An Architecture for Integrated Introspective

This paper presents a computational model of integrated introspective learning, which is a deliberative learning process in which a rea-soner introspects about its own performance on a reasoning task, identiies what it needs to learn to improve its performance, formulates learning goals to acquire the required knowledge, and pursues its learning goals using multiple learning strategies. We discuss two case studies of integrated introspective learning in two diierent task domains. The rst case study deals with learning diagnostic knowledge during a troubleshooting task, and is based on observations of human operators engaged in a real-world troubleshooting task at an electronics assembly plant. The second case study deals with learning multiple kinds of causal and explanatory knowledge during a story understanding task. The model is com-putationally justiied as a uniform and ex-tensible framework for deliberative learning using multiple learning strategies, and cogni-tively justiied as a plausible model of human deliberative learning.