├── LICENSE ├── RAA-DuelingDQN ├── logs │ └── QbertNoFrameskip-v4 │ │ ├── seed-101 │ │ ├── events.out.tfevents.1556717534.ubuntu │ │ ├── net.pth │ │ ├── scalars.npy │ │ └── tmp │ │ │ ├── openaigym.episode_batch.0.15987.stats.json │ │ │ └── openaigym.manifest.0.15987.manifest.json │ │ ├── seed-102 │ │ └── scalars.npy │ │ ├── seed-103 │ │ └── scalars.npy │ │ ├── seed-104 │ │ └── scalars.npy │ │ └── seed-105 │ │ └── scalars.npy ├── main.py ├── run_atari.sh ├── src │ ├── anderson_alpha.py │ ├── dqn.py │ ├── logger.py │ ├── model.py │ └── raa_dqn.py └── utils │ ├── atari_wrappers.py │ ├── gym_setup.py │ ├── replay_buffer.py │ └── schedules.py ├── RAA-TD3 ├── logs │ └── Walker2d-v2 │ │ ├── seed-101 │ │ ├── data │ │ │ ├── eval.npy │ │ │ └── residual.npy │ │ └── model │ │ │ ├── actor.pth │ │ │ └── critic.pth │ │ ├── seed-102 │ │ └── data │ │ │ ├── eval.npy │ │ │ └── residual.npy │ │ ├── seed-103 │ │ └── data │ │ │ ├── eval.npy │ │ │ └── residual.npy │ │ ├── seed-104 │ │ └── data │ │ │ ├── eval.npy │ │ │ └── residual.npy │ │ ├── seed-105 │ │ └── data │ │ │ ├── eval.npy │ │ │ └── residual.npy │ │ ├── seed-106 │ │ └── data │ │ │ ├── eval.npy │ │ │ └── residual.npy │ │ └── seed-107 │ │ └── data │ │ ├── eval.npy │ │ └── residual.npy ├── main.py ├── run_mujoco.sh └── src │ ├── RAATD3_v0.py │ ├── RAATD3_v1.py │ ├── TD3.py │ ├── anderson.py │ ├── nets.py │ └── replay.py ├── README.md ├── learning_curves ├── Ant.png ├── BreakoutNoFrameskip.png ├── EnduroNoFrameskip.png ├── HalfCheetah.png ├── Hopper.png ├── QbertNoFrameskip.png ├── SpaceInvadersNoFrameskip.png └── Walker2d.png └── poster └── poster.pdf /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/LICENSE -------------------------------------------------------------------------------- /RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/events.out.tfevents.1556717534.ubuntu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/events.out.tfevents.1556717534.ubuntu -------------------------------------------------------------------------------- /RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/net.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/net.pth -------------------------------------------------------------------------------- /RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/scalars.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/scalars.npy -------------------------------------------------------------------------------- /RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/tmp/openaigym.episode_batch.0.15987.stats.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/tmp/openaigym.episode_batch.0.15987.stats.json -------------------------------------------------------------------------------- /RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/tmp/openaigym.manifest.0.15987.manifest.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-101/tmp/openaigym.manifest.0.15987.manifest.json -------------------------------------------------------------------------------- /RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-102/scalars.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-102/scalars.npy -------------------------------------------------------------------------------- /RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-103/scalars.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-103/scalars.npy -------------------------------------------------------------------------------- /RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-104/scalars.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-104/scalars.npy -------------------------------------------------------------------------------- /RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-105/scalars.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/logs/QbertNoFrameskip-v4/seed-105/scalars.npy -------------------------------------------------------------------------------- /RAA-DuelingDQN/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/main.py -------------------------------------------------------------------------------- /RAA-DuelingDQN/run_atari.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/run_atari.sh -------------------------------------------------------------------------------- /RAA-DuelingDQN/src/anderson_alpha.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/src/anderson_alpha.py -------------------------------------------------------------------------------- /RAA-DuelingDQN/src/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/src/dqn.py -------------------------------------------------------------------------------- /RAA-DuelingDQN/src/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/src/logger.py -------------------------------------------------------------------------------- /RAA-DuelingDQN/src/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/src/model.py -------------------------------------------------------------------------------- /RAA-DuelingDQN/src/raa_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/src/raa_dqn.py -------------------------------------------------------------------------------- /RAA-DuelingDQN/utils/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/utils/atari_wrappers.py -------------------------------------------------------------------------------- /RAA-DuelingDQN/utils/gym_setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/utils/gym_setup.py -------------------------------------------------------------------------------- /RAA-DuelingDQN/utils/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/utils/replay_buffer.py -------------------------------------------------------------------------------- /RAA-DuelingDQN/utils/schedules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-DuelingDQN/utils/schedules.py -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-101/data/eval.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-101/data/eval.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-101/data/residual.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-101/data/residual.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-101/model/actor.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-101/model/actor.pth -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-101/model/critic.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-101/model/critic.pth -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-102/data/eval.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-102/data/eval.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-102/data/residual.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-102/data/residual.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-103/data/eval.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-103/data/eval.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-103/data/residual.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-103/data/residual.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-104/data/eval.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-104/data/eval.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-104/data/residual.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-104/data/residual.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-105/data/eval.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-105/data/eval.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-105/data/residual.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-105/data/residual.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-106/data/eval.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-106/data/eval.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-106/data/residual.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-106/data/residual.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-107/data/eval.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-107/data/eval.npy -------------------------------------------------------------------------------- /RAA-TD3/logs/Walker2d-v2/seed-107/data/residual.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/logs/Walker2d-v2/seed-107/data/residual.npy -------------------------------------------------------------------------------- /RAA-TD3/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/main.py -------------------------------------------------------------------------------- /RAA-TD3/run_mujoco.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/run_mujoco.sh -------------------------------------------------------------------------------- /RAA-TD3/src/RAATD3_v0.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/src/RAATD3_v0.py -------------------------------------------------------------------------------- /RAA-TD3/src/RAATD3_v1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/src/RAATD3_v1.py -------------------------------------------------------------------------------- /RAA-TD3/src/TD3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/src/TD3.py -------------------------------------------------------------------------------- /RAA-TD3/src/anderson.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/src/anderson.py -------------------------------------------------------------------------------- /RAA-TD3/src/nets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/src/nets.py -------------------------------------------------------------------------------- /RAA-TD3/src/replay.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/RAA-TD3/src/replay.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/README.md -------------------------------------------------------------------------------- /learning_curves/Ant.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/learning_curves/Ant.png -------------------------------------------------------------------------------- /learning_curves/BreakoutNoFrameskip.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/learning_curves/BreakoutNoFrameskip.png -------------------------------------------------------------------------------- /learning_curves/EnduroNoFrameskip.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/learning_curves/EnduroNoFrameskip.png -------------------------------------------------------------------------------- /learning_curves/HalfCheetah.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/learning_curves/HalfCheetah.png -------------------------------------------------------------------------------- /learning_curves/Hopper.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/learning_curves/Hopper.png -------------------------------------------------------------------------------- /learning_curves/QbertNoFrameskip.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/learning_curves/QbertNoFrameskip.png -------------------------------------------------------------------------------- /learning_curves/SpaceInvadersNoFrameskip.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/learning_curves/SpaceInvadersNoFrameskip.png -------------------------------------------------------------------------------- /learning_curves/Walker2d.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/learning_curves/Walker2d.png -------------------------------------------------------------------------------- /poster/poster.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shiwj16/raa-drl/HEAD/poster/poster.pdf --------------------------------------------------------------------------------