Hutter, Marcus2015-12-10March 6-99789078677246http://hdl.handle.net/1885/58189Feature Markov Decision Processes (ΦMDPs) [Hut09] are well-suited for learning agents in general environments. Nevertheless, unstructured (Φ)MDPs are limited to relatively simple environments, Structured MDPs like Dynamic Bayesian Networks (DBNs) are usCopyright Information: © Atlantis Press and the Author(s). This article is distributed under the terms of the Creative Commons Attribution License, which permits non-commercial use, distribution and reproduction in any medium, provided the original work iKeywords: Building blockes; Cost criteria; Dynamic Bayesian network; Dynamic bayesian networks; General learning; Learning agents; Markov Decision Processes; Primary contribution; Real-world problem; Distributed parameter networks; Feature extraction; Inference eng200910.2991/agi.2009.62016-02-24