Search
2006 Volume 21
Article Contents
RESEARCH ARTICLE   Open Access    

Building autonomic systems using collaborative reinforcement learning

More Information
  • This paper presents Collaborative Reinforcement Learning (CRL), a coordination model for online system optimization in decentralized multi-agent systems. In CRL system optimization problems are represented as a set of discrete optimization problems, each of whose solution cost is minimized by model-based reinforcement learning agents collaborating on their solution. CRL systems can be built to provide autonomic behaviours such as optimizing system performance in an unpredictable environment and adaptation to partial failures. We evaluate CRL using an ad hoc routing protocol that optimizes system routing performance in an unpredictable network environment.
  • 加载中
  • Cite this article

    JIM DOWLING, RAYMOND CUNNINGHAM, EOIN CURRAN, VINNY CAHILL. 2006. Building autonomic systems using collaborative reinforcement learning. The Knowledge Engineering Review. 21:56 doi: 10.1017/S0269888906000956
    JIM DOWLING, RAYMOND CUNNINGHAM, EOIN CURRAN, VINNY CAHILL. 2006. Building autonomic systems using collaborative reinforcement learning. The Knowledge Engineering Review. 21:56 doi: 10.1017/S0269888906000956

Article Metrics

Article views(17) PDF downloads(86)

RESEARCH ARTICLE   Open Access    

Building autonomic systems using collaborative reinforcement learning

The Knowledge Engineering Review  21 Article number: 10.1017/S0269888906000956  (2006)  |  Cite this article

Abstract: This paper presents Collaborative Reinforcement Learning (CRL), a coordination model for online system optimization in decentralized multi-agent systems. In CRL system optimization problems are represented as a set of discrete optimization problems, each of whose solution cost is minimized by model-based reinforcement learning agents collaborating on their solution. CRL systems can be built to provide autonomic behaviours such as optimizing system performance in an unpredictable environment and adaptation to partial failures. We evaluate CRL using an ad hoc routing protocol that optimizes system routing performance in an unpredictable network environment.

    • © 2006 Cambridge University Press
  • About this article
    Cite this article
    JIM DOWLING, RAYMOND CUNNINGHAM, EOIN CURRAN, VINNY CAHILL. 2006. Building autonomic systems using collaborative reinforcement learning. The Knowledge Engineering Review. 21:56 doi: 10.1017/S0269888906000956
    JIM DOWLING, RAYMOND CUNNINGHAM, EOIN CURRAN, VINNY CAHILL. 2006. Building autonomic systems using collaborative reinforcement learning. The Knowledge Engineering Review. 21:56 doi: 10.1017/S0269888906000956
  • Catalog

      /

      DownLoad:  Full-Size Img  PowerPoint
      Return
      Return