| Cooperative Inverse Reinforcement Learning D Hadfield-Menell, SJ Russell, P Abbeel, A Dragan Advances in Neural Information Processing Systems 29, 2016 | 840 | 2016 |
| Inverse Reward Design D Hadfield-Menell, S Milli, P Abbeel, SJ Russell, A Dragan Advances in Neural Information Processing Systems 30, 2017 | 507 | 2017 |
| Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ... Transactions on Machine Learning Research, 2023 | 429 | 2023 |
| Toward Transparent AI: A survey on interpreting the inner structures of deep neural networks T Räuker, A Ho, S Casper, D Hadfield-Menell 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 464-483, 2023 | 189 | 2023 |
| The off-switch game D Hadfield-Menell, A Dragan, P Abbeel, S Russell Proceedings of the Twenty-Sixth International Joint Conference on Artificial …, 2017 | 189 | 2017 |
| On the geometry of adversarial examples M Khoury, D Hadfield-Menell arXiv preprint arXiv:1811.00525, 2018 | 113* | 2018 |
| Incomplete contracting and AI alignment D Hadfield-Menell, GK Hadfield Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 417-422, 2019 | 108 | 2019 |
| Pragmatic-pedagogic value alignment JF Fisac, MA Gates, JB Hamrick, C Liu, D Hadfield-Menell, ... Robotics research: the 18th international symposium Isrr, 49-57, 2020 | 106 | 2020 |
| Guided search for task and motion plans using learned heuristics R Chitnis, D Hadfield-Menell, A Gupta, S Srivastava, E Groshev, C Lin, ... 2016 IEEE International Conference on Robotics and Automation (ICRA), 447-454, 2016 | 95 | 2016 |
| Consequences of Misaligned AI S Zhuang, D Hadfield-Menell Advances in Neural Information Processing Systems 33, 15763-15773, 2020 | 93 | 2020 |
| Explore, establish, exploit: Red teaming language models from scratch S Casper, J Lin, J Kwon, G Culp, D Hadfield-Menell arXiv preprint arXiv:2306.09442, 2023 | 84 | 2023 |
| What are you optimizing for? aligning recommender systems with human values J Stray, I Vendrov, J Nixon, S Adler, D Hadfield-Menell arXiv preprint arXiv:2107.10939, 2021 | 83 | 2021 |
| Should robots be obedient? S Milli, D Hadfield-Menell, A Dragan, S Russell Proceedings of the 26th International Joint Conference on Artificial …, 2017 | 81 | 2017 |
| Building Human Values into Recommender Systems: An Interdisciplinary Synthesis and Open Problems J Stray, A Halevy, P Assar, D Hadfield-menell, C Boutilier, A Ashar, ... ACM Transactions on Recommender Systems, 2023 | 70* | 2023 |
| On the utility of model learning in hri R Choudhury, G Swamy, D Hadfield-Menell, AD Dragan 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI …, 2019 | 68 | 2019 |
| Conservative Agency via Attainable Utility Preservation AM Turner, D Hadfield-Menell, P Tadepalli Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 385-391, 2020 | 67 | 2020 |
| Expressive robot motion timing A Zhou, D Hadfield-Menell, A Nagabandi, AD Dragan Proceedings of the 2017 ACM/IEEE international conference on human-robot …, 2017 | 67 | 2017 |
| Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents R Köster, D Hadfield-Menell, R Everett, L Weidinger, GK Hadfield, ... Proceedings of the National Academy of Sciences 119 (3), e2106028118, 2022 | 60* | 2022 |
| Modular task and motion planning in belief space D Hadfield-Menell, E Groshev, R Chitnis, P Abbeel 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2015 | 60 | 2015 |
| Black-Box Access is Insufficient for Rigorous AI Audits S Casper, C Ezell, C Siegmann, N Kolt, TL Curtis, B Bucknall, A Haupt, ... Proceedings of the 2024 ACM Conference on Fairness, Accountability, and …, 2024 | 59 | 2024 |
Anca D DraganAssistant Professor at UC Berkeley // Director, AI Safety and Alignment, Google DeepMindVerified email at berkeley.edu