AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors

Model-based methods have significantly contributed to distinguishing task-irrelevant distractors for visual control. However, prior research has primarily focused on heterogeneous distractors like noisy background videos, leaving homogeneous distractors that closely resemble controllable agents larg...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-06
Main Authors: Wang, Yucen, Wan, Shenghua, Gan, Le, Feng, Shuai, De-Chuan, Zhan
Format: Article
Language:English
Subjects:
Algorithms
Background noise
Control tasks
Controllability
Visual control
Visual tasks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Model-based methods have significantly contributed to distinguishing task-irrelevant distractors for visual control. However, prior research has primarily focused on heterogeneous distractors like noisy background videos, leaving homogeneous distractors that closely resemble controllable agents largely unexplored, which poses significant challenges to existing methods. To tackle this problem, we propose Implicit Action Generator (IAG) to learn the implicit actions of visual distractors, and present a new algorithm named implicit Action-informed Diverse visual Distractors Distinguisher (AD3), that leverages the action inferred by IAG to train separated world models. Implicit actions effectively capture the behavior of background distractors, aiding in distinguishing the task-irrelevant components, and the agent can optimize the policy within the task-relevant state space. Our method achieves superior performance on various visual control tasks featuring both heterogeneous and homogeneous distractors. The indispensable role of implicit actions learned by IAG is also empirically validated.
ISSN:2331-8422