Alberto Marchesi

111 papers A* 38A 6B 1Journal 65

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Stronger Benchmark for Online Bilateral Trade: From Fixed Prices to Distributions. CoRR Anna Lunghi, Mattia Piccinato, Matteo Castiglioni, Alberto Marchesi
2026	A*	`conf`	Better Regret Rates in Bilateral Trade via Sublinear Budget Violation. SODA Anna Lunghi, Matteo Castiglioni, Alberto Marchesi
2026	J	`jnl`	Learning in Bayesian Stackelberg Games With Unknown Follower's Types. CoRR Matteo Bollini, Francesco Bacchiocchi, Samuel Coutts, Matteo Castiglioni, Alberto Marchesi
2026	J	`jnl`	Replicable Constrained Bandits. CoRR Matteo Bollini, Gianmarco Genalti, Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi
2026	J	`jnl`	The Sample Complexity of Uniform Approximation for Multi-Dimensional CDFs and Fixed-Price Mechanisms. CoRR Matteo Castiglioni, Anna Lunghi, Alberto Marchesi
2026	J	`jnl`	Truly Adapting to Adversarial Constraints in Constrained MABs. CoRR Francesco Emanuele Stradi, Kalana Kalupahana, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	J	`jnl`	Better Regret Rates in Bilateral Trade via Sublinear Budget Violation. CoRR Anna Lunghi, Matteo Castiglioni, Alberto Marchesi
2025	J	`jnl`	Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints. CoRR Francesco Emanuele Stradi, Eleonora Fidelia Chiefari, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	A*	`conf`	Contract Design Under Approximate Best Responses. ICML Francesco Bacchiocchi, Jiarui Gan, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	J	`jnl`	Contract Design Under Approximate Best Responses. CoRR Francesco Bacchiocchi, Jiarui Gan, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	J	`jnl`	Data-Dependent Regret Bounds for Constrained MABs. CoRR Gianmarco Genalti, Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	A*	`conf`	Learning Adversarial MDPs with Stochastic Hard Constraints. ICML Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	J	`jnl`	Learning optimal contracts with small action spaces. Artif. Intell. Francesco Bacchiocchi, Matteo Castiglioni, Nicola Gatti, Alberto Marchesi
2025	J	`jnl`	No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need! CoRR Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Christian Kroer
2025	J	`jnl`	Online Two-Sided Markets: Many Buyers Enhance Learning. CoRR Anna Lunghi, Matteo Castiglioni, Alberto Marchesi
2025	J	`jnl`	Online learning in sequential Bayesian persuasion: Handling unknown priors. Artif. Intell. Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Francesco Trovò
2025	A*	`conf`	Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization. ICLR Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	A*	`conf`	Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints. ICML Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	A*	`conf`	Regret Minimization for Piecewise Linear Rewards: Contracts, Auctions, and Beyond. EC Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	J	`jnl`	Regret Minimization for Piecewise Linear Rewards: Contracts, Auctions, and Beyond. CoRR Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2025	A	`conf`	The Sample Complexity of Stackelberg Games. AISTATS Francesco Bacchiocchi, Matteo Bollini, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	J	`jnl`	Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback. CoRR Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	J	`jnl`	Contracting With a Reinforcement Learning Agent by Playing Trick or Treat. CoRR Matteo Bollini, Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	A	`conf`	Finding Effective Ad Allocations: How to Exploit User History. AAMAS Matteo Castiglioni, Alberto Latino, Alberto Marchesi, Giulia Romano, Nicola Gatti, Chokha Palayamkottai
2024	J	`jnl`	Learning Adversarial MDPs with Stochastic Hard Constraints. CoRR Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	J	`jnl`	Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints. CoRR Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	A	`conf`	Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games. AISTATS Martino Bernasconi, Alberto Marchesi, Francesco Trovò
2024	A*	`conf`	Learning Optimal Contracts: How to Exploit Small Action Spaces. ICLR Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	J	`jnl`	Markov Persuasion Processes: Learning to Persuade from Scratch. CoRR Francesco Bacchiocchi, Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	A*	`conf`	Online Bayesian Persuasion Without a Clue. NeurIPS Francesco Bacchiocchi, Matteo Bollini, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	J	`jnl`	Online Bayesian Persuasion Without a Clue. CoRR Francesco Bacchiocchi, Matteo Bollini, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	A*	`conf`	Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints. ICML Francesco Emanuele Stradi, Jacopo Germano, Gianmarco Genalti, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	J	`jnl`	Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization. CoRR Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2024	J	`jnl`	Regret-Minimizing Contracts: Agency Under Uncertainty. CoRR Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi
2024	J	`jnl`	The Sample Complexity of Stackelberg Games. CoRR Francesco Bacchiocchi, Matteo Bollini, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2023	J	`jnl`	A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints. CoRR Jacopo Germano, Francesco Emanuele Stradi, Gianmarco Genalti, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2023	A*	`conf`	Constrained Phi-Equilibria. ICML Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Francesco Trovò, Nicola Gatti
2023	J	`jnl`	Constrained Phi-Equilibria. CoRR Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Francesco Trovò, Nicola Gatti
2023	J	`jnl`	Designing menus of contracts efficiently: The power of randomization. Artif. Intell. Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2023	J	`jnl`	Increasing revenue in Bayesian posted price auctions through signaling. Artif. Intell. Matteo Castiglioni, Alberto Marchesi, Giulia Romano, Nicola Gatti
2023	J	`jnl`	Learning Optimal Contracts: How to Exploit Small Action Spaces. CoRR Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2023	J	`jnl`	Multi-Agent Contract Design: How to Commission Multiple Agents with Individual Outcome. CoRR Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2023	A*	`conf`	Multi-Agent Contract Design: How to Commission Multiple Agents with Individual Outcomes. EC Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2023	A*	`conf`	Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion. ICML Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Francesco Trovò, Nicola Gatti
2023	J	`jnl`	Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion. CoRR Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti, Francesco Trovò
2023	A*	`conf`	Persuading Farsighted Receivers in MDPs: the Power of Honesty. NeurIPS Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Mirco Mutti
2023	J	`jnl`	Persuading Farsighted Receivers in MDPs: the Power of Honesty. CoRR Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Mirco Mutti
2023	J	`jnl`	Regret minimization in online Bayesian persuasion: Handling adversarial receiver's types under full and partial feedback models. Artif. Intell. Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti
2023	J	`jnl`	Selling Information while Being an Interested Party. CoRR Matteo Castiglioni, Francesco Bacchiocchi, Alberto Marchesi, Giulia Romano, Nicola Gatti
2022	A*	`conf`	A Unifying Framework for Online Optimization with Long-Term Constraints. NeurIPS Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Giulia Romano, Nicola Gatti
2022	J	`jnl`	A Unifying Framework for Online Optimization with Long-Term Constraints. CoRR Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Giulia Romano, Nicola Gatti
2022	A	`conf`	Bayesian Persuasion Meets Mechanism Design: Going Beyond Intractability with Type Reporting. AAMAS Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2022	J	`jnl`	Bayesian Persuasion Meets Mechanism Design: Going Beyond Intractability with Type Reporting. CoRR Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2022	J	`jnl`	Bayesian agency: Linear versus tractable contracts. Artif. Intell. Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2022	A*	`conf`	Designing Menus of Contracts Efficiently: The Power of Randomization. EC Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2022	J	`jnl`	Designing Menus of Contracts Efficiently: The Power of Randomization. CoRR Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2022	A*	`conf`	Efficiency of Ad Auctions with Price Displaying. AAAI Matteo Castiglioni, Diodato Ferraioli, Nicola Gatti, Alberto Marchesi, Giulia Romano
2022	J	`jnl`	Efficiency of Ad Auctions with Price Displaying. CoRR Matteo Castiglioni, Diodato Ferraioli, Nicola Gatti, Alberto Marchesi, Giulia Romano
2022	J	`jnl`	Last-iterate Convergence to Trembling-hand Perfect Equilibria. CoRR Martino Bernasconi, Alberto Marchesi, Francesco Trovò
2022	A*	`conf`	Public Signaling in Bayesian Ad Auctions. IJCAI Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Giulia Romano, Nicola Gatti
2022	J	`jnl`	Public Signaling in Bayesian Ad Auctions. CoRR Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Giulia Romano, Nicola Gatti
2022	A*	`conf`	Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints. ICML Martino Bernasconi, Federico Cacciamani, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Francesco Trovò
2022	A*	`conf`	Sequential Information Design: Learning to Persuade in the Dark. NeurIPS Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Francesco Trovò
2022	J	`jnl`	Sequential Information Design: Learning to Persuade in the Dark. CoRR Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Francesco Trovò
2022	A*	`conf`	Signaling in Posted Price Auctions. AAAI Matteo Castiglioni, Giulia Romano, Alberto Marchesi, Nicola Gatti
2022	J	`jnl`	Signaling in Posted Price Auctions. CoRR Matteo Castiglioni, Giulia Romano, Alberto Marchesi, Nicola Gatti
2022	J	`jnl`	Simple Uncoupled No-regret Learning Dynamics for Extensive-form Correlated Equilibrium. J. ACM Gabriele Farina, Andrea Celli, Alberto Marchesi, Nicola Gatti
2022	A*	`conf`	The Power of Media Agencies in Ad Auctions: Improving Utility through Coordinated Bidding. IJCAI Giulia Romano, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2022	J	`jnl`	The Power of Media Agencies in Ad Auctions: Improving Utility through Coordinated Bidding. CoRR Giulia Romano, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2021	A*	`conf`	Bayesian Agency: Linear versus Tractable Contracts. EC Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2021	J	`jnl`	Bayesian Agency: Linear versus Tractable Contracts. CoRR Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2021	J	`jnl`	Committing to correlated strategies with multiple leaders. Artif. Intell. Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2021	A*	`conf`	Decentralized No-regret Learning Algorithms for Extensive-form Correlated Equilibria (Extended Abstract). IJCAI Andrea Celli, Alberto Marchesi, Gabriele Farina, Nicola Gatti
2021	A*	`conf`	Exploiting Opponents Under Utility Constraints in Sequential Games. NeurIPS Martino Bernasconi de Luca, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Alberto Marchesi, Francesco Trovò
2021	A*	`conf`	Multi-Receiver Online Bayesian Persuasion. ICML Matteo Castiglioni, Alberto Marchesi, Andrea Celli, Nicola Gatti
2021	J	`jnl`	Multi-Receiver Online Bayesian Persuasion. CoRR Matteo Castiglioni, Alberto Marchesi, Andrea Celli, Nicola Gatti
2021	A*	`conf`	Online Posted Pricing with Unknown Time-Discounted Valuations. AAAI Giulia Romano, Gianluca Tartaglia, Alberto Marchesi, Nicola Gatti
2021	A*	`conf`	Signaling in Bayesian Network Congestion Games: the Subtle Power of Symmetry. AAAI Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti
2021	J	`jnl`	Simple Uncoupled No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium. CoRR Gabriele Farina, Andrea Celli, Alberto Marchesi, Nicola Gatti
2021	A*	`conf`	Trembling-Hand Perfection and Correlation in Sequential Games. AAAI Alberto Marchesi, Nicola Gatti
2020	J	`jnl`	A characterization of quasi-perfect equilibria. Games Econ. Behav. Nicola Gatti, Mario Gilli, Alberto Marchesi
2020	J	`jnl`	Bilevel programming methods for computing single-leader-multi-follower equilibria in normal-form and polymatrix games. EURO J. Comput. Optim. Nicola Basilico, Stefano Coniglio, Nicola Gatti, Alberto Marchesi
2020	J	`jnl`	Computing a Pessimistic Stackelberg Equilibrium with Multiple Followers: The Mixed-Pure Case. Algorithmica Stefano Coniglio, Nicola Gatti, Alberto Marchesi
2020	—	`—`	Leadership games: multiple followers, multiple leaders, and perfection. Alberto Marchesi
2020	A	`conf`	Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spaces. AAMAS Alberto Marchesi, Francesco Trovò, Nicola Gatti
2020	A*	`conf`	No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium. NeurIPS Andrea Celli, Alberto Marchesi, Gabriele Farina, Nicola Gatti
2020	J	`jnl`	No-regret learning dynamics for extensive-form correlated and coarse correlated equilibria. CoRR Andrea Celli, Alberto Marchesi, Gabriele Farina, Nicola Gatti
2020	A*	`conf`	Online Bayesian Persuasion. NeurIPS Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti
2020	J	`jnl`	Online Posted Pricing with Unknown Time-Discounted Valuations. CoRR Giulia Romano, Gianluca Tartaglia, Alberto Marchesi, Nicola Gatti
2020	J	`jnl`	Signaling in Bayesian Network Congestion Games: the Subtle Power of Symmetry. CoRR Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti
2020	J	`jnl`	Trembling-Hand Perfection and Correlation in Sequential Games. CoRR Alberto Marchesi, Nicola Gatti
2019	J	`jnl`	Be a Leader or Become a Follower: The Strategy to Commit to with Multiple Leaders (Extended Version). CoRR Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2019	A*	`conf`	Be a Leader or Become a Follower: The Strategy to Commit to with Multiple Leaders. IJCAI Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
2019	J	`jnl`	Leadership in Congestion Games: Multiple User Classes and Non-Singleton Actions (Extended Version). CoRR Alberto Marchesi, Matteo Castiglioni, Nicola Gatti
2019	A*	`conf`	Leadership in Congestion Games: Multiple User Classes and Non-Singleton Actions. IJCAI Alberto Marchesi, Matteo Castiglioni, Nicola Gatti
2019	J	`jnl`	Leadership in singleton congestion games: What is hard and what is easy. Artif. Intell. Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Stefano Coniglio
2019	J	`jnl`	Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spaces. CoRR Alberto Marchesi, Francesco Trovò, Nicola Gatti
2019	A*	`conf`	Learning to Correlate in Multi-Player General-Sum Sequential Games. NeurIPS Andrea Celli, Alberto Marchesi, Tommaso Bianchi, Nicola Gatti
2019	J	`jnl`	Learning to Correlate in Multi-Player General-Sum Sequential Games. CoRR Andrea Celli, Alberto Marchesi, Tommaso Bianchi, Nicola Gatti
2019	A*	`conf`	Quasi-Perfect Stackelberg Equilibrium. AAAI Alberto Marchesi, Gabriele Farina, Christian Kroer, Nicola Gatti, Tuomas Sandholm
2018	J	`jnl`	Computing a Pessimistic Leader-Follower Equilibrium with Multiple Followers: the Mixed-Pure Case. CoRR Stefano Coniglio, Nicola Gatti, Alberto Marchesi
2018	J	`jnl`	Computing the Strategy to Commit to in Polymatrix Games (Extended Version). CoRR Giuseppe De Nittis, Alberto Marchesi, Nicola Gatti
2018	A*	`conf`	Computing the Strategy to Commit to in Polymatrix Games. AAAI Giuseppe De Nittis, Alberto Marchesi, Nicola Gatti
2018	A*	`conf`	Leadership in Singleton Congestion Games. IJCAI Alberto Marchesi, Stefano Coniglio, Nicola Gatti
2018	J	`jnl`	Leadership in Singleton Congestion Games: What is Hard and What is Easy. CoRR Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Stefano Coniglio
2018	J	`jnl`	Learning dynamics in limited-control repeated games. Intelligenza Artificiale Andrea Celli, Alberto Marchesi
2018	J	`jnl`	Quasi-Perfect Stackelberg Equilibrium. CoRR Alberto Marchesi, Gabriele Farina, Christian Kroer, Nicola Gatti, Tuomas Sandholm
2018	A*	`conf`	Trembling-Hand Perfection in Extensive-Form Games with Commitment. IJCAI Gabriele Farina, Alberto Marchesi, Christian Kroer, Nicola Gatti, Tuomas Sandholm
2017	B	`conf`	Bilevel Programming Approaches to the Computation of Optimistic and Pessimistic Single-Leader-Multi-Follower Equilibria. SEA Nicola Basilico, Stefano Coniglio, Nicola Gatti, Alberto Marchesi
2017	A	`conf`	On the Complexity of Nash Equilibrium Reoptimization. UAI Andrea Celli, Alberto Marchesi, Nicola Gatti
2017	A*	`conf`	Pessimistic Leader-Follower Equilibria with Multiple Followers. IJCAI Stefano Coniglio, Nicola Gatti, Alberto Marchesi