Learning Structured Decision Problems with Unawareness

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish
Title of host publicationProceedings of the 36th International Conference on Machine Learning (ICML)
EditorsKamalika Chaudhuri, Rusland Salakhutdinov
Place of PublicationLong Beach, USA
PublisherPMLR
Pages2941-2950
Number of pages10
Volume97
Publication statusE-pub ahead of print - 3 Jul 2019
EventThirty-sixth International Conference on Machine Learning - Long Beach Convention Center, Long Beach, United States
Duration: 9 Jun 201915 Jun 2019
Conference number: 36
https://icml.cc/Conferences/2019

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume97
ISSN (Electronic)2640-3498

Conference

ConferenceThirty-sixth International Conference on Machine Learning
Abbreviated titleICML 2019
Country/TerritoryUnited States
CityLong Beach
Period9/06/1915/06/19
Internet address

Fingerprint

Dive into the research topics of 'Learning Structured Decision Problems with Unawareness'. Together they form a unique fingerprint.

Cite this