Redirigiendo al acceso original de articulo en 16 segundos...
Inicio  /  Applied Sciences  /  Vol: 13 Par: 3 (2023)  /  Artículo
ARTÍCULO
TITULO

Decoupled Monte Carlo Tree Search for Cooperative Multi-Agent Planning

Okan Asik    
Fatma Basak Aydemir and Hüseyin Levent Akin    

Resumen

The number of agents exponentially increases the complexity of a cooperative multi-agent planning problem. Decoupled planning is one of the viable approaches to reduce this complexity. By integrating decoupled planning with Monte Carlo Tree Search, we present a new scalable planning approach. The search tree maintains the updates of the individual actions of each agent separately. However, this separation brings coordination and action synchronization problems. When the agent does not know the action of the other agent, it uses the returned reward to deduce the desirability of its action. When a deterministic action selection policy is used in the Monte Carlo Tree Search algorithm, the actions of agents are synchronized. Of all possible action combinations, only some of them are evaluated. We show the effect of action synchronization on different problems and propose stochastic action selection policies. We also propose a combined method as a pruning step in centralized planning to address the coordination problem in decoupled planning. We create a centralized search tree with a subset of joint actions selected by the evaluation of decoupled planning. We empirically show that decoupled planning has a similar performance compared to a central planning algorithm when stochastic action selection is used in repeated matrix games and multi-agent planning problems. We also show that the combined method improves the performance of the decoupled method in different problems. We compare the proposed method to a decoupled method in regard to a warehouse commissioning problem. Our method achieved more than 10% improvement in performance.

 Artículos similares

       
 
Xi Lyu, Yushan Sun, Lifeng Wang, Jiehui Tan and Liwen Zhang    
This study aims to solve the problems of sparse reward, single policy, and poor environmental adaptability in the local motion planning task of autonomous underwater vehicles (AUVs). We propose a two-layer deep deterministic policy gradient algorithm-bas... ver más

 
Xun Zhang, Ziqi Wang, Huijun Chen and Hao Ding    
The control strategy of an underdriven unmanned underwater vehicle (UUV) equipped with front sonar and actuator faults in a continuous task environment is investigated. Considering trajectory tracking and local path planning in complex-obstacle environme... ver más

 
Zixiao Zhu, Lichuan Zhang, Lu Liu, Dongwei Wu, Shuchang Bai, Ranzhen Ren and Wenlong Geng    
Positioning errors introduced by low-precision navigation devices can affect the overall accuracy of a positioning system. To address this issue, this paper proposes a master-slave multi-AUV collaborative navigation method based on hierarchical reinforce... ver más

 
Xiaoyong Zhang, Wei Yue and Wenbin Tang    
To enhance the anti-submarine and search capabilities of multiple Unmanned Aerial Vehicle (UAV) groups in complex marine environments, this paper proposes a flexible action-evaluation algorithm known as Knowledge-Driven Soft Actor-Critic (KD-SAC), which ... ver más
Revista: Applied Sciences

 
Hao Yang, Kai Bian, Tieji Wang, Zidong Jin, Bo Liu, Hui Sun and Junbin Chang    
In order to effectively prevent and control the problem of water inrush from the through-type fault floor, based on the analysis of the case data of water inrush from the fault structure in the Fengfeng mining area, the types of karst water inrush from t... ver más
Revista: Applied Sciences