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

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

SLowRL: Safe Low-Rank Adaptation Reinforcement Learning for Locomotion
Mar 17, 2026Elham Daneshmand, Shafeef Omar, Glen Berseth +2RL Fine-Tuning RL for Legged Locomotion
McGill University · Mila - Quebec AI Institute · Technical University of Munich +1
Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies
Mar 16, 2026Mumuksh Tayal, Manan Tayal, Ravi PrakashFlow Matching Offline RL
Indian Institute of Science, India
Ensuring Safety in Automated Mechanical Ventilation through Offline Reinforcement Learning and Digital Twin Verification
Mar 11, 2026Hang Yu, Huidong Liu, Qingchen Zhang +5Offline RL Safe RL
School of Engineering, University of Warwick, Coventry, UK · School of Computer Science, Chongqing University, China · School of Computer Science and Technology, Hainan University, China +1
SEA-Nav: Efficient Policy Learning for Safe and Agile Quadruped Navigation in Cluttered Environments
Mar 10, 2026Shiyi Chen, Mingye Yang, Haiyi Liu +6Quadruped Robot Navigation Robot Navigation
Tsinghua University, Beijing, China. · Imperial College London, London, UK.
SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action Space
Mar 10, 2026Swaminathan S K, Aritra HazraReinforcement Learning Offline-To-Online RL
Department of Computer Science and Engineering, IIT Kharagpur
Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning
Mar 8, 2026Janaka Chathuranga Brahmanage, Akshat KumarSafe RL Constrained RL
School of Computing and Information Systems, Singapore Management University.
COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance
Mar 8, 2026Dennis GrossFormal Methods for RL Interpretability in RL
Beyond Scalar Rewards: Distributional Reinforcement Learning with Preordered Objectives for Safe and Reliable Autonomous Driving
Mar 6, 2026Ahmed Abouelazm, Jonas Michel, Daniel Bogdoll +2Multi-Objective Reinforcement Learning RL for Autonomous Driving
FZI Research Center for Information Technology, Germany · Karlsruhe Institute of Technology, Germany
Conformal Policy Control
Mar 2, 2026Drew Prinster, Clara Fannjiang, Ji Won Park +4Constrained RL RL Exploration
Prescient Design, Genentech, U.S.A. · Johns Hopkins University, Baltimore, U.S.A. · New York University, NYC, U.S.A. +1
Integrating LTL Constraints into PPO for Safe Reinforcement Learning
Mar 1, 2026Maifang Zhang, Hang Yu, Qian Zuo +3Safe RL Constrained RL
School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, Scotland. · School of Computer Science, Faculty of Engineering, University of Sydney, Darlington NSW 2008, Australia. · School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh EH14 4AS, Scotland.
Learning to maintain safety through expert demonstrations in settings with unknown constraints: A Q-learning perspective
Feb 27, 2026George Papadopoulos, George A. VourosSafe RL Constrained RL
University of Piraeus, Piraeus, Greece
Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty
Feb 24, 2026Xu Wan, Chao Yang, Cheng Yang +2Safe RL Reinforcement Learning
Zhejiang University · Alibaba DAMO Academy · Peking University
Bellman Value Decomposition for Task Logic in Safe Optimal Control
Feb 23, 2026William Sharpless, Oswin So, Dylan Hirsch +2Safe RL Reinforcement Learning
UCSD · MIT
Interacting safely with cyclists using Hamilton-Jacobi reachability and reinforcement learning
Feb 20, 2026Aarati Andrea Noronha, Jean OhAutonomous Driving Planning Safe RL
LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy
Feb 19, 2026Hsin-Jung Yang, Zhanhong Jiang, Prajwal Koirala +3Reinforcement Learning Safe RL
Dept. of Mechanical Engineering Iowa State University Ames, USA · Translational AI Center Iowa State University Ames, USA · Sibley School of Mechanical and Aerospace Engineering Cornell University Ithaca, USA
Safe Continuous-time Multi-Agent Reinforcement Learning via Epigraph Form
Feb 19, 2026Xuefeng Wang, Lei Zhang, Henglin Pu +2Multi-Agent Reinforcement Learning Continuous-Time RL
Purdue University
Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems
Feb 18, 2026Jialiang Fan, Shixiong Jiang, Mengyu Liu +1Adversarial Attacks Black-Box Adversarial Attacks
University of Notre Dame, Notre Dame, IN, USA. · Washington State University Tri-Cities, Richland, WA, USA.
Dual-Quadruped Collaborative Transportation in Narrow Environments via Safe Reinforcement Learning
Feb 18, 2026Zhezhi Lei, Zhihai Bi, Wenxin Wang +1Multi-Robot Cargo Transportation Multi-Robot Systems
Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China · Advanced Remanufacturing & Technology Centre (ARTC), Agency for Science, Technology and Research (A*STAR), Singapore 637143 · Cheng Kar-Shun Robotics Institute, The Hong Kong University of Science and Technology, Hong Kong SAR, China
Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning
Feb 17, 2026Oswin So, Eric Yang Yu, Songyuan Zhang +3Safe RL Reachability Analysis
Department of Aeronautics and Astronautics, MIT · MIT Lincoln Laboratory
Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC
Feb 16, 2026Dennis GrossFormal Methods for RL Formal Verification
Near-Optimal Sample Complexity for Online Constrained MDPs
Feb 16, 2026Chang Liu, Yunfan Li, Lin F. YangConstrained RL Safe RL
University of California, Los Angeles
High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learning
Feb 9, 2026Jiarui Zhang, Chengyong Lei, Chengjiang Dai +4RL for Robotics UAV Navigation
Institute of Cyber-Systems and Control, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China · Differential Robotics, Hangzhou 311121, China.
The impact of temporal resampling on the safety of clinical reinforcement learning: A simulated trial
Feb 6, 2026Thomas Frost, Hrisheekesh Vaidya, Steve HarrisReinforcement Learning Offline RL
University College London, London, United Kingdom · University College London Hospitals NHS Foundation Trust, London, United Kingdom
Constrained Group Relative Policy Optimization
Feb 5, 2026Roger Girgis, Rodrigue de Schaetzen, Luke Rowe +3Group Relative Policy Optimization Constrained RL
Mila – Quebec AI Institute Université de Montréal
Reversible Simplex Supervision with Post-Action Debt Accounting for Goal-Reaching RL
Jan 27, 2026Mehdi Heydari Shahna, Joongheon Kim, Jouni MattilaRL for Robotics Robot Safety
Faculty of Engineering and Natural Sciences, Tampere University, Tampere, Finland · Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea
SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints
Dec 29, 2025Dominik Wagner, Ankit Kanwar, Luke OngSafety-Critical Control Policy Optimization
NTU Singapore · Sony Corporation
Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models
Dec 10, 2025Heng Zhang, Rui Dai, Gokhan Solak +4Safe Robot Manipulation Contact-Rich Robotic Manipulation
Human-Robot Interfaces and Interaction Lab, Istituto Italiano di Tecnologia, Genova, Italy. · Ph.D. program of national interest in Robotics and Intelligent Machines (DRIM), Universit`a di Genova, Genoa, Italy. · Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN, USA. +3
Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning
Nov 6, 2025Jiaming Zhang, Yujie Yang, Haoning Wang +2Safe RL Constrained RL
Department of Mathematical Sciences Tsinghua University Beijing, 100084, China · School of Vehicle and Mobility Tsinghua University Beijing, 100084, China · Department of Mathematical Sciences, Tsinghua University Beijing, 100084, China +1
CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
Oct 16, 2025Lizhi Yang, Blake Werner, Massimiliano de Sa +1RL for Robotics Control Barrier Functions
Caltech MCE
SafeOR-Gym: A Benchmark Suite for Safe Reinforcement Learning Algorithms on Practical Operations Research Problems
Jun 2, 2025Asha Ramanujam, Adam Elyoumi, Hao Chen +5RL Benchmarks Constrained RL
Davidson School of Chemical Engineering, Purdue University, West Lafayette, IN · Energy Sciences, ExxonMobil Technology and Engineering Company, Annandale, NJ · Energy Sciences, ExxonMobil Technology and Engineering Company, Annadale, NJ

Mar 17, 2026J/K move · Enter open · S save

SLowRL: Safe Low-Rank Adaptation Reinforcement Learning for Locomotion

Elham Daneshmand, Shafeef Omar, Glen Berseth, Majid Khadiv+1

McGill University · Mila - Quebec AI Institute · Technical University of Munich+1

RL Fine-Tuning RL for Legged Locomotion Sim-to-Real Transfer Safe RL

Open paper AskPDF arXiv

Sim-to-real transfer of locomotion policies often leads to performance degradation due to the inevitable sim-to-real gap. Naively fine-tuning these policies directly on hardware is problematic, as it poses risks of mechanical failure and suffers from high sample inefficiency. In this paper, we address the challenge of safely and efficiently fine-tuning reinforcement learning (RL) policies for dynamic locomotion tasks. Specifically, we focus on fine-tuning policies learned in simulation directly on hardware, while explicitly enforcing safety constraints. In doing so, we introduce SLowRL, a framework that combines Low-Rank Adaptation (LoRA) with training-time safety enforcement via a recovery policy. We evaluate our method both in simulation and on a real Unitree Go2 quadruped robot for jump and trot tasks. Experimental results show that our method achieves a

46.5\%

reduction in fine-tuning time and near-zero safety violations compared to standard proximal policy optimization (PPO) baselines. Notably, we find that a rank-1 adaptation alone is sufficient to recover pre-trained performance in the real world, while maintaining stable and safe real-world fine-tuning. These results demonstrate the practicality of safe, efficient fine-tuning for dynamic real-world robotic applications.