Author

Gianmarco Tedeschi

h-index 0 View on Semantic Scholar

We have 1 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification

In the sparse-reward, goal-directed setting, the sample complexity upper bound for HBPI-UCRL is strictly lower than that of its non-hierarchical counterpart, providing theoretical justification for the empirical success of HRL.

Anders Jonsson, E. Kaufmann, Gianmarco Tedeschi et al. · arXiv.org · 0 citations