panda-gym: Open-source goal-conditioned environments for robotic learning

TL;DR

panda-gym provides open-source, goal-conditioned reinforcement learning environments for the Franka Emika Panda robot, enabling easy task creation and benchmarking with state-of-the-art algorithms in a physics simulation.

Contribution

The paper introduces panda-gym, a flexible, open-source set of RL environments for robotic tasks using PyBullet, facilitating research and benchmarking in robotic learning.

Findings

Baseline results with state-of-the-art algorithms are provided.

The environments are easy to extend for new tasks or robots.

panda-gym is freely available for the research community.

Abstract

This paper presents panda-gym, a set of Reinforcement Learning (RL) environments for the Franka Emika Panda robot integrated with OpenAI Gym. Five tasks are included: reach, push, slide, pick & place and stack. They all follow a Multi-Goal RL framework, allowing to use goal-oriented RL algorithms. To foster open-research, we chose to use the open-source physics engine PyBullet. The implementation chosen for this package allows to define very easily new tasks or new robots. This paper also presents a baseline of results obtained with state-of-the-art model-free off-policy algorithms. panda-gym is open-source and freely available at https://github.com/qgallouedec/panda-gym.