|
|
|
|
|
|
|
|
1. |
Record Nr. |
UNINA9910827023303321 |
|
|
Autore |
Oliehoek Frans A |
|
|
Titolo |
Value-based planning for teams of agents in stochastic partially observable environments [[electronic resource] /] / door Frans Adriaan Oliehoek |
|
|
|
|
|
|
|
Pubbl/distr/stampa |
|
|
[Amsterdam], : Amsterdam University Press, 2010 |
|
|
|
|
|
|
|
ISBN |
|
1-282-63390-2 |
9786612633904 |
90-485-1230-1 |
|
|
|
|
|
|
|
|
Descrizione fisica |
|
1 online resource (222 p.) |
|
|
|
|
|
|
Collana |
|
|
|
|
|
|
Disciplina |
|
|
|
|
|
|
Soggetti |
|
|
|
|
|
|
Lingua di pubblicazione |
|
|
|
|
|
|
Formato |
Materiale a stampa |
|
|
|
|
|
Livello bibliografico |
Monografia |
|
|
|
|
|
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). |
|
|
|
|
|
|
|