Building Evaluation Functions for Chess and Shogi with Uniformity Regularization Networks.

Shanchuan Wan Tomoyuki Kaneko

Published in: CIG (2018)

Keyphrases

evaluation function
computer chess
human players
temporal difference
social networks
alpha beta
game tree search
heuristic function
iterative deepening
temporal difference learning
branching factor
two player games
network structure
td learning
monte carlo search
monte carlo tree search