Information-Theoretic Abstractions for Planning in Agents with Computational Constraints

TL;DR

This paper introduces a framework for adaptive path-planning in agents with limited computational resources, where abstractions emerge dynamically to approximate the environment and facilitate efficient planning.

Contribution

It presents a novel approach to generate environment abstractions based on computational constraints, linking planning, anytime algorithms, and bounded rationality.

Findings

Theoretical analysis of abstraction properties

Numerical example demonstrating approach utility

Connections to anytime algorithms and bounded rationality

Abstract

In this paper, we develop a framework for path-planning on abstractions that are not provided to the agent a priori but instead emerge as a function of the available computational resources. We show how a path-planning problem in an environment can be systematically approximated by solving a sequence of easier to solve problems on abstractions of the original space. The properties of the problem are analyzed, and a number of theoretical results are presented and discussed. A numerical example is presented to show the utility of the approach and to corroborate the theoretical findings. We conclude by providing a discussion detailing the connections of the proposed approach to anytime algorithms and bounded rationality.