arXiv cs.AI· Xi Chen, Fengqi Hu, Zeyu Shen, Jiaying Xu, Shangding Gu, Pan Xu, Anqi Liu, Laixi Shi·· 12 小时前AI 评分31
RobustRLlib：面向鲁棒强化学习算法的统一库与基准
RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
AI 导读
RobustRLlib 是一个以算法为中心的鲁棒强化学习库与基准，在统一接口下集成了 17 种代表性的在线、离线与安全 RL 算法，并配套覆盖真实世界偏移及人形机器人、视觉-语言-动作任务的评测平台。对 273 种扰动配置的系统评测给出了当前鲁棒 RL 算法的最新能力图谱，揭示其有效范围与仍存在的鲁棒性差距。该平台开源且易于使用，提供可复现、可扩展的代码库。
正文 · 原文
Abstract:Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under diverse shifts and disruptions. Existing robust RL algorithms offer a rich set of mechanisms and principles, yet two major barriers limit their broader potential: limited algorithm reusability and an unclear empirical capability boundary. We introduce RobustRLlib, an algorithm-centric library and benchmark that addresses both challenges. It integrates 17 representative robust online, offline, and safe RL algorithms under a unified interface for substantially improved reusability, together with an enhanced evaluation platform spanning diverse real-world shifts and advanced humanoid and vision-language-action tasks. Systematic evaluation over 273 perturbation configurations provides an up-to-date capability map of current robust RL algorithms, revealing where they remain effective and where substantial robustness gaps persist. As an open-source, user-friendly platform, RobustRLlib offers a reproducible and extensible codebase for applying existing methods to new problems and developing new robust RL algorithms.
| Comments: | Project page, code, and tutorial: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2610.32971 [cs.LG] |
| (or arXiv:2610.32971v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32971 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xi Chen [view email]
[v1]
Fri, 23 Oct 2026 17:57:22 UTC (4,099 KB)
来源：arXiv cs.AI · arxiv.org