Inferring Implicit Goals Across Differing Task Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tulli, Silvia, Vasileiou, Stylianos Loukas, Chetouani, Mohamed, Sreedharan, Sarath
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917905928552448
author Tulli, Silvia
Vasileiou, Stylianos Loukas
Chetouani, Mohamed
Sreedharan, Sarath
author_facet Tulli, Silvia
Vasileiou, Stylianos Loukas
Chetouani, Mohamed
Sreedharan, Sarath
contents One of the significant challenges to generating value-aligned behavior is to not only account for the specified user objectives but also any implicit or unspecified user requirements. The existence of such implicit requirements could be particularly common in settings where the user's understanding of the task model may differ from the agent's estimate of the model. Under this scenario, the user may incorrectly expect some agent behavior to be inevitable or guaranteed. This paper addresses such expectation mismatch in the presence of differing models by capturing the possibility of unspecified user subgoal in the context of a task captured as a Markov Decision Process (MDP) and querying for it as required. Our method identifies bottleneck states and uses them as candidates for potential implicit subgoals. We then introduce a querying strategy that will generate the minimal number of queries required to identify a policy guaranteed to achieve the underlying goal. Our empirical evaluations demonstrate the effectiveness of our approach in inferring and achieving unstated goals across various tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17704
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inferring Implicit Goals Across Differing Task Models
Tulli, Silvia
Vasileiou, Stylianos Loukas
Chetouani, Mohamed
Sreedharan, Sarath
Artificial Intelligence
Robotics
Systems and Control
One of the significant challenges to generating value-aligned behavior is to not only account for the specified user objectives but also any implicit or unspecified user requirements. The existence of such implicit requirements could be particularly common in settings where the user's understanding of the task model may differ from the agent's estimate of the model. Under this scenario, the user may incorrectly expect some agent behavior to be inevitable or guaranteed. This paper addresses such expectation mismatch in the presence of differing models by capturing the possibility of unspecified user subgoal in the context of a task captured as a Markov Decision Process (MDP) and querying for it as required. Our method identifies bottleneck states and uses them as candidates for potential implicit subgoals. We then introduce a querying strategy that will generate the minimal number of queries required to identify a policy guaranteed to achieve the underlying goal. Our empirical evaluations demonstrate the effectiveness of our approach in inferring and achieving unstated goals across various tasks.
title Inferring Implicit Goals Across Differing Task Models
topic Artificial Intelligence
Robotics
Systems and Control
url https://arxiv.org/abs/2501.17704