FDPP: Fine-tune Diffusion Policy with Human Preference скачать в хорошем качестве

FDPP: Fine-tune Diffusion Policy with Human Preference

This is the supplementary video for the ICRA 25 publication on finetuning of diffusion policies using Reinforcement Learning (RL). An arXiv upload of the paper can be found here https://arxiv.org/pdf/2501.08259. Abstract : Imitation learning from human demonstrations enables robots to perform complex manipulation tasks and has recently witnessed huge success. However, these techniques often struggle to adapt behavior to new preferences or changes in the environment. To address these limitations, we propose Fine-tuning Diffusion Policy with Human Preference (FDPP). FDPP learns a reward function through preference-based learning. This reward is then used to fine-tune the pre-trained policy with reinforcement learning (RL), resulting in alignment of pre-trained policy with new human preferences while still solving the original task. Our experiments across various robotic tasks and preferences demonstrate that FDPP effectively customizes policy behavior without compromising performance. Additionally, we show that incorporating Kullback–Leibler (KL) regularization during fine-tuning prevents over-fitting and helps maintain the competencies of the initial policy.