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]

Authors

Yifan Lin

This author has not been identified. Look up 'Yifan Lin' in Google

Yuhao Wang

This author has not been identified. Look up 'Yuhao Wang' in Google

Enlu Zhou

This author has not been identified. Look up 'Enlu Zhou' in Google