ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article 멀티 에이전트 강화학습 기술 동향
Cited - time in scopus Download 278 time Share share facebook twitter linkedin kakaostory
Authors
유병현, 데브라니 데비, 김현우, 송화전, 박경문, 이성원
Issue Date
2020-12
Citation
전자통신동향분석, v.35, no.6, pp.137-149
ISSN
1225-6455
Publisher
한국전자통신연구원
Language
Korean
Type
Journal Article
DOI
https://dx.doi.org/10.22648/ETRI.2020.J.350614
Abstract
Several multi-agent reinforcement learning (MARL) algorithms have achieved overwhelming results in recent years. They have demonstrated their potential in solving complex problems in the field of real-time strategy online games, robotics, and autonomous vehicles. However these algorithms face many challenges when dealing with massive problem spaces in sparse reward environments. Based on the centralized training and decentralized execution (CTDE) architecture, the MARL algorithms discussed in the literature aim to solve the current challenges by formulating novel concepts of inter-agent modeling, credit assignment, multiagent communication, and the exploration-exploitation dilemma. The fundamental objective of this paper is to deliver a comprehensive survey of existing MARL algorithms based on the problem statements rather than on the technologies. We also discuss several experimental frameworks to provide insight into the use of these algorithms and to motivate some promising directions for future research.
KSP Keywords
Autonomous vehicle, Credit assignment, Experimental Frameworks, Exploration-exploitation dilemma, Novel concepts, Real-time strategy, Reinforcement Learning(RL), agent modeling, complex problems, multi-agent reinforcement learning, online games
This work is distributed under the term of Korea Open Government License (KOGL)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
Type 4: