Error-Bounded Approximations for Infinite-Horizon Discounted Decentralized POMDPs - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Error-Bounded Approximations for Infinite-Horizon Discounted Decentralized POMDPs

Résumé

We address decentralized stochastic control problems represented as decentralized partially observable Markov decision processes (Dec-POMDPs). This formalism provides a general model for decision-making under uncertainty in cooperative, decentralized settings, but the worst-case complexity makes it difficult to solve optimally (NEXP-complete). Recent advances suggest recasting Dec-POMDPs into continuous-state and deterministic MDPs. In this form, however, states and actions are embedded into high-dimensional spaces, making accurate estimate of states and greedy selection of actions intractable for all but trivial-sized problems. The primary contribution of this paper is the first framework for error-monitoring during approximate estimation of states and selection of actions. Such a framework permits us to convert state-of-the-art exact methods into error-bounded algorithms, which results in a scalability increase as demonstrated by experiments over problems of unprecedented sizes.
Fichier principal
Vignette du fichier
ecml14.pdf (155.26 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01096610 , version 1 (17-12-2014)

Identifiants

Citer

Jilles Steeve Dibangoye, Olivier Buffet, François Charpillet. Error-Bounded Approximations for Infinite-Horizon Discounted Decentralized POMDPs. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), Sep 2014, Nancy, France. pp.338 - 353, ⟨10.1007/978-3-662-44848-9_22⟩. ⟨hal-01096610⟩
142 Consultations
333 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More