This paper describes two approaches that enable the AI Planner LPGP to reason about domains with exogenous events and goals with duration: the first investigates how such domains...
This paper investigates the use of reinforcement learning in electric power system emergency control. The approach consists of using numerical simulations together with on-policy M...
Abstract--We present an approach to compress arbitrary files using a Huffman-like prefix-free code generated through the use of a genetic algorithm, thus requiring no prior knowled...
A two-dimensional (2-D) convolution mask is proposed for detecting the location of irregularities and defects in a periodic two-dimensional signal or image. In this approach, defe...
We describe a new pruning approach to remove phrase pairs from translation models of statistical machine translation systems. The approach applies the original translation system ...