{"total":39,"rows":[{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"area":null},{"id":"2312.03502","title":"Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation","created":"2023-12-06","cited_by_count":31,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2311.01885","title":"Domain Randomization via Entropy Maximization","created":"2023-11-03","cited_by_count":19,"area":null},{"id":"2307.06333","title":"Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation","created":"2023-07-12","cited_by_count":16,"area":null},{"id":"2412.14401","title":"The One RING: a Robotic Indoor Navigation Generalist","created":"2024-12-18","cited_by_count":16,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2111.00213","title":"Adjacency constraint for efficient hierarchical reinforcement learning","created":"2021-10-30","cited_by_count":10,"area":null},{"id":"2305.18464","title":"Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2310.04590","title":"Deep Model Predictive Optimization","created":"2023-10-06","cited_by_count":7,"area":null},{"id":"2305.11686","title":"Domain Adaptive Sim-to-Real Segmentation of Oropharyngeal Organs Towards Robot-assisted Intubation","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2404.12648","title":"Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation","created":"2024-04-19","cited_by_count":6,"area":null},{"id":"2510.11689","title":"Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2206.14661","title":"Online vs. Offline Adaptive Domain Randomization Benchmark","created":"2022-06-29","cited_by_count":4,"area":null},{"id":"2312.10289","title":"Active Reinforcement Learning for Robust Building Control","created":"2023-12-16","cited_by_count":4,"area":null},{"id":"2312.12558","title":"Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge","created":"2023-12-19","cited_by_count":4,"area":null},{"id":"2208.04987","title":"Vehicle Type Specific Waypoint Generation","created":"2022-08-09","cited_by_count":2,"area":null},{"id":"2305.17552","title":"Online Nonstochastic Model-Free Reinforcement Learning","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2502.04809","title":"Humans Coexist, So Must Embodied Artificial Agents","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2503.00296","title":"Synthetic data enables context-aware bioacoustic sound event detection","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2505.21553","title":"MetaSTNet: Multimodal Meta-learning for Cellular Traffic Conformal Prediction","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2510.01708","title":"PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomization","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2310.11075","title":"Sim-to-Real Transfer of Adaptive Control Parameters for AUV Stabilization under Current Disturbance","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2504.19715","title":"Model-based controller assisted domain randomization for transient vibration suppression of nonlinear powertrain system with parametric uncertainty","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2506.10133","title":"Statistical Guarantees for Offline Domain Randomization","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2305.06657","title":"On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm","created":"2023-05-11","cited_by_count":0,"area":null},{"id":"2305.10883","title":"Domain Adaptive Sim-to-Real Segmentation of Oropharyngeal Organs","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2408.02685","title":"Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2409.03614","title":"1 Modular Parallel Manipulator for Long-Term Soft Robotic Data Collection","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2508.17468","title":"A Synthetic Dataset for Manometry Recognition in Robotic Applications","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2509.05732","title":"Simulation Priors for Data-Efficient Deep Learning","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2509.15045","title":"Synthetic-to-Real Object Detection using YOLOv11 and Domain Randomization Strategies","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2601.19406","title":"Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.17174","title":"Continual Uncertainty Learning for Robust Control of Nonlinear Systems with Multiple Heterogeneous Uncertainties","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2605.12084","title":"Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.22062","title":"How Should a Simulation-to-Reality Transfer Budget Be Spent?","created":"2026-06-20","cited_by_count":0,"area":null}],"next_cursor":null}