Experimental Analysis of Reward Design for Continuing Task in Multiagent Domains -- RoboCup Soccer Keepaway ---Reference-Cited by-同舟云学术

Experimental Analysis of Reward Design for Continuing Task in Multiagent Domains -- RoboCup Soccer Keepaway --

Published:2006 Issue:6 Volume:21 Page:537-546
ISSN:1346-0714
Container-title:Transactions of the Japanese Society for Artificial Intelligence
language:en
Short-container-title:Transactions of the Japanese Society for Artificial Intelligence

Author:

Arai Sachiyo¹,Tanaka Nobuyuki²

Affiliation:

1. Department of Urban Environmental Systems, Chiba University

2. Graduate School of Science and Technology, Chiba University

Publisher

Japanese Society for Artificial Intelligence

Subject

Artificial Intelligence,Software

Link

http://www.jstage.jst.go.jp/article/tjsai/21/6/21_6_537/_pdf

Reference17 articles.

1. [Kwee 01] Kwee, I., Hutter, M., and Schmidhuber, J.: Gradient-based Reinforcement Planning in Policy-Search Methods, Proceedings of the 5th European Workshop on Reinforcement Learning (EWRL-5), No. 27, pp. 27-29 (2001)

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Proposal of PSwithEFP and its Evaluation in Multi-Agent Reinforcement Learning;Journal of Advanced Computational Intelligence and Intelligent Informatics;2017-09-20

2. Proposal of an Action Selection Strategy with Expected Failure Probability and Its Evaluation in Multi-agent Reinforcement Learning;Multi-Agent Systems and Agreement Technologies;2017

3. Evaluation of the Improved Penalty Avoiding Rational Policy Making Algorithm in Real World Environment;Intelligent Information and Database Systems;2012

4. Designing and Evaluation of Mobile Robot using Optical Information .TAU.-margin;Journal of the Robotics Society of Japan;2010

5. A New Improved Penalty Avoiding Rational Policy Making Algorithm for Keepaway with Continuous State Spaces;Journal of Advanced Computational Intelligence and Intelligent Informatics;2009-11-20