Showing 2023Show all
2 papers · 1 filter
cs.LG2023
-Adaptive Regret Minimization in Heavy-Tailed Bandits
Gianmarco Genalti, Lupo Marsigli, Nicola Gatti +1
Heavy-tailed distributions naturally arise in several settings, from finance to telecommunications. While regret minimization under subgaussian or bounded rewards has been widely s…
cs.LG2023
A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints
Jacopo Germano, Francesco Emanuele Stradi, Gianmarco Genalti +3
We study online learning in episodic constrained Markov decision processes (CMDPs), where the learner aims at collecting as much reward as possible over the episodes, while satisfy…