Yiwei Bai   \

Undergraduate Student
ACM Honored Class@Shanghai Jiao Tong University

Office: 344, Gates Hall, Cornell, Ithaca, NY 14853
Email: bywbilly [at] gmail (dot) com

CV  /  GitHub  /  LinkedIn

Biography

Hi! I am a senior undergraduate student at ACM Honors Class, Zhiyuan College, Shanghai Jiao Tong University. Currently, I am a research intern at Cornell Institute for Computational Sustainability, where I am supervised by Professor Carla P. Gomes. Previously, I was fortunate to work as a research assistant at APEX LAB, directed by Professor Weinan Zhang and Professor Wang Jun. I also worked as a research intern at Tianrang network tech Ltd,.co advised by Professor Guirong Xue

I am applying for the Ph.D. programs which start from Fall 2018. My research interests lie in the intersection of reinforcement learning, decision making, and systems.
Education
Shanghai Jiao Tong University, China
Bachelor of Science, Sep. 2014 to Jun. 2018
Cornell University, USA
Research Intern, June. 2017 to Dec. 2017
Publication

Scalable Relaxations of Sparse Packing Constraints: Optimal Biocontrol in Predator-Prey Networks
Johan Bjorcks, Yiwei Bai, Yexiang Xue, Xiaojian Wu, Mark Whitemore, Carla P. Gomes

  • In this research, we solved an important problem in computational sustainability -- biological control of invasive species.

  • We proposed an approximation algorithm based on a width relaxation and randomized projections, which is quite scalable compared with previous work and can be used for realistic problem

  • We evaluated our algorithm in the context of biocontrol for the insect pest Hemlock Wolly Adelgid(HWA) in eastern North America.

    		•

    An Empirical Study of Collective Behaviors in Many-agent Reinforcement Learning
    Yiwei Bai*, Lantao Yu*, Yaodong Yang*, Jun Wang, Weinan Zhang, Ying Wen, Yong Yu

  • In this research, we designed and developed Million-level Multi-Agent Reinforcement Learning Platform. You could find the platform here.

  • We tried to understand AI population with multi-agent reinforcement learning and verify the principles developed in the real world could be applied to AI population.

    		•
    Research Projects

    Yi, an AI platform playing the GO(game)
    Yiwei Bai, Lequn Chen, and colleagues in Tianrang, (advised by Professor Guirong Xue), Jan. 2017

  • Yi won the Four-th prize in the first International Computer Go Competition
  • Yi won the Ninth place in the 10th UEC Cup
  • I and colleagues trained and tuned the policy network and value network
  • I and colleagues designed and implemented the reinforcement learning framework of the value network incorporated with policy network

    		•
    Course Projects

    An Empirical Study of Deep Learning Toolkits on Tone Classification Yiwei Bai, Lequn Chen, and Huichen Li, (advised by Professor Kai Yu), Jan. 2017

  • We designed and implemented several deep learning models in TensorFlow, Theano and MXNet for tone classification

  • We also conducted an empirical comparison between these deep learning toolkits (TensorFlow, Theano and MXNet).

    		•
    Teaching

    Teaching Assistant • Introduction to Programming Language (CS106, Fall 2015) • Shanghai Jiao Tong University

    Honors and Awards

    Academic Excellence Scholarship (2nd) • Shanghai Jiao Tong University • 2015 and 2016
    Awarded to top 10% students

    Zhiyuan College Honored Scholarship • Shanghai Jiao Tong University • 2015 and 2016
    Awarded to top x students

    Gold Medal of ACM Shanghai Metropolitan Contest • Association for Computing Machinery • 2015

    Honorable Mention in American Mathematical Contest in Modeling(MCM) • Consortium for Mathematics and Its Applications • 2016