Does "Do Differentiable Simulators Give Better Policy Gradients?'' Give Better Policy Gradients?

TL;DR

This paper investigates whether differentiable simulators provide better policy gradients in reinforcement learning, proposing lightweight methods to handle discontinuities and variance issues, with findings emphasizing variance control's importance.

Contribution

It introduces DDCG, a simple estimator switching method, and IVW-H, a variance stabilization technique, demonstrating their effectiveness in handling discontinuities and variance in policy gradient estimation.

Findings

DDCG achieves robust performance with minimal hyperparameters.

IVW-H stabilizes variance without explicit discontinuity detection.

Variance control often outweighs estimator switching in practical scenarios.

Abstract

In policy gradient reinforcement learning, access to a differentiable model enables 1st-order gradient estimation that accelerates learning compared to relying solely on derivative-free 0th-order estimators. However, discontinuous dynamics cause bias and undermine the effectiveness of 1st-order estimators. Prior work addressed this bias by constructing a confidence interval around the REINFORCE 0th-order gradient estimator and using these bounds to detect discontinuities. However, the REINFORCE estimator is notoriously noisy, and we find that this method requires task-specific hyperparameter tuning and has low sample efficiency. This paper asks whether such bias is the primary obstacle and what minimal fixes suffice. First, we re-examine standard discontinuous settings from prior work and introduce DDCG, a lightweight test that switches estimators in nonsmooth regions; with a single hyperparameter, DDCG achieves robust performance and remains reliable with small samples. Second, on differentiable robotics control tasks, we present IVW-H, a per-step inverse-variance implementation that stabilizes variance without explicit discontinuity detection and yields strong results. Together, these findings indicate that while estimator switching improves robustness in controlled studies, careful variance control often dominates in practical deployments.