We propose and analyze a distribution learning algorithm for variable memory length Markov processes. These processes can be described by a subclass of probabilistic nite automata...
We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a mo...
We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...
Structured QBDs by Abstraction Daniel Klink, Anne Remke, Boudewijn R. Haverkort, Fellow, IEEE, and Joost-Pieter Katoen, Member, IEEE Computer Society —This paper studies quantita...
Daniel Klink, Anne Remke, Boudewijn R. Haverkort, ...
Abstract— In this paper, we consider a class of continuoustime, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation ...