Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology Changes

In recent years, the problem of reinforcement learning has become increasingly complex, and the computational demands with respect to such processes have increased. Accordingly, various methods for effective learning have been proposed. With the help of humans, the learning object can learn more acc...

Full description

Bibliographic Details
Main Authors: Jinbae Kim, Hyunsoo Lee
Format: Article
Language:English
Published: MDPI AG 2020-08-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/10/17/5828
_version_ 1797556152925421568
author Jinbae Kim
Hyunsoo Lee
author_facet Jinbae Kim
Hyunsoo Lee
author_sort Jinbae Kim
collection DOAJ
description In recent years, the problem of reinforcement learning has become increasingly complex, and the computational demands with respect to such processes have increased. Accordingly, various methods for effective learning have been proposed. With the help of humans, the learning object can learn more accurately and quickly to maximize the reward. However, the rewards calculated by the system and via human intervention (that make up the learning environment) differ and must be used accordingly. In this paper, we propose a framework for learning the problems of competitive network topologies, wherein the environment dynamically changes agent, by computing the rewards via the system and via human evaluation. The proposed method is adaptively updated with the rewards calculated via human evaluation, making it more stable and reducing the penalty incurred while learning. It also ensures learning accuracy, including rewards generated from complex network topology consisting of multiple agents. The proposed framework contributes to fast training process using multi-agent cooperation. By implementing these methods as software programs, this study performs numerical analysis to demonstrate the effectiveness of the adaptive evaluation framework applied to the competitive network problem depicting the dynamic environmental topology changes proposed herein. As per the numerical experiments, the greater is the human intervention, the better is the learning performance with the proposed framework.
first_indexed 2024-03-10T16:57:54Z
format Article
id doaj.art-467b4cfe3ae34c55a8f6f5fac8f50916
institution Directory Open Access Journal
issn 2076-3417
language English
last_indexed 2024-03-10T16:57:54Z
publishDate 2020-08-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj.art-467b4cfe3ae34c55a8f6f5fac8f509162023-11-20T11:04:14ZengMDPI AGApplied Sciences2076-34172020-08-011017582810.3390/app10175828Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology ChangesJinbae Kim0Hyunsoo Lee1School of Industrial Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaSchool of Industrial Engineering, Kumoh National Institute of Technology, Gumi 39177, KoreaIn recent years, the problem of reinforcement learning has become increasingly complex, and the computational demands with respect to such processes have increased. Accordingly, various methods for effective learning have been proposed. With the help of humans, the learning object can learn more accurately and quickly to maximize the reward. However, the rewards calculated by the system and via human intervention (that make up the learning environment) differ and must be used accordingly. In this paper, we propose a framework for learning the problems of competitive network topologies, wherein the environment dynamically changes agent, by computing the rewards via the system and via human evaluation. The proposed method is adaptively updated with the rewards calculated via human evaluation, making it more stable and reducing the penalty incurred while learning. It also ensures learning accuracy, including rewards generated from complex network topology consisting of multiple agents. The proposed framework contributes to fast training process using multi-agent cooperation. By implementing these methods as software programs, this study performs numerical analysis to demonstrate the effectiveness of the adaptive evaluation framework applied to the competitive network problem depicting the dynamic environmental topology changes proposed herein. As per the numerical experiments, the greater is the human intervention, the better is the learning performance with the proposed framework.https://www.mdpi.com/2076-3417/10/17/5828adaptive algorithmcompetitive network agentdynamically changes networkshuman–machine–agent interactionreinforcement learning
spellingShingle Jinbae Kim
Hyunsoo Lee
Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology Changes
Applied Sciences
adaptive algorithm
competitive network agent
dynamically changes networks
human–machine–agent interaction
reinforcement learning
title Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology Changes
title_full Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology Changes
title_fullStr Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology Changes
title_full_unstemmed Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology Changes
title_short Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology Changes
title_sort cooperative multi agent interaction and evaluation framework considering competitive networks with dynamic topology changes
topic adaptive algorithm
competitive network agent
dynamically changes networks
human–machine–agent interaction
reinforcement learning
url https://www.mdpi.com/2076-3417/10/17/5828
work_keys_str_mv AT jinbaekim cooperativemultiagentinteractionandevaluationframeworkconsideringcompetitivenetworkswithdynamictopologychanges
AT hyunsoolee cooperativemultiagentinteractionandevaluationframeworkconsideringcompetitivenetworkswithdynamictopologychanges