02356nam 2200565 a 450 991079134530332120230725015506.01-282-63390-2978661263390490-485-1230-1(CKB)2560000000011872(EBL)542537(OCoLC)645097316(SSID)ssj0000430499(PQKBManifestationID)12140200(PQKBTitleCode)TC0000430499(PQKBWorkID)10456155(PQKB)10812368(MiAaPQ)EBC542537(Au-PeEL)EBL542537(CaPaEBR)ebr10397498(CaONFJC)MIL263390(EXLCZ)99256000000001187220100730d2010 uy 0engur|n|---|||||txtccrValue-based planning for teams of agents in stochastic partially observable environments[electronic resource] /door Frans Adriaan Oliehoek[Amsterdam] Amsterdam University Press20101 online resource (222 p.)UvA proefschriftenDescription based upon print version of record.90-5629-610-8 Includes bibliographical references (p. 197-211).Introduction; Decision-Theoretic Planning for Teams of Agents; Optimal Value Functions for Dec-POMDPs; Approximate Value Functions & Heuristic Policy Search; Factored Dec-POMDPs: Exploiting Locality of Interaction; Lossless Clustering of Histories; Conclusions and Discussion; Summary; Samenvatting; Problem Specifications; Immediate Reward Value Function Formulations; Formalization of Regression to Factored Q-Value Functions; Proofs; Bibliography; AcknowledgmentsIn this thesis decision-making problems are formalized using a stochastic discrete-time model called decentralized partially observable Markov decision process (Dec-POMDP).UvA proefschriftenMathematicsMathematics.510Oliehoek Frans A950734MiAaPQMiAaPQMiAaPQBOOK9910791345303321Value-based planning for teams of agents in stochastic partially observable environments3782200UNINA