{"total":247,"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":"2107.09003","title":"Constraints Penalized Q-learning for Safe Offline Reinforcement Learning","created":"2021-07-19","cited_by_count":91,"area":"offlinerl"},{"id":"2401.17583","title":"Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion","created":"2024-01-31","cited_by_count":73,"area":null},{"id":"2503.03480","title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","created":"2025-03-05","cited_by_count":72,"area":"vla"},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71,"area":null},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69,"area":null},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2011.04709","title":"f-IRL: Inverse Reinforcement Learning via State Marginal Matching","created":"2020-11-09","cited_by_count":67,"area":"offlinerl"},{"id":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"area":"offlinerl"},{"id":"2209.15090","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","created":"2022-09-29","cited_by_count":60,"area":null},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2209.07089","title":"Constrained Update Projection Approach to Safe Policy Optimization","created":"2022-09-15","cited_by_count":58,"area":null},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57,"area":"wm"},{"id":"2302.03122","title":"State-wise Safe Reinforcement Learning: A Survey","created":"2023-02-06","cited_by_count":55,"area":null},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2105.02343","title":"CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints","created":"2021-05-05","cited_by_count":49,"area":null},{"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":"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":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2203.02638","title":"Safe Reinforcement Learning for Legged Locomotion","created":"2022-03-05","cited_by_count":35,"area":null},{"id":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2101.00531","title":"Context-Aware Safe Reinforcement Learning for Non-Stationary Environments","created":"2021-01-02","cited_by_count":33,"area":null},{"id":"2110.06831","title":"Safe Driving via Expert Guided Policy Optimization","created":"2021-10-13","cited_by_count":31,"area":"driving"},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2105.10682","title":"Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety","created":"2021-05-22","cited_by_count":30,"area":null},{"id":"2201.12427","title":"Towards Safe Reinforcement Learning with a Safety Editor Policy","created":"2022-01-28","cited_by_count":30,"area":null},{"id":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2210.07573","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","created":"2022-10-14","cited_by_count":29,"area":null},{"id":"2211.11056","title":"Safe Control Under Input Limits with Neural Control Barrier Functions","created":"2022-11-20","cited_by_count":29,"area":null},{"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":"2112.09495","title":"Stability Verification in Stochastic Control Systems via Neural Network Supermartingales","created":"2021-12-17","cited_by_count":26,"area":null},{"id":"2204.07417","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","created":"2022-04-15","cited_by_count":26,"area":null},{"id":"2101.09207","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","created":"2021-01-22","cited_by_count":25,"area":null},{"id":"2106.12764","title":"Density Constrained Reinforcement Learning","created":"2021-06-24","cited_by_count":25,"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":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23,"area":"deeprl"},{"id":"2203.12759","title":"Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots","created":"2022-03-23","cited_by_count":22,"area":null},{"id":"2212.05727","title":"Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks","created":"2022-12-12","cited_by_count":22,"area":null},{"id":"2112.13941","title":"Safe Reinforcement Learning with Chance-constrained Model Predictive Control","created":"2021-12-27","cited_by_count":20,"area":null},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2110.10351","title":"Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2102.11055","title":"Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization","created":"2021-02-22","cited_by_count":18,"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":"2104.06922","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization","created":"2021-04-14","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":"2301.10339","title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning","created":"2023-01-24","cited_by_count":17,"area":null},{"id":"2410.11671","title":"Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents","created":"2024-10-15","cited_by_count":17,"area":"deeprl"},{"id":"2112.07701","title":"Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning","created":"2021-12-14","cited_by_count":16,"area":null},{"id":"2302.01680","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2402.05149","title":"FlowPG: Action-constrained Policy Gradient with Normalizing Flows","created":"2024-02-07","cited_by_count":16,"area":"deeprl"},{"id":"2107.04200","title":"Safe Exploration by Solving Early Terminated MDP","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2209.06866","title":"Robust Constrained Reinforcement Learning","created":"2022-09-14","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":"2210.12546","title":"Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems","created":"2022-10-22","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":"2502.01208","title":"On Almost Surely Safe Alignment of Large Language Models at Inference-Time","created":"2025-02-03","cited_by_count":14,"area":"alignment"},{"id":"2305.13681","title":"GUARD: A Safe Reinforcement Learning Benchmark","created":"2023-05-23","cited_by_count":13,"area":null},{"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":"2505.24445","title":"Learning Safety Constraints for Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"safety"},{"id":"2103.09230","title":"Lyapunov Barrier Policy Optimization","created":"2021-03-16","cited_by_count":12,"area":null},{"id":"2301.12593","title":"Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning","created":"2023-01-30","cited_by_count":12,"area":null},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2207.10415","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","created":"2022-07-21","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":"2304.08743","title":"Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints","created":"2023-04-18","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":"2601.07821","title":"Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation","created":"2026-01-12","cited_by_count":11,"area":"offlinerl"},{"id":"2102.07716","title":"How RL Agents Behave When Their Actions Are Modified","created":"2021-02-15","cited_by_count":10,"area":null},{"id":"2102.13446","title":"Safe Distributional Reinforcement Learning","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2405.04714","title":"RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes","created":"2024-05-07","cited_by_count":10,"area":"driving"},{"id":"2211.15034","title":"Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2301.13375","title":"Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees","created":"2023-01-31","cited_by_count":9,"area":null},{"id":"2306.12594","title":"State-wise Constrained Policy Optimization","created":"2023-06-21","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":"2412.18855","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","created":"2024-12-25","cited_by_count":9,"area":"offlinerl"},{"id":"2503.12932","title":"Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs","created":"2025-03-17","cited_by_count":9,"area":"deeprl"},{"id":"2103.05922","title":"RMP2: A Structured Composable Policy Class for Robot Learning","created":"2021-03-10","cited_by_count":8,"area":null},{"id":"2202.09644","title":"Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic","created":"2022-02-19","cited_by_count":8,"area":null},{"id":"2204.05176","title":"Towards Painless Policy Optimization for Constrained MDPs","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8,"area":"deeprl"},{"id":"2508.01561","title":"One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning","created":"2025-08-03","cited_by_count":8,"area":"deeprl"},{"id":"2109.14325","title":"Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning","created":"2021-09-29","cited_by_count":7,"area":null},{"id":"2111.08397","title":"CLARA: A Constrained Reinforcement Learning Based Resource Allocation Framework for Network Slicing","created":"2021-11-16","cited_by_count":7,"area":null},{"id":"2206.08528","title":"SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving","created":"2022-06-17","cited_by_count":7,"area":"driving"},{"id":"2312.12145","title":"OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2202.04849","title":"SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition","created":"2022-02-10","cited_by_count":6,"area":null},{"id":"2206.02675","title":"Effects of Safety State Augmentation on Safe Exploration","created":"2022-06-06","cited_by_count":6,"area":null},{"id":"2306.04026","title":"Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theory","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2310.09574","title":"Reduced Policy Optimization for Continuous Control with Hard Constraints","created":"2023-10-14","cited_by_count":6,"area":null},{"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":"2505.19238","title":"Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees","created":"2025-05-25","cited_by_count":6,"area":"deeprl"}],"next_cursor":"100"}