Provably Bounded-Optimal Agents

TL;DR

This paper introduces the concept of bounded optimality as a practical alternative to perfect rationality in AI, providing methods to construct such agents within certain architectures and environments, and exploring their theoretical and practical implications.

Contribution

It formalizes bounded optimality and asymptotic bounded optimality, constructs agents with these properties, and discusses their significance for AI theory and practice.

Findings

Constructed bounded-optimal agents for simple architectures

Defined and constructed universal ABO programs

Linked bounded optimality to broader philosophical and economic ideas

Abstract

Since its inception, artificial intelligence has relied upon a theoretical foundation centered around perfect rationality as the desired property of intelligent systems. We argue, as others have done, that this foundation is inadequate because it imposes fundamentally unsatisfiable requirements. As a result, there has arisen a wide gap between theory and practice in AI, hindering progress in the field. We propose instead a property called bounded optimality. Roughly speaking, an agent is bounded-optimal if its program is a solution to the constrained optimization problem presented by its architecture and the task environment. We show how to construct agents with this property for a simple class of machine architectures in a broad class of real-time environments. We illustrate these results using a simple model of an automated mail sorting facility. We also define a weaker property, asymptotic bounded optimality (ABO), that generalizes the notion of optimality in classical complexity theory. We then construct universal ABO programs, i.e., programs that are ABO no matter what real-time constraints are applied. Universal ABO programs can be used as building blocks for more complex systems. We conclude with a discussion of the prospects for bounded optimality as a theoretical basis for AI, and relate it to similar trends in philosophy, economics, and game theory.