We propose a generic method for obtaining quickly good upper bounds on the minimal value of a multistage stochastic program. The method is based on the simulation of a feasible dec...
We consider the problem of learning classifiers in structured domains, where some objects have a subset of features that are inherently absent due to complex relationships between...
Gal Chechik, Geremy Heitz, Gal Elidan, Pieter Abbe...
In this paper, we address two issues of long-standing interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning aft...
Recent scaling up of POMDP solvers towards realistic applications is largely due to point-based methods such as PBVI, Perseus, and HSVI, which quickly converge to an approximate so...
XCS with computed prediction, namely XCSF, has been recently extended in several ways. In particular, a novel prediction update algorithm based on recursive least squares and the ...