English

Information-Theoretic Abstractions for Planning in Agents with Computational Constraints

Robotics 2021-07-29 v2 Artificial Intelligence Information Theory math.IT

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.

Keywords

Cite

@article{arxiv.2005.09611,
  title  = {Information-Theoretic Abstractions for Planning in Agents with Computational Constraints},
  author = {Daniel T. Larsson and Dipankar Maity and Panagiotis Tsiotras},
  journal= {arXiv preprint arXiv:2005.09611},
  year   = {2021}
}
R2 v1 2026-06-23T15:40:03.047Z