------------------------------------------------------------- /1-grid-world/3-monte-carlo/mc_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/3-monte-carlo/mc_agent.py -------------------------------------------------------------------------------- /1-grid-world/4-sarsa/.python-version: -------------------------------------------------------------------------------- 1 | 3.5.0 2 | -------------------------------------------------------------------------------- /1-grid-world/4-sarsa/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/4-sarsa/environment.py -------------------------------------------------------------------------------- /1-grid-world/4-sarsa/sarsa_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/4-sarsa/sarsa_agent.py -------------------------------------------------------------------------------- /1-grid-world/5-q-learning/.python-version: -------------------------------------------------------------------------------- 1 | 3.5.0 2 | -------------------------------------------------------------------------------- /1-grid-world/5-q-learning/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/5-q-learning/environment.py -------------------------------------------------------------------------------- /1-grid-world/5-q-learning/q_learning_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/5-q-learning/q_learning_agent.py -------------------------------------------------------------------------------- /1-grid-world/6-deep-sarsa/deep_sarsa_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/6-deep-sarsa/deep_sarsa_agent.py -------------------------------------------------------------------------------- /1-grid-world/6-deep-sarsa/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/6-deep-sarsa/environment.py -------------------------------------------------------------------------------- /1-grid-world/6-deep-sarsa/save_graph/deep_sarsa_trained.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/6-deep-sarsa/save_graph/deep_sarsa_trained.png -------------------------------------------------------------------------------- /1-grid-world/6-deep-sarsa/save_model/deep_sarsa_trained.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/6-deep-sarsa/save_model/deep_sarsa_trained.h5 -------------------------------------------------------------------------------- /1-grid-world/7-reinforce/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/7-reinforce/environment.py -------------------------------------------------------------------------------- /1-grid-world/7-reinforce/reinforce_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/7-reinforce/reinforce_agent.py -------------------------------------------------------------------------------- /1-grid-world/7-reinforce/save_graph/reinforce_trained.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/7-reinforce/save_graph/reinforce_trained.png -------------------------------------------------------------------------------- /1-grid-world/7-reinforce/save_model/reinforce_trained.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/7-reinforce/save_model/reinforce_trained.h5 -------------------------------------------------------------------------------- /1-grid-world/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/README.md -------------------------------------------------------------------------------- /1-grid-world/gridworld.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/gridworld.png -------------------------------------------------------------------------------- /1-grid-world/gridworld_changing.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/gridworld_changing.png -------------------------------------------------------------------------------- /1-grid-world/img/circle.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/img/circle.png -------------------------------------------------------------------------------- /1-grid-world/img/down.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/img/down.png -------------------------------------------------------------------------------- /1-grid-world/img/left.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/img/left.png -------------------------------------------------------------------------------- /1-grid-world/img/rectangle.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/img/rectangle.png -------------------------------------------------------------------------------- /1-grid-world/img/right.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/img/right.png -------------------------------------------------------------------------------- /1-grid-world/img/triangle.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/img/triangle.png -------------------------------------------------------------------------------- /1-grid-world/img/up.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/1-grid-world/img/up.png -------------------------------------------------------------------------------- /2-cartpole/1-dqn/SumTree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/1-dqn/SumTree.py -------------------------------------------------------------------------------- /2-cartpole/1-dqn/cartpole_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/1-dqn/cartpole_dqn.py -------------------------------------------------------------------------------- /2-cartpole/1-dqn/cartpole_only_per.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/1-dqn/cartpole_only_per.py -------------------------------------------------------------------------------- /2-cartpole/1-dqn/save_graph/Cartpole_DQN.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/1-dqn/save_graph/Cartpole_DQN.png -------------------------------------------------------------------------------- /2-cartpole/1-dqn/save_model/cartpole_dqn.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/1-dqn/save_model/cartpole_dqn.h5 -------------------------------------------------------------------------------- /2-cartpole/2-double-dqn/cartpole_ddqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/2-double-dqn/cartpole_ddqn.py -------------------------------------------------------------------------------- /2-cartpole/2-double-dqn/save_graph/cartpole_ddqn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/2-double-dqn/save_graph/cartpole_ddqn.png -------------------------------------------------------------------------------- /2-cartpole/2-double-dqn/save_model/cartpole_ddqn.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/2-double-dqn/save_model/cartpole_ddqn.h5 -------------------------------------------------------------------------------- /2-cartpole/3-reinforce/cartpole_reinforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/3-reinforce/cartpole_reinforce.py -------------------------------------------------------------------------------- /2-cartpole/3-reinforce/save_graph/cartpole_reinforce.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/3-reinforce/save_graph/cartpole_reinforce.png -------------------------------------------------------------------------------- /2-cartpole/3-reinforce/save_model/cartpole_reinforce.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/3-reinforce/save_model/cartpole_reinforce.h5 -------------------------------------------------------------------------------- /2-cartpole/4-actor-critic/cartpole_a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/4-actor-critic/cartpole_a2c.py -------------------------------------------------------------------------------- /2-cartpole/4-actor-critic/save_graph/cartpole_a2c.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/4-actor-critic/save_graph/cartpole_a2c.png -------------------------------------------------------------------------------- /2-cartpole/4-actor-critic/save_model/cartpole_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/4-actor-critic/save_model/cartpole_actor.h5 -------------------------------------------------------------------------------- /2-cartpole/4-actor-critic/save_model/cartpole_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/4-actor-critic/save_model/cartpole_critic.h5 -------------------------------------------------------------------------------- /2-cartpole/5-a3c/cartpole_a3c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/5-a3c/cartpole_a3c.py -------------------------------------------------------------------------------- /2-cartpole/5-a3c/save_model/Cartpole_A3C_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/5-a3c/save_model/Cartpole_A3C_actor.h5 -------------------------------------------------------------------------------- /2-cartpole/5-a3c/save_model/Cartpole_A3C_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/5-a3c/save_model/Cartpole_A3C_critic.h5 -------------------------------------------------------------------------------- /2-cartpole/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/LICENSE -------------------------------------------------------------------------------- /2-cartpole/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/README.md -------------------------------------------------------------------------------- /2-cartpole/cartpole.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/2-cartpole/cartpole.png -------------------------------------------------------------------------------- /3-atari/1-breakout/breakout_a3c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/breakout_a3c.py -------------------------------------------------------------------------------- /3-atari/1-breakout/breakout_ddqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/breakout_ddqn.py -------------------------------------------------------------------------------- /3-atari/1-breakout/breakout_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/breakout_dqn.py -------------------------------------------------------------------------------- /3-atari/1-breakout/breakout_dueling_ddqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/breakout_dueling_ddqn.py -------------------------------------------------------------------------------- /3-atari/1-breakout/play_a3c_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/play_a3c_model.py -------------------------------------------------------------------------------- /3-atari/1-breakout/play_dqn_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/play_dqn_model.py -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_1_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_1_actor.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_1_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_1_critic.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_2_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_2_actor.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_2_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_2_critic.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_3_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_3_actor.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_3_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_3_critic.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_4_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_4_actor.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_4_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_4_critic.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_5_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_5_actor.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_a3c_5_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_a3c_5_critic.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_dqn.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_dqn.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_dqn_1.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_dqn_1.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_dqn_2.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_dqn_2.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_dqn_3.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_dqn_3.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_dqn_4.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_dqn_4.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/save_model/breakout_dqn_5.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/save_model/breakout_dqn_5.h5 -------------------------------------------------------------------------------- /3-atari/1-breakout/summary/breakout_a3c/events.out.tfevents.1497264638: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/summary/breakout_a3c/events.out.tfevents.1497264638 -------------------------------------------------------------------------------- /3-atari/1-breakout/summary/breakout_dqn/events.out.tfevents.1496968668.young-System-Product-Name: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/1-breakout/summary/breakout_dqn/events.out.tfevents.1496968668.young-System-Product-Name -------------------------------------------------------------------------------- /3-atari/2-pong/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/2-pong/README.md -------------------------------------------------------------------------------- /3-atari/2-pong/assets/pg.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/2-pong/assets/pg.gif -------------------------------------------------------------------------------- /3-atari/2-pong/assets/score.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/2-pong/assets/score.png -------------------------------------------------------------------------------- /3-atari/2-pong/pong_a3c.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /3-atari/2-pong/pong_reinforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/2-pong/pong_reinforce.py -------------------------------------------------------------------------------- /3-atari/2-pong/save_model/pong_reinforce.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/2-pong/save_model/pong_reinforce.h5 -------------------------------------------------------------------------------- /3-atari/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/3-atari/LICENSE -------------------------------------------------------------------------------- /4-gym/1-mountaincar/mountaincar_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/4-gym/1-mountaincar/mountaincar_dqn.py -------------------------------------------------------------------------------- /4-gym/1-mountaincar/save_model/MountainCar_DQN.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/4-gym/1-mountaincar/save_model/MountainCar_DQN.h5 -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/README.md -------------------------------------------------------------------------------- /images/Reinforcement-Learning.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/images/Reinforcement-Learning.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/requirements.txt -------------------------------------------------------------------------------- /wiki/how-to-windows.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/how-to-windows.md -------------------------------------------------------------------------------- /wiki/img/how-to-windows.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/img/how-to-windows.png -------------------------------------------------------------------------------- /wiki/img/link-env-with-pychar-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/img/link-env-with-pychar-1.png -------------------------------------------------------------------------------- /wiki/img/link-env-with-pychar-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/img/link-env-with-pychar-2.png -------------------------------------------------------------------------------- /wiki/img/link-env-with-pychar.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/img/link-env-with-pychar.png -------------------------------------------------------------------------------- /wiki/install_guide_osx+ubuntu.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/install_guide_osx+ubuntu.md -------------------------------------------------------------------------------- /wiki/rlcode_image/cartpole_exam.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/cartpole_exam.png -------------------------------------------------------------------------------- /wiki/rlcode_image/console_hello_world.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/console_hello_world.png -------------------------------------------------------------------------------- /wiki/rlcode_image/default_config.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/default_config.png -------------------------------------------------------------------------------- /wiki/rlcode_image/file_setting.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/file_setting.png -------------------------------------------------------------------------------- /wiki/rlcode_image/hello_world_ubuntu.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/hello_world_ubuntu.png -------------------------------------------------------------------------------- /wiki/rlcode_image/openai_github.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/openai_github.png -------------------------------------------------------------------------------- /wiki/rlcode_image/project_interpreter.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/project_interpreter.png -------------------------------------------------------------------------------- /wiki/rlcode_image/pycham_new_project.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/pycham_new_project.png -------------------------------------------------------------------------------- /wiki/rlcode_image/pycharm_community.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/pycharm_community.png -------------------------------------------------------------------------------- /wiki/rlcode_image/pycharm_drag.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/pycharm_drag.png -------------------------------------------------------------------------------- /wiki/rlcode_image/pycharm_init.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/pycharm_init.png -------------------------------------------------------------------------------- /wiki/rlcode_image/python3_terminal.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/python3_terminal.jpg -------------------------------------------------------------------------------- /wiki/rlcode_image/python_download.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/python_download.png -------------------------------------------------------------------------------- /wiki/rlcode_image/python_installed.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/python_installed.png -------------------------------------------------------------------------------- /wiki/rlcode_image/python_intalled.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/python_intalled.png -------------------------------------------------------------------------------- /wiki/rlcode_image/rl_book_hello_world.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/rl_book_hello_world.png -------------------------------------------------------------------------------- /wiki/rlcode_image/rl_book_project.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/rl_book_project.png -------------------------------------------------------------------------------- /wiki/rlcode_image/rl_book_venv.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/rl_book_venv.png -------------------------------------------------------------------------------- /wiki/rlcode_image/rl_book_virtualenv.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/rl_book_virtualenv.png -------------------------------------------------------------------------------- /wiki/rlcode_image/rlcode_book_directory.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/rlcode_book_directory.png -------------------------------------------------------------------------------- /wiki/rlcode_image/rlcode_project.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/rlcode_project.png -------------------------------------------------------------------------------- /wiki/rlcode_image/run_hello_world.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/run_hello_world.png -------------------------------------------------------------------------------- /wiki/rlcode_image/sh_pycharm.sh.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/sh_pycharm.sh.png -------------------------------------------------------------------------------- /wiki/rlcode_image/terminal_rlcode_book.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rlcode/reinforcement-learning/HEAD/wiki/rlcode_image/terminal_rlcode_book.png --------------------------------------------------------------------------------