Constrained RL

RL: Reinforcement Learning

Ask about this topic

Overview

Constrained reinforcement learning studies how agents can maximize rewards while obeying limits on costs such as collisions, energy use, latency, or harm. Many methods model the problem as a constrained Markov decision process and use Lagrangian or primal-dual updates; others enforce feasibility with action masks, projections, safety shields, control barrier functions, or reachability analysis. These approaches are used in settings from robot control and power systems to language-model alignment, with work spanning online and offline learning, multi-agent tasks, and formal guarantees for regret and constraint satisfaction. A central challenge is balancing useful performance with reliable safety: average-cost limits can miss rare severe failures, while strict safeguards may make learning conservative or difficult to scale.

Latest papers

CardsList

226 papers38 papers in the last four weeks, up 46% on the four weeks before. 0.2% of all new papers.

  1. Latency-aware Human-in-the-Loop Reinforcement Learning for Semantic Communications

    Feb 17, 2026Peizheng Li, Xinyi Lin, Adnan AijazSemantic CommunicationTask-Oriented Semantic Communication

    Bristol Research and Innovation Laboratory, Toshiba Europe Ltd., U.K.

  2. Near-Optimal Sample Complexity for Online Constrained MDPs

    Feb 16, 2026Chang Liu, Yunfan Li, Lin F. YangConstrained RLSafe RL

    University of California, Los Angeles

  3. Constrained Group Relative Policy Optimization

    Feb 5, 2026Roger Girgis, Rodrigue de Schaetzen, Luke Rowe +3Group Relative Policy OptimizationConstrained RL

    Mila – Quebec AI Institute Université de Montréal

  4. Cantelli Constrained Policy Optimization

    Jan 30, 2026Rohan Tangri, Jan-Peter CalliessPolicy OptimizationConstrained RL

    Machine Learning Research Group, University of Oxford, Oxford, United Kingdom

  5. PlatoLTL: Scaling LTL-Guided Multi-Task RL

    Jan 30, 2026Jacques Cloete, Mathias Jackermeier, Ioannis Havoutis +1RL for RoboticsConstrained RL

    Oxford Robotics Institute University of Oxford Oxford, United Kingdom · Department of Computer Science University of Oxford Oxford, United Kingdom

  6. SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints

    Dec 29, 2025Dominik Wagner, Ankit Kanwar, Luke OngSafety-Critical ControlPolicy Optimization

    NTU Singapore · Sony Corporation

  7. Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning

    Nov 6, 2025Jiaming Zhang, Yujie Yang, Haoning Wang +2Safe RLConstrained 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

  8. CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions

    Oct 16, 2025Lizhi Yang, Blake Werner, Massimiliano de Sa +1RL for RoboticsControl Barrier Functions

    Caltech MCE

  9. Gain Tuning Is Not What You Need: Reward Gain Adaptation for Constrained Locomotion Learning

    Oct 12, 2025Arthicha Srisuchinnawong, Poramate ManoonpongConstrained RLRL for Legged Locomotion

    Vidyasirimedhi Institute of Science and Technology, Rayong, Thailand. · The University of Southern Denmark, Odense, Denmark.

  10. Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints

    Sep 24, 2025Francesco Emanuele Stradi, Eleonora Fidelia Chiefari, Matteo Castiglioni +2Markov Decision ProcessesConstrained RL

    Politecnico di Milano

  11. SafeOR-Gym: A Benchmark Suite for Safe Reinforcement Learning Algorithms on Practical Operations Research Problems

    Jun 2, 2025Asha Ramanujam, Adam Elyoumi, Hao Chen +5RL BenchmarksConstrained 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

  12. TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels

    Apr 17, 2025Siow Meng Low, Ze Gong, Akshat KumarRL ControlCredit Assignment in RL

    School of Computing and Information Systems, Singapore Management University, Singapore · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

  13. Learning Constraints-Based Adaptive Hypergraph Neural Networks for Solving Vehicle Routing Problems

    Mar 13, 2025Zhenwei Wang, Tiehua Zhang, Jing Liu +3Constrained RLVehicle Routing

    University of Nottingham Ningbo China, 199 East Taikang Road, Ningbo, 315100, Zhejiang, China · Tongji University, 1239,Siping Road, Shanghai, 200092, Shanghai, China · State Key Laboratory for Novel Software Technology, Nanjing University, 163,Xianlin Road, Nanjing, 210023, Jiangsu, China +1

  14. Navigating Demand Uncertainty in Container Shipping: Deep Reinforcement Learning for Enabling Adaptive and Feasible Master Stowage Planning

    Feb 18, 2025Jaike van Twiller, Yossiri Adulyasak, Erick Delage +2Constrained RL

    IT University of Copenhagen, Denmark · HEC Montréal, Qc, Canada · GERAD, Qc, Canada +1

  15. The Price of Failure Risk: Clipped Barrier Policy Gradients with Convex Regularization

    Nov 28, 2024Pekka Malo, Lauri Viitasaari, Antti Suominen +2Policy Gradient MethodsConstrained RL

    Aalto University, Department of Information and Service Management, Finland. · University of Helsinki, Department of Forest Sciences, Finland.

  16. Constrained Reinforcement Learning for Safe Heat Pump Control

    Sep 29, 2024Baohe Zhang, Lilli Frison, Thomas Brox +1RL ControlConstrained RL

    Faculty of Computer Science, University of Freiburg, Germany · Systems Control and Optimization Laboratory, Department of Microsystems Engineering, University of Freiburg, Germany