User profiles for Xue Bin Peng
Xue Bin PengAssistant Professor, Simon Fraser University, NVIDIA Verified email at sfu.ca Cited by 6993 |
Sim-to-real transfer of robotic control with dynamics randomization
Simulations are attractive environments for training agents as they provide an abundant
source of data and alleviate certain safety concerns during the training process. But the …
source of data and alleviate certain safety concerns during the training process. But the …
Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning
Learning physics-based locomotion skills is a difficult problem, leading to solutions that
typically exploit prior knowledge of various forms. In this paper we aim to learn a variety of …
typically exploit prior knowledge of various forms. In this paper we aim to learn a variety of …
[HTML][HTML] Deep reinforcement learning for modeling human locomotion control in neuromechanical simulation
Modeling human motor control and predicting how humans will move in novel environments
is a grand scientific challenge. Researchers in the fields of biomechanics and motor control …
is a grand scientific challenge. Researchers in the fields of biomechanics and motor control …
Deepmimic: Example-guided deep reinforcement learning of physics-based character skills
A longstanding goal in character animation is to combine data-driven specification of behavior
with a system that can execute a similar behavior in a physical simulation, thus enabling …
with a system that can execute a similar behavior in a physical simulation, thus enabling …
Learning agile robotic locomotion skills by imitating animals
Reproducing the diverse and agile locomotion skills of animals has been a longstanding
challenge in robotics. While manually-designed controllers have been able to emulate many …
challenge in robotics. While manually-designed controllers have been able to emulate many …
Amp: Adversarial motion priors for stylized physics-based character control
Synthesizing graceful and life-like behaviors for physically simulated characters has been a
fundamental challenge in computer animation. Data-driven methods that leverage motion …
fundamental challenge in computer animation. Data-driven methods that leverage motion …
Sfv: Reinforcement learning of physical skills from videos
Data-driven character animation based on motion capture can produce highly naturalistic
behaviors and, when combined with physics simulation, can provide for natural procedural …
behaviors and, when combined with physics simulation, can provide for natural procedural …
Terrain-adaptive locomotion skills using deep reinforcement learning
Reinforcement learning offers a promising methodology for developing skills for simulated
characters, but typically requires working with sparse hand-crafted features. Building on …
characters, but typically requires working with sparse hand-crafted features. Building on …
Advantage-weighted regression: Simple and scalable off-policy reinforcement learning
In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that
uses standard supervised learning methods as subroutines. Our goal is an algorithm that …
uses standard supervised learning methods as subroutines. Our goal is an algorithm that …
Reinforcement learning for robust parameterized locomotion control of bipedal robots
Developing robust walking controllers for bipedal robots is a challenging endeavor.
Traditional model-based locomotion controllers require simplifying assumptions and careful …
Traditional model-based locomotion controllers require simplifying assumptions and careful …