Mutual Information Surprise: Rethinking Unexpectedness in Autonomous Systems

TL;DR

This paper introduces Mutual Information Surprise (MIS), a novel framework that redefines surprise as a measure of epistemic growth, enabling more adaptive and self-aware autonomous systems.

Contribution

The work presents MIS as a new surprise measure, along with a statistical test and reaction policy, improving system stability and learning in dynamic environments.

Findings

MIS outperforms classical surprise measures in stability and responsiveness

The MIS-based policy enhances predictive accuracy in dynamic tasks

Empirical results demonstrate improved adaptation in autonomous systems

Abstract

A community of researchers appears to think that a machine can be surprised and have introduced various surprise measures, principally the Shannon Surprise and the Bayesian Surprise. The questions of what constitutes a surprise and how to react to one still elicit debates. In this work, we introduce Mutual Information Surprise (MIS), a new framework that redefines surprise not as anomaly measure, but as a signal of epistemic growth. Furthermore, we develop a statistical test sequence that could trigger a surprise reaction and propose a MIS-based reaction policy that dynamically governs system behavior through sampling adjustment and process forking. Empirical evaluations -- on both synthetic domains and a dynamic pollution map estimation task -- show that a system governed by the MIS-based reaction policy significantly outperforms those under classical surprise-based approaches in stability, responsiveness, and predictive accuracy. The important implication of our new proposal is that MIS quantifies the impact of new observations on mutual information, shifts surprise from reactive to reflective, enables reflection on learning progression, and thus offers a path toward self-aware and adaptive autonomous systems. We expect the new surprise measure to play a critical role in further advancing autonomous systems on their ability to learn and adapt in a complex and dynamic environment.