Advanced Double Layered Multi-Agent Systems Based on A3C in Real-Time Path Planning
In this paper, we propose an advanced double layered multi-agent system to reduce learning time, expressing a state space using a 2D grid. This system is based on asynchronous advantage actor-critic systems (A3C) and reduces the state space that agents need to consider by hierarchically expressing a...
Main Authors: | Dajeong Lee, Junoh Kim, Kyungeun Cho, Yunsick Sung |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/10/22/2762 |
Similar Items
-
Learning Macromanagement in Starcraft by Deep Reinforcement Learning
by: Wenzhen Huang, et al.
Published: (2021-05-01) -
A Penetration Method for UAV Based on Distributed Reinforcement Learning and Demonstrations
by: Kexv Li, et al.
Published: (2023-03-01) -
A new noise network and gradient parallelisation‐based asynchronous advantage actor‐critic algorithm
by: Zhengshun Fei, et al.
Published: (2022-09-01) -
Application of Improved Asynchronous Advantage Actor Critic Reinforcement Learning Model on Anomaly Detection
by: Kun Zhou, et al.
Published: (2021-02-01) -
Distributed Multi-Agent Approach for Achieving Energy Efficiency and Computational Offloading in MECNs Using Asynchronous Advantage Actor-Critic
by: Israr Khan, et al.
Published: (2023-11-01)