ALL INTELLIGENCE
OpenAI 官方博客T1·Models

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.

Full Report

Variance reduction for policy gradient with action-dependent factorized baselines