EUVIMEDEUVIMED entdecken
Crossref

GLAM: Global-Local Variation Awareness in Mamba-based World Model

Qian He, Wenqi Liang, Chunhui Hao, Gan Sun, Jiandong Tian

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (16) · 17105-17113

DOI: 10.1609/aaai.v39i16.33880 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Qian He und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mimicking the real interaction trajectory in the inference of the world model has been shown to improve the sample efficiency of model-based reinforcement learning (MBRL) algorithms. Many methods directly use known state sequences for reasoning. However, this approach fails to enhance the quality of reasoning by capturing the subtle variation between states. Much like how humans infer trends in event development from this variation, in this work, we introduce Global-Local variation Awareness Mamba-based world model (GLAM) that improves reasoning quality by perceiving and predicting variation between states. GLAM comprises two Mamba-based parallel reasoning modules, GMamba and LMamba, which focus on perceiving variation from global and local perspectives, respectively, during the reasoning process. GMamba focuses on identifying patterns of variation between states in the input sequence and leverages these patterns to enhance the prediction of future state variation. LMamba emphasizes reasoning about unknown information, such as rewards, termination signals, and visual representations, by perceiving variation in adjacent states. By integrating the strengths of the two modules, GLAM accounts for higher-value variation in environmental changes, providing the agent with more efficient imagination-based training. We demonstrate that our method outperforms existing methods in normalized human scores on the Atari 100k benchmark.

Zitieren

APA

He, Q., Liang, W., Hao, C., Sun, G., & Tian, J. (2025). GLAM: Global-Local Variation Awareness in Mamba-based World Model. Proceedings of the AAAI Conference on Artificial Intelligence, 39(16), 17105-17113. https://doi.org/10.1609/aaai.v39i16.33880

Vancouver

He Q, Liang W, Hao C, Sun G, Tian J. GLAM: Global-Local Variation Awareness in Mamba-based World Model. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(16):17105-17113. doi:10.1609/aaai.v39i16.33880

BibTeX
@article{He2025,
  author = {He, Qian and Liang, Wenqi and Hao, Chunhui and Sun, Gan and Tian, Jiandong},
  title = {GLAM: Global-Local Variation Awareness in Mamba-based World Model},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {16},
  pages = {17105--17113},
  doi = {10.1609/aaai.v39i16.33880}
}
Kostenlos starten →