Xue Bin Peng
Xue Bin (Jason) Peng is an Assistant Professor at Simon Fraser University and a Research Scientist at NVIDIA, holding a Canada CIFAR AI Chair through Amii. He earned his Ph.D. from UC Berkeley under the advisement of Sergey Levine and Pieter Abbeel. His research focuses on developing machine learning techniques, particularly deep reinforcement learning and motion imitation, to synthesize agile and naturalistic motor skills for physically simulated characters and real-world robots. He is best known for creating the AMP (Adversarial Motion Priors) framework and DeepMimic, and received the 2022 ACM SIGGRAPH Outstanding Doctoral Dissertation Award.
“The decoupled policy uses an adversarial motion reward [3]. Its discriminator compares two-frame transitions from policy rollouts with transitions from the training references using lower-body and torso poses in the pelvis frame.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.