task · first seen 4 Oct 2026
safe reinforcement learning
Also: safe RL, constrained reinforcement learning, safety-constrained reinforcement learning, Lagrangian constrained policy optimization
Reinforcement learning that maximizes return while satisfying constraints on cumulative cost or safety violations.
Mentions per week
PapersCodeDiscussion
Earliest sources
- A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action PoliciesPapers · 4 Oct 2026 · Tu Nguyen, Matthieu Zimmer, Vu Anh Vu, Ziyi Wang, Jannik Hammel Nielsen, Xuebing…
- Reachability-Aware Diffusion Policy OptimizationPapers · 5 Oct 2026 · Hikmet Simsir, Kutay Demiray, Ozgur S. Oguz
- Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement LearningPapers · 5 Oct 2026 · Nicolas Hochuli, Lorenzo Miele, Kristina Shea, Tino Stankovic
- Safe on Average, Unsafe in the Tail: When Is the Episodic-Cost Tail Controllable?Papers · 7 Oct 2026 · Samuel Tetteh, Cody Fleming
- A Unified Bellman Operator for Safety-Critical Reinforcement LearningPapers · 8 Oct 2026 · Nishanth Arun Rao, Royina Karegoudra Jayanth, Benjamin Eysenbach, Jaime Fernánd…
- FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional SystemsPapers · 8 Oct 2026 · Songyuan Zhang, Baljeet Singh, Sarthak Ranjeet Kaingade, Chuchu Fan, Bryan Trinh
Latest sources
- Algorithm Distillation for Safe In-Context Reinforcement LearningPapers · 16 Nov 2026 · Minjae Kwon, Amir Moeini, Shangtong Zhang, Lu Feng
- Towards Probabilistically Safe Reinforcement Learning: Theory and Deployment on Humanoid and Aerial RobotsPapers · 14 Nov 2026 · Pol Mestres, Varun Gabbita, Jason H. K. Siu, Sergio A. Esteban, Hampus Serneke,…
- Safety as a Budget: Calibrating the Control Channel of Constrained GRPO for Vision-Language ModelsPapers · 12 Nov 2026 · Bo Han
- BECON: Belief-Conditioned Constrained Multi-Objective Reinforcement Learning under Drifting Preferences and BudgetsPapers · 9 Nov 2026 · Bui Trong Duc, Huynh Thi Thanh Binh
- Probably Safe Sim-to-Real Transfer with Lifetime ValidityPapers · 6 Nov 2026 · Rohan Tangri, Jan-Peter Calliess
- Safety-Focused Reinforcement Learning Using Risk-Sensitive Coupled ControlPapers · 6 Nov 2026 · Jiabin Lin, Shana Moothedath, Vivek S. Borkar
- Safe Reinforcement Learning via Probabilistic Option ShieldingPapers · 6 Nov 2026 · Gian Luca Ascari, Isidoro Tamassia, Ying Jiao, Luc De Raedt, Giuseppe Marra
- Accelerating Safe Reinforcement Learning with Massive ParallelismPapers · 5 Nov 2026 · Joonyoung Lim, Younghwan Yoo
- Rare Event Constrained Reinforcement Learning with Large DeviationsPapers · 1 Nov 2026 · Rahul Misra
- Structural Dual Adaptation for Safe Reinforcement LearningPapers · 31 Oct 2026 · Runsheng Yu, Zhuoyang Song, Zengde Deng, Qixin Zhang, Li Shen, Jiaxing Zhang
- DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous ProcessesPapers · 30 Oct 2026 · Yeojin Jang, Minu Baek, Gihun Gil, Minsung Jung, Beomdo Park, Woohyeon Kwon, Hye…
- OmniPiano: Diverse Dexterous Piano-Playing Challenges for Standard, Robust, Safe, and Multi-Agent RLPapers · 30 Oct 2026 · Fan Xu, Fan Yang, Yifan Xu, Ruiyuan Zhang, Yimou Wu, Nuo Yi, Muning Wen, Guang C…