Guardado en:
Detalles Bibliográficos
Autor principal: Liu, Xingtu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.23448
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910104041816064
author Liu, Xingtu
author_facet Liu, Xingtu
contents In this work, we study out-of-distribution (OOD) generalization in meta-reinforcement learning from an information-theoretic perspective. We begin by establishing OOD generalization bounds for meta-supervised learning under two distinct distribution shift scenarios: standard distribution mismatch and a broad-to-narrow training setting. Building on this foundation, we formalize the generalization problem in meta-reinforcement learning and establish fine-grained generalization bounds that exploit the structure of Markov Decision Processes. Lastly, we analyze the generalization performance of a gradient-based meta-reinforcement learning algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23448
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning
Liu, Xingtu
Machine Learning
In this work, we study out-of-distribution (OOD) generalization in meta-reinforcement learning from an information-theoretic perspective. We begin by establishing OOD generalization bounds for meta-supervised learning under two distinct distribution shift scenarios: standard distribution mismatch and a broad-to-narrow training setting. Building on this foundation, we formalize the generalization problem in meta-reinforcement learning and establish fine-grained generalization bounds that exploit the structure of Markov Decision Processes. Lastly, we analyze the generalization performance of a gradient-based meta-reinforcement learning algorithm.
title An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2510.23448