├── .gitignore ├── 01_0_play_frozenlake_det.py ├── 01_1_play_frozenlake_det.py ├── 02_random_frozenkake_det.py ├── 03_0_q_table_frozenlake_det.py ├── 03_1_q_table_frozenlake_det.py ├── 03_2_q_table_frozenlake_det.py ├── 04_play_frozenlake.py ├── 05_0_q_table_frozenlake.py ├── 05_q_table_frozenlake.py ├── 06_q_net_frozenlake.py ├── 07_0_random_cartpole.py ├── 07_1_q_net_cartpole.py ├── 07_2_dqn_2013_cartpole.py ├── 07_3_dqn_2015_cartpole.py ├── 08_1_pg_cartpole.py ├── 08_2_softmax_pg_cartpole.py ├── 08_3_softmax_pg_pacman.py ├── 08_4_softmax_pg_pong.py ├── 08_4_softmax_pg_pong_y.py ├── 09_2_cross_entropy.py ├── 10_1_Actor_Critic.ipynb ├── 10_2_A3C_threads.py ├── README.md ├── assets ├── actor_critic.png └── openai_user.jpg ├── dqn.py ├── gym.ini ├── gym_uploader.py ├── mini_pacman.py ├── requirements.txt ├── tests ├── __init__.py └── test_DQN.py └── utils ├── __init__.py └── prints.py /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | __pycache__ 3 | gym-results/ 4 | pacman_log 5 | -------------------------------------------------------------------------------- /01_0_play_frozenlake_det.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/01_0_play_frozenlake_det.py -------------------------------------------------------------------------------- /01_1_play_frozenlake_det.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/01_1_play_frozenlake_det.py -------------------------------------------------------------------------------- /02_random_frozenkake_det.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/02_random_frozenkake_det.py -------------------------------------------------------------------------------- /03_0_q_table_frozenlake_det.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/03_0_q_table_frozenlake_det.py -------------------------------------------------------------------------------- /03_1_q_table_frozenlake_det.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/03_1_q_table_frozenlake_det.py -------------------------------------------------------------------------------- /03_2_q_table_frozenlake_det.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/03_2_q_table_frozenlake_det.py -------------------------------------------------------------------------------- /04_play_frozenlake.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/04_play_frozenlake.py -------------------------------------------------------------------------------- /05_0_q_table_frozenlake.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/05_0_q_table_frozenlake.py -------------------------------------------------------------------------------- /05_q_table_frozenlake.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/05_q_table_frozenlake.py -------------------------------------------------------------------------------- /06_q_net_frozenlake.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/06_q_net_frozenlake.py -------------------------------------------------------------------------------- /07_0_random_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/07_0_random_cartpole.py -------------------------------------------------------------------------------- /07_1_q_net_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/07_1_q_net_cartpole.py -------------------------------------------------------------------------------- /07_2_dqn_2013_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/07_2_dqn_2013_cartpole.py -------------------------------------------------------------------------------- /07_3_dqn_2015_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/07_3_dqn_2015_cartpole.py -------------------------------------------------------------------------------- /08_1_pg_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/08_1_pg_cartpole.py -------------------------------------------------------------------------------- /08_2_softmax_pg_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/08_2_softmax_pg_cartpole.py -------------------------------------------------------------------------------- /08_3_softmax_pg_pacman.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/08_3_softmax_pg_pacman.py -------------------------------------------------------------------------------- /08_4_softmax_pg_pong.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/08_4_softmax_pg_pong.py -------------------------------------------------------------------------------- /08_4_softmax_pg_pong_y.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/08_4_softmax_pg_pong_y.py -------------------------------------------------------------------------------- /09_2_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/09_2_cross_entropy.py -------------------------------------------------------------------------------- /10_1_Actor_Critic.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/10_1_Actor_Critic.ipynb -------------------------------------------------------------------------------- /10_2_A3C_threads.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/10_2_A3C_threads.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/README.md -------------------------------------------------------------------------------- /assets/actor_critic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/assets/actor_critic.png -------------------------------------------------------------------------------- /assets/openai_user.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/assets/openai_user.jpg -------------------------------------------------------------------------------- /dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/dqn.py -------------------------------------------------------------------------------- /gym.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/gym.ini -------------------------------------------------------------------------------- /gym_uploader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/gym_uploader.py -------------------------------------------------------------------------------- /mini_pacman.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/mini_pacman.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/requirements.txt -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/test_DQN.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/tests/test_DQN.py -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /utils/prints.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hunkim/ReinforcementZeroToAll/HEAD/utils/prints.py --------------------------------------------------------------------------------