Q-value Heuristics for Approximate Solutions of Dec-POMDPs

By Frans Adriaan Oliehoek, Nikos A. Vlassis. 2007

8 citations recorded by the source corpus.

Citations in the corpus

• Multi-agent reinforcement learning as a rehearsal for decentralized planning (2016, neutral): “Among other work related to this idea, pre-solved MDP (and POMDP) policies have been used as search heuristics for Dec-POMDP solvers before [21].”