Synchronizing to the Environment: Information Theoretic
Constraints on Agent Learning.
J.P. Crutchfield and D. P. Feldman, Synchronizing to the Environment:
Information Theoretic Constraints on Agent Learning. Advances
in Complex Systems, 4:251-264, 2001.
Abstract
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.
Download the Paper:
[Back to Publications Page]