Sample-Based Planning and Learning with Function Approximation
Statistical Science · 01.11.2025 · 40 (4) · 517-545
DOI: 10.1214/25-sts1001 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistical Science, erschienen am 01.11.2025. Verfasst von Tor Lattimore und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 62 Literaturangaben.
Abstract (Originalsprache)
We give a short tutorial on sample-based planning and learning with function approximation for reinforcement learning. The focus is on explaining the standard setups and algorithm design principles. The core algorithmic ideas explained are approximate backwards induction, the (Bellman) eluder dimension and the optimism principle.
Zitieren
APA
Lattimore, T., & Szepesvári, C. (2025). Sample-Based Planning and Learning with Function Approximation. Statistical Science, 40(4), 517-545. https://doi.org/10.1214/25-sts1001
Vancouver
Lattimore T, Szepesvári C. Sample-Based Planning and Learning with Function Approximation. Statistical Science. 2025;40(4):517-545. doi:10.1214/25-sts1001
BibTeX
@article{Lattimore2025,
author = {Lattimore, Tor and Szepesvári, Csaba},
title = {Sample-Based Planning and Learning with Function Approximation},
journal = {Statistical Science},
year = {2025},
volume = {40},
number = {4},
pages = {517--545},
doi = {10.1214/25-sts1001}
}
EUVIMED