Author name cluster

Shogo Takeuchi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAAI Conference 2013 Conference Paper

Optimizing Objective Function Parameters for Strength in Computer Game-Playing

Yoshikuni Sato
Makoto Miwa
Shogo Takeuchi
Daisuke Takahashi

The learning of evaluation functions from game records has been widely studied in the ﬁeld of computer game-playing. Conventional learning methods optimize the evaluation function parameters by using the game records of expert players in order to imitate their plays. Such conventional methods utilize objective functions to increase the agreement between the moves selected by game-playing programs and the moves in the records of actual games. The methods, however, have a problem in that increasing the agreement does not always improve the strength of a program. Indeed, it is not clear how this agreement relates to the strength of a trained program. To address this problem, this paper presents a learning method to optimize objective function parameters for strength in game-playing. The proposed method employs an evolutionary learning algorithm with the strengths (Elo ratings) of programs as their ﬁtness scores. Experimental results show that the proposed method is effective since programs using the objective function produced by the proposed method are superior to those using conventional objective functions.

PDF Details

AAAI Conference 2007 Conference Paper

Visualization and Adjustment of Evaluation Functions Based on Evaluation Values and Win Probability

Shogo Takeuchi
Kazunori Yamaguchi

We present a method of visualizing and adjusting the evaluation functions in game programming in this paper. It is widely recognized that an evaluation function should assign a higher evaluation value to a position with greater probability of a win. However, this relation has not been utilized directly to tune evaluation functions because of the difﬁculty of measuring the probability of wins in deterministic games. We present the use of win percentage to utilize this relation in positions having the same evaluation value as win probability, where the positions we used were stored in a large database of game records. We introduce an evaluation curve formed by evaluation values and win probabilities, to enable evaluation functions to be visualized. We observed that evaluation curves form a sigmoid in various kinds of games and that these curves may split depending on the properties of positions. Because such splits indicate that an evaluation function that is visualized misestimates positions with less probability of winning, we can improve this by ﬁtting evaluation curves to one. Our experiments with Chess and Shogi revealed that deﬁciencies in evaluation functions could be successfully visualized, and that improvements by automatically adjusting their weights were conﬁrmed by self-plays.

PDF Details