arrow
返回

Multi-agent behavioral control system using deep reinforcement learning

delete2019-09-01
delete22
PRE
AI
N
Ngoc Duy Nguyen
T
Thanh Thi Nguyen *
S
Saeid Nahavandi
DOI:10.1016/j.neucom.2019.05.062delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
Deep reinforcement learning (DRL) has emerged as the dominant approach to achieving successive advancements in the creation of human-wise agents. By leveraging neural networks as decision-making controllers, DRL supplements traditional reinforcement methods to address the curse of dimensionality in complicated tasks. However, agents in complicated environments are likely to get stuck in sub-optimal solutions. In such cases, the agent inadvertently turns into a zombie owing to its short-term vision and harmful behaviors. In this study, we use human learning strategies to adjust agent behaviors in high-dimensional environments. Therefore, the agent behaves predictably and succeeds in attaining its designated goal. In summary, the contribution of this study is two-fold. First, we introduce a lightweight workflow that enables a nonexpert to preserve a certain level of safety in AI systems. Specifically, the workflow involves a novel concept of a target map and a multi-agent behavioral control system named Multi-Policy Control System (MPCS). MPCS successfully controls agent behaviors in real time without involving the burden of human feedback. Second, we develop a multi-agent game named Tank Battle that provides a configurable environment to examine agent behaviors and human-agent interactions in DRL. Finally, simulation results show that agents guided by MPCS outperform agents that do not use MPCS with respect to the mean of total rewards and human-like behaviors in complicated environments such as Seaquest and Tank Battle. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Multi-agent system
Reinforcement learning
Deep learning
Robotics
Human control
Autonomous system
Human-machine interaction
Agent behavior
Neural network
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Neurocomputing 封面图
Neurocomputing
IF:
6.5
论文数:
2.5W
被引数:
8.4W

机构

D
Deakin University
学者数:
1.1K
论文数: 502
被引数: 1.6W
引用论文

引用论文

Complexity of D″ in the presence of slab‐debris and phase changes
err2006-03-04
err0
errOAAI
errDaoyuan Sun; Teh‐Ru Alex Song; Don Helmberger
err分享
err收藏
err分享
err收藏
Salient material properties and haptic volume perception: The influences of surface texture, thermal conductivity, and compliance
err2012-09-13
err0
PREAI
errWouter M. Bergmann Tiest; Mirela Kahrimanovic; Ilona Niemantsverdriet; Kassahun Bogale; Astrid M. L. Kappers
err分享
err收藏
没有更多内容