Skip to main navigation Skip to search Skip to main content

Rethinking the Evaluation of Non-stationary Dueling Bandits for Human-Robot Interaction

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

14 Downloads (Pure)

Abstract

Non-stationary dueling bandits are promising for modeling evolving preferences in human-robot interaction, but current evaluations rely on synthetic data and ignore user experience. This short contribution proposes a regret formulation that incorporates interaction costs—such as annoyance, cognitive effort, and trust degradation. Furthermore, suggestions for standardized, user-in-the-loop evaluation is presented. Recognizing the challenges of long-term studies with real users, large language models could be used to simulate non-stationary user behavior for early-stage testing. This enables deeper insight into algorithm usability and supports the development of adaptive systems that are not only efficient, but also aligned with human expectations and experience.

Original languageEnglish
Title of host publicationSocial Robotics + AI
Subtitle of host publication17th International Conference, ICSR+AI 2025, Proceedings
EditorsMariacarla Staffa, John-John Cabibihan, Bruno Siciliano, Shuzhi Sam Ge, Leon Bodenhagen, Adriana Tapus, Silvia Rossi, Filippo Cavallo, Laura Fiorini, Marco Matarese, Hongsheng He
Place of PublicationSingapore
PublisherSpringer
Pages450-455
Number of pages6
ISBN (Electronic)978-981-95-2379-5
ISBN (Print)978-981-95-2378-8
DOIs
Publication statusE-pub ahead of print/First online - 2 Jan 2026
Event17th International Conference on Social Robotics, ICSR+AI 2025 - University of Naples Parthenope at the Centro Direzioale, Isola C4, Naples, Italy
Duration: 10 Sept 2025 → 12 Sept 2025

Publication series

NameLecture Notes in Computer Science
Volume16131 LNAI
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference17th International Conference on Social Robotics, ICSR+AI 2025
Country/TerritoryItaly
CityNaples
Period10/09/25 → 12/09/25

Keywords

  • 2026 OA procedure
  • Human-Robot Interaction
  • Preference Learning
  • Evaluation Methods

Fingerprint

Dive into the research topics of 'Rethinking the Evaluation of Non-stationary Dueling Bandits for Human-Robot Interaction'. Together they form a unique fingerprint.

Cite this