├── .github └── workflows │ └── manual.yml ├── .gitignore ├── CODEOWNERS ├── LICENSE ├── README.md ├── cheatsheet ├── LICENSE.txt ├── README.md ├── cheatsheet.pdf ├── cheatsheet.tex └── udacity-logo.png ├── cross-entropy ├── CEM.ipynb ├── README.md └── checkpoint.pth ├── ddpg-bipedal ├── DDPG.ipynb ├── README.md ├── ddpg_agent.py └── model.py ├── ddpg-pendulum ├── DDPG.ipynb ├── README.md ├── checkpoint_actor.pth ├── checkpoint_critic.pth ├── ddpg_agent.py └── model.py ├── discretization ├── Discretization.ipynb ├── Discretization_Solution.ipynb └── README.md ├── dqn ├── README.md ├── exercise │ ├── Deep_Q_Network.ipynb │ ├── dqn_agent.py │ └── model.py └── solution │ ├── Deep_Q_Network_Solution.ipynb │ ├── checkpoint.pth │ ├── dqn_agent.py │ └── model.py ├── dynamic-programming ├── Dynamic_Programming.ipynb ├── Dynamic_Programming_Solution.ipynb ├── README.md ├── check_test.py ├── frozenlake.py └── plot_utils.py ├── finance ├── DRL.ipynb ├── ddpg_agent.py ├── model.py ├── syntheticChrissAlmgren.py ├── text_images │ ├── 4.jpeg │ ├── Actor-Critic.png │ ├── RL.png │ ├── nvidia.png │ └── udacity.png └── utils.py ├── hill-climbing ├── Hill_Climbing.ipynb └── README.md ├── lab-taxi ├── README.md ├── agent.py ├── main.py └── monitor.py ├── monte-carlo ├── Monte_Carlo.ipynb ├── Monte_Carlo_Solution.ipynb ├── README.md ├── images │ └── optimal.png └── plot_utils.py ├── p1_navigation ├── Navigation.ipynb ├── Navigation_Pixels.ipynb └── README.md ├── p2_continuous-control ├── Continuous_Control.ipynb ├── Crawler.ipynb └── README.md ├── p3_collab-compet ├── README.md ├── Soccer.ipynb └── Tennis.ipynb ├── python ├── Basics.ipynb ├── README.md ├── communicator_objects │ ├── __init__.py │ ├── agent_action_proto_pb2.py │ ├── agent_info_proto_pb2.py │ ├── brain_parameters_proto_pb2.py │ ├── brain_type_proto_pb2.py │ ├── command_proto_pb2.py │ ├── engine_configuration_proto_pb2.py │ ├── environment_parameters_proto_pb2.py │ ├── header_pb2.py │ ├── resolution_proto_pb2.py │ ├── space_type_proto_pb2.py │ ├── unity_input_pb2.py │ ├── unity_message_pb2.py │ ├── unity_output_pb2.py │ ├── unity_rl_initialization_input_pb2.py │ ├── unity_rl_initialization_output_pb2.py │ ├── unity_rl_input_pb2.py │ ├── unity_rl_output_pb2.py │ ├── unity_to_external_pb2.py │ └── unity_to_external_pb2_grpc.py ├── curricula │ ├── push.json │ ├── test.json │ └── wall.json ├── learn.py ├── requirements.txt ├── setup.py ├── tests │ ├── __init__.py │ ├── mock_communicator.py │ ├── test_bc.py │ ├── test_ppo.py │ ├── test_unityagents.py │ └── test_unitytrainers.py ├── trainer_config.yaml ├── unityagents │ ├── __init__.py │ ├── brain.py │ ├── communicator.py │ ├── curriculum.py │ ├── environment.py │ ├── exception.py │ ├── rpc_communicator.py │ └── socket_communicator.py └── unitytrainers │ ├── __init__.py │ ├── bc │ ├── __init__.py │ ├── models.py │ └── trainer.py │ ├── buffer.py │ ├── models.py │ ├── ppo │ ├── __init__.py │ ├── models.py │ └── trainer.py │ ├── trainer.py │ └── trainer_controller.py ├── reinforce ├── README.md └── REINFORCE.ipynb ├── temporal-difference ├── README.md ├── Temporal_Difference.ipynb ├── Temporal_Difference_Solution.ipynb ├── check_test.py └── plot_utils.py └── tile-coding ├── README.md ├── Tile_Coding.ipynb └── Tile_Coding_Solution.ipynb /.github/workflows/manual.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/.github/workflows/manual.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/.gitignore -------------------------------------------------------------------------------- /CODEOWNERS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/CODEOWNERS -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/README.md -------------------------------------------------------------------------------- /cheatsheet/LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/cheatsheet/LICENSE.txt -------------------------------------------------------------------------------- /cheatsheet/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/cheatsheet/README.md -------------------------------------------------------------------------------- /cheatsheet/cheatsheet.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/cheatsheet/cheatsheet.pdf -------------------------------------------------------------------------------- /cheatsheet/cheatsheet.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/cheatsheet/cheatsheet.tex -------------------------------------------------------------------------------- /cheatsheet/udacity-logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/cheatsheet/udacity-logo.png -------------------------------------------------------------------------------- /cross-entropy/CEM.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/cross-entropy/CEM.ipynb -------------------------------------------------------------------------------- /cross-entropy/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/cross-entropy/README.md -------------------------------------------------------------------------------- /cross-entropy/checkpoint.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/cross-entropy/checkpoint.pth -------------------------------------------------------------------------------- /ddpg-bipedal/DDPG.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-bipedal/DDPG.ipynb -------------------------------------------------------------------------------- /ddpg-bipedal/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-bipedal/README.md -------------------------------------------------------------------------------- /ddpg-bipedal/ddpg_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-bipedal/ddpg_agent.py -------------------------------------------------------------------------------- /ddpg-bipedal/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-bipedal/model.py -------------------------------------------------------------------------------- /ddpg-pendulum/DDPG.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-pendulum/DDPG.ipynb -------------------------------------------------------------------------------- /ddpg-pendulum/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-pendulum/README.md -------------------------------------------------------------------------------- /ddpg-pendulum/checkpoint_actor.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-pendulum/checkpoint_actor.pth -------------------------------------------------------------------------------- /ddpg-pendulum/checkpoint_critic.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-pendulum/checkpoint_critic.pth -------------------------------------------------------------------------------- /ddpg-pendulum/ddpg_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-pendulum/ddpg_agent.py -------------------------------------------------------------------------------- /ddpg-pendulum/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/ddpg-pendulum/model.py -------------------------------------------------------------------------------- /discretization/Discretization.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/discretization/Discretization.ipynb -------------------------------------------------------------------------------- /discretization/Discretization_Solution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/discretization/Discretization_Solution.ipynb -------------------------------------------------------------------------------- /discretization/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/discretization/README.md -------------------------------------------------------------------------------- /dqn/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dqn/README.md -------------------------------------------------------------------------------- /dqn/exercise/Deep_Q_Network.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dqn/exercise/Deep_Q_Network.ipynb -------------------------------------------------------------------------------- /dqn/exercise/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dqn/exercise/dqn_agent.py -------------------------------------------------------------------------------- /dqn/exercise/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dqn/exercise/model.py -------------------------------------------------------------------------------- /dqn/solution/Deep_Q_Network_Solution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dqn/solution/Deep_Q_Network_Solution.ipynb -------------------------------------------------------------------------------- /dqn/solution/checkpoint.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dqn/solution/checkpoint.pth -------------------------------------------------------------------------------- /dqn/solution/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dqn/solution/dqn_agent.py -------------------------------------------------------------------------------- /dqn/solution/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dqn/solution/model.py -------------------------------------------------------------------------------- /dynamic-programming/Dynamic_Programming.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dynamic-programming/Dynamic_Programming.ipynb -------------------------------------------------------------------------------- /dynamic-programming/Dynamic_Programming_Solution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dynamic-programming/Dynamic_Programming_Solution.ipynb -------------------------------------------------------------------------------- /dynamic-programming/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dynamic-programming/README.md -------------------------------------------------------------------------------- /dynamic-programming/check_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dynamic-programming/check_test.py -------------------------------------------------------------------------------- /dynamic-programming/frozenlake.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dynamic-programming/frozenlake.py -------------------------------------------------------------------------------- /dynamic-programming/plot_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/dynamic-programming/plot_utils.py -------------------------------------------------------------------------------- /finance/DRL.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/DRL.ipynb -------------------------------------------------------------------------------- /finance/ddpg_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/ddpg_agent.py -------------------------------------------------------------------------------- /finance/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/model.py -------------------------------------------------------------------------------- /finance/syntheticChrissAlmgren.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/syntheticChrissAlmgren.py -------------------------------------------------------------------------------- /finance/text_images/4.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/text_images/4.jpeg -------------------------------------------------------------------------------- /finance/text_images/Actor-Critic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/text_images/Actor-Critic.png -------------------------------------------------------------------------------- /finance/text_images/RL.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/text_images/RL.png -------------------------------------------------------------------------------- /finance/text_images/nvidia.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/text_images/nvidia.png -------------------------------------------------------------------------------- /finance/text_images/udacity.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/text_images/udacity.png -------------------------------------------------------------------------------- /finance/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/finance/utils.py -------------------------------------------------------------------------------- /hill-climbing/Hill_Climbing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/hill-climbing/Hill_Climbing.ipynb -------------------------------------------------------------------------------- /hill-climbing/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/hill-climbing/README.md -------------------------------------------------------------------------------- /lab-taxi/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/lab-taxi/README.md -------------------------------------------------------------------------------- /lab-taxi/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/lab-taxi/agent.py -------------------------------------------------------------------------------- /lab-taxi/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/lab-taxi/main.py -------------------------------------------------------------------------------- /lab-taxi/monitor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/lab-taxi/monitor.py -------------------------------------------------------------------------------- /monte-carlo/Monte_Carlo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/monte-carlo/Monte_Carlo.ipynb -------------------------------------------------------------------------------- /monte-carlo/Monte_Carlo_Solution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/monte-carlo/Monte_Carlo_Solution.ipynb -------------------------------------------------------------------------------- /monte-carlo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/monte-carlo/README.md -------------------------------------------------------------------------------- /monte-carlo/images/optimal.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/monte-carlo/images/optimal.png -------------------------------------------------------------------------------- /monte-carlo/plot_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/monte-carlo/plot_utils.py -------------------------------------------------------------------------------- /p1_navigation/Navigation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/p1_navigation/Navigation.ipynb -------------------------------------------------------------------------------- /p1_navigation/Navigation_Pixels.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/p1_navigation/Navigation_Pixels.ipynb -------------------------------------------------------------------------------- /p1_navigation/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/p1_navigation/README.md -------------------------------------------------------------------------------- /p2_continuous-control/Continuous_Control.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/p2_continuous-control/Continuous_Control.ipynb -------------------------------------------------------------------------------- /p2_continuous-control/Crawler.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/p2_continuous-control/Crawler.ipynb -------------------------------------------------------------------------------- /p2_continuous-control/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/p2_continuous-control/README.md -------------------------------------------------------------------------------- /p3_collab-compet/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/p3_collab-compet/README.md -------------------------------------------------------------------------------- /p3_collab-compet/Soccer.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/p3_collab-compet/Soccer.ipynb -------------------------------------------------------------------------------- /p3_collab-compet/Tennis.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/p3_collab-compet/Tennis.ipynb -------------------------------------------------------------------------------- /python/Basics.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/Basics.ipynb -------------------------------------------------------------------------------- /python/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/README.md -------------------------------------------------------------------------------- /python/communicator_objects/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/__init__.py -------------------------------------------------------------------------------- /python/communicator_objects/agent_action_proto_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/agent_action_proto_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/agent_info_proto_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/agent_info_proto_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/brain_parameters_proto_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/brain_parameters_proto_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/brain_type_proto_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/brain_type_proto_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/command_proto_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/command_proto_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/engine_configuration_proto_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/engine_configuration_proto_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/environment_parameters_proto_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/environment_parameters_proto_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/header_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/header_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/resolution_proto_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/resolution_proto_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/space_type_proto_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/space_type_proto_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/unity_input_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/unity_input_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/unity_message_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/unity_message_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/unity_output_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/unity_output_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/unity_rl_initialization_input_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/unity_rl_initialization_input_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/unity_rl_initialization_output_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/unity_rl_initialization_output_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/unity_rl_input_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/unity_rl_input_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/unity_rl_output_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/unity_rl_output_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/unity_to_external_pb2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/unity_to_external_pb2.py -------------------------------------------------------------------------------- /python/communicator_objects/unity_to_external_pb2_grpc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/communicator_objects/unity_to_external_pb2_grpc.py -------------------------------------------------------------------------------- /python/curricula/push.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/curricula/push.json -------------------------------------------------------------------------------- /python/curricula/test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/curricula/test.json -------------------------------------------------------------------------------- /python/curricula/wall.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/curricula/wall.json -------------------------------------------------------------------------------- /python/learn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/learn.py -------------------------------------------------------------------------------- /python/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/requirements.txt -------------------------------------------------------------------------------- /python/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/setup.py -------------------------------------------------------------------------------- /python/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/tests/__init__.py -------------------------------------------------------------------------------- /python/tests/mock_communicator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/tests/mock_communicator.py -------------------------------------------------------------------------------- /python/tests/test_bc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/tests/test_bc.py -------------------------------------------------------------------------------- /python/tests/test_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/tests/test_ppo.py -------------------------------------------------------------------------------- /python/tests/test_unityagents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/tests/test_unityagents.py -------------------------------------------------------------------------------- /python/tests/test_unitytrainers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/tests/test_unitytrainers.py -------------------------------------------------------------------------------- /python/trainer_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/trainer_config.yaml -------------------------------------------------------------------------------- /python/unityagents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unityagents/__init__.py -------------------------------------------------------------------------------- /python/unityagents/brain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unityagents/brain.py -------------------------------------------------------------------------------- /python/unityagents/communicator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unityagents/communicator.py -------------------------------------------------------------------------------- /python/unityagents/curriculum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unityagents/curriculum.py -------------------------------------------------------------------------------- /python/unityagents/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unityagents/environment.py -------------------------------------------------------------------------------- /python/unityagents/exception.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unityagents/exception.py -------------------------------------------------------------------------------- /python/unityagents/rpc_communicator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unityagents/rpc_communicator.py -------------------------------------------------------------------------------- /python/unityagents/socket_communicator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unityagents/socket_communicator.py -------------------------------------------------------------------------------- /python/unitytrainers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/__init__.py -------------------------------------------------------------------------------- /python/unitytrainers/bc/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/bc/__init__.py -------------------------------------------------------------------------------- /python/unitytrainers/bc/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/bc/models.py -------------------------------------------------------------------------------- /python/unitytrainers/bc/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/bc/trainer.py -------------------------------------------------------------------------------- /python/unitytrainers/buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/buffer.py -------------------------------------------------------------------------------- /python/unitytrainers/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/models.py -------------------------------------------------------------------------------- /python/unitytrainers/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/ppo/__init__.py -------------------------------------------------------------------------------- /python/unitytrainers/ppo/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/ppo/models.py -------------------------------------------------------------------------------- /python/unitytrainers/ppo/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/ppo/trainer.py -------------------------------------------------------------------------------- /python/unitytrainers/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/trainer.py -------------------------------------------------------------------------------- /python/unitytrainers/trainer_controller.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/python/unitytrainers/trainer_controller.py -------------------------------------------------------------------------------- /reinforce/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/reinforce/README.md -------------------------------------------------------------------------------- /reinforce/REINFORCE.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/reinforce/REINFORCE.ipynb -------------------------------------------------------------------------------- /temporal-difference/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/temporal-difference/README.md -------------------------------------------------------------------------------- /temporal-difference/Temporal_Difference.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/temporal-difference/Temporal_Difference.ipynb -------------------------------------------------------------------------------- /temporal-difference/Temporal_Difference_Solution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/temporal-difference/Temporal_Difference_Solution.ipynb -------------------------------------------------------------------------------- /temporal-difference/check_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/temporal-difference/check_test.py -------------------------------------------------------------------------------- /temporal-difference/plot_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/temporal-difference/plot_utils.py -------------------------------------------------------------------------------- /tile-coding/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/tile-coding/README.md -------------------------------------------------------------------------------- /tile-coding/Tile_Coding.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/tile-coding/Tile_Coding.ipynb -------------------------------------------------------------------------------- /tile-coding/Tile_Coding_Solution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/udacity/deep-reinforcement-learning/HEAD/tile-coding/Tile_Coding_Solution.ipynb --------------------------------------------------------------------------------