skip to main content
10.1145/2184512.2184618acmconferencesArticle/Chapter ViewAbstractPublication Pagesacm-seConference Proceedingsconference-collections
poster

Intrinsically motivated exploration via intrinsic value calculation

Published: 29 March 2012 Publication History

Abstract

Intrinsically motivated exploration is an emerging topic in the area of exploration in reinforcement learning agents, and many authors have proposed methods of implementing intrinsically motivated (or curious) exploration paradigms. However, these implementations accomplish their exploration through the addition of an intrinsic reward to the existing reward which is received by the agent. The limitations of such intrinsic reward schemes are identified in this study and an alternative intrinsic value scheme is proposed which addresses these limitations.

References

[1]
J. Schmidhuber. Curious Model-Building control systems. In Proceedings of the International Joint Conference on Neural Networks, Singapore, volume 2, pages 1458--1463. IEEE press, 1991.
[2]
J. Schmidhuber. Simple algorithmic theory of subjective beauty, novelty, surprise, interestingness, attention, curiosity, creativity, art, science, music, jokes. SICE Journal of the Society of Instrument and Control Engineers, 48(1):21--32, 2009.
[3]
S. Singh, R. L. Lewis, A. G. Barto, and J. Sorg. Intrinsically motivated reinforcement learning: An evolutionary perspective. Autonomous Mental Development, IEEE Transactions on, 2(2):70--82, June 2010.

Index Terms

  1. Intrinsically motivated exploration via intrinsic value calculation

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    ACMSE '12: Proceedings of the 50th annual ACM Southeast Conference
    March 2012
    424 pages
    ISBN:9781450312035
    DOI:10.1145/2184512
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 29 March 2012

    Check for updates

    Author Tags

    1. curiosity
    2. intrinsic motivation
    3. reinforcement learning

    Qualifiers

    • Poster

    Conference

    ACM SE '12
    Sponsor:
    ACM SE '12: ACM Southeast Regional Conference
    March 29 - 31, 2012
    Alabama, Tuscaloosa

    Acceptance Rates

    ACMSE '12 Paper Acceptance Rate 28 of 56 submissions, 50%;
    Overall Acceptance Rate 502 of 1,023 submissions, 49%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 111
      Total Downloads
    • Downloads (Last 12 months)2
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 09 Jan 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media