{"total":80,"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":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48,"area":"offlinerl"},{"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":"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":"2306.09205","title":"Reward-Free Curricula for Training Robust World Models","created":"2023-06-15","cited_by_count":13,"area":"wm"},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"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":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2509.18648","title":"SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer","created":"2025-09-23","cited_by_count":8,"area":"deeprl"},{"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":"2601.18217","title":"Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents","created":"2026-01-26","cited_by_count":6,"area":"agents"},{"id":"2405.19080","title":"OMPO: A Unified Framework for RL under Policy and Dynamics Shifts","created":"2024-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2406.02282","title":"Test-Time Regret Minimization in Meta Reinforcement Learning","created":"2024-06-04","cited_by_count":5,"area":"deeprl"},{"id":"2503.24371","title":"Policy Gradient for LQR with Domain Randomization","created":"2025-03-31","cited_by_count":5,"area":"deeprl"},{"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":"2403.07916","title":"Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization","created":"2024-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2502.01800","title":"Flow-based Domain Randomization for Learning and Sequencing Robotic Skills","created":"2025-02-03","cited_by_count":4,"area":"deeprl"},{"id":"2511.04249","title":"Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policies","created":"2025-11-06","cited_by_count":4,"area":"deeprl"},{"id":"2512.05230","title":"Invariance Co-training for Robot Visual Generalization","created":"2025-12-04","cited_by_count":4,"area":"vla"},{"id":"2409.19617","title":"LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World","created":"2024-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2606.00133","title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"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":"2505.18447","title":"Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning","created":"2025-05-24","cited_by_count":2,"area":"deeprl"},{"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":"2407.16842","title":"Adapting Image-based RL Policies via Predicted Rewards","created":"2024-07-23","cited_by_count":1,"area":"deeprl"},{"id":"2410.04719","title":"Domains as Objectives: Domain-Uncertainty-Aware Policy Optimization through Explicit Multi-Domain Convex Coverage Set Learning","created":"2024-10-07","cited_by_count":1,"area":"deeprl"},{"id":"2501.14443","title":"Learning more with the same effort: how randomization improves the robustness of a robotic deep reinforcement learning agent","created":"2025-01-24","cited_by_count":1,"area":"deeprl"},{"id":"2503.00499","title":"Shaping Laser Pulses with Reinforcement Learning","created":"2025-03-01","cited_by_count":1,"area":"deeprl"},{"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":"2505.18418","title":"McARL:Morphology-Control-Aware Reinforcement Learning for Generalizable Quadrupedal Locomotion","created":"2025-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2506.10133","title":"Statistical Guarantees for Offline Domain Randomization","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2508.10171","title":"SynSpill: Improved Industrial Spill Detection With Synthetic Data","created":"2025-08-13","cited_by_count":1,"area":"mllm"},{"id":"2509.22379","title":"A Multi-Modality Evaluation of the Reality Gap in Autonomous Driving Systems","created":"2025-09-26","cited_by_count":1,"area":"driving"},{"id":"2510.24194","title":"Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames","created":"2025-10-28","cited_by_count":1,"area":"offlinerl"},{"id":"2601.21845","title":"Constrained Meta Reinforcement Learning with Provable Test-Time Safety","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2606.18594","title":"Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation","created":"2026-06-17","cited_by_count":1,"area":"deeprl"},{"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":"2502.17221","title":"A Reinforcement Learning Approach to Non-prehensile Manipulation through Sliding","created":"2025-02-24","cited_by_count":0,"area":"deeprl"},{"id":"2504.03983","title":"I Can Hear You Coming: RF Sensing for Uncooperative Satellite Evasion","created":"2025-04-04","cited_by_count":0,"area":"deeprl"},{"id":"2507.07348","title":"Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts","created":"2025-07-10","cited_by_count":0,"area":"deeprl"},{"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":"2510.20152","title":"Soft Switching Expert Policies for Controlling Systems with Uncertain Parameters","created":"2025-10-23","cited_by_count":0,"area":"deeprl"},{"id":"2512.13869","title":"Coarse-to-Fine Hierarchical Alignment for UAV-based Human Detection using Diffusion Models","created":"2025-12-15","cited_by_count":0,"area":"diffusion"},{"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":"2603.22876","title":"Grounding Sim-to-Real Generalization in Robotic Manipulation: An Empirical Study with Vision-Language-Action Models","created":"2026-03-24","cited_by_count":0,"area":"vla"},{"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":"2605.12084","title":"Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.27659","title":"Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment","created":"2026-05-26","cited_by_count":0,"area":"deeprl"},{"id":"2606.12042","title":"KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic Feasibility","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2606.22062","title":"How Should a Simulation-to-Reality Transfer Budget Be Spent?","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.22145","title":"Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System","created":"2026-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.17326","title":"Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints","created":"2026-07-19","cited_by_count":0,"area":"deeprl"},{"id":"2609.01418","title":"Provably Safe Sim-to-Real Transfer","created":"2026-09-01","cited_by_count":0,"area":"deeprl"},{"id":"2609.16300","title":"Policy Gradient over History-Dependent Policy Classes for LQR with Domain Randomization","created":"2026-09-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}