University of Hertfordshire Research Archive

        JavaScript is disabled for your browser. Some features of this site may not work without it.

        Browse

        All of UHRABy Issue DateAuthorsTitlesThis CollectionBy Issue DateAuthorsTitles

        Arkivum Files

        My Downloads
        View Item 
        • UHRA Home
        • University of Hertfordshire
        • Research publications
        • View Item
        • UHRA Home
        • University of Hertfordshire
        • Research publications
        • View Item

        Empowerment for continuous agent-environment systems

        Author
        Jung, Tobias
        Polani, D.
        Stone, Peter
        Attention
        2299/9651
        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.
        Publication date
        2011-02
        Published in
        Adaptive Behavior
        Published version
        https://doi.org/10.1177/1059712310392389
        Other links
        http://hdl.handle.net/2299/9651
        Metadata
        Show full item record
        Keep in touch

        © 2019 University of Hertfordshire

        I want to...

        • Apply for a course
        • Download a Prospectus
        • Find a job at the University
        • Make a complaint
        • Contact the Press Office

        Go to...

        • Accommodation booking
        • Your student record
        • Bayfordbury
        • KASPAR
        • UH Arts

        The small print

        • Terms of use
        • Privacy and cookies
        • Criminal Finances Act 2017
        • Modern Slavery Act 2015
        • Sitemap

        Find/Contact us

        • T: +44 (0)1707 284000
        • E: ask@herts.ac.uk
        • Where to find us
        • Parking
        • hr
        • qaa
        • stonewall
        • AMBA
        • ECU Race Charter
        • disability confident
        • AthenaSwan