We propose several tracking adaptation approaches to recover from early tracking errors in sign language recognition by optimizing the obtained tracking paths w.r.t. to the hypoth...
Philippe Dreuw, Jens Forster, Thomas Deselaers, He...
Rectangular hybrid automatamodel digital control programs of analog plant environments. We study rectangular hybrid automatawhere the plant state evolves continuously in real-numbe...
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...
Policy search is a method for approximately solving an optimal control problem by performing a parametric optimization search in a given class of parameterized policies. In order ...
We consider a class of hybrid dynamical systems and obtain conditions under which the behavior of these systems can be reduced to a finite state automaton. Specifically, we consi...
S. Di Gennaro, C. Horn, Sanjeev R. Kulkarni, Peter...