I am a second-year Master's student in Computer Science at the School of Computer Science, Carnegie Mellon University. I work in the Robots Perceiving and Doing lab advised by Prof. David Held. My research interest lies in reinforcment learning & robotics.

I received my B.S. in Data Science from Yuanpei College, Peking University. At PKU, I worked under the supervision of Prof. Bin Dong on applying RL to solve scientific computing problems.

I am applying for Ph.D. starting in Fall 2021. Feel free to reach me at yufeiw2 [at] andrew [dot] cmu [dot] edu!
CV | Google Scholar | Github | 3-slide Research Summary



Research Interest


My research interest lies in robot learning, i.e., using learning-based methods to build intelligent robots that can autonomously and continuously acquire perception and control skills in the physical world. See a 3-slide per project summary of the research projects that I have conducted so far here.



Publications

(* indicates equal contribution)

ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning
Yufei Wang*, Gautham Narayan*, Xingyu Lin, Brian Okorn, David Held
CoRL 2020
Paper / Project Page / Code

SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation
Xingyu Lin, Yufei Wang, Jake Olkin, David Held
CoRL 2020
Paper / Project Page / Code

f-IRL: Inverse Reinforcement Learning via State Marginal Matching
Tianwei Ni*, Harshit Sikchi*, Yufei Wang*, Tejus Gupta*, Lisa Lee, Ben Eysenbach (*equal contribution, orders determined by dice rolling)
CoRL 2020
Abridged in RSS 2020, Workshop on Structured Approaches to Robot Learning for Improved Generalization
Paper / Projec Page / Code

Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient
Yufei Wang*, Tianwei Ni*
ICML 2020, Workshop on Automated Machine Learning [Link]
Paper / Video / Code

Beyond Exponentially Discounted Sum: Automatic Learning of Return Function
Yufei Wang*, Qiwei Ye*, Tie-Yan Liu
NeurIPS 2020 Deep RL workshop
Paper

Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
Yufei Wang*, Ziju Shen*, Zichao Long, Bin Dong
Communications in Computational Physics 2020
Paper / Code

Deep Reinforcement Learning for Green Security Games with Real-Time Information
Yufei Wang, Zheyuan Ryan Shi, Lantao Yu, Yi Wu, Rohit Singh, Lucas Joppa, Fei Fang
AAAI 2019
Paper / Slides





Preprints


Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imaging
Ziju Shen*, Yufei Wang*, Dufan Wu, Xu Yang, Bin Dong
arXiv





Graduate Courses & Teaching