Dylan Hadfield-Menell

Dylan Hadfield-Menell – MIT EECS at Electrical Engineering, Massachusetts Institute of Technology2 Followers

Breaking new ground in the realms of Artificial Intelligence, Machine Learning, and Robotics, Dylan Hadfield-Menell serves as an Assistant Professor at the Massachusetts Institute of Technology's Electrical Engineering and Computer Science department. With a keen focus on advancing the frontiers of AI and robotics, his work explores the intricate dynamics between humans and intelligent systems. At MIT, he is involved in pioneering research that seeks to enhance the capabilities of machines to learn and adapt in complex environments. His contributions are instrumental in shaping the future of intelligent systems, aiming to create technology that seamlessly integrates with human needs and societal goals.

Research Interests

Artificial Intelligence Machine Learning Robotics Human-AI Interaction Intelligent Systems Adaptive Learning Systems

Publications

1 - Formal contracts mitigate social dilemmas in multi-agent reinforcement learning,Autonomous Agents and Multi-Agent Systems

Andreas Haupt , Phillip Christoffersen , Mehul Damani , Dylan Hadfield-Menell ,

, 2024-10-18

2 - Judging facts, judging norms: Training machine learning models to judge humans requires a modified approach to labeling data,Science Advances

Aparna Balagopalan , David Madras , David H. Yang , Dylan Hadfield-Menell , Gillian K. Hadfield , Marzyeh Ghassemi ,

, 2023-05-12

3 - Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents,Proceedings of the National Academy of Sciences

Raphael Köster , Dylan Hadfield-Menell , Richard Everett , Laura Weidinger , Gillian K. Hadfield , Joel Z. Leibo ,

, 2022-01-12

4 - When Curation Becomes Creation,Queue

Liu Leqi , Dylan Hadfield-Menell , Zachary C. Lipton ,

, 11-15, 2021-06-30

5 - When curation becomes creation,Communications of the ACM

Liu Leqi , Dylan Hadfield-Menell , Zachary C. Lipton ,

, 44-47, 2021-11-19

6 - Incomplete Contracting and AI Alignment,Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society

Dylan Hadfield-Menell , Gillian K. Hadfield ,

, 417-422, 2019-01-27

7 - Incomplete Contracting and AI Alignment,SSRN Electronic Journal

Dylan Hadfield-Menell , Gillian K. Hadfield ,

, 2018-01-01

8 - Legible Normativity for AI Alignment,Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society

Dylan Hadfield-Menell , Mckane Andrus , Gillian Hadfield ,

, 115-121, 2019-01-27

9 - A Penalty Default Approach to Preemptive Harm Disclosure and Mitigation for AI Systems,Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society

Rui-Jie Yew , Dylan Hadfield-Menell ,

, 823-830, 2022-07-26

10 - Simplifying Reward Design through Divide-and-Conquer,Robotics: Science and Systems XIV

Ellis Ratner , Dylan Hadfield-Menell , Anca Dragan ,

, 2018-06-26

11 - Conservative Agency via Attainable Utility Preservation,Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society

Alexander Matt Turner , Dylan Hadfield-Menell , Prasad Tadepalli ,

, 385-391, 2020-02-07

12 - Optimization in the now: Dynamic peephole optimization for hierarchical planning,2013 IEEE International Conference on Robotics and Automation

Dylan Hadfield-Menell , Leslie Pack Kaelbling , Tomas Lozano-Perez ,

, 4560-4567, 2013-05-01

13 - Modular task and motion planning in belief space,2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Dylan Hadfield-Menell , Edward Groshev , Rohan Chitnis , Pieter Abbeel ,

, 4991-4998, 2015-09-01

14 - Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?,Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Kevin Liu , Stephen Casper , Dylan Hadfield-Menell , Jacob Andreas ,

, 2023-01-01

15 - The Assistive Multi-Armed Bandit,2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

Lawrence Chan , Dylan Hadfield-Menell , Siddhartha Srinivasa , Anca Dragan ,

, 354-363, 2019-03-01

16 - Estimating and Penalizing Preference Shift in Recommender Systems,Fifteenth ACM Conference on Recommender Systems

Micah Carroll , Dylan Hadfield-Menell , Stuart Russell , Anca Dragan ,

, 661-667, 2021-09-13

Share Dylan's Profile