강화학습 기반의 분산 다중 에이전트 협업 경로 탐색에 관한 연구
A Study of Collaborative and Distributed Multi-agent Path-planning using Reinforcement Learning
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
동적 시스템 환경에서 지능형 협업 자율 시스템을 위한 기계학습 기반의 다양한 방법들이 연구및 개발되고 있다. 본 연구에서는 분산 노드 기반 컴퓨팅 방식의 자율형 다중 에이전트 경로 탐색 방법을 제안하고 있으며, 지능형 학습을 통한 시스템 최적화를 위해 강화학습 방법을 적용하여 다양한 실험을 진행하였다. 강화학습 기반의 다중 에이전트 시스템은 에이전트의 연속된 행동에 따른 누적 보상을 평가하고 이를 학습하여 정책을 개선하는 지능형 최적화 기계학습 방법이다. 본 연구에서 제안한 방법은 강화학습 기반 다중 에이전트 최적화 경로 탐색 성능을 높이기위해 학습 초기 경로 탐색 방법을 개선한 최적화 방법을 제안하고 있다. 또한, 분산된 다중 목표를 구성하여 에이전트간 정보 공유를 이용한 학습 최적화를 시도하였으며, 비동기식 에이전트 경로 탐색 기능을 추가하여 실제 분산 환경 시스템에서 일어날 수 있는 다양한 문제점 및 한계점에대한 솔루션을 제안하고자 한다.
Abstract
In this paper, an autonomous multi-agent path planning using reinforcement learning for monitoring of infrastructures and resources in a computationally distributed system was proposed. Reinforcement-learning-based multi-agent exploratory system in a distributed node enable to evaluate a cumulative reward every action and to provide the optimized knowledge for next available action repeatedly by learning process according to a learning policy. Here, the proposed methods were presented by (a) approach of dynamics-based motion constraints multi-agent path-planning to reduce smaller agent steps toward the given destination(goal), where these agents are able to geographically explore on the environment with initial random-trials versus optimal-trials, (b) approach using agent sub-goal selection to provide more efficient agent exploration(path-planning) to reach the final destination(goal), and (c) approach of reinforcement learning schemes by using the proposed autonomous and asynchronous triggering of agent exploratory phases.
참고문헌 (19)
- D. B. Megherbi, "Multi-Agent Distributed Dynamic Scheduling for Large Distributed Critical Key Infrastructures and Resources(CKIR)Surveillance and Monitoring", Proceeding of IEEE International Conference on Technology for Homeland Security(HST) (2011)
- K. Zhang, "Networked Multi-Agent Reinforcement Learning in Continuous Spaces", Proceeding of 2018 IEEE Conference on Decision and Control (CDC) (2018)
- D. B. Megherbi, "A Distributed Multi-Agent Tracking, awareness, and communication System Architecture for Synchronized Real-Time Situational Understanding, Surveillance, Decision-Making, and Control", Proceeding of IEEE International Conference on Technology for Homeland Security(HST) (2009)
- D. B. Megherbi, "An Intelligent Multi-agent Distributed Battlefield via Multi-Token Message Passing", Proceeding of IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (2009)
- J. Soler, "Towards a Real-Time Multi-Agent System Architecture" (2002), Universidad Politécnica de Valencia
- The Soft Real Time Agent Control Architecture, "B. Horling", UMASS Department of Computer Science, ~, pp.Technical Report WS-02-15 (2002)
- Stuart Russell, "Artificial Intelligence" (2003), Prentice Hall
- Xue Jinlin, "Reinforcement Learning for Engine Idle Speed Control", Proceeding of 2010International Conference on Measuring Technology and Mechatronics Automation (ICMTMA) (2010)
- D. B. Megherbi, "A hybrid P2P and master-slave architecture for intelligent multi-agent reinforcement learning in a distributed computing environment: A case study", Proceeding of IEEE International Conference, Computational Intelligence for Measurement Systems and Applications (CIMSA) (2010)
- M. Madera, "An Interconnected Dynamical System Composed of Dynamics-based Reinforcement Learning Agents in a Distributed Environment: A Case Study", Proceeding of IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (2012)
- W. M. Zuberek, "Performance Limitations of Block-Multithread ed Distributed-Memory System", Proceeding of the Winter Simulation Conference(WSC) (2009)
- M. R Shaker, "Vision-based reinforcement learning using approximate policy iteration", Proceeding of 2009 International Conference (2009)
- J. JIANG, "Multi-task Coalition Parallel Formation Strategy Based on Reinforcement Learning", Acta Automatica Sinica, 34(3), pp.349~352 (2008)
- D. B. Megherbi, "A Collaborative Distributed Multi-Agent Reinforcement Learning Technique for Dynamic Agent Shortest Path Planning via Selected Sub-goals in Complex Cluttered Environments", Proceeding of IEEE Conference, CogSIMA (2015)
- D. B. Megherbi, "A Hybrid Cognitive", Reactive Intelligent Agent Autonomous Path Planning Technique in a Networked-Distributed Unstructured Environment for Reinforcement Learning, 2012, pp.59(3), 1188~1217
- C. Picus, "Boltzmann Machine Topology Learning for Distributed Sensor Networks Using Loopy Belief Propagation Inference. Machine Learning and Applications", Proceeding of 2008th Seventh International Conference, ICMLA (2008)
- D. B. Megherbi, "A Study of Collaborative Distributed Multi-Goal and Multi-agent based Systems for Large Critical Key Infrastructures and Resources (CKIR) Dynamic Monitoring and Surveillance", Proceeding of IEEE International Conference on Technologies for Homeland Security (2013)
- J. Kim, "Imitation Reinforcement Learning-Based Remote Rotary Inverted Pendulum Control in OpenFlow Network", IEEE Access, 7 (2019)
- A. Sharma, "DADS:Unsupervised Reinforcement Learning for Skill Discovery", Google Research at the Google Brain team and the Robotics at Google team, ~ (2020)