@COMMENT This file was generated by bib2html.pl version 0.90
@COMMENT written by Patrick Riley
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@Article{AB11-jung,
author="Tobias Jung and Daniel Polani and Peter Stone",
title="Empowerment for continuous agent-environment systems",
journal="Adaptive Behavior",
volume="19",
number="1",
pages="16-39",
year="2011",
abstract={
This paper develops generalizations of empowerment to
continuous states. Empowerment is a recently introduced
information-theoretic quantity motivated by hypotheses
about the efficiency of the sensorimotor loop in biological
organisms, but also from considerations stemming from
curiosity-driven learning. Empowemerment measures, for
agent-environment systems with stochastic transitions, how
much influence an agent has on its environment, but only
that influence that can be sensed by the agent sensors. It
is an information-theoretic generalization of joint
controllability (influence on environment) and
observability (measurement by sensors) of the environment
by the agent, both controllability and observability being
usually defined in control theory as the dimensionality of
the control/observation spaces. Earlier work has shown
that empowerment has various interesting and relevant
properties, e.g., it allows us to identify salient states
using only the dynamics, and it can act as intrinsic reward
without requiring an external reward. However, in this
previous work empowerment was limited to the case of
small-scale and discrete domains and furthermore state
transition probabilities were assumed to be known. The goal
of this paper is to extend empowerment to the significantly
more important and relevant case of continuous
vector-valued state spaces and initially unknown state
transition probabilities. The continuous state space is
addressed by Monte-Carlo approximation; the unknown
transitions are addressed by model learning and prediction
for which we apply Gaussian processes regression with
iterated forecasting. In a number of well-known continuous
control tasks we examine the dynamics induced by
empowerment and include an application to exploration and
online model-learning.},
wwwnote={Available from Adaptive Behavior page.},
}