{"total":297,"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":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84,"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":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69,"area":null},{"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":"2110.05415","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","created":"2021-10-11","cited_by_count":59,"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":"2302.03122","title":"State-wise Safe Reinforcement Learning: A Survey","created":"2023-02-06","cited_by_count":55,"area":null},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"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":"2202.02526","title":"LyaNet: A Lyapunov Framework for Training Neural ODEs","created":"2022-02-05","cited_by_count":44,"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":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35,"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":"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":"2107.12931","title":"Autonomous Reinforcement Learning via Subgoal Curricula","created":"2021-07-27","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":"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":"2501.17974","title":"Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization","created":"2025-01-29","cited_by_count":29,"area":"lr"},{"id":"2202.06626","title":"MuZero with Self-competition for Rate Control in VP9 Video Compression","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2309.14236","title":"MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation","created":"2023-09-25","cited_by_count":28,"area":"wm"},{"id":"2105.13281","title":"GoSafe: Globally Optimal Safe Robot Learning","created":"2021-05-27","cited_by_count":27,"area":null},{"id":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2105.14937","title":"Safe Pontryagin Differentiable Programming","created":"2021-05-31","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":"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":"2106.00099","title":"Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs","created":"2021-05-31","cited_by_count":22,"area":"offlinerl"},{"id":"2212.01861","title":"Online Shielding for Reinforcement Learning","created":"2022-12-04","cited_by_count":22,"area":null},{"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":"2504.03515","title":"Dexterous Manipulation through Imitation Learning: A Survey","created":"2025-04-04","cited_by_count":21,"area":"offlinerl"},{"id":"2202.07565","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","created":"2022-02-15","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":"2311.01753","title":"RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization","created":"2023-11-03","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":"2303.10506","title":"Neural Operators of Backstepping Controller and Observer Gain Functions for Reaction-Diffusion PDEs","created":"2023-03-18","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":"2106.01577","title":"A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes","created":"2021-06-03","cited_by_count":17,"area":null},{"id":"2110.11383","title":"Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes","created":"2021-10-21","cited_by_count":17,"area":null},{"id":"2201.09562","title":"GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems","created":"2022-01-24","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":"2212.13769","title":"Lexicographic Multi-Objective Reinforcement Learning","created":"2022-12-28","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":"2103.14722","title":"Almost Surely Stable Deep Dynamics","created":"2021-03-26","cited_by_count":16,"area":null},{"id":"2109.03861","title":"Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems","created":"2021-09-08","cited_by_count":16,"area":null},{"id":"2306.00629","title":"Identifiability and Generalizability in Constrained Inverse Reinforcement Learning","created":"2023-06-01","cited_by_count":16,"area":"offlinerl"},{"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":"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":"2302.00171","title":"Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approach","created":"2023-02-01","cited_by_count":15,"area":null},{"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":"2101.05916","title":"Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability","created":"2021-01-15","cited_by_count":14,"area":null},{"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":"2110.07699","title":"Safe Autonomous Racing via Approximate Reachability on Ego-vision","created":"2021-10-14","cited_by_count":13,"area":null},{"id":"2111.03165","title":"Infinite Time Horizon Safety of Bayesian Neural Networks","created":"2021-11-04","cited_by_count":13,"area":null},{"id":"2304.04066","title":"Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach","created":"2023-04-08","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":"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":"2103.09230","title":"Lyapunov Barrier Policy Optimization","created":"2021-03-16","cited_by_count":12,"area":null},{"id":"2110.00843","title":"SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interaction","created":"2021-10-02","cited_by_count":12,"area":null},{"id":"2402.05279","title":"Safety Filters for Black-Box Dynamical Systems by Learning Discriminating Hyperplanes","created":"2024-02-07","cited_by_count":12,"area":"deeprl"},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2210.06380","title":"Near-Optimal Multi-Agent Learning for Safe Coverage Control","created":"2022-10-12","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":"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":"2312.00342","title":"Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk","created":"2023-12-01","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":"2312.00561","title":"A safe exploration approach to constrained Markov decision processes","created":"2023-12-01","cited_by_count":10,"area":null},{"id":"2201.01347","title":"Learning Differentiable Safety-Critical Control using Control Barrier Functions for Generalization to Novel Environments","created":"2022-01-04","cited_by_count":9,"area":null},{"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":"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":"2112.03575","title":"MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance","created":"2021-12-07","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":"2308.14424","title":"Shielded Reinforcement Learning for Hybrid Systems","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2312.10230","title":"Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex Programming","created":"2023-12-15","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":"2509.18648","title":"SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer","created":"2025-09-23","cited_by_count":8,"area":"deeprl"},{"id":"2210.14492","title":"Provable Safe Reinforcement Learning with Binary Feedback","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2301.08940","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2311.03600","title":"Scalable and Efficient Continual Learning from Demonstration via a Hypernetwork-generated Stable Dynamics Model","created":"2023-11-06","cited_by_count":7,"area":"offlinerl"},{"id":"2405.15994","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","created":"2024-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2111.07395","title":"Explicit Explore, Exploit, or Escape ($E^4$): near-optimal safety-constrained reinforcement learning in polynomial time","created":"2021-11-14","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":"2202.04849","title":"SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition","created":"2022-02-10","cited_by_count":6,"area":null},{"id":"2203.01190","title":"Model-free Neural Lyapunov Control for Safe Robot Navigation","created":"2022-03-02","cited_by_count":6,"area":null},{"id":"2206.01341","title":"Equipping Black-Box Policies with Model-Based Advice for Stable Nonlinear Control","created":"2022-06-02","cited_by_count":6,"area":null}],"next_cursor":"100"}