{"total":21,"rows":[{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"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":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2205.09284","title":"Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble","created":"2022-05-19","cited_by_count":18,"area":null},{"id":"2505.02874","title":"Uncertainty Quantification for Machine Learning in Healthcare: A Survey","created":"2025-05-04","cited_by_count":14,"area":null},{"id":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","cited_by_count":7,"area":null},{"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":"2312.10289","title":"Active Reinforcement Learning for Robust Building Control","created":"2023-12-16","cited_by_count":4,"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":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2406.10775","title":"A Rate-Distortion View of Uncertainty Quantification","created":"2024-06-16","cited_by_count":3,"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":"2110.09712","title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2207.14443","title":"A Survey of Learning on Small Data: Generalization, Optimization, and Challenge","created":"2022-07-29","cited_by_count":1,"area":null},{"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":"2602.05776","title":"Cross-Domain Offline Policy Adaptation via Selective Transition Correction","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2411.11099","title":"Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning","created":"2024-11-17","cited_by_count":0,"area":null},{"id":"2509.13132","title":"An Uncertainty-Weighted Decision Transformer for Navigation in Dense, Complex Driving Scenarios","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2607.26599","title":"Uncertainty-Guided LLM Semantic Augmentation for Heterogeneous Treatment Effect Estimation","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}