OneUpWallStreet/TD-Gammon

Implementation of TD Gammon algorithm by Gerald Tesauro at IBM's Thomas J. Watson Research Center in Python.

20
/ 100
Experimental

This project implements the famous TD-Gammon algorithm, which teaches itself to play Backgammon. It takes the current state of a Backgammon board as input and suggests the best move, improving its play through self-play. This is ideal for researchers in reinforcement learning or AI enthusiasts interested in classic AI game-playing agents.

No commits in the last 6 months.

Use this if you are studying or experimenting with self-play reinforcement learning and want to see a classic algorithm applied to a board game.

Not ideal if you are looking for a commercial-grade Backgammon application or a real-time, high-performance game AI that can leverage GPU acceleration.

Reinforcement Learning Game AI Backgammon Self-Play AI Research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

Category

card-game-ai

Last pushed

Mar 13, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OneUpWallStreet/TD-Gammon"

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