Synchronizing to the Environment: Information Theoretic Constraints on Agent Learning

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We show that the way in which the Shannon entropy of sequences produced by an information source converges to the source's entropy rate can be used to monitor how an intelligent agent builds and effectively uses a predictive model of its environment. We introduce natural measures of the environment's apparent memory and the amounts of information that must be (i) extracted from observations for an agent to synchronize to the environment and (ii) stored by an agent for optimal prediction. If structural properties are ignored, the missed regularities are converted to apparent randomness. Conversely, using representations that assume too much memory results in false predictability.
6 pages, 5 figures, Santa Fe Institute Working Paper 01-03-020, http://www.santafe.edu/projects/CompMech/papers/stte.html

Keywords

Adaptation and Self-Organizing Systems

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/79971

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/nlin/0103038
 http://arxiv.org/abs/nlin/0103038

Collections

arXiv