LEADER 02356nam  2200565 a 450 
001 9910791345303321
005 20230725015506.0
010   $a1-282-63390-2
010   $a9786612633904
010   $a90-485-1230-1
035   $a(CKB)2560000000011872
035   $a(EBL)542537
035   $a(OCoLC)645097316
035   $a(SSID)ssj0000430499
035   $a(PQKBManifestationID)12140200
035   $a(PQKBTitleCode)TC0000430499
035   $a(PQKBWorkID)10456155
035   $a(PQKB)10812368
035   $a(MiAaPQ)EBC542537
035   $a(Au-PeEL)EBL542537
035   $a(CaPaEBR)ebr10397498
035   $a(CaONFJC)MIL263390
035   $a(EXLCZ)992560000000011872
100   $a20100730d2010      uy             0
101 0 $aeng
135   $aur|n|---|||||
181   $ctxt
182   $cc
183   $acr
200 10$aValue-based planning for teams of agents in stochastic partially observable environments$b[electronic resource] /$fdoor Frans Adriaan Oliehoek
210   $a[Amsterdam] $cAmsterdam University Press$d2010
215   $a1 online resource (222 p.)
225 1 $aUvA proefschriften
300   $aDescription based upon print version of record.
311   $a90-5629-610-8 
320   $aIncludes bibliographical references (p. 197-211).
327   $aIntroduction; 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; Acknowledgments
330   $aIn this thesis decision-making problems are formalized using a stochastic discrete-time model called decentralized partially observable Markov decision process (Dec-POMDP).
410  0$aUvA proefschriften
606   $aMathematics
615  0$aMathematics.
676   $a510
700   $aOliehoek$b Frans A$0950734
801  0$bMiAaPQ
801  1$bMiAaPQ
801  2$bMiAaPQ
906   $aBOOK
912   $a9910791345303321
996   $aValue-based planning for teams of agents in stochastic partially observable environments$93782200
997   $aUNINA