Stochastic grammar has been used in many video analysis and event recognition applications as an efficient model to represent large-scale video activity. However, in previous works...
Traditional artificial intelligence techniques do not perform well in applications such as real-time strategy games because of the extensive search spaces which need to be explore...
Abstract. Case-based planning (CBP) is based on reusing past successful plans for solving new problems. CBP is particularly useful in environments where the large amount of time re...
Plan recognition is the problem of inferring the goals and plans of an agent after observing its behavior. Recently, it has been shown that this problem can be solved efficiently,...
In our research we study rational agents which learn how to choose the best conditional, partial plan in any situation. The agent uses an incomplete symbolic inference engine, emp...