We propose a novel unsupervised learning framework for activity perception. To understand activities in complicated scenes from visual data, we propose a hierarchical Bayesian mod...
Policy making is a multi-actor process: it involves a variety of actors, each trying to further their own interests. How these actors decide and act largely depends on the way the...
Decision-theoretic reasoning and planning algorithms are increasingly being used for mobile robot navigation, due to the signi cant uncertainty accompanying the robots' perce...
RVRL (Rule Value Reinforcement Learning) is a new algorithm which extends an existing learning framework that models the environment of a situated agent using a probabilistic rule...
As animals interact with their environments, they must constantly update estimates about their states. Bayesian models combine prior probabilities, a dynamical model and sensory e...
Richard S. Zemel, Quentin J. M. Huys, Rama Nataraj...