datamllab/rlcard

Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

70
/ 100
Verified

Provides standardized OpenAI Gym-compatible environments with native support for imperfect information handling across games, enabling direct integration with modern RL frameworks. Implements state abstraction and legal action masking to address challenges specific to card games, while maintaining compatibility with PettingZoo for multi-agent training scenarios. Includes built-in algorithms (DQN, Policy Gradient, Monte Carlo Tree Search) and human-playable interfaces for interactive evaluation.

3,416 stars and 5,599 monthly downloads. Used by 1 other package. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 20 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

3,416

Forks

732

Language

Python

License

MIT

Last pushed

Jun 26, 2024

Monthly downloads

5,599

Commits (30d)

0

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/datamllab/rlcard"

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