What Makes Value Learning Efficient in Residual Reinforcement Learning?

TL;DR

This paper investigates the challenges of value learning in residual reinforcement learning, identifying key bottlenecks and proposing DAWN, a simple method that significantly improves learning efficiency across various benchmarks.

Contribution

The paper uncovers fundamental bottlenecks in residual RL value learning and introduces DAWN, a minimal approach with effective solutions for efficient training.

Findings

DAWN improves value learning efficiency across multiple benchmarks.

Base-policy transitions act as value anchors for warmup.

Critic normalization restores representation sensitivity.

Abstract

Residual reinforcement learning (RL) enables stable online refinement of expressive pretrained policies by freezing the base and learning only bounded corrections. However, value learning in residual RL poses unique challenges that remain poorly understood. In this work, we identify two key bottlenecks: cold start pathology, where the critic lacks knowledge of the value landscape around the base policy, and structural scale mismatch, where the residual contribution is dwarfed by the base action. Through systematic investigation, we uncover the mechanisms underlying these bottlenecks, revealing that simple yet principled solutions suffice: base-policy transitions serve as an essential value anchor for implicit warmup, and critic normalization effectively restores representation sensitivity for discerning value differences. Based on these insights, we propose DAWN (Data-Anchored Warmup and Normalization), a minimal approach targeting efficient value learning in residual RL. By addressing these bottlenecks, DAWN demonstrates substantial efficiency gains across diverse benchmarks, policy architectures, and observation modalities.