├── .idea ├── .gitignore ├── Reinforcement-Learning-Book.iml ├── inspectionProfiles │ └── profiles_settings.xml ├── misc.xml ├── modules.xml └── vcs.xml ├── Chap4 ├── a2c_actor.py ├── a2c_agent.py ├── a2c_critic.py ├── a2c_load_play.py ├── a2c_main.py └── save_weights │ ├── pendulum_actor.h5 │ └── pendulum_critic.h5 ├── Chap5 ├── A3CData │ ├── a3c_actor.py │ ├── a3c_agent.py │ ├── a3c_critic.py │ ├── a3c_load_play.py │ ├── a3c_main.py │ └── save_weights │ │ ├── pendulum_actor.h5 │ │ ├── pendulum_critic.h5 │ │ └── pendulum_epi_reward.txt └── A3CGradient │ ├── a3c_actor.py │ ├── a3c_agent.py │ ├── a3c_critic.py │ ├── a3c_load_play.py │ ├── a3c_main.py │ └── save_weights │ ├── pendulum_actor.h5 │ └── pendulum_critic.h5 ├── Chap6 ├── ppo_actor.py ├── ppo_agent.py ├── ppo_critic.py ├── ppo_load_play.py ├── ppo_main.py └── save_weights │ ├── pendulum_actor.h5 │ └── pendulum_critic.h5 ├── Chap7 ├── ddpg_actor.py ├── ddpg_agent.py ├── ddpg_critic.py ├── ddpg_load_play.py ├── ddpg_main.py ├── replaybuffer.py └── save_weights │ ├── pendulum_actor.h5 │ └── pendulum_critic.h5 └── README.md /.idea/.gitignore: -------------------------------------------------------------------------------- 1 | # Default ignored files 2 | /workspace.xml 3 | -------------------------------------------------------------------------------- /.idea/Reinforcement-Learning-Book.iml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/.idea/Reinforcement-Learning-Book.iml -------------------------------------------------------------------------------- /.idea/inspectionProfiles/profiles_settings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/.idea/inspectionProfiles/profiles_settings.xml -------------------------------------------------------------------------------- /.idea/misc.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/.idea/misc.xml -------------------------------------------------------------------------------- /.idea/modules.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/.idea/modules.xml -------------------------------------------------------------------------------- /.idea/vcs.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/.idea/vcs.xml -------------------------------------------------------------------------------- /Chap4/a2c_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap4/a2c_actor.py -------------------------------------------------------------------------------- /Chap4/a2c_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap4/a2c_agent.py -------------------------------------------------------------------------------- /Chap4/a2c_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap4/a2c_critic.py -------------------------------------------------------------------------------- /Chap4/a2c_load_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap4/a2c_load_play.py -------------------------------------------------------------------------------- /Chap4/a2c_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap4/a2c_main.py -------------------------------------------------------------------------------- /Chap4/save_weights/pendulum_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap4/save_weights/pendulum_actor.h5 -------------------------------------------------------------------------------- /Chap4/save_weights/pendulum_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap4/save_weights/pendulum_critic.h5 -------------------------------------------------------------------------------- /Chap5/A3CData/a3c_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CData/a3c_actor.py -------------------------------------------------------------------------------- /Chap5/A3CData/a3c_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CData/a3c_agent.py -------------------------------------------------------------------------------- /Chap5/A3CData/a3c_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CData/a3c_critic.py -------------------------------------------------------------------------------- /Chap5/A3CData/a3c_load_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CData/a3c_load_play.py -------------------------------------------------------------------------------- /Chap5/A3CData/a3c_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CData/a3c_main.py -------------------------------------------------------------------------------- /Chap5/A3CData/save_weights/pendulum_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CData/save_weights/pendulum_actor.h5 -------------------------------------------------------------------------------- /Chap5/A3CData/save_weights/pendulum_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CData/save_weights/pendulum_critic.h5 -------------------------------------------------------------------------------- /Chap5/A3CData/save_weights/pendulum_epi_reward.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /Chap5/A3CGradient/a3c_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CGradient/a3c_actor.py -------------------------------------------------------------------------------- /Chap5/A3CGradient/a3c_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CGradient/a3c_agent.py -------------------------------------------------------------------------------- /Chap5/A3CGradient/a3c_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CGradient/a3c_critic.py -------------------------------------------------------------------------------- /Chap5/A3CGradient/a3c_load_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CGradient/a3c_load_play.py -------------------------------------------------------------------------------- /Chap5/A3CGradient/a3c_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CGradient/a3c_main.py -------------------------------------------------------------------------------- /Chap5/A3CGradient/save_weights/pendulum_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CGradient/save_weights/pendulum_actor.h5 -------------------------------------------------------------------------------- /Chap5/A3CGradient/save_weights/pendulum_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap5/A3CGradient/save_weights/pendulum_critic.h5 -------------------------------------------------------------------------------- /Chap6/ppo_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap6/ppo_actor.py -------------------------------------------------------------------------------- /Chap6/ppo_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap6/ppo_agent.py -------------------------------------------------------------------------------- /Chap6/ppo_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap6/ppo_critic.py -------------------------------------------------------------------------------- /Chap6/ppo_load_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap6/ppo_load_play.py -------------------------------------------------------------------------------- /Chap6/ppo_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap6/ppo_main.py -------------------------------------------------------------------------------- /Chap6/save_weights/pendulum_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap6/save_weights/pendulum_actor.h5 -------------------------------------------------------------------------------- /Chap6/save_weights/pendulum_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap6/save_weights/pendulum_critic.h5 -------------------------------------------------------------------------------- /Chap7/ddpg_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap7/ddpg_actor.py -------------------------------------------------------------------------------- /Chap7/ddpg_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap7/ddpg_agent.py -------------------------------------------------------------------------------- /Chap7/ddpg_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap7/ddpg_critic.py -------------------------------------------------------------------------------- /Chap7/ddpg_load_play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap7/ddpg_load_play.py -------------------------------------------------------------------------------- /Chap7/ddpg_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap7/ddpg_main.py -------------------------------------------------------------------------------- /Chap7/replaybuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap7/replaybuffer.py -------------------------------------------------------------------------------- /Chap7/save_weights/pendulum_actor.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap7/save_weights/pendulum_actor.h5 -------------------------------------------------------------------------------- /Chap7/save_weights/pendulum_critic.h5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/Chap7/save_weights/pendulum_critic.h5 -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Yeachan-Heo/Reinforcement-Learning-Book/HEAD/README.md --------------------------------------------------------------------------------