# Universal Humanoid Motion Representations for Physics-Based Control

arXiv: https://arxiv.org/abs/2310.04582 · HTML: https://mlsanity.com/paper/2310.04582/

## Key facts

- Cited by 116 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 55 references that are in the map.
- First posted on arXiv 6 Oct 2023.

## Builds on (most cited first, 30 of 39)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [DLow: Diversifying Latent Flows for Diverse Human Motion Prediction](https://mlsanity.com/paper/2003.08386/) (2020)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills](https://mlsanity.com/paper/1804.02717/) (2018)
- [MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators](https://mlsanity.com/paper/2306.10900/) (2023)
- [Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion](https://mlsanity.com/paper/2304.01893/) (2023)
- [Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion](https://mlsanity.com/paper/2210.10044/) (2022)
- [SimPoE: Simulated Character Control for 3D Human Pose Estimation](https://mlsanity.com/paper/2104.00683/) (2021)
- [MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies](https://mlsanity.com/paper/1905.09808/) (2019)
- [Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation](https://mlsanity.com/paper/2106.05969/) (2021)
- [3D Human Motion Estimation via Motion Compression and Refinement](https://mlsanity.com/paper/2008.03789/) (2020)
- [Neural probabilistic motor primitives for humanoid control](https://mlsanity.com/paper/1811.11711/) (2018)
- [CALM: Conditional Adversarial Latent Models for Directable Virtual Characters](https://mlsanity.com/paper/2305.02195/) (2023)
- [Kickstarting Deep Reinforcement Learning](https://mlsanity.com/paper/1803.03835/) (2018)
- [PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting](https://mlsanity.com/paper/2210.10542/) (2022)
- [QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars](https://mlsanity.com/paper/2209.09391/) (2022)
- [Latent Space Policies for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1804.02808/) (2018)

## Built on by (most cited first, 30 of 116)

- [OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning](https://mlsanity.com/paper/2406.08858/) (2024)
- [BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion](https://mlsanity.com/paper/2508.08241/) (2025)
- [Expressive Whole-Body Control for Humanoid Robots](https://mlsanity.com/paper/2402.16796/) (2024)
- [Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation](https://mlsanity.com/paper/2403.04436/) (2024)
- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)
- [SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control](https://mlsanity.com/paper/2511.07820/) (2025)
- [Flow Matching Policy Gradients](https://mlsanity.com/paper/2507.21053/) (2025)
- [ExBody2: Advanced Expressive Humanoid Whole-Body Control](https://mlsanity.com/paper/2412.13196/) (2024)
- [DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control](https://mlsanity.com/paper/2410.05260/) (2024)
- [HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit](https://mlsanity.com/paper/2502.13013/) (2025)
- [InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2502.20390/) (2025)
- [Visual Imitation Enables Contextual Humanoid Control](https://mlsanity.com/paper/2505.03729/) (2025)
- [Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models](https://mlsanity.com/paper/2504.11054/) (2025)
- [Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control](https://mlsanity.com/paper/2412.07773/) (2024)
- [TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization](https://mlsanity.com/paper/2503.19901/) (2025)
- [LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction](https://mlsanity.com/paper/2506.13751/) (2025)
- [MaskControl: Spatio-Temporal Control for Masked Motion Synthesis](https://mlsanity.com/paper/2410.10780/) (2024)
- [LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment](https://mlsanity.com/paper/2403.13307/) (2024)
- [PDP: Physics-Based Character Animation via Diffusion Policy](https://mlsanity.com/paper/2406.00960/) (2024)
- [SMPLOlympics: Sports Environments for Physically Simulated Humanoids](https://mlsanity.com/paper/2407.00187/) (2024)
- [Learning from Massive Human Videos for Universal Humanoid Pose Control](https://mlsanity.com/paper/2412.14172/) (2024)
- [Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control](https://mlsanity.com/paper/2503.11801/) (2025)
- [Learning Getting-Up Policies for Real-World Humanoid Robots](https://mlsanity.com/paper/2502.12152/) (2025)
- [UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control](https://mlsanity.com/paper/2504.12540/) (2025)
- [PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios](https://mlsanity.com/paper/2404.19722/) (2024)
- [Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions](https://mlsanity.com/paper/2410.12773/) (2024)
- [Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis](https://mlsanity.com/paper/2508.02106/) (2025)
- [PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System](https://mlsanity.com/paper/2510.11072/) (2025)
- [Real-Time Simulated Avatar from Head-Mounted Sensors](https://mlsanity.com/paper/2403.06862/) (2024)

## Abstract (arXiv)

We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. Due to the high dimensionality of humanoids and the inherent difficulties in reinforcement learning, prior methods have focused on learning skill embeddings for a narrow range of movement styles (e.g. locomotion, game characters) from specialized motion datasets. This limited scope hampers their applicability in complex tasks. We close this gap by significantly increasing the coverage of our motion representation space. To achieve this, we first learn a motion imitator that can imitate all of human motion from a large, unstructured motion dataset. We then create our motion representation by distilling skills directly from the imitator. This is achieved by using an encoder-decoder structure with a variational information bottleneck. Additionally, we jointly learn a prior conditioned on proprioception (humanoid's own pose and velocities) to improve model expressiveness and sampling efficiency for downstream tasks. By sampling from the prior, we can generate long, stable, and diverse human motions. Using this latent space for hierarchical RL, we show that our policies solve tasks using human-like behavior. We demonstrate the effectiveness of our motion representation by solving generative tasks (e.g. strike, terrain traversal) and motion tracking using VR controllers.