# datamllab/rlcard

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

Repository: https://github.com/datamllab/rlcard
Canonical: https://ross.abutalabs.com/products/rlcard
Homepage: http://www.rlcard.org
Language: Python
License: MIT
License Family: permissive
Topics: reinforcement-learning, deep-reinforcement-learning, game-ai, poker, card-game, poker-game, openai-gym, gym-environment, card-games, blackjack, texas, uno, mahjong, game-bot, doudizhu, multi-agent, game, ai
Last push: 2024-06-26T23:01:52+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2554, "days_push": 798, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3540, forks 753 (observed 2026-08-28T04:08:09.179646+00:00)

## What it is
RLCard is a Python toolkit for reinforcement learning research in card games, providing environments for Blackjack, Leduc Hold'em, Texas Hold'em, Dou Dizhu, Mahjong, and UNO with easy-to-use interfaces for RL and search algorithms. It bridges reinforcement learning and imperfect-information games and supports PettingZoo multi-agent APIs.

## Use cases
- train RL agents to play poker
- research imperfect information games
- benchmark reinforcement learning algorithms on card games
- build an AI bot for Dou Dizhu or Mahjong
- create a gym environment for a card game
- teach reinforcement learning with game examples

## When to choose
- you need ready-made card game environments for RL experiments
- you want a Python library with PyTorch algorithm implementations
- you are studying multi-agent or imperfect-information game AI

## When to avoid
- you need real-time or 3D game environments
- you want a production game bot service rather than a research toolkit
- you need perfect-information board games like chess or Go

## Facets
- artifact type: library
- maturity: maintenance
- function: reinforcement-learning, simulation, game-engine, machine-learning
- domain: reinforcement-learning, artificial-intelligence, machine-learning
- platform: python, cross-platform
- tags: card-games, poker, imperfect-information-games, gym-environment, multi-agent, game-ai, blackjack, doudizhu, mahjong, uno, game-development

## Member repositories
- datamllab/rlcard (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:09.179646+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:34:29.987226+00:00, confidence not recorded.
  - readme: https://github.com/datamllab/rlcard (fetched 2026-08-28T04:08:09.179646+00:00, sha 22dd37a956c6)
  - homepage: http://www.rlcard.org (fetched 2026-08-29T09:28:41.798390+00:00, sha feb59589f370)
  - registry_pypi: https://pypi.org/pypi/rlcard/json (fetched 2026-08-29T09:28:41.807765+00:00, sha a9503e2c757c)
- Data as of 2026-08-30T08:39:29.467469+00:00.