Abstract/Details

Scalable cooperative multiagent reinforcement learning in the context of an organization


2006 2006

Other formats: Order a copy

Abstract (summary)

Reinforcement learning techniques have been successfully used to solve single agent optimization problems but many of the real problems involve multiple agents, or multi-agent systems. This explains the growing interest in multi-agent reinforcement learning algorithms, or MARL. To be applicable in large real domains, MARL algorithms need to be both stable and scalable. A scalable MARL will be able to perform adequately as the number of agents increases. A MARL algorithm is stable if all agents (eventually) converge to a stable joint policy. Unfortunately, most of the previous approaches lack at least one of these two crucial properties.

This dissertation proposes a scalable and stable MARL framework using a network of mediator agents. The network connections restrict the space of valid policies, which reduces the search time and achieves scalability. Optimizing performance in such a system consists of optimizing two subproblems: optimizing mediators' local policies and optimizing the structure of the network interconnecting mediators and servers. I present extensions to Markovian models that allow exponential savings in time and space. I also present the first integrated framework for MARL in a network, which includes both a MARL algorithm and a reorganization algorithm that work concurrently with one another. To evaluate performance, I use the distributed task allocation problem as a motivating domain.

Indexing (details)


Subject
Computer science
Classification
0984: Computer science
Identifier / keyword
Applied sciences; Cooperative; Multiagent; Organization; Reinforcement learning; Scalable
Title
Scalable cooperative multiagent reinforcement learning in the context of an organization
Author
Abdallah, Sherief
Number of pages
187
Publication year
2006
Degree date
2006
School code
0118
Source
DAI-B 67/11, Dissertation Abstracts International
Place of publication
Ann Arbor
Country of publication
United States
ISBN
9780542977657
Advisor
Lesser, Victor
University/institution
University of Massachusetts Amherst
University location
United States -- Massachusetts
Degree
Ph.D.
Source type
Dissertations & Theses
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
3242334
ProQuest document ID
305303100
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Document URL
http://search.proquest.com/docview/305303100
Access the complete full text

You can get the full text of this document if it is part of your institution's ProQuest subscription.

Try one of the following:

  • Connect to ProQuest through your library network and search for the document from there.
  • Request the document from your library.
  • Go to the ProQuest login page and enter a ProQuest or My Research username / password.