Skip to main content
SpringerLink
Log in

Sample Efficient Multiagent Learning in the Presence of Markovian Agents

  • Book
  • © 2014

Overview

Authors:
  1. Doran Chakraborty

    1. Department of Computer Science, The University of Texas at Austin, Austin, USA

    View author publications

    You can also search for this author in PubMed   Google Scholar

  • Presents recent research in sample efficient multiagent learning in the presence of markovian agents
  • Develops multiagent learning algorithms not previously been achieved
  • Takes steps towards building completely autonomous learning algorithms

Part of the book series: Studies in Computational Intelligence (SCI, volume 523)

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

Access this book

Log in via an institution
eBook USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

Licence this eBook for your library

Institutional subscriptions

Table of contents (9 chapters)

  1. Front Matter

    Pages 1-12
    Download chapter PDF

  2. Introduction

    • Doran Chakraborty
    Pages 1-5

  3. Background

    • Doran Chakraborty
    Pages 7-17

  4. Learn or Exploit in Adversary Induced Markov Decision Processes

    • Doran Chakraborty
    Pages 19-28

  5. Convergence, Targeted Optimality and Safety in Multiagent Learning

    • Doran Chakraborty
    Pages 29-47

  6. Maximizing Social Welfare in the Presence of Markovian Agents

    • Doran Chakraborty
    Pages 49-71

  7. Targeted Modeling of Markovian Agents

    • Doran Chakraborty
    Pages 73-97

  8. Structure Learning in Factored MDPs

    • Doran Chakraborty
    Pages 99-111

  9. Related Work

    • Doran Chakraborty
    Pages 113-123

  10. Conclusion and Future Work

    • Doran Chakraborty
    Pages 125-129

  11. Back Matter

    Pages 131-146
    Download chapter PDF
Back to top

Keywords

About this book

The problem of Multiagent Learning (or MAL) is concerned with the study of how intelligent entities can learn and adapt in the presence of other such entities that are simultaneously adapting. The problem is often studied in the stylized settings provided by repeated matrix games (a.k.a. normal form games). The goal of this book is to develop MAL algorithms for such a setting that achieve a new set of objectives which have not been previously achieved. In particular this book deals with learning in the presence of a new class of agent behavior that has not been studied or modeled before in a MAL context: Markovian agent behavior. Several new challenges arise when interacting with this particular class of agents. The book takes a series of steps towards building completely autonomous learning algorithms that maximize utility while interacting with such agents. Each algorithm is meticulously specified with a thorough formal treatment that elucidates its key theoretical properties.

Reviews

From the book reviews:

“The book presents the PhD findings of the author in the field of multiagent learning. … All the concepts are thoroughly described and accompanied by theoretical analysis and empirical testing. A book suitable for researchers working in multiagent learning and game theory.” (Ruxandra Stoean, zbMATH, Vol. 1288, 2014)

Authors and Affiliations

  • Department of Computer Science, The University of Texas at Austin, Austin, USA

    Doran Chakraborty

Bibliographic Information

  • Book Title: Sample Efficient Multiagent Learning in the Presence of Markovian Agents

  • Authors: Doran Chakraborty

  • Series Title: Studies in Computational Intelligence

  • DOI: https://doi.org/10.1007/978-3-319-02606-0

  • Publisher: Springer Cham

  • eBook Packages: Engineering, Engineering (R0)

  • Copyright Information: Springer International Publishing Switzerland 2014

  • Hardcover ISBN: 978-3-319-02605-3Published: 11 October 2013

  • Softcover ISBN: 978-3-319-35293-0Published: 23 August 2016

  • eBook ISBN: 978-3-319-02606-0Published: 30 September 2013

  • Series ISSN: 1860-949X

  • Series E-ISSN: 1860-9503

  • Edition Number: 1

  • Number of Pages: XVIII, 147

  • Number of Illustrations: 31 b/w illustrations

  • Topics: Computational Intelligence, Artificial Intelligence

Publish with us

Policies and ethics

Back to top

Search

Navigation