Skip to Main Content
 

Global Search Box

 
 
 
 

Files

ETD Abstract Container

Abstract Header

Approximate Action Selection For Large, Coordinating, Multiagent Systems

Sosnowski, Scott T

Abstract Details

2016, Master of Sciences, Case Western Reserve University, EECS - Computer and Information Sciences.
Many practical decision-making problems involve coordinating teams of agents. In our work, we focus on the problem of coordinated action selection in reinforcement learning with large stochastic multi-agent systems that are centrally controlled. Previous work has shown how to formulate coordination as exact inference in a Markov network, but this becomes intractable for large teams of agents. We investigate the idea of "approximate coordination" as a solution to an approximate inference problem in a Markov network. We look at a pursuit domain and a simplified real-time strategy game and find that in these situations, such approaches are able to find good policies when exact approaches become intractable.
Soumya Ray (Advisor)
Marc Buchner (Committee Member)
M. Cenk Çavusoglu (Committee Member)
Michael Lewicki (Committee Member)
120 p.

Recommended Citations

Citations

  • Sosnowski, S. T. (2016). Approximate Action Selection For Large, Coordinating, Multiagent Systems [Master's thesis, Case Western Reserve University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=case1459468867

    APA Style (7th edition)

  • Sosnowski, Scott. Approximate Action Selection For Large, Coordinating, Multiagent Systems. 2016. Case Western Reserve University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=case1459468867.

    MLA Style (8th edition)

  • Sosnowski, Scott. "Approximate Action Selection For Large, Coordinating, Multiagent Systems." Master's thesis, Case Western Reserve University, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=case1459468867

    Chicago Manual of Style (17th edition)