Vai al contenuto principale della pagina

Value-based planning for teams of agents in stochastic partially observable environments [[electronic resource] /] / door Frans Adriaan Oliehoek



(Visualizza in formato marc)    (Visualizza in BIBFRAME)

Autore: Oliehoek Frans A Visualizza persona
Titolo: Value-based planning for teams of agents in stochastic partially observable environments [[electronic resource] /] / door Frans Adriaan Oliehoek Visualizza cluster
Pubblicazione: [Amsterdam], : Amsterdam University Press, 2010
Descrizione fisica: 1 online resource (222 p.)
Disciplina: 510
Soggetto topico: Mathematics
Note generali: Description based upon print version of record.
Nota di bibliografia: Includes bibliographical references (p. 197-211).
Nota di contenuto: 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; Acknowledgments
Sommario/riassunto: In this thesis decision-making problems are formalized using a stochastic discrete-time model called decentralized partially observable Markov decision process (Dec-POMDP).
Titolo autorizzato: Value-based planning for teams of agents in stochastic partially observable environments  Visualizza cluster
ISBN: 1-282-63390-2
9786612633904
90-485-1230-1
Formato: Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione: Inglese
Record Nr.: 9910827023303321
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Serie: UvA proefschriften