Learning Reward Functions by Integrating Human Demonstrations and Preferences M Palan, NC Landolfi, G Shevchuk, D Sadigh arXiv preprint arXiv:1906.08928, 2019 | 135 | 2019 |
Asking Easy Questions: A User-Friendly Approach to Active Reward Learning B Erdem, M Palan, NC Landolfi, DP Losey, D Sadigh Conference on Robot Learning, 1177-1190, 2020 | 115* | 2020 |
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 | 91 | 2020 |
Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferences E Bıyık, DP Losey, M Palan, NC Landolfi, G Shevchuk, D Sadigh The International Journal of Robotics Research 41 (1), 45-67, 2022 | 86 | 2022 |
An efficient, generalized bellman update for cooperative inverse reinforcement learning D Malik, M Palaniappan, J Fisac, D Hadfield-Menell, S Russell, A Dragan International Conference on Machine Learning, 3394-3402, 2018 | 39* | 2018 |
Fitting a Linear Control Policy to Demonstrations with a Kalman Constraint M Palan, S Barratt, A McCauley, D Sadigh, V Sindhwani, S Boyd Learning for Dynamics and Control, 374-383, 2020 | 19 | 2020 |
Developing Continuous Reinforcement Learning Methods that are Robust to Inconsistent Time Discretization G Shevchuk, M Palan | | 2019 |