policy
alphazero-guerzhoy
jonah-chen · PyTorch
or hover any field below to flag it
Overview
Name
alphazero-guerzhoy
Author
jonah-chen
Framework
PyTorch
License
MIT
Skill type
other
Evidence level
untested
Task description
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
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list alphazero-guerzhoy yet.
Datasets that reference this policy
0No datasets reference alphazero-guerzhoy yet.