/bullet-gym

Experimental (stable, go here: https://github.com/benelot/pybullet-gym) repository of OpenAI Gym environments implemented with Bullet Physics using pybullet.

Primary LanguagePythonMIT LicenseMIT

[DEPRECATED]: For the stable release use https://github.com/benelot/pybullet-gym.

bullet-gym - The pybullet environment for use with the OpenAI Gym Reinforcement Learning Research Platform

OpenAI gym is currently one of the most widely used toolkit for developing and comparing reinforcement learning algorithms. Unfortunately, for several challenging continuous control environments it requires the user to install MuJoCo, a commercial physics engine which requires a license to run for longer than 30 days. Such a commercial barrier hinders open research, especially in the perspective that other appropriate physics engines exist. This repository provides alternative implementations of the original MuJoCo environments which can be used for free. The environments have been reimplemented using BulletPhysics' python wrapper pybullet, such that they seamlessly integrate into the OpenAI gym framework. In order to show the usability of the new environments, several RL agents from the Keras-RL are configured to be trained out of the box. To further simplify the training of agents, a Trainer class was implemented which helps to capture commandline arguments in a unified fashion. The trainer provides a set of standard arguments, but additional arguments can be defined by the agent and the environment to enable the researcher to provide special parameters to either one.

Thanks to matpalm for a beautiful example on how to use pybullet with OpenAI Gym.

Repository Contents

The following environments are available to be run with the agents:

The following agents are available to be run with the environments:

Dependencies