bupticybee/AlphaNLHoldem

An unoffical implementation of AlphaHoldem. 1v1 nl-holdem AI.

45
/ 100
Emerging

This tool provides an AI opponent for heads-up no-limit Texas Hold'em. You can play against a pre-trained AI through a simple web interface, or train your own AI by providing computing resources. This is intended for poker enthusiasts, AI researchers, or competitive players looking to practice and analyze strategic play against a strong, logical opponent.

108 stars. No commits in the last 6 months.

Use this if you want to play practice hands of 1v1 No-Limit Hold'em against a sophisticated AI, or if you're an AI researcher interested in self-play model-free reinforcement learning for poker.

Not ideal if you're looking for a standard 6-player or 9-player poker simulator, or if you need an AI for full 100bb ACPC rules with standard bet sizing, as this uses a 50bb environment.

poker-strategy texas-holdem game-ai reinforcement-learning heads-up-poker
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

108

Forks

28

Language

Jupyter Notebook

License

AGPL-3.0

Category

card-game-ai

Last pushed

Jul 07, 2023

Commits (30d)

0

Get this data via API

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

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