The paper introduces new evaluation metrics for safe reinforcement learning that go beyond average safety guarantees by examining how often and how severely safety bounds are violated, consistency across tasks and bounds, and the relationship between training-time and final policy behavior. It also proposes a safety tier system for categorizing algorithms and presents empirical safety evaluations on multiple navigation tasks. The authors recommend reporting aggregate metrics, distributional data, and task‑specific results together, and provide an open‑source suite, SafeRLEval, to facilitate reliable safety assessment.
By Lindsay Spoor, Aske Plaat, Thomas Moerland
The paper proves that using a permissive safety filter in reinforcement learning does not compromise asymptotic performance. By formalizing safety through a safety‑critical Markov decision process and a filtered MDP, the authors show that optimal policies in the filtered MDP achieve the same return as the best safe policy in the original setting. Experiments on Safety Gymnasium confirm zero violations during training and performance that matches or exceeds unfiltered baselines.
By Donggeon David Oh, Duy P. Nguyen, Haimin Hu, Jaime Fern\'andez Fisac
arXiv:2607. 13175v1 Announce Type: cross Abstract: Safe reinforcement learning typically enforces safety by bounding expected cumulative costs, a criterion that often fails to detect rare but catastrophic tail events.
By Yassine Chemingui, Chenhua Fan, Honghao Wei, Janardhan Rao Doppa
arXiv:2608. 10204v1 Announce Type: new Abstract: Safe reinforcement learning maximizes reward subject to safety constraints.
By Chenhua Fan, Jiahui Zhu, Yuhang Zhang, Honghao Wei
arXiv:2609. 12014v1 Announce Type: new Abstract: Safe offline reinforcement learning assumes a cost function on every transition.
By Adam Haroon, Cody Fleming
FAITH is a model‑free reinforcement learning framework that separates safety from task performance by using a learned safety filter. The filter approximates the optimal state‑action safety value with a feedforward network, allowing the task policy to optimize return through filtered dynamics without a competing safety term. Experiments on a double integrator, Safety Gym, a 29‑DoF humanoid, and a real Unitree G1 show that FAITH achieves high returns while maintaining near‑perfect safety and handling infeasible starts gracefully.
By Songyuan Zhang, Baljeet Singh, Sarthak Ranjeet Kaingade, Chuchu Fan, Bryan Trinh
The paper introduces Safe Contrastive Reinforcement Learning (Safe-CRL), a method that corrects bias in contrastive RL caused by failure-terminated Markov decision processes. By applying mass-weighted InfoNCE and a log-survival-mass score, Safe-CRL uses only a one-bit failure signal to improve survival and goal-reaching performance across twelve robot navigation and locomotion tasks. The approach demonstrates complex failure-avoidance behaviors and completes the theoretical foundation of contrastive RL under failure termination.
By Guopeng Li, Yiyang Duan, Yiru Jiao, Chengcheng Xu
arXiv:2606. 14415v1 Announce Type: new Abstract: Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as Constrained Markov Decision Processes (CMDPs).
By Ayoub Belouadah, Sylvain Kubler, Yves Le Traon
arXiv:2610.05166v2 Announce Type: replace
Abstract: A safe action is not necessarily a viable one. A frozen vision-language-action (VLA) policy can favor a locally admissible move that leaves no poli...
By Tu Nguyen, Matthieu Zimmer, Vu Anh Vu, Ziyi Wang, Jannik Hammel Nielsen, Xuebing Zhou, Haitham Bou Ammar
arXiv:2606. 25127v1 Announce Type: new Abstract: We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving.
By Mohamed Benabdelouahad, Ahmed Djalal Hacini, Nadir Farhi, Aissa Boulmerka
arXiv:2603. 15136v2 Announce Type: replace-cross Abstract: Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints.
By Mumuksh Tayal, Manan Tayal, Ravi Prakash
SafeDiSTL is a constrained multi‑agent reinforcement learning framework that decomposes joint constraints using Signal Temporal Logic robustness to assign credit to individual agents. By measuring episode‑level violations through running‑maximum cost increments and computing action sensitivities, the method distributes each cost increment among agents at the same decision time, accounting for delayed effects. Experiments on cooperative payload transport, connected navigation, and networked traffic control show that SafeDiSTL improves safe‑success rates and throughput compared to constrained baselines while preserving unconstrained policy performance.
By Hongrui Zheng, Aditya Singh, Rahul Mangharam