Predicting the Expected Behavior of Agents that Learn About Agents: The CLRI Framework
dc.contributor.author | Vidal, José M. | en_US |
dc.contributor.author | Durfee, Edmund H. | en_US |
dc.date.accessioned | 2006-09-11T14:10:20Z | |
dc.date.available | 2006-09-11T14:10:20Z | |
dc.date.issued | 2003-01 | en_US |
dc.identifier.citation | Vidal, José M.; Durfee, Edmund H.; (2003). "Predicting the Expected Behavior of Agents that Learn About Agents: The CLRI Framework." Autonomous Agents and Multi-Agent Systems 6(1): 77-107. <http://hdl.handle.net/2027.42/44021> | en_US |
dc.identifier.issn | 1387-2532 | en_US |
dc.identifier.issn | 1573-7454 | en_US |
dc.identifier.uri | https://hdl.handle.net/2027.42/44021 | |
dc.description.abstract | We describe a framework and equations used to model and predict the behavior of multi-agent systems (MASs) with learning agents. A difference equation is used for calculating the progression of an agent's error in its decision function, thereby telling us how the agent is expected to fare in the MAS. The equation relies on parameters which capture the agent's learning abilities, such as its change rate, learning rate and retention rate, as well as relevant aspects of the MAS such as the impact that agents have on each other. We validate the framework with experimental results using reinforcement learning agents in a market system, as well as with other experimental results gathered from the AI literature. Finally, we use PAC-theory to show how to calculate bounds on the values of the learning parameters. | en_US |
dc.format.extent | 261242 bytes | |
dc.format.extent | 3115 bytes | |
dc.format.mimetype | application/pdf | |
dc.format.mimetype | text/plain | |
dc.language.iso | en_US | |
dc.publisher | Kluwer Academic Publishers; Springer Science+Business Media | en_US |
dc.subject.other | Computer Science | en_US |
dc.subject.other | Software Engineering/Programming and Operating Systems | en_US |
dc.subject.other | Data Structures, Cryptology and Information Theory | en_US |
dc.subject.other | User Interfaces and Human Computer Interaction | en_US |
dc.subject.other | Artificial Intelligence (Incl. Robotics) | en_US |
dc.subject.other | Multi-agent Systems | en_US |
dc.subject.other | Machine Learning | en_US |
dc.subject.other | Complex Systems | en_US |
dc.title | Predicting the Expected Behavior of Agents that Learn About Agents: The CLRI Framework | en_US |
dc.type | Article | en_US |
dc.subject.hlbsecondlevel | Computer Science | en_US |
dc.subject.hlbsecondlevel | Philosophy | en_US |
dc.subject.hlbtoplevel | Engineering | en_US |
dc.subject.hlbtoplevel | Humanities | en_US |
dc.description.peerreviewed | Peer Reviewed | en_US |
dc.contributor.affiliationum | Advanced Technology Laboratory, University of Michigan, Ann Arbor, MI, 48102 | en_US |
dc.contributor.affiliationother | Swearingen Engineering Center, University of South Carolina, Columbia, SC, 29208 | en_US |
dc.contributor.affiliationumcampus | Ann Arbor | en_US |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/44021/1/10458_2004_Article_5109060.pdf | en_US |
dc.identifier.doi | http://dx.doi.org/10.1023/A:1021765422660 | en_US |
dc.identifier.source | Autonomous Agents and Multi-Agent Systems | en_US |
dc.owningcollname | Interdisciplinary and Peer-Reviewed |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.