University of Hertfordshire

From the same journal

By the same authors

Empowerment for continuous agent-environment systems

Research output: Contribution to journalArticlepeer-review

View graph of relations
Original languageEnglish
Pages (from-to)16-39
Number of pages24
JournalAdaptive Behavior
Volume19
Issue1
DOIs
Publication statusPublished - Feb 2011

Abstract

This article 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. Empowerment 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, for example, 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 article 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.

Notes

“The final, definitive version of this article has been published in the Journal Adaptive behavior, 149 (1) 2011 © SAGE Publications Ltd, 2011: on SAGE Journals Online: http://online.sagepub.com/" [Full text of this article is not available in the UHRA]

ID: 392720