PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Find a file
2020-05-06 10:57:31 +02:00
.github Rename to stable-baselines3 2020-05-05 15:02:35 +02:00
docs Update doc 2020-05-05 17:41:57 +02:00
scripts Fix for test failures 2020-03-31 10:18:56 +02:00
stable_baselines3 Remove saved device + update doc 2020-05-05 17:19:21 +02:00
tests Sync identity envs 2020-05-05 16:52:22 +02:00
.coveragerc Sync with Stable-Baselines 2020-05-05 16:28:38 +02:00
.gitignore Update gitignore 2020-05-06 10:57:31 +02:00
LICENSE Init: TD3 2019-09-05 17:29:41 +02:00
Makefile Sync with Stable-Baselines 2020-05-05 16:28:38 +02:00
NOTICE Rename to stable-baselines3 2020-05-05 15:02:35 +02:00
README.md Sync with Stable-Baselines 2020-05-05 16:28:38 +02:00
setup.cfg Rename to stable-baselines3 2020-05-05 15:02:35 +02:00
setup.py Sync with Stable-Baselines 2020-05-05 16:28:38 +02:00

Build Status Documentation Status

Stable Baselines3

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

NOTE: Python 3.6 is required!

Implemented Algorithms

  • A2C

  • 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{stable-baselines3,
  author = {Raffin, Antonin and Hill, Ashley and Ernestus, Maximilian and Gleave, Adam and Kanervisto, Anssi and Dormann, Noah},
  title = {Stable Baselines3},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/DLR-RM/stable-baselines3}},
}