Work

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

Year: 2025

Type: article

Source: Operations Research

DOI: 10.1287/opre.2024.0854

Authors: Yifan Lin, Yuhao Wang, Enlu Zhou

Institution: Georgia Institute of Technology

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4410360592

FWCI: 0.854

Cites: 11

Cited by: 2

Related to: 10