In partially observable worlds with many agents, nested beliefs are formed when agents simultaneously reason about the unknown state of the world and the beliefs of the other agen...
Luke S. Zettlemoyer, Brian Milch, Leslie Pack Kael...
An efficient policy search algorithm should estimate the local gradient of the objective function, with respect to the policy parameters, from as few trials as possible. Whereas m...
The search for finite-state controllers for partially observable Markov decision processes (POMDPs) is often based on approaches like gradient ascent, attractive because of their ...
A key feature of modern optimal planners such as Graphplan and Blackbox is their ability to prune large parts of the search space. Previous Partial Order Causal Link (POCL) planne...
Dynamic topological logics are combinations of topological and temporal modal logics that are used for reasoning about dynamical systems consisting of a topological space and a con...
Boris Konev, Roman Kontchakov, Frank Wolter, Micha...