Highlights on Learning Cost Functions

  • [we often misspecify cost functions, but the cost we specify is a useful observation about the underlying true cost the robot should optimize] D. Hadfiled-Menell, S. Milli, P. Abbeel, S. Russell, and A.D. Dragan. Inverse Reward Design. Neural Information Processing Systems (NIPS), 2017. (oral, acceptance rate 1.2%)
  • [here we advocate that Inverse RL should be formulated as a collaboration in which the robot is no longer a passive observer, and the human is no longer an uninterested expert acting as if in isolation] D. Hadfield-Menell, A.D. Dragan, P. Abbeel, and S. Russell. "Cooperative Inverse Reinforcement Learning". Neural Information Processing Systems (NIPS), 2016.
  • [rather than solving CIRL via generic methods, here we dig into its structure to create faster solvers] D. Malik, M. Palaniappan, J. Fisac, D. Hadfield-Menell, S. Russell, and A. D. Dragan. An Efficient, Generalized Bellman Update for Cooperative Inverse Reinforcement Learning. International Conference on Machine Learning (ICML), 2018. (oral)
  • [there are many heuristics for responding to physical interaction from a human, but here we observe that pHRI is intentional and thus informative of the human's preferences for the task, thereby defining the notion of an optimal response; we also derive a real-time approximation] A. Bajcsy, D. Losey, M. O'Malley, and A.D. Dragan. Learning Robot Objectives from Physical Human Interaction. Conference on Robot Learning (CoRL), 2017. (oral, acceptance rate 10%)
  • [even prior to observing human behavior, the current state of the environment leaks information about what people want, because people have been acting in that environemnt already] R. Shah, D. Krasheninnikov, J. Alexander, P. Abbeel, and A.D. Dragan. Preferences Implicit in the State of the World. International Conference on Learning Representations (ICLR), 2019.

Highlights on Learning to Coordinate with People

All Conference Papers & Journal Articles