DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning

TL;DR

This paper introduces DmC, a novel approach for cross-domain offline reinforcement learning that uses k-NN estimation and a diffusion model to generate target-aligned samples, improving performance with limited target data.

Contribution

The paper proposes DmC, a new framework combining k-NN based domain proximity estimation and a diffusion model to generate aligned samples, addressing dataset imbalance and partial domain overlap.

Findings

DmC outperforms existing methods in MuJoCo environments.

Using k-NN mitigates overfitting in domain gap estimation.

Generated samples improve policy learning with limited target data.

Abstract

Cross-domain offline reinforcement learning (RL) seeks to enhance sample efficiency in offline RL by utilizing additional offline source datasets. A key challenge is to identify and utilize source samples that are most relevant to the target domain. Existing approaches address this challenge by measuring domain gaps through domain classifiers, target transition dynamics modeling, or mutual information estimation using contrastive loss. However, these methods often require large target datasets, which is impractical in many real-world scenarios. In this work, we address cross-domain offline RL under a limited target data setting, identifying two primary challenges: (1) Dataset imbalance, which is caused by large source and small target datasets and leads to overfitting in neural network-based domain gap estimators, resulting in uninformative measurements; and (2) Partial domain overlap, where only a subset of the source data is closely aligned with the target domain. To overcome these issues, we propose DmC, a novel framework for cross-domain offline RL with limited target samples. Specifically, DmC utilizes $k$-nearest neighbor ($k$-NN) based estimation to measure domain proximity without neural network training, effectively mitigating overfitting. Then, by utilizing this domain proximity, we introduce a nearest-neighbor-guided diffusion model to generate additional source samples that are better aligned with the target domain, thus enhancing policy learning with more effective source samples. Through theoretical analysis and extensive experiments in diverse MuJoCo environments, we demonstrate that DmC significantly outperforms state-of-the-art cross-domain offline RL methods, achieving substantial performance gains.