Elements of Task Theory.

Tasks are of primary importance for artificial intelligence (AI), yet no theory about their characteristics exists. The kind of task theory we envision is one that allows an objective comparison of tasks, based on measurable physical properties, and that can serve as a foundation for studying, evaluating, and comparing learning controllers of various kinds on a variety of tasks by providing principled ways for constructing, comparing, and changing tasks with particular properties and levels of difficulty. In prior papers we have outlined an approach towards this goal; in this paper we present further principles for its development, including causal relations. We use these principles to expand our prior ideas, with the aim of laying the groundwork for covering levels of detail, prior knowledge of the learner/performer and task difficulty, to name some of the complex issues that must be solved for a useful task theory.