The class of finite Sturmian words consists of words having particularly simple compressed representation, which is a generalization of the Fibonacci recurrence for Fibonacci word...
We are interested by contributing to stochastic problems of which the main distinction is that some tasks may create other tasks. In particular, we present a first approach which...
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a mo...
This paper addresses the implementation of advanced, online simulation experiments upon the World-Wide Web. The paper first discusses the system considered for this study. The pap...
We present an on-line learning framework tailored towards real-time learning from observed user behavior in search engines and other information retrieval systems. In particular, ...