Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/77955
DC FieldValue
dc.titleA general framework for interacting Bayes-optimally with self-interested agents using arbitrary parametric model and model prior
dc.contributor.authorHoang, T.N.
dc.contributor.authorLow, K.H.
dc.date.accessioned2014-07-04T03:10:47Z
dc.date.available2014-07-04T03:10:47Z
dc.date.issued2013
dc.identifier.citationHoang, T.N.,Low, K.H. (2013). A general framework for interacting Bayes-optimally with self-interested agents using arbitrary parametric model and model prior. IJCAI International Joint Conference on Artificial Intelligence : 1394-1400. ScholarBank@NUS Repository.
dc.identifier.isbn9781577356332
dc.identifier.issn10450823
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/77955
dc.description.abstractRecent advances in Bayesian reinforcement learning (BRL) have shown that Bayes-optimality is theoretically achievable by modeling the environment's latent dynamics using Flat-Dirichlet- Multinomial (FDM) prior. In self-interested multiagent environments, the transition dynamics are mainly controlled by the other agent's stochastic behavior for which FDM's independence and modeling assumptions do not hold. As a result, FDM does not allow the other agent's behavior to be generalized across different states nor specified using prior domain knowledge. To overcome these practical limitations of FDM, we propose a generalization of BRL to integrate the general class of parametric models and model priors, thus allowing practitioners' domain knowledge to be exploited to produce a fine-grained and compact representation of the other agent's behavior. Empirical evaluation shows that our approach outperforms existing multi-agent reinforcement learning algorithms.
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.sourcetitleIJCAI International Joint Conference on Artificial Intelligence
dc.description.page1394-1400
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Page view(s)

66
checked on Nov 24, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.