mlsanityData to 7 Oct 2026

The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control

arXiv 2411.01349 ↗First posted 2 Nov 2024cs.RO cs.LGcited by 1

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Humanoids have the potential to be the ideal embodiment in environments designed for humans. Thanks to the structural similarity to the human body, they benefit from rich sources of demonstration data, e.g., collected via teleoperation, motion capture, or even using videos of humans performing tasks. However, distilling a policy from demonstrations is still a challenging problem. While Diffusion Policies (DPs) have shown impressive results in robotic manipulation, their applicability to locomotion and humanoid control remains underexplored. In this paper, we investigate how dataset diversity and size affect the performance of DPs for humanoid whole-body control. In a simulated IsaacGym environment, we generate synthetic demonstrations by training Adversarial Motion Prior (AMP) agents under various Domain Randomization (DR) conditions, and we compare DPs fitted to datasets of different size and diversity. Our findings show that, although DPs can achieve stable walking behavior, successful training of locomotion policies requires significantly larger and more diverse datasets compared to manipulation tasks, even in simple scenarios.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 25 of its 28 references that are in the map. First posted on arXiv 2 Nov 2024.

Builds on

25 of 28 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Diffusion Policy Policy Optimization1 Sep
  2. 2024BiRoDiff: Diffusion policies for bipedal robot locomotion on unseen terrains7 Jul
  3. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations6 Mar
  4. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representations16 Feb
  5. 2023Efficient Diffusion Policies for Offline Reinforcement Learning31 May
  6. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policies5 Apr
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar
  8. 2023Imitating Human Behaviour with Diffusion Models25 Jan

Other references · 17

  1. 2016Generative Adversarial Imitation Learningcited by 1,576
  2. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  5. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  6. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  7. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  8. 2021IQ-Learn: Inverse soft-Q Learning for Imitationcited by 191
  9. 2024OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learningcited by 167
  10. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 132
  11. 2024Learning Human-to-Humanoid Real-Time Whole-Body Teleoperationcited by 112
  12. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 68
5 more
  1. 2024DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasetscited by 47
  2. 2023LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotioncited by 31
  3. 2023LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learningcited by 28
  4. 2021GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Modelcited by 23
  5. 2023Time-Efficient Reinforcement Learning with Stochastic Stateful Policiescited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Pretraining in Actor-Critic Reinforcement Learning for Locomotioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning
  2. 2026HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
  3. 2026FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences ↗
  4. 2026DreamControl-v2: Simpler and Scalable Autonomous Humanoid Skills via Trainable Guided Diffusion Priors
  5. 2026SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation
  6. 2026SCDP: Learning Humanoid Locomotion from Partial Observations via Mixed-Observation Distillation
  7. 2024Generalizable Humanoid Manipulation with 3D Diffusion Policies
  8. 2026Humanoid-DART: Humanoid Loco-Manipulation using Diffusion-guided Augmentation through Relabeling and Tracking