DADP: Domain Adaptive Diffusion Policy

TL;DR

DADP introduces a novel approach for learning domain adaptive policies by disentangling static domain features from dynamic properties using diffusion models and temporal context strategies, enabling better zero-shot generalization.

Contribution

The paper proposes DADP, a method that employs unsupervised disentanglement and diffusion injection to improve domain adaptation in control policies.

Findings

DADP outperforms prior methods on locomotion and manipulation benchmarks.

Lagged Context Dynamical Prediction effectively disentangles static domain features.

DADP demonstrates strong zero-shot generalization across unseen domains.

Abstract

Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control. Substantial progress has been made through domain representation learning to capture domain-specific information, thus enabling domain-aware decision making. We analyze the process of learning domain representations through dynamical prediction and find that selecting contexts adjacent to the current step causes the learned representations to entangle static domain information with varying dynamical properties. Such mixture can confuse the conditioned policy, thereby constraining zero-shot adaptation. To tackle the challenge, we propose DADP (Domain Adaptive Diffusion Policy), which achieves robust adaptation through unsupervised disentanglement and domain-aware diffusion injection. First, we introduce Lagged Context Dynamical Prediction, a strategy that conditions future state estimation on a historical offset context; by increasing this temporal gap, we unsupervisedly disentangle static domain representations by filtering out transient properties. Second, we integrate the learned domain representations directly into the generative process by biasing the prior distribution and reformulating the diffusion target. Extensive experiments on challenging benchmarks across locomotion and manipulation demonstrate the superior performance, and the generalizability of DADP over prior methods. More visualization results are available on the https://outsider86.github.io/DomainAdaptiveDiffusionPolicy/.