Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Yifan, Wang, Yuhao, Zhou, Enlu
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2403.00675