Representations for action selection learning from real-time observation of task experts

Mark A. Wood, Joanna J. Bryson

Research output: Contribution to journalConference article

Abstract

The association of perception and action is key to learning by observation in general, and to program-level task imitation in particular. The question is how to structure this information such that learning is tractable for resource-bounded agents. By introducing a combination of symbolic representation with Bayesian reasoning, we demonstrate both theoretical and empirical improvements to a general-purpose imitation system originally based on a model of infant social learning. We also show how prior task knowledge and selective attention can be rigorously incorporated via loss matrices and Automatic Relevance Determination respectively.

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

@article{7fc0d0f6e492452ba41a4e4a4145305f,
title = "Representations for action selection learning from real-time observation of task experts",
abstract = "The association of perception and action is key to learning by observation in general, and to program-level task imitation in particular. The question is how to structure this information such that learning is tractable for resource-bounded agents. By introducing a combination of symbolic representation with Bayesian reasoning, we demonstrate both theoretical and empirical improvements to a general-purpose imitation system originally based on a model of infant social learning. We also show how prior task knowledge and selective attention can be rigorously incorporated via loss matrices and Automatic Relevance Determination respectively.",
author = "Wood, {Mark A.} and Bryson, {Joanna J.}",
year = "2007",
month = "12",
day = "1",
language = "English",
pages = "641--646",
journal = "IJCAI International Joint Conference on Artificial Intelligence",
issn = "1045-0823",
publisher = "Lawrence Erlbaum Associates",

}

TY - JOUR

T1 - Representations for action selection learning from real-time observation of task experts

AU - Wood, Mark A.

AU - Bryson, Joanna J.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - The association of perception and action is key to learning by observation in general, and to program-level task imitation in particular. The question is how to structure this information such that learning is tractable for resource-bounded agents. By introducing a combination of symbolic representation with Bayesian reasoning, we demonstrate both theoretical and empirical improvements to a general-purpose imitation system originally based on a model of infant social learning. We also show how prior task knowledge and selective attention can be rigorously incorporated via loss matrices and Automatic Relevance Determination respectively.

AB - The association of perception and action is key to learning by observation in general, and to program-level task imitation in particular. The question is how to structure this information such that learning is tractable for resource-bounded agents. By introducing a combination of symbolic representation with Bayesian reasoning, we demonstrate both theoretical and empirical improvements to a general-purpose imitation system originally based on a model of infant social learning. We also show how prior task knowledge and selective attention can be rigorously incorporated via loss matrices and Automatic Relevance Determination respectively.

UR - http://www.scopus.com/inward/record.url?scp=84880911394&partnerID=8YFLogxK

M3 - Conference article

SP - 641

EP - 646

JO - IJCAI International Joint Conference on Artificial Intelligence

T2 - IJCAI International Joint Conference on Artificial Intelligence

JF - IJCAI International Joint Conference on Artificial Intelligence

SN - 1045-0823

ER -