Alberto Maria Metelli

7

Papers

4

Total Citations

Papers (7)

Parameterized Projected Bellman Operator

Graph-Triggered Rising Bandits

Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms

No-Regret Reinforcement Learning in Smooth MDPs

Learning Optimal Deterministic Policies with Stochastic Policy Gradients

Factored-Reward Bandits with Intermediate Observations

Best Arm Identification for Stochastic Rising Bandits