• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Tao, Junyuan (Tao, Junyuan.) | Li, Desheng (Li, Desheng.) (Scholars:李德胜)

Indexed by:

EI Scopus

Abstract:

RoboCup offers a set of challenges for machine learning researchers because it is a dynamic, nondeterministic, goal delayed and continuous state space problem. Reinforcement learning (RL) is often used for strategy learning in RoboCup, which is a method to learn an optimal control policy for sequential decision-making problems. But it is difficult to apply RL to continuous state space problems because of the exponential growth of states in the number of state variables. An effective method is to combine RL with function approximation. However, this combination sometimes leads to diverge. In this paper, we analyze the main reason that cause the non-convergent of the current approximation RL algorithms and propose an optimal strategy learning method. The two processes - value evaluation and policy improvement in RL have been separated. Policy search process is controlled strictly in the direction of improving performance according the evaluation value provided by the value function. And we apply this algorithm to a standard RoboCup sub-problem-Keepaway successfully. Experiment result has verified the effective of the method and showed the algorithm could converge to a local optimal policy. ©2006 IEEE.

Keyword:

Learning algorithms Problem solving State space methods Reinforcement learning Robotics Function evaluation Decision making

Author Community:

  • [ 1 ] [Tao, Junyuan]Department of Automatic Measurement and Control, Harbin Institute of Technology, Harbin, Heilongjiang Province, China
  • [ 2 ] [Li, Desheng]Department of Mechanical and Electronic Engineering, Beijing University of Technology, Beijing, China

Reprint Author's Address:

Show more details

Related Keywords:

Related Article:

Source :

Year: 2006

Volume: 2006

Page: 301-305

Language: English

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count: 2

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 2

Online/Total:645/5427590
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.