{"total":112,"rows":[{"id":"2504.13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins","created":"2025-04-17","cited_by_count":121,"area":null},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72,"area":null},{"id":"2409.02920","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)","created":"2024-09-04","cited_by_count":69,"area":null},{"id":"2505.19017","title":"WorldEval: World Model as Real-World Robot Policies Evaluator","created":"2025-05-25","cited_by_count":68,"area":"wm"},{"id":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56,"area":"deeprl"},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50,"area":"wm"},{"id":"2505.22642","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","created":"2025-05-28","cited_by_count":44,"area":"deeprl"},{"id":"2506.13751","title":"LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction","created":"2025-06-16","cited_by_count":43,"area":"vla"},{"id":"2510.05070","title":"ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning","created":"2025-10-06","cited_by_count":41,"area":null},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"area":"deeprl"},{"id":"2506.12811","title":"Flow-Based Policy for Online Reinforcement Learning","created":"2025-06-15","cited_by_count":37,"area":"deeprl"},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2408.06316","title":"Body Transformer: Leveraging Robot Embodiment for Policy Learning","created":"2024-08-12","cited_by_count":32,"area":null},{"id":"2507.00435","title":"RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation","created":"2025-07-01","cited_by_count":32,"area":null},{"id":"2407.07788","title":"BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark","created":"2024-07-10","cited_by_count":30,"area":null},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2407.00187","title":"SMPLOlympics: Sports Environments for Physically Simulated Humanoids","created":"2024-06-28","cited_by_count":29,"area":null},{"id":"2405.18418","title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","created":"2024-05-28","cited_by_count":27,"area":"wm"},{"id":"2505.02094","title":"SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations","created":"2025-05-04","cited_by_count":25,"area":"deeprl"},{"id":"2505.09698","title":"ManipBench: Benchmarking Vision-Language Models for Low-Level Robot Manipulation","created":"2025-05-14","cited_by_count":24,"area":"lr"},{"id":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23,"area":"deeprl"},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2404.02817","title":"A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches","created":"2024-04-03","cited_by_count":20,"area":null},{"id":"2509.25174","title":"XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning","created":"2025-09-29","cited_by_count":17,"area":"deeprl"},{"id":"2410.13855","title":"Diffusing States and Matching Scores: A New Framework for Imitation Learning","created":"2024-10-17","cited_by_count":16,"area":"diffusion"},{"id":"2412.17730","title":"Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking","created":"2024-12-23","cited_by_count":16,"area":null},{"id":"2503.18871","title":"Bootstrapped Model Predictive Control","created":"2025-03-24","cited_by_count":16,"area":null},{"id":"2505.05753","title":"Towards Embodiment Scaling Laws in Robot Locomotion","created":"2025-05-09","cited_by_count":16,"area":null},{"id":"2505.07819","title":"H$^3$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning","created":"2025-05-12","cited_by_count":16,"area":"diffusion"},{"id":"2502.19652","title":"Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning","created":"2025-02-27","cited_by_count":13,"area":"deeprl"},{"id":"2507.00833","title":"HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning","created":"2025-07-01","cited_by_count":13,"area":"lr"},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11,"area":"deeprl"},{"id":"2411.12155","title":"Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning","created":"2024-11-19","cited_by_count":10,"area":"deeprl"},{"id":"2502.20630","title":"Subtask-Aware Visual Reward Learning from Segmented Demonstrations","created":"2025-02-28","cited_by_count":10,"area":"deeprl"},{"id":"2506.09366","title":"SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending","created":"2025-06-11","cited_by_count":9,"area":"deeprl"},{"id":"2511.00423","title":"Bootstrap Off-policy with World Model","created":"2025-11-01","cited_by_count":7,"area":"wm"},{"id":"2409.16611","title":"Achieving Stable High-Speed Locomotion for Humanoid Robots with Deep Reinforcement Learning","created":"2024-09-25","cited_by_count":6,"area":"deeprl"},{"id":"2502.17322","title":"TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control","created":"2025-02-24","cited_by_count":6,"area":"deeprl"},{"id":"2508.14881","title":"Compute-Optimal Scaling for Value-Based Deep RL","created":"2025-08-20","cited_by_count":6,"area":"deeprl"},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2602.12829","title":"FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching","created":"2026-02-13","cited_by_count":6,"area":"diffusion"},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2504.15046","title":"Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision","created":"2025-04-21","cited_by_count":5,"area":"offlinerl"},{"id":"2505.04860","title":"D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation","created":"2025-05-08","cited_by_count":5,"area":"offlinerl"},{"id":"2508.07842","title":"DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Experts","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2509.01765","title":"Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control","created":"2025-09-01","cited_by_count":5,"area":"deeprl"},{"id":"2601.19707","title":"Scalable Exploration for High-Dimensional Continuous Control via Value-Guided Flow","created":"2026-01-27","cited_by_count":5,"area":"deeprl"},{"id":"2604.04539","title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","created":"2026-04-06","cited_by_count":5,"area":"deeprl"},{"id":"2508.00400","title":"Sari Sandbox: A Virtual Retail Store Environment for Embodied AI Agents","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2509.23328","title":"Space Robotics Bench: Robot Learning Beyond Earth","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2510.08549","title":"Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2603.20147","title":"AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning","created":"2026-03-20","cited_by_count":4,"area":"deeprl"},{"id":"2605.27724","title":"HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning","created":"2026-05-26","cited_by_count":4,"area":"offlinerl"},{"id":"2412.05313","title":"{\\lambda}: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2504.09532","title":"Humanoid Agent via Embodied Chain-of-Action Reasoning with Multimodal Foundation Models for Zero-Shot Loco-Manipulation","created":"2025-04-13","cited_by_count":3,"area":"agents"},{"id":"2507.07820","title":"AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2602.14351","title":"WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control","created":"2026-02-15","cited_by_count":3,"area":"wm"},{"id":"2604.14698","title":"Mean Flow Policy Optimization","created":"2026-04-16","cited_by_count":3,"area":"diffusion"},{"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":"2606.01672","title":"RDA: Reward Design Agent for Reinforcement Learning","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2606.17574","title":"DeepInsight: A Unified Evaluation Infrastructure Across the Physical AI Stack","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2503.22249","title":"FLAM: Foundation Model-Based Body Stabilization for Humanoid Locomotion and Manipulation","created":"2025-03-28","cited_by_count":2,"area":null},{"id":"2505.12748","title":"TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2505.24156","title":"Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction","created":"2025-05-30","cited_by_count":2,"area":"vla"},{"id":"2510.02590","title":"Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning","created":"2025-10-02","cited_by_count":2,"area":"deeprl"},{"id":"2510.04280","title":"A KL-regularization Framework for Learning to Plan with Adaptive Priors","created":"2025-10-05","cited_by_count":2,"area":"deeprl"},{"id":"2512.08411","title":"Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems","created":"2025-12-09","cited_by_count":2,"area":"wm"},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2602.21203","title":"Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics","created":"2026-02-24","cited_by_count":2,"area":"deeprl"},{"id":"2603.13707","title":"REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning","created":"2026-03-14","cited_by_count":2,"area":"diffusion"},{"id":"2605.04712","title":"SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning","created":"2026-05-06","cited_by_count":2,"area":"moe"},{"id":"2605.16692","title":"EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control","created":"2026-05-15","cited_by_count":2,"area":"deeprl"},{"id":"2606.11901","title":"DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2506.12095","title":"DoublyAware: Dual Planning and Policy Awareness for Temporal Difference Learning in Humanoid Locomotion","created":"2025-06-12","cited_by_count":1,"area":"deeprl"},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.09960","title":"GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2601.17507","title":"MetaWorld: Skill Transfer and Composition in a Hierarchical World Model for Grounding High-Level Instructions","created":"2026-01-24","cited_by_count":1,"area":"wm"},{"id":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2603.12612","title":"FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control","created":"2026-03-13","cited_by_count":1,"area":"deeprl"},{"id":"2605.04568","title":"Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination","created":"2026-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2605.08733","title":"Generative Actor-Critic with Soft Bridge Policies","created":"2026-05-09","cited_by_count":1,"area":"deeprl"},{"id":"2605.11711","title":"Debiased Model-based Representations for Sample-efficient Continuous Control","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2605.21429","title":"roto 2.0: The Robot Tactile Olympiad","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2606.25591","title":"WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning","created":"2026-06-24","cited_by_count":1,"area":"vla"},{"id":"2606.29820","title":"Dual-Flow Reinforcement Learning with State-Aware Exploration","created":"2026-06-29","cited_by_count":1,"area":"deeprl"},{"id":"2609.08853","title":"CAST: Alternating State-Value Targets and Expanded Policy Gradients for Model-Based Reinforcement Learning","created":"2026-09-08","cited_by_count":1,"area":"deeprl"},{"id":"2609.10895","title":"ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs","created":"2026-09-09","cited_by_count":1,"area":"mllm"},{"id":"2408.00342","title":"MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2505.04193","title":"Trajectory Entropy Reinforcement Learning for Robust Robot Motor Skill Learning","created":"2025-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2508.16943","title":"LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Cluttered Scenes","created":"2025-08-23","cited_by_count":0,"area":"deeprl"},{"id":"2511.17925","title":"Switch-JustDance: Benchmarking Whole Body Motion Tracking Controllers Using a Commercial Console Game","created":"2025-11-22","cited_by_count":0,"area":null},{"id":"2603.01452","title":"Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning","created":"2026-03-02","cited_by_count":0,"area":"deeprl"},{"id":"2603.08572","title":"MetaWorld-X: Hierarchical World Modeling via VLM-Orchestrated Experts for Humanoid Loco-Manipulation","created":"2026-03-09","cited_by_count":0,"area":"wm"},{"id":"2604.21351","title":"Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot","created":"2026-04-23","cited_by_count":0,"area":"deeprl"},{"id":"2605.10236","title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2606.31691","title":"FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion","created":"2026-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2608.07086","title":"Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2608.16556","title":"DeepInsight II: One Trace from Benchmark to Robot","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":"100"}