Proposal of PSwithEFP and its Evaluation in Multi-Agent Reinforcement Learning
- 20 September 2017
- journal article
- Published by Fuji Technology Press Ltd. in Journal of Advanced Computational Intelligence and Intelligent Informatics
- Vol. 21 (5), 930-938
- https://doi.org/10.20965/jaciii.2017.p0930
Abstract
When multiple agents learn a task simultaneously in an environment, the learning results often become unstable. This problem is known as the concurrent learning problem and to date, several methods have been proposed to resolve it. In this paper, we propose a new method that incorporates expected failure probability (EFP) into the action selection strategy to give agents a kind of mutual adaptability. The effectiveness of the proposed method is confirmed using Keepaway task.Keywords
This publication has 20 references indexed in Scilit:
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Introduction of Fixed Mode States into Online Reinforcement Learning with Penalties and Rewards and its Application to Biped Robot Waist Trajectory GenerationJournal of Advanced Computational Intelligence and Intelligent Informatics, 2012
- Proposal and Evaluation of the Active Course Classification Support System with Exploitation-Oriented LearningLecture Notes in Computer Science, 2012
- Acquiring a Government Bond Trading Strategy Using Reinforcement LearningJournal of Advanced Computational Intelligence and Intelligent Informatics, 2009
- A New Improved Penalty Avoiding Rational Policy Making Algorithm for Keepaway with Continuous State SpacesJournal of Advanced Computational Intelligence and Intelligent Informatics, 2009
- Motivated reinforcement learning for adaptive characters in open-ended simulation gamesPublished by Association for Computing Machinery (ACM) ,2007
- Experimental Analysis of Reward Design for Continuing Task in Multiagent Domains -- RoboCup Soccer Keepaway --Transactions of the Japanese Society for Artificial Intelligence, 2006
- Reinforcement Learning for RoboCup Soccer KeepawayAdaptive Behavior, 2005
- Acrobot control by learning the switching of multiple controllersArtificial Life and Robotics, 2005
- Reinforcement Learning: An IntroductionIEEE Transactions on Neural Networks, 1998