지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2023.11
- 수록면
- 847 - 853 (7page)
- DOI
- 10.5302/J.ICROS.2023.23.0129
이용수
초록· 키워드
오류제보하기
An environment is a complex space in which numerous agents and objects interact. In this environment, rational agents act to maximize utility, and their actions are learned through reinforcement learning algorithms using deep neural networks. Since most environments are non-stationary, a single agent cannot solely achieve maximum utility through its observations and inferences using a network. However, when multiple agents can communicate with each other, a single agent can access richer information about the state of the environment simply by receiving messages from other agents. Nonetheless, the inferred information from other agents is generated by a neural network, which can be vulnerable or incorporate the personal perspective of the agents processing the information. For example, even when presented with a single observation, two agents can encode significantly different messages due to variations in their parameter modules. Therefore, it is crucial to consider the subjectivity of messages in multi-agent reinforcement learning (MARL). Building on the assumption that the encoded information is inherently subjective and reflects the agent that encodes it, we address the challenge of objective and subjective information in MARL. One limitation is that the information processed by a neural network is often challenging to interpret. In the initial phases of addressing this subjectivity concern, we focus on a relatively minor challenge: determining whether subjective information surpasses objective information in utility. Consequently, we compare the usefulness of messages exchanged between agents in two forms: raw observation and the output of a neural network.
목차
Abstract
I. 서론
II. 다중 에이전트 강화학습
III. 정보의 주관성
IV. 게이트 기반 메시지 교환
V. 다중 에이전트 메시지 교환
VI. 논의
VII. 결론
REFERENCES
참고문헌 (24)
참고문헌 신청
S. G. Park and D. H. Kim, “Autonomous flying of drone based on PPO reinforcement learning algorithm," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 26, no. 11, pp. 955-963, 2020. doi: 10.5302/J.ICROS.2020.20.0125
K.-S. Kim, J.-H. Moon, D.-K. Kim, S.-b. Jo, and J.-M. Lee, “Natural behavior learning based on deep reinforcement learning for autonomous navigation of mobile robots," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 24, no. 3, pp.
B. Park, C. Kang, and J. Choi, “Cooperative multi-robot task allocation with reinforcement learning," Applied Sciences, vol. 12, no. 1, pp. 272, 2022. doi: https://doi.org/10.3390/app12010272
G. Brockman, V. Cheung, L. Pettersson, J. Schneider, J. Schulman, J. Tang, and W. Zaremba, “Openai gym," arXiv preprint arXiv:1606.01540, 2016.
V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, “Playing atari with deep reinforcement learning," arXiv preprint arXiv:1312.5602, 2013.
K.-S. Kim, J.-H. Moon, D.-K. Kim, S.-b. Jo, and J.-M. Lee, “Natural behavior learning based on deep reinforcement learning for autonomous navigation of mobile robots," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 24, no. 3, pp.
B. Park, C. Kang, and J. Choi, “Cooperative multi-robot task allocation with reinforcement learning," Applied Sciences, vol. 12, no. 1, pp. 272, 2022. doi: https://doi.org/10.3390/app12010272
G. Brockman, V. Cheung, L. Pettersson, J. Schneider, J. Schulman, J. Tang, and W. Zaremba, “Openai gym," arXiv preprint arXiv:1606.01540, 2016.
V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, “Playing atari with deep reinforcement learning," arXiv preprint arXiv:1312.5602, 2013.
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Generating Multi-agent Patrol Areas by Reinforcement Learning
제어로봇시스템학회 국제학술대회 논문집
2021 .10
-
Consensus speed of multi-agent systems driven by simultaneously fair value exchange
제어로봇시스템학회 국제학술대회 논문집
2024 .10
-
Meta Multi-agent Reinforcement Learning for UAVs-aided IoT Networks: Initial Work
한국통신학회 학술대회논문집
2022 .02
-
3가 티타늄을 환원제로 하는 무전해 주석도금
한국표면공학회 학술발표회 초록집
2016 .05
-
Multi-agent Reinforcement Learning in a Large Scale Environment via Supervisory Network and Curriculum Learning
제어로봇시스템학회 국제학술대회 논문집
2021 .10
-
멀티 에이전트 강화학습에서 행동-관측 통신데이터의 영향
제어로봇시스템학회 국내학술대회 논문집
2023 .06
-
Flocking Control for Multiple Polygonal Agents with Limited Communication Ranges
전기학회논문지
2019 .07
-
Decentralized Multi-Agent Reinforcement Learning Exploration with Inter-Agent Communication-Based Action Space
제어로봇시스템학회 국제학술대회 논문집
2024 .10
-
Attention-Based Randomized Ensemble Multi-Agent Q-Learning
제어로봇시스템학회 국제학술대회 논문집
2023 .10
-
Autonomous Drone Surveillance in a Known Environment Using Reinforcement Learning
제어로봇시스템학회 국제학술대회 논문집
2022 .11
-
강화 학습 기반의 지능형 에이전트 설계 및 구현
Proceedings of KIIT Conference
2022 .12
-
강화 학습 에이전트의 개성 부여를 유도하는 내재적 보상 방법 연구
대한전자공학회 학술대회
2022 .06
-
A Study of Collaborative and Distributed Multi-agent Path-planning using Reinforcement Learning
한국컴퓨터정보학회논문지
2021 .03
-
Distributed Estimation of the Geometric Center of Multi-target by a Group of Agents With Bearing Measurements
제어로봇시스템학회 논문지
2023 .11
-
Adaptive and optimized agent placement scheme for parallel agent-based simulation
[ETRI] ETRI Journal
2022 .04
-
Crowd Simulation Based on Statistical Analysis of Surveillance Video
한국방송미디어공학회 학술발표대회 논문집
2024 .11
-
Comparison of Multi-Agent Reinforcement Learning Algorithms in Cooperative Grid Environments
한국정보과학회 학술발표논문집
2024 .06
-
Multi-agent system의 Consensus에 대해 알아보자
제어로봇시스템학회지
2019 .12
-
그래프 어텐션 기반 에이전트 상호작용을 고려한 경로 예측
한국자동차공학회 춘계학술대회
2021 .06
-
Learning to Box: Reinforcement Learning using Heuristic Three-step Curriculum Learning
제어로봇시스템학회 국제학술대회 논문집
2022 .11
이 논문의 저자 정보
이 논문과 함께 이용한 논문
항공우주분야 디지털 트윈 기술동향
김명언
항공우주산업기술동향
2023
.12
에이전트 기반 시뮬레이션 모델링 기법을 활용한 스마트팩토리 디지털 트윈 개발
박지민
,
김민정
,
신문수
대한산업공학회 추계학술대회 논문집
2023
.11
멀티 에이전트 강화학습을 활용한 유무인 협업 임무 수행 연구
송진안
,
최기영
한국항공우주학회지
2023
.09
멀티 에이전트 강화학습에서 행동-관측 통신데이터의 영향
오다현
,
김현진
제어로봇시스템학회 국내학술대회 논문집
2023
.06
항만 물류 환경에서 다중 에이전트 강화학습 기반 최적 배차 모델링 방법
이효준
,
장우석
,
이성진
외 1명
한국정보기술학회논문지
2023
.06
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-151-24-02-088336050