mlsanityData to 7 Oct 2026

Learning human behaviors from motion capture by adversarial imitation

arXiv 1707.02201 ↗First posted 7 Jul 2017cs.RO cs.LG cs.SYcited by 75

Not on the map. Why?

Cited by 32 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies. However, methods that use pure reinforcement learning with simple reward functions tend to produce non-humanlike and overly stereotyped movement behaviors. In this work, we extend generative adversarial imitation learning to enable training of generic neural network policies to produce humanlike movement patterns from limited demonstrations consisting only of partially observed state features, without access to actions, even when the demonstrations come from a body with different and unknown physical parameters. We leverage this approach to build sub-skill policies from motion capture data and show that they can be reused to solve tasks when controlled by a higher level controller.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 3; 2019: 8; 2020: 8; 2021: 17; 2022: 15; 2023: 9; 2024: 4; 2025: 9; 2026: 2.

75 papers.

Sort:

By area:

  1. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  2. 2023Vision-Language Models as Success Detectorscited by 138
  3. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  4. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111
  5. 2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flowcited by 103
  6. 2020Toward the Fundamental Limits of Imitation Learningcited by 96
  7. 2019Recent Advances in Imitation Learning from Observationcited by 92
  8. 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
  9. 2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 73
  10. 2020Offline Learning from Demonstrations and Unlabeled Experiencecited by 72
  11. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 68
  12. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 59
38 more
  1. 2021Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learningcited by 53
  2. 2023PADL: Language-Directed Physics-Based Character Controlcited by 47
  3. 2019Task-Relevant Adversarial Imitation Learningcited by 45
  4. 2021Hierarchical Skills for Efficient Explorationcited by 37
  5. 2024ViViDex: Learning Vision-based Dexterous Manipulation from Human Videoscited by 33
  6. 2022Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrationscited by 30
  7. 2022Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviorscited by 27
  8. 2023Composite Motion Learning with Task Controlcited by 26
  9. 2023QuestEnvSim: Environment-Aware Simulated Motion Tracking from Sparse Sensorscited by 26
  10. 2022MoCapAct: A Multi-Task Dataset for Simulated Humanoid Controlcited by 24
  11. 2024Hierarchical World Models as Visual Whole-Body Humanoid Controllerscited by 24
  12. 2019Imitation Learning from Video by Leveraging Proprioceptioncited by 23
  13. 2020Semi-supervised reward learning for offline reinforcement learningcited by 22
  14. 2021Transflower: probabilistic autoregressive dance generation with multimodal attentioncited by 22
  15. 2019Scaling data-driven robotics with reward sketching and batch reinforcement learningcited by 18
  16. 2021AMP: Adversarial Motion Priors for Stylized Physics-Based Character Controlcited by 18
  17. 2019Adversarial Imitation Learning from Incomplete Demonstrationscited by 16
  18. 2022Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrationscited by 15
  19. 2023AdaptNet: Policy Adaptation for Physics-Based Character Controlcited by 15
  20. 2021Imitation by Predicting Observationscited by 13
  21. 2021Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Taskscited by 13
  22. 2021A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Controlcited by 12
  23. 2022Accelerating Reinforcement Learning for Autonomous Driving using Task-Agnostic and Ego-Centric Motion Skillscited by 12
  24. 2020Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Netscited by 11
  25. 2022Imitation Learning from Observations under Transition Model Disparitycited by 11
  26. 2022Learning to Get Upcited by 11
  27. 2023MyoDex: A Generalizable Prior for Dexterous Manipulationcited by 11
  28. 2023H-GAP: Humanoid Control with a Generalist Plannercited by 11
  29. 2021OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotioncited by 10
  30. 2022Improving Policy Learning via Language Dynamics Distillationcited by 9
  31. 2024F"urElise: Capturing and Physically Synthesizing Hand Motions of Piano Performancecited by 8
  32. 2019Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Modelcited by 7
  33. 2020Domain-Adversarial and Conditional State Space Model for Imitation Learningcited by 7
  34. 2020Generative Adversarial Imitation Learning with Neural Networks: Global Optimality and Convergence Ratecited by 7
  35. 2022Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulationcited by 7
  36. 2020On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstrationcited by 6
  37. 2022No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RLcited by 6
  38. 2025Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputscited by 6

50 most cited of 75 All 75 (JSON)