├── .gitignore ├── LICENSE ├── Plotting_tools_tutorial └── Wandb_simple_tutorial.ipynb ├── Policy_Based ├── Actor_Critic │ ├── 4. DiscreteActorCritic.ipynb │ ├── 5. ContinuousActorCritic.ipynb │ ├── Network.py │ └── train.py ├── DDPG │ └── Untitled.ipynb ├── REINFORCE │ ├── 1. DiscreteREINFORCE.ipynb │ ├── 2. ContinuousREINFORCE.ipynb │ ├── 3. DiscreteREINFORCEwithBaseline.ipynb │ ├── network.py │ └── train.py └── SAC_not_complete │ └── replay_buffer.py ├── README.md ├── Ray_tutorial ├── 1. Ray_Simple_Turorial.ipynb ├── 2. Simple_ReplayBuffer_Tutorial.ipynb ├── 3. Simple_ParameterServer_Tutorial.ipynb ├── 4. Visualization_with_Ray.ipynb ├── 5-1 Algorithm_validation_test_without_ray.ipynb ├── 5. Distributed_DQN_with_restricted_update_steps.ipynb ├── 6. Distributed_DQN_actors_on_CPUs.ipynb ├── 6. Distributed_DQN_actors_on_GPUs.ipynb └── Vanila_Distributed_DQN │ ├── (not yet) Atari_Disributed_DQN.ipynb │ ├── agent.py │ ├── qnetwork.py │ ├── replay_buffer.py │ └── train.py └── Value_Based ├── C51 ├── C51_1dim │ ├── agent.py │ ├── qnetwork.py │ ├── replay_buffer.py │ └── train.py ├── Distributional_DQN(C51)_1dim input (simple atari game).ipynb ├── Distributional_DQN(C51)_2dim input.ipynb ├── agent.py ├── qnetwork.py ├── replay_buffer.py └── train.py ├── DoubleDQN ├── Double_DQN_1dim.ipynb ├── Double_DQN_2dim.ipynb ├── agent.py ├── qnetwork.py ├── replay_buffer.py └── train.py ├── Double_Duel_Noisy_C51 ├── agent.py ├── qnetwork.py ├── replay_buffer.py └── train.py ├── Double_Duel_Noisy_C51_MultiTD ├── agent.py ├── qnetwork.py ├── replay_buffer.py └── train.py ├── Double_Duel_Noisy_C51_MultiTD_1dim ├── agent.py ├── qnetwork.py ├── replay_buffer.py └── train.py ├── DuelingDQN ├── Dueling_DQN_1dim.ipynb ├── Dueling_DQN_2dim.ipynb ├── agent.py ├── qnetwork.py ├── replay_buffer.py └── train.py ├── Multi_step_TD ├── agent.py ├── qnetwork.py ├── replay_buffer.py └── train.py ├── NoisyNet ├── NoisyNet_1dim.ipynb ├── NoisyNet_2dim.ipynb ├── agent.py ├── agent_utils.py ├── qnetwork.py ├── replay_buffer.py └── train.py ├── PER ├── 1_dim_state │ ├── agent.py │ ├── qnetwork.py │ ├── replay_buffer.py │ ├── segment_tree.py │ └── train.py ├── agent.py ├── qnetwork.py ├── replay_buffer.py ├── segment_tree.py └── train.py ├── PER_and_Noisy ├── agent.py ├── qnetwork.py ├── replay_buffer.py ├── segment_tree.py └── train.py ├── Rainbow ├── agent.py ├── qnetwork.py ├── replay_buffer.py ├── segment_tree.py └── train.py ├── Rainbow_1dim ├── agent.py ├── qnetwork.py ├── replay_buffer.py ├── segment_tree.py └── train.py └── Vanila_DQN ├── Prioritized_Experience_Replay_DQN_1dim_input_(simple atari game).ipynb ├── Vanila_DQN_1dim input (simple atari game).ipynb ├── Vanila_DQN_2dim input (same as DQN paper).ipynb ├── agent.py ├── qnetwork.py ├── replay_buffer.py └── train.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/LICENSE -------------------------------------------------------------------------------- /Plotting_tools_tutorial/Wandb_simple_tutorial.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Plotting_tools_tutorial/Wandb_simple_tutorial.ipynb -------------------------------------------------------------------------------- /Policy_Based/Actor_Critic/4. DiscreteActorCritic.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/Actor_Critic/4. DiscreteActorCritic.ipynb -------------------------------------------------------------------------------- /Policy_Based/Actor_Critic/5. ContinuousActorCritic.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/Actor_Critic/5. ContinuousActorCritic.ipynb -------------------------------------------------------------------------------- /Policy_Based/Actor_Critic/Network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/Actor_Critic/Network.py -------------------------------------------------------------------------------- /Policy_Based/Actor_Critic/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/Actor_Critic/train.py -------------------------------------------------------------------------------- /Policy_Based/DDPG/Untitled.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/DDPG/Untitled.ipynb -------------------------------------------------------------------------------- /Policy_Based/REINFORCE/1. DiscreteREINFORCE.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/REINFORCE/1. DiscreteREINFORCE.ipynb -------------------------------------------------------------------------------- /Policy_Based/REINFORCE/2. ContinuousREINFORCE.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/REINFORCE/2. ContinuousREINFORCE.ipynb -------------------------------------------------------------------------------- /Policy_Based/REINFORCE/3. DiscreteREINFORCEwithBaseline.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/REINFORCE/3. DiscreteREINFORCEwithBaseline.ipynb -------------------------------------------------------------------------------- /Policy_Based/REINFORCE/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/REINFORCE/network.py -------------------------------------------------------------------------------- /Policy_Based/REINFORCE/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/REINFORCE/train.py -------------------------------------------------------------------------------- /Policy_Based/SAC_not_complete/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Policy_Based/SAC_not_complete/replay_buffer.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/README.md -------------------------------------------------------------------------------- /Ray_tutorial/1. Ray_Simple_Turorial.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/1. Ray_Simple_Turorial.ipynb -------------------------------------------------------------------------------- /Ray_tutorial/2. Simple_ReplayBuffer_Tutorial.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/2. Simple_ReplayBuffer_Tutorial.ipynb -------------------------------------------------------------------------------- /Ray_tutorial/3. Simple_ParameterServer_Tutorial.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/3. Simple_ParameterServer_Tutorial.ipynb -------------------------------------------------------------------------------- /Ray_tutorial/4. Visualization_with_Ray.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/4. Visualization_with_Ray.ipynb -------------------------------------------------------------------------------- /Ray_tutorial/5-1 Algorithm_validation_test_without_ray.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/5-1 Algorithm_validation_test_without_ray.ipynb -------------------------------------------------------------------------------- /Ray_tutorial/5. Distributed_DQN_with_restricted_update_steps.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/5. Distributed_DQN_with_restricted_update_steps.ipynb -------------------------------------------------------------------------------- /Ray_tutorial/6. Distributed_DQN_actors_on_CPUs.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/6. Distributed_DQN_actors_on_CPUs.ipynb -------------------------------------------------------------------------------- /Ray_tutorial/6. Distributed_DQN_actors_on_GPUs.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/6. Distributed_DQN_actors_on_GPUs.ipynb -------------------------------------------------------------------------------- /Ray_tutorial/Vanila_Distributed_DQN/(not yet) Atari_Disributed_DQN.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/Vanila_Distributed_DQN/(not yet) Atari_Disributed_DQN.ipynb -------------------------------------------------------------------------------- /Ray_tutorial/Vanila_Distributed_DQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/Vanila_Distributed_DQN/agent.py -------------------------------------------------------------------------------- /Ray_tutorial/Vanila_Distributed_DQN/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/Vanila_Distributed_DQN/qnetwork.py -------------------------------------------------------------------------------- /Ray_tutorial/Vanila_Distributed_DQN/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/Vanila_Distributed_DQN/replay_buffer.py -------------------------------------------------------------------------------- /Ray_tutorial/Vanila_Distributed_DQN/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Ray_tutorial/Vanila_Distributed_DQN/train.py -------------------------------------------------------------------------------- /Value_Based/C51/C51_1dim/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/C51_1dim/agent.py -------------------------------------------------------------------------------- /Value_Based/C51/C51_1dim/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/C51_1dim/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/C51/C51_1dim/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/C51_1dim/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/C51/C51_1dim/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/C51_1dim/train.py -------------------------------------------------------------------------------- /Value_Based/C51/Distributional_DQN(C51)_1dim input (simple atari game).ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/Distributional_DQN(C51)_1dim input (simple atari game).ipynb -------------------------------------------------------------------------------- /Value_Based/C51/Distributional_DQN(C51)_2dim input.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/Distributional_DQN(C51)_2dim input.ipynb -------------------------------------------------------------------------------- /Value_Based/C51/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/agent.py -------------------------------------------------------------------------------- /Value_Based/C51/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/C51/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/C51/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/C51/train.py -------------------------------------------------------------------------------- /Value_Based/DoubleDQN/Double_DQN_1dim.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DoubleDQN/Double_DQN_1dim.ipynb -------------------------------------------------------------------------------- /Value_Based/DoubleDQN/Double_DQN_2dim.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DoubleDQN/Double_DQN_2dim.ipynb -------------------------------------------------------------------------------- /Value_Based/DoubleDQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DoubleDQN/agent.py -------------------------------------------------------------------------------- /Value_Based/DoubleDQN/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DoubleDQN/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/DoubleDQN/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DoubleDQN/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/DoubleDQN/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DoubleDQN/train.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51/agent.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51/train.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51_MultiTD/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51_MultiTD/agent.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51_MultiTD/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51_MultiTD/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51_MultiTD/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51_MultiTD/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51_MultiTD/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51_MultiTD/train.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51_MultiTD_1dim/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51_MultiTD_1dim/agent.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51_MultiTD_1dim/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51_MultiTD_1dim/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51_MultiTD_1dim/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51_MultiTD_1dim/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/Double_Duel_Noisy_C51_MultiTD_1dim/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Double_Duel_Noisy_C51_MultiTD_1dim/train.py -------------------------------------------------------------------------------- /Value_Based/DuelingDQN/Dueling_DQN_1dim.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DuelingDQN/Dueling_DQN_1dim.ipynb -------------------------------------------------------------------------------- /Value_Based/DuelingDQN/Dueling_DQN_2dim.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DuelingDQN/Dueling_DQN_2dim.ipynb -------------------------------------------------------------------------------- /Value_Based/DuelingDQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DuelingDQN/agent.py -------------------------------------------------------------------------------- /Value_Based/DuelingDQN/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DuelingDQN/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/DuelingDQN/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DuelingDQN/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/DuelingDQN/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/DuelingDQN/train.py -------------------------------------------------------------------------------- /Value_Based/Multi_step_TD/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Multi_step_TD/agent.py -------------------------------------------------------------------------------- /Value_Based/Multi_step_TD/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Multi_step_TD/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/Multi_step_TD/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Multi_step_TD/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/Multi_step_TD/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Multi_step_TD/train.py -------------------------------------------------------------------------------- /Value_Based/NoisyNet/NoisyNet_1dim.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/NoisyNet/NoisyNet_1dim.ipynb -------------------------------------------------------------------------------- /Value_Based/NoisyNet/NoisyNet_2dim.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/NoisyNet/NoisyNet_2dim.ipynb -------------------------------------------------------------------------------- /Value_Based/NoisyNet/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/NoisyNet/agent.py -------------------------------------------------------------------------------- /Value_Based/NoisyNet/agent_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/NoisyNet/agent_utils.py -------------------------------------------------------------------------------- /Value_Based/NoisyNet/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/NoisyNet/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/NoisyNet/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/NoisyNet/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/NoisyNet/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/NoisyNet/train.py -------------------------------------------------------------------------------- /Value_Based/PER/1_dim_state/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/1_dim_state/agent.py -------------------------------------------------------------------------------- /Value_Based/PER/1_dim_state/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/1_dim_state/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/PER/1_dim_state/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/1_dim_state/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/PER/1_dim_state/segment_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/1_dim_state/segment_tree.py -------------------------------------------------------------------------------- /Value_Based/PER/1_dim_state/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/1_dim_state/train.py -------------------------------------------------------------------------------- /Value_Based/PER/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/agent.py -------------------------------------------------------------------------------- /Value_Based/PER/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/PER/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/PER/segment_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/segment_tree.py -------------------------------------------------------------------------------- /Value_Based/PER/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER/train.py -------------------------------------------------------------------------------- /Value_Based/PER_and_Noisy/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER_and_Noisy/agent.py -------------------------------------------------------------------------------- /Value_Based/PER_and_Noisy/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER_and_Noisy/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/PER_and_Noisy/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER_and_Noisy/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/PER_and_Noisy/segment_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER_and_Noisy/segment_tree.py -------------------------------------------------------------------------------- /Value_Based/PER_and_Noisy/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/PER_and_Noisy/train.py -------------------------------------------------------------------------------- /Value_Based/Rainbow/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow/agent.py -------------------------------------------------------------------------------- /Value_Based/Rainbow/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/Rainbow/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/Rainbow/segment_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow/segment_tree.py -------------------------------------------------------------------------------- /Value_Based/Rainbow/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow/train.py -------------------------------------------------------------------------------- /Value_Based/Rainbow_1dim/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow_1dim/agent.py -------------------------------------------------------------------------------- /Value_Based/Rainbow_1dim/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow_1dim/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/Rainbow_1dim/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow_1dim/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/Rainbow_1dim/segment_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow_1dim/segment_tree.py -------------------------------------------------------------------------------- /Value_Based/Rainbow_1dim/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Rainbow_1dim/train.py -------------------------------------------------------------------------------- /Value_Based/Vanila_DQN/Prioritized_Experience_Replay_DQN_1dim_input_(simple atari game).ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Vanila_DQN/Prioritized_Experience_Replay_DQN_1dim_input_(simple atari game).ipynb -------------------------------------------------------------------------------- /Value_Based/Vanila_DQN/Vanila_DQN_1dim input (simple atari game).ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Vanila_DQN/Vanila_DQN_1dim input (simple atari game).ipynb -------------------------------------------------------------------------------- /Value_Based/Vanila_DQN/Vanila_DQN_2dim input (same as DQN paper).ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Vanila_DQN/Vanila_DQN_2dim input (same as DQN paper).ipynb -------------------------------------------------------------------------------- /Value_Based/Vanila_DQN/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Vanila_DQN/agent.py -------------------------------------------------------------------------------- /Value_Based/Vanila_DQN/qnetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Vanila_DQN/qnetwork.py -------------------------------------------------------------------------------- /Value_Based/Vanila_DQN/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Vanila_DQN/replay_buffer.py -------------------------------------------------------------------------------- /Value_Based/Vanila_DQN/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kyunghoon-jung/RL_implementation/HEAD/Value_Based/Vanila_DQN/train.py --------------------------------------------------------------------------------