A key problem in reinforcement learning is finding a good balance between the need to explore the environment and the need to gain rewards by exploiting existing knowledge. Much ...
We consider the problem of solving a nonhomogeneous infinite horizon Markov Decision Process (MDP) problem in the general case of potentially multiple optimal first period polic...
Torpong Cheevaprawatdomrong, Irwin E. Schochetman,...
Approximate linear programming (ALP) offers a promising framework for solving large factored Markov decision processes (MDPs) with both discrete and continuous states. Successful ...
Abstract. We consider an upper confidence bound algorithm for Markov decision processes (MDPs) with deterministic transitions. For this algorithm we derive upper bounds on the onl...
Abstract. In parametric Markov Decision Processes (PMDPs), transition probabilities are not fixed, but are given as functions over a set of parameters. A PMDP denotes a family of ...