Abstract. We consider Reinforcement Learning for average reward zerosum stochastic games. We present and analyze two algorithms. The first is based on relative Q-learning and the ...
Abstract. Temporally extended goals are used in planning to express safety and maintenance conditions. Linear temporal logic is the language often used to express temporally extend...
Abstract. We consider the problem of learning a mapping from question to answer messages. The training data for this problem consist of pairs of messages that have been received an...
Abstract. In this paper, we investigate the properties of commonly used prepruning heuristics for rule learning by visualizing them in PN-space. PN-space is a variant of ROC-space,...
Among the possible approaches for expressing real-time problems with the B method, two are dominant : the use of the usual B mechanisms to define temporal constraints on the one h...