Nicolas Espinosa Dice
I am a first-year PhD student at Cornell University, where I am advised by Wen Sun. My research focuses on reinforcement and imitation learning.
Prior to Cornell, I received a B.S. from Harvey Mudd College, where I was advised by George D. Montanez and Dagan Karp. I worked with George D. Montanez in the AMISTAD Lab and Weiqing Gu at Dasion.
Prior to Cornell, I received a B.S. from Harvey Mudd College, where I was advised by George D. Montanez and Dagan Karp. I worked with George D. Montanez in the AMISTAD Lab and Weiqing Gu at Dasion.
Last updated: August 2024
Research
Efficient Inverse Reinforcement Learning without Compounding Errors
Nicolas Espinosa Dice,
Gokul Swamy,
Sanjiban Choudhury,
Wen Sun
RLC 2024 RLSW, RLBRew
Project Page /
Paper /
Code
There are two seemingly contradictory desiderata for IRL algorithms: (a) preventing the compounding errors that stymie offline approaches like behavioral cloning and (b) avoiding the worst-case exploration complexity of reinforcement learning (RL). Prior work has been able to achieve either (a) or (b) but not both simultaneously. We prove that, under a novel structural condition we term reward-agnostic policy completeness, efficient IRL algorithms do avoid compounding errors, giving us the best of both worlds.