# DiffMimic: Efficient Motion Mimicking with Differentiable Physics

arXiv: https://arxiv.org/abs/2304.03274 · HTML: https://mlsanity.com/paper/2304.03274/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 6 Apr 2023.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [DiffTaichi: Differentiable Programming for Physical Simulation](https://mlsanity.com/paper/1910.00935/) (2019)
- [A Differentiable Physics Engine for Deep Learning in Robotics](https://mlsanity.com/paper/1611.01652/) (2016)
- [MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies](https://mlsanity.com/paper/1905.09808/) (2019)
- [Accelerated Policy Learning with Parallel Differentiable Simulation](https://mlsanity.com/paper/2204.07137/) (2022)
- [PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics](https://mlsanity.com/paper/2104.03311/) (2021)
- [ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics](https://mlsanity.com/paper/1810.01054/) (2018)
- [Do Differentiable Simulators Give Better Policy Gradients?](https://mlsanity.com/paper/2202.00817/) (2022)
- [DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact](https://mlsanity.com/paper/2106.05306/) (2021)
- [Visual Grounding of Learned Physical Models](https://mlsanity.com/paper/2004.13664/) (2020)
- [DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools](https://mlsanity.com/paper/2203.17275/) (2022)
- [Differentiable Simulation of Soft Multi-body Systems](https://mlsanity.com/paper/2205.01758/) (2022)
- [Hierarchical visuomotor control of humanoids](https://mlsanity.com/paper/1811.09656/) (2018)
- [MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control](https://mlsanity.com/paper/2208.07363/) (2022)
- [SFV: Reinforcement Learning of Physical Skills from Videos](https://mlsanity.com/paper/1810.03599/) (2018)
- [Learning and Exploring Motor Skills with Spacetime Bounds](https://mlsanity.com/paper/2103.16807/) (2021)
- [Differentiable Physics Simulations with Contacts: Do They Have Correct Gradients w.r.t. Position, Velocity and Control?](https://mlsanity.com/paper/2207.05060/) (2022)
- [Efficient Hyperparameter Optimization for Physics-based Character Animation](https://mlsanity.com/paper/2104.12365/) (2021)
- [Imitation Learning via Differentiable Physics](https://mlsanity.com/paper/2206.04873/) (2022)

## Built on by (most cited first, 19 of 19)

- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction](https://mlsanity.com/paper/2312.04393/) (2023)
- [CoMo: Controllable Motion Generation through Language Guided Pose Code Editing](https://mlsanity.com/paper/2403.13900/) (2024)
- [Learning Quadruped Locomotion Using Differentiable Simulation](https://mlsanity.com/paper/2403.14864/) (2024)
- [InsActor: Instruction-driven Physics-based Characters](https://mlsanity.com/paper/2312.17135/) (2023)
- [Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation](https://mlsanity.com/paper/2412.12089/) (2024)
- [PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitation](https://mlsanity.com/paper/2404.01081/) (2024)
- [Real-Time Simulated Avatar from Head-Mounted Sensors](https://mlsanity.com/paper/2403.06862/) (2024)
- [Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking](https://mlsanity.com/paper/2412.17730/) (2024)
- [Residual Policy Learning for Perceptive Quadruped Control Using Differentiable Simulation](https://mlsanity.com/paper/2410.03076/) (2024)
- [Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation](https://mlsanity.com/paper/2308.10898/) (2023)
- [Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs](https://mlsanity.com/paper/2502.05641/) (2025)
- [A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motions](https://mlsanity.com/paper/2412.17377/) (2024)
- [Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions](https://mlsanity.com/paper/2507.23778/) (2025)
- [DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model](https://mlsanity.com/paper/2405.07309/) (2024)
- [HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions](https://mlsanity.com/paper/2603.15612/) (2026)
- [Agile Robotics: Optimal Control, Reinforcement Learning, and Differentiable Simulation](https://mlsanity.com/paper/2407.01568/) (2024)
- [Dynamic Full-body Motion Agent with Object Interaction via Blending Pre-trained Modular Controllers](https://mlsanity.com/paper/2605.11369/) (2026)
- [Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming](https://mlsanity.com/paper/2606.06094/) (2026)

## Abstract (arXiv)

Motion mimicking is a foundational task in physics-based character animation. However, most existing motion mimicking methods are built upon reinforcement learning (RL) and suffer from heavy reward engineering, high variance, and slow convergence with hard explorations. Specifically, they usually take tens of hours or even days of training to mimic a simple motion sequence, resulting in poor scalability. In this work, we leverage differentiable physics simulators (DPS) and propose an efficient motion mimicking method dubbed DiffMimic. Our key insight is that DPS casts a complex policy learning task to a much simpler state matching problem. In particular, DPS learns a stable policy by analytical gradients with ground-truth physical priors hence leading to significantly faster and stabler convergence than RL-based methods. Moreover, to escape from local optima, we utilize a Demonstration Replay mechanism to enable stable gradient backpropagation in a long horizon. Extensive experiments on standard benchmarks show that DiffMimic has a better sample efficiency and time efficiency than existing methods (e.g., DeepMimic). Notably, DiffMimic allows a physically simulated character to learn Backflip after 10 minutes of training and be able to cycle it after 3 hours of training, while the existing approach may require about a day of training to cycle Backflip. More importantly, we hope DiffMimic can benefit more differentiable animation systems with techniques like differentiable clothes simulation in future research.