{"total":88,"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":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166,"area":"wm"},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"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":"2101.01993","title":"A Survey of Deep RL and IL for Autonomous Driving Policy Learning","created":"2021-01-06","cited_by_count":61,"area":"driving"},{"id":"2112.05251","title":"Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation","created":"2021-12-09","cited_by_count":59,"area":"offlinerl"},{"id":"2107.00646","title":"Learning to See before Learning to Act: Visual Pre-training for Manipulation","created":"2021-07-01","cited_by_count":51,"area":null},{"id":"2211.12717","title":"Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks","created":"2022-11-23","cited_by_count":49,"area":null},{"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":"2102.05289","title":"Bayesian Inference with Certifiable Adversarial Robustness","created":"2021-02-10","cited_by_count":26,"area":null},{"id":"2207.08673","title":"Back to the Manifold: Recovering from Out-of-Distribution States","created":"2022-07-18","cited_by_count":20,"area":null},{"id":"2306.07745","title":"Kernelized Reinforcement Learning with Order Optimal Regret Bounds","created":"2023-06-13","cited_by_count":20,"area":null},{"id":"2503.03707","title":"Curating Demonstrations using Online Experience","created":"2025-03-05","cited_by_count":18,"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":"2112.07701","title":"Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning","created":"2021-12-14","cited_by_count":16,"area":null},{"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":"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":"2205.01887","title":"Uncertainty estimation of pedestrian future trajectory using Bayesian approximation","created":"2022-05-04","cited_by_count":12,"area":null},{"id":"2207.07920","title":"Physics Embedded Neural Network Vehicle Model and Applications in Risk-Aware Autonomous Driving Using Latent Features","created":"2022-07-16","cited_by_count":12,"area":null},{"id":"2103.06403","title":"A Vision Based Deep Reinforcement Learning Algorithm for UAV Obstacle Avoidance","created":"2021-03-11","cited_by_count":10,"area":null},{"id":"2107.04775","title":"LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks","created":"2021-07-10","cited_by_count":10,"area":null},{"id":"2401.17441","title":"Explaining Predictive Uncertainty by Exposing Second-Order Effects","created":"2024-01-30","cited_by_count":10,"area":null},{"id":"2402.08078","title":"Large Language Models as Agents in Two-Player Games","created":"2024-02-12","cited_by_count":10,"area":"agents"},{"id":"2107.04491","title":"Offline reinforcement learning with uncertainty for treatment strategies in sepsis","created":"2021-07-09","cited_by_count":9,"area":"offlinerl"},{"id":"2303.06710","title":"Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning","created":"2023-03-12","cited_by_count":9,"area":null},{"id":"2310.19424","title":"Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills","created":"2023-10-30","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":"2302.00727","title":"Sample Complexity of Kernel-Based Q-Learning","created":"2023-02-01","cited_by_count":8,"area":null},{"id":"2306.10742","title":"BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming","created":"2023-06-19","cited_by_count":8,"area":null},{"id":"2404.16879","title":"Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey","created":"2024-04-22","cited_by_count":8,"area":"deeprl"},{"id":"2305.12240","title":"Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics","created":"2023-05-20","cited_by_count":7,"area":null},{"id":"2112.12612","title":"Towards Disturbance-Free Visual Mobile Manipulation","created":"2021-12-17","cited_by_count":6,"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":"2206.02675","title":"Effects of Safety State Augmentation on Safe Exploration","created":"2022-06-06","cited_by_count":6,"area":null},{"id":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"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":"2410.23498","title":"Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm","created":"2024-10-30","cited_by_count":6,"area":"deeprl"},{"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":"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":"2306.14601","title":"Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception","created":"2023-06-26","cited_by_count":5,"area":null},{"id":"2109.13858","title":"Domain Generalization for Vision-based Driving Trajectory Generation","created":"2021-09-22","cited_by_count":4,"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":"2402.08208","title":"Inherent Diverse Redundant Safety Mechanisms for AI-based Software Elements in Automotive Applications","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2603.05504","title":"RoboPocket: Improve Robot Policies Instantly with Your Phone","created":"2026-03-05","cited_by_count":4,"area":"offlinerl"},{"id":"2011.11293","title":"Evolutionary Planning in Latent Space","created":"2020-11-23","cited_by_count":3,"area":"wm"},{"id":"2104.14912","title":"Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning","created":"2021-04-30","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":"2109.08342","title":"Dropout's Dream Land: Generalization from Learned Simulators to Reality","created":"2021-09-17","cited_by_count":3,"area":"wm"},{"id":"2110.15907","title":"Learning to Be Cautious","created":"2021-10-29","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":"2209.09648","title":"Safe Reinforcement Learning with Contrastive Risk Prediction","created":"2022-09-10","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":"2305.16620","title":"Pedestrian Trajectory Forecasting Using Deep Ensembles Under Sensing Uncertainty","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2406.01782","title":"Multi-agent assignment via state augmented reinforcement learning","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2209.11789","title":"SAFER: Safe Collision Avoidance using Focused and Efficient Trajectory Search with Reinforcement Learning","created":"2022-09-23","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":"2403.16178","title":"Mixed-Initiative Human-Robot Teaming under Suboptimality with Online Bayesian Adaptation","created":"2024-03-24","cited_by_count":2,"area":null},{"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":"2505.13837","title":"Enhancing Robot Navigation Policies with Task-Specific Uncertainty Managements","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2510.10149","title":"Robust Learning of Diffusion Models with Extremely Noisy Conditions","created":"2025-10-11","cited_by_count":2,"area":"diffusion"},{"id":"2112.05299","title":"Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots","created":"2021-12-10","cited_by_count":1,"area":null},{"id":"2209.15618","title":"Beyond Bayes-optimality: meta-learning what you know you don't know","created":"2022-09-30","cited_by_count":1,"area":null},{"id":"2210.06377","title":"Smooth Trajectory Collision Avoidance through Deep Reinforcement Learning","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2406.13025","title":"ABNet: Attention BarrierNet for Safe and Scalable Robot Learning","created":"2024-06-18","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":"2506.16720","title":"DRARL: Disengagement-Reason-Augmented Reinforcement Learning for Efficient Improvement of Autonomous Driving Policy","created":"2025-06-20","cited_by_count":1,"area":"driving"},{"id":"2102.08029","title":"Transferring Domain Knowledge with an Adviser in Continuous Tasks","created":"2021-02-16","cited_by_count":0,"area":null},{"id":"2110.06435","title":"Dropout Prediction Uncertainty Estimation Using Neuron Activation Strength","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2202.12348","title":"Bayesian Deep Learning for Graphs","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2209.09079","title":"MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation","created":"2022-09-19","cited_by_count":0,"area":null},{"id":"2312.03296","title":"Cooperative Probabilistic Trajectory Forecasting under Occlusion","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2402.06297","title":"Dynamic Q-planning for Online UAV Path Planning in Unknown and Complex Environments","created":"2024-02-09","cited_by_count":0,"area":"deeprl"},{"id":"2408.02295","title":"Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning","created":"2024-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2411.19729","title":"Risk-Averse Certification of Bayesian Neural Networks","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2511.03473","title":"Reinforcement Learning Using known Invariances","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2605.09183","title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","created":"2026-05-09","cited_by_count":0,"area":"offlinerl"},{"id":"2605.27720","title":"Bayesian Deployment Approval for Learned Landing Controllers under Finite Rollout Validation","created":"2026-05-26","cited_by_count":0,"area":"deeprl"},{"id":"2606.16558","title":"ROSA-RL: Uncertainty-Aware Roundabout Optimized Speed Advisory with Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2610.11580","title":"Uncertainty-Aware Optimization for Physics-Aware Highway Trajectory Prediction","created":"2026-10-08","cited_by_count":0,"area":null},{"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}