PeopleofSuperintelligence

Researcher

Nan Jiang

Also known as 姜楠

Nan Jiang is a computer scientist at the University of Illinois Urbana-Champaign who builds the theoretical foundations of reinforcement learning, with a focus on function approximation. After a Bachelor of Engineering in automation at Tsinghua University in 2011 and a PhD at the University of Michigan in 2017, he spent 2017–2018 as a postdoctoral researcher at Microsoft Research in New York City and joined the Illinois faculty in 2018. His 2016 paper with Akshay Krishnamurthy, Alekh Agarwal, John Langford and Robert Schapire introduced the Bellman rank, and the 2022 Adversarially Trained Actor Critic paper he coauthored with Ching-An Cheng, Tengyang Xie and Agarwal was an ICML Outstanding Paper Runner-up. An NSF CAREER Award came in 2022, followed by a Sloan Research Fellowship and a Google Research Scholar award in 2024. He is an associate professor of computer science at Illinois and an action editor of the Journal of Machine Learning Research.

Badges

Timeline

  1. 2011–2017

    Tsinghua and a Michigan PhD

    A Bachelor of Engineering in automation from Tsinghua University comes in 2011, and a PhD in computer science and engineering from the University of Michigan follows in 2017.

  2. 2016–2017

    The Bellman rank paper

    In October 2016, he posts a paper with Akshay Krishnamurthy, Alekh Agarwal, John Langford and Robert Schapire that introduces contextual decision processes and the Bellman rank, a complexity measure for exploration in reinforcement learning with function approximation. The work appears at ICML in 2017.

  3. 2017–2018

    Postdoc at Microsoft Research

    From 2017 to 2018, he is a postdoctoral researcher at Microsoft Research in New York City.

  4. 2018–2024

    Joining the Illinois faculty

    In 2018, he joins the computer science faculty at the University of Illinois Urbana-Champaign as an assistant professor. His research there builds theoretical foundations of reinforcement learning, with a focus on function approximation that lets an agent generalize from known states to unknown states.

  5. March 2022

    An NSF CAREER Award

    In March 2022, an NSF CAREER Award funds his project "Theoretical Foundations of Offline Reinforcement Learning" with $500,000 over five years.

  6. 2022

    ICML runner-up for ATAC

    In 2022, he coauthors Adversarially Trained Actor Critic (ATAC) with Ching-An Cheng, Tengyang Xie and Alekh Agarwal, an offline reinforcement learning algorithm built as a two-player Stackelberg game between a policy actor and an adversarially trained value critic. ICML names the paper an Outstanding Paper Runner-up in July 2022.

  7. 2024

    Sloan Fellowship and Google award

    In 2024, he receives a Sloan Research Fellowship from the Alfred P. Sloan Foundation. Google names him a Google Research Scholar for a proposal on bridging online and offline reinforcement learning.

  8. Since 2024

    Associate professor at Illinois

    He becomes an associate professor of computer science at Illinois in 2024 and an action editor of the Journal of Machine Learning Research. In October 2025, he and Tengyang Xie post "Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees", an article on the theory of offline reinforcement learning. In July 2026, he gives an HKUST seminar, "Rethinking the theoretical foundation of reinforcement learning", as an associate professor at Illinois.

Career

  1. Since 2018University of Illinois Urbana-ChampaignAssistant Professor of Computer Science, Associate Professor of Computer Science
  2. 2017–2018Microsoft ResearchPostdoctoral Researcher

Education

  1. 2017University of MichiganPhD
  2. 2011Tsinghua UniversityBachelor of Engineering

From the biography.

  1. 23% of people shaping AI who left a university for a company later returned to a universityIncludes Nan Jiang. We estimate that 468 of the 2,011 people shaping AI who left a university for a company (23%) later returned to a university after a median of 5 years, and 163 of 829 (20%) made the reverse round trip.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes University of Illinois Urbana-Champaign. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  3. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes University of Illinois Urbana-Champaign. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes University of Illinois Urbana-Champaign. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Nan Jiang yet. Send us a free-licensed photo.

  1. Nan Jiang nanjiang.cs.illinois.edu. Checked 21 October 2026.
  2. Nan Jiang siebelschool.illinois.edu. Checked 21 October 2026.
  3. [1610.09512] Contextual Decision Processes with Low Bellman Rank are PAC-Learnable arxiv.org. Checked 21 October 2026.
  4. Nan Jiang Furthers Development in Reinforcement Learning with NSF CAREER Award | Siebel School of Computing and Data Science | Illinois siebelschool.illinois.edu. Checked 21 October 2026.
  5. Nan Jiang selected as a 2024 Sloan Research Fellow | Siebel School of Computing and Data Science | Illinois siebelschool.illinois.edu. Checked 21 October 2026.
  6. [2202.02446] Adversarially Trained Actor Critic for Offline Reinforcement Learning arxiv.org. Checked 21 October 2026.
  7. Four CS professors named 2024 Google Research Scholars | Siebel School of Computing and Data Science | Illinois siebelschool.illinois.edu. Checked 21 October 2026.
  8. [2510.04088] Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees arxiv.org. Checked 21 October 2026.
  9. Rethinking the theoretical foundation of reinforcement learning | HKUST CSE cse.hkust.edu.hk. Checked 21 October 2026.