Multi-Labelled Value Networks for Computer Go

TL;DR

This paper introduces a multi-labelled value network architecture for Go that trains multiple win rate values for different komi settings, supporting dynamic komi and improving game-playing strength, especially in handicap games.

Contribution

It presents a novel multi-labelled value network architecture and a dynamic komi method, enhancing Go AI performance and enabling handicap game play.

Findings

Lower mean squared error compared to traditional value networks

67.6% win rate against baseline programs

Significant improvement in handicap game strength with dynamic komi

Abstract

This paper proposes a new approach to a novel value network architecture for the game Go, called a multi-labelled (ML) value network. In the ML value network, different values (win rates) are trained simultaneously for different settings of komi, a compensation given to balance the initiative of playing first. The ML value network has three advantages, (a) it outputs values for different komi, (b) it supports dynamic komi, and (c) it lowers the mean squared error (MSE). This paper also proposes a new dynamic komi method to improve game-playing strength. This paper also performs experiments to demonstrate the merits of the architecture. First, the MSE of the ML value network is generally lower than the value network alone. Second, the program based on the ML value network wins by a rate of 67.6% against the program based on the value network alone. Third, the program with the proposed dynamic komi method significantly improves the playing strength over the baseline that does not use dynamic komi, especially for handicap games. To our knowledge, up to date, no handicap games have been played openly by programs using value networks. This paper provides these programs with a useful approach to playing handicap games.