AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dong, Zibin, Yuan, Yifu, Hao, Jianye, Ni, Fei, Mu, Yao, Zheng, Yan, Hu, Yujing, Lv, Tangjie, Fan, Changjie, Hu, Zhipeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914665588588544
author Dong, Zibin
Yuan, Yifu
Hao, Jianye
Ni, Fei
Mu, Yao
Zheng, Yan
Hu, Yujing
Lv, Tangjie
Fan, Changjie
Hu, Zhipeng
author_facet Dong, Zibin
Yuan, Yifu
Hao, Jianye
Ni, Fei
Mu, Yao
Zheng, Yan
Hu, Yujing
Lv, Tangjie
Fan, Changjie
Hu, Zhipeng
contents Aligning agent behaviors with diverse human preferences remains a challenging problem in reinforcement learning (RL), owing to the inherent abstractness and mutability of human preferences. To address these issues, we propose AlignDiff, a novel framework that leverages RL from Human Feedback (RLHF) to quantify human preferences, covering abstractness, and utilizes them to guide diffusion planning for zero-shot behavior customizing, covering mutability. AlignDiff can accurately match user-customized behaviors and efficiently switch from one to another. To build the framework, we first establish the multi-perspective human feedback datasets, which contain comparisons for the attributes of diverse behaviors, and then train an attribute strength model to predict quantified relative strengths. After relabeling behavioral datasets with relative strengths, we proceed to train an attribute-conditioned diffusion model, which serves as a planner with the attribute strength model as a director for preference aligning at the inference phase. We evaluate AlignDiff on various locomotion tasks and demonstrate its superior performance on preference matching, switching, and covering compared to other baselines. Its capability of completing unseen downstream tasks under human instructions also showcases the promising potential for human-AI collaboration. More visualization videos are released on https://aligndiff.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2310_02054
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
Dong, Zibin
Yuan, Yifu
Hao, Jianye
Ni, Fei
Mu, Yao
Zheng, Yan
Hu, Yujing
Lv, Tangjie
Fan, Changjie
Hu, Zhipeng
Artificial Intelligence
Aligning agent behaviors with diverse human preferences remains a challenging problem in reinforcement learning (RL), owing to the inherent abstractness and mutability of human preferences. To address these issues, we propose AlignDiff, a novel framework that leverages RL from Human Feedback (RLHF) to quantify human preferences, covering abstractness, and utilizes them to guide diffusion planning for zero-shot behavior customizing, covering mutability. AlignDiff can accurately match user-customized behaviors and efficiently switch from one to another. To build the framework, we first establish the multi-perspective human feedback datasets, which contain comparisons for the attributes of diverse behaviors, and then train an attribute strength model to predict quantified relative strengths. After relabeling behavioral datasets with relative strengths, we proceed to train an attribute-conditioned diffusion model, which serves as a planner with the attribute strength model as a director for preference aligning at the inference phase. We evaluate AlignDiff on various locomotion tasks and demonstrate its superior performance on preference matching, switching, and covering compared to other baselines. Its capability of completing unseen downstream tasks under human instructions also showcases the promising potential for human-AI collaboration. More visualization videos are released on https://aligndiff.github.io/.
title AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
topic Artificial Intelligence
url https://arxiv.org/abs/2310.02054