{"total":145,"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":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114,"area":"driving"},{"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":"2110.05415","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","created":"2021-10-11","cited_by_count":59,"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":"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":"2403.02475","title":"Enhancing LLM Safety via Constrained Direct Preference Optimization","created":"2024-03-04","cited_by_count":49,"area":"alignment"},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47,"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":"2309.13528","title":"Iterative Reachability Estimation for Safe Reinforcement Learning","created":"2023-09-24","cited_by_count":37,"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":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35,"area":null},{"id":"2203.02638","title":"Safe Reinforcement Learning for Legged Locomotion","created":"2022-03-05","cited_by_count":35,"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":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"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":"2210.07573","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":"2105.14937","title":"Safe Pontryagin Differentiable Programming","created":"2021-05-31","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":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23,"area":"deeprl"},{"id":"2405.01677","title":"Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation","created":"2024-05-02","cited_by_count":21,"area":"deeprl"},{"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":"2210.04839","title":"Benchmarking Reinforcement Learning Techniques for Autonomous Navigation","created":"2022-10-10","cited_by_count":19,"area":null},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"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":"2112.07701","title":"Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning","created":"2021-12-14","cited_by_count":16,"area":null},{"id":"2407.09645","title":"Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey","created":"2024-07-12","cited_by_count":16,"area":"deeprl"},{"id":"2302.13137","title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","created":"2023-02-25","cited_by_count":15,"area":null},{"id":"2403.14508","title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function","created":"2024-03-21","cited_by_count":15,"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":"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":"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":"2110.07699","title":"Safe Autonomous Racing via Approximate Reachability on Ego-vision","created":"2021-10-14","cited_by_count":13,"area":null},{"id":"2305.09793","title":"Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions","created":"2023-05-16","cited_by_count":13,"area":null},{"id":"2103.09230","title":"Lyapunov Barrier Policy Optimization","created":"2021-03-16","cited_by_count":12,"area":null},{"id":"2206.05240","title":"ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning","created":"2022-06-10","cited_by_count":12,"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":"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":"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":"2312.00561","title":"A safe exploration approach to constrained Markov decision processes","created":"2023-12-01","cited_by_count":10,"area":null},{"id":"2312.15127","title":"Gradient Shaping for Multi-Constraint Safe Reinforcement Learning","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2411.02957","title":"Embedding Safety into RL: A New Take on Trust Region Methods","created":"2024-11-05","cited_by_count":10,"area":"deeprl"},{"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":"2302.10030","title":"Safe Deep Reinforcement Learning by Verifying Task-Level Properties","created":"2023-02-20","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":"2405.16390","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","created":"2024-05-26","cited_by_count":9,"area":"deeprl"},{"id":"2405.20860","title":"Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation","created":"2024-05-31","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":"2112.03575","title":"MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance","created":"2021-12-07","cited_by_count":8,"area":null},{"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":"2210.14492","title":"Provable Safe Reinforcement Learning with Binary Feedback","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2312.10385","title":"Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning","created":"2023-12-16","cited_by_count":7,"area":null},{"id":"2208.09106","title":"A Risk-Sensitive Approach to Policy Optimization","created":"2022-08-19","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":"2102.10806","title":"Provably Correct Training of Neural Network Controllers Using Reachability Analysis","created":"2021-02-22","cited_by_count":5,"area":null},{"id":"2105.12545","title":"Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning","created":"2021-05-26","cited_by_count":5,"area":null},{"id":"2108.03952","title":"Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces","created":"2021-08-09","cited_by_count":5,"area":null},{"id":"2308.00707","title":"Approximate Model-Based Shielding for Safe Reinforcement Learning","created":"2023-07-27","cited_by_count":5,"area":null},{"id":"2407.15537","title":"Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints","created":"2024-07-22","cited_by_count":5,"area":"deeprl"},{"id":"2412.04327","title":"Action Mapping for Reinforcement Learning in Continuous Environments with Constraints","created":"2024-12-05","cited_by_count":5,"area":"deeprl"},{"id":"2507.14850","title":"Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems","created":"2025-07-20","cited_by_count":5,"area":null},{"id":"2110.14468","title":"DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention","created":"2021-10-27","cited_by_count":4,"area":null},{"id":"2112.11217","title":"Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles","created":"2021-12-18","cited_by_count":4,"area":null},{"id":"2201.07286","title":"Conservative Distributional Reinforcement Learning with Safety Constraints","created":"2022-01-18","cited_by_count":4,"area":null},{"id":"2210.11245","title":"Neural ODEs as Feedback Policies for Nonlinear Optimal Control","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2301.11592","title":"Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties","created":"2023-01-27","cited_by_count":4,"area":null},{"id":"2402.04182","title":"Reinforcement Learning with Ensemble Model Predictive Safety Certification","created":"2024-02-06","cited_by_count":4,"area":"deeprl"},{"id":"2405.05890","title":"Safe Exploration Using Bayesian World Models and Log-Barrier Optimization","created":"2024-05-09","cited_by_count":4,"area":"wm"},{"id":"2406.11774","title":"Optimal Transport-Assisted Risk-Sensitive Q-Learning","created":"2024-06-17","cited_by_count":4,"area":"deeprl"},{"id":"2408.14063","title":"Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning","created":"2024-08-26","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":"2107.13944","title":"Lyapunov-based uncertainty-aware safe reinforcement learning","created":"2021-07-29","cited_by_count":3,"area":null},{"id":"2204.11411","title":"Road Traffic Law Adaptive Decision-making for Self-Driving Vehicles","created":"2022-04-25","cited_by_count":3,"area":"driving"},{"id":"2209.15452","title":"Safe Exploration Method for Reinforcement Learning under Existence of Disturbance","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2212.06998","title":"Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning","created":"2022-12-14","cited_by_count":3,"area":null},{"id":"2301.11374","title":"Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation","created":"2023-01-26","cited_by_count":3,"area":null},{"id":"2308.11267","title":"Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes","created":"2023-08-22","cited_by_count":3,"area":null},{"id":"2405.02754","title":"Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning","created":"2024-05-04","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":"2409.12045","title":"Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning","created":"2024-09-18","cited_by_count":3,"area":"deeprl"},{"id":"2503.05724","title":"Addressing Moral Uncertainty using Large Language Models for Ethical Decision-Making","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2506.00700","title":"Central Path Proximal Policy Optimization","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2103.12020","title":"Improving Actor-Critic Reinforcement Learning via Hamiltonian Monte Carlo Method","created":"2021-03-22","cited_by_count":2,"area":null},{"id":"2202.10464","title":"A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2203.01696","title":"Fail-Safe Adversarial Generative Imitation Learning","created":"2022-03-03","cited_by_count":2,"area":"offlinerl"},{"id":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2403.06397","title":"DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2406.09563","title":"e-COP : Episodic Constrained Optimization of Policies","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2506.23090","title":"Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems","created":"2025-06-29","cited_by_count":2,"area":"offlinerl"},{"id":"2508.01883","title":"Proactive Constrained Policy Optimization with Preemptive Penalty","created":"2025-08-03","cited_by_count":2,"area":"deeprl"},{"id":"2601.06540","title":"Self-Organizing Dual-Buffer Adaptive Clustering Experience Replay (SODACER) for Safe Reinforcement Learning in Optimal Control","created":"2026-01-10","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":"2111.05670","title":"DeCOM: Decomposed Policy for Constrained Cooperative Multi-Agent Reinforcement Learning","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2301.00521","title":"A Policy Optimization Method Towards Optimal-time Stability","created":"2023-01-02","cited_by_count":1,"area":null}],"next_cursor":"100"}