{"total":72,"rows":[{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680,"area":null},{"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":"2107.12045","title":"How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review","created":"2021-07-26","cited_by_count":39,"area":null},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2201.08355","title":"Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees","created":"2022-01-20","cited_by_count":27,"area":null},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","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":"2403.07263","title":"Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction","created":"2024-03-12","cited_by_count":23,"area":null},{"id":"2203.11437","title":"Representation Uncertainty in Self-Supervised Learning as Variational Inference","created":"2022-03-22","cited_by_count":22,"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":"2104.03111","title":"Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation","created":"2021-04-07","cited_by_count":15,"area":null},{"id":"2104.04785","title":"Generating Physically-Consistent Satellite Imagery for Climate Visualizations","created":"2021-04-10","cited_by_count":13,"area":null},{"id":"2104.11706","title":"Safe Chance Constrained Reinforcement Learning for Batch Process Control","created":"2021-04-23","cited_by_count":11,"area":null},{"id":"2112.02694","title":"Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning","created":"2021-12-05","cited_by_count":9,"area":null},{"id":"2105.02331","title":"Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance","created":"2021-05-05","cited_by_count":8,"area":null},{"id":"2203.14749","title":"Adaptive Risk-Tendency: Nano Drone Navigation in Cluttered Environments with Distributional Reinforcement Learning","created":"2022-03-28","cited_by_count":6,"area":null},{"id":"2503.05238","title":"Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation","created":"2025-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2506.09270","title":"Uncertainty Prioritized Experience Replay","created":"2025-06-10","cited_by_count":6,"area":"deeprl"},{"id":"2109.10552","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2111.05819","title":"Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention","created":"2021-11-10","cited_by_count":5,"area":null},{"id":"2211.04009","title":"SOTIF Entropy: Online SOTIF Risk Quantification and Mitigation for Autonomous Driving","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2306.06754","title":"Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning","created":"2023-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2312.11348","title":"Monte Carlo Tree Search in the Presence of Transition Uncertainty","created":"2023-12-18","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":"2508.17448","title":"Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality","created":"2025-08-24","cited_by_count":4,"area":"deeprl"},{"id":"2104.10818","title":"XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees","created":"2021-04-22","cited_by_count":3,"area":null},{"id":"2107.13944","title":"Lyapunov-based uncertainty-aware safe reinforcement learning","created":"2021-07-29","cited_by_count":3,"area":null},{"id":"2205.04590","title":"A Verification Framework for Certifying Learning-Based Safety-Critical Aviation Systems","created":"2022-05-09","cited_by_count":3,"area":null},{"id":"2206.03211","title":"Variational Meta Reinforcement Learning for Social Robotics","created":"2022-06-07","cited_by_count":3,"area":null},{"id":"2210.03649","title":"How to Enable Uncertainty Estimation in Proximal Policy Optimization","created":"2022-10-07","cited_by_count":3,"area":null},{"id":"2211.04340","title":"Calibrating Perception Uncertainty for Autonomous Driving","created":"2022-11-08","cited_by_count":3,"area":"driving"},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2603.08128","title":"TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Same","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2108.10673","title":"Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding","created":"2021-08-24","cited_by_count":2,"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":"2308.12478","title":"Attention-Based Acoustic Feature Fusion Network for Depression Detection","created":"2023-08-24","cited_by_count":2,"area":null},{"id":"2311.03651","title":"SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2409.10655","title":"Disentangling Uncertainty for Safe Social Navigation using Deep Reinforcement Learning","created":"2024-09-16","cited_by_count":2,"area":"deeprl"},{"id":"2410.15178","title":"GUIDEd Agents: Enhancing Navigation Policies through Task-Specific Uncertainty Abstraction in Localization-Limited Environments","created":"2024-10-19","cited_by_count":2,"area":null},{"id":"2502.15922","title":"On the Design of Safe Continual RL Methods for Control of Nonlinear Systems","created":"2025-02-21","cited_by_count":2,"area":"deeprl"},{"id":"2503.23650","title":"A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective","created":"2025-03-31","cited_by_count":2,"area":"driving"},{"id":"2505.13837","title":"Enhancing Robot Navigation Policies with Task-Specific Uncertainty Managements","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2507.06519","title":"Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policies","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2210.08672","title":"Decision-Making Among Bounded Rational Agents","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2301.05297","title":"Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Components","created":"2023-01-12","cited_by_count":1,"area":null},{"id":"2308.06129","title":"Uncertainty Quantification for Image-based Traffic Prediction across Cities","created":"2023-08-11","cited_by_count":1,"area":null},{"id":"2311.14270","title":"Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery","created":"2023-11-24","cited_by_count":1,"area":"distill"},{"id":"2403.07888","title":"Cross-modality debiasing: using language to mitigate sub-population shifts in imaging","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2407.19860","title":"Anomalous State Sequence Modeling to Enhance Safety in Reinforcement Learning","created":"2024-07-29","cited_by_count":1,"area":"deeprl"},{"id":"2503.04219","title":"Quantum-Inspired Reinforcement Learning in the Presence of Epistemic Ambivalence","created":"2025-03-06","cited_by_count":1,"area":"deeprl"},{"id":"2503.17125","title":"LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2505.21119","title":"Universal Value-Function Uncertainties","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2506.01167","title":"Accelerated Learning with Linear Temporal Logic using Differentiable Simulation","created":"2025-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2508.09346","title":"How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy","created":"2025-08-12","cited_by_count":1,"area":"wm"},{"id":"2512.00030","title":"Perturbation-mitigated USV Navigation with Distributionally Robust Reinforcement Learning","created":"2025-11-08","cited_by_count":1,"area":"deeprl"},{"id":"2208.10533","title":"Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics","created":"2022-08-22","cited_by_count":0,"area":null},{"id":"2210.13545","title":"MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2212.08800","title":"Cognitive Level-$k$ Meta-Learning for Safe and Pedestrian-Aware Autonomous Driving","created":"2022-12-17","cited_by_count":0,"area":"driving"},{"id":"2212.13819","title":"Don't do it: Safer Reinforcement Learning With Rule-based Guidance","created":"2022-12-28","cited_by_count":0,"area":null},{"id":"2302.03586","title":"Adaptive Aggregation for Safety-Critical Control","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2302.13152","title":"On Bellman's principle of optimality and Reinforcement learning for safety-constrained Markov decision process","created":"2023-02-25","cited_by_count":0,"area":null},{"id":"2401.16618","title":"A comparison of RL-based and PID controllers for 6-DOF swimming robots: hybrid underwater object tracking","created":"2024-01-29","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":"2408.03892","title":"MORTAR: A Model-based Runtime Action Repair Framework for AI-enabled Cyber-Physical Systems","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2408.16776","title":"Online Behavior Modification for Expressive User Control of RL-Trained Robots","created":"2024-08-15","cited_by_count":0,"area":"deeprl"},{"id":"2503.07376","title":"AttentionSwarm: Reinforcement Learning with Attention Control Barier Function for Crazyflie Drones in Dynamic Environments","created":"2025-03-10","cited_by_count":0,"area":"deeprl"},{"id":"2512.02386","title":"Risk-Sensitive Q-Learning in Continuous Time with Application to Dynamic Portfolio Selection","created":"2025-12-02","cited_by_count":0,"area":"deeprl"},{"id":"2601.06505","title":"Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2604.19737","title":"Safe Continual Reinforcement Learning in Non-stationary Environments","created":"2026-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2610.19714","title":"Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies","created":"2026-10-14","cited_by_count":0,"area":"driving"}],"next_cursor":null}