Marcello Restelli

9

Papers

9

Total Citations

Papers (9)

Parameterized Projected Bellman Operator

Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story

Towards Principled Unsupervised Multi-Agent Reinforcement Learning

NeurIPS 2025arXiv

No-Regret Reinforcement Learning in Smooth MDPs

Factored-Reward Bandits with Intermediate Observations

Best Arm Identification for Stochastic Rising Bandits

How to Explore with Belief: State Entropy Maximization in POMDPs

Online Markov Decision Processes Configuration with Continuous Decision Space

Graph-Triggered Rising Bandits