Cooperative Markov decision processes: time consistency, greedy players satisfaction, and cooperation maintenance - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue International Journal of Game Theory Année : 2013

Cooperative Markov decision processes: time consistency, greedy players satisfaction, and cooperation maintenance

Résumé

We deal with multi-agent Markov decision processes (MDPs) in which cooperation among players is allowed. We find a cooperative payoff distribution procedure (MDP-CPDP) that distributes in the course of the game the payoff that players would earn in the long run game. We show under which conditions such a MDP-CPDP fulfills a time consistency property, contents greedy players, and strengthen the coalition cohesiveness throughout the game. Finally we refine the concept of Core for Cooperative MDPs.

Dates et versions

hal-00926471 , version 1 (09-01-2014)

Identifiants

Citer

Konstantin Avrachenkov, Laura Cottatellucci, Lorenzo Maggi. Cooperative Markov decision processes: time consistency, greedy players satisfaction, and cooperation maintenance. International Journal of Game Theory, 2013, 42 (1), pp.239-262. ⟨10.1007/s00182-012-0343-9⟩. ⟨hal-00926471⟩
137 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More