Skip to main content
Springer Nature Link
Log in

Parallel Distributed Profit Sharing for PC Cluster

  • Conference paper
Artificial Neural Networks – ICANN 2006 (ICANN 2006)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 4131))

Included in the following conference series:

  • 3419 Accesses

Abstract

This paper presents a parallel reinforcement learning method considered communication cost. In our method, each agent communicates only action sequences with a constant episode interval. As the communication interval is longer, communication cost is smaller, but parallelism is lower. Implementing our method on PC cluster, we investigate such trade-off characteristics. We show that computation time to learning can be reduced by properly adjusting the communication interval.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Kretchmar, R.M.: Parallel Reinforcement Learning. In: Proc. of the 6th World Conference on Systemics, Cybernetics and Informatics, vol. 6, pp. 114–118 (2002)

    Google Scholar 

  2. Antonova, D.: Parallel Reinforcement Learning - Extending the Concept to Continuous Multi-State Tasks., thesis, Denison University (2003)

    Google Scholar 

  3. Watkins, C.J.H., Dayan, P.: Technical note: Q-learning. Machine Learning 8, 55–68 (1992)

    Google Scholar 

  4. Grefenstette, J.J.: Credit Assignment in Rule Discovery Systems Based on Genetic Algorithms. Machine Learning 3, 225–245 (1988)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Musashi Institute of Technology, 1-28-1 Tamazutsumi, Setagayaku, Tokyo, 158-8557, Japan

    Takuya Fujishiro, Hidehiro Nakano & Arata Miyauchi

Authors
  1. Takuya Fujishiro
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hidehiro Nakano
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Arata Miyauchi
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. School of Electrical and Computer Engineering, Image, Video and Multimedia Systems Laboratory, National Technical University of Athens, GR-157 80, Zographou, Greece

    Stefanos D. Kollias

  2. Department of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zographou, Greece

    Andreas Stafylopatis

  3. Department of Informatics, Nicolaus Copernicus University, Toruń, Poland

    Włodzisław Duch

  4. Adaptive Informatics Research Centre, Helsinki University of Technology, HUT, P.O. Box 5400, 02015, Finland

    Erkki Oja

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Fujishiro, T., Nakano, H., Miyauchi, A. (2006). Parallel Distributed Profit Sharing for PC Cluster. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds) Artificial Neural Networks – ICANN 2006. ICANN 2006. Lecture Notes in Computer Science, vol 4131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11840817_84

Download citation

  • DOI: https://doi.org/10.1007/11840817_84

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-38625-4

  • Online ISBN: 978-3-540-38627-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics