arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.02486cs.LG
收藏

对抗动态偏移的双鲁棒跨域离线强化学习

Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts

CityUHK(城市大学 Hong Kong 分校);UIUC(伊利诺伊大学香槟分校);Tsinghua University(清华大学);Yale University(耶鲁大学);CUHK(SZ)(香港中文大学(深圳));Tencent(腾讯)

Zhongjian Qiao, Rui Yang, Jiafei Lyu, Xiu Li, Zhongxiang Dai, Zhuoran Yang, Siyang Gao, Shuang Qiu

AI总结:

本文提出DROCO算法,通过引入鲁棒跨域Bellman算子和动态价值惩罚等技术,提升跨域离线强化学习在动态偏移下的双鲁棒性。

摘要:

单域离线强化学习(RL)常面临数据覆盖有限的问题,而跨域离线RL通过利用其他域的额外数据来解决这一问题,但现有研究主要关注训练时的鲁棒性(处理训练数据中的动态偏移),忽略了在实际部署中面对动态扰动时的测试时鲁棒性。本文研究了跨域离线RL中对动态偏移的双鲁棒性(训练时和测试时)。我们首先实证表明,使用跨域离线RL训练的策略在评估时对动态扰动表现出脆弱性,尤其是在目标域数据有限时。为解决此问题,我们引入了一个新颖的鲁棒跨域Bellman(RCB)算子,该算子在增强对动态扰动的测试时鲁棒性的同时,保持对非分布动态转换的保守性,从而保证训练时的鲁棒性。为进一步对抗RCB算子可能引起的潜在价值高估或低估,我们引入了动态价值惩罚和Huber损失两种技术,从而得到实用的\textbf{D}ual-\textbf{RO}bust \textbf{C}ross-domain \textbf{O}ffline RL(DROCO)算法。在各种动态偏移场景下的广泛实证结果表明,DROCO在多个基准上表现更优,并展示了对动态扰动的增强鲁棒性。

英文摘要:

Single-domain offline reinforcement learning (RL) often suffers from limited data coverage, while cross-domain offline RL handles this issue by leveraging additional data from other domains with dynamics shifts. However, existing studies primarily focus on train-time robustness (handling dynamics shifts from training data), neglecting the test-time robustness against dynamics perturbations when deployed in practical scenarios. In this paper, we investigate dual (both train-time and test-time) robustness against dynamics shifts in cross-domain offline RL. We first empirically show that the policy trained with cross-domain offline RL exhibits fragility under dynamics perturbations during evaluation, particularly when target domain data is limited. To address this, we introduce a novel robust cross-domain Bellman (RCB) operator, which enhances test-time robustness against dynamics perturbations while staying conservative to the out-of-distribution dynamics transitions, thus guaranteeing the train-time robustness. To further counteract potential value overestimation or underestimation caused by the RCB operator, we introduce two techniques, the dynamic value penalty and the Huber loss, into our framework, resulting in the practical \textbf{D}ual-\textbf{RO}bust \textbf{C}ross-domain \textbf{O}ffline RL (DROCO) algorithm. Extensive empirical results across various dynamics shift scenarios show that DROCO outperforms strong baselines and exhibits enhanced robustness to dynamics perturbations.

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。

↑