Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach - Department of Complex Systems, Artificial Intelligence  & Robotics
Communication Dans Un Congrès Année : 2024

Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach

Résumé

A recent theory shows that a multi-player decentralized partially observable Markov decision process can be transformed into an equivalent single-player game, enabling the application of Bellman's principle of optimality to solve the single-player game by breaking it down into single-stage subgames. However, this approach entangles the decision variables of all players at each single-stage subgame, resulting in backups with a double-exponential complexity. This paper demonstrates how to disentangle these decision variables while maintaining optimality under hierarchical information sharing, a prominent management style in our society. To achieve this, we apply the principle of optimality to solve any single-stage subgame by breaking it down further into smaller subgames, enabling us to make single-player decisions at a time. Our approach reveals that extensive-form games always exist with solutions to a single-stage subgame, significantly reducing time complexity. Our experimental results show that the algorithms leveraging these findings can scale up to much larger multi-player games without compromising optimality.
Fichier principal
Vignette du fichier
peralez24a.pdf (871.42 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04698507 , version 1 (16-09-2024)

Licence

Identifiants

Citer

Johan Peralez, Aurélien Delage, Olivier Buffet, Jilles Dibangoye. Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach. ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienne, Austria. pp.63010. ⟨hal-04698507⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More