Combining reinforcement learning with information-state update rules

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

25 Citations (Scopus)

Abstract

Reinforcement learning gives a way to learn under what circumstances to perform which actions. However, this approach lacks a formal framework for specifying hand-crafted restrictions, for specifying the effects of the system actions, or for specifying the user simulation. The information state approach, in contrast, allows system and user behavior to be specified as update rules, with preconditions and effects. This approach can be used to specify complex dialogue behavior in a systematic way. We propose combining these two approaches, thus allowing a formal specification of the dialogue behavior, and allowing hand-crafted preconditions, with remaining ones determined via reinforcement learning so as to minimize dialogue cost.

Original languageEnglish (US)
Title of host publicationNAACL HLT 2007 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference
Pages268-275
Number of pages8
StatePublished - 2007
EventHuman Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007 - Rochester, NY, United States
Duration: Apr 22 2007Apr 27 2007

Other

OtherHuman Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007
CountryUnited States
CityRochester, NY
Period4/22/074/27/07

Fingerprint

reinforcement
dialogue
learning
simulation
lack
costs
Reinforcement Learning

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Heeman, P. (2007). Combining reinforcement learning with information-state update rules. In NAACL HLT 2007 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference (pp. 268-275)

Combining reinforcement learning with information-state update rules. / Heeman, Peter.

NAACL HLT 2007 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. 2007. p. 268-275.

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

Heeman, P 2007, Combining reinforcement learning with information-state update rules. in NAACL HLT 2007 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. pp. 268-275, Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, NAACL HLT 2007, Rochester, NY, United States, 4/22/07.
Heeman P. Combining reinforcement learning with information-state update rules. In NAACL HLT 2007 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. 2007. p. 268-275
Heeman, Peter. / Combining reinforcement learning with information-state update rules. NAACL HLT 2007 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. 2007. pp. 268-275
@inproceedings{127a4c13195643cea9a81a1074302bc6,
title = "Combining reinforcement learning with information-state update rules",
abstract = "Reinforcement learning gives a way to learn under what circumstances to perform which actions. However, this approach lacks a formal framework for specifying hand-crafted restrictions, for specifying the effects of the system actions, or for specifying the user simulation. The information state approach, in contrast, allows system and user behavior to be specified as update rules, with preconditions and effects. This approach can be used to specify complex dialogue behavior in a systematic way. We propose combining these two approaches, thus allowing a formal specification of the dialogue behavior, and allowing hand-crafted preconditions, with remaining ones determined via reinforcement learning so as to minimize dialogue cost.",
author = "Peter Heeman",
year = "2007",
language = "English (US)",
pages = "268--275",
booktitle = "NAACL HLT 2007 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference",

}

TY - GEN

T1 - Combining reinforcement learning with information-state update rules

AU - Heeman, Peter

PY - 2007

Y1 - 2007

N2 - Reinforcement learning gives a way to learn under what circumstances to perform which actions. However, this approach lacks a formal framework for specifying hand-crafted restrictions, for specifying the effects of the system actions, or for specifying the user simulation. The information state approach, in contrast, allows system and user behavior to be specified as update rules, with preconditions and effects. This approach can be used to specify complex dialogue behavior in a systematic way. We propose combining these two approaches, thus allowing a formal specification of the dialogue behavior, and allowing hand-crafted preconditions, with remaining ones determined via reinforcement learning so as to minimize dialogue cost.

AB - Reinforcement learning gives a way to learn under what circumstances to perform which actions. However, this approach lacks a formal framework for specifying hand-crafted restrictions, for specifying the effects of the system actions, or for specifying the user simulation. The information state approach, in contrast, allows system and user behavior to be specified as update rules, with preconditions and effects. This approach can be used to specify complex dialogue behavior in a systematic way. We propose combining these two approaches, thus allowing a formal specification of the dialogue behavior, and allowing hand-crafted preconditions, with remaining ones determined via reinforcement learning so as to minimize dialogue cost.

UR - http://www.scopus.com/inward/record.url?scp=70349253156&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349253156&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:70349253156

SP - 268

EP - 275

BT - NAACL HLT 2007 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference

ER -