Connect-4 AI inspired by the AlphaZero paper that uses Monte-Carlo Tree Search, and a neural policy and value estimator neural network trained with samples generated from self play between previous iterations of the model.
agent
reinforcement-learning
ai
deep-learning
mcts
monte-carlo-tree-search
alphago
connect4
human-player
alphazero
estimator-network
-
Updated
Jul 25, 2022 - Python