Moments Matter:Stabilizing Policy Optimization using Return Distributions

TL;DR

This paper introduces a moment-based regularization method for policy optimization in deep RL that leverages return distribution moments to improve stability without expensive distribution estimation.

Contribution

It proposes a novel approach using higher-order moments of return distributions to stabilize policy updates in continuous control tasks.

Findings

Achieves up to 75% stability improvement in Walker2D.

Maintains comparable evaluation returns to standard PPO.

Effectively reduces policy instability caused by noisy updates.

Abstract

Deep Reinforcement Learning (RL) agents often learn policies that achieve the same episodic return yet behave very differently, due to a combination of environmental (random transitions, initial conditions, reward noise) and algorithmic (minibatch selection, exploration noise) factors. In continuous control tasks, even small parameter shifts can produce unstable gaits, complicating both algorithm comparison and real-world transfer. Previous work has shown that such instability arises when policy updates traverse noisy neighborhoods and that the spread of post-update return distribution $R(\theta)$, obtained by repeatedly sampling minibatches, updating $\theta$, and measuring final returns, is a useful indicator of this noise. Although explicitly constraining the policy to maintain a narrow $R(\theta)$ can improve stability, directly estimating $R(\theta)$ is computationally expensive in high-dimensional settings. We propose an alternative that takes advantage of environmental stochasticity to mitigate update-induced variability. Specifically, we model state-action return distribution through a distributional critic and then bias the advantage function of PPO using higher-order moments (skewness and kurtosis) of this distribution. By penalizing extreme tail behaviors, our method discourages policies from entering parameter regimes prone to instability. We hypothesize that in environments where post-update critic values align poorly with post-update returns, standard PPO struggles to produce a narrow $R(\theta)$. In such cases, our moment-based correction narrows $R(\theta)$, improving stability by up to 75% in Walker2D, while preserving comparable evaluation returns.