Torchy Baselines

PyTorch version of Stable Baselines, a set of improved implementations of reinforcement learning algorithms.

NOTE: Python 3.6 is required!

Implemented Algorithms

• A2C

• CEM-RL (with TD3)

• PPO

• SAC

• TD3

• SDE support for A2C, PPO, SAC and TD3.

Roadmap

• cf github Roadmap

Run the Tests

pip install -e .[tests]
make pytest

Type check

pip install -e .[tests]
make type

Build the Documentation

pip install -e .[docs]
make doc

Spell check for the documentation:

make spelling

Citing the Project

To cite this repository in publications:

@misc{torchy-baselines,
  author = {Raffin, Antonin and Hill, Ashley and Ernestus, Maximilian and Gleave, Adam and Kanervisto, Anssi and Dormann, Noah},
  title = {Torchy Baselines},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/araffin/torchy-baselines}},
}