Residual gradient (RG) was proposed as an alternative to TD(0) for policy evaluation when function approximation is used, but there exists little formal analysis comparing them ex...
: This paper describes a novel method for displaying and examining the execution space of a rule interpreter. This method provides both coarse-grained and fine-grained views. The c...
Abstract. In recent years, there has been a great deal of work in modeling audio using non-negative matrix factorization and its probabilistic counterparts as they yield rich model...
Abstract. This paper presents a model-checking approach for analyzing discrete-time Markov reward models. For this purpose, the temporal logic probabilistic CTL is extended with re...