{"total":142,"rows":[{"id":"2310.12567","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark","created":"2023-10-19","cited_by_count":143,"area":null},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80,"area":null},{"id":"2305.09304","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","created":"2023-05-16","cited_by_count":80,"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":"2205.11814","title":"Penalized Proximal Policy Optimization for Safe Reinforcement Learning","created":"2022-05-24","cited_by_count":68,"area":null},{"id":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67,"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":"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":"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":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","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":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","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":"2205.13536","title":"Verifying Learning-Based Robotic Navigation Systems","created":"2022-05-26","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":"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":"2210.07573","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":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","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":"2111.07695","title":"Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning","created":"2021-11-15","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":"2106.12764","title":"Density Constrained Reinforcement Learning","created":"2021-06-24","cited_by_count":25,"area":null},{"id":"2111.00552","title":"Policy Optimization for Constrained MDPs with Provable Fast Global Convergence","created":"2021-10-31","cited_by_count":23,"area":null},{"id":"2301.10923","title":"Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints","created":"2023-01-26","cited_by_count":21,"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":"2106.03442","title":"Average-Reward Reinforcement Learning with Trust Region Methods","created":"2021-06-07","cited_by_count":19,"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":"2502.03369","title":"Learning from Active Human Involvement through Proxy Value Propagation","created":"2025-02-05","cited_by_count":19,"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":"2107.04200","title":"Safe Exploration by Solving Early Terminated MDP","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2108.11623","title":"Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian","created":"2021-08-26","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":"2309.00711","title":"Learning Shared Safety Constraints from Multi-task Demonstrations","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2102.08539","title":"Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning","created":"2021-02-17","cited_by_count":13,"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":"2406.04558","title":"On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2201.12243","title":"Joint Differentiable Optimization and Verification for Certified Reinforcement Learning","created":"2022-01-28","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":"2302.06064","title":"Provably Safe Reinforcement Learning with Step-wise Violation Constraints","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2504.01212","title":"Cooper: A Library for Constrained Optimization in Deep Learning","created":"2025-04-01","cited_by_count":11,"area":null},{"id":"2607.02375","title":"Representation Distribution Matching for One-Step Visual Generation","created":"2026-07-02","cited_by_count":11,"area":null},{"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":"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":"2301.04330","title":"Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks","created":"2023-01-11","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":"2302.10030","title":"Safe Deep Reinforcement Learning by Verifying Task-Level Properties","created":"2023-02-20","cited_by_count":9,"area":null},{"id":"2311.02227","title":"State-Wise Safe Reinforcement Learning With Pixel Observations","created":"2023-11-03","cited_by_count":9,"area":null},{"id":"2204.05176","title":"Towards Painless Policy Optimization for Constrained MDPs","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2310.02440","title":"Learning Diverse Skills for Local Navigation under Multi-constraint Optimality","created":"2023-10-03","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":"2210.14492","title":"Provable Safe Reinforcement Learning with Binary Feedback","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2302.06695","title":"Online Safety Property Collection and Refinement for Safe Deep Reinforcement Learning in Mapless Navigation","created":"2023-02-13","cited_by_count":7,"area":null},{"id":"2306.07001","title":"Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2310.20673","title":"Balancing Act: Constraining Disparate Impact in Sparse Models","created":"2023-10-31","cited_by_count":7,"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":"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":"2302.11694","title":"Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Control","created":"2023-02-22","cited_by_count":5,"area":null},{"id":"2306.00035","title":"ROSARL: Reward-Only Safe Reinforcement Learning","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2312.00344","title":"TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2406.08315","title":"Improving Policy Optimization via $\\varepsilon$-Retrain","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2501.14912","title":"Feasible Learning","created":"2025-01-24","cited_by_count":5,"area":null},{"id":"2505.20578","title":"Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2505.20628","title":"Position: Adopt Constraints Over Fixed Penalties in Deep Learning","created":"2025-05-27","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":"2111.12953","title":"Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning","created":"2021-11-25","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":"2304.08845","title":"Feasible Policy Iteration for Safe Reinforcement Learning","created":"2023-04-18","cited_by_count":4,"area":null},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2310.07207","title":"Robust Safe Reinforcement Learning under Adversarial Disturbances","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2601.19402","title":"PROTEUS: SLA-Aware Routing via Lagrangian RL for Multi-LLM Serving Systems","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2602.14468","title":"LACONIC: Length-Aware Constrained Reinforcement Learning for LLM","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2107.13944","title":"Lyapunov-based uncertainty-aware safe reinforcement learning","created":"2021-07-29","cited_by_count":3,"area":null},{"id":"2304.10510","title":"Censoring chemical data to mitigate dual use risk","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2309.02669","title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2309.10657","title":"Learning Adaptive Safety for Multi-Agent Systems","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2412.04426","title":"Towards Fast Safe Online Reinforcement Learning via Policy Finetuning","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2501.15618","title":"Your Learned Constraint is Secretly a Backward Reachable Tube","created":"2025-01-26","cited_by_count":3,"area":null},{"id":"2604.03489","title":"Improving Feasibility via Fast Autoencoder-Based Projections","created":"2026-04-03","cited_by_count":3,"area":null},{"id":"2605.00649","title":"Model Compression with Exact Budget Constraints via Riemannian Manifolds","created":"2026-05-01","cited_by_count":3,"area":null},{"id":"2203.12048","title":"Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2207.02464","title":"A Learning System for Motion Planning of Free-Float Dual-Arm Space Manipulator towards Non-Cooperative Object","created":"2022-07-06","cited_by_count":2,"area":null},{"id":"2303.01346","title":"Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2303.04118","title":"A Multiplicative Value Function for Safe and Efficient Reinforcement Learning","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2304.09869","title":"Evolving Constrained Reinforcement Learning Policy","created":"2023-04-19","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":"2501.04426","title":"Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2503.05035","title":"QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2504.20932","title":"Improvements of Dark Experience Replay and Reservoir Sampling towards Better Balance between Consolidation and Plasticity","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2605.11688","title":"Shaping Zero-Shot Coordination via State Blocking","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2606.18308","title":"TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2209.12029","title":"Open-Ended Diverse Solution Discovery with Regulated Behavior Patterns for Cross-Domain Adaptation","created":"2022-09-24","cited_by_count":1,"area":null}],"next_cursor":"100"}