Effects of cooperative and competitive coevolution on complexity in a linguistic prediction game

We propose a linguistic prediction game with competitive and cooperative variants, and a model of game players based on finite state automata. We present a complexity metric for these automata, and study the coevolutionary dynamics of complexity growth in a variety of multi-species simulations. We present quantitative results using this complexity metric and analyze the causes of varying rates of complexity growth across different types of interactions. We find that while both purely competitive and purely cooperative coevolution are able to drive complexity growth above the rate of genetic drift, mixed systems with both competitive and cooperative interactions achieve significantly higher evolved complexity.

[1]  R. Gibbons.  Game theory for applied economists , 1992 .

[2]  A. Kolmogorov.  Three approaches to the quantitative definition of information , 1968 .

[3]  J. Pollack,et al.  Challenges in coevolutionary learning: arms-race dynamics, open-endedness, and medicocre stable states , 1998 .

[4]  J. Krebs,et al.  Arms races between and within species , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[5]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[6]  Dilip Mookherjee,et al.  Learning behavior in an experimental matching pennies game , 1994 .

[7]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[8]  C. Adami,et al.  Introduction To Artificial Life , 1997, IEEE Trans. Evol. Comput..

[9]  Sheng Yu,et al.  State Complexity of Regular Languages , 2001, J. Autom. Lang. Comb..

[10]  C. Adami,et al.  Evolution of Biological Complexity , 2000, Proc. Natl. Acad. Sci. USA.

[11]  S. Gould.  Full House: The Spread of Excellence from Plato to Darwin , 1996 .

[12]  D. Hull.  Universal Darwinism , 1995, Nature.

[13]  Kenneth O. Stanley,et al.  Open-Ended Evolution: Perspectives from the OEE Workshop in York , 2016, Artificial Life.

[14]  Jean-Arcady Meyer,et al.  Coevolving Communicative Behavior in a Linear Pursuer-Evader Game , 1998 .

[15]  Jordan B. Pollack,et al.  Coevolving communicative behavior in a linear pursuer-evadergame , 1998 .

[16]  Carol E. Cleland,et al.  The Nature of Life: Classical and Contemporary Perspectives from Philosophy and Science: Does ‘life’ have a definition? , 2010 .

[17]  Martín Abadi,et al.  Learning to Protect Communications with Adversarial Neural Cryptography , 2016, ArXiv.

[18]  Stephen Wolfram,et al.  Cellular automata as models of complexity , 1984, Nature.

[19]  Kristian Lindgren,et al.  Evolutionary phenomena in simple dynamics , 1992 .

[20]  John E. Hopcroft,et al.  An n log n algorithm for minimizing states in a finite automaton , 1971 .

[21]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[22]  John S. McCaskill,et al.  Open Problems in Artificial Life , 2000, Artificial Life.

[23]  Kevin B. Korb,et al.  Network Measures of Ecosystem Complexity , 2010, ALIFE.

[24]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[25]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[26]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.