arXiv AI
Convex-Analytic View of Query Selection for Safety Verification of Markov Decision Processes
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 15
Evaluation Metrics for Safe Reinforcement Learning
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.
arXiv Machine Learning
Sep 21
Provably Optimal Reinforcement Learning under Safety Filtering
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.
Hugging Face Trending Papers
Aug 26
Quantitative Analysis of $ω$-Regular Robust MDPs
Robust Markov Decision Processes (RMDPs) generalize classical MDPs by allowing uncertainty in transition probabilities and optimizing against their worst-case realization. We consider $(s,a)$-rectangu...
arXiv AI
Oct 15
Certifying Almost-Sure Reachability in Unknown MDPs
arXiv:2610.18119v1 Announce Type: cross Abstract: {\em Specification-Guided Reinforcement Learning (RL)} has largely concerned itself with \emph{learning} an optimal policy against a formal specifica...
arXiv AI
Jul 23
Safe Remediation as Risk-Constrained Intervention Decision in Microservice Systems
arXiv:2607. 20005v1 Announce Type: new Abstract: In modern IT operations (IT-Ops), the cost of an incorrect repair often exceeds the cost of no action at all.
arXiv AI
Oct 5
Instance-Dependent Regret for CMDPs with Step-Wise Constraints
arXiv:2610.02520v1 Announce Type: cross Abstract: We study online learning in episodic tabular constrained Markov decision processes with step-wise safety constraints. In such a setting, the constrai...