This workshop consists of invited and contributed talks, as well as a discussion panel.
All times are in local NZT.
8:30-8:45 Introduction
8:45-9:45 Invited Talk: Sarath Sreedharan
Expectations and Mental Models: A Holistic Approach to Understanding
Explainability, Value Alignment, and Trust
9:45-10:00 Topical Paper #1
What a Thing to Say! Which Linguistic Politeness Strategies Should Robots Use in Noncompliance Interactions? / Terran Mott, Aaron Fanganello, Tom Williams
10:00-10:30 Coffee Break
10:30-12:30 Contributed Papers
Rebelling Without Retaliation: AI and Robots Must Maintain Trust While Disobeying / Paul Robinette, Zahra Khavas and Russell Perkins
When would you trust a disobedient robot? Establishing a baseline for trust dynamics in robotic noncompliance interactions / Gordon Briggs and Christina Wasylyshyn
On Depths of Recursive Thinking in Observer-Aware Planning / Shuwa Miura
Rebellion and Disobedience in HRI: Insights from human-horse interaction / Eakta Jain and J. Cortney Bradford (See also in RaD-HRI)
12:30-14:00 Lunch
14:00-15:00 Invited Talk: Johnathan Mell
Known Deception and Unknown Deception: Reconciling End-to-End ML and Traditional AI
15:00-15:15 Topical Paper #2
Understanding the spirit of a norm: Challenges for norm‐learning agents / Thomas Arnold and Matthias Scheutz
15:15-16:00 AAMAS Preview Talks
Norm Enforcement with a Soft Touch: Faster Emergence, Happier Agents / Sz-Ting Tzeng, Nirav Ajmeri, and Munindar Singh
Deceptive Path Planning via Reinforcement Learning with Graph Neural Networks / Michael Fatemi, Wesley Suttle, and Brian Sadler
16:00-16:30 Coffee Break
16:30-16:45 AAMAS Preview Talk
The Triangles of Dishonesty: Modelling the Evolution of Lies, Bullshit, and Deception in Agent Societies / Stefan Sarkadi and Peter Lewis
16:45-17:45 Panel
Your AI Knows Best: is disobedience OK when it’s ‘for your own good’?
17:45-18:00 General Discussion & Wrap-up
Sarath Sreedharan is an Assistant Professor at Colorado State University. His core research interests include designing human-aware decision-making systems to generate behaviors that align with human expectations. He completed his Ph.D. at Arizona State University, where his doctoral dissertation received one of the 2022 Dean’s Dissertation Awards for Ira A. Fulton Schools of Engineering and was an Honorable mention for the ICAPS-23 Outstanding Dissertation Award. His research has been published in various premier research conferences, including AAAI, ICAPS, IJCAI, AAMAS, IROS, HRI, ICRA, ICML, ICLR, and NeurIPS, and journals like AIJ, and in AI Magazine. He has presented tutorials on his research at various forums and is the lead author of a Morgan Claypool monograph on explainable human-AI interactions. He was selected as a DARPA Riser Scholar for 2022 and a Highlighted New Faculty at AAAI-23. His research has won multiple awards, including the Best System's Demo and Exhibit Award at ICAPS-20 and the Best Paper Award at Bridging Planning \& RL workshop at ICAPS 2022. He was also recognized as a AAAI-20 Outstanding Program Committee Member, Highlighted Reviewer at ICLR 22, IJCAI 2022 and 2023 Distinguished Program Committee Member, and Top Reviewer at NeurIPS 22.
Dr. Johnathan Mell is a professor, researcher, and technology innovator working at the crossroads of artificial intelligence, human behavior, and engineering. Dr. Mell is a tenure-track professor at the University of Central Florida, where he lectures on AI in video games, and leads the ScionAI lab, which researches topics relating to making and understanding more human-like AI systems. He received his Ph.D. and Master’s in Computer Science from University of Southern California, and holds a bachelor’s degree from the University of Pennsylvania School of Engineering and Applied Science as well as a second bachelor’s degree from the Wharton School of Business. Dr. Mell has appeared at numerous global conferences, and is also regularly invited as a panelist or speaker to both academic conferences and popular science venues to discuss AI. Dr. Mell aims to connect business, gaming, and cutting-edge artificial intelligence in a fully integrated way, and utilizes modern techniques to make consistent, trustworthy, and useful AIs. His current work is focused on artificial negotiation, the game Diplomacy, and social emotions in AI.