%0 Journal Article
%T Study of Temporal Difference Learning in Computer Games<br>面向机器博弈的即时差分学习研究
%A XU Chang-ming
%A MA Zong-min
%A XU Xin-he
%A LI Xin-xing
%A <br>徐长明
%A 马宗民
%A 徐心和
%A 李新星
%J 计算机科学
%D 2010
%I 
%X Temporal Difference (Abbr. TD) learning algorithm was used to adjust weights of evaluation function by using Connect6 game as testbed in this paper,which makes the weights adjustment process can be done automatically. A new evaluation scheme was proposed,which can solve the difficult to combine the prior knowledge and multi-layer neural network organically. On account of the specific application,the method selecting part of the whole TD sectuence to learn was proposed, by which the interference of useless states is prevented to a certain extent. After 10020 self-learning training, the winning rate is increased with 8 % around against the same Connect6-playing program, which is a good result.
%K Computer games
%K Temporal difference learning
%K Connect6<br>机器博弈
%K 即时差分学习
%K 六子棋
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=64A12D73428C8B8DBFB978D04DFEB3C1&aid=4A10AC9363E3CB6949310619DAE318DB&yid=140ECF96957D60B2&vid=42425781F0B1C26E&iid=5D311CA918CA9A03&sid=D5C73DEF4CF8FAF3&eid=E089FDF3CDAE8561&journal_id=1002-137X&journal_name=计算机科学&referenced_num=0&reference_num=15