We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Abstract. Construction of secure hyperelliptic curves is of most important yet most difficult problem in design of cryptosystems based on the discrete logarithm problems on hyperel...
In the past, Markov Decision Processes (MDPs) have become a standard for solving problems of sequential decision under uncertainty. The usual request in this framework is the compu...
We introduce a new approach to the maximum flow problem. This approach is based on assigning arc lengths based on the residual flow value and the residual arc capacities. Our appro...
Document representations can rapidly become unwieldy if they try to encapsulate all possible document properties, ranging tract structure to detailed rendering and layout. We pres...