We examine the problem of evaluating a policy in the contextual bandit setting using only observations collected during the execution of another policy. We show that policy evalua...
John Langford, Alexander L. Strehl, Jennifer Wortm...
Abstract. The proposed work exploits methods and techniques for automatic characterization of images for content-based access to personal photo libraries. Several techniques, even ...
—Robot imitation is a useful and promising alternative to robot programming. Robot imitation involves two crucial issues. The first is how a robot can imitate a human whose phys...
Ryunosuke Yokoya, Tetsuya Ogata, Jun Tani, Kazunor...
When users input their passwords in a public place, they may be at risk of attackers stealing their password. An attacker can capture a password by direct observation or by record...
Susan Wiedenbeck, Jim Waters, Leonardo Sobrado, Je...
Most formulations of Reinforcement Learning depend on a single reinforcement reward value to guide the search for the optimal policy solution. If observation of this reward is rar...