RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
The paper introduces RobustRLlib, a library and benchmark for robust reinforcement learning that improves reusability and provides an empirical capability map of current robust RL algorithms.
The paper introduces a new library and benchmark that improves reusability and provides a more comprehensive understanding of robust RL algorithms.
Before reading this…
Applications
- →real-world deployment
- →humanoid and vision-language-action tasks
To understand this paper, make sure you know these concepts first:
- reinforcement learningfind papers →
- robustnessfind papers →
Abstract
More Like ThisRobust 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.