Abstract

Developing systems that learn how to perform complex tasks presents a significant challenge to the artificial intelligence (AI) community. As the knowledge to be learned becomes complex, with diverse procedural constructs and uncertainties to be validated, the system needs to integrate a wide range of learning and reasoning methods with different focuses and strengths. For example, one learning method may be used to generalize from user demonstrations, another to learn by practice and exploration, and another to test hypotheses with experiments. The POIROT system pursues such a multistrategy learning methodology that employs multiple integrated learners and knowledge validation modules to acquire complex procedural knowledge for a medical logistics domain (Burstein et al., 2008).
For a learning system of such complexity, activities of participating agents must be coordinated to ensure that their collective activities produce the desired procedural knowledge. This kind of control is inherently metalevel (Anderson & Oates, 2007; Cox & Raja, this vol., chap. 1) in that it requires the system to reflect on what it is doing and why, to monitor its progress, and to make adjustments to its behavior when performance falls short of expectations. Without such introspection, effective coordination and prioritization of the base-level learning and reasoning components would not be possible. This type of introspection corresponds to a form of metareasoning centered on “stepping back” from the system to analyze its behavior, as discussed by Perlis (this vol., chap. 2). As such, it contrasts with the majority of work to date on metareasoning, which has …

Date

2011

Authors

Jihie Kim, Karen L Myers, Melinda T Gervasio, Yolanda Gil

Book

Metareasoning

Pages

77-100