[Updated on Apr. 18] Integration of CiNii Articles into CiNii Research


Bibliographic Information

Other Title
  • Learning Weights of Training Data by Game Results

Search this article



Recently, machine learning is attracting much attention in the field of game programming, and it has succeeded in tuning evaluation functions, search depth, playout policies in Monte-Carlo Tree Search, etc. Existing machine learning methods in game programming tune parameters by using game records of human expert players. However, computer programs have almost the same strength as human professional players in some games such as shogi. Thus, learning by simply using human records is not necessarily good for generating strong computer players. In this paper, we propose a new learning method that estimates the importance of each training record by playing many games and tunes parameters according to the importance. The experimental results show the effectiveness of our method for learning evaluation functions, realization probability search, and playout policies. Moreover, the results show that features of training data such as progress of games or tactics affects their importance.


  • 情報処理学会論文誌

    情報処理学会論文誌 55 (11), 2399-2409, 2014-11-15

    Information Processing Society of Japan (IPSJ)


Report a problem

Back to top