{"total":316,"rows":[{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290,"area":"wm"},{"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":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"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":"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":"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":"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":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57,"area":"wm"},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54,"area":"wm"},{"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":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"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":"2401.03160","title":"HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving","created":"2024-01-06","cited_by_count":32,"area":"driving"},{"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":"2210.07573","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":"2306.00603","title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","created":"2023-06-01","cited_by_count":28,"area":"offlinerl"},{"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":"2402.15776","title":"Truly No-Regret Learning in Constrained MDPs","created":"2024-02-24","cited_by_count":23,"area":"deeprl"},{"id":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23,"area":"deeprl"},{"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":"2404.09080","title":"Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications","created":"2024-04-13","cited_by_count":15,"area":"deeprl"},{"id":"2401.14758","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","created":"2024-01-26","cited_by_count":14,"area":"deeprl"},{"id":"2410.22600","title":"Solving Minimum-Cost Reach Avoid using Reinforcement Learning","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2102.08539","title":"Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning","created":"2021-02-17","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":"2409.15755","title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","created":"2024-09-24","cited_by_count":13,"area":"deeprl"},{"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":"2502.15119","title":"CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models","created":"2025-02-21","cited_by_count":12,"area":"mllm"},{"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":"2401.03629","title":"DDM-Lag : A Diffusion-based Decision-making Model for Autonomous Vehicles with Lagrangian Safety Enhancement","created":"2024-01-08","cited_by_count":11,"area":"diffusion"},{"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":"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":"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":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","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":"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":"2404.14238","title":"Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories","created":"2024-04-22","cited_by_count":9,"area":"deeprl"},{"id":"2412.15429","title":"Offline Safe Reinforcement Learning Using Trajectory Classification","created":"2024-12-19","cited_by_count":9,"area":"offlinerl"},{"id":"2503.23101","title":"RL2Grid: Benchmarking Reinforcement Learning in Power Grid Operations","created":"2025-03-29","cited_by_count":9,"area":"deeprl"},{"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":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8,"area":"deeprl"},{"id":"2409.00858","title":"Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving","created":"2024-09-01","cited_by_count":8,"area":"driving"},{"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":"2405.15994","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","created":"2024-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"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":"2410.14468","title":"Knowledge Transfer from Simple to Complex: A Safe and Efficient Reinforcement Learning Framework for Autonomous Driving Decision-Making","created":"2024-10-18","cited_by_count":6,"area":"driving"},{"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"}],"next_cursor":"100"}