Skip to main content

2015 | OriginalPaper | Buchkapitel

Team Search Tactics Through Multi-Agent HyperNEAT

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

search-config
loading …

Abstract

User defined tactics for teams of unmanned systems can be brittle and difficult to define. The state and action space grows with each new system added to the team which increases the difficultly in designing robust behaviors. In this paper we present a method for using Multi-agent HyperNEAT to develop tactics for a team of simulated unmanned systems that is robust to novel situations, and scales with the number of team members. We focus on the tactics of a search area coverage task, where the need for team work, and robust asset management are critical to success.

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!

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!

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!

Literatur
1.
Zurück zum Zitat Aaltonen, T., Adelman, J., Akimoto, T., Albrow, M.G., González, B.Á., Amerio, S., Amidei, D., Anastassov, A.: Measurement of the top-quark mass with dilepton events selected using neuroevolution at CDF. Phys. Rev. Lett. 102, 152001 (2009)CrossRef Aaltonen, T., Adelman, J., Akimoto, T., Albrow, M.G., González, B.Á., Amerio, S., Amidei, D., Anastassov, A.: Measurement of the top-quark mass with dilepton events selected using neuroevolution at CDF. Phys. Rev. Lett. 102, 152001 (2009)CrossRef
2.
Zurück zum Zitat Cardamone, L., Loiacono, D., Lanzi, P.L.: Learning to drive in the open racing car simulator using online neuroevolution. IEEE Trans. Comput. Intell. AI Games 2, 176–190 (2010)CrossRef Cardamone, L., Loiacono, D., Lanzi, P.L.: Learning to drive in the open racing car simulator using online neuroevolution. IEEE Trans. Comput. Intell. AI Games 2, 176–190 (2010)CrossRef
4.
Zurück zum Zitat D’Ambrosio, D.B., Lehman, J., Risi, S., Stanley, K.O.: Evolving policy geometry for scalable multiagent learning. In: Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), pp. 731–738 (2010) D’Ambrosio, D.B., Lehman, J., Risi, S., Stanley, K.O.: Evolving policy geometry for scalable multiagent learning. In: Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), pp. 731–738 (2010)
5.
Zurück zum Zitat D’Ambrosio, D.B., Stanley, K.O.: Generative encoding for multiagent learning. In: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation GECCO 2008, vol. 2008, p. 819 (2008) D’Ambrosio, D.B., Stanley, K.O.: Generative encoding for multiagent learning. In: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation GECCO 2008, vol. 2008, p. 819 (2008)
6.
Zurück zum Zitat Dragoni, A.F., Giorgini, P.: Belief revision through the belief-function formalism in a multi-agent environment. In: Müller, J.P., Wooldridge, M.J., Jennings, N.R. (eds.) Intelligent Agents III Agent Theories, Architectures, and Languages. LNCS, vol. 1193, pp. 103–115. Springer, Heidelberg (1997)CrossRef Dragoni, A.F., Giorgini, P.: Belief revision through the belief-function formalism in a multi-agent environment. In: Müller, J.P., Wooldridge, M.J., Jennings, N.R. (eds.) Intelligent Agents III Agent Theories, Architectures, and Languages. LNCS, vol. 1193, pp. 103–115. Springer, Heidelberg (1997)CrossRef
7.
Zurück zum Zitat D’Ambrosio, D.B., Stanley, K.O.: Scalable multiagent learning through indirect encoding of policy geometry. Evol. Intel. 6(1), 1–26 (2013)CrossRef D’Ambrosio, D.B., Stanley, K.O.: Scalable multiagent learning through indirect encoding of policy geometry. Evol. Intel. 6(1), 1–26 (2013)CrossRef
8.
Zurück zum Zitat Friedrich, H., Rogalla, O., Dillmann, R.: Communication and propagation of action knowledge in multi-agent systems. Robot. Auton. Syst. 29(1), 41–50 (1999)CrossRef Friedrich, H., Rogalla, O., Dillmann, R.: Communication and propagation of action knowledge in multi-agent systems. Robot. Auton. Syst. 29(1), 41–50 (1999)CrossRef
9.
Zurück zum Zitat Garland, A., Alterman, R.: Preparation of multi-agent knowledge for reuse. In: Proceedings of the Fall Symposium on Adaptation of Knowledge for Reuse, vol. 26, p. 33 (1995) Garland, A., Alterman, R.: Preparation of multi-agent knowledge for reuse. In: Proceedings of the Fall Symposium on Adaptation of Knowledge for Reuse, vol. 26, p. 33 (1995)
10.
Zurück zum Zitat Gauci, J., Stanley, K.O.: Autonomous evolution of topographic regularities in artificial neural networks. Neural Comput. 22, 1860–1898 (2010)CrossRefMATH Gauci, J., Stanley, K.O.: Autonomous evolution of topographic regularities in artificial neural networks. Neural Comput. 22, 1860–1898 (2010)CrossRefMATH
11.
Zurück zum Zitat Gauci, J., Stanley, K.: A case study on the critical role of geometric regularity in machine learning. In: AAAI, pp. 628–633 (2008) Gauci, J., Stanley, K.: A case study on the critical role of geometric regularity in machine learning. In: AAAI, pp. 628–633 (2008)
12.
Zurück zum Zitat Le Pape, C.: A combination of centralized and distributed methods for multi-agent planning and scheduling. In: Proceedings of the 1990 IEEE International Conference on Robotics and Automation, pp. 488–493. IEEE (1990) Le Pape, C.: A combination of centralized and distributed methods for multi-agent planning and scheduling. In: Proceedings of the 1990 IEEE International Conference on Robotics and Automation, pp. 488–493. IEEE (1990)
13.
Zurück zum Zitat Panait, L., Luke, S.: Cooperative multi-agent learning: the state of the art. Auton. Agent. Multi Agent Syst. 11(3), 387–434 (2005)CrossRef Panait, L., Luke, S.: Cooperative multi-agent learning: the state of the art. Auton. Agent. Multi Agent Syst. 11(3), 387–434 (2005)CrossRef
14.
Zurück zum Zitat Pugh, J.K., Goodell, S., Stanley, K.O.: Directional communication in evolved multiagent teams. Technical report, University of Central Florida, Orlando, FL (2013) Pugh, J.K., Goodell, S., Stanley, K.O.: Directional communication in evolved multiagent teams. Technical report, University of Central Florida, Orlando, FL (2013)
15.
Zurück zum Zitat Sen, S., Weiss, G.: Learning in multiagent systems. In: Weiss, G. (ed.) Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence, Chap. 6, pp. 259–298. The MIT Press, Cambridge (1999) Sen, S., Weiss, G.: Learning in multiagent systems. In: Weiss, G. (ed.) Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence, Chap. 6, pp. 259–298. The MIT Press, Cambridge (1999)
16.
Zurück zum Zitat Stanley, K.O.: Compositional pattern producing networks: a novel abstraction of development. Genet. Program Evolvable Mach. 8, 131–162 (2007)CrossRef Stanley, K.O.: Compositional pattern producing networks: a novel abstraction of development. Genet. Program Evolvable Mach. 8, 131–162 (2007)CrossRef
17.
Zurück zum Zitat Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Real-time neuroevolution in the NERO video game. IEEE Trans. Evol. Comput. 9, 653–668 (2005)CrossRef Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Real-time neuroevolution in the NERO video game. IEEE Trans. Evol. Comput. 9, 653–668 (2005)CrossRef
18.
Zurück zum Zitat Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artif. Life 15, 185–212 (2009)CrossRef Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artif. Life 15, 185–212 (2009)CrossRef
19.
Zurück zum Zitat Stanley, K.O., Miikkulainen, R.: A taxonomy for artificial embryogeny. Artif. Life 9, 93–130 (2003)CrossRef Stanley, K.O., Miikkulainen, R.: A taxonomy for artificial embryogeny. Artif. Life 9, 93–130 (2003)CrossRef
20.
Zurück zum Zitat Stanley, K.O., Miikkulainen, R.: Competitive coevolution through evolutionary complexification (2004) Stanley, K.O., Miikkulainen, R.: Competitive coevolution through evolutionary complexification (2004)
21.
Zurück zum Zitat Stone, P., Veloso, M.: Multiagent Systems: A Survey from a Machine Learning Perspective (2000) Stone, P., Veloso, M.: Multiagent Systems: A Survey from a Machine Learning Perspective (2000)
22.
Zurück zum Zitat Taylor, M.E., Whiteson, S., Stone, P.: Comparing evolutionary and temporal difference methods in a reinforcement learning domain. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation GECCO 2006, p. 1321 (2006) Taylor, M.E., Whiteson, S., Stone, P.: Comparing evolutionary and temporal difference methods in a reinforcement learning domain. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation GECCO 2006, p. 1321 (2006)
23.
Zurück zum Zitat Turing, A.M.: The chemical basis of morphogenesis. Bull. Math. Biol. 52, 153–197 (1990)CrossRef Turing, A.M.: The chemical basis of morphogenesis. Bull. Math. Biol. 52, 153–197 (1990)CrossRef
24.
Zurück zum Zitat Verbancsics, P., Stanley, K.O.: Evolving static representations for task transfer. J. Mach. Learn. Res. 11, 1737–1769 (2010)MathSciNetMATH Verbancsics, P., Stanley, K.O.: Evolving static representations for task transfer. J. Mach. Learn. Res. 11, 1737–1769 (2010)MathSciNetMATH
25.
Zurück zum Zitat Whiteson, S., Stone, P.: Evolutionary function approximation for reinforcement learning. J. Mach. Learn. Res. 7, 877–917 (2006)MathSciNetMATH Whiteson, S., Stone, P.: Evolutionary function approximation for reinforcement learning. J. Mach. Learn. Res. 7, 877–917 (2006)MathSciNetMATH
26.
Zurück zum Zitat Whiteson, S., Whiteson, D.: Machine learning for event selection in high energy physics. Eng. Appl. Artif. Intell. 22, 1203–1217 (2009)CrossRef Whiteson, S., Whiteson, D.: Machine learning for event selection in high energy physics. Eng. Appl. Artif. Intell. 22, 1203–1217 (2009)CrossRef
27.
Zurück zum Zitat Yao, X.: Evolving artificial neural networks (1999) Yao, X.: Evolving artificial neural networks (1999)
Metadaten
Titel
Team Search Tactics Through Multi-Agent HyperNEAT
verfasst von
John Reeder
Copyright-Jahr
2015
DOI
https://doi.org/10.1007/978-3-319-23108-2_7