mlsanityData to 7 Oct 2026

Data-efficient Deep Reinforcement Learning for Dexterous Manipulation

arXiv 1704.03073 ↗First posted 10 Apr 2017cs.LG cs.ROcited by 61

Not on the map. Why?

Abstract (arXiv)

Deep learning and reinforcement learning methods have recently been used to solve a variety of problems in continuous control domains. An obvious application of these techniques is dexterous manipulation tasks in robotics which are difficult to solve using traditional control theory or hand-engineered approaches. One example of such a task is to grasp an object and precisely stack it on another. Solving this difficult and practically relevant problem in the real world is an important long-term goal for the field of robotics. Here we take a step towards this goal by examining the problem in simulation and providing models and techniques aimed at solving it. We introduce two extensions to the Deep Deterministic Policy Gradient algorithm (DDPG), a model-free Q-learning based method, which make it significantly more data-efficient and scalable. Our results show that by making extensive use of off-policy data and replay, it is possible to find control policies that robustly grasp objects and stack them. Further, our results hint that it may soon be feasible to train successful stacking policies by collecting interactions on real robots.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 0; 2020: 1; 2021: 15; 2022: 6; 2023: 14; 2024: 12; 2025: 7; 2026: 4.

61 papers.

Sort:

By area:

  1. 2025Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscationcited by 338
  2. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  3. 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learningcited by 113
  4. 2021Asymmetric self-play for automatic goal discovery in robotic manipulationcited by 71
  5. 2021What Matters for Adversarial Imitation Learning?cited by 70
  6. 2023Vision-Language Models as a Source of Rewardscited by 65
  7. 2024Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learningcited by 63
  8. 2023Learning to Generate Better Than Your LLMcited by 49
  9. 2018Learning to Play with Intrinsically-Motivated Self-Aware Agentscited by 34
  10. 2021Curiosity-Driven Exploration via Latent Bayesian Surprisecited by 22
  11. 2021Contrastive Active Inferencecited by 21
  12. 2023Causal Policy Gradient for Whole-Body Mobile Manipulationcited by 18
38 more
  1. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  2. 2021Hyperparameter Selection for Imitation Learningcited by 17
  3. 2021Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learningcited by 17
  4. 2023FOCUS: Object-Centric World Models for Robotics Manipulationcited by 17
  5. 2023Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Owncited by 16
  6. 2021Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learningcited by 15
  7. 2023DEFT: Dexterous Fine-Tuning for Real-World Hand Policiescited by 15
  8. 2021Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learningcited by 14
  9. 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
  10. 2023Rapid Motor Adaptation for Robotic Manipulator Armscited by 13
  11. 2024Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learningcited by 12
  12. 2025Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agentscited by 12
  13. 2021Discovering User-Interpretable Capabilities of Black-Box Planning Agentscited by 10
  14. 2022Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inferencecited by 9
  15. 2021Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Taskscited by 8
  16. 2023Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attackscited by 7
  17. 2024DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robotscited by 7
  18. 2021Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradientscited by 6
  19. 2023Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings (Extended Version)cited by 6
  20. 2024Predictive Coding for Decision Transformercited by 6
  21. 2021Discovering Generalizable Skills via Automated Generation of Diverse Taskscited by 5
  22. 2022Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learningcited by 5
  23. 2021MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environmentscited by 4
  24. 2023A Lightweight and Transferable Design for Robust LEGO Manipulationcited by 4
  25. 2025A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewardscited by 4
  26. 2020Imitation Learning for High Precision Peg-in-Hole Taskscited by 3
  27. 2022Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learningcited by 3
  28. 2024Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generationcited by 3
  29. 2024Multi-Agent Reinforcement Learning for Maritime Operational Technology Cyber Securitycited by 2
  30. 2024Diffusion-Informed Probabilistic Contact Search for Multi-Finger Manipulationcited by 2
  31. 2021Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Roboticscited by 1
  32. 2022Multi-Phase Multi-Objective Dexterous Manipulation with Adaptive Hierarchical Curriculumcited by 1
  33. 2023H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulationcited by 1
  34. 2024Learning Off-policy with Model-based Intrinsic Motivation For Active Online Explorationcited by 1
  35. 2024Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examplescited by 1
  36. 2024Enhancing Quantum Memory Lifetime with Measurement-Free Local Error Correction and Reinforcement Learningcited by 1
  37. 2025Leveraging Analytic Gradients in Provably Safe Reinforcement Learningcited by 1
  38. 2025Prompt-to-Product: Generative Assembly via Bimanual Manipulationcited by 1

50 most cited of 61 All 61 (JSON)