Modulation of exploratory behavior for adaptation to the context

A. Blanchard; Lola Cañamero

Modulation of exploratory behavior for adaptation to the context

A. Blanchard, Lola Cañamero

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

12 Citations (Scopus)

27 Downloads (Pure)

Abstract

For autonomous agents (children, animals or robots), exploratory learning is essential as it allows them to take advantage of their past experiences in order to improve their reactions in any situation similar to a situation already experimented. We have already exposed in Blanchard and Canamero (2005) how a robot can learn which situations it should memorize and try to reach, but we expose here architectures allowing the robot to take initiatives and explore new situations by itself. However, exploring is a risky behavior and we propose to moderate this behavior using novelty and context based on observations of animals behaviors. After having implemented and tested these architectures, we present a very interesting emergent behavior which is low-level imitation modulated by context.

Original language	English
Title of host publication	Procs of Biologically Inspired Robotics Symposium 2006
Subtitle of host publication	Part of AISB'06
Pages	131-137
Publication status	Published - 2006
Event	AISB'06: Adaptation in Artificial and Biological Systems - Bristol, United Kingdom Duration: 3 Apr 2006 → 4 Apr 2006

Conference

Conference	AISB'06: Adaptation in Artificial and Biological Systems
Country/Territory	United Kingdom
City	Bristol
Period	3/04/06 → 4/04/06

Access to Document

902175Accepted author manuscript, 851 KB

Cite this

@inproceedings{40ddfdc61a3749ed82752927104e14f9,

title = "Modulation of exploratory behavior for adaptation to the context",

abstract = "For autonomous agents (children, animals or robots), exploratory learning is essential as it allows them to take advantage of their past experiences in order to improve their reactions in any situation similar to a situation already experimented. We have already exposed in Blanchard and Canamero (2005) how a robot can learn which situations it should memorize and try to reach, but we expose here architectures allowing the robot to take initiatives and explore new situations by itself. However, exploring is a risky behavior and we propose to moderate this behavior using novelty and context based on observations of animals behaviors. After having implemented and tested these architectures, we present a very interesting emergent behavior which is low-level imitation modulated by context.",

author = "A. Blanchard and Lola Ca{\~n}amero",

year = "2006",

language = "English",

pages = "131--137",

booktitle = "Procs of Biologically Inspired Robotics Symposium 2006",

note = "AISB'06: Adaptation in Artificial and Biological Systems ; Conference date: 03-04-2006 Through 04-04-2006",

}

TY - GEN

T1 - Modulation of exploratory behavior for adaptation to the context

AU - Blanchard, A.

AU - Cañamero, Lola

PY - 2006

Y1 - 2006

N2 - For autonomous agents (children, animals or robots), exploratory learning is essential as it allows them to take advantage of their past experiences in order to improve their reactions in any situation similar to a situation already experimented. We have already exposed in Blanchard and Canamero (2005) how a robot can learn which situations it should memorize and try to reach, but we expose here architectures allowing the robot to take initiatives and explore new situations by itself. However, exploring is a risky behavior and we propose to moderate this behavior using novelty and context based on observations of animals behaviors. After having implemented and tested these architectures, we present a very interesting emergent behavior which is low-level imitation modulated by context.

AB - For autonomous agents (children, animals or robots), exploratory learning is essential as it allows them to take advantage of their past experiences in order to improve their reactions in any situation similar to a situation already experimented. We have already exposed in Blanchard and Canamero (2005) how a robot can learn which situations it should memorize and try to reach, but we expose here architectures allowing the robot to take initiatives and explore new situations by itself. However, exploring is a risky behavior and we propose to moderate this behavior using novelty and context based on observations of animals behaviors. After having implemented and tested these architectures, we present a very interesting emergent behavior which is low-level imitation modulated by context.

M3 - Conference contribution

SP - 131

EP - 137

BT - Procs of Biologically Inspired Robotics Symposium 2006

T2 - AISB'06: Adaptation in Artificial and Biological Systems

Y2 - 3 April 2006 through 4 April 2006

ER -

Modulation of exploratory behavior for adaptation to the context

Abstract

Conference

Access to Document

Fingerprint

Cite this