Assistant Professor (From Fall 2022)
Department of Computer Science
University of Virginia

Email: shangtong@virginia.edu

[Google Scholar] [Twitter] [Curriculum Vitae] [Github]
I am looking for self-motivated students interested in RL at different levels!

Biography

Shangtong Zhang is a DPhil student at the University of Oxford. The goal of his research is to solve sequential decision making problems in a scalable and reliable way. Currently, he focuses on reinforcement learning as a solution method. His work won the best paper award at AAMAS and his research is funded by an EPSRC studentship. He spent some time at Microsoft Research and DeepMind during his DPhil.

News

  • 2022/05: One paper is accepted by JMLR.
  • 2022/04: I will join UVA as an assistant professor starting from Fall 2022.
  • 2021/12: One paper is accepted at AAMAS 2022 for oral presentation.
  • 2021/12: One paper is accepted at AAAI 2022.
  • 2021/11: One paper about offline StarCraft II is accepted by Deep RL Workshop at NeurIPS.
  • 2021/09: I give a talk at the group meeting of the RL team at DeepMind.
  • 2021/09: I give a talk at Microsoft Research Summit.
  • 2021/06: I start interning at Microsoft Research Montreal.
  • 2021/05: Two papers are accepted at ICML 2021.
  • 2021/02: I start interning at DeepMind London.
  • 2020/12: One paper is accepted at AAAI 2021.
  • 2020/09: One paper is accepted at NeurIPS 2020.
  • 2020/06: Two papers are accepted at ICML 2020.
  • 2020/06: I start interning at Microsoft Research Montreal.
  • 2020/05: I’m awarded Light Senior Scholarship by St Catherine’s College.
  • 2020/05: One paper is awarded AAMAS 2020 Best Paper Award.
  • 2019/09: Two papers are accepted at NeurIPS 2019.