AAAI 2024technical1 citations

Multi-world Model in Continual Reinforcement Learning

Kevin Shen

Abstract

World Models are made of generative networks that can predict future states of a single environment which it was trained on. This research proposes a Multi-world Model, a foundational model built from World Models for the field of continual reinforcement learning that is trained on many different environments, enabling it to generalize state sequence predictions even for unseen settings.

BibTeX
@article{Shen_2024, title={Multi-world Model in Continual Reinforcement Learning}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30555}, DOI={10.1609/aaai.v38i21.30555}, abstractNote={World Models are made of generative networks that can predict future states of a single environment which it was trained on. This research proposes a Multi-world Model, a foundational model built from World Models for the field of continual reinforcement learning that is trained on many different environments, enabling it to generalize state sequence predictions even for unseen settings.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Shen, Kevin}, year={2024}, month={Mar.}, pages={23757-23759} }