weixiang-smart/panda-gym

Set of robotic environments based on PyBullet physics engine and gymnasium.

panda-gym

Set of OpenAI/gym robotic environments based on PyBullet physics engine.

Documentation

Check out the documentation.

Installation

Using PyPI

pip install panda-gym

From source

git clone https://github.com/qgallouedec/panda-gym.git
pip install -e panda-gym

Usage

import gym
import panda_gym

env = gym.make('PandaReach-v2', render=True)

obs = env.reset()
done = False
while not done:
    action = env.action_space.sample() # random action
    obs, reward, done, info = env.step(action)

env.close()

You can also

Environments

PandaReach-v2	PandaPush-v2
PandaSlide-v2	PandaPickAndPlace-v2
PandaStack-v2	PandaFlip-v2

Baselines results

Baselines results and pre-trained agents available in rl-baselines3-zoo.

Citation

Cite as

@misc{gallouédec2021multigoal,
      title={Multi-Goal Reinforcement Learning environments for simulated Franka Emika Panda robot}, 
      author={Quentin Gallou{\'e}dec and Nicolas Cazin and Emmanuel Dellandr{\'e}a and Liming Chen},
      year={2021},
      eprint={2106.13687},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

Environments are widely inspired from OpenAI Fetch environments.