# DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion

arXiv: https://arxiv.org/abs/2505.18780 · HTML: https://mlsanity.com/paper/2505.18780/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Humanoid and legged locomotion world models, one of 11 directions in World models.
- Builds on 65 of its 87 references that are in the map.
- First posted on arXiv 24 May 2025.

## Placed in

- World models / [Humanoid and legged locomotion world models](https://mlsanity.com/wm/humanoid-and-legged-locomotion-world-models/)

## Builds on (most cited first, 30 of 65)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning](https://mlsanity.com/paper/2208.06193/) (2022)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [UniSim: A Neural Closed-Loop Sensor Simulator](https://mlsanity.com/paper/2308.01898/) (2023)
- [OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning](https://mlsanity.com/paper/2406.08858/) (2024)
- [HumanPlus: Humanoid Shadowing and Imitation from Humans](https://mlsanity.com/paper/2406.10454/) (2024)
- [FAST-LIO2: Fast Direct LiDAR-inertial Odometry](https://mlsanity.com/paper/2107.06829/) (2021)
- [HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model](https://mlsanity.com/paper/2503.10631/) (2025)
- [Extreme Parkour with Legged Robots](https://mlsanity.com/paper/2309.14341/) (2023)
- [Goal-Conditioned Reinforcement Learning: Problems and Solutions](https://mlsanity.com/paper/2201.08299/) (2022)
- [Robot Parkour Learning](https://mlsanity.com/paper/2309.05665/) (2023)
- [Open-TeleVision: Teleoperation with Immersive Active Visual Feedback](https://mlsanity.com/paper/2407.01512/) (2024)

## Built on by (most cited first, 5 of 5)

- [Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations](https://mlsanity.com/paper/2601.09518/) (2026)
- [Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robots](https://mlsanity.com/paper/2603.06181/) (2026)
- [Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why](https://mlsanity.com/paper/2507.05906/) (2025)
- [Architecture Is All You Need: Diversity-Enabled Sweet Spots for Robust Humanoid Locomotion](https://mlsanity.com/paper/2510.14947/) (2025)
- [World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain](https://mlsanity.com/paper/2609.02542/) (2026)

## Abstract (arXiv)

Achieving versatile humanoid locomotion with a single policy presents a critical scalability challenge. Prevailing methods often rely on distilling multiple terrain-specific teacher policies into a unified student policy. However, while such distillation captures basic locomotion primitives, it struggles to organically compose these skills to adapt to complex environments, resulting in poor generalization to novel composite terrains unseen during training. To overcome this, we present DreamPolicy, a unified framework that integrates offline data with a diffusion-based world model, enabling a single policy to master both known and unseen terrains. Central to our approach is a terrain-aware world model, driven by an autoregressive diffusion world model trained on aggregated rollouts from specialized policies. This model synthesizes physically plausible future trajectories, which serve as dynamic objectives for a conditioned policy, thereby bypassing manual reward engineering. Unlike distillation, our world model captures generalizable locomotion skills, allowing for robust zero-shot transfer to unseen composite terrains. DreamPolicy naturally scales with data availability. As the offline dataset expands, the diffusion world model continuously acquires richer skills. Experiments demonstrate that DreamPolicy outperforms the strongest baseline by up to 27% on unseen terrains and 38% on combined terrains. By unifying world model-based planning and policy learning, DreamPolicy breaks the "one task, one policy" bottleneck and establishes a scalable, data-driven paradigm for generalist humanoid control.