Saved in:
Bibliographic Details
Main Authors: Gospodinov, Emiliyan, Shaj, Vaisakh, Becker, Philipp, Geyer, Stefan, Neumann, Gerhard
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.01342
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915003203846144
author Gospodinov, Emiliyan
Shaj, Vaisakh
Becker, Philipp
Geyer, Stefan
Neumann, Gerhard
author_facet Gospodinov, Emiliyan
Shaj, Vaisakh
Becker, Philipp
Geyer, Stefan
Neumann, Gerhard
contents Developing foundational world models is a key research direction for embodied intelligence, with the ability to adapt to non-stationary environments being a crucial criterion. In this work, we introduce a new formalism, Hidden Parameter-POMDP, designed for control with adaptive world models. We demonstrate that this approach enables learning robust behaviors across a variety of non-stationary RL benchmarks. Additionally, this formalism effectively learns task abstractions in an unsupervised manner, resulting in structured, task-aware latent spaces.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01342
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity
Gospodinov, Emiliyan
Shaj, Vaisakh
Becker, Philipp
Geyer, Stefan
Neumann, Gerhard
Machine Learning
Artificial Intelligence
Developing foundational world models is a key research direction for embodied intelligence, with the ability to adapt to non-stationary environments being a crucial criterion. In this work, we introduce a new formalism, Hidden Parameter-POMDP, designed for control with adaptive world models. We demonstrate that this approach enables learning robust behaviors across a variety of non-stationary RL benchmarks. Additionally, this formalism effectively learns task abstractions in an unsupervised manner, resulting in structured, task-aware latent spaces.
title Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.01342