Paper ID: 2407.19631

"A Good Bot Always Knows Its Limitations": Assessing Autonomous System Decision-making Competencies through Factorized Machine Self-confidence

Brett Israelsen, Nisar R. Ahmed, Matthew Aitken, Eric W. Frew, Dale A. Lawrence, Brian M. Argrow

How can intelligent machines assess their competencies in completing tasks? This question has come into focus for autonomous systems that algorithmically reason and make decisions under uncertainty. It is argued here that machine self-confidence - a form of meta-reasoning based on self-assessments of an agent's knowledge about the state of the world and itself, as well as its ability to reason about and execute tasks - leads to many eminently computable and useful competency indicators for such agents. This paper presents a culmination of work on this concept in the form of a computational framework called Factorized Machine Self-confidence (FaMSeC), which provides a holistic engineering-focused description of factors driving an algorithmic decision-making process, including: outcome assessment, solver quality, model quality, alignment quality, and past experience. In FaMSeC, self confidence indicators are derived from hierarchical `problem-solving statistics' embedded within broad classes of probabilistic decision-making algorithms such as Markov decision processes. The problem-solving statistics are obtained by evaluating and grading probabilistic exceedance margins with respect to given competency standards, which are specified for each of the various decision-making competency factors by the informee (e.g. a non-expert user or an expert system designer). This approach allows `algorithmic goodness of fit' evaluations to be easily incorporated into the design of many kinds of autonomous agents in the form of human-interpretable competency self-assessment reports. Detailed descriptions and application examples for a Markov decision process agent show how two of the FaMSeC factors (outcome assessment and solver quality) can be computed and reported for a range of possible tasking contexts through novel use of meta-utility functions, behavior simulations, and surrogate prediction models.

Submitted: Jul 29, 2024