RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
[Uczenie maszynowe] Autorzy: Xi Chen, Fengqi Hu, Zeyu Shen i 5 więcej
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 effect…
- Kategoria arxiv
- cs.LG
- Kategoria
- Uczenie maszynowe