Active Advantage-Aligned Online Reinforcement Learning with Offline Data

TL;DR

This paper introduces A3RL, a novel active sampling method that effectively combines online and offline reinforcement learning, improving sample efficiency and policy performance through confidence-aware data prioritization.

Contribution

The paper proposes A3RL with a confidence-aware sampling strategy that dynamically prioritizes data, addressing challenges in combining online and offline RL.

Findings

A3RL outperforms existing online RL methods with offline data.

Theoretical analysis supports the effectiveness of the active sampling strategy.

Empirical results demonstrate improved policy performance and sample efficiency.

Abstract

Online reinforcement learning (RL) enhances policies through direct interactions with the environment, but faces challenges related to sample efficiency. In contrast, offline RL leverages extensive pre-collected data to learn policies, but often produces suboptimal results due to limited data coverage. Recent efforts integrate offline and online RL in order to harness the advantages of both approaches. However, effectively combining online and offline RL remains challenging due to issues that include catastrophic forgetting, lack of robustness to data quality and limited sample efficiency in data utilization. In an effort to address these challenges, we introduce A3RL, which incorporates a novel confidence aware Active Advantage Aligned (A3) sampling strategy that dynamically prioritizes data aligned with the policy's evolving needs from both online and offline sources, optimizing policy improvement. Moreover, we provide theoretical insights into the effectiveness of our active sampling strategy and conduct diverse empirical experiments and ablation studies, demonstrating that our method outperforms competing online RL techniques that leverage offline data.