arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.12136cs.LGstat.ML
收藏

可证明的有限样本离线强化学习领域适应

Provable Domain Adaptation for Offline Reinforcement Learning with Limited Samples

Rensselaer Polytechnic Institute(新泽西理工学院);Columbia University(哥伦比亚大学)

Weiqin Chen, Xinjie Zhang, Sandipan Mishra, Santiago Paternain

AI总结:

本文提出首个可证明的有限样本离线强化学习领域适应框架,通过理论分析和实验验证,探讨权重分配对性能的影响,并提供收敛保证。

摘要:

离线强化学习(RL)从静态的目标数据集中学习有效的策略。尽管最先进的离线RL算法性能优异,但其表现依赖于目标数据集的规模,当目标数据集中样本有限时,性能会显著下降,这在现实应用中很常见。为了解决这个问题,利用相关源数据集(如模拟器)中的辅助样本进行领域适应是有益的。然而,如何在有限的目标数据集和大但有偏的源数据集之间找到最优的权衡方式,并确保可证明的理论保证仍然是一个开放性挑战。到目前为止,本文提出了第一个框架,从理论上探讨了分配给每个数据集的权重对离线RL性能的影响。特别是,我们建立了性能界限,并证明了最优权重的存在,这可以在简化假设下以闭合形式计算。我们还以收敛到最优解的邻域提供了算法保证。值得注意的是,这些结果依赖于源数据集的质量和目标数据集中的样本数量。我们在著名的Procgen和MuJoCo基准上进行了实验证实了本文的理论贡献。

英文摘要:

Offline reinforcement learning (RL) learns effective policies from a static target dataset. The performance of state-of-the-art offline RL algorithms notwithstanding, it relies on the size of the target dataset, and it degrades if limited samples in the target dataset are available, which is often the case in real-world applications. To address this issue, domain adaptation that leverages auxiliary samples from related source datasets (such as simulators) can be beneficial. However, establishing the optimal way to trade off the limited target dataset and the large-but-biased source dataset while ensuring provably theoretical guarantees remains an open challenge. To the best of our knowledge, this paper proposes the first framework that theoretically explores the impact of the weights assigned to each dataset on the performance of offline RL. In particular, we establish performance bounds and the existence of the optimal weight, which can be computed in closed form under simplifying assumptions. We also provide algorithmic guarantees in terms of convergence to a neighborhood of the optimum. Notably, these results depend on the quality of the source dataset and the number of samples in the target dataset. Our empirical results on the well-known Procgen and MuJoCo benchmarks substantiate the theoretical contributions in this work.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑