We describe a “bag-of-rectangles” method for representing and recognizing human actions in videos. In this method, each human pose in an action sequence is represented by orien...
Abstract. The paper presents the preliminary version of Ontobella - a domain ontology of beliefs. The philosophical assumptions of this system are taken from the philosophy of Roma...
Pawel Garbacz, Marek Lechniak, Piotr Kulicki, Robe...
We investigate the problem of learning action effects in partially observable STRIPS planning domains. Our approach is based on a voted kernel perceptron learning model, where act...
This paper describes several ensemble methods that combine multiple different reinforcement learning (RL) algorithms in a single agent. The aim is to enhance learning speed and fin...
We consider the frame problem, that is, char acterizing the assumption that properties tend to persist over time. We show that there are at least three distinct assumptions that...