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.
@article{arxiv.2411.01342,
title = {Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity},
author = {Emiliyan Gospodinov and Vaisakh Shaj and Philipp Becker and Stefan Geyer and Gerhard Neumann},
journal= {arXiv preprint arXiv:2411.01342},
year = {2024}
}
Comments
Accepted at NeurIPS 2024 Workshop Adaptive Foundation Models