Motivation Driven Learning of Action Affordances

I. Cos-Aguilera; Lola Cañamero; G. Hayes

Motivation Driven Learning of Action Affordances

I. Cos-Aguilera, Lola Cañamero, G. Hayes

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

183 Downloads (Pure)

Abstract

Survival in the animal realm often depends on the ability to elucidate the potentialities for action offered by every situation. This paper argues that affordance learning is a powerful ability for adaptive, embodied, situated agents, and presents a motivation-driven method for their learning. The method proposed considers the agent and its environment as a single unit, thus intrinsically relating agent's interactions to fluctuations of the agent's internal motivation. Being that the motivational state is an expression of the agent's physiology, the existing causality of interactions and their effect on the motivational state is exploited as a principle to learn object affordances. The hypothesis is tested in a Webots 4.0 simulator with a Khepera robot.

Original language	English
Title of host publication	Procs of Symposium on Agents that Want and Like - Motivational and Emotional Roots of Cognition and Action
Subtitle of host publication	AISB'05
Publisher	The Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB)
Pages	33-36
ISBN (Print)	1-902956-41-7
Publication status	Published - 2005
Event	SSAISB Convention 2005 - Hatfield, United Kingdom Duration: 12 Apr 2005 → 15 Apr 2005

Conference

Conference	SSAISB Convention 2005
Country/Territory	United Kingdom
City	Hatfield
Period	12/04/05 → 15/04/05

Access to Document

902180Final published version, 2.9 MB

Cite this

@inproceedings{7b0a87f6a35e4c4aa39ac961f7a71f74,

title = "Motivation Driven Learning of Action Affordances",

abstract = "Survival in the animal realm often depends on the ability to elucidate the potentialities for action offered by every situation. This paper argues that affordance learning is a powerful ability for adaptive, embodied, situated agents, and presents a motivation-driven method for their learning. The method proposed considers the agent and its environment as a single unit, thus intrinsically relating agent's interactions to fluctuations of the agent's internal motivation. Being that the motivational state is an expression of the agent's physiology, the existing causality of interactions and their effect on the motivational state is exploited as a principle to learn object affordances. The hypothesis is tested in a Webots 4.0 simulator with a Khepera robot.",

author = "I. Cos-Aguilera and Lola Ca{\~n}amero and G. Hayes",

year = "2005",

language = "English",

isbn = "1-902956-41-7",

pages = "33--36",

booktitle = "Procs of Symposium on Agents that Want and Like - Motivational and Emotional Roots of Cognition and Action",

publisher = "The Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB)",

address = "United Kingdom",

note = "SSAISB Convention 2005 ; Conference date: 12-04-2005 Through 15-04-2005",

}

Cos-Aguilera, I, Cañamero, L & Hayes, G 2005, Motivation Driven Learning of Action Affordances. in Procs of Symposium on Agents that Want and Like - Motivational and Emotional Roots of Cognition and Action: AISB'05. The Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB), pp. 33-36, SSAISB Convention 2005, Hatfield, United Kingdom, 12/04/05.

Motivation Driven Learning of Action Affordances. / Cos-Aguilera, I.; Cañamero, Lola; Hayes, G.
Procs of Symposium on Agents that Want and Like - Motivational and Emotional Roots of Cognition and Action: AISB'05. The Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB), 2005. p. 33-36.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Motivation Driven Learning of Action Affordances

AU - Cos-Aguilera, I.

AU - Cañamero, Lola

AU - Hayes, G.

PY - 2005

Y1 - 2005

N2 - Survival in the animal realm often depends on the ability to elucidate the potentialities for action offered by every situation. This paper argues that affordance learning is a powerful ability for adaptive, embodied, situated agents, and presents a motivation-driven method for their learning. The method proposed considers the agent and its environment as a single unit, thus intrinsically relating agent's interactions to fluctuations of the agent's internal motivation. Being that the motivational state is an expression of the agent's physiology, the existing causality of interactions and their effect on the motivational state is exploited as a principle to learn object affordances. The hypothesis is tested in a Webots 4.0 simulator with a Khepera robot.

AB - Survival in the animal realm often depends on the ability to elucidate the potentialities for action offered by every situation. This paper argues that affordance learning is a powerful ability for adaptive, embodied, situated agents, and presents a motivation-driven method for their learning. The method proposed considers the agent and its environment as a single unit, thus intrinsically relating agent's interactions to fluctuations of the agent's internal motivation. Being that the motivational state is an expression of the agent's physiology, the existing causality of interactions and their effect on the motivational state is exploited as a principle to learn object affordances. The hypothesis is tested in a Webots 4.0 simulator with a Khepera robot.

M3 - Conference contribution

SN - 1-902956-41-7

SP - 33

EP - 36

BT - Procs of Symposium on Agents that Want and Like - Motivational and Emotional Roots of Cognition and Action

PB - The Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB)

T2 - SSAISB Convention 2005

Y2 - 12 April 2005 through 15 April 2005

ER -

Motivation Driven Learning of Action Affordances

Abstract

Conference

Access to Document

Fingerprint

Cite this