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

Yifan Lin, Yuhao Wang, Enlu Zhou. Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate. Operations Research, 73(6):3010-3026, 2025. [doi]

Abstract

Abstract is missing.