Several algorithms for learning near-optimal policies in Markov Decision Processes have been analyzed and proven efficient. Empirical results have suggested that Model-based Inter...
This paper presents a novel Gaussian process (GP) approach to regression with inputdependent noise rates. We follow Goldberg et al.'s approach and model the noise variance us...
Kristian Kersting, Christian Plagemann, Patrick Pf...
The asymptotic bias and variance are important determinants of the quality of a simulation run. In particular, the asymptotic bias can be used to approximate the bias introduced b...
Aad P. A. van Moorsel, Latha A. Kant, William H. S...
Sets of features in Markov decision processes can play a critical role ximately representing value and in abstracting the state space. Selection of features is crucial to the succe...
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...