Learning Structured Decision Problems with Unawareness

Craig Innes; Alex Lascarides

Learning Structured Decision Problems with Unawareness

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

Abstract

Structured models of decision making often assume an agent is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we learn influence diagrams from both domain exploration and expert assertions in a way which guarantees convergence to optimal behaviour, even when the agent starts unaware of actions or belief variables that are critical to success. Our experiments show that our agent learns optimal behaviour on small and large decision problems, and that allowing an agent to conserve information upon discovering new possibilities results in faster convergence.

Original language	English
Title of host publication	Proceedings of the 36th International Conference on Machine Learning (ICML)
Editors	Kamalika Chaudhuri, Rusland Salakhutdinov
Place of Publication	Long Beach, USA
Publisher	PMLR
Pages	2941-2950
Number of pages	10
Volume	97
Publication status	E-pub ahead of print - 3 Jul 2019
Event	Thirty-sixth International Conference on Machine Learning - Long Beach Convention Center, Long Beach, United States Duration: 9 Jun 2019 → 15 Jun 2019 Conference number: 36 https://icml.cc/Conferences/2019

Publication series

Name	Proceedings of Machine Learning Research
Publisher	PMLR
Volume	97
ISSN (Electronic)	2640-3498

Conference

Conference	Thirty-sixth International Conference on Machine Learning
Abbreviated title	ICML 2019
Country/Territory	United States
City	Long Beach
Period	9/06/19 → 15/06/19
Internet address	https://icml.cc/Conferences/2019

Access to Document

Learning Structured Decision_INNES_DoA210419_AFVAccepted author manuscript, 561 KB
Learning Structured Decision_INNES_DoA210419_supplementaryOther version, 470 KB

http://proceedings.mlr.press/v97/innes19a.html

Cite this

@inproceedings{0c9a6fcfa659489184946d4dd43c7766,

title = "Learning Structured Decision Problems with Unawareness",

abstract = "Structured models of decision making often assume an agent is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we learn influence diagrams from both domain exploration and expert assertions in a way which guarantees convergence to optimal behaviour, even when the agent starts unaware of actions or belief variables that are critical to success. Our experiments show that our agent learns optimal behaviour on small and large decision problems, and that allowing an agent to conserve information upon discovering new possibilities results in faster convergence.",

author = "Craig Innes and Alex Lascarides",

year = "2019",

month = jul,

day = "3",

language = "English",

volume = "97",

series = "Proceedings of Machine Learning Research",

publisher = "PMLR",

pages = "2941--2950",

editor = "Kamalika Chaudhuri and Rusland Salakhutdinov",

booktitle = "Proceedings of the 36th International Conference on Machine Learning (ICML)",

note = "Thirty-sixth International Conference on Machine Learning, ICML 2019 ; Conference date: 09-06-2019 Through 15-06-2019",

url = "https://icml.cc/Conferences/2019",

}

Innes, C & Lascarides, A 2019, Learning Structured Decision Problems with Unawareness. in K Chaudhuri & R Salakhutdinov (eds), Proceedings of the 36th International Conference on Machine Learning (ICML). vol. 97, Proceedings of Machine Learning Research, vol. 97, PMLR, Long Beach, USA, pp. 2941-2950, Thirty-sixth International Conference on Machine Learning, Long Beach, California, United States, 9/06/19. <http://proceedings.mlr.press/v97/innes19a.html>

Learning Structured Decision Problems with Unawareness. / Innes, Craig ; Lascarides, Alex.

Proceedings of the 36th International Conference on Machine Learning (ICML). ed. / Kamalika Chaudhuri; Rusland Salakhutdinov. Vol. 97 Long Beach, USA : PMLR, 2019. p. 2941-2950 (Proceedings of Machine Learning Research; Vol. 97).

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

TY - GEN

T1 - Learning Structured Decision Problems with Unawareness

AU - Innes, Craig

AU - Lascarides, Alex

N1 - Conference code: 36

PY - 2019/7/3

Y1 - 2019/7/3

N2 - Structured models of decision making often assume an agent is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we learn influence diagrams from both domain exploration and expert assertions in a way which guarantees convergence to optimal behaviour, even when the agent starts unaware of actions or belief variables that are critical to success. Our experiments show that our agent learns optimal behaviour on small and large decision problems, and that allowing an agent to conserve information upon discovering new possibilities results in faster convergence.

AB - Structured models of decision making often assume an agent is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we learn influence diagrams from both domain exploration and expert assertions in a way which guarantees convergence to optimal behaviour, even when the agent starts unaware of actions or belief variables that are critical to success. Our experiments show that our agent learns optimal behaviour on small and large decision problems, and that allowing an agent to conserve information upon discovering new possibilities results in faster convergence.

M3 - Conference contribution

VL - 97

T3 - Proceedings of Machine Learning Research

SP - 2941

EP - 2950

BT - Proceedings of the 36th International Conference on Machine Learning (ICML)

A2 - Chaudhuri, Kamalika

A2 - Salakhutdinov, Rusland

PB - PMLR

CY - Long Beach, USA

T2 - Thirty-sixth International Conference on Machine Learning

Y2 - 9 June 2019 through 15 June 2019

ER -

Learning Structured Decision Problems with Unawareness

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this