Agency, learning and animal-based reinforcement learning

E. Alonso, E. Mondragon

Research output: Chapter in Book/Report/Conference proceedingChapter

4 Citations (Scopus)

Abstract

In this paper we contend that adaptation and learning are essential in designing and building autonomous software systems for real-life applications. In particular, we will argue that in dynamic, complex domains autonomy and adaptability go hand by hand, that is, that agents cannot make their own decisions if they are not provided with the ability to adapt to the changes occurring in the environment they are situated. In the second part, we maintain the need for taking up animal learning models and theories to overcome some serious problems in reinforcement learning.
Original languageEnglish
Title of host publicationAgents and Computational Autonomy
Subtitle of host publicationPotential, Risks, and Solutions
EditorsM Nickles, M Rovatsos, G Weiss
Place of PublicationBerlin, Germany
PublisherSpringer
Pages1-6
Number of pages6
ISBN (Print)9783540224778
Publication statusPublished - 2004

Publication series

NameLecture Notes in Computer Science
Volume2969

Fingerprint

Reinforcement learning
Animals

Cite this

Alonso, E., & Mondragon, E. (2004). Agency, learning and animal-based reinforcement learning. In M. Nickles, M. Rovatsos, & G. Weiss (Eds.), Agents and Computational Autonomy: Potential, Risks, and Solutions (pp. 1-6). (Lecture Notes in Computer Science; Vol. 2969). Berlin, Germany: Springer.

Agency, learning and animal-based reinforcement learning. / Alonso, E.; Mondragon, E.

Agents and Computational Autonomy: Potential, Risks, and Solutions. ed. / M Nickles; M Rovatsos; G Weiss. Berlin, Germany : Springer, 2004. p. 1-6 (Lecture Notes in Computer Science; Vol. 2969).

Research output: Chapter in Book/Report/Conference proceedingChapter

Alonso, E & Mondragon, E 2004, Agency, learning and animal-based reinforcement learning. in M Nickles, M Rovatsos & G Weiss (eds), Agents and Computational Autonomy: Potential, Risks, and Solutions. Lecture Notes in Computer Science, vol. 2969, Springer, Berlin, Germany, pp. 1-6.
Alonso E, Mondragon E. Agency, learning and animal-based reinforcement learning. In Nickles M, Rovatsos M, Weiss G, editors, Agents and Computational Autonomy: Potential, Risks, and Solutions. Berlin, Germany: Springer. 2004. p. 1-6. (Lecture Notes in Computer Science).
Alonso, E. ; Mondragon, E. / Agency, learning and animal-based reinforcement learning. Agents and Computational Autonomy: Potential, Risks, and Solutions. editor / M Nickles ; M Rovatsos ; G Weiss. Berlin, Germany : Springer, 2004. pp. 1-6 (Lecture Notes in Computer Science).
@inbook{5ab42190489e4ebb986c56307c6d66b3,
title = "Agency, learning and animal-based reinforcement learning",
abstract = "In this paper we contend that adaptation and learning are essential in designing and building autonomous software systems for real-life applications. In particular, we will argue that in dynamic, complex domains autonomy and adaptability go hand by hand, that is, that agents cannot make their own decisions if they are not provided with the ability to adapt to the changes occurring in the environment they are situated. In the second part, we maintain the need for taking up animal learning models and theories to overcome some serious problems in reinforcement learning.",
author = "E. Alonso and E. Mondragon",
note = "ID number: ISIP:000223492900001",
year = "2004",
language = "English",
isbn = "9783540224778",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "1--6",
editor = "M Nickles and M Rovatsos and G Weiss",
booktitle = "Agents and Computational Autonomy",

}

TY - CHAP

T1 - Agency, learning and animal-based reinforcement learning

AU - Alonso, E.

AU - Mondragon, E.

N1 - ID number: ISIP:000223492900001

PY - 2004

Y1 - 2004

N2 - In this paper we contend that adaptation and learning are essential in designing and building autonomous software systems for real-life applications. In particular, we will argue that in dynamic, complex domains autonomy and adaptability go hand by hand, that is, that agents cannot make their own decisions if they are not provided with the ability to adapt to the changes occurring in the environment they are situated. In the second part, we maintain the need for taking up animal learning models and theories to overcome some serious problems in reinforcement learning.

AB - In this paper we contend that adaptation and learning are essential in designing and building autonomous software systems for real-life applications. In particular, we will argue that in dynamic, complex domains autonomy and adaptability go hand by hand, that is, that agents cannot make their own decisions if they are not provided with the ability to adapt to the changes occurring in the environment they are situated. In the second part, we maintain the need for taking up animal learning models and theories to overcome some serious problems in reinforcement learning.

M3 - Chapter

SN - 9783540224778

T3 - Lecture Notes in Computer Science

SP - 1

EP - 6

BT - Agents and Computational Autonomy

A2 - Nickles, M

A2 - Rovatsos, M

A2 - Weiss, G

PB - Springer

CY - Berlin, Germany

ER -