Safe RL

RL: Reinforcement Learning

Safe reinforcement learning aims to maximize task performance while limiting hazards such as collisions, equipment damage, or unsafe medical decisions, including during exploration and deployment. Common approaches formulate constraints as costs in constrained Markov decision processes and use primal-dual or Lagrangian optimization; others add control-barrier-function, Lyapunov, or reachability shields that filter actions, sometimes using learned models to account for uncertainty. Work also addresses offline learning, human preference feedback, temporal-logic specifications, and applications from robotics and driving to healthcare and energy control. A central challenge is balancing strong, reliable safety guarantees with reward, data efficiency, and adaptation to unfamiliar conditions; benchmarks also show that methods vary across tasks and that average costs can hide rare severe failures.

Latest papers

215 papers24 papers in the last four weeks, up 14% on the four weeks before. 0.1% of all new papers.

CORMA: Constraint-Routed Decision Mamba for Generalizable Multi-Constraint Offline Safe Reinforcement Learning
Oct 25, 2026Changxu Ni, Feiran You, Yongan Guo +5Safe RL Reinforcement Learning
Southeast University · The University of Hong Kong · Nanjing University of Posts and Telecommunications
Physics-Informed Graph-Based Safe RL with Constraint-Specific Critics for Community Battery Coordination in Distribution Network
Oct 24, 2026Chenghao Huang, Yue Yang, Hao WangPower Systems Safe RL
Department of Data Science and AI, Faculty of IT and Monash Energy Institute, Monash University, Melbourne, VIC 3800, Australia
RBGA: Residual-Budget Guide Arbitration for Offline-to-Online Safe Reinforcement Learning in Dexterous Manipulation
Oct 24, 2026Zongyou Yu, Ao Zhou, Xiongbo Shi +7Reinforcement Learning Safe RL
Tongji University · Shanghai Innovation Institute · Xiaomi EV +2
SEVI: Safe Evidential Real-World Reinforcement Learning
Oct 22, 2026Shaekh Mohammad Shithil, Lantao LiuSafe RL Robotic RL
Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN 47408 USA
SAFTER: Safety-Aware Filtering Through Explicit Recoverability for Robust Reinforcement Learning under Distribution Shift
Oct 21, 2026Benedictus C. G. Cinun, Bin HuSafe RL Reinforcement Learning
Department of Electrical and Computer Engineering, University of Houston, Houston, TX 77004, USA · Department of Engineering Technology, University of Houston, Houston, TX 77004, USA
Prescribed Performance Guided Safe Reinforcement Learning for Roundabout Navigation of Autonomous Vehicles
Oct 20, 2026Wenhan Li, Yangrui Zhang, Hang Zhou +2Autonomous Driving Planning RL for Autonomous Driving
Robotics and Autonomous Systems Thrust, Systems Hub, the Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong Province, China
RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning
Oct 16, 2026Alexander W. Goodall, Francesco BelardinelliSafe RL Formal Methods for RL
Department of Computer Science Imperial College London
Safe Reinforcement Learning with Receding-Horizon Safety Critic and Differentiable Action Shields
Oct 14, 2026Siwei Ju, Jan Peters, Oleg ArenzSafe RL Safety Filtering
Department of Computer Science, Technical University of Darmstadt, Germany. · Hessian.AI. · German Research Center for AI (DFKI), Research Department: Systems AI for Robot Learning. +1
Beyond Safe Execution: Safe Online Reinforcement Learning for Autonomous Driving with Value Calibration and Adaptive Guidance
Oct 13, 2026Zeqiao Li, Yijing Wang, Haoyu Wang +2RL for Autonomous Driving Safe RL
A Reinforcement Learning Framework for Safety-Aware Haptic Shared Control in Surgical Robotics
Oct 11, 2026Zihao Zhang, Karl Handwerker, Balint VargaRobotic Control Human-Robot Collaboration
Institute of Control Systems, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems
Oct 8, 2026Songyuan Zhang, Baljeet Singh, Sarthak Ranjeet Kaingade +2Safe RL Constrained RL
Massachusetts Institute of Technology · Amazon
A Unified Bellman Operator for Safety-Critical Reinforcement Learning
Oct 8, 2026Nishanth Arun Rao, Royina Karegoudra Jayanth, Benjamin Eysenbach +1Safe RL Constrained RL
Department of Electrical and Computer Engineering Princeton University · Department of Computer Science Princeton University
Toward Optimal Regret in Adversarial MDPs with Stochastic Hard Constraints
Oct 8, 2026Qian Zuo, Francesco Emanuele StradiMarkov Decision Processes Constrained RL
University of Edinburgh · Politecnico di Milano
Safe Meta-Policy Design with Risk Control
Oct 7, 2026Wenbin Zhou, Michael Lingzhi Li, Shixiang ZhuSafe RL Risk-Sensitive RL
Heinz College of Information Systems and Public Policy, Carnegie Mellon University · Technology and Operations Management, Harvard Business School
Safe on Average, Unsafe in the Tail: When Is the Episodic-Cost Tail Controllable?
Oct 7, 2026Samuel Tetteh, Cody FlemingSafe RL Constrained RL
Iowa State University Ames, Iowa, USA
Reachability-Aware Diffusion Policy Optimization
Oct 5, 2026Hikmet Simsir, Kutay Demiray, Ozgur S. OguzConstrained RL Diffusion Policy
Department of Computer Engineering, Bilkent University
CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies
Oct 3, 2026Santhosh GS, Ananya Ravi, Devika Jay +5Reinforcement Learning Safe RL
Center for Responsible AI IIT Madras Chennai, India · Ericsson Research India
Instance-Dependent Regret for CMDPs with Step-Wise Constraints
Oct 1, 2026Qian Zuo, Francesco Emanuele Stradi, Leyang Xue +1Constrained RL Safe RL
University of Edinburgh · Politecnico di Milano · University College London
DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles
Sep 30, 2026Sanghyuk Park, Kwanwoo Lee, Taekyung Kim +2RL for Robotics Control Barrier Functions
Department of Intelligence and Information, Seoul National University, Republic of Korea · Department of Robotics, University of Michigan, Ann Arbor, MI, USA · Department of Mechanical Engineering, Yonsei University, Republic of Korea +1
Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy
Sep 29, 2026Huan Rong, Chao Yin, Anouar Imel +2Constrained RL RL for Autonomous Driving
School of Artificial Intelligence, Nanjing University of Information Science & Technology, Jiangsu, Nanjing, 210-044, China · School of Information and Communication Engineering, University of Electronic Science and Technology of China, Sichuan, Chengdu, 611731, China · School of Software, Nanjing University of Information Science & Technology, 210044, Jiangsu, China +1
RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts
Sep 29, 2026Hongbin Lin, Chaoda Zheng, Yiming Yang +11End-to-End Autonomous Driving Action-Conditioned World Models
The Chinese University of Hong Kong, Shenzhen · XPeng Motors · Xidian University
RefineDrive: Reliable Failure-Guided Learning for Vision-Language-Action Driving
Sep 28, 2026Zhe Sun, Ziyi Luo, Yehao Lu +2VLMs for Autonomous Driving Autonomous Driving Planning
College of Computer Science and Technology, Zhejiang University, Hangzhou, China · Yinwang Intelligent Technology Co., Ltd.
Model-Informed Safe Reinforcement Learning for Bipedal Locomotion via Step-to-Step Prediction
Sep 28, 2026Victor Paredes, Ayonga HereidHumanoid Robot Locomotion Control Barrier Functions
Mechanical and Aerospace Engineering, The Ohio State University, Columbus, OH, USA.
Vision--Language Signals in Constrained RL: Safety Gains Without Anticipation
Sep 28, 2026Samuel Tetteh, Cody FlemingConstrained RL RL for Autonomous Driving
Iowa State University Ames, Iowa, USA
Hierarchical Multi-agent Reinforcement Learning for Warehouse Robot Coordination under Communication Loss
Sep 27, 2026Weihao Sun, Gehui Xu, Andreas A. MalikopoulosHierarchical RL Multi-Robot Coordination
Systems Engineering Program, Cornell University, Ithaca, NY 14850 USA · Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, UK · Applied Mathematics, Systems Engineering, Mechanical Engineering, Electrical & Computer Engineering, and School of Civil & Environmental Engineering, Cornell University, Ithaca, NY, USA
Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning
Sep 27, 2026Boyang Li, Matthew Kim, Sylvia Lee HerbertScore Matching Constrained RL
University of California San Diego
Constrained Flow Policy Updates: A Generalized Schrödinger Bridge View
Sep 26, 2026Boyang Li, Matthew Kim, Sylvia HerbertFlow-Based Policy Learning Reinforcement Learning
University of California San Diego
Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning
Sep 23, 2026Ruihan Wu, Rui Yang, Donggeon David Oh +2Sequential MARL RL for Robotics
Department of Computer Science, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544, USA
Computationally efficient safe exploration in reinforcement learning
Sep 19, 2026Shreeram Murali, Shankar A. Deka, Dominik BaumannSafe RL Constrained RL
Cyber-physical Systems Group · Nonlinear Systems and Control Group, Aalto University, Espoo, Finland
SAGE: Safety-Aligned Gradient Enforcement for Human--Robot Collaboration
Sep 17, 2026Yisen Li, Hao Zhang, Ruize Geng +3Safe RL Robot Safety
University of Texas at Arlington · Carnegie Mellon University

Oct 25, 2026J/K move · Enter open · S save

CORMA: Constraint-Routed Decision Mamba for Generalizable Multi-Constraint Offline Safe Reinforcement Learning

Changxu Ni, Feiran You, Yongan Guo, Hongyang Du+4

Southeast University · The University of Hong Kong · Nanjing University of Posts and Telecommunications

Safe RL Reinforcement Learning Constrained RL Offline RL

Open paper AskPDF arXiv

Offline safe reinforcement learning (RL) learns safety-aware policies from static datasets while satisfying safety constraints during deployment. Motivated by the strong trajectorymodeling capabilities of Transformers, recent Decision Transformer (DT)-based methods formulate offline safe RL as conditional sequence modeling by conditioning action generation on return-to-go (RTG) and cost-to-go (CTG) tokens, thereby enabling adaptation to varying safety budgets. However, existing DT-based methods are developed for single-constraint tasks. For tasks with multiple constraints, generalizing learned policies to unseen combinations of safety budgets remains challenging due to the conflicting requirements imposed by heterogeneous constraints. Moreover, the quadratic complexity of Transformer architectures significantly increases the computational overhead in multi-constraint tasks, as representing additional constraints requires more CTG tokens. Recently, Mamba has emerged as an efficient sequence-modeling backbone, offering linear computational complexity and strong generalization capabilities. In this paper, we propose CORMA, a constraint-routed decision Mamba framework for generalizable multi-constraint offline safe RL. CORMA decomposes policy inference into constraint-aware RTG estimation and adaptive action generation, where constraint-specific experts model feasible RTG distributions and a router-guided product-of-experts mechanism fuses these distributions to provide safety-aware guidance for a Mamba-based action decoder. A three-stage optimization strategy is designed to improve training stability. Extensive experiments on OSRL benchmarks demonstrate that CORMA achieves superior reward-safety trade-offs, reduces inference latency by 37% compared with DT-based methods, and exhibits stronger zero-shot generalization to unseen safety-budget combinations than offline safe RL baselines.