inspirai/TimeChamber
A Massively Parallel Large Scale Self-Play Framework
Leverages Isaac Gym's GPU-accelerated parallel simulation to run thousands of environments simultaneously on a single GPU (80,000+ FPS on RTX 3070Ti), enabling fast self-play training with PPO and prioritized fictitious player pools. Includes vectorized policy evaluation for rapid ELO rating calculations across multiple agents, and provides three competitive multi-agent benchmark tasks (Humanoid Strike, Ant Sumo, Ant Battle) built on rl_games integration.
361 stars. No commits in the last 6 months.
Stars
361
Forks
38
Language
Python
License
MIT
Category
Last pushed
Jan 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/inspirai/TimeChamber"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google-deepmind/concordia
A library for generative social simulation
Mai-xiyu/Minecraft_AI
AI Play Minecraft
mikelma/craftium
A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI...
cocacola-lab/MineLand
Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs
Dominien/brunnfeld-agentic-world
Medieval village economy simulation — up to 1000 LLM agents across multiple villages, driven by...