A Multi-Agent Centralized Strategy Gradient Reinforcement Learning Algorithm Based on State Transition

The prevalent utilization of deterministic strategy algorithms in Multi-Agent Deep Reinforcement Learning (MADRL) for collaborative tasks has posed a significant challenge in achieving stable and high-performance cooperative behavior. Addressing the need for the balanced exploration and exploitation...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Algorithms Ročník 17; číslo 12; s. 579
Hlavní autori:	Sheng, Lei, Chen, Honghui, Chen, Xiliang
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Basel MDPI AG 01.12.2024
Predmet:	Actors Actresses Algorithms automatic representation Automation Collaborative learning Control simulation Control stability Cooperation Cooperative control Critics Data mining Deep learning deterministic strategy gradient algorithm Efficiency Exploitation exploration Learning strategies Machine learning multi-agent reinforcement learning Multiagent systems Network reliability Representations Robot control Robots state transition
ISSN:	1999-4893, 1999-4893
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!