├── .gitattributes ├── .gitignore ├── APEX ├── APEX_Local_MemoryBuffer.py ├── APEX_Rank_Priority_MemoryBuffer.py ├── dpg_actor_slim.py ├── dpg_learner.py ├── neural_networks.py ├── sac_actor.py └── sac_learner.py ├── R2D2 ├── DTOs.py ├── LearningRateDecayScheduler.py ├── R2D2_AgentBuffer.py ├── R2D2_SAC_Agent.py ├── R2D2_SAC_Learner.py ├── R2D2_TrajectoryStore.py └── neural_networks.py ├── README.md ├── env └── lunar_lander.py ├── lunar_lander_ActiveDendritsNetwork.py ├── lunar_lander_ActorCritic.py ├── lunar_lander_DDPG.py ├── lunar_lander_DSAC.py ├── lunar_lander_IQN.py ├── lunar_lander_PPO.py ├── lunar_lander_PolicyGradient.py ├── lunar_lander_QR_DQN.py ├── lunar_lander_RND_Curiosity.py ├── lunar_lander_SAC.py ├── lunar_lander_SAC_CAPS.py ├── lunar_lander_SAC_ERE.py ├── lunar_lander_SAC_R2D2.py ├── lunar_lander_SAC_value.py ├── lunar_lander_TD3.py ├── lunar_lander_a2c_tdn_buffer_with_entropy.py ├── lunar_lander_a2c_tdn_entropy.py ├── lunar_lander_ape-x-SAC.py ├── lunar_lander_ape-x.py ├── lunar_lander_doubleDQN.py ├── lunar_lander_double_dueling_DQN.py ├── lunar_lander_double_dueling_DQN_IS.py ├── lunar_lander_double_dueling_DQN_IS_rank.py ├── lunar_lander_keras.py ├── reinforcement-learning.pyproj ├── reinforcement-learning.sln ├── rl_utils ├── ERE_MemoryBuffer.py ├── LearningRateDecayScheduler.py ├── OUActionNoise.py ├── SARST_NStepReturn_RandomAccess_MemoryBuffer.py ├── SARST_NStepReturn_RandomAccess_MemoryBuffer_NoOverwrite.py ├── SARST_RandomAccess_MemoryBuffer.py ├── SARST_Rank_Priority_MemoryBuffer.py ├── SARST_TD_Priority_MemoryBuffer.py ├── UncertaintyService.py ├── ad_layer.py └── cos_layer.py └── side_notes.txt /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/.gitattributes -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/.gitignore -------------------------------------------------------------------------------- /APEX/APEX_Local_MemoryBuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/APEX/APEX_Local_MemoryBuffer.py -------------------------------------------------------------------------------- /APEX/APEX_Rank_Priority_MemoryBuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/APEX/APEX_Rank_Priority_MemoryBuffer.py -------------------------------------------------------------------------------- /APEX/dpg_actor_slim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/APEX/dpg_actor_slim.py -------------------------------------------------------------------------------- /APEX/dpg_learner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/APEX/dpg_learner.py -------------------------------------------------------------------------------- /APEX/neural_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/APEX/neural_networks.py -------------------------------------------------------------------------------- /APEX/sac_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/APEX/sac_actor.py -------------------------------------------------------------------------------- /APEX/sac_learner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/APEX/sac_learner.py -------------------------------------------------------------------------------- /R2D2/DTOs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/R2D2/DTOs.py -------------------------------------------------------------------------------- /R2D2/LearningRateDecayScheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/R2D2/LearningRateDecayScheduler.py -------------------------------------------------------------------------------- /R2D2/R2D2_AgentBuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/R2D2/R2D2_AgentBuffer.py -------------------------------------------------------------------------------- /R2D2/R2D2_SAC_Agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/R2D2/R2D2_SAC_Agent.py -------------------------------------------------------------------------------- /R2D2/R2D2_SAC_Learner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/R2D2/R2D2_SAC_Learner.py -------------------------------------------------------------------------------- /R2D2/R2D2_TrajectoryStore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/R2D2/R2D2_TrajectoryStore.py -------------------------------------------------------------------------------- /R2D2/neural_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/R2D2/neural_networks.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/README.md -------------------------------------------------------------------------------- /env/lunar_lander.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/env/lunar_lander.py -------------------------------------------------------------------------------- /lunar_lander_ActiveDendritsNetwork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_ActiveDendritsNetwork.py -------------------------------------------------------------------------------- /lunar_lander_ActorCritic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_ActorCritic.py -------------------------------------------------------------------------------- /lunar_lander_DDPG.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_DDPG.py -------------------------------------------------------------------------------- /lunar_lander_DSAC.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_DSAC.py -------------------------------------------------------------------------------- /lunar_lander_IQN.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_IQN.py -------------------------------------------------------------------------------- /lunar_lander_PPO.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_PPO.py -------------------------------------------------------------------------------- /lunar_lander_PolicyGradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_PolicyGradient.py -------------------------------------------------------------------------------- /lunar_lander_QR_DQN.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_QR_DQN.py -------------------------------------------------------------------------------- /lunar_lander_RND_Curiosity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_RND_Curiosity.py -------------------------------------------------------------------------------- /lunar_lander_SAC.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_SAC.py -------------------------------------------------------------------------------- /lunar_lander_SAC_CAPS.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_SAC_CAPS.py -------------------------------------------------------------------------------- /lunar_lander_SAC_ERE.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_SAC_ERE.py -------------------------------------------------------------------------------- /lunar_lander_SAC_R2D2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_SAC_R2D2.py -------------------------------------------------------------------------------- /lunar_lander_SAC_value.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_SAC_value.py -------------------------------------------------------------------------------- /lunar_lander_TD3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_TD3.py -------------------------------------------------------------------------------- /lunar_lander_a2c_tdn_buffer_with_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_a2c_tdn_buffer_with_entropy.py -------------------------------------------------------------------------------- /lunar_lander_a2c_tdn_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_a2c_tdn_entropy.py -------------------------------------------------------------------------------- /lunar_lander_ape-x-SAC.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_ape-x-SAC.py -------------------------------------------------------------------------------- /lunar_lander_ape-x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_ape-x.py -------------------------------------------------------------------------------- /lunar_lander_doubleDQN.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_doubleDQN.py -------------------------------------------------------------------------------- /lunar_lander_double_dueling_DQN.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_double_dueling_DQN.py -------------------------------------------------------------------------------- /lunar_lander_double_dueling_DQN_IS.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_double_dueling_DQN_IS.py -------------------------------------------------------------------------------- /lunar_lander_double_dueling_DQN_IS_rank.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_double_dueling_DQN_IS_rank.py -------------------------------------------------------------------------------- /lunar_lander_keras.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/lunar_lander_keras.py -------------------------------------------------------------------------------- /reinforcement-learning.pyproj: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/reinforcement-learning.pyproj -------------------------------------------------------------------------------- /reinforcement-learning.sln: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/reinforcement-learning.sln -------------------------------------------------------------------------------- /rl_utils/ERE_MemoryBuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/ERE_MemoryBuffer.py -------------------------------------------------------------------------------- /rl_utils/LearningRateDecayScheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/LearningRateDecayScheduler.py -------------------------------------------------------------------------------- /rl_utils/OUActionNoise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/OUActionNoise.py -------------------------------------------------------------------------------- /rl_utils/SARST_NStepReturn_RandomAccess_MemoryBuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/SARST_NStepReturn_RandomAccess_MemoryBuffer.py -------------------------------------------------------------------------------- /rl_utils/SARST_NStepReturn_RandomAccess_MemoryBuffer_NoOverwrite.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/SARST_NStepReturn_RandomAccess_MemoryBuffer_NoOverwrite.py -------------------------------------------------------------------------------- /rl_utils/SARST_RandomAccess_MemoryBuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/SARST_RandomAccess_MemoryBuffer.py -------------------------------------------------------------------------------- /rl_utils/SARST_Rank_Priority_MemoryBuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/SARST_Rank_Priority_MemoryBuffer.py -------------------------------------------------------------------------------- /rl_utils/SARST_TD_Priority_MemoryBuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/SARST_TD_Priority_MemoryBuffer.py -------------------------------------------------------------------------------- /rl_utils/UncertaintyService.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/UncertaintyService.py -------------------------------------------------------------------------------- /rl_utils/ad_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/ad_layer.py -------------------------------------------------------------------------------- /rl_utils/cos_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/rl_utils/cos_layer.py -------------------------------------------------------------------------------- /side_notes.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vformanyuk/reinforcement-learning/HEAD/side_notes.txt --------------------------------------------------------------------------------