In multiple criteria Markov Decision Processes (MDP) where multiple costs are incurred at every decision point, current methods solve them by minimising the expected primary cost ...
Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in whic...
Magnifying Lens Abstraction in Markov Decision Processes ∗ Pritam Roy1 David Parker2 Gethin Norman2 Luca de Alfaro1 Computer Engineering Dept, UC Santa Cruz, Santa Cruz, CA, USA ...
Pritam Roy, David Parker, Gethin Norman, Luca de A...
— 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,” ...
One of the difficulties to adapt MDPs for the control of cooperative multi-agent systems, is the complexity issued from Decentralized MDPs. Moreover, existing approaches can not ...