Saved in:
Bibliographic Details
Main Authors: Yu, Zhongwei, Ruan, Jingqing, Xing, Dengpeng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.12615
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910454277734400
author Yu, Zhongwei
Ruan, Jingqing
Xing, Dengpeng
author_facet Yu, Zhongwei
Ruan, Jingqing
Xing, Dengpeng
contents Causal dynamics models (CDMs) have demonstrated significant potential in addressing various challenges in reinforcement learning. To learn CDMs, recent studies have performed causal discovery to capture the causal dependencies among environmental variables. However, the learning of CDMs is still confined to small-scale environments due to computational complexity and sample efficiency constraints. This paper aims to extend CDMs to large-scale object-oriented environments, which consist of a multitude of objects classified into different categories. We introduce the Object-Oriented CDM (OOCDM) that shares causalities and parameters among objects belonging to the same class. Furthermore, we propose a learning method for OOCDM that enables it to adapt to a varying number of objects. Experiments on large-scale tasks indicate that OOCDM outperforms existing CDMs in terms of causal discovery, prediction accuracy, generalization, and computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12615
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Causal Dynamics Models in Object-Oriented Environments
Yu, Zhongwei
Ruan, Jingqing
Xing, Dengpeng
Machine Learning
Causal dynamics models (CDMs) have demonstrated significant potential in addressing various challenges in reinforcement learning. To learn CDMs, recent studies have performed causal discovery to capture the causal dependencies among environmental variables. However, the learning of CDMs is still confined to small-scale environments due to computational complexity and sample efficiency constraints. This paper aims to extend CDMs to large-scale object-oriented environments, which consist of a multitude of objects classified into different categories. We introduce the Object-Oriented CDM (OOCDM) that shares causalities and parameters among objects belonging to the same class. Furthermore, we propose a learning method for OOCDM that enables it to adapt to a varying number of objects. Experiments on large-scale tasks indicate that OOCDM outperforms existing CDMs in terms of causal discovery, prediction accuracy, generalization, and computational efficiency.
title Learning Causal Dynamics Models in Object-Oriented Environments
topic Machine Learning
url https://arxiv.org/abs/2405.12615