We consider the fundamental problem of monitoring (i.e. tracking) the belief state in a dynamic system, when the model is only approximately correct and when the initial belief st...
— We introduce the Oracular Partially Observable Markov Decision Process (OPOMDP), a type of POMDP in which the world produces no observations; instead there is an “oracle,” ...
Recent scaling up of decentralized partially observable Markov decision process (DEC-POMDP) solvers towards realistic applications is mainly due to approximate methods. Of this fa...