Cybernetic1/reinforcement-learning-experiments
Reinforcement learning experiments with Tic Tac Toe, especially with "logical representations"
This project helps researchers and AI practitioners experiment with reinforcement learning (RL) algorithms for logical reasoning tasks, specifically using Tic-Tac-Toe as a demonstration. It takes in various RL configurations, including policy gradient and Q-learning with different neural network architectures, and outputs performance metrics and visualizations that show how well an AI learns to play the game.
Use this if you are an AI researcher or practitioner looking to understand and compare different reinforcement learning approaches, especially those using symmetric neural networks or transformers for problems involving sequential decision-making and logical states.
Not ideal if you are looking for a plug-and-play solution to integrate a Tic-Tac-Toe AI into an application or if you need robust, production-ready RL implementations.
Stars
7
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Cybernetic1/reinforcement-learning-experiments"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Cledersonbc/tic-tac-toe-minimax
Minimax is a AI algorithm.
LazoVelko/Tic-Tac-Toe
An unbeatable game of Tic Tac Toe.
mscroggs/MENACE
Machine Educable Noughts And Crosses Engine
GantMan/tictactoe-ai-tfjs
Train your own TensorFlow.js Tic Tac Toe
jamesq9/Tic-Tac-Toe-Machine-Learning-Using-Reinforcement-Learning
A Python Program to implement Machine Learning for the Game Tic Tac Toe (3x3) using...