Abstract

We consider the problem of creating assistants that can help agents solve new sequential decision problems, assuming the agent is not able to specify the reward function explicitly to the assistant. Instead of acting in place of the agent as in current automation-based approaches, we give the assistant an advisory role and keep the agent in the loop as the main decision maker. The difficulty is that we must account for potential biases of the agent which may cause it to seemingly irrationally reject advice. To do this we introduce a novel formalization of assistance that models these biases, allowing the assistant to infer and adapt to them. We then introduce a new method for planning the assistant's actions which can scale to large decision making problems. We show experimentally that our approach adapts to these agent biases, and results in higher cumulative reward for the agent than automation-based alternatives. Lastly, we show that an approach combining advice and automation outperforms advice alone at the cost of losing some safety guarantees.
Original languageEnglish
Title of host publicationAAAI-23 Technical Tracks 10
EditorsBrian Williams, Yiling Chen, Jennifer Neville
PublisherAAAI Press
Pages11551-11559
Number of pages9
ISBN (Electronic)978-1-57735-880-0
DOIs
Publication statusPublished - 27 Jun 2023
MoE publication typeA4 Conference publication
EventAAAI Conference on Artificial Intelligence - Walter E. Washington Convention Center, Washington, United States
Duration: 7 Feb 202314 Feb 2023
Conference number: 37
https://aaai-23.aaai.org/

Publication series

NameProceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
Number10
Volume37
ISSN (Electronic)2374-3468

Conference

ConferenceAAAI Conference on Artificial Intelligence
Abbreviated titleAAAI
Country/TerritoryUnited States
CityWashington
Period07/02/202314/02/2023
Internet address

Fingerprint

Dive into the research topics of 'Zero-Shot Assistance in Sequential Decision Problems'. Together they form a unique fingerprint.

Cite this