An environment of the board game Go using OpenAI's Gym API
-
Updated
May 3, 2022 - Python
#
alpha-zero
Here are 27 public repositories matching this topic...
AlphaZero implementation for Othello, Connect-Four and Tic-Tac-Toe based on "Mastering the game of Go without human knowledge" and "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm" by DeepMind.
game machine-learning reinforcement-learning deep-learning tensorflow tic-tac-toe connect-four reversi mcts othello tictactoe resnet deepmind connect4 alphago-zero alpha-zero alphazero self-play
-
Updated
Apr 14, 2018 - Python
Learning from zero (mostly based off of AlphaZero) in General Game Playing.
hex chess reinforcement-learning deep-learning baduk reversi ggp connect6 general-game-playing breakthrough alpha-zero alphazero amazons gzero expert-iteration
-
Updated
Nov 21, 2022 - Python
Using self-play, MCTS, and a deep neural network to create a hearthstone ai player
ai deep-learning hearthstone deep-reinforcement-learning pytorch monte-carlo-tree-search alpha-zero self-play ismcts
-
Updated
Nov 1, 2018 - Python
Deep Reinforcement Learning for Chess
-
Updated
Nov 22, 2022 - Python
A clean and easy implementation of MuZero, AlphaZero and Self-Play reinforcement learning algorithms for any game.
-
Updated
Oct 15, 2024 - Python
An implementation of the AlphaZero algorithm for adversarial games to be used with the machine learning framework of your choice
-
Updated
Aug 30, 2020 - Python
A gomoku AI based on Alpha Zero paper.
-
Updated
May 1, 2023 - Python
HybridAlpha - a mix between AlphaGo Zero and AlphaZero for multiple games
python machine-learning deep-learning tensorflow keras deep-reinforcement-learning pytorch extensible mcts neural-networks othello tictactoe resnet flexibility alpha-beta-pruning greedy-algorithms gobang connect4 alphago-zero alpha-zero
-
Updated
May 23, 2020 - Python
A simplified version of Shogi with the AI is trained by alpha-zero-type training method
-
Updated
Jan 10, 2018 - Python
hyper optimized alpha zero implementation to play gomoku (distributed training with ray, mcts with cython)
-
Updated
Jan 15, 2023 - Python
Omok using MCTS (UCT, PUCT)
-
Updated
May 5, 2018 - Python
Pokémon battle simulator that uses the technique proposed in AlphaZero to beat the opponent.
-
Updated
Jul 25, 2022 - Python
Reinforcement Learning applied to 3-Player Chinese Checkers
-
Updated
Feb 21, 2020 - Python
This is a repository about Reinforcement Learning in which two agents, a Deep-Q-Network agent and an Alpha-Zero agent, learn to play Bullet Chess.
-
Updated
Aug 1, 2025 - Python
reinforcement learning applied to simple board games
-
Updated
Aug 15, 2024 - Python
The board game Go implemented in JAX for fast game processing and machine learning training.
-
Updated
Mar 6, 2023 - Python
AlphaZero for ultimate tic-tac-toe.
reinforcement-learning deep-learning neural-network pytorch artificial-intelligence mcts monte-carlo-tree-search ultimate-tic-tac-toe alpha-zero alphazero self-play
-
Updated
May 21, 2019 - Python
Improve this page
Add a description, image, and links to the alpha-zero topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the alpha-zero topic, visit your repo's landing page and select "manage topics."