—This paper presents a method for learning decision theoretic models of human behaviors from video data. Our system learns relationships between the movements of a person, the co...
Gaze is an extremely important aspect of human face to face interaction. Over the course of an interaction, a single individual’s gaze can perform many different functions, such...
This paper formalizes the semantics of trust and studies the transitivity of trust. On the Web, people and software agents have to interact with “strangers”. This makes trust ...
Rich representations in reinforcement learning have been studied for the purpose of enabling generalization and making learning feasible in large state spaces. We introduce Object...
Policy gradient approaches are a powerful instrument for learning how to interact with the environment. Existing approaches have focused on propositional and continuous domains on...