PeopleofSuperintelligence

Researcher

Andrea Celli

Andrea Celli is a computer scientist whose research develops no-regret learning methods for equilibrium finding in strategic games. He earned a computer science PhD at Politecnico di Milano, visited Carnegie Mellon’s Electronic Marketplaces Lab during his doctorate, and received the 2017 Lesmo prize for the best Italian MSc thesis in artificial intelligence. His 2020 paper on extensive-form correlated equilibria received a NeurIPS Outstanding Paper award and introduced an efficient no-trigger-regret algorithm. Later papers advanced equilibrium learning in 2022, proved the complexity of approximate Φ-equilibria in generalized games in 2025, and studied game payoff estimation from observed play in 2026. As of October 2026, he is an assistant professor in Bocconi’s Department of Computing Sciences.

Works
74
Citations
400
h-index
11
Badges
Links
Website

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2017

    A Lesmo prize

    In 2017, he receives the Lesmo prize for the best Italian MSc thesis in artificial intelligence.

  2. 2018

    A CMU research visit

    During his PhD, he visits Carnegie Mellon’s Electronic Marketplaces Lab from January 2018 to May 2018.

  3. 2020

    A NeurIPS paper award

    In 2020, he coauthors “No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium” with Alberto Marchesi, Gabriele Farina and Nicola Gatti. The paper gives the first uncoupled no-regret dynamics for extensive-form correlated equilibria and an efficient no-trigger-regret algorithm; NeurIPS names it an Outstanding Paper.

  4. September 2021

    Joining Bocconi

    After earning a computer science PhD at Politecnico di Milano and completing a postdoctoral stint there, he spends one year as a postdoctoral researcher with Facebook Research’s Core Data Science team in London. In September 2021, he joins Bocconi’s Department of Decision Sciences as an assistant professor.

  5. 2022

    Faster equilibrium learning

    In 2022, he coauthors “Faster No-Regret Learning Dynamics for Extensive-Form Correlated and Coarse Correlated Equilibria” with Ioannis Anagnostides, Gabriele Farina, Christian Kroer and Tuomas Sandholm. The paper establishes faster no-regret dynamics for extensive-form correlated equilibria in multiplayer, general-sum games with imperfect information.

  6. 2025

    Complexity of correlated equilibria

    In 2025, he coauthors “The Complexity of Correlated Equilibria in Generalized Games” with Martino Bernasconi, Matteo Castiglioni and Gabriele Farina. The paper proves that computing an approximate Φ-equilibrium in generalized games is PPAD-complete.

  7. 2026

    Estimating feasible payoffs

    In 2026, he coauthors “Optimal Rates for Feasible Payoff Set Estimation in Games” with Annalisa Barbara, Riccardo Poiani and Martino Bernasconi. The paper studies inferring feasible payoff sets from observed behavior and establishes minimax-optimal rates for exact and approximate equilibrium play in zero-sum and general-sum games.

  8. As of October 2026

    Assistant professor at Bocconi

    As of October 2026, he is an assistant professor in Bocconi University’s Department of Computing Sciences.

Career

  1. Since 2021Bocconi UniversityAssistant Professor
  2. Until 2021Facebook Research
  3. 2018Carnegie Mellon University
  4. 2017–2021Polytechnic University of MilanPostdoctoral researcher

Education

  1. Polytechnic University of MilanPhD in computer science

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Andrea Celli. 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.
  2. 16% of AI career moves in the 2020s went from a university to a companyIncludes Andrea Celli. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Bocconi University. 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.
  4. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Bocconi University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.

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 Andrea Celli yet. Send us a free-licensed photo.

  1. Andrea Celli | Bocconi University unibocconi.it. Checked 22 October 2026.
  2. Carnegie Mellon’s Electronic Marketplaces Laboratory cs.cmu.edu. Checked 22 October 2026.
  3. NeurIPS 2020 Awards neurips.cc. Checked 22 October 2026.
  4. No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium proceedings.neurips.cc. Checked 22 October 2026.
  5. A Record Addition of New Faculty Members from September unibocconi.it. Checked 22 October 2026.
  6. Faster No-Regret Learning Dynamics for Extensive-Form Correlated and Coarse Correlated Equilibria arxiv.org. Checked 22 October 2026.
  7. The Complexity of Correlated Equilibria in Generalized Games arxiv.org. Checked 22 October 2026.
  8. Optimal Rates for Feasible Payoff Set Estimation in Games arxiv.org. Checked 22 October 2026.