Designing experiments to test and improve hypothesized planning knowledge derived from demonstration

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A number of techniques have been developed to effectively extract and generalize planning knowledge based on expert demonstration. In this paper we consider a complementary approach to learning in which experiments are designed to test hypothesized planning knowledge. In particular, we describe an algorithm that automatically generates experiments to test assertions about plan-step ordering. Experimenting with plan-step ordering can identify asserted ordering constraints that are in fact not necessary, as well as uncover necessary ordering constraints previously not represented. The algorithm consists of three parts: identifying the space of step-ordering hypotheses, efficiently generating ordering tests, and planning experiments that use the tests to identify order constraints that are not currently represented. This method is implemented in the CMAX experiment design module and is part of the POIROT integrated learning system. We discuss the role of experimentation in planning knowledge refinement and some future directions for CMAX's development.

Original languageEnglish (US)
Title of host publicationAAAI Workshop - Technical Report
Pages20-25
Number of pages6
VolumeWS-07-02
StatePublished - 2007
Externally publishedYes
Event2007 AAAI Workshop - Vancouver, BC, Canada
Duration: Jul 23 2007Jul 23 2007

Other

Other2007 AAAI Workshop
CountryCanada
CityVancouver, BC
Period7/23/077/23/07

Fingerprint

Demonstrations
Planning
Experiments
Learning systems

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Designing experiments to test and improve hypothesized planning knowledge derived from demonstration. / Morrison, Clayton T; Cohen, Paul R.

AAAI Workshop - Technical Report. Vol. WS-07-02 2007. p. 20-25.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Morrison, CT & Cohen, PR 2007, Designing experiments to test and improve hypothesized planning knowledge derived from demonstration. in AAAI Workshop - Technical Report. vol. WS-07-02, pp. 20-25, 2007 AAAI Workshop, Vancouver, BC, Canada, 7/23/07.
@inproceedings{f52bee7dfe7e43ad9f342a863639faf7,
title = "Designing experiments to test and improve hypothesized planning knowledge derived from demonstration",
abstract = "A number of techniques have been developed to effectively extract and generalize planning knowledge based on expert demonstration. In this paper we consider a complementary approach to learning in which experiments are designed to test hypothesized planning knowledge. In particular, we describe an algorithm that automatically generates experiments to test assertions about plan-step ordering. Experimenting with plan-step ordering can identify asserted ordering constraints that are in fact not necessary, as well as uncover necessary ordering constraints previously not represented. The algorithm consists of three parts: identifying the space of step-ordering hypotheses, efficiently generating ordering tests, and planning experiments that use the tests to identify order constraints that are not currently represented. This method is implemented in the CMAX experiment design module and is part of the POIROT integrated learning system. We discuss the role of experimentation in planning knowledge refinement and some future directions for CMAX's development.",
author = "Morrison, {Clayton T} and Cohen, {Paul R}",
year = "2007",
language = "English (US)",
isbn = "9781577353294",
volume = "WS-07-02",
pages = "20--25",
booktitle = "AAAI Workshop - Technical Report",

}

TY - GEN

T1 - Designing experiments to test and improve hypothesized planning knowledge derived from demonstration

AU - Morrison, Clayton T

AU - Cohen, Paul R

PY - 2007

Y1 - 2007

N2 - A number of techniques have been developed to effectively extract and generalize planning knowledge based on expert demonstration. In this paper we consider a complementary approach to learning in which experiments are designed to test hypothesized planning knowledge. In particular, we describe an algorithm that automatically generates experiments to test assertions about plan-step ordering. Experimenting with plan-step ordering can identify asserted ordering constraints that are in fact not necessary, as well as uncover necessary ordering constraints previously not represented. The algorithm consists of three parts: identifying the space of step-ordering hypotheses, efficiently generating ordering tests, and planning experiments that use the tests to identify order constraints that are not currently represented. This method is implemented in the CMAX experiment design module and is part of the POIROT integrated learning system. We discuss the role of experimentation in planning knowledge refinement and some future directions for CMAX's development.

AB - A number of techniques have been developed to effectively extract and generalize planning knowledge based on expert demonstration. In this paper we consider a complementary approach to learning in which experiments are designed to test hypothesized planning knowledge. In particular, we describe an algorithm that automatically generates experiments to test assertions about plan-step ordering. Experimenting with plan-step ordering can identify asserted ordering constraints that are in fact not necessary, as well as uncover necessary ordering constraints previously not represented. The algorithm consists of three parts: identifying the space of step-ordering hypotheses, efficiently generating ordering tests, and planning experiments that use the tests to identify order constraints that are not currently represented. This method is implemented in the CMAX experiment design module and is part of the POIROT integrated learning system. We discuss the role of experimentation in planning knowledge refinement and some future directions for CMAX's development.

UR - http://www.scopus.com/inward/record.url?scp=51849090462&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51849090462&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:51849090462

SN - 9781577353294

VL - WS-07-02

SP - 20

EP - 25

BT - AAAI Workshop - Technical Report

ER -