A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints J Germano, FE Stradi, G Genalti, M Castiglioni, A Marchesi, N Gatti arXiv preprint arXiv:2304.14326, 2023 | 6 | 2023 |
Online adversarial mdps with off-policy feedback and known transitions F Bacchiocchi, FE Stradi, M Papini, AM Metelli, N Gatti Sixteenth European Workshop on Reinforcement Learning, 2023 | 1 | 2023 |
Online Markov Decision Processes Configuration with Continuous Decision Space D Maran, P Olivieri, FE Stradi, G Urso, N Gatti, M Restelli Proceedings of the AAAI Conference on Artificial Intelligence 38 (13), 14315 …, 2024 | | 2024 |
Learning Adversarial MDPs with Stochastic Hard Constraints FE Stradi, M Castiglioni, A Marchesi, N Gatti arXiv preprint arXiv:2403.03672, 2024 | | 2024 |
Markov Persuasion Processes: Learning to Persuade from Scratch F Bacchiocchi, FE Stradi, M Castiglioni, A Marchesi, N Gatti arXiv preprint arXiv:2402.03077, 2024 | | 2024 |
Bandits with Ranking Feedback D Maran, F Bacchiocchi, FE Stradi, M Castiglioni, N Gatti, M Restelli | | 2023 |
Online Configuration in Continuous Decision Space D Maran, P Olivieri, FE Stradi, G Urso, N Gatti, M Restelli Sixteenth European Workshop on Reinforcement Learning, 2023 | | 2023 |
Safely guiding a no-regret learner to the equilibrium FE Stradi | | 2022 |