The Integration of A Priori Knowledge into a Go Playing Neural Network
暂无分享,去创建一个
The best current computer Go programs are hand crafted expert systems. They are using conventional AI technics such as pattern matching, rule based systems and goal oriented selective search. Due to the increasing complexity of managing this kind of knowledge representation by hand, the playing strength of these programs is still far from human master level. This article describes methods for integrating expert Go knowledge into a learning artiicial neural network. These methods are implemented in the program NeuroGo. The network learns by playing against itself using temporal diierence learning and backpropagation. The expert knowledge that is implemented at present in NeuroGo is simple compared with a conventional computer Go program. Despite of this, NeuroGo is able to achieve a playing strength which is equal to a conventional program playing at a medium level.
[1] David B. Benson,et al. Life in the game of Go , 1976 .
[2] Terrence J. Sejnowski,et al. Temporal Difference Learning of Position Evaluation in the Game of Go , 1993, NIPS.
[3] Martin Müller,et al. Computer go as a sum of local games: an application of combinatorial game theory , 1995 .