mlsanityData to 14 Oct 2026

Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost

arXiv 1810.06045 ↗First posted 14 Oct 2018cs.AI cs.ROcited by 84

Not on the map. Why?

Cited by 24 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Dexterous multi-fingered robotic hands can perform a wide range of manipulation skills, making them an appealing component for general-purpose robotic manipulators. However, such hands pose a major challenge for autonomous control, due to the high dimensionality of their configuration space and complex intermittent contact interactions. In this work, we propose deep reinforcement learning (deep RL) as a scalable solution for learning complex, contact rich behaviors with multi-fingered hands. Deep RL provides an end-to-end approach to directly map sensor readings to actions, without the need for task specific models or policy classes. We show that contact-rich manipulation behavior with multi-fingered hands can be learned by directly training with model-free deep RL algorithms in the real world, with minimal additional assumption and without the aid of simulation. We learn a variety of complex behaviors on two different low-cost hardware platforms. We show that each task can be learned entirely from scratch, and further study how the learning process can be further accelerated by using a small number of human demonstrations to bootstrap learning. Our experiments demonstrate that complex multi-fingered manipulation skills can be learned in the real world in about 4-7 hours for most tasks, and that demonstrations can decrease this to 2-3 hours, indicating that direct deep RL training in the real world is a viable and practical alternative to simulation and model-based control. urlhttps://sites.google.com/view/deeprl-handmanipulation

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 2; 2021: 12; 2022: 13; 2023: 20; 2024: 13; 2025: 14; 2026: 9.

84 papers.

Sort:

By area:

  1. 2024Diffusion Policy Policy Optimizationcited by 280
  2. 2023Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuningcited by 237
  3. 2021Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemblecited by 214
  4. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 213
  5. 2021A System for General In-Hand Object Re-Orientationcited by 165
  6. 2019Goal-conditioned Imitation Learningcited by 162
  7. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 154
  8. 2024Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulationcited by 144
  9. 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learningcited by 136
  10. 2022Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learningcited by 119
  11. 2024GRAPE: Generalizing Robot Policy via Preference Alignmentcited by 109
  12. 2022Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapescited by 101
38 more
  1. 2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 95
  2. 2022DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Videocited by 89
  3. 2022DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulationcited by 84
  4. 2023DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objectscited by 66
  5. 2023Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Playcited by 62
  6. 2022Learning Generalizable Dexterous Manipulation from Human Grasp Affordancecited by 51
  7. 2021Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learningcited by 50
  8. 2023Adaptive Policy Learning for Offline-to-Online Reinforcement Learningcited by 40
  9. 2023Dynamic Handover: Throw and Catch with Bimanual Handscited by 35
  10. 2023Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learningcited by 34
  11. 2021Autonomous Reinforcement Learning via Subgoal Curriculacited by 33
  12. 2023MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulationcited by 28
  13. 2024ASID: Active Exploration for System Identification in Robotic Manipulationcited by 28
  14. 2022Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidancecited by 23
  15. 2023Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robotcited by 23
  16. 2023DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physicscited by 23
  17. 2022DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrationscited by 22
  18. 2022When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learningcited by 21
  19. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 21
  20. 2021Reinforcement Learning with Latent Flowcited by 19
  21. 2025DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulationcited by 19
  22. 2024Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learningcited by 17
  23. 2023REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulationcited by 15
  24. 2023A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learningcited by 15
  25. 2024DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulationcited by 15
  26. 2022Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Visioncited by 13
  27. 2023Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedbackcited by 13
  28. 2021On the Feasibility of Learning Finger-gaiting In-hand Manipulation with Intrinsic Sensingcited by 11
  29. 2024Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulationcited by 11
  30. 2025Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Explorationcited by 11
  31. 2024Controlling diverse robots by inferring Jacobian fields with deep networkscited by 10
  32. 2022All the Feels: A dexterous hand with large-area tactile sensingcited by 8
  33. 2021Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learningcited by 7
  34. 2022Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulationcited by 7
  35. 2023Statistical Complexity and Optimal Algorithms for Non-linear Ridge Banditscited by 7
  36. 2022Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learningcited by 5
  37. 2023Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculumcited by 5
  38. 2025Active Advantage-Aligned Online Reinforcement Learning with Offline Datacited by 5

50 most cited of 84 All 84 (JSON)