Chance-Constrained Active Inference

TL;DR

This paper introduces a novel approach to Active Inference using chance constraints, enabling goal-directed behavior with controlled constraint violations, and provides a message passing framework applicable to graphical models and neural generative models.

Contribution

It proposes integrating chance constraints into Active Inference, offering a flexible way to balance robustness and empirical violations, and develops a general message passing framework for such constraints.

Findings

Chance-constrained Active Inference allows for probabilistic constraint violations.

The message passing framework simplifies incorporating chance constraints into models.

The approach enhances the flexibility and robustness of goal-directed behavior in biological and artificial agents.

Abstract

Active Inference (ActInf) is an emerging theory that explains perception and action in biological agents, in terms of minimizing a free energy bound on Bayesian surprise. Goal-directed behavior is elicited by introducing prior beliefs on the underlying generative model. In contrast to prior beliefs, which constrain all realizations of a random variable, we propose an alternative approach through chance constraints, which allow for a (typically small) probability of constraint violation, and demonstrate how such constraints can be used as intrinsic drivers for goal-directed behavior in ActInf. We illustrate how chance-constrained ActInf weights all imposed (prior) constraints on the generative model, allowing e.g., for a trade-off between robust control and empirical chance constraint violation. Secondly, we interpret the proposed solution within a message passing framework. Interestingly, the message passing interpretation is not only relevant to the context of ActInf, but also provides a general purpose approach that can account for chance constraints on graphical models. The chance constraint message updates can then be readily combined with other pre-derived message update rules, without the need for custom derivations. The proposed chance-constrained message passing framework thus accelerates the search for workable models in general, and can be used to complement message-passing formulations on generative neural models.