影响力指数

89.59/100

前 0.6%

全站排名 #392

发表论文29 篇

平均评分5.6

年均产出9.7 篇/年

Matteo Castiglioni

Assistant Professor@Politecnico di Milano·意大利·OpenReview

研究方向

game theory · bayesian persuasion · regret minimization · online learning · equilibrium computation · social influence · election manipulation

5.3

Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information

ICLR 2026Poster

三作

4.4

Beyond Slater’s Condition in Online CMDPs with Stochastic and Adversarial Constraints

ICLR 2026Rejected

三作

2.7

No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!

NeurIPS 2025Poster

二作

7.3

Taming Adversarial Constraints in CMDPs

NeurIPS 2025Poster

三作

7.3

Markov Persuasion Processes: Learning to Persuade From Scratch

NeurIPS 2025Poster

三作

7.0

Feature-Based Online Bilateral Trade

ICLR 2025Poster

三作

6.8

Data-Dependent Regret Bounds for Constrained MABs

NeurIPS 2025Poster

三作

6.4

The Complexity of Correlated Equilibria in Generalized Games

NeurIPS 2025Poster

二作

6.1

Learning Adversarial MDPs with Stochastic Hard Constraints

ICML 2025Poster

二作

6.0

Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization

ICLR 2025Poster

二作

5.5

No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization

ICML 2025Poster

二作

5.5

Contract Design Under Approximate Best Responses

ICML 2025Poster

三作

5.3

Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints

ICLR 2025Rejected

三作

4.9

Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints

ICML 2025Poster

三作

4.2

Markov Persuasion Processes: Learning to Persuade From Scratch

ICLR 2025Rejected

三作

3.6

Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback

ICLR 2025Rejected

三作

-1

No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization

ICLR 2025Desk Rejected

合作者 (20)

Francesco Emanuele Stradi

14 篇

Francesco Bacchiocchi

Matteo Castiglioni

Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information

Beyond Slater’s Condition in Online CMDPs with Stochastic and Adversarial Constraints

Delayed Adversarial Attacks on Stochastic Bandits

Attacking Combinatorial Bandits: Beyond Bounded Rewards

Online Bilateral Trade With Minimal Feedback: Don’t Waste Seller’s Time

No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!

Taming Adversarial Constraints in CMDPs

Markov Persuasion Processes: Learning to Persuade From Scratch

Feature-Based Online Bilateral Trade

Data-Dependent Regret Bounds for Constrained MABs

The Complexity of Correlated Equilibria in Generalized Games

Learning Adversarial MDPs with Stochastic Hard Constraints

Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization

No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization

Contract Design Under Approximate Best Responses

Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints

Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints

Markov Persuasion Processes: Learning to Persuade From Scratch

Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback

No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization