Xue Bin (Jason) Peng

xbpeng@berkeley.edu
I'm currently a Ph.D. student at UC Berkeley advised by Professor Sergey Levine and Professor Pieter Abbeel. I received an M.Sc from the University of British Columbia, advised by Professor Michiel van de Panne. My work lies in the intersection between computer graphics and machine learning, with a focus on reinforcement learning for motion control of simulated characters. I have previously interned at OpenAI, Adobe Research, Disney Research, Microsoft (343 Industries), and Capcom.

Publications

Learning Agile Robotic Locomotion Skills by Imitating Animals
Xue Bin Peng, Erwin Coumans, Tingnan Zhang, Tsang-Wei Lee, Jie Tan, Sergey Levine
arXiv Preprint 2020
[Project page] [Paper]
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Anirudh Goyal, Shagun Sodhani, Jonathan Binas, Xue Bin Peng, Sergey Levine, Yoshua Bengio
International Conference on Learning Representations (ICLR 2020)
[Project page] [Paper]
Reward-Conditioned Policies
Aviral Kumar, Xue Bin Peng, Sergey Levine
arXiv Preprint 2019
[Project page] [Paper]
On Learning Symmetric Locomotion
Farzad Adbolhosseini, Hung Yu Ling, Zhaoming Xie, Xue Bin Peng, Michiel van de Panne
ACM SIGGRAPH Conference on Motion, Interaction, and Games (MIG 2019)
[Project page] [Paper]
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
Xue Bin Peng, Aviral Kumar, Grace Zhang, Sergey Levine
arXiv Preprint 2019
[Project page] [Paper]
MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies
Xue Bin Peng, Michael Chang, Grace Zhang, Pieter Abbeel, Sergey Levine
Neural Information Processing Systems (NeurIPS 2019)
[Project page] [Paper]
Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
Xue Bin Peng, Angjoo Kanazawa, Sam Toyer, Pieter Abbeel, Sergey Levine
International Conference on Learning Representations (ICLR 2019)
[Project page] [Paper]
SFV: Reinforcement Learning of Physical Skills from Videos
Xue Bin Peng, Angjoo Kanazawa, Jitendra Malik, Pieter Abbeel, Sergey Levine
ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2018)
[Project page] [Paper]
DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
Xue Bin Peng, Pieter Abbeel, Sergey Levine, Michiel van de Panne
ACM Transactions on Graphics (Proc. SIGGRAPH 2018)
[Project page] [Paper]
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
Xue Bin Peng, Marcin Andrychowicz, Wojciech Zaremba, Pieter Abbeel
IEEE International Conference on Robotics and Automation (ICRA 2018)
[Project page] [Paper]
DeepLoco: Developing Locomotion Skills Using Hierarchical Deep Reinforcement Learning
Xue Bin Peng, Glen Berseth, KangKang Yin, Michiel van de Panne
ACM Transactions on Graphics (Proc. SIGGRAPH 2017)
[Project page] [Paper]
Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?
Xue Bin Peng, Michiel van de Panne
ACM SIGGRAPH / Eurographics Symposium on Computer Animation 2017
Best Student Paper Award
[Project page] [Paper]
Terrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning
Xue Bin Peng, Glen Berseth, Michiel van de Panne
ACM Transactions on Graphics (Proc. SIGGRAPH 2016)
[Project page] [Paper]
Dynamic Terrain Traversal Skills Using Reinforcement Learning
Xue Bin Peng, Glen Berseth, Michiel van de Panne
ACM Transactions on Graphics (Proc. SIGGRAPH 2015)
[Project page] [Paper]