Goal-Driven Learning in Multistrategy Reasoning and Learning Systems Ashwin Ram, College of Computing Michael T. Cox, College of Computing S. Narayanan, School of Industrial & Systems Engineering Georgia Institute of Technology Atlanta, Georgia 30332-0280 1 Introduction This chapter presents a computational model of introspective multistrategy learning, which is a deliberative or strategic learning process in which a reasoner introspects about its own performance to decide what to learn and how to learn it. The reasoner introspects about its own performance on a reasoning task, assigns credit or blame for its performance, identifies 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. Our theory models the following characteristics of goal-driven learning: (i) that learning is active, and strategic, goal-driven processes underlie much of the learning that occurs during the performance of analytical tasks in complex, real-world domains; (ii) that learning is experiential and occurs incrementally through the performance of a reasoning task; (iii) that learning is opportunistic, and learning goals that are not immediately satisfiable are remembered so that the reasoner can recognize and use later opportunities to pursue them; (iv) that learning is diverse and involves multiple different strategies for acquiring new To appear in A. Ram and D. Leake (eds.), Goal-Driven Learning, MIT Press/Bradford Books, Cambridge, MA, forthcoming. 1