stillonearth/bevy_rl_shooter
Multi-Agent FPS Gym Environment with bevy_rl
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.
Stars
24
Forks
—
Language
Rust
License
MIT
Category
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.
Higher-rated alternatives
Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with...
facebookresearch/BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL...
utiasDSL/gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
datamllab/rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
proroklab/VectorizedMultiAgentSimulator
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement...