Publications

  • Conference Papers

  • The Assistive Multi-Armed Bandit.Lawrence Chan, Dylan Hadfield-Menell, Siddartha S. Srinivasa, Anca D. Dragan ACM/IEEE International Conference on Human-Robot Interaction, 354:363, 2019. [PDF]
  • On the Utility of Model Learning in HRI. Rohan Choudhury, Gokul Swamy, Dylan Hadfield-Menell, Anca Dragan, ACM/IEEE International Conference on Human-Robot Interaction, 317-325, 2019. [PDF]
  • Human-AI Learning Performance in Multi-Armed Bandits. R Pandya, SH Huang, Dylan Hadfield-Menell, AD Dragan, Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 369-375, 2019. [PDF]
  • Legible Normativity for AI Alignment: The Value of Silly Rules. Dylan Hadfield-Menell, McKane Andrus, Gillian K. Hadfield Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 115-121, 2019. [PDF]
  • Incomplete contracting and AI alignment. Dylan Hadfield-Menell, Gillian K. Hadfield, Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 417-422, 2019. [PDF]
  • An Efficient Generalized Bellman Update for Cooperative Inverse Reinforcement Learning. Dhruv Malik, Malayandi Palaniappan, Jamie F. Fisac, Dylan Hadfield-Menell, Stuart J. Russell, Anca D. Dragan, Proceedings of Machine Learning Research, 3391-3399, 2018. [PDF]
  • Simplifying Reward Design through Divide-and-Conquer. Ellis Ratner, Dylan Hadfield-Menell, Anca D. Dragan, Robotics: Science and Systems, 2018. [PDF]
  • Inverse Reward Design. Dylan Hadfield-Menell, Smitha Milli, Pieter Abbeel, Stuart Russell, and Anca D. Dragan. In Neural Information Processing Systems, 2017. [PDF]
  • The Off-Switch Game. Dylan Hadfield-Menell, Anca D. Dragan, Pieter Abbeel, and Stuart Russell. In International Joint Conference on Artificial Intelligence, 2017. [PDF]
  • Should Robots be Obedient? Smitha Milli, Dylan Hadfield-Menell, Anca D. Dragan, and Stuart Russell. In International Joint Conference on Artificial Intelligence, 2017. [PDF]
  • Expressive Robot Motion Timing. Allan Zhou, Dylan Hadfield-Menell, and Anca D. Dragan. In International Conference on Human Robot Interaction, 2017. [PDF]
  • Cooperative Inverse Reinforcement Learning. Dylan Hadfield-Menell, Anca D. Dragan, Pieter Abbeel, and Stuart Russell. In Neural Information Processing Systems, 2016. [PDF][supplementary material]
  • Sequential Quadratic Programming for Task Plan Optimization. Dylan Hadfield-Menell, Chris Lin, Rohan Chitnis, Pieter Abbeel, and Stuart Russell. In IEEE/RSJ Conference on Intelligent Robots and Systems, 2016. [pdf][video]
  • Guided Search for Task and Motion Plans Using Learned Heuristics. Rohan Chitnis, Dylan Hadfield-Menell, Abhishek Gupta, Siddharth Srivastava, Edward Groshev, Christopher Lin, and Pieter Abbeel. In IEEE Conference on Robotics and Automation, 2016.[PDF][video]
  • Modular Task and Motion Planning in Belief Space. Dylan Hadfield-Menell, Edward Groshev, Rohan Chitnis, and Pieter Abbeel. In IEEE/RSJ Conference on Intelligent Robots and Systems, 2015. [PDF]
  • Multitasking: Efficient Optimal Planning for Bandit Superprocesses. Dylan Hadfield-Menell, and Stuart Russell. In Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, 2015. [PDF][supplementary material]
  • Beyond Lowest-Warping Cost Action Selection in Trajectory Transfer. Dylan Hadfield-Menell, Alex X. Lee, Chelsea Finn, Eric Tzeng, Sandy Huang, and Pieter Abbeel. In IEEE Conference on Robotics and Automation, 2015.[PDF]
  • Unifying Scene Registration and Trajectory Optimization for Learning from Demonstrations with Application to Manipulation of Deformable Objects. Alex X. Lee, Sandy H. Huang, Dylan Hadfield-Menell, Eric Tzeng, Pieter Abbeel. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2014.[PDF]
  • Optimization in the Now: Dynamic Peephole Optimization for Hierarchical Planning. Dylan Hadfield-Menell, Leslie Pack Kaelbling, and Tomás Lozano-Pérez. In IEEE Conference on Robotics and Automation, 2013.[PDF]
  • Talks and Panels

  • Human Values in AI, Wonderfest Science Fellow Speaker Series, 2019.
  • Formalizing the Value Alignment Problem in AI, ICLR Workshop on Safe Machine Learning: Specification, Robustness, and Assurance, New Orleans 2019.
  • Future of Life Institute - Beneficial AGI, Moderator, Technical safety student panel: What does the next generation of researchers think that the action items should be? Puerto Rico, 2019. [video]
  • The Assistive Multi-Armed Bandit, Human Robot Interaction, Daegu, Korea, 2019. [paper]
  • On the Utility of Model Learning in HRI, Human Robot Interaction, Daegu, Korea, 2019. [paper]
  • Value Alignment in Artificial Intelligence, Hastings Institute Control and Responsible Innovation in the Development of Autonomous Machines Experts Workshop, New York, 2018.
  • Science Envoy: Science Slam, Computer History Museum, Palo Alto, 2018.
  • Inverse Reward Design, ISAT/DARPA Workshop on Diverse Ways of Inferring Missions, Washington DC, 2017.
  • Inverse Reward Design, NeurIPS Oral, Long Beach, 2017. [PDF]
  • The Off-Switch Game, International Joint Conference on Artificial Intelligence, Melbourne, 2017. [PDF]
  • Value Alignment in Artificial Intelligence, Oxford Future Humanity Institute Workshop on Malicious Actors and A.I., Oxford, England 2017.
  • The Off-Switch:Designing Corrigible, yet Functional, Artificial Agents, Intelligence Research Institute & Future of Humanity Institute, Colloquium Series on Robust and Beneficial AI, 2016. [PDF, video]
  • Sequential Quadratic Programming for Task Plan Optimization, Planning & Robotics Workshop at International Conference on Planning and Scheduling Systems, 2016. [PDF]
  • Cooperative Inverse Reinforcement Learning, NeurIPS Spotlight, Barcelona, 2016. [PDF, video]
  • Cooperative Inverse Reinforcement Learning, Algorithmic HRI Workshop, Paris, 2016.
  • Sequential quadratic programming for task plan optimization, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016. [PDF]
  • Learning an Interface to Improve Efficiency in Combined Task and Motion Planning. Rohan Chitnis, Dylan Hadfield-Menell, Siddharth Srivastava, Abhishek Gupta, and Pieter Abbeel. In IROS Workshop on Machine Learning in Planning and Control of Robot Motion, 2015.[PDF]
  • Multitasking: Optimal Planning for Bandit Superprocesses, AAAI Conference on Uncertainty in A.I., Amsterdam, Netherlands, 2015. [PDF][supplementary material]
  • Modular Task and Motion Planning in Belief Space, IEEE Conference on Robotics and Automation, Incheon, Korea, 2015.[PDF]
  • Learning to Select Expert Demonstrations, Robotics: Science and Systems Workshop on Information-based Grasp and Manipulation Planning, 2014. [abstract | slides]
  • Optimization in the Now: Dynamic Peephole Optimization for Task and Motion Planning, IEEE Conference on Robotics and Automation, Karlsruhe, Germany, 2013.

Professional Activities and Service

  • Workshops (Co-)Organized

  • Aligned AI. Neural Information Processing Systems, Long Beach, California 2017.
  • Reliable Machine Learning in the Wild. International Conference on Machine Learning, Sydney, Australia 2017.
  • Reliable Machine Learning in the Wild. Neural Information Processing Systems, Barcelona, Spain 2016.
  • Program Committees and Journal Refereeing

  • Transactions on Human Robot Interaction; International Journal of Robotics Research; AIES, Artificial Intelligence Ethics and Society, 2017, 2018, 2019
  • HRI, Human-Robot Interaction, 2018, 2019, 2020
  • NeurIPS, Neural Information Processing Systems, 2016, 2017, 2018, 2019; AAAI, Conference on Artificial Intelligence, 2018
  • IJCAI, International Joint Conference on Artificial Intelligence, 2016, 2017
  • IROS, IEEE Conference on Intelligent Robots and Systems, 2015, 2016
  • ICRA, IEEE Conference on Robotics and Automation, 2016, 2017, 2018
  • AI4ALL, Summer Camp for Underrepresented Talent, Berkeley, CA 2017, 2018