{"total":449,"rows":[{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71,"area":null},{"id":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61,"area":null},{"id":"2204.00755","title":"Safe Reinforcement Learning via Shielding under Partial Observability","created":"2022-04-02","cited_by_count":56,"area":null},{"id":"2202.10341","title":"Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization","created":"2022-02-17","cited_by_count":49,"area":"driving"},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47,"area":null},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"id":"2104.04413","title":"Provable Repair of Deep Neural Networks","created":"2021-04-09","cited_by_count":42,"area":null},{"id":"2303.03226","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","created":"2023-03-06","cited_by_count":42,"area":null},{"id":"2108.01846","title":"Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations","created":"2021-08-04","cited_by_count":39,"area":null},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"area":null},{"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":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2205.13536","title":"Verifying Learning-Based Robotic Navigation Systems","created":"2022-05-26","cited_by_count":33,"area":null},{"id":"2212.03228","title":"ISAACS: Iterative Soft Adversarial Actor-Critic for Safety","created":"2022-12-06","cited_by_count":28,"area":null},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2508.00500","title":"ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction","created":"2025-08-01","cited_by_count":28,"area":"agents"},{"id":"2201.08355","title":"Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees","created":"2022-01-20","cited_by_count":27,"area":null},{"id":"2210.10691","title":"Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes","created":"2022-10-19","cited_by_count":26,"area":null},{"id":"2210.05308","title":"Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees","created":"2022-10-11","cited_by_count":23,"area":null},{"id":"2403.18765","title":"CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning","created":"2024-03-27","cited_by_count":23,"area":"deeprl"},{"id":"2212.01861","title":"Online Shielding for Reinforcement Learning","created":"2022-12-04","cited_by_count":22,"area":null},{"id":"2210.10765","title":"When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning","created":"2022-10-19","cited_by_count":21,"area":null},{"id":"2208.10605","title":"SoK: Explainable Machine Learning for Computer Security Applications","created":"2022-08-22","cited_by_count":20,"area":null},{"id":"2108.04214","title":"Neural Network Repair with Reachability Analysis","created":"2021-08-09","cited_by_count":19,"area":null},{"id":"2209.07133","title":"COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checking","created":"2022-09-15","cited_by_count":19,"area":null},{"id":"2205.06311","title":"Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments","created":"2022-05-12","cited_by_count":18,"area":null},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"area":null},{"id":"2001.09227","title":"Active Task-Inference-Guided Deep Inverse Reinforcement Learning","created":"2020-01-24","cited_by_count":17,"area":"offlinerl"},{"id":"2110.09461","title":"In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications","created":"2021-10-18","cited_by_count":17,"area":null},{"id":"2209.13308","title":"Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction","created":"2022-09-27","cited_by_count":17,"area":null},{"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":"2211.10871","title":"SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control","created":"2022-11-20","cited_by_count":15,"area":null},{"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":"2101.08153","title":"Shielding Atari Games with Bounded Prescience","created":"2021-01-20","cited_by_count":14,"area":null},{"id":"2312.01456","title":"Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees","created":"2023-12-03","cited_by_count":14,"area":null},{"id":"2510.04284","title":"Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning","created":"2025-10-05","cited_by_count":14,"area":"agents"},{"id":"2205.04887","title":"Search-Based Testing of Reinforcement Learning","created":"2022-05-07","cited_by_count":13,"area":null},{"id":"2406.06507","title":"Verification-Guided Shielding for Deep Reinforcement Learning","created":"2024-06-10","cited_by_count":13,"area":"deeprl"},{"id":"2505.17342","title":"A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"2512.01295","title":"Systems Security Foundations for Agentic Computing","created":"2025-12-01","cited_by_count":13,"area":"agents"},{"id":"2208.14426","title":"Correct-by-Construction Runtime Enforcement in AI -- A Survey","created":"2022-08-30","cited_by_count":12,"area":null},{"id":"2301.05294","title":"Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersections","created":"2023-01-12","cited_by_count":12,"area":null},{"id":"2406.08878","title":"CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving","created":"2024-06-13","cited_by_count":12,"area":"driving"},{"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":"2509.24243","title":"SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functions","created":"2025-09-29","cited_by_count":12,"area":"diffusion"},{"id":"2001.09293","title":"Learning Non-Markovian Reward Models in MDPs","created":"2020-01-25","cited_by_count":11,"area":"alignment"},{"id":"2207.13446","title":"Dynamic Shielding for Reinforcement Learning in Black-Box Environments","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2210.01801","title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation","created":"2022-10-02","cited_by_count":11,"area":null},{"id":"2210.10865","title":"Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2211.17250","title":"Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions","created":"2022-11-30","cited_by_count":11,"area":null},{"id":"2302.06064","title":"Provably Safe Reinforcement Learning with Step-wise Violation Constraints","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2304.06281","title":"Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning","created":"2023-04-13","cited_by_count":11,"area":null},{"id":"2403.02619","title":"Training Machine Learning models at the Edge: A Survey","created":"2024-03-05","cited_by_count":11,"area":null},{"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":"2102.13446","title":"Safe Distributional Reinforcement Learning","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2107.07316","title":"Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning","created":"2021-07-15","cited_by_count":10,"area":"driving"},{"id":"2111.04894","title":"Safe Policy Optimization with Local Generalized Linear Function Approximations","created":"2021-11-09","cited_by_count":10,"area":null},{"id":"2201.13248","title":"SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation","created":"2022-01-27","cited_by_count":10,"area":null},{"id":"2308.02594","title":"SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents","created":"2023-08-03","cited_by_count":10,"area":null},{"id":"2401.03188","title":"A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence","created":"2024-01-06","cited_by_count":10,"area":null},{"id":"2412.07331","title":"NeSyA: Neurosymbolic Automata","created":"2024-12-10","cited_by_count":10,"area":"lr"},{"id":"2009.12600","title":"Online Learning of Non-Markovian Reward Models","created":"2020-09-26","cited_by_count":9,"area":"alignment"},{"id":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2112.08438","title":"Programmatic Reward Design by Example","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2112.09655","title":"Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report)","created":"2021-12-17","cited_by_count":9,"area":null},{"id":"2112.11490","title":"Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding","created":"2021-12-21","cited_by_count":9,"area":null},{"id":"2204.09772","title":"A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines","created":"2022-04-20","cited_by_count":9,"area":"offlinerl"},{"id":"2212.01838","title":"Automata Learning meets Shielding","created":"2022-12-04","cited_by_count":9,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2310.08602","title":"Safe Deep Policy Adaptation","created":"2023-10-08","cited_by_count":9,"area":null},{"id":"2112.03575","title":"MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance","created":"2021-12-07","cited_by_count":8,"area":null},{"id":"2205.06212","title":"Contingency-constrained economic dispatch with safe reinforcement learning","created":"2022-05-12","cited_by_count":8,"area":null},{"id":"2308.14424","title":"Shielded Reinforcement Learning for Hybrid Systems","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2309.06239","title":"Risk-Aware Reinforcement Learning through Optimal Transport Theory","created":"2023-09-12","cited_by_count":8,"area":null},{"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":"2410.10460","title":"Compositional Shielding and Reinforcement Learning for Multi-Agent Systems","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2210.14492","title":"Provable Safe Reinforcement Learning with Binary Feedback","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2307.01316","title":"Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approach","created":"2023-07-03","cited_by_count":7,"area":"driving"},{"id":"2307.14316","title":"Reinforcement Learning by Guided Safe Exploration","created":"2023-07-26","cited_by_count":7,"area":null},{"id":"2312.01818","title":"Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto","created":"2023-12-04","cited_by_count":7,"area":"agents"},{"id":"2402.10998","title":"Provably Safe Neural Network Controllers via Differential Dynamic Logic","created":"2024-02-16","cited_by_count":7,"area":null},{"id":"2405.15994","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","created":"2024-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2511.11828","title":"Conformal Constrained Policy Optimization for Cost-Effective LLM Agents","created":"2025-11-14","cited_by_count":7,"area":"agents"},{"id":"2201.03698","title":"Verified Probabilistic Policies for Deep Reinforcement Learning","created":"2022-01-10","cited_by_count":6,"area":null},{"id":"2202.02404","title":"Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"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":"2506.15847","title":"SafeMimic: Towards Safe and Autonomous Human-to-Robot Imitation for Mobile Manipulation","created":"2025-06-18","cited_by_count":6,"area":null},{"id":"2103.14600","title":"Model-Free Learning of Safe yet Effective Controllers","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2104.10219","title":"Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning","created":"2021-04-20","cited_by_count":5,"area":null}],"next_cursor":"100"}