nach oben

Erschienen in:

2018 | OriginalPaper | Buchkapitel

Building Collaboration in Multi-agent Systems Using Reinforcement Learning

verfasst von : Mehmet Emin Aydin, Ryan Fellows

Erschienen in: Computational Collective Intelligence

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

This paper presents a proof-of concept study for demonstrating the viability of building collaboration among multiple agents through standard Q learning algorithm embedded in particle swarm optimisation. Collaboration is formulated to be achieved among the agents via competition, where the agents are expected to balance their action in such a way that none of them drifts away of the team and none intervene any fellow neighbours territory, either. Particles are devised with Q learning for self training to learn how to act as members of a swarm and how to produce collaborative/collective behaviours. The produced experimental results are supportive to the proposed idea suggesting that a substantive collaboration can be build via proposed learning algorithm.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Cluster-Based Instance Selection for the Imbalanced Data Classification

Nächstes Kapitel The Shapley Value for Multigraphs

Ayhan, M.B., Aydin, M.E., Oztemel, E.: A multi-agent based approach for change management in manufacturing enterprises. J. Intell. Manuf. 26(5), 975–988 (2015)CrossRef

Aydin, M.E., Fellows, R.: A reinforcement learning algorithm for building collaboration in multi-agent systems. arXiv preprint arXiv:1711.10574 (2017)

Aydin, M.E., Bessis, N., Asimakopoulou, E., Xhafa, F., Wu, J.: Scanning environments with swarms of learning birds: a computational intelligence approach for managing disasters. In: IEEE International Conference on Advanced Information Networking and Applications (AINA), pp. 332–339 (2011)

Aydin, M.E.: Coordinating metaheuristic agents with swarm intelligence. J. Intell. Manuf. 23(4), 991–999 (2012)CrossRef

Aydin, M.E., Kwan, R., Leung, C., Zhang, J.: Multiuser scheduling in HSDPA with particle swarm optimization. In: Giacobini, M., et al. (eds.) EvoWorkshops 2009. LNCS, vol. 5484, pp. 71–80. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-01129-0_8CrossRef

Aydin, M.E.: Metaheuristic agent teams for job shop scheduling problems. In: Mařík, V., Vyatkin, V., Colombo, A.W. (eds.) HoloMAS 2007. LNCS (LNAI), vol. 4659, pp. 185–194. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74481-8_18CrossRef

Bradtke, J., Barto, A.G.: Linear least-squares algorithms for temporal difference learning. Mach. Learn. 22(1–3), 33–57 (1996)MATH

Bull, L.: Two simple learning classifier systems. In: Bull, L., Kovacs, T. (eds.) Foundations of Learning Classifier Systems. STUDFUZZ, vol. 183, pp. 63–89. Springer, Heidelberg (2005). https://doi.org/10.1007/11319122_4CrossRefMATH

Bull, L., Kovacs, T.: Foundations of Learning Classier Systems, vol. 183. Springer, Heidelberg (2005). https://doi.org/10.1007/b100387CrossRefMATH

10.

Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of National Conference on Artificial Intelligence (AAAI 1998), pp. 746–752 (1998)

11.

Colorni, A., Dorigo, M., Maniezzo, V., Trubian, M.: Ant system for job-shop scheduling. Belgian J. Oper. Res. Stat. Comput. Sci. (JORBEL) 34(1), 39–53 (1994)MATH

12.

Dong, X.: Consensus control of swarm systems. In: Dong, X. (ed.) Formation and Containment Control for High-order Linear Swarm Systems. Springer Theses, pp. 33–51. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-662-47836-3_3CrossRefMATH

13.

Eberhart, R., Kennedy, J.: A new optimizer using particle swarm theory. In: Proceedings of the 6th International Symposium on Micro-Machine and Human Science, pp. 39–43 (1995)

14.

Foerster, J., Assael, Y.M., de Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2137–2145 (2016)

15.

Gath, M.: Optimizing Transport Logistics Processes with Multiagent Planning and Control. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-658-14003-8. Ph.D. thesisCrossRef

16.

Hercog, L.M.: Better manufacturing process organization using multi-agent self-organization and co-evolutionary classifier systems: the multibar problem. Appl. Soft Comput. 13(3), 1407–1418 (2013)CrossRef

17.

Iima, H., Kuroe, Y.: Swarm reinforcement learning algorithm based on particle swarm optimization whose personal bests have lifespans. In: Leung, C.S., Lee, M., Chan, J.H. (eds.) ICONIP 2009. LNCS, vol. 5864, pp. 169–178. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-10684-2_19CrossRef

18.

Kazemi, A., Zarandi, M.F., Husseini, S.M.: A multi-agent system to solve the production-distribution planning problem for a supply chain: a genetic algorithm approach. Int. J. Adv. Manuf. Technol. 44(1–2), 180–193 (2009)CrossRef

19.

Kennedy, J., Eberhart, R.C.: A discrete binary version of the particle swarm algorithm. In: 1997 IEEE International Conference on Systems, Man, and Cybernetics, Computational Cybernetics and Simulation, Orlando, FL, pp. 4104–4108 (1997)

20.

Kennedy, J., Eberhart, R., Shi, Y.: Swarm Intelligence. Morgan Kaufmann, San Mateo (2001)

21.

Kok, J.R., Vlassis, N.: Sparse cooperative q-learning. In: Proceedings of the International Conference on Machine Learning, pp. 481–488. ACM (2004)

22.

Kolp, M., Giorgini, P., Mylopoulos, J.: Multi-agent architectures as organizational structures. Auton. Agents Multi-agent Syst. 13, 3–25 (2006)CrossRef

23.

Kouider, A., Bouzouia, B.: Multi-agent job shop scheduling system based on co-operative approach of idle time minimisation. Int. J. Prod. Res. 50(2), 409–424 (2012)CrossRef

24.

Meng, Y.: Q-learning adjusted bio-inspired multi-robot coordination. In: Recent Advances in Multi-Robot Systems, pp. 139–152. I-Tech Education and Publishing (2008)

25.

Mohebbi, S., Shafaei, R.: E-supply network coordination: the design of intelligent agents for buyer-supplier dynamic negotiations. J. Intell. Manuf. 23, 375–391 (2012)CrossRef

26.

Panait, L., Luke, S.: Cooperative multi-agent learning: the state of the art. Auton. Agents. Multi-agent Syst. 11(3), 387–434 (2005)CrossRef

27.

Poli, R., Kennedy, J., Blackwell, T.: Particle swarm optimization. Swarm Intell. 1, 33–57 (2007)CrossRef

28.

Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)

29.

Tasgetiren, M., Liang, Y., Sevkli, M., Gencyilmaz, G.: Particle swarm optimization algorithm for makespan and total flow-time minimization in permutation flow-shop sequencing problem. Eur. J. Oper. Res. 177(3), 1930–1947 (2007)CrossRef

30.

Tesauro, G.: Practical issues in temporal difference learning. Mach. Learn. 8(3–4), 257–277 (1992)MATH

31.

Tsitsiklis, J.N., Sutton, R.: Asynchronous stochastic approximation and Q-learning. Mach. Learn. 16(3), 185–202 (1994)MATH

32.

Vazquez-Salceda, J., Dignum, V., Dignum, F.: Organizing multi-agent systems. Auton. Agents Multi-agent Syst. 11, 307–360 (2005)CrossRef

33.

Watkins, C.: Learning from delayed rewards. Ph.D. thesis, Cambridge University (1989)

34.

Watkins, C., Dayan, P.: Technical note: Q-learning. Mach. Learn. 8, 279–292 (1992)MATH

35.

Wilensky, U., Rand, W.: An Introduction to Agent-based Modeling: Modeling Natural, Social and Engineered Complex Systems with NetLogo. MIT Press, Cambridge (2015)

Titel: Building Collaboration in Multi-agent Systems Using Reinforcement Learning
verfasst von: Mehmet Emin Aydin
Ryan Fellows
Verlag: Springer International Publishing
Buch: Computational Collective Intelligence
Print ISBN: 978-3-319-98445-2

Electronic ISBN: 978-3-319-98446-9

Copyright-Jahr: 2018
DOI: https://doi.org/10.1007/978-3-319-98446-9_19

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner