Multiagent Reinforcement Learning with Regret Matching for Robot Soccer
Joint Authors
Source
Mathematical Problems in Engineering
Issue
Vol. 2013, Issue 2013 (31 Dec. 2013), pp.1-8, 8 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2013-09-09
Country of Publication
Egypt
No. of Pages
8
Main Subjects
Abstract EN
This paper proposes a novel multiagent reinforcement learning (MARL) algorithm Nash-Q learning with regret matching, in which regret matching is used to speed up the well-known MARL algorithm Nash-Q learning.
It is critical that choosing a suitable strategy for action selection to harmonize the relation between exploration and exploitation to enhance the ability of online learning for Nash-Q learning.
In Markov Game the joint action of agents adopting regret matching algorithm can converge to a group of points of no-regret that can be viewed as coarse correlated equilibrium which includes Nash equilibrium in essence.
It is can be inferred that regret matching can guide exploration of the state-action space so that the rate of convergence of Nash-Q learning algorithm can be increased.
Simulation results on robot soccer validate that compared to original Nash-Q learning algorithm, the use of regret matching during the learning phase of Nash-Q learning has excellent ability of online learning and results in significant performance in terms of scores, average reward and policy convergence.
American Psychological Association (APA)
Liu, Qiang& Ma, Jiachen& Xie, Wei. 2013. Multiagent Reinforcement Learning with Regret Matching for Robot Soccer. Mathematical Problems in Engineering،Vol. 2013, no. 2013, pp.1-8.
https://search.emarefa.net/detail/BIM-1011183
Modern Language Association (MLA)
Liu, Qiang…[et al.]. Multiagent Reinforcement Learning with Regret Matching for Robot Soccer. Mathematical Problems in Engineering No. 2013 (2013), pp.1-8.
https://search.emarefa.net/detail/BIM-1011183
American Medical Association (AMA)
Liu, Qiang& Ma, Jiachen& Xie, Wei. Multiagent Reinforcement Learning with Regret Matching for Robot Soccer. Mathematical Problems in Engineering. 2013. Vol. 2013, no. 2013, pp.1-8.
https://search.emarefa.net/detail/BIM-1011183
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1011183