Inicio  /  Future Internet  /  Vol: 14 Par: 1 (2022)  /  Artículo
ARTÍCULO
TITULO

The Important Role of Global State for Multi-Agent Reinforcement Learning

Shuailong Li    
Wei Zhang    
Yuquan Leng and Xiaohui Wang    

Resumen

Environmental information plays an important role in deep reinforcement learning (DRL). However, many algorithms do not pay much attention to environmental information. In multi-agent reinforcement learning decision-making, because agents need to make decisions combined with the information of other agents in the environment, this makes the environmental information more important. To prove the importance of environmental information, we added environmental information to the algorithm. We evaluated many algorithms on a challenging set of StarCraft II micromanagement tasks. Compared with the original algorithm, the standard deviation (except for the VDN algorithm) was smaller than that of the original algorithm, which shows that our algorithm has better stability. The average score of our algorithm was higher than that of the original algorithm (except for VDN and COMA), which shows that our work significantly outperforms existing multi-agent RL methods.

 Artículos similares

       
 
Yunshuai Li, Xinyuan Shao, Zhixiang Wu, Zhongyi Sun, Mingzhe Li, Lingxiu Jiang, Yuanhong Xian and Peng Wang    
Land surface temperature plays an important role in the water cycle and surface energy balance. Using data collected by a vorticity covariance tower from 2010 to 2022, the relative threshold method and TRM method were employed to study the land?atmospher... ver más
Revista: Water

 
Davy Preuveneers and Wouter Joosen    
Ontologies have the potential to play an important role in the cybersecurity landscape as they are able to provide a structured and standardized way to semantically represent and organize knowledge about a domain of interest. They help in unambiguously m... ver más
Revista: Future Internet

 
Wenjie Zhen, Shifang Huang, Zhihui Tian and Xiaoyue Yang    
Tourist maps provide tourists with destination information that reflects their unique characteristics and cultural connotations and play an important role in attracting tourists and serving marketing purposes. However, existing designs of tourist maps of... ver más

 
Frédéric Leroux, Mickaël Germain, Étienne Clabaut, Yacine Bouroubi and Tony St-Pierre    
Digital twins are increasingly gaining popularity as a method for simulating intricate natural and urban environments, with the precise segmentation of 3D objects playing an important role. This study focuses on developing a methodology for extracting bu... ver más

 
Serge Riazanoff, Axel Corseaux, Clément Albinet, Peter A. Strobl, Carlos López-Vázquez, Peter L. Guth and Takeo Tadono    
In recent decades, an important number of regional and global digital elevation models (DEMs) have been released publicly. As a consequence, researchers need to choose between several of these models to perform their studies and to use these DEMs as thir... ver más