Complexity of bird song caused by adversarial imitation learning

  • Seiya YamazakiEmail author
  • Hiroyuki Iizuka
  • Masahito Yamamoto
Original Article


Biological evolution produces complexity through genetic variations based on randomness. In conventional communication or language simulation models, genetic variations based on randomness and fitness function rewarding task achievements play an important role in evolving communication signals to complex ones. However, it is known that not only genetic variations evolve communication but also imitative learning during developmental processes contributes to the evolution of communication. What we investigated here was to find a different principle of generating complexity which does not rely on the randomness or external environmental complexity but only on the learning processes in communication. Our hypothesis is that the contradictory learning mechanism we call the adversarial imitation learning can work to increase the complexity without relying on the random processes. To investigate our hypothesis, we implemented the adversarial imitation learning on a simulation where two agents interact with and imitate each other. Our results showed that the adversarial imitation learning causes chaotic dynamics and investigating the learning results in different types of interaction between the two; it was clarified that the adversarial imitation learning is necessary for the emergence of the chaotic time series.


Adversarial imitation learning Complexity Chaos 



This work was partially supported by JSPS KAKENHI Grant number JP18H05057.


  1. 1.
    Holland JH (1975) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control and artificial intelligence, 2nd edn, expanded 1992. University of Michigan PressGoogle Scholar
  2. 2.
    Darwin C, Wallace A (1858) On the tendency of species to form varieties; and on the perpetuation of varieties and species by natural means of selection. J Proc Linn Soc Lond Zool 3:45–62CrossRefGoogle Scholar
  3. 3.
    Wilson DS (1983) The group selection controversy: history and current status. Ann Rev Ecol Syst 14:159–187CrossRefGoogle Scholar
  4. 4.
    Froese T, Virgo N, Ikegami T (2011) Life as a process of open-ended becoming: analysis of a minimal model. In: Lenaerts T, Giacobini M, Bersini H, Bourgine P, Dorigo M, Doursat R (eds) Advances in artificial life, ECAL 2011: proceedings of the eleventh european conference on the synthesis and simulation of living systems. MIT Press, Cambridge, MA, pp 250–257Google Scholar
  5. 5.
    Miconi T (2008) Evosphere: evolutionary dynamics in a population of fighting virtual creatures. IEEE, pp 3066–3073Google Scholar
  6. 6.
    Tchernichovski O, Marcus G (2014) Vocal learning beyond imitation: mechanisms of adaptive vocal development in songbirds and human infants. Curr Opin Neurobiol 28:42–47CrossRefGoogle Scholar
  7. 7.
    Tchernichovski O, Nottebohm F (1998) Social inhibition of song imitation among sibling male zebra finches. Proc Natl Acad Sci 95:8951–8956CrossRefGoogle Scholar
  8. 8.
    Derégnaucourt S, Gahr M (2013) Horizontal transmission of the father’s song in the zebra finch (Taeniopygia guttata). Biol Lett 9:20130247CrossRefGoogle Scholar
  9. 9.
    ten Cate C, Okanoya K (2012) Revisiting the syntactic abilities of non-human animals: natural vocalizations and artificial grammar learning. Philos Trans R Soc B Biol Sci 367:1984–1994CrossRefGoogle Scholar
  10. 10.
    Catchpole CK (1981) Vocal communication in birds. Jpn J Ornithol 30:87–89CrossRefGoogle Scholar
  11. 11.
    Steels L, Vogt P (1997) Grounding adaptive language games in robotic agents. In: Proceedings of the fourth European conference on artificial life, Brighton, UK, pp 474–482Google Scholar
  12. 12.
    Marocco D, Nolfi S (2007) Emergence of communication in embodied agents evolved for the ability to solve a collective navigation problem. Connect Sci 19:53–74CrossRefGoogle Scholar
  13. 13.
    Sasahara K, Ikegami T (2007) Evolution of birdsong syntax by interjection communication. Artif Life 13:259–277CrossRefGoogle Scholar
  14. 14.
    Hashimoto T, Ikegami T (1996) Emergence of net-grammar in communicating agents. BioSystems 38:1–14CrossRefGoogle Scholar
  15. 15.
    Suzuki J, Kaneko K (1994) Imitation games. Phys D Nonlinear Phenom 75:328–342CrossRefGoogle Scholar
  16. 16.
    Yamazaki S, Iizuka H, Yamamoto M (2018) Emergence of chaotic time series by adversarial imitation learning. MIT Press, pp 659–664Google Scholar
  17. 17.
    Robinson AJ, Frank Fallside (1987) The utility driven dynamic error propagation network. University of Cambridge Department of Engineering, CambridgeGoogle Scholar
  18. 18.
    Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: Proceedings of the 30th international conference on machine learning, ICML 2013, Atlanta, GA, USA, 16–21 June 2013, pp 1310–1318Google Scholar
  19. 19.
    Lyapunov AM (1992) The general problem of the stability of motion. Int J Control 55:531–534MathSciNetCrossRefGoogle Scholar
  20. 20.
    Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets, pp 2672–2680Google Scholar
  21. 21.
    Moran N, Pollack JB (2017) Effects of cooperative and competitive coevolution on complexity in a linguistic prediction game, pp 298–205Google Scholar

Copyright information

© International Society of Artificial Life and Robotics (ISAROB) 2019

Authors and Affiliations

  • Seiya Yamazaki
    • 1
    Email author
  • Hiroyuki Iizuka
    • 1
  • Masahito Yamamoto
    • 1
  1. 1.Graduate School of Information Science and TechnologyHokkaido UniversitySapporoJapan

Personalised recommendations