Goal-Directed Metacontrol for Integrated Procedure Learning

Abstract

Developing systems that learn how to perform complex tasks presents a significant challenge to the artificial intelligence 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 process 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, Chapter 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 135 behaviour 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 (Chapter 2). As such, it contrasts with the majority of work to date on metareasoning, which has focused on the problem of bounded rationality, as described by Zilberstein (Chapter 3).Developing a metalevel reasoner for such a complex, integrated learning system poses several challenges, including• Assessing the progress of learning over time;• Systematically addressing conflicts and failures that arise during learning;• Addressing gaps and shortcomings of the individual and aggregate learning results;• Supporting flexible interactions among agents that pursue different learning strategies.We describe a metalevel framework for coordinating the activities of a community of learners to create an integrated learning system. The metalevel framework is organized around learning goals, which are formulated through introspective reasoning to identify problems and requirements for the ongoing 136 learning process. These learning goals are posted to a shared blackboard to direct the other components in the system. Goals can be either process or knowledge oriented.Process goals define specific tasks to be performed as part of the learning process and are used to coordinate the activities of the various learning and reasoning components. Examples of process goals for task learning include hypothesis creation, hypothesis merging, explanation of observations, and hypothesis validation through experimentation.Knowledge goals provide the means for a component to convey the need for additional information to f...

Towards Continuous Scientific Data Analysis and Hypothesis Evolution

“…In addition, given the size of the hypothesis space in the science domains we are tackling, we need the ability to direct the system with some initial hypotheses to be tested, and to be able to decide what data is relevant to these hypotheses in the first place. Usually in machine learning it is assumed that the system will process all the data that it is given, and in this sense our system is adding a metareasoning layer to set up its own analytic and learning goals [Cox and Raja 2011;Kim et al 2011]. Our user hypotheses are akin to meta-level goals, and our lines of inquiry and workflows akin to problem-solving strategies.…”

Interactive knowledge capture in the new millennium: how the Semantic Web changed everything

“…At any given point, the system should be aware of its knowledge gaps and decide whether they affect its ability to do specific kinds of problem solving. We have developed a framework to keep track of multiple alternative models of a procedure that evolve over time as additional information is provided (Kim & Gil 2007;Gil et al, 2010a;Kim et al, 2010). These techniques are used in our work on learning procedures from natural instruction mentioned above (Gil et al, 2011).…”