{"total":70,"rows":[{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302,"area":"offlinerl"},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"area":"offlinerl"},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85,"area":null},{"id":"2110.14012","title":"Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification","created":"2021-10-26","cited_by_count":80,"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":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50,"area":"offlinerl"},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2102.05762","title":"Risk-Averse Bayes-Adaptive Reinforcement Learning","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2102.04399","title":"How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation","created":"2021-02-08","cited_by_count":27,"area":null},{"id":"2201.01666","title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","created":"2022-01-05","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":"2310.05858","title":"Distributional Soft Actor-Critic with Three Refinements","created":"2023-10-09","cited_by_count":25,"area":null},{"id":"2212.00124","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","created":"2022-11-30","cited_by_count":23,"area":"offlinerl"},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2512.24138","title":"GARDO: Reinforcing Diffusion Models without Reward Hacking","created":"2025-12-30","cited_by_count":17,"area":"diffusion"},{"id":"2102.11075","title":"SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning","created":"2021-02-22","cited_by_count":15,"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":"2407.01985","title":"The Epistemic Uncertainty Hole: an issue of Bayesian Neural Networks","created":"2024-07-02","cited_by_count":11,"area":null},{"id":"2110.03446","title":"A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction","created":"2021-10-06","cited_by_count":10,"area":null},{"id":"2306.01460","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2207.10495","title":"Generating and Detecting True Ambiguity: A Forgotten Danger in DNN Supervision Testing","created":"2022-07-21","cited_by_count":8,"area":null},{"id":"2306.07124","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2312.12145","title":"OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2109.07827","title":"Enabling risk-aware Reinforcement Learning for medical interventions through uncertainty decomposition","created":"2021-09-16","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":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6,"area":"offlinerl"},{"id":"2302.08669","title":"Learning to Forecast Aleatoric and Epistemic Uncertainties over Long Horizon Trajectories","created":"2023-02-17","cited_by_count":6,"area":"wm"},{"id":"2309.12038","title":"Uncertainty-driven Exploration Strategies for Online Grasp Learning","created":"2023-09-21","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":"2407.00801","title":"Model-Free Active Exploration in Reinforcement Learning","created":"2024-06-30","cited_by_count":5,"area":"deeprl"},{"id":"2306.07235","title":"Deep Gaussian Mixture Ensembles","created":"2023-06-12","cited_by_count":4,"area":null},{"id":"2403.08152","title":"Multi-Fidelity Reinforcement Learning for Time-Optimal Quadrotor Re-planning","created":"2024-03-13","cited_by_count":4,"area":"deeprl"},{"id":"2602.05048","title":"MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2110.15907","title":"Learning to Be Cautious","created":"2021-10-29","cited_by_count":3,"area":null},{"id":"2202.10903","title":"Confident Neural Network Regression with Bootstrapped Deep Ensembles","created":"2022-02-22","cited_by_count":3,"area":null},{"id":"2207.13730","title":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","created":"2022-07-27","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":"2309.05582","title":"Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning","created":"2023-09-11","cited_by_count":3,"area":null},{"id":"2310.16546","title":"Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2402.07107","title":"Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning","created":"2024-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2507.20382","title":"Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation through Risk-Adaptive Reinforcement Learning","created":"2025-07-27","cited_by_count":3,"area":"deeprl"},{"id":"2604.06425","title":"Neural Computers","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2302.01727","title":"Distributional constrained reinforcement learning for supply chain optimization","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2401.02914","title":"A unified uncertainty-aware exploration: Combining epistemic and aleatory uncertainty","created":"2024-01-05","cited_by_count":2,"area":"deeprl"},{"id":"2408.08446","title":"Lifelong Reinforcement Learning via Neuromodulation","created":"2024-08-15","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":"2603.18396","title":"RE-SAC: Disentangling aleatoric and epistemic risks in bus fleet control: A stable and robust ensemble DRL approach","created":"2026-03-19","cited_by_count":2,"area":"deeprl"},{"id":"2208.13125","title":"Normality-Guided Distributional Reinforcement Learning for Continuous Control","created":"2022-08-28","cited_by_count":1,"area":null},{"id":"2310.10818","title":"Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2404.02545","title":"Grid-Mapping Pseudo-Count Constraint for Offline Reinforcement Learning","created":"2024-04-03","cited_by_count":1,"area":"offlinerl"},{"id":"2405.08638","title":"vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement","created":"2024-05-14","cited_by_count":1,"area":"deeprl"},{"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":"2410.04322","title":"Toward Debugging Deep Reinforcement Learning Programs with RLExplorer","created":"2024-10-06","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":"2604.26360","title":"Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2110.02129","title":"A study of first-passage time minimization via Q-learning in heated gridworlds","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2204.05196","title":"Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios","created":"2022-04-11","cited_by_count":0,"area":"driving"},{"id":"2204.06509","title":"Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning","created":"2022-04-13","cited_by_count":0,"area":"driving"},{"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":"2310.05179","title":"DRL-ORA: Distributional Reinforcement Learning with Online Risk Adaption","created":"2023-10-08","cited_by_count":0,"area":null},{"id":"2406.02456","title":"Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2504.16635","title":"Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models","created":"2025-04-23","cited_by_count":0,"area":"deeprl"},{"id":"2509.15981","title":"Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations","created":"2025-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2602.08655","title":"From Robotics to Sepsis Treatment: Offline RL via Geometric Pessimism","created":"2026-02-09","cited_by_count":0,"area":"offlinerl"},{"id":"2606.04812","title":"Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe Guarantees","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2607.11607","title":"Auditing the Risk Claims of Distributional Reinforcement Learning","created":"2026-07-13","cited_by_count":0,"area":"deeprl"},{"id":"2608.29860","title":"Uncertainty-Driven Replay Memory for Reinforcement Learning","created":"2026-08-30","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}