Variance Reduction for Policy Gradient via Action-Dependent Baselines
Original title: Variance reduction for policy gradient with action-dependent factorized baselines
35AI Score
This paper proposes a variance reduction method for policy gradients using action-dependent factorized baselines. By introducing baselines that depend on actions, it aims to reduce gradient estimation noise and improve the convergence stability of reinforcement learning algorithms.
Related Entities
Full Report
Variance reduction for policy gradient with action-dependent factorized baselines