Multi-World Model in Continual Reinforcement Learning

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.

Cite

Text

Shen. "Multi-World Model in Continual Reinforcement Learning." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30555

Markdown

[Shen. "Multi-World Model in Continual Reinforcement Learning." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/shen2024aaai-multi/) doi:10.1609/AAAI.V38I21.30555

BibTeX

@inproceedings{shen2024aaai-multi,
  title     = {{Multi-World Model in Continual Reinforcement Learning}},
  author    = {Shen, Kevin},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23757-23759},
  doi       = {10.1609/AAAI.V38I21.30555},
  url       = {https://mlanthology.org/aaai/2024/shen2024aaai-multi/}
}