Current studies have demonstrated that the representational power of predictive state representations (PSRs) is at least equal to the one of partially observable Markov decision p...
Abdeslam Boularias, Masoumeh T. Izadi, Brahim Chai...
The requirements on production systems and their planning and control systems are constantly growing. Systems have to be flexible and provide viable solutions at the same time. Di...
Mark Aufenanger, Wilhelm Dangelmaier, Christoph La...
Abstract. In this paper we present three methods for image autoannotation used by the Wroclaw University of Technology group at ImageCLEF 2010 Photo Annotation track. All of our ex...
Greedy search is commonly used in an attempt to generate solutions quickly at the expense of completeness and optimality. In this work, we consider learning sets of weighted actio...
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...