# PDP: Physics-Based Character Animation via Diffusion Policy

arXiv: https://arxiv.org/abs/2406.00960 · HTML: https://mlsanity.com/paper/2406.00960/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills](https://mlsanity.com/paper/1804.02717/) (2018)
- [Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots](https://mlsanity.com/paper/2103.14295/) (2021)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [Neural probabilistic motor primitives for humanoid control](https://mlsanity.com/paper/1811.11711/) (2018)
- [MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations](https://mlsanity.com/paper/2310.10198/) (2023)
- [DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets](https://mlsanity.com/paper/2404.19264/) (2024)
- [UniCon: Universal Neural Controller For Physics-based Character Motion](https://mlsanity.com/paper/2011.15119/) (2020)
- [Neural Categorical Priors for Physics-Based Character Control](https://mlsanity.com/paper/2308.07200/) (2023)
- [ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters](https://mlsanity.com/paper/2210.06063/) (2022)
- [Learning Bipedal Walking for Humanoids with Current Feedback](https://mlsanity.com/paper/2303.03724/) (2023)
- [Diffusion Co-Policy for Synergistic Human-Robot Collaborative Tasks](https://mlsanity.com/paper/2305.12171/) (2023)

## Built on by (most cited first, 30 of 31)

- [BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion](https://mlsanity.com/paper/2508.08241/) (2025)
- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)
- [Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control](https://mlsanity.com/paper/2503.11801/) (2025)
- [UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control](https://mlsanity.com/paper/2504.12540/) (2025)
- [From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance](https://mlsanity.com/paper/2510.14952/) (2025)
- [Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking](https://mlsanity.com/paper/2412.17730/) (2024)
- [SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control](https://mlsanity.com/paper/2512.03028/) (2025)
- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)
- [InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2602.06035/) (2026)
- [SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control](https://mlsanity.com/paper/2511.19236/) (2025)
- [StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data](https://mlsanity.com/paper/2505.03154/) (2025)
- [From Generated Human Videos to Physically Plausible Robot Trajectories](https://mlsanity.com/paper/2512.05094/) (2025)
- [InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs](https://mlsanity.com/paper/2512.07410/) (2025)
- [SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control](https://mlsanity.com/paper/2605.22894/) (2026)
- [Diffusion-based Planning with Learned Viability Filters](https://mlsanity.com/paper/2502.19564/) (2025)
- [Learning Smooth Time-Varying Linear Policies with an Action Jacobian Penalty](https://mlsanity.com/paper/2602.18312/) (2026)
- [GPC: Large-Scale Generative Pretraining for Transferable Motor Control](https://mlsanity.com/paper/2606.29148/) (2026)
- [RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters](https://mlsanity.com/paper/2507.20117/) (2025)
- [Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control](https://mlsanity.com/paper/2602.21599/) (2026)
- [MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control](https://mlsanity.com/paper/2605.26006/) (2026)
- [From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Control](https://mlsanity.com/paper/2506.00043/) (2025)
- [SCDP: Learning Humanoid Locomotion from Partial Observations via Mixed-Observation Distillation](https://mlsanity.com/paper/2603.09574/) (2026)
- [FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesis](https://mlsanity.com/paper/2604.10199/) (2026)
- [EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing](https://mlsanity.com/paper/2605.13041/) (2026)
- [NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control](https://mlsanity.com/paper/2605.20209/) (2026)
- [Recovering Physically Plausible Human-Object Interactions from Monocular Videos](https://mlsanity.com/paper/2606.05359/) (2026)
- [Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics](https://mlsanity.com/paper/2606.22806/) (2026)
- [In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics](https://mlsanity.com/paper/2606.26981/) (2026)
- [Progressively Learning Heterogeneous Skills in a Unified Latent Space](https://mlsanity.com/paper/2608.23258/) (2026)
- [LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction](https://mlsanity.com/paper/2609.19688/) (2026)

## Abstract (arXiv)

Generating diverse and realistic human motion that can physically interact with an environment remains a challenging research area in character animation. Meanwhile, diffusion-based methods, as proposed by the robotics community, have demonstrated the ability to capture highly diverse and multi-modal skills. However, naively training a diffusion policy often results in unstable motions for high-frequency, under-actuated control tasks like bipedal locomotion due to rapidly accumulating compounding errors, pushing the agent away from optimal training trajectories. The key idea lies in using RL policies not just for providing optimal trajectories but for providing corrective actions in sub-optimal states, giving the policy a chance to correct for errors caused by environmental stimulus, model errors, or numerical errors in simulation. Our method, Physics-Based Character Animation via Diffusion Policy (PDP), combines reinforcement learning (RL) and behavior cloning (BC) to create a robust diffusion policy for physics-based character animation. We demonstrate PDP on perturbation recovery, universal motion tracking, and physics-based text-to-motion synthesis.