Temporal logics are widely used in specifying goals of agents. We noticed that when directing agents, humans often revise their requirements for the agent, especially as they gath...
Based on Information Theory, optimal feature selection should be carried out by searching Markov blankets. In this paper, we formally analyze the current Markov blanket discovery ...
We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
Transfer learning is the ability of an agent to apply knowledge learned in previous tasks to new problems or domains. We approach this problem by focusing on model formulation, i....
A great deal of research has addressed the problem of generating optimal plans, but these plans are of limited use in circumstances where noisy sensors, unanticipated exogenous ac...