Saved in:
Bibliographic Details
Main Authors: Hayashi, Kohei, Koyama, Masanori, Guerreiro, Julian Jorge Andrade
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.09911
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915195405729792
author Hayashi, Kohei
Koyama, Masanori
Guerreiro, Julian Jorge Andrade
author_facet Hayashi, Kohei
Koyama, Masanori
Guerreiro, Julian Jorge Andrade
contents Various world model frameworks are being developed today based on autoregressive frameworks that rely on discrete representations of actions and observations, and these frameworks are succeeding in constructing interactive generative models for the target environment of interest. Meanwhile, humans demonstrate remarkable generalization abilities to combine experiences in multiple environments to mentally simulate and learn to control agents in diverse environments. Inspired by this human capability, we introduce World modeling through Lie Action (WLA), an unsupervised framework that learns continuous latent action representations to simulate across environments. WLA learns a control interface with high controllability and predictive ability by simultaneously modeling the dynamics of multiple environments using Lie group theory and object-centric autoencoder. On synthetic benchmark and real-world datasets, we demonstrate that WLA can be trained using only video frames and, with minimal or no action labels, can quickly adapt to new environments with novel action sets.
format Preprint
id arxiv_https___arxiv_org_abs_2503_09911
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inter-environmental world modeling for continuous and compositional dynamics
Hayashi, Kohei
Koyama, Masanori
Guerreiro, Julian Jorge Andrade
Machine Learning
Various world model frameworks are being developed today based on autoregressive frameworks that rely on discrete representations of actions and observations, and these frameworks are succeeding in constructing interactive generative models for the target environment of interest. Meanwhile, humans demonstrate remarkable generalization abilities to combine experiences in multiple environments to mentally simulate and learn to control agents in diverse environments. Inspired by this human capability, we introduce World modeling through Lie Action (WLA), an unsupervised framework that learns continuous latent action representations to simulate across environments. WLA learns a control interface with high controllability and predictive ability by simultaneously modeling the dynamics of multiple environments using Lie group theory and object-centric autoencoder. On synthetic benchmark and real-world datasets, we demonstrate that WLA can be trained using only video frames and, with minimal or no action labels, can quickly adapt to new environments with novel action sets.
title Inter-environmental world modeling for continuous and compositional dynamics
topic Machine Learning
url https://arxiv.org/abs/2503.09911