# REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning

arXiv: https://arxiv.org/abs/2603.13707 · HTML: https://mlsanity.com/paper/2603.13707/

## Key facts

- Cited by 2 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 35 of its 42 references that are in the map.
- First posted on arXiv 14 Mar 2026.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 35)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Diffusion Policy Policy Optimization](https://mlsanity.com/paper/2409.00588/) (2024)
- [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)
- [Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning](https://mlsanity.com/paper/2304.13653/) (2023)
- [HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation](https://mlsanity.com/paper/2403.10506/) (2024)
- [SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control](https://mlsanity.com/paper/2511.07820/) (2025)
- [From Imitation to Refinement -- Residual RL for Precise Assembly](https://mlsanity.com/paper/2407.16677/) (2024)
- [HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit](https://mlsanity.com/paper/2502.13013/) (2025)
- [Efficient Online Reinforcement Learning for Diffusion Policy](https://mlsanity.com/paper/2502.00361/) (2025)
- [WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts](https://mlsanity.com/paper/2406.06005/) (2024)
- [Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning](https://mlsanity.com/paper/2501.02116/) (2025)
- [Residual Off-Policy RL for Finetuning Behavior Cloning Policies](https://mlsanity.com/paper/2509.19301/) (2025)
- [Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control](https://mlsanity.com/paper/2412.07773/) (2024)
- [BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds](https://mlsanity.com/paper/2502.10363/) (2025)
- [Hierarchical Planning and Control for Box Loco-Manipulation](https://mlsanity.com/paper/2306.09532/) (2023)
- [TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System](https://mlsanity.com/paper/2511.02832/) (2025)
- [FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation](https://mlsanity.com/paper/2505.06776/) (2025)
- [Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation](https://mlsanity.com/paper/2409.20514/) (2024)
- [HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos](https://mlsanity.com/paper/2509.16757/) (2025)
- [Sim-to-Real Learning for Humanoid Box Loco-Manipulation](https://mlsanity.com/paper/2310.03191/) (2023)
- [VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation](https://mlsanity.com/paper/2509.20322/) (2025)
- [Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer](https://mlsanity.com/paper/2512.01061/) (2025)
- [Tailoring Solution Accuracy for Fast Whole-body Model Predictive Control of Legged Robots](https://mlsanity.com/paper/2407.10789/) (2024)
- [Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations](https://mlsanity.com/paper/2602.06643/) (2026)

## Built on by (most cited first, 2 of 2)

- [PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control](https://mlsanity.com/paper/2609.24840/) (2026)
- [EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation](https://mlsanity.com/paper/2609.36575/) (2026)

## Abstract (arXiv)

Humanoid loco-manipulation requires coordinated task-space motion planning with stable loco-manipulation command tracking under complex robot-environment dynamics and long-horizon tasks. While diffusion policies (DPs) show promise for learning from demonstrations, deploying them on humanoids poses critical challenges: the motion planner trained offline is decoupled from the loco-manipulation controller, leading to poor command tracking, compounding distribution shift, and task failures. The common approach of scaling demonstration data is prohibitively expensive for high-dimensional humanoid systems. To address this challenge, we present REFINE-DP (REinforcement learning FINE-tuning of Diffusion Policy), a hierarchical framework that jointly optimizes a DP motion planner and an RL-based loco-manipulation controller. The DP is fine-tuned via a PPO-based diffusion policy gradient to improve task success rate, while the controller is simultaneously updated to accurately track the planner's evolving command distribution, reducing the distributional mismatch that degrades motion quality. We validate REFINE-DP on a humanoid robot performing loco-manipulation tasks, including door traversal and long-horizon object transport. REFINE-DP achieves an over 90% success rate in simulation, even in out-of-distribution cases not seen in the pre-training data, and enables real-world execution without privileged state information. Our proposed method substantially outperforms pre-trained DP baselines and demonstrates that RL fine-tuning is key to reliable humanoid loco-manipulation. https://refine-dp.github.io/REFINE-DP/