Principles of frugal inference and control

TL;DR

This paper introduces a resource-aware control framework that balances utility and computational costs, revealing principles for efficient inference and control in uncertain environments.

Contribution

It proposes a novel POMDP variant that treats inference as a resource, deriving principles for resource-efficient control applicable to nonlinear problems.

Findings

Inference shifts from lossless to lossy under cost constraints.

Multiple solutions exist for combining imperfect inference with control.

Control can reduce representation costs and counteract estimation errors.

Abstract

A central challenge for intelligent agents in an uncertain world is striking the right balance between utility maximization and resource use, not only for external movement but also for internal computation. Existing theories of control under uncertainty typically treat inference as cost-free, despite the substantial computational and energetic burden it imposes in both artificial and biological systems. To remedy this problem, we introduce a novel variant of the POMDP framework in which the information acquired through inference is treated as a resource that must be optimized alongside utility. Solving a local linear-Gaussian approximation of the resulting problem reveals three general principles of resource-efficient control. First, when information is costly, inference shifts from a Bayes-optimal (lossless) compression of the past to a lossy regime that strategically leaves some uncertainty unresolved to optimize resource use. Second, relaxing exact Bayesian inference creates a manifold of equivalent solutions, reflecting multiple ways to combine imperfect inference with compensatory control. This flexibility can be used to meet additional objectives or constraints without sacrificing performance on the original task. Third, beyond goal attainment, control can be leveraged to counteract estimation errors and steer the system into regimes where representation costs are lower. We empirically demonstrate that these principles generalize beyond the local linear-Gaussian approximation, enabling the solution of nonlinear control problems such as pole balancing and drone stabilization. Together, these results establish a framework for rational computation that extends existing approaches to information-constrained decision-making and offers normative insight into how brains and machines can achieve effective behavior under tight computational constraints.