Video Games as a Testbed for Open-Ended Phenomena

Understanding and engineering open-endedness, or the indefinite generation of novelty and complexity at arbitrary scales, has long been studied by implementing nature-inspired simulations specifically designed for artificial life studies. This paper argues that video games serve as a complementary domain for research on open-endedness. In support of this claim, experiments in this paper evaluate the effects of age-based and spatial destructive events in two game domains: an interactive Game of Life and the city-building game SimCity. These games are played by a neural-network-controlled gameplay agent trying to maximize reward. Results indicate that experiments with SimCity are more likely to identify statistically significant differences in complexity as a result of applied destructive events, highlighting the utility of this game domain for studying artificial life phenomena.

[1]  Gregory Shakhnarovich,et al.  FractalNet: Ultra-Deep Neural Networks without Residuals , 2016, ICLR.

[2]  Staffan Björk,et al.  Zero-Player Games - What We Talk about When We Talk about Players , 2012, CGAMES 2012.

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

[4]  Jesper Juul,et al.  The Open and the Closed: Games of Emergence and Games of Progression , 2002, CGDC Conf..

[5]  Jay Wright Forrester,et al.  Urban Dynamics , 1969 .

[6]  Charles Ofria,et al.  Avida , 2004, Artificial Life.

[7]  L. Yaeger.  Computational Genetics, Physiology, Metabolism, Neural Systems, Learning, Vision, and Behavior or PolyWorld: Life in a New Context , 1997 .

[8]  M. Bedau.  Weak Emergence * , 1997 .

[9]  M. Plissart.  A world without end , 2008 .

[10]  Pierre-Yves Oudeyer,et al.  Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments , 2019, CoRL.

[11]  Eörs Szathmáry,et al.  The Major Transitions in Evolution , 1997 .

[12]  Thomas S. Ray,et al.  An Approach to the Synthesis of Life , 1991 .

[13]  Kenneth O. Stanley,et al.  On the Critical Role of Divergent Selection in Evolvability , 2016, Front. Robot. AI.

[14]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[15]  Risto Miikkulainen,et al.  Towards an empirical measure of evolvability , 2005, GECCO '05.

[16]  L. Altenberg,et al.  PERSPECTIVE: COMPLEX ADAPTATIONS AND THE EVOLUTION OF EVOLVABILITY , 1996, Evolution; international journal of organic evolution.

[17]  Hod Lipson,et al.  The evolutionary origins of modularity , 2012, Proceedings of the Royal Society B: Biological Sciences.

[18]  Mark A. Bedau,et al.  Four Puzzles About Life , 1998, Artificial Life.

[19]  K. Ruiz-Mirazo,et al.  Enabling conditions for ‘open-ended evolution’ , 2007 .

[20]  Lee Spector,et al.  Division blocks and the open-ended evolution of development, form, and behavior , 2007, GECCO '07.

[21]  R. Miikkulainen,et al.  Extinction Events Can Accelerate Evolution , 2015, PloS one.

[22]  Kenneth O. Stanley,et al.  Identifying Necessary Conditions for Open-Ended Evolution through the Artificial Life World of Chromaria , 2014, ALIFE.

[23]  Russell K. Standish,et al.  Open-Ended Artificial Evolution , 2002, Int. J. Comput. Intell. Appl..

[24]  A. Knoll,et al.  Evolution caused by extreme events , 2017, Philosophical Transactions of the Royal Society B: Biological Sciences.

[25]  Pablo González de Prado Salas,et al.  Intrinsic Mortality Governs Evolvability , 2018 .

[26]  Jeff Jones,et al.  On using compressibility to detect when slime mould completed computation , 2016, Complex..

[27]  Julian Togelius,et al.  Learning Controllable Content Generators , 2021, 2021 IEEE Conference on Games (CoG).

[28]  Alastair Channon,et al.  A virtual creatures model for studies in artificial evolution , 2005, 2005 IEEE Congress on Evolutionary Computation.

[29]  M. Pigliucci.  Is evolvability evolvable? , 2008, Nature Reviews Genetics.

[30]  Robert I. Damper,et al.  Towards the evolutionary emergence of increasingly complex advantageous behaviours , 2000, Int. J. Syst. Sci..

[31]  M. Félix,et al.  Phenotypic neighborhood and micro-evolvability. , 2004, Trends in genetics : TIG.

[32]  Marcus W Feldman,et al.  SPATIAL ENVIRONMENTAL VARIATION CAN SELECT FOR EVOLVABILITY , 2011, Evolution; international journal of organic evolution.

[33]  Timothy J. Taylor,et al.  From artificial evolution to artificial life , 1999 .

[34]  Charles Ofria,et al.  What’s holding artificial life back from open-ended evolution? , 2015 .

[35]  Kenneth O. Stanley,et al.  Abandoning Objectives: Evolution Through the Search for Novelty Alone , 2011, Evolutionary Computation.

[36]  Sam Earle.  Using Fractal Neural Networks to Play SimCity 1 and Conway's Game of Life at Variable Scales , 2020, ArXiv.

[37]  Josef Sivic,et al.  Evolving Structures in Complex Systems , 2019, 2019 IEEE Symposium Series on Computational Intelligence (SSCI).

[38]  L. B. Soros,et al.  Necessary Conditions for Open-Ended Evolution , 2018 .