Residual Networks for Computer Go

Improved Policy Networks for Computer Go

Golois uses residual policy networks to play Go. Two improvements to these residual policy networks are proposed and tested. The first one is to use three output planes. The second one is to add Spatial Batch Normalization.

Multi-Labelled Value Networks for Computer Go

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, ...

Computer Go

Computer Go is one of the biggest challenges faced by game programmers. This survey describes the typical components of a Go program, and discusses knowledge representation, search methods and techniques for solving specific subproblems in this domain. Along with a summary of the development of computer Go in recent years, areas for future research are pointed out.  2002 Elsevier Science B.V. ...

Computer Go

Residual Networks of Residual Networks: Multilevel Residual Networks

A residual-networks family with hundreds or even thousands of layers dominates major image recognition tasks, but building a network by simply stacking residual blocks inevitably limits its optimization ability. This paper proposes a novel residual-network architecture, Residual networks of Residual networks (RoR), to dig the optimization ability of residual networks. RoR substitutes optimizing...