Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning

TL;DR

This paper introduces EDIS, a diffusion-based method that leverages offline data to improve online reinforcement learning, reducing data shift issues and enhancing performance in various environments.

Contribution

EDIS is a novel diffusion sampling approach that distills offline knowledge for better online data generation, compatible with existing offline-to-online RL methods.

Findings

EDIS achieves a 20% average performance boost on MuJoCo, AntMaze, and Adroit environments.

Theoretical analysis shows EDIS reduces suboptimality compared to traditional offline or online data reuse.

EDIS can be integrated with methods like Cal-QL and IQL as a plug-in enhancement.

Abstract

Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, \textbf{E}nergy-guided \textbf{DI}ffusion \textbf{S}ampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions to distill this knowledge for enhanced data generation in the online phase. The theoretical analysis demonstrates that EDIS exhibits reduced suboptimality compared to solely utilizing online data or directly reusing offline data. EDIS is a plug-in approach and can be combined with existing methods in offline-to-online RL setting. By implementing EDIS to off-the-shelf methods Cal-QL and IQL, we observe a notable 20% average improvement in empirical performance on MuJoCo, AntMaze, and Adroit environments. Code is available at \url{https://github.com/liuxhym/EDIS}.