Clean PyTorch implementations of imitation and reward learning algorithms

Runs tests multiple times to expose flakiness.

A python documentation linter which checks that the docstring description matches the definition.

A pytest plugin for regression testing and regenerating Jupyter Notebooks

Version control for machine learning

Multi-Agent Connected Autonomous Driving (MACAD) Gym environments for Deep RL. Code for the paper presented in the Machine Learning for Autonomous Driving Workshop at NeurIPS 2019:

A py.test plugin to validate Jupyter notebooks

LaTeX support for the IntelliJ platform by JetBrains.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Extends cloudpickle to dynamically pickle modules from your working directory

PlayGround: AI Research into Multi-Agent Learning.

Maximum Causal Entropy Inverse Reinforcement Learning