├── .gitignore ├── LICENSE ├── README.md ├── docker ├── Dockerfile └── build.sh ├── kill.sh ├── run.sh ├── run_it.sh └── src ├── action ├── __init__.py ├── bsp_action.py ├── count_action.py ├── eps_greedy.py ├── optimistic_action.py └── testing.py ├── agent ├── __init__.py ├── atari_dqn.py ├── atari_qrdqn.py ├── bsp_atari_conv.py ├── bsp_maze_conv.py ├── conv_dqn.py ├── conv_dqn_bigger.py ├── dora │ ├── __init__.py │ ├── maze_conv.py │ └── specifier.py ├── fc_atari_dqn.py ├── fc_dqn.py ├── maze_conv.py ├── rnd_net │ ├── __init__.py │ ├── atari_conv_net.py │ ├── bigger_conv_net.py │ ├── conv_net.py │ ├── fc_net.py │ ├── smaller_conv_net.py │ └── specifier.py ├── specifier.py └── tiny_dqn.py ├── buffer ├── __init__.py └── buffer.py ├── config └── default.yaml ├── count ├── HashCount.py ├── __init__.py ├── atari_count.py ├── dora_count.py ├── rnd_count.py └── rnd_network_count.py ├── envs ├── OpenAI_AtariWrapper.py ├── __init__.py ├── atari.py ├── env_wrapper.py ├── gridworld.py ├── maze.py ├── montezuma.py └── nchain.py ├── main.py ├── trainer ├── __init__.py └── dqn_train.py └── utils ├── __init__.py ├── dict2namedtuple.py ├── logging.py └── timehelper.py /.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__/ 2 | *.pyc 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/README.md -------------------------------------------------------------------------------- /docker/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/docker/Dockerfile -------------------------------------------------------------------------------- /docker/build.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | docker build -t tabhid/explore . -------------------------------------------------------------------------------- /kill.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/kill.sh -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/run.sh -------------------------------------------------------------------------------- /run_it.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/run_it.sh -------------------------------------------------------------------------------- /src/action/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/action/bsp_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/action/bsp_action.py -------------------------------------------------------------------------------- /src/action/count_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/action/count_action.py -------------------------------------------------------------------------------- /src/action/eps_greedy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/action/eps_greedy.py -------------------------------------------------------------------------------- /src/action/optimistic_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/action/optimistic_action.py -------------------------------------------------------------------------------- /src/action/testing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/action/testing.py -------------------------------------------------------------------------------- /src/agent/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/agent/atari_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/atari_dqn.py -------------------------------------------------------------------------------- /src/agent/atari_qrdqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/atari_qrdqn.py -------------------------------------------------------------------------------- /src/agent/bsp_atari_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/bsp_atari_conv.py -------------------------------------------------------------------------------- /src/agent/bsp_maze_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/bsp_maze_conv.py -------------------------------------------------------------------------------- /src/agent/conv_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/conv_dqn.py -------------------------------------------------------------------------------- /src/agent/conv_dqn_bigger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/conv_dqn_bigger.py -------------------------------------------------------------------------------- /src/agent/dora/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/agent/dora/maze_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/dora/maze_conv.py -------------------------------------------------------------------------------- /src/agent/dora/specifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/dora/specifier.py -------------------------------------------------------------------------------- /src/agent/fc_atari_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/fc_atari_dqn.py -------------------------------------------------------------------------------- /src/agent/fc_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/fc_dqn.py -------------------------------------------------------------------------------- /src/agent/maze_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/maze_conv.py -------------------------------------------------------------------------------- /src/agent/rnd_net/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/agent/rnd_net/atari_conv_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/rnd_net/atari_conv_net.py -------------------------------------------------------------------------------- /src/agent/rnd_net/bigger_conv_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/rnd_net/bigger_conv_net.py -------------------------------------------------------------------------------- /src/agent/rnd_net/conv_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/rnd_net/conv_net.py -------------------------------------------------------------------------------- /src/agent/rnd_net/fc_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/rnd_net/fc_net.py -------------------------------------------------------------------------------- /src/agent/rnd_net/smaller_conv_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/rnd_net/smaller_conv_net.py -------------------------------------------------------------------------------- /src/agent/rnd_net/specifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/rnd_net/specifier.py -------------------------------------------------------------------------------- /src/agent/specifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/specifier.py -------------------------------------------------------------------------------- /src/agent/tiny_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/agent/tiny_dqn.py -------------------------------------------------------------------------------- /src/buffer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/buffer/buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/buffer/buffer.py -------------------------------------------------------------------------------- /src/config/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/config/default.yaml -------------------------------------------------------------------------------- /src/count/HashCount.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/count/HashCount.py -------------------------------------------------------------------------------- /src/count/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/count/atari_count.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/count/atari_count.py -------------------------------------------------------------------------------- /src/count/dora_count.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/count/dora_count.py -------------------------------------------------------------------------------- /src/count/rnd_count.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/count/rnd_count.py -------------------------------------------------------------------------------- /src/count/rnd_network_count.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/count/rnd_network_count.py -------------------------------------------------------------------------------- /src/envs/OpenAI_AtariWrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/envs/OpenAI_AtariWrapper.py -------------------------------------------------------------------------------- /src/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/envs/__init__.py -------------------------------------------------------------------------------- /src/envs/atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/envs/atari.py -------------------------------------------------------------------------------- /src/envs/env_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/envs/env_wrapper.py -------------------------------------------------------------------------------- /src/envs/gridworld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/envs/gridworld.py -------------------------------------------------------------------------------- /src/envs/maze.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/envs/maze.py -------------------------------------------------------------------------------- /src/envs/montezuma.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/envs/montezuma.py -------------------------------------------------------------------------------- /src/envs/nchain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/envs/nchain.py -------------------------------------------------------------------------------- /src/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/main.py -------------------------------------------------------------------------------- /src/trainer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/trainer/dqn_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/trainer/dqn_train.py -------------------------------------------------------------------------------- /src/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/utils/dict2namedtuple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/utils/dict2namedtuple.py -------------------------------------------------------------------------------- /src/utils/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/utils/logging.py -------------------------------------------------------------------------------- /src/utils/timehelper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/oxwhirl/opiq/HEAD/src/utils/timehelper.py --------------------------------------------------------------------------------