cs.AI updates on arXiv.org 19小时前
Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出一种利用Wasserstein距离进行离线强化学习的策略,以应对分布偏移问题。该方法通过输入凸神经网络建模,实现无判别器的Wasserstein距离计算,避免对抗训练,在D4RL基准数据集上表现出色。

arXiv:2507.10843v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) aims to learn an optimal policy from a static dataset, making it particularly valuable in scenarios where data collection is costly, such as robotics. A major challenge in offline RL is distributional shift, where the learned policy deviates from the dataset distribution, potentially leading to unreliable out-of-distribution actions. To mitigate this issue, regularization techniques have been employed. While many existing methods utilize density ratio-based measures, such as the $f$-divergence, for regularization, we propose an approach that utilizes the Wasserstein distance, which is robust to out-of-distribution data and captures the similarity between actions. Our method employs input-convex neural networks (ICNNs) to model optimal transport maps, enabling the computation of the Wasserstein distance in a discriminator-free manner, thereby avoiding adversarial training and ensuring stable learning. Our approach demonstrates comparable or superior performance to widely used existing methods on the D4RL benchmark dataset. The code is available at https://github.com/motokiomura/Q-DOT .

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

离线强化学习 Wasserstein距离 输入凸神经网络 D4RL基准数据集
相关文章