# Learning human behaviors from motion capture by adversarial imitation

arXiv: https://arxiv.org/abs/1707.02201 · HTML: https://mlsanity.com/paper/1707.02201/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2017.

## Built on by (most cited first, 30 of 77)

- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [Vision-Language Models as Success Detectors](https://mlsanity.com/paper/2303.07280/) (2023)
- [Reinforcement and Imitation Learning for Diverse Visuomotor Skills](https://mlsanity.com/paper/1802.09564/) (2018)
- [SimPoE: Simulated Character Control for 3D Human Pose Estimation](https://mlsanity.com/paper/2104.00683/) (2021)
- [Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow](https://mlsanity.com/paper/1810.00821/) (2018)
- [Toward the Fundamental Limits of Imitation Learning](https://mlsanity.com/paper/2009.05990/) (2020)
- [Recent Advances in Imitation Learning from Observation](https://mlsanity.com/paper/1905.13566/) (2019)
- [Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions](https://mlsanity.com/paper/2203.15103/) (2022)
- [From Motor Control to Team Play in Simulated Humanoid Football](https://mlsanity.com/paper/2105.12196/) (2021)
- [Demonstration-Guided Reinforcement Learning with Learned Skills](https://mlsanity.com/paper/2107.10253/) (2021)
- [Offline Learning from Demonstrations and Unlabeled Experience](https://mlsanity.com/paper/2011.13885/) (2020)
- [A Survey of Deep RL and IL for Autonomous Driving Policy Learning](https://mlsanity.com/paper/2101.01993/) (2021)
- [Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning](https://mlsanity.com/paper/2110.01770/) (2021)
- [PADL: Language-Directed Physics-Based Character Control](https://mlsanity.com/paper/2301.13868/) (2023)
- [Task-Relevant Adversarial Imitation Learning](https://mlsanity.com/paper/1910.01077/) (2019)
- [Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations](https://mlsanity.com/paper/2206.11693/) (2022)
- [Hierarchical Skills for Efficient Exploration](https://mlsanity.com/paper/2110.10809/) (2021)
- [ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2404.15709/) (2024)
- [Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors](https://mlsanity.com/paper/2203.17138/) (2022)
- [Composite Motion Learning with Task Control](https://mlsanity.com/paper/2305.03286/) (2023)
- [QuestEnvSim: Environment-Aware Simulated Motion Tracking from Sparse Sensors](https://mlsanity.com/paper/2306.05666/) (2023)
- [Hierarchical World Models as Visual Whole-Body Humanoid Controllers](https://mlsanity.com/paper/2405.18418/) (2024)
- [MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control](https://mlsanity.com/paper/2208.07363/) (2022)
- [Imitation Learning from Video by Leveraging Proprioception](https://mlsanity.com/paper/1905.09335/) (2019)
- [Semi-supervised reward learning for offline reinforcement learning](https://mlsanity.com/paper/2012.06899/) (2020)
- [Transflower: probabilistic autoregressive dance generation with multimodal attention](https://mlsanity.com/paper/2106.13871/) (2021)
- [Scaling data-driven robotics with reward sketching and batch reinforcement learning](https://mlsanity.com/paper/1909.12200/) (2019)
- [AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control](https://mlsanity.com/paper/2104.02180/) (2021)
- [Adversarial Imitation Learning from Incomplete Demonstrations](https://mlsanity.com/paper/1905.12310/) (2019)
- [AdaptNet: Policy Adaptation for Physics-Based Character Control](https://mlsanity.com/paper/2310.00239/) (2023)

## 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.