In this paper we develop a theoretical analysis of the performance of sampling-based fitted value iteration (FVI) to solve infinite state-space, discounted-reward Markovian decisi...
Abstract: Several approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervis...
We present several new algorithms as well as new lower and upper bounds for optimizing functions underlying infinite games pertinent to computer-aided verification.
This paper addresses the issue of determining the iteration bound for a synchronous data flow graph (SDFG) and determining whether or not a SDFG is live based on some calculations...
Samer F. Khasawneh, Michael E. Richter, Timothy W....
Abstract. We present ABC, a software tool for automatically computing symbolic upper bounds on the number of iterations of nested program loops. The system combines static analysis...