jonah-chen/alphazero-guerzhoy
A RL agent using ResNet and MCTS to master the game of Gomoku through self-play inspired by the algorithm of Alpha-zero and AlphaGo. Named after its victim—inspired by the names AlphaGo-Fan and AlphaGo-Lee—but scoped beyond defeating Guerzhoy's simple AI (see gomoku.py) rather its goal is to master the game of Gomoku.
PythonMIT
Issues
- 0
Docstrings that does nothing
#5 opened by jonah-chen - 3
TF Memory Leak
#4 opened by jonah-chen - 0
newiswin overlines
#3 opened by MAK13789 - 0
iswin problem
#1 opened by MAK13789 - 0
Problems we need to fix by wednesday
#2 opened by MAK13789