堅牢強化学習のための統一ライブラリとベンチマーク
RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
17種の堅牢なオンライン・オフライン・安全RLアルゴリズムを統一インターフェースで実装し、多様な摂動下での評価ベンチマークを提供するライブラリを提案した論文。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Xi Chen, Fengqi Hu, Zeyu Shen, Jiaying Xu, Shangding Gu, Pan Xu, Anqi Liu, Laixi Shi
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
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.