Exploiting Separability in Multiagent Planning with Continuous-State MDPs

Jilles Steeve Dibangoye 1, * Christopher Amato 2 Olivier Buffet 1, * François Charpillet 1
* Auteur correspondant
1 MAIA - Autonomous intelligent machine
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : Recent years have seen significant advances in techniques for optimally solving multiagent problems represented as decentralized partially observable Markov decision processes (Dec-POMDPs). A new method achieves scalability gains by converting Dec-POMDPs into continuous state MDPs. This method relies on the assumption of a centralized planning phase that generates a set of decentralized policies for the agents to execute. However, scalability remains limited when the number of agents or problem variables becomes large. In this paper, we show that, under certain separability conditions of the optimal value function, the scalability of this approach can increase considerably. This separability is present when there is locality of interaction, which — as other approaches (such as those based on the ND-POMDP subclass) have already shown — can be exploited to improve performance. Unlike most previous methods, the novel continuous-state MDP algorithm retains optimality and convergence guarantees. Results show that the extension using separability can scale to a large number of agents and domain variables while maintaining optimality.
Type de document :
Communication dans un congrès
Alessio Lomuscio; Paul Scerri; Ana Bazzan; Michael Huhns. 13th International Conference on Autonomous Agents and Multiagent Systems, May 2014, Paris, France. ACM, 2014, Proceedings of the 13th International Conference on Autonomous Agents and Multiagent Systems. 〈http://aamas2014.lip6.fr〉
Liste complète des métadonnées

Littérature citée [35 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01092066
Contributeur : Olivier Buffet <>
Soumis le : mercredi 10 décembre 2014 - 15:32:32
Dernière modification le : jeudi 11 janvier 2018 - 06:25:23
Document(s) archivé(s) le : mercredi 11 mars 2015 - 10:10:54

Fichier

aamas14a.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01092066, version 1

Collections

Citation

Jilles Steeve Dibangoye, Christopher Amato, Olivier Buffet, François Charpillet. Exploiting Separability in Multiagent Planning with Continuous-State MDPs. Alessio Lomuscio; Paul Scerri; Ana Bazzan; Michael Huhns. 13th International Conference on Autonomous Agents and Multiagent Systems, May 2014, Paris, France. ACM, 2014, Proceedings of the 13th International Conference on Autonomous Agents and Multiagent Systems. 〈http://aamas2014.lip6.fr〉. 〈hal-01092066〉

Partager

Métriques

Consultations de la notice

222

Téléchargements de fichiers

103