%0 Journal Article
%T Polynomial Approximation Based Learning Search<br>基于函数逼近的学习式搜索
%A Zhang Wei
%A Liu Jiren
%A Li Huatian
%A <br>张伟
%A 刘积仁
%A 李华天
%J 自动化学报
%D 1994
%I 
%X In this paper, Polynomial Approximation method and theory are introduced into the research of Learning Search of Artificial Intelligence. In this way, we can use a search algorithm repeatedly to construct a heuristic estimate function h(·) which uniformly approximates to the optimal estimate function h*(·) with arbitrarily high precision. One of such learning setrch algorithms, A-Bn, is presented and it is shown that, when the number of training samples becomes large enough, the worst-case complexity of A-B, can be reduced to O(poly(N)), where N is the length of the optimal solution path, poly (N) is a polynomial of N.
%K Artificial Intelligence
%K Heuristic Search
%K Machine Learning
%K Complexity<br>人工智能
%K 函数逼近
%K 学习式搜索
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=CB2B11C6D51FE0C91822C8F3F0729E89&yid=3EBE383EEA0A6494&vid=A04140E723CB732E&iid=0B39A22176CE99FB&sid=6CCE24D86D03D083&eid=1DF3F9D75A12D97B&journal_id=0254-4156&journal_name=自动化学报&referenced_num=0&reference_num=3