Flexible general purpose robots need to tailor their visual processing to their task, on the fly. We propose a new approach to this within a planning framework, where the goal is ...
Finite-state controllers represent an effective action selection mechanisms widely used in domains such as video-games and mobile robotics. In contrast to the policies obtained fr...
Predictive state representations (PSRs) are a recently proposed way of modeling controlled dynamical systems. PSR-based models use predictions of observable outcomes of tests that...
We describe a formal framework for diagnosis and repair problems that shares elements of the well known partially observable MDP and cost-sensitive classification models. Our cost...
Michael L. Littman, Nishkam Ravi, Eitan Fenson, Ri...
This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedba...