Skip to main content

UAV Flight Simulator Gymnasium Environments for Reinforcement Learning Research.

Project description

Ruff total downloads weekly downloads

PyFlyt - UAV Flight Simulator for Reinforcement Learning Research

Comes with Gymnasium and PettingZoo environments built in!

View the documentation here!

This is a library for testing reinforcement learning algorithms on UAVs. This repo is still under development. We are also actively looking for users and developers, if this sounds like you, don't hesitate to get in touch!

Installation

pip3 install wheel numpy
pip3 install pyflyt

numpy and wheel must be installed prior to pyflyt such that pybullet is built with numpy support.

Usage

Usage is similar to any other Gymnasium and PettingZoo environment:

Gymnasium

import gymnasium
import PyFlyt.gym_envs # noqa

env = gymnasium.make("PyFlyt/QuadX-Hover-v0", render_mode="human")
obs = env.reset()

termination = False
truncation = False

while not termination or truncation:
    observation, reward, termination, truncation, info = env.step(env.action_space.sample())

View the official documentation for gymnasium environments here.

PettingZoo

from PyFlyt.pz_envs import MAFixedwingDogfightEnv

env = MAFixedwingDogfightEnv(render_mode="human")
observations, infos = env.reset()

while env.agents:
    # this is where you would insert your policy
    actions = {agent: env.action_space(agent).sample() for agent in env.agents}

    observations, rewards, terminations, truncations, infos = env.step(actions)
env.close()

View the official documentation for pettingzoo environments here.

Citation

If you use our work in your research and would like to cite it, please use the following bibtex entry:

@article{tai2023pyflyt,
  title={PyFlyt--UAV Simulation Environments for Reinforcement Learning Research},
  author={Tai, Jun Jet and Wong, Jim and Innocente, Mauro and Horri, Nadjim and Brusey, James and Phang, Swee King},
  journal={arXiv preprint arXiv:2304.01305},
  year={2023}
}

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

PyFlyt-0.19.0.tar.gz (170.7 kB view hashes)

Uploaded Source

Built Distribution

PyFlyt-0.19.0-py3-none-any.whl (198.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page