University of Hertfordshire

From the same journal

By the same authors

Goal-directed Empowerment: combining Intrinsic Motivation and Task-oriented Behaviour

Research output: Contribution to journalArticlepeer-review

Standard

Harvard

APA

Vancouver

Author

Bibtex

@article{e1d849c31c87489aaa4203597dada0cc,
title = "Goal-directed Empowerment: combining Intrinsic Motivation and Task-oriented Behaviour",
abstract = "Empowerment is an information-theoretic measure representing the capacity of an agent to affect its environment. It quantifies its ability to inject information in the environment via its actions and to recapture this information through its sensors. In a nutshell, it measures the number of future options available and perceivable by the agent. Originally, the definition of empowerment does not depend on any particular extrinsic goal and it is determined only by the interaction of the agent with the world and the structure of its action-perception cycle.In this paper we introduce a new formalism that combines empowerment maximization with externally specifiable goal-directed behaviour. This has two main implications: on the one hand, the study of the relationship between empowerment optimization and goal-directedness, to investigate to which extent these two desirable behaviours can co-exist; on the other hand, from a more operational point of view, the derivation of a method to generate a behaviour (i.e., a policy of a Markov decision process) that is both empowered and goal-directed, in order to design agents capable of being as {"}empowered{"} as possible when facing any extrinsic task. Finally, we study how this hybrid policy is able to handle problems of uncertain or changing goals and delayed goal commitment.",
keywords = "Empowerment, Goal-directed Behaviour, Information Theory, Intrinsic Motivation, Markov Decision Process, Robustness.",
author = "{Catenacci Volpi}, Nicola and Daniel Polani",
note = "{\textcopyright} 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. ",
year = "2020",
month = dec,
day = "7",
doi = "10.1109/TCDS.2020.3042938",
language = "English",
journal = "IEEE Transactions on Cognitive and Developmental Systems",
issn = "2379-8920",
publisher = "IEEE",

}

RIS

TY - JOUR

T1 - Goal-directed Empowerment: combining Intrinsic Motivation and Task-oriented Behaviour

AU - Catenacci Volpi, Nicola

AU - Polani, Daniel

N1 - © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2020/12/7

Y1 - 2020/12/7

N2 - Empowerment is an information-theoretic measure representing the capacity of an agent to affect its environment. It quantifies its ability to inject information in the environment via its actions and to recapture this information through its sensors. In a nutshell, it measures the number of future options available and perceivable by the agent. Originally, the definition of empowerment does not depend on any particular extrinsic goal and it is determined only by the interaction of the agent with the world and the structure of its action-perception cycle.In this paper we introduce a new formalism that combines empowerment maximization with externally specifiable goal-directed behaviour. This has two main implications: on the one hand, the study of the relationship between empowerment optimization and goal-directedness, to investigate to which extent these two desirable behaviours can co-exist; on the other hand, from a more operational point of view, the derivation of a method to generate a behaviour (i.e., a policy of a Markov decision process) that is both empowered and goal-directed, in order to design agents capable of being as "empowered" as possible when facing any extrinsic task. Finally, we study how this hybrid policy is able to handle problems of uncertain or changing goals and delayed goal commitment.

AB - Empowerment is an information-theoretic measure representing the capacity of an agent to affect its environment. It quantifies its ability to inject information in the environment via its actions and to recapture this information through its sensors. In a nutshell, it measures the number of future options available and perceivable by the agent. Originally, the definition of empowerment does not depend on any particular extrinsic goal and it is determined only by the interaction of the agent with the world and the structure of its action-perception cycle.In this paper we introduce a new formalism that combines empowerment maximization with externally specifiable goal-directed behaviour. This has two main implications: on the one hand, the study of the relationship between empowerment optimization and goal-directedness, to investigate to which extent these two desirable behaviours can co-exist; on the other hand, from a more operational point of view, the derivation of a method to generate a behaviour (i.e., a policy of a Markov decision process) that is both empowered and goal-directed, in order to design agents capable of being as "empowered" as possible when facing any extrinsic task. Finally, we study how this hybrid policy is able to handle problems of uncertain or changing goals and delayed goal commitment.

KW - Empowerment

KW - Goal-directed Behaviour

KW - Information Theory

KW - Intrinsic Motivation

KW - Markov Decision Process

KW - Robustness.

UR - http://www.scopus.com/inward/record.url?scp=85097946551&partnerID=8YFLogxK

U2 - 10.1109/TCDS.2020.3042938

DO - 10.1109/TCDS.2020.3042938

M3 - Article

JO - IEEE Transactions on Cognitive and Developmental Systems

JF - IEEE Transactions on Cognitive and Developmental Systems

SN - 2379-8920

ER -