I am a postdoctoral researcher at Facebook (London offices). I work with the Core Data Science team at problems at the intersection of CS and Economics.

Previous to that, I was a a postdoctoral researcher at Politecnico di Milano. I hold a Ph.D. in Computer Science from the same institution, advised by Professor Nicola Gatti. My PhD combined Artificial Intelligence and Game Theory to produce artificial agents capable of strategic reasoning in adversarial settings. In particular, I am interested in equilibrium computation problems in general settings. The main goal of my research is understanding how agents can learn to coordinate their actions in complex non-cooperative environments.

I stayed as a Visiting Researcher at Carnegie Mellon University during winter/spring 2018, where I had the opportunity to work with Professor Tuomas Sandholm at the Electronic Marketplaces Lab.

I have been awarded the 2017 Lesmo prize for the best Italian MSc Thesis in Artificial Intelligence.

🎖 My paper "No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium" won a best paper award at NeurIPS 2020.

My CV can be found here.

Follow @with_high_prob

Publications

W	Faster Algorithms for Optimal Ex-Ante Coordinated Collusive Strategies in Extensive-Form Zero-Sum Games Gabriele Farina, Andrea Celli, Nicola Gatti, Tuomas Sandholm Working paper [ paper ]

W	Public Bayesian Persuasion: Being Almost Optimal and Almost Persuasive Matteo Castiglioni, Andrea Celli, Nicola Gatti Working paper [ paper ]

C13	Signaling in Bayesian Network Congestion Games: the Subtle Power of Symmetry Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti In AAAI 2021 (accepted for publication) [ paper ]

C12	Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies Federico Cacciamani, Andrea Celli, Marco Ciccone, Nicola Gatti In AAMAS 2021 (accepted for publication)

C11	No-regret learning dynamics for extensive-form correlated equilibria Andrea Celli, Alberto Marchesi, Gabriele Farina, Nicola Gatti In the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS-20). Oral presentation and best paper award [ paper ]

C10	Online Bayesian Persuasion Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti In the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS-20). Spotlight presentation.

C9	Persuading Voters: It’s Easy to Whisper, It’s Hard to Speak Loud Matteo Castiglioni, Andrea Celli, Nicola Gatti In the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20). [ paper ]

C8	Bayesian Persuasion with Sequential Games Andrea Celli, Stefano Coniglio, Nicola Gatti In the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20). [ paper ]

C7	Learning to Correlate in Multi-Player General-Sum Sequential Games Andrea Celli, Alberto Marchesi, Tommaso Bianchi, Nicola Gatti In the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) [ paper ]

C6	Computing Optimal Ex Ante Correlated Equilibria in Two-Player Sequential Games Andrea Celli, Stefano Coniglio, Nicola Gatti In the 18th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS 2019) [ paper ]

E1	Personality-Based Representations of Imperfect-Recall Games Andrea Celli, Giulia Romano, Nicola Gatti In the 18th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS 2019, Extended abstract) [ paper ]

C5	Ex ante coordination and collusion in zero-sum multi-player extensive-form games Gabriele Farina, Andrea Celli, Nicola Gatti, Tuomas Sandholm In the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) [ paper ][ video ]

C4	Computational Results for Extensive-Form Adversarial Team Games Andrea Celli, Nicola Gatti. In the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18). [ paper ]

C3	On the Complexity of Nash Equilibrium Reoptimization Andrea Celli, Alberto Marchesi, Nicola Gatti. In the 33rd Conference on Uncertainty in Artificial Intelligence (UAI-2017). [ paper ]

C2	Coordinating Multiple Defensive Resources in Patrolling Games with Alarm Systems Nicola Basilico, Andrea Celli, Giuseppe De Nittis, Nicola Gatti. In the Sixteenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2017). [ paper ]

C1	Team-Maxmin Equilibrium: Efficiency Bounds and Algorithms Nicola Basilico, Andrea Celli, Giuseppe De Nittis, Nicola Gatti. In the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17). [ paper ]

J2	Learning dynamics in limited-control repeated games Andrea Celli, Alberto Marchesi In Intelligenza Artificiale, vol. 12, no. 2, pp. 89-101, 2018.

J1	Computing the Team-maxmin Equilibrium in Single-Team Single-Adversary Team Games Nicola Basilico, Andrea Celli, Giuseppe De Nittis, Nicola Gatti. In Intelligenza Artificiale, vol. 11, no. 1, pp. 67-79, 2017.

2019	Teaching assistant Informatica A

	Teaching assistant Game Theory

2018	Teaching assistant Informatica A (061202)

	Teaching assistant Economics and Computation (097688)

Ways to contact me:
My Twitter profile and my Linkedin profile

Publications

Ways to contact me: