├── .gitignore ├── README.md ├── __init__.py ├── cross-entropy-method └── main.py ├── ddpg ├── main.py └── utils.py ├── dqn ├── Pipfile ├── args.py ├── checklist.md ├── dqn.py ├── env.py ├── exploration.py ├── flappy_bird.py ├── main.py ├── model.py ├── replay_buffer.py ├── train.py └── types.py ├── es └── __init__.py ├── kelly.py ├── lib ├── __init__.py └── replay_buffer.py ├── mlsh ├── main.py └── utils.py ├── pg ├── __init__.py └── main.py ├── ppo └── ppo.py ├── pyproject.toml ├── ray-tutorial ├── README.rst ├── examples │ ├── block_linear_algebra.py │ ├── evolution_strategies.py │ └── hyperparameter_search.py ├── exercises │ ├── exercise01.ipynb │ ├── exercise02.ipynb │ ├── exercise03.ipynb │ ├── exercise04.ipynb │ ├── exercise05.ipynb │ ├── exercise06.ipynb │ ├── exercise07.ipynb │ ├── exercise08.ipynb │ ├── exercise09.ipynb │ └── exercise10.ipynb └── rl_exercises │ ├── rl_exercise01.ipynb │ ├── rl_exercise02.ipynb │ ├── rl_exercise03.ipynb │ ├── rl_exercise04.ipynb │ └── rl_exercise05.ipynb ├── reptile ├── README.md ├── main.py ├── parallel_reduce.py └── utils.py ├── utils.py └── xor_lstm ├── README.md ├── model-or_.pth ├── model-xor-cuda.pth ├── model-xor.pth ├── xor_lstm.py └── xor_mlp.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/README.md -------------------------------------------------------------------------------- /__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /cross-entropy-method/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/cross-entropy-method/main.py -------------------------------------------------------------------------------- /ddpg/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ddpg/main.py -------------------------------------------------------------------------------- /ddpg/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ddpg/utils.py -------------------------------------------------------------------------------- /dqn/Pipfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/Pipfile -------------------------------------------------------------------------------- /dqn/args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/args.py -------------------------------------------------------------------------------- /dqn/checklist.md: -------------------------------------------------------------------------------- 1 | - [] grep TODO 2 | -------------------------------------------------------------------------------- /dqn/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/dqn.py -------------------------------------------------------------------------------- /dqn/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/env.py -------------------------------------------------------------------------------- /dqn/exploration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/exploration.py -------------------------------------------------------------------------------- /dqn/flappy_bird.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/flappy_bird.py -------------------------------------------------------------------------------- /dqn/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/main.py -------------------------------------------------------------------------------- /dqn/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/model.py -------------------------------------------------------------------------------- /dqn/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/replay_buffer.py -------------------------------------------------------------------------------- /dqn/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/train.py -------------------------------------------------------------------------------- /dqn/types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/dqn/types.py -------------------------------------------------------------------------------- /es/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /kelly.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/kelly.py -------------------------------------------------------------------------------- /lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /lib/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/lib/replay_buffer.py -------------------------------------------------------------------------------- /mlsh/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/mlsh/main.py -------------------------------------------------------------------------------- /mlsh/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/mlsh/utils.py -------------------------------------------------------------------------------- /pg/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pg/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/pg/main.py -------------------------------------------------------------------------------- /ppo/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ppo/ppo.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/pyproject.toml -------------------------------------------------------------------------------- /ray-tutorial/README.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/README.rst -------------------------------------------------------------------------------- /ray-tutorial/examples/block_linear_algebra.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/examples/block_linear_algebra.py -------------------------------------------------------------------------------- /ray-tutorial/examples/evolution_strategies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/examples/evolution_strategies.py -------------------------------------------------------------------------------- /ray-tutorial/examples/hyperparameter_search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/examples/hyperparameter_search.py -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise01.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise01.ipynb -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise02.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise02.ipynb -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise03.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise03.ipynb -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise04.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise04.ipynb -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise05.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise05.ipynb -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise06.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise06.ipynb -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise07.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise07.ipynb -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise08.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise08.ipynb -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise09.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise09.ipynb -------------------------------------------------------------------------------- /ray-tutorial/exercises/exercise10.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/exercises/exercise10.ipynb -------------------------------------------------------------------------------- /ray-tutorial/rl_exercises/rl_exercise01.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/rl_exercises/rl_exercise01.ipynb -------------------------------------------------------------------------------- /ray-tutorial/rl_exercises/rl_exercise02.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/rl_exercises/rl_exercise02.ipynb -------------------------------------------------------------------------------- /ray-tutorial/rl_exercises/rl_exercise03.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/rl_exercises/rl_exercise03.ipynb -------------------------------------------------------------------------------- /ray-tutorial/rl_exercises/rl_exercise04.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/rl_exercises/rl_exercise04.ipynb -------------------------------------------------------------------------------- /ray-tutorial/rl_exercises/rl_exercise05.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/ray-tutorial/rl_exercises/rl_exercise05.ipynb -------------------------------------------------------------------------------- /reptile/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/reptile/README.md -------------------------------------------------------------------------------- /reptile/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/reptile/main.py -------------------------------------------------------------------------------- /reptile/parallel_reduce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/reptile/parallel_reduce.py -------------------------------------------------------------------------------- /reptile/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/reptile/utils.py -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/utils.py -------------------------------------------------------------------------------- /xor_lstm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/xor_lstm/README.md -------------------------------------------------------------------------------- /xor_lstm/model-or_.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/xor_lstm/model-or_.pth -------------------------------------------------------------------------------- /xor_lstm/model-xor-cuda.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/xor_lstm/model-xor-cuda.pth -------------------------------------------------------------------------------- /xor_lstm/model-xor.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/xor_lstm/model-xor.pth -------------------------------------------------------------------------------- /xor_lstm/xor_lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/xor_lstm/xor_lstm.py -------------------------------------------------------------------------------- /xor_lstm/xor_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alok/rl_implementations/HEAD/xor_lstm/xor_mlp.py --------------------------------------------------------------------------------