EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Mutual information oriented deep skill chaining for multi‐agent reinforcement learning

Zaipeng Xie, Cheng Ji, Chentai Qiao, WenZhan Song, Zewen Li, Yufeng Zhang, Yujing Zhang

CAAI Transactions on Intelligence Technology · 2024-08 · 9 (4) · 1014-1030

DOI: 10.1049/cit2.12322 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CAAI Transactions on Intelligence Technology, online erschienen am 28.03.2024. Verfasst von Zaipeng Xie und 6 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi‐agent reinforcement learning relies on reward signals to guide the policy networks of individual agents. However, in high‐dimensional continuous spaces, the non‐stationary environment can provide outdated experiences that hinder convergence, resulting in ineffective training performance for multi‐agent systems. To tackle this issue, a novel reinforcement learning scheme, Mutual Information Oriented Deep Skill Chaining (MioDSC), is proposed that generates an optimised cooperative policy by incorporating intrinsic rewards based on mutual information to improve exploration efficiency. These rewards encourage agents to diversify their learning process by engaging in actions that increase the mutual information between their actions and the environment state. In addition, MioDSC can generate cooperative policies using the options framework, allowing agents to learn and reuse complex action sequences and accelerating the convergence speed of multi‐agent learning. MioDSC was evaluated in the multi‐agent particle environment and the StarCraft multi‐agent challenge at varying difficulty levels. The experimental results demonstrate that MioDSC outperforms state‐of‐the‐art methods and is robust across various multi‐agent system tasks with high stability.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Xie, Z., Ji, C., Qiao, C., Song, W., Li, Z., Zhang, Y., & Zhang, Y. (2024). Mutual information oriented deep skill chaining for multi‐agent reinforcement learning. CAAI Transactions on Intelligence Technology, 9(4), 1014-1030. https://doi.org/10.1049/cit2.12322

Vancouver

Xie Z, Ji C, Qiao C, Song W, Li Z, Zhang Y, et al. Mutual information oriented deep skill chaining for multi‐agent reinforcement learning. CAAI Transactions on Intelligence Technology. 2024;9(4):1014-1030. doi:10.1049/cit2.12322

BibTeX
@article{Xie2024,
  author = {Xie, Zaipeng and Ji, Cheng and Qiao, Chentai and Song, WenZhan and Li, Zewen and Zhang, Yufeng and Zhang, Yujing},
  title = {Mutual information oriented deep skill chaining for multi‐agent reinforcement learning},
  journal = {CAAI Transactions on Intelligence Technology},
  year = {2024},
  volume = {9},
  number = {4},
  pages = {1014--1030},
  doi = {10.1049/cit2.12322}
}
Kostenlos starten →