For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...
Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., li...
In mobile ad hoc networks, nodes interact peer-to-peer. They self-organize, share workloads and provide services that they also use. There are middleware platforms, designed for t...
Abstract. We consider the framework of stochastic multi-armed bandit problems and study the possibilities and limitations of strategies that explore sequentially the arms. The stra...
We consider the operator mapping problem for in-network stream processing, i.e., the application of a tree of operators in steady-state to multiple data objects that are continuou...
Anne Benoit, Henri Casanova, Veronika Rehn-Sonigo,...