We describe an evaluation of spoken dialogue strategies designed using hierarchical reinforcement learning agents. The dialogue strategies were learnt in a simulated environment a...
The management of group context in socially mediating technologies is an important challenge for the design community. To better understand how users manage group context, we expl...
Due to recent breakthroughs in hash functions cryptanalysis, some new hash schemes have been proposed. GRINDAHL is a novel hash function, designed by Knudsen, Rechberger and Thomse...
This paper extends the game-theoretic notion of internal regret to the case of on-line potfolio selection problems. New sequential investment strategies are designed to minimize th...
Designing the dialogue strategy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing di...
Diane J. Litman, Michael S. Kearns, Satinder P. Si...