Skip to content

Latest commit

 

History

History
21 lines (12 loc) · 621 Bytes

README.md

File metadata and controls

21 lines (12 loc) · 621 Bytes

Little-Go

USC CS561 project. Implement a GO agent for 5x5 GO, no machine learning libraries allowed.

Algorithm Applied

  • Feature extraction: Extract 1x1, 2x2 and 3x3 windows of location dependent and independent features on board.

  • Value estimation: Calculated by extracted features and their weights.

  • Learning algorithm: TD(0).

  • Search method: Monte-Carlo Tree Search.

Efficiency

Incorporate weight sharing among features to accelarate learning. Running efficiency improved by C++ in feature extraction and tree search.

Result

Winrate against class championship player in previous years: 0.6