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

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 \citeauthor{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 …

application breaking cs.gt cs.lg decentralized decision enabling form game hierarchical information markov observable process shows solve stage theory variables