Matteo Castiglioni

7

Papers

13

Total Citations

Papers (7)

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

Bandits with Replenishable Knapsacks: the Best of both Worlds

Feature-Based Online Bilateral Trade

Data-Dependent Regret Bounds for Constrained MABs

Online Learning under Budget and ROI Constraints via Weak Adaptivity

Graph-Triggered Rising Bandits

Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints