We introduce and analyze a natural algorithm for multi-venue exploration from censored data, which is motivated by the Dark Pool Problem of modern quantitative finance. We prove t...
Kuzman Ganchev, Yuriy Nevmyvaka, Michael Kearns, J...
We present a discriminative model that casts appearance modeling and visual matching into a single objective for visual tracking. Most previous discriminative models for visual tra...
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Conversational recommender systems support human-computer interaction strategies in order to assist online tourists in the important activity of dynamic packaging, i.e., in buildi...
We present the first large-scale empirical application of reinforcement learning to the important problem of optimized trade execution in modern financial markets. Our experiments...