Learning how to play tic-tac-toe with game theory, reinforcement learning... and bunch of matchboxes
-
Updated
Nov 28, 2023 - Python
#
menace-matchboxes
Here are 3 public repositories matching this topic...
Master the ultimate Tic Tac Toe experience with multiple AI opponents, which learn from your gameplay. ReactJS implementation of Tic Tac Toe featuring AI opponents DQN neural networks and Menace Matchboxes with persistent learning capabilities.
react game machine-learning tic-tac-toe artificial-intelligence dqn azure-functions tictactoe menace-matchboxes
-
Updated
Feb 16, 2025 - TypeScript
Reinforcement Learning with tabular methods: TD-learning (Q-learning and SARSA) and MENACE-like approach applied to a Rubik's cube with a move set restricted to 180-degree turns.
reinforcement-learning q-learning epsilon-greedy sarsa simulated-annealing td-learning softmax menace-matchboxes
-
Updated
Aug 1, 2021 - C
Improve this page
Add a description, image, and links to the menace-matchboxes topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the menace-matchboxes topic, visit your repo's landing page and select "manage topics."