mlsanityData to 14 Oct 2026

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

arXiv 2410.21845 ↗First posted 29 Oct 2024cs.RO cs.AIcited by 189

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Reinforcement learning (RL) holds great promise for enabling autonomous acquisition of complex robotic manipulation skills, but realizing this potential in real-world settings has been challenging. We present a human-in-the-loop vision-based RL system that demonstrates impressive performance on a diverse set of dexterous manipulation tasks, including dynamic manipulation, precision assembly, and dual-arm coordination. Our approach integrates demonstrations and human corrections, efficient RL algorithms, and other system-level design choices to learn policies that achieve near-perfect success rates and fast cycle times within just 1 to 2.5 hours of training. We show that our method significantly outperforms imitation learning baselines and prior RL approaches, with an average 2x improvement in success rate and 1.8x faster execution. Through extensive experiments and analysis, we provide insights into the effectiveness of our approach, demonstrating how it learns robust, adaptive policies for both reactive and predictive control strategies. Our results suggest that RL can indeed learn a wide range of complex vision-based manipulation policies directly in the real world within practical training times. We hope this work will inspire a new generation of learned robotic manipulation techniques, benefiting both industrial applications and research advancements. Videos and code are available at our project website https://hil-serl.github.io/.

Key facts. Cited by 189 papers in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. First posted on arXiv 29 Oct 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 56; 2026: 131.

189 papers.

Sort:

By area:

  1. 2025VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learningcited by 176
  2. 2025Steering Your Diffusion Policy with Latent Space Reinforcement Learningcited by 169
  3. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 154
  4. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  5. 2025Self-Improving Vision-Language-Action Models with Data Generation via Residual RLcited by 78
  6. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 74
  7. 2025A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learningcited by 71
  8. 2025WMPO: World Model-based Policy Optimization for Vision-Language-Action Modelscited by 70
  9. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 69
  10. 2024Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Datacited by 63
  11. 2025RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learningcited by 59
  12. 2025Residual Off-Policy RL for Finetuning Behavior Cloning Policiescited by 55
38 more
  1. 2026WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RLcited by 50
  2. 2025TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimizationcited by 49
  3. 2026RL Token: Bootstrapping Online RL with Vision-Language-Action Modelscited by 49
  4. 2024RLDG: Robotic Generalist Policy Distillation via Reinforcement Learningcited by 47
  5. 2025GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulationcited by 45
  6. 2025GWM: Towards Scalable Gaussian World Models for Robotic Manipulationcited by 39
  7. 2025RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correctioncited by 39
  8. 2026ENPIRE: Agentic Robot Policy Self-Improvement in the Real Worldcited by 38
  9. 2025CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learningcited by 37
  10. 2025World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulationcited by 35
  11. 2025DiWA: Diffusion Policy Adaptation with World Modelscited by 31
  12. 2025Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Correctionscited by 29
  13. 2025WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulationcited by 23
  14. 2026Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stackcited by 22
  15. 2026SOP: A Scalable Online Post-Training System for Vision-Language-Action Modelscited by 21
  16. 2025Act2Goal: From World Model To General Goal-conditioned Policycited by 20
  17. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  18. 2026Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policiescited by 15
  19. 2025Human-assisted Robotic Policy Refinement via Action Preference Optimizationcited by 13
  20. 2026Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuningcited by 13
  21. 2025Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agentscited by 12
  22. 2026chi0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistenciescited by 12
  23. 2026Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Modelscited by 11
  24. 2026EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Modelscited by 11
  25. 2025Reinforcement Learning for Large Model: A Surveycited by 9
  26. 2026NavDreamer: Video Models as Zero-Shot 3D Navigatorscited by 9
  27. 2025Uncertainty Comes for Free: Human-in-the-Loop Policies with Diffusion Modelscited by 8
  28. 2025TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learningcited by 8
  29. 2025Real-world Reinforcement Learning from Suboptimal Interventionscited by 8
  30. 2026LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoningcited by 8
  31. 2026World Engine: Towards the Era of Post-Training for Autonomous Drivingcited by 8
  32. 2025Genie Centurion: Accelerating Scalable Real-World Robot Training with Human Rewind-and-Refine Guidancecited by 7
  33. 2025CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulationcited by 7
  34. 2025Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoidscited by 7
  35. 2025SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Explorationcited by 6
  36. 2026TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulationcited by 6
  37. 2026UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptationcited by 6
  38. 2026UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learningcited by 6

50 most cited of 189 All 189 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Survey of Learning-based Approaches for Robotic In-Hand Manipulation
  2. 2024Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper
  3. 2025Dexterous Manipulation through Imitation Learning: A Survey
  4. 2026Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration
  5. 2024Dexterous Manipulation Based on Prior Dexterous Grasp Pose Knowledge
  6. 2025RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation
  7. 2026Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
  8. 2025Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration