├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── batch_rl ├── __init__.py ├── baselines │ ├── __init__.py │ ├── agents │ │ ├── __init__.py │ │ ├── dqn_agent.py │ │ ├── quantile_agent.py │ │ └── random_agent.py │ ├── configs │ │ ├── dqn.gin │ │ ├── quantile.gin │ │ └── random.gin │ ├── replay_memory │ │ ├── __init__.py │ │ ├── logged_prioritized_replay_buffer.py │ │ └── logged_replay_buffer.py │ ├── run_experiment.py │ └── train.py ├── fixed_replay │ ├── __init__.py │ ├── agents │ │ ├── __init__.py │ │ ├── dqn_agent.py │ │ ├── multi_head_dqn_agent.py │ │ ├── multi_network_dqn_agent.py │ │ ├── quantile_agent.py │ │ └── rainbow_agent.py │ ├── configs │ │ ├── c51.gin │ │ ├── dqn.gin │ │ ├── multi_head_dqn.gin │ │ ├── quantile.gin │ │ └── rem.gin │ ├── replay_memory │ │ └── fixed_replay_buffer.py │ ├── run_experiment.py │ └── train.py ├── multi_head │ ├── __init__.py │ ├── atari_helpers.py │ ├── multi_head_dqn_agent.py │ ├── multi_network_dqn_agent.py │ └── quantile_agent.py └── tests │ ├── atari_init_test.py │ └── fixed_replay_runner_test.py └── online ├── configs ├── c51.gin ├── dqn.gin ├── quantile.gin └── rem.gin └── train.py /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/README.md -------------------------------------------------------------------------------- /batch_rl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/__init__.py -------------------------------------------------------------------------------- /batch_rl/baselines/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/__init__.py -------------------------------------------------------------------------------- /batch_rl/baselines/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/agents/__init__.py -------------------------------------------------------------------------------- /batch_rl/baselines/agents/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/agents/dqn_agent.py -------------------------------------------------------------------------------- /batch_rl/baselines/agents/quantile_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/agents/quantile_agent.py -------------------------------------------------------------------------------- /batch_rl/baselines/agents/random_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/agents/random_agent.py -------------------------------------------------------------------------------- /batch_rl/baselines/configs/dqn.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/configs/dqn.gin -------------------------------------------------------------------------------- /batch_rl/baselines/configs/quantile.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/configs/quantile.gin -------------------------------------------------------------------------------- /batch_rl/baselines/configs/random.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/configs/random.gin -------------------------------------------------------------------------------- /batch_rl/baselines/replay_memory/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/replay_memory/__init__.py -------------------------------------------------------------------------------- /batch_rl/baselines/replay_memory/logged_prioritized_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/replay_memory/logged_prioritized_replay_buffer.py -------------------------------------------------------------------------------- /batch_rl/baselines/replay_memory/logged_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/replay_memory/logged_replay_buffer.py -------------------------------------------------------------------------------- /batch_rl/baselines/run_experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/run_experiment.py -------------------------------------------------------------------------------- /batch_rl/baselines/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/baselines/train.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/__init__.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/agents/__init__.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/agents/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/agents/dqn_agent.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/agents/multi_head_dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/agents/multi_head_dqn_agent.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/agents/multi_network_dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/agents/multi_network_dqn_agent.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/agents/quantile_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/agents/quantile_agent.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/agents/rainbow_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/agents/rainbow_agent.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/configs/c51.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/configs/c51.gin -------------------------------------------------------------------------------- /batch_rl/fixed_replay/configs/dqn.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/configs/dqn.gin -------------------------------------------------------------------------------- /batch_rl/fixed_replay/configs/multi_head_dqn.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/configs/multi_head_dqn.gin -------------------------------------------------------------------------------- /batch_rl/fixed_replay/configs/quantile.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/configs/quantile.gin -------------------------------------------------------------------------------- /batch_rl/fixed_replay/configs/rem.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/configs/rem.gin -------------------------------------------------------------------------------- /batch_rl/fixed_replay/replay_memory/fixed_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/replay_memory/fixed_replay_buffer.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/run_experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/run_experiment.py -------------------------------------------------------------------------------- /batch_rl/fixed_replay/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/fixed_replay/train.py -------------------------------------------------------------------------------- /batch_rl/multi_head/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/multi_head/__init__.py -------------------------------------------------------------------------------- /batch_rl/multi_head/atari_helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/multi_head/atari_helpers.py -------------------------------------------------------------------------------- /batch_rl/multi_head/multi_head_dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/multi_head/multi_head_dqn_agent.py -------------------------------------------------------------------------------- /batch_rl/multi_head/multi_network_dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/multi_head/multi_network_dqn_agent.py -------------------------------------------------------------------------------- /batch_rl/multi_head/quantile_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/multi_head/quantile_agent.py -------------------------------------------------------------------------------- /batch_rl/tests/atari_init_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/tests/atari_init_test.py -------------------------------------------------------------------------------- /batch_rl/tests/fixed_replay_runner_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/batch_rl/tests/fixed_replay_runner_test.py -------------------------------------------------------------------------------- /online/configs/c51.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/online/configs/c51.gin -------------------------------------------------------------------------------- /online/configs/dqn.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/online/configs/dqn.gin -------------------------------------------------------------------------------- /online/configs/quantile.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/online/configs/quantile.gin -------------------------------------------------------------------------------- /online/configs/rem.gin: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/online/configs/rem.gin -------------------------------------------------------------------------------- /online/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-research/batch_rl/HEAD/online/train.py --------------------------------------------------------------------------------