Safe RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 138% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 153

All topics

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation
Jun 17, 2026Ahmad Farooq, Kamran IqbalNeural Network Verification Multi-Robot Coordination
Department of Electrical and Computer Engineering, University of Arkansas at Little Rock, Little Rock, AR 72204 USA
TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning
Jun 16, 2026Zijie Meng, Ziwei Li, Yufei Liu +5Cyber-Physical Systems Reinforcement Learning
Peking University · National Taiwan University · WHU +1
Memory-Efficient Meta-Reinforcement Learning for Adaptive Safety-Critical Control in Adversarial Spacecraft Proximity Operations
Jun 16, 2026Alejandro Posadas-Nava, Richard Linares, Minduli WijayatungaSpacecraft Rendezvous and Proximity Operations Control Barrier Functions
Researcher, AeroAstro, MIT, 77 Massachusetts Avenue, Cambridge, MA 02139-4307. · Associate Professor and Rockwell International Career Development Professor, AeroAstro, MIT, 77 Massachusetts Avenue, Cambridge, MA 02139-4307. · Assistant Professor, Department of Aerospace Engineering, University of Illinois, Urbana-Champaign, 104 S Wright St, Urbana, IL 61801.
Greed Is Learned: Visible Incentives as Reward-Hacking Triggers
Jun 15, 2026Tong Che, Rui WuReward Hacking LLM Safety
Rutgers University
SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model
Jun 15, 2026Kai Tang, Peidong Jia, Zhong Chu +15Constrained RL Robot Safety
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Beijing Innovation Center of Humanoid Robotics · Nanyang Technological University +2
Hamilton-Jacobi Reachability-Based Safe Reinforcement Learning for Emergency Collision Avoidance
Jun 13, 2026Yuhong Jiang, Shiyue Zhao, Junzhi Zhang +4Collision Avoidance Reachability Analysis
School of Vehicle and Mobility, Tsinghua University, Beijing, China · State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China
Safe Reinforcement Learning of Autonomous Highway Driving: A Unified Framework for Safety and Efficiency
Jun 12, 2026Chufei Yan, Zhihao Cui, Yiyan Lv +3Reinforcement Learning Mixture of Experts
School of Physics, Northeast Normal University, Changchun, 130024, China. · 2Clean Energy Automotive Engineering Center, School of Automotive Studies, Tongji University, Shanghai, 201804, China. · 3Mengshi Automobile Technology Company, Dongfeng Motor Corporation, Wuhan, 430010, China.
Provably Safe, Yet Scalable Reinforcement Learning
Jun 12, 2026Kai S. Yun, Zeyang Li, Navid AzizanRL Control Safety-Critical Control
MIT
CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning
Jun 12, 2026Ayoub Belouadah, Sylvain Kubler, Yves Le TraonConstrained RL Safe RL
SnT, University of Luxembourg
Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning
Jun 12, 2026Omar Adalat, Edwin Hamel-De le Court, Francesco BelardinelliMulti-Agent Coordination Formal Verification
Imperial College London, London SW7 2AZ, UK · University of Manchester, Manchester M13 9PL, UK
Utility-Constrained Policy Optimization
Jun 12, 2026Mehrdad Moghimi, Bernardo Avila PiresConstrained RL Risk-Sensitive RL
York University Toronto, Canada · Google DeepMind London, United Kingdom
Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement Learning
Jun 10, 2026Qingyun Guo, Junyi Shi, Jianuo Huang +1Control Barrier Functions Offline RL
Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland · School of Computing and Data Science, Xiamen University Malaysia, Sepang, Malaysia · Department of Computer Science, University of Toronto, Toronto, Canada
Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models
Jun 9, 2026Samuel Tetteh, Cody FlemingConstrained RL Robot Safety
Iowa State University Ames, Iowa, USA
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
Jun 8, 2026Kaustubh Mani, Yann Pequignot, Vincent Mai +1Sharpness-Aware Minimization RL Exploration
Universit´e de Montr´eal · Mila - Qu´ebec AI Institute · Universit´e Laval +2
Safe-RULE: Safe Reinforcement UnLEarning
Jun 8, 2026Shixiong Jiang, Taozheng Zhu, Fanxin KongOffline RL Safe RL
Department of Computer Science and Engineering, University of Notre Dame
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
Jun 7, 2026Lingxuan Wu, Zijian Zhu, Lizhong Wang +5Robot Policy Learning Diffusion Policy
Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua-Bosch Joint ML Center, THBI Lab, BNRist Center, Tsinghua University, Beijing, 100084, China · Peng Cheng Laboratory, 518108, China
Merging model-based control with multi-agent reinforcement learning for multi-agent cooperative teaming strategies
Jun 4, 2026Christian Llanes, Spencer W. Jensen, Samuel CooganMulti-Agent Control Multi-Robot Coordination
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA. · Sandia National Laboratories, Albuquerque, NM 87123, USA.
Learning of Robot Safety Policies via Adversarial Synthetic Scenarios
Jun 4, 2026Nikolai Dorofeev, Alexey Odinokov, Rostislav YavorskiyRobot Policy Learning Adversarial Scenario Generation
SafePI.ai Grenoble, France · SafePI.ai Belgrade, Serbia · SafePI.ai Madrid, Spain
Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe Guarantees
Jun 3, 2026Mohit Prashant, Arvind EaswaranControl Barrier Functions Risk-Sensitive RL
Nanyang Technological University
COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered Projection
Jun 3, 2026Guopeng Li, Moritz A. Zanger, Matthijs T. J. Spaan +1Robotic Control Multi-Objective Reinforcement Learning
Department of Cognitive Robotics, Delft University of Technology · School of Transportation, Southeast University, China · Department of Intelligent Systems, Delft University of Technology, the Netherlands
Explainably Safe Reinforcement Learning
Jun 3, 2026Sabine Rieder, Stefan Pranger, Debraj Chakraborty +2Reinforcement Learning Interpretability in RL
Masaryk University · Technical University of Munich · Graz University of Technology
Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning
Jun 3, 2026Damian Lebiedź, Robert ŚlepaczukSafe RL Algorithmic Trading
Faculty of Economic Sciences, University of Warsaw, ul. Długa 44/50, Warsaw, 00-241, Poland · Quantitative Finance Research Group, Department of Quantitative Finance and Machine Learning, Faculty of Economic Sciences, University of Warsaw, ul. Długa 44/50, Warsaw, 00-241, Poland
Easy-to-Use Shielding for Reinforcement Learning
Jun 2, 2026Stefan Pranger, Bettina KönighoferReinforcement Learning RL Exploration
Institute of Information Security, Graz University of Technology
Autopilot-Preserving Residual Q-Learning with HJB-Inspired Finite-Action Risk Filtering for Fixed-Wing UAV Command Supervision
May 31, 2026Mehmet Iscan, Batuhan TemizAerial Robotics Stochastic Optimal Control
PythaLab, Yildiz Technical University, Istanbul, Turkey · Autopilot Systems Chief Engineer, Turkish Aerospace (TUSAŞ), Ankara, Turkey
All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning
May 31, 2026Bernd Frauenknecht, Devdutt Subhasish, Artur Eisele +2Robotic RL Safe RL
Institute for Data Science in Mechanical Engineering, RWTH Aachen University, 52062 Aachen, Germany
Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment
May 31, 2026Xun Shen, Yuepeng Wang, Akifumi Wachi +13Reinforcement Learning Sequential Decision Making
Tokyo University of Agriculture and Technology · LY Corporation · National University of Singapore +6
A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning
May 31, 2026Yuepeng Wang, Ken Kawano, Yoshihiko Fujisawa +12RL Benchmarks Reinforcement Learning
Tokyo University of Agriculture and Technology · Institute of Science Tokyo · National University of Singapore +5
Robust Shielding for Safe Reinforcement Learning
May 29, 2026Edwin Hamel-De le Court, Thom Badings, Alessandro Abate +2Robust Markov Decision Processes Formal Verification
Department of Computer Science, University of Manchester, United Kingdom · Faculty of Computer Science & DSME, RWTH Aachen University, Germany · Department of Computer Science, University of Oxford, United Kingdom +1
Safe Equilibrium Policy Optimization for Strategic Agent Policies
May 29, 2026Karthika Arumugam, Kiran Kumar Manku, Amit DhandaMulti-Agent System Optimization Game-Playing Agents
†Amazon, USA
SARAD: LLM-Based Safety-Aware Hybrid Reinforcement Learning with Collision Prediction for Autonomous Driving
May 27, 2026Kangyu Wu, Peng Cui, Guoxi Chen +1Autonomous Driving Traffic Accident Anticipation
School of Automation, Southeast University, Nanjing, China · Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Nanjing, China

Jun 17, 2026, cs.ROJ/K move · Enter open · S save

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation

Ahmad Farooq, Kamran Iqbal

Department of Electrical and Computer Engineering, University of Arkansas at Little Rock, Little Rock, AR 72204 USA

Neural Network Verification Multi-Robot Coordination Safe RL Multi-Agent Communication Multi-Agent Reinforcement Learning

Open paper AskPDF arXiv

Multi-agent reinforcement learning (MARL) enables agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deployment in drone swarms and autonomous vehicle fleets. We present the first end-to-end framework for safety verification of learned multi-agent communication policies through policy abstraction: neural policies are distilled into interpretable decision trees, then formally verified, with empirical validation confirming that verified safety properties transfer to original networks. Our four-stage pipeline consists of domain-specific feature extraction from agent observations, decision tree distillation achieving 97.9% +/- 1.2% fidelity to neural policies, automated translation to PRISM probabilistic model checker specifications with complete feature-to-state-variable correspondence, and compositional verification of Probabilistic Computation Tree Logic (PCTL) properties via pairwise decomposition with union-bound aggregation and empirical neighbor modeling. Evaluating Vector-Quantized Variational Information Bottleneck (VQ-VIB) policies for multi-drone coordination with 5-7 agents, we verify 18 temporal logic properties across safety, liveness, and cooperation, achieving 88.9% property satisfaction with all five safety thresholds satisfied (0.3% collision probability vs. 1% threshold). Monte Carlo validation of original neural policies confirms that verified safety properties transfer with <=0.6 percentage-point deviation (95% CI). Discrete VQ-VIB messages provide +11.6 to +13.6 percentage-point fidelity advantages over continuous methods, enabling 3-4x faster verification. Our framework provides empirically validated safety verification for distilled policy abstractions, serving as a practical bridge between deep MARL and formal safety workflows for multi-robot deployment.

Momentum

Related topics

Latest papers 153