Imitation Learning Based on an Intrinsic Motivation Mechanism for Efficient Coding

A hypothesis regarding the development of imitation learning is presented that is rooted in intrinsic motivations. It is derived from a recently proposed form of intrinsically motivated learning (IML) for efficient coding in active perception, wherein an agent learns to perform actions with its sens...

Full description

Bibliographic Details
Published in:Frontiers in Psychology
Main Author: Jochen eTriesch
Format: Article
Language:English
Published: Frontiers Media S.A. 2013-11-01
Subjects:
Online Access:http://journal.frontiersin.org/Journal/10.3389/fpsyg.2013.00800/full
_version_ 1851877674148954112
author Jochen eTriesch
author_facet Jochen eTriesch
author_sort Jochen eTriesch
collection DOAJ
container_title Frontiers in Psychology
description A hypothesis regarding the development of imitation learning is presented that is rooted in intrinsic motivations. It is derived from a recently proposed form of intrinsically motivated learning (IML) for efficient coding in active perception, wherein an agent learns to perform actions with its sense organs to facilitate efficient encoding of the sensory data. To this end, actions of the sense organs that improve the encoding of the sensory data trigger an internally generated reinforcement signal. Here it is argued that the same IML mechanism might also support the development of imitation when general actions beyond those of the sense organs are considered: The learner first observes a tutor performing a behavior and learns a model of the the behavior's sensory consequences. The learner then acts itself and receives an internally generated reinforcement signal reflecting how well the sensory consequences of its own behavior are encoded by the sensory model. Actions that are more similar to those of the tutor will lead to sensory signals that are easier to encode and produce a higher reinforcement signal. Through this, the learner's behavior is progressively tuned to make the sensory consequences of its actions match the learned sensory model. I discuss this mechanism in the context of human language acquisition and bird song learning where similar ideas have been proposed. The suggested mechanism also offers an account for the development of mirror neurons and makes a number of predictions. Overall, it establishes a connection between principles of efficient coding, intrinsic motivations and imitation.
format Article
id doaj-art-400cc328c9e649e893ae0aebc438dfda
institution Directory of Open Access Journals
issn 1664-1078
language English
publishDate 2013-11-01
publisher Frontiers Media S.A.
record_format Article
spelling doaj-art-400cc328c9e649e893ae0aebc438dfda2025-08-19T22:14:28ZengFrontiers Media S.A.Frontiers in Psychology1664-10782013-11-01410.3389/fpsyg.2013.0080062419Imitation Learning Based on an Intrinsic Motivation Mechanism for Efficient CodingJochen eTriesch0Frankfurt Institute for Advanced Studies (FIAS)A hypothesis regarding the development of imitation learning is presented that is rooted in intrinsic motivations. It is derived from a recently proposed form of intrinsically motivated learning (IML) for efficient coding in active perception, wherein an agent learns to perform actions with its sense organs to facilitate efficient encoding of the sensory data. To this end, actions of the sense organs that improve the encoding of the sensory data trigger an internally generated reinforcement signal. Here it is argued that the same IML mechanism might also support the development of imitation when general actions beyond those of the sense organs are considered: The learner first observes a tutor performing a behavior and learns a model of the the behavior's sensory consequences. The learner then acts itself and receives an internally generated reinforcement signal reflecting how well the sensory consequences of its own behavior are encoded by the sensory model. Actions that are more similar to those of the tutor will lead to sensory signals that are easier to encode and produce a higher reinforcement signal. Through this, the learner's behavior is progressively tuned to make the sensory consequences of its actions match the learned sensory model. I discuss this mechanism in the context of human language acquisition and bird song learning where similar ideas have been proposed. The suggested mechanism also offers an account for the development of mirror neurons and makes a number of predictions. Overall, it establishes a connection between principles of efficient coding, intrinsic motivations and imitation.http://journal.frontiersin.org/Journal/10.3389/fpsyg.2013.00800/fullImitationmirror neuronlanguage developmentefficient codingbird songintrinsic motivation
spellingShingle Jochen eTriesch
Imitation Learning Based on an Intrinsic Motivation Mechanism for Efficient Coding
Imitation
mirror neuron
language development
efficient coding
bird song
intrinsic motivation
title Imitation Learning Based on an Intrinsic Motivation Mechanism for Efficient Coding
title_full Imitation Learning Based on an Intrinsic Motivation Mechanism for Efficient Coding
title_fullStr Imitation Learning Based on an Intrinsic Motivation Mechanism for Efficient Coding
title_full_unstemmed Imitation Learning Based on an Intrinsic Motivation Mechanism for Efficient Coding
title_short Imitation Learning Based on an Intrinsic Motivation Mechanism for Efficient Coding
title_sort imitation learning based on an intrinsic motivation mechanism for efficient coding
topic Imitation
mirror neuron
language development
efficient coding
bird song
intrinsic motivation
url http://journal.frontiersin.org/Journal/10.3389/fpsyg.2013.00800/full
work_keys_str_mv AT jochenetriesch imitationlearningbasedonanintrinsicmotivationmechanismforefficientcoding