Yecheng (Jason) Ma
Jason is a CIS PhD student advised by Osbert Bastani and Dinesh Jayaraman. He is interested in machine learning, reinforcement learning, and their applications to robotics.
POLICY AWARE MODEL LEARNING VIA
TRANSITION OCCUPANCY MATCHING
Conservative Offline Distributional Reinforcement Learning￼
Publisher In NeurIPS
Highlights from GRASP at CoRL 2022
December 20, 2022