MIT Libraries homeMIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • Singapore-MIT Alliance (SMA)
  • Computer Science (CS)
  • View Item
  • DSpace@MIT Home
  • Singapore-MIT Alliance (SMA)
  • Computer Science (CS)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

All learning is local: Multi-agent learning in global reward games

Author(s)
Chang, Yu-Han; Ho, Tracey; Kaelbling, Leslie P.
Thumbnail
DownloadCS004.pdf (1.343Mb)
Metadata
Show full item record
Abstract
In large multiagent games, partial observability, coordination, and credit assignment persistently plague attempts to design good learning algorithms. We provide a simple and efficient algorithm that in part uses a linear system to model the world from a single agent’s limited perspective, and takes advantage of Kalman filtering to allow an agent to construct a good training signal and effectively learn a near-optimal policy in a wide variety of settings. A sequence of increasingly complex empirical tests verifies the efficacy of this technique.
Date issued
2004-01
URI
http://hdl.handle.net/1721.1/3851
Series/Report no.
Computer Science (CS);
Keywords
Kalman filtering, multi-agent systems, Q-learning, reinforcement learning

Collections
  • Computer Science (CS)

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries homeMIT Libraries logo

Find us on

Twitter Facebook Instagram YouTube RSS

MIT Libraries navigation

SearchHours & locationsBorrow & requestResearch supportAbout us
PrivacyPermissionsAccessibility
MIT
Massachusetts Institute of Technology
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.