{"total":57,"rows":[{"id":"2310.12567","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark","created":"2023-10-19","cited_by_count":143,"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":"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":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54,"area":"wm"},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"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":"2306.12371","title":"Optimistic Active Exploration of Dynamical Systems","created":"2023-06-21","cited_by_count":32,"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":"2306.00603","title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","created":"2023-06-01","cited_by_count":28,"area":"offlinerl"},{"id":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23,"area":"deeprl"},{"id":"2210.07553","title":"Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate","created":"2022-10-14","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":"2403.14508","title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function","created":"2024-03-21","cited_by_count":15,"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":"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":"2210.01801","title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation","created":"2022-10-02","cited_by_count":11,"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":"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":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","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":"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":"2206.02675","title":"Effects of Safety State Augmentation on Safe Exploration","created":"2022-06-06","cited_by_count":6,"area":null},{"id":"2311.07558","title":"Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2601.19612","title":"Safe Exploration via Policy Priors","created":"2026-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2308.00707","title":"Approximate Model-Based Shielding for Safe Reinforcement Learning","created":"2023-07-27","cited_by_count":5,"area":null},{"id":"2402.00816","title":"Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments","created":"2024-02-01","cited_by_count":5,"area":"deeprl"},{"id":"2511.14262","title":"Object-Centric World Models for Causality-Aware Reinforcement Learning","created":"2025-11-18","cited_by_count":4,"area":"wm"},{"id":"2405.11718","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","created":"2024-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2407.04942","title":"FOSP: Fine-tuning Offline Safe Policy through World Models","created":"2024-07-06","cited_by_count":3,"area":"wm"},{"id":"2410.06474","title":"Flipping-based Policy for Chance-Constrained Markov Decision Processes","created":"2024-10-09","cited_by_count":3,"area":"deeprl"},{"id":"2412.11138","title":"Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation","created":"2024-12-15","cited_by_count":3,"area":"deeprl"},{"id":"2304.11104","title":"Approximate Shielding of Atari Agents for Safe Exploration","created":"2023-04-21","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":"2507.00485","title":"PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning","created":"2025-07-01","cited_by_count":2,"area":"deeprl"},{"id":"2307.08024","title":"Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review","created":"2023-07-16","cited_by_count":1,"area":null},{"id":"2404.10064","title":"The Feasibility Theory of Constrained Reinforcement Learning: A Tutorial Study","created":"2024-04-15","cited_by_count":1,"area":"deeprl"},{"id":"2411.19809","title":"Q-learning-based Model-free Safety Filter","created":"2024-11-29","cited_by_count":1,"area":"deeprl"},{"id":"2505.07911","title":"Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review","created":"2025-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2509.16650","title":"Safe and Near-Optimal Control with Online Dynamics Learning","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2602.06445","title":"ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking","created":"2026-02-06","cited_by_count":1,"area":"deeprl"},{"id":"2602.12444","title":"Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2305.05354","title":"Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2310.06903","title":"Reinforcement Learning in a Safety-Embedded MDP with Trajectory Optimization","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2406.03912","title":"GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model","created":"2024-06-06","cited_by_count":0,"area":"deeprl"},{"id":"2503.07848","title":"Safe Explicable Policy Search","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2506.04828","title":"Safe Planning and Policy Optimization via World Model Learning","created":"2025-06-05","cited_by_count":0,"area":"wm"},{"id":"2510.10960","title":"Game-Theoretic Risk-Shaped Reinforcement Learning for Safe Autonomous Driving","created":"2025-10-13","cited_by_count":0,"area":"driving"},{"id":"2601.04686","title":"Nightmare Dreamer: Dreaming About Unsafe States And Planning Ahead","created":"2026-01-08","cited_by_count":0,"area":"deeprl"},{"id":"2602.04821","title":"Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement Learning","created":"2026-02-04","cited_by_count":0,"area":"wm"},{"id":"2602.20729","title":"Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty","created":"2026-02-24","cited_by_count":0,"area":"deeprl"},{"id":"2604.28144","title":"Global Optimality for Constrained Exploration via Penalty Regularization","created":"2026-04-30","cited_by_count":0,"area":"deeprl"},{"id":"2605.19469","title":"Sampling-Based Safe Reinforcement Learning","created":"2026-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2607.13172","title":"Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models","created":"2026-07-14","cited_by_count":0,"area":"wm"},{"id":"2608.30283","title":"BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Safe Reinforcement Learning","created":"2026-08-31","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}