No-Regret Reinforcement Learning in Smooth MDPs

no code implementations • 6 Feb 2024 • Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restell

Obtaining no-regret guarantees for reinforcement learning (RL) in the case of problems with continuous state and/or action spaces is still one of the major open challenges in the field.

reinforcement-learning Reinforcement Learning (RL)

Autoregressive Bandits

1 code implementation • 12 Dec 2022 • Francesco Bacchiocchi, Gianmarco Genalti, Davide Maran, Marco Mussi, Marcello Restelli, Nicola Gatti, Alberto Maria Metelli

Autoregressive processes naturally arise in a large variety of real-world scenarios, including stock markets, sales forecasting, weather prediction, advertising, and pricing.

Decision Making

Tight Performance Guarantees of Imitator Policies with Continuous Actions

no code implementations • 7 Dec 2022 • Davide Maran, Alberto Maria Metelli, Marcello Restelli

In this paper, we study BC with the goal of providing theoretical guarantees on the performance of the imitator policy in the case of continuous actions.

Delayed Reinforcement Learning by Imitation

no code implementations • 11 May 2022 • Pierre Liotet, Davide Maran, Lorenzo Bisi, Marcello Restelli

When the agent's observations or interactions are delayed, classic reinforcement learning tools usually fail.

Imitation Learning reinforcement-learning +1