sotetsuk/pgx

♟️ Vectorized RL game environments in JAX

50
/ 100
Established

This project offers a collection of high-speed, parallel game simulators for researchers and developers working on reinforcement learning (RL) in discrete state spaces. It takes game rules and parameters as input, and outputs simulated game states and outcomes, enabling the efficient training and evaluation of AI agents. Anyone developing or experimenting with AI that learns to play board games like Chess, Go, or Backgammon would find this useful.

593 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to rapidly simulate many instances of board games for training reinforcement learning agents, leveraging GPU acceleration for speed.

Not ideal if you are looking for physics-based simulations or continuous control tasks.

reinforcement-learning game-AI board-game-simulation AI-training discrete-environments
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 15 / 25

How are scores calculated?

Stars

593

Forks

44

Language

Python

License

Apache-2.0

Last pushed

Mar 06, 2025

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sotetsuk/pgx"

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