Matteo Castiglioni
~Matteo_Castiglioni1
25
论文总数
12.5
年均投稿
平均评分
接收情况18/25
会议分布
ICLR
12
NeurIPS
9
ICML
4
发表论文 (25 篇)
202516 篇
3
No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization
ICML 2025Poster
4
Online Bilateral Trade With Minimal Feedback: Don’t Waste Seller’s Time
NeurIPS 2025Poster
-
No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization
ICLR 2025desk_rejected
4
No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
NeurIPS 2025Poster
4
The Complexity of Correlated Equilibria in Generalized Games
NeurIPS 2025Poster
4
Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization
ICLR 2025Poster
4
Learning Adversarial MDPs with Stochastic Hard Constraints
ICML 2025Poster
4
Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints
ICLR 2025Rejected
4
Taming Adversarial Constraints in CMDPs
NeurIPS 2025Poster
4
Markov Persuasion Processes: Learning to Persuade From Scratch
NeurIPS 2025Poster
5
Markov Persuasion Processes: Learning to Persuade From Scratch
ICLR 2025Rejected
4
Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
ICML 2025Poster
4
Feature-Based Online Bilateral Trade
ICLR 2025Poster
5
Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback
ICLR 2025Rejected
4
Data-Dependent Regret Bounds for Constrained MABs
NeurIPS 2025Poster
4
Contract Design Under Approximate Best Responses
ICML 2025Poster
20249 篇
4
Safe Online Bid Optimization with Return On Investment and Budget Constraints
ICLR 2024Rejected
4
Online Information Acquisition: Hiring Multiple Agents
ICLR 2024Poster
3
Learning Optimal Contracts: How to Exploit Small Action Spaces
ICLR 2024Poster
4
Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
NeurIPS 2024Poster
4
Bandits with Replenishable Knapsacks: the Best of both Worlds
ICLR 2024Poster
4
Online Bayesian Persuasion Without a Clue
NeurIPS 2024Spotlight
4
Bandits with Ranking Feedback
ICLR 2024Rejected
4
Bandits with Ranking Feedback
NeurIPS 2024Poster
4
A Best-of-Both-Worlds Algorithm for MDPs with Long-Term Constraints
ICLR 2024Rejected