Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones

Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm which navigates this tradeoff by (1) leveraging offline dat...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE robotics and automation letters 2021-07, Vol.6 (3), p.4915-4922
Hauptverfasser:	Thananjeyan, Brijen, Balakrishna, Ashwin, Nair, Suraj, Luo, Michael, Srinivasan, Krishnan, Hwang, Minho, Gonzalez, Joseph E., Ibarz, Julian, Finn, Chelsea, Goldberg, Ken
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Constraints Domains Image manipulation Learning Navigation Obstacle avoidance Optimization Recovery Recovery zones Reinforcement learning Safety
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!