mlsanityData to 14 Oct 2026

Neural probabilistic motor primitives for humanoid control

arXiv 1811.11711 ↗First posted 28 Nov 2018cs.LG cs.AI cs.ROcited by 97

Not on the map. Why?

Abstract (arXiv)

We focus on the problem of learning a single motor module that can flexibly express a range of behaviors for the control of high-dimensional physically simulated humanoids. To do this, we propose a motor architecture that has the general structure of an inverse model with a latent-variable bottleneck. We show that it is possible to train this model entirely offline to compress thousands of expert policies and learn a motor primitive embedding space. The trained neural probabilistic motor primitive system can perform one-shot imitation of whole-body humanoid behaviors, robustly mimicking unseen trajectories. Additionally, we demonstrate that it is also straightforward to train controllers to reuse the learned motor primitive space to solve tasks, and the resulting movements are relatively naturalistic. To support the training of our model, we compare two approaches for offline policy cloning, including an experience efficient method which we call linear feedback policy cloning. We encourage readers to view a supplementary video ( https://youtu.be/CaDEf-QcKwA ) summarizing our results.

Key facts. Cited by 97 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 3; 2021: 14; 2022: 16; 2023: 24; 2024: 17; 2025: 13; 2026: 10.

97 papers.

Sort:

By area:

  1. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 166
  2. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 116
  3. 2020Hyperparameter Selection for Offline Reinforcement Learningcited by 114
  4. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 114
  5. 2023Synthesizing Diverse Human Motions in 3D Indoor Scenescited by 109
  6. 2025Reinforcement Learning with Action Chunkingcited by 107
  7. 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
  8. 2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 76
  9. 2023MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representationscited by 60
  10. 2021The Wanderings of Odysseus in 3D Scenescited by 59
  11. 2020RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learningcited by 57
  12. 2022Efficient Planning in a Compact Latent Action Spacecited by 57
38 more
  1. 2024Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learningcited by 56
  2. 2025Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Modelscited by 56
  3. 2023C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characterscited by 55
  4. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrationscited by 53
  5. 2021Hierarchical Skills for Efficient Explorationcited by 38
  6. 2023Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Modelscited by 37
  7. 2023Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priorscited by 36
  8. 2024AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agentscited by 32
  9. 2024PDP: Physics-Based Character Animation via Diffusion Policycited by 31
  10. 2022Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviorscited by 30
  11. 2023RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learningcited by 30
  12. 2024SMPLOlympics: Sports Environments for Physically Simulated Humanoidscited by 29
  13. 2023Composite Motion Learning with Task Controlcited by 28
  14. 2024Hierarchical World Models as Visual Whole-Body Humanoid Controllerscited by 27
  15. 2021Learning Transferable Motor Skills with Hierarchical Latent Mixture Policiescited by 26
  16. 2022MoCapAct: A Multi-Task Dataset for Simulated Humanoid Controlcited by 25
  17. 2022Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Roboticscited by 24
  18. 2023Language-Conditioned Imitation Learning with Base Skill Priors under Unstructured Datacited by 20
  19. 2024Strategy and Skill Learning for Physics-based Table Tennis Animationcited by 20
  20. 2021Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Informationcited by 19
  21. 2021AMP: Adversarial Motion Priors for Stylized Physics-Based Character Controlcited by 18
  22. 2021Collect & Infer -- a fresh look at data-efficient Reinforcement Learningcited by 17
  23. 2024SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillationcited by 17
  24. 2024Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robotscited by 16
  25. 2025Skill Expansion and Composition in Parameter Spacecited by 14
  26. 2021Imitation by Predicting Observationscited by 13
  27. 2021Motion Planning by Learning the Solution Manifold in Trajectory Optimizationcited by 13
  28. 2024Leveraging Skills from Unlabeled Prior Data for Efficient Online Explorationcited by 13
  29. 2022Accelerating Reinforcement Learning for Autonomous Driving using Task-Agnostic and Ego-Centric Motion Skillscited by 12
  30. 2023Efficient Planning with Latent Diffusioncited by 12
  31. 2023MyoDex: A Generalizable Prior for Dexterous Manipulationcited by 11
  32. 2023H-GAP: Humanoid Control with a Generalist Plannercited by 11
  33. 2021OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotioncited by 10
  34. 2022MO2: Model-Based Offline Optionscited by 10
  35. 2022Learning to Brachiate via Simplified Model Imitationcited by 9
  36. 2023Hierarchical generative modelling for autonomous robotscited by 9
  37. 2024Proximal Policy Distillationcited by 9
  38. 2025AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learningcited by 9

50 most cited of 97 All 97 (JSON)