{"total":126,"rows":[{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2403.18765","title":"CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning","created":"2024-03-27","cited_by_count":23,"area":"deeprl"},{"id":"2510.14959","title":"CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions","created":"2025-10-16","cited_by_count":17,"area":"deeprl"},{"id":"2405.14058","title":"Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates","created":"2024-05-22","cited_by_count":16,"area":"deeprl"},{"id":"2407.09645","title":"Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey","created":"2024-07-12","cited_by_count":16,"area":"deeprl"},{"id":"2404.09080","title":"Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications","created":"2024-04-13","cited_by_count":15,"area":"deeprl"},{"id":"2405.13863","title":"Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning","created":"2024-05-22","cited_by_count":15,"area":"deeprl"},{"id":"2406.06507","title":"Verification-Guided Shielding for Deep Reinforcement Learning","created":"2024-06-10","cited_by_count":13,"area":"deeprl"},{"id":"2508.10316","title":"Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances","created":"2025-08-14","cited_by_count":12,"area":"deeprl"},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"id":"2404.16879","title":"Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey","created":"2024-04-22","cited_by_count":8,"area":"deeprl"},{"id":"2407.00286","title":"Digital Twin-Assisted Data-Driven Optimization for Reliable Edge Caching in Wireless Networks","created":"2024-06-29","cited_by_count":8,"area":"deeprl"},{"id":"2405.15994","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","created":"2024-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2405.18180","title":"Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding","created":"2024-05-28","cited_by_count":6,"area":"deeprl"},{"id":"2503.08241","title":"HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents","created":"2025-03-11","cited_by_count":6,"area":"deeprl"},{"id":"2402.00816","title":"Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments","created":"2024-02-01","cited_by_count":5,"area":"deeprl"},{"id":"2403.18725","title":"Probabilistic Model Checking of Stochastic Reinforcement Learning Policies","created":"2024-03-27","cited_by_count":5,"area":"deeprl"},{"id":"2405.14183","title":"Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time","created":"2024-05-23","cited_by_count":5,"area":"deeprl"},{"id":"2406.11774","title":"Optimal Transport-Assisted Risk-Sensitive Q-Learning","created":"2024-06-17","cited_by_count":4,"area":"deeprl"},{"id":"2410.22459","title":"Predicting Future Actions of Reinforcement Learning Agents","created":"2024-10-29","cited_by_count":4,"area":"deeprl"},{"id":"2503.09270","title":"Rule-Guided Reinforcement Learning Policy Evaluation and Improvement","created":"2025-03-12","cited_by_count":4,"area":"deeprl"},{"id":"2508.09128","title":"A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions","created":"2025-08-12","cited_by_count":4,"area":"deeprl"},{"id":"2405.17287","title":"Opinion-Guided Reinforcement Learning","created":"2024-05-27","cited_by_count":3,"area":"deeprl"},{"id":"2407.00681","title":"Safe Reinforcement Learning for Power System Control: A Review","created":"2024-06-30","cited_by_count":3,"area":"deeprl"},{"id":"2407.02231","title":"Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approach","created":"2024-07-02","cited_by_count":3,"area":"deeprl"},{"id":"2410.02038","title":"Realizable Continuous-Space Shields for Safe Reinforcement Learning","created":"2024-10-02","cited_by_count":3,"area":"deeprl"},{"id":"2410.06474","title":"Flipping-based Policy for Chance-Constrained Markov Decision Processes","created":"2024-10-09","cited_by_count":3,"area":"deeprl"},{"id":"2410.07359","title":"Learning-Based Shielding for Safe Autonomy under Unknown Dynamics","created":"2024-10-07","cited_by_count":3,"area":"deeprl"},{"id":"2501.16613","title":"Safe Reinforcement Learning for Real-World Engine Control","created":"2025-01-28","cited_by_count":3,"area":"deeprl"},{"id":"2510.18082","title":"Provably Optimal Reinforcement Learning under Safety Filtering","created":"2025-10-20","cited_by_count":3,"area":"deeprl"},{"id":"2602.14505","title":"Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC","created":"2026-02-16","cited_by_count":3,"area":"deeprl"},{"id":"2402.08502","title":"Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea","created":"2024-02-13","cited_by_count":2,"area":"deeprl"},{"id":"2402.13785","title":"Composing Reinforcement Learning Policies, with Formal Guarantees","created":"2024-02-21","cited_by_count":2,"area":"deeprl"},{"id":"2403.05693","title":"Shielded Deep Reinforcement Learning for Complex Spacecraft Tasking","created":"2024-03-08","cited_by_count":2,"area":"deeprl"},{"id":"2405.06770","title":"Demonstrating Reinforcement Learning and Run Time Assurance for Spacecraft Inspection Using Unmanned Aerial Vehicles","created":"2024-05-10","cited_by_count":2,"area":"deeprl"},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2408.00147","title":"Formal Ethical Obligations in Reinforcement Learning Agents: Verification and Policy Updates","created":"2024-07-31","cited_by_count":2,"area":"deeprl"},{"id":"2409.08382","title":"Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems","created":"2024-09-12","cited_by_count":2,"area":"deeprl"},{"id":"2411.07700","title":"Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning","created":"2024-11-12","cited_by_count":2,"area":"deeprl"},{"id":"2502.15922","title":"On the Design of Safe Continual RL Methods for Control of Nonlinear Systems","created":"2025-02-21","cited_by_count":2,"area":"deeprl"},{"id":"2504.04675","title":"HypRL: Reinforcement Learning of Control Policies for Hyperproperties","created":"2025-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2505.21852","title":"A Provable Approach for End-to-End Safe Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2506.11033","title":"Adaptive Shielding for Safe Reinforcement Learning under Hidden-Parameter Dynamics Shifts","created":"2025-05-20","cited_by_count":2,"area":"deeprl"},{"id":"2509.12085","title":"Compositional shield synthesis for safe reinforcement learning in partial observability","created":"2025-09-15","cited_by_count":2,"area":"deeprl"},{"id":"2510.05061","title":"Automaton Constrained Q-Learning","created":"2025-10-06","cited_by_count":2,"area":"deeprl"},{"id":"2601.22024","title":"SymbXRL: Symbolic Explainable Deep Reinforcement Learning for Mobile Networks","created":"2026-01-29","cited_by_count":2,"area":"deeprl"},{"id":"2604.02226","title":"When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning","created":"2026-04-02","cited_by_count":2,"area":"deeprl"},{"id":"2606.00270","title":"Robust Shielding for Safe Reinforcement Learning","created":"2026-05-29","cited_by_count":2,"area":"deeprl"},{"id":"2402.15893","title":"Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement Learning","created":"2024-02-24","cited_by_count":1,"area":"deeprl"},{"id":"2404.18821","title":"Control Policy Correction Framework for Reinforcement Learning-based Energy Arbitrage Strategies","created":"2024-04-29","cited_by_count":1,"area":"deeprl"},{"id":"2405.01198","title":"Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies","created":"2024-05-02","cited_by_count":1,"area":"deeprl"},{"id":"2405.15430","title":"Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics","created":"2024-05-24","cited_by_count":1,"area":"deeprl"},{"id":"2405.19414","title":"Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning","created":"2024-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2405.20534","title":"Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning","created":"2024-05-30","cited_by_count":1,"area":"deeprl"},{"id":"2410.08022","title":"Probabilistic Satisfaction of Temporal Logic Constraints in Reinforcement Learning via Adaptive Policy-Switching","created":"2024-10-10","cited_by_count":1,"area":"deeprl"},{"id":"2411.17861","title":"Accelerating Proximal Policy Optimization Learning Using Task Prediction for Solving Environments with Delayed Rewards","created":"2024-11-26","cited_by_count":1,"area":"deeprl"},{"id":"2502.07764","title":"Polynomial-Time Approximability of Constrained Reinforcement Learning","created":"2025-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2504.06386","title":"SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL","created":"2025-04-08","cited_by_count":1,"area":"deeprl"},{"id":"2506.22423","title":"ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks","created":"2025-06-27","cited_by_count":1,"area":"deeprl"},{"id":"2511.21531","title":"Predictive Safety Shield for Dyna-Q Reinforcement Learning","created":"2025-11-26","cited_by_count":1,"area":"deeprl"},{"id":"2601.21094","title":"Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed","created":"2026-01-28","cited_by_count":1,"area":"deeprl"},{"id":"2602.10598","title":"Neuro-symbolic Action Masking for Deep Reinforcement Learning","created":"2026-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2602.12444","title":"Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2604.14032","title":"Hierarchical Reinforcement Learning with Runtime Safety Shielding for Power Grid Operation","created":"2026-04-15","cited_by_count":1,"area":"deeprl"},{"id":"2605.12561","title":"Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance","created":"2026-05-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.25267","title":"Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning","created":"2026-05-24","cited_by_count":1,"area":"deeprl"},{"id":"2606.04029","title":"Position: Deployed Reinforcement Learning should be Continual","created":"2026-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2606.09825","title":"An Agency-Transferring Model-Free Policy Enhancement Technique","created":"2026-06-08","cited_by_count":1,"area":"deeprl"},{"id":"2606.14536","title":"Provably Safe, Yet Scalable Reinforcement Learning","created":"2026-06-12","cited_by_count":1,"area":"deeprl"},{"id":"2607.01651","title":"One Demonstration Is Enough for Real-World Robotic Reinforcement Learning","created":"2026-07-02","cited_by_count":1,"area":"deeprl"},{"id":"2405.03005","title":"Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints","created":"2024-05-05","cited_by_count":0,"area":"deeprl"},{"id":"2405.06771","title":"Space Processor Computation Time Analysis for Reinforcement Learning and Run Time Assurance Control Policies","created":"2024-05-10","cited_by_count":0,"area":"deeprl"},{"id":"2405.12355","title":"Investigating the Impact of Choice on Deep Reinforcement Learning for Space Controls","created":"2024-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2407.04481","title":"Using Petri Nets as an Integrated Constraint Mechanism for Reinforcement Learning Tasks","created":"2024-07-05","cited_by_count":0,"area":"deeprl"},{"id":"2407.06931","title":"A Unified Approach to Multi-task Legged Navigation: Temporal Logic Meets Reinforcement Learning","created":"2024-07-09","cited_by_count":0,"area":"deeprl"},{"id":"2408.00997","title":"A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid Environments","created":"2024-08-02","cited_by_count":0,"area":"deeprl"},{"id":"2408.16776","title":"Online Behavior Modification for Expressive User Control of RL-Trained Robots","created":"2024-08-15","cited_by_count":0,"area":"deeprl"},{"id":"2409.08233","title":"Towards Online Safety Corrections for Robotic Manipulation Policies","created":"2024-09-12","cited_by_count":0,"area":"deeprl"},{"id":"2502.12756","title":"Navigating Demand Uncertainty in Container Shipping: Deep Reinforcement Learning for Enabling Adaptive and Feasible Master Stowage Planning","created":"2025-02-18","cited_by_count":0,"area":"deeprl"},{"id":"2503.10318","title":"Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning","created":"2025-03-13","cited_by_count":0,"area":"deeprl"},{"id":"2503.13414","title":"Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processes","created":"2025-03-17","cited_by_count":0,"area":"deeprl"},{"id":"2503.24183","title":"Scalable Ride-Sourcing Vehicle Rebalancing with Service Accessibility Guarantee: A Constrained Mean-Field Reinforcement Learning Approach","created":"2025-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2504.03983","title":"I Can Hear You Coming: RF Sensing for Uncooperative Satellite Evasion","created":"2025-04-04","cited_by_count":0,"area":"deeprl"},{"id":"2504.12557","title":"TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels","created":"2025-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2505.12354","title":"A universal policy wrapper with guarantees","created":"2025-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2506.03469","title":"Verification-Guided Falsification for Safe RL via Explainable Abstraction and Risk-Aware Exploration","created":"2025-06-04","cited_by_count":0,"area":"deeprl"},{"id":"2506.14125","title":"Situational-Constrained Sequential Resources Allocation via Reinforcement Learning","created":"2025-06-17","cited_by_count":0,"area":"deeprl"},{"id":"2510.04555","title":"Tail-Safe Hedging: Explainable Risk-Sensitive Reinforcement Learning with a White-Box CBF--QP Safety Layer in Arbitrage-Free Markets","created":"2025-10-06","cited_by_count":0,"area":"deeprl"},{"id":"2510.18478","title":"Safe But Not Sorry: Reducing Over-Conservatism in Safety Critics via Uncertainty-Aware Modulation","created":"2025-10-21","cited_by_count":0,"area":"deeprl"},{"id":"2510.18485","title":"Learning to Navigate Under Imperfect Perception: Conformalised Segmentation for Safe Reinforcement Learning","created":"2025-10-21","cited_by_count":0,"area":"deeprl"},{"id":"2510.22859","title":"Guardian: Decoupling Exploration from Safety in Reinforcement Learning","created":"2025-10-26","cited_by_count":0,"area":"deeprl"},{"id":"2511.02605","title":"Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning","created":"2025-11-04","cited_by_count":0,"area":"deeprl"},{"id":"2512.01046","title":"Shielded Controller Units for RL with Operational Constraints Applied to Remote Microgrids","created":"2025-11-30","cited_by_count":0,"area":"deeprl"},{"id":"2512.04246","title":"Toward Virtuous Reinforcement Learning: A Critique and Roadmap","created":"2025-12-03","cited_by_count":0,"area":"deeprl"},{"id":"2512.23770","title":"SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints","created":"2025-12-29","cited_by_count":0,"area":"deeprl"},{"id":"2601.08646","title":"Provably Safe Reinforcement Learning for Stochastic Reach-Avoid Problems with Entropy Regularization","created":"2026-01-13","cited_by_count":0,"area":"deeprl"},{"id":"2601.19499","title":"Reversible Simplex Supervision with Post-Action Debt Accounting for Goal-Reaching RL","created":"2026-01-27","cited_by_count":0,"area":"deeprl"},{"id":"2602.03968","title":"Safety-Critical Reinforcement Learning with Viability-Based Action Shielding for Hypersonic Longitudinal Flight","created":"2026-02-03","cited_by_count":0,"area":"deeprl"},{"id":"2602.08977","title":"Contraction Metric Based Safe Reinforcement Learning Force Control for a Hydraulic Actuator with Real-World Training","created":"2026-02-09","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}