Sotabase

Career

· Assistant Professor, Simon Fraser University2022–
· Research Intern, NVIDIA2021–2022
· Research Intern, Google Brain2019–2020
· Member of Technical Staff (Intern), OpenAI2017–2017
· PhD in Computer Science, University of California, Berkeley2017–2021
· Research Intern, Adobe Research2015–2015
· Lab Associate (Intern), Disney Research Pittsburgh2015–2015
· MS in Computer Science, University of British Columbia2015–2017
· Intern Software Developer, Microsoft Studios2013–2013
· Co-op Rendering Engineer, Capcom Vancouver2012–2012
· Computer Science Honours (B.Sc.), University of British Columbia2010–2015

Publications (51)

Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
IEEE International Conference on Robotics and Automation · 2017
1,548
cited
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
arXiv.org · 2019
708
cited
Learning Agile Robotic Locomotion Skills by Imitating Animals
Robotics: Science and Systems · 2020
613
cited
DeepMimic
ACM Transactions on Graphics · 2018
559
cited
DeepLoco
ACM Transactions on Graphics · 2017
440
cited
Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots
IEEE International Conference on Robotics and Automation · 2021
268
cited
Terrain-adaptive locomotion skills using deep reinforcement learning
ACM Transactions on Graphics · 2016
262
cited
Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
International Conference on Learning Representations · 2018
232
cited
MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies
Neural Information Processing Systems · 2019
217
cited
Learning locomotion skills using DeepRL: does the choice of action space matter?
Symposium on Computer Animation · 2016
197
cited
Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions
IEEE/RJS International Conference on Intelligent RObots and Systems · 2022
165
cited
Reinforcement learning for versatile, dynamic, and robust bipedal locomotion control
Int. J. Robotics Res. · 2024
161
cited
Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion
Computer Vision and Pattern Recognition · 2023
156
cited
Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World
IEEE International Conference on Robotics and Automation · 2021
132
cited
Deep reinforcement learning for modeling human locomotion control in neuromechanical simulation
Journal of NeuroEngineering and Rehabilitation · 2020
128
cited
Offline Meta-Reinforcement Learning with Advantage Weighting
International Conference on Machine Learning · 2020
119
cited
CALM: Conditional Adversarial Latent Models  for Directable Virtual Characters
International Conference on Computer Graphics and Interactive Techniques · 2023
108
cited
Synthesizing Physical Character-Scene Interactions
International Conference on Computer Graphics and Interactive Techniques · 2023
108
cited
Reward-Conditioned Policies
arXiv.org · 2019
103
cited
Learning Physically Simulated Tennis Skills from Broadcast Videos
ACM Transactions on Graphics · 2023
95
cited
Sotabase
Xue Bin Peng | Researcher Profile | Sotabase | Sotabase