Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fan, Chenyou, Bai, Chenjia, Shan, Zhao, He, Haoran, Zhang, Yang, Wang, Zhen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913939388891136
author Fan, Chenyou
Bai, Chenjia
Shan, Zhao
He, Haoran
Zhang, Yang
Wang, Zhen
author_facet Fan, Chenyou
Bai, Chenjia
Shan, Zhao
He, Haoran
Zhang, Yang
Wang, Zhen
contents Diffusion models have demonstrated their capabilities in modeling trajectories of multi-tasks. However, existing multi-task planners or policies typically rely on task-specific demonstrations via multi-task imitation, or require task-specific reward labels to facilitate policy optimization via Reinforcement Learning (RL). They are costly due to the substantial human efforts required to collect expert data or design reward functions. To address these challenges, we aim to develop a versatile diffusion planner capable of leveraging large-scale inferior data that contains task-agnostic sub-optimal trajectories, with the ability to fast adapt to specific tasks. In this paper, we propose SODP, a two-stage framework that leverages Sub-Optimal data to learn a Diffusion Planner, which is generalizable for various downstream tasks. Specifically, in the pre-training stage, we train a foundation diffusion planner that extracts general planning capabilities by modeling the versatile distribution of multi-task trajectories, which can be sub-optimal and has wide data coverage. Then for downstream tasks, we adopt RL-based fine-tuning with task-specific rewards to quickly refine the diffusion planner, which aims to generate action sequences with higher task-specific returns. Experimental results from multi-task domains including Meta-World and Adroit demonstrate that SODP outperforms state-of-the-art methods with only a small amount of data for reward-guided fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19949
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
Fan, Chenyou
Bai, Chenjia
Shan, Zhao
He, Haoran
Zhang, Yang
Wang, Zhen
Machine Learning
Artificial Intelligence
Diffusion models have demonstrated their capabilities in modeling trajectories of multi-tasks. However, existing multi-task planners or policies typically rely on task-specific demonstrations via multi-task imitation, or require task-specific reward labels to facilitate policy optimization via Reinforcement Learning (RL). They are costly due to the substantial human efforts required to collect expert data or design reward functions. To address these challenges, we aim to develop a versatile diffusion planner capable of leveraging large-scale inferior data that contains task-agnostic sub-optimal trajectories, with the ability to fast adapt to specific tasks. In this paper, we propose SODP, a two-stage framework that leverages Sub-Optimal data to learn a Diffusion Planner, which is generalizable for various downstream tasks. Specifically, in the pre-training stage, we train a foundation diffusion planner that extracts general planning capabilities by modeling the versatile distribution of multi-task trajectories, which can be sub-optimal and has wide data coverage. Then for downstream tasks, we adopt RL-based fine-tuning with task-specific rewards to quickly refine the diffusion planner, which aims to generate action sequences with higher task-specific returns. Experimental results from multi-task domains including Meta-World and Adroit demonstrate that SODP outperforms state-of-the-art methods with only a small amount of data for reward-guided fine-tuning.
title Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2409.19949