stillonearth/bevy_rl_shooter

Multi-Agent FPS Gym Environment with bevy_rl

23
/ 100
Experimental

This project provides a customizable simulation where multiple AI agents compete in a deathmatch scenario. It takes in control commands for each agent (movement, rotation) and outputs agent states, rewards for kills, and visual information (camera pixels). This tool is for AI researchers and game developers who want to train and test reinforcement learning algorithms for competitive multi-agent systems.

No commits in the last 6 months.

Use this if you need a flexible, multi-agent first-person shooter environment to develop and benchmark reinforcement learning strategies for AI bots.

Not ideal if you are looking for a pre-trained AI agent or a complete game, as this is an environment for training, not a ready-to-play application.

AI-training-environments multi-agent-systems reinforcement-learning-simulation game-AI-development robotics-simulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

24

Forks

Language

Rust

License

MIT

Last pushed

May 25, 2023

Monthly downloads

3

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/stillonearth/bevy_rl_shooter"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.