Information-Theoretic Abstractions for Resource-Constrained Agents via Mixed-Integer Linear Programming
Abstract
In this paper, a mixed-integer linear programming formulation for the problem of obtaining task-relevant, multi-resolution, graph abstractions for resource-constrained agents is presented. The formulation leverages concepts from information-theoretic signal compression, specifically the information bottleneck (IB) method, to pose a graph abstraction problem as an optimal encoder search over the space of multi-resolution trees. The abstractions emerge in a task-relevant manner as a function of agent information-processing constraints, and are not provided to the system a priori. We detail our formulation and show how the problem can be realized as an integer linear program. A non-trivial numerical example is presented to demonstrate the utility in employing our approach to obtain hierarchical tree abstractions for resource-limited agents.
Cite
@article{arxiv.2102.10015,
title = {Information-Theoretic Abstractions for Resource-Constrained Agents via Mixed-Integer Linear Programming},
author = {Daniel T. Larsson and Dipankar Maity and Panagiotis Tsiotras},
journal= {arXiv preprint arXiv:2102.10015},
year = {2021}
}