Maintaining System State Information in a Multiagent Environment for Effective Learning

11 References
  • CHEN Gang
    Information Communication Institute of Singapore, School of Electrical and Electronic Engineering, Nanyang Technological University
  • YANG Zhonghua
    Information Communication Institute of Singapore, School of Electrical and Electronic Engineering, Nanyang Technological University
  • HE Hao
    Singapore Institute of Manufacturing Technology
  • GOH Kiah-Mok
    Singapore Institute of Manufacturing Technology

Search this article

Description

One fundamental issue in multiagent reinforcement learning is how to deal with the limited local knowledge of an agent in order to achieve effective learning. In this paper, we argue that this issue can be more effectively solved if agents are equipped with a consistent global view. We achieve this by requiring agents to follow an interacting protocol. The properties of the protocol are derived and theoretically analyzed. A distributed protocol that satisfies these properties is presented. The experimental evaluations are conducted for a well-known test-case (i. e., pursuit game) in the context of two learning algorithms. The results show that the protocol is effective and the reinforcement learning algorithms using it perform much better.

Journal

References(11)*help

See more

Keywords

Details 詳細情報について

  • CRID
    1572543027349073664
  • NII Article ID
    110003214145
  • NII Book ID
    AA10826272
  • ISSN
    09168532
  • Text Lang
    en
  • Data Source
    • CiNii Articles

Report a problem

Back to top