https://github.com/mauroluzzatto/learn-tictactoe-through-self-play
This repository contains a Q-Learning algorithm that learns to play TicTacToe through self-play.
https://github.com/mauroluzzatto/learn-tictactoe-through-self-play
gym gym-environment q-learning reinforcement-learning self-learning tic-tac-toe
Last synced: 20 days ago
JSON representation
This repository contains a Q-Learning algorithm that learns to play TicTacToe through self-play.
- Host: GitHub
- URL: https://github.com/mauroluzzatto/learn-tictactoe-through-self-play
- Owner: MauroLuzzatto
- Created: 2022-01-18T21:30:49.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-05-18T12:44:05.000Z (over 3 years ago)
- Last Synced: 2024-11-11T03:54:33.873Z (11 months ago)
- Topics: gym, gym-environment, q-learning, reinforcement-learning, self-learning, tic-tac-toe
- Language: Jupyter Notebook
- Homepage:
- Size: 214 KB
- Stars: 4
- Watchers: 2
- Forks: 0
- Open Issues: 0