Distributed Age-Layered Novelty Search

Novelty search is a powerful biologically motivated method for discovering successful behaviors especially in deceptive domains, like those in artificial life. This paper extends the biological motivation further by distributing novelty search to run in parallel in multiple islands, with periodic migration among them. In this manner, it is possible to scale novelty search to larger populations and more diverse runs, and also to harness available computing power better. A second extension is to improve novelty searchs ability to solve practical problems by biasing the migration and elitism towards higher fitness. The resulting method, DANS, is shown to find better solutions much faster than pure single-population novelty search, making it a promising candidate for solving deceptive design problems in the real world.

[1]  Anders Lyhne Christensen,et al.  Devising Effective Novelty Search Algorithms: A Comprehensive Empirical Study , 2015, GECCO.

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

[3]  Anders Lyhne Christensen,et al.  Evolution of swarm robotics systems with novelty search , 2013, Swarm Intelligence.

[4]  Josh C. Bongard.  Innocent Until Proven Guilty: Reducing Robot Shaping From Polynomial to Linear Time , 2011, IEEE Transactions on Evolutionary Computation.

[5]  Phil Husbands,et al.  Evolutionary robotics , 2014, Evolutionary Intelligence.

[6]  Kenneth O. Stanley,et al.  Evolving a diversity of virtual creatures through novelty search and local competition , 2011, GECCO '11.

[7]  Peter Krcah.  Combination of Novelty Search and Fitness-Based Search Applied to Robot Body-Brain Co-Evolution , 2010 .

[8]  Hormoz Shahrzad,et al.  Tackling the Boolean Multiplexer Function Using a Highly Distributed Genetic Programming System , 2014, GPTP.

[9]  Hormoz Shahrzad,et al.  Introducing an Age-Varying Fitness Estimation Function , 2013 .

[10]  Antoine Cully,et al.  Robots that can adapt like animals , 2014, Nature.

[11]  Jean-Baptiste Mouret,et al.  Illuminating search spaces by mapping elites , 2015, ArXiv.

[12]  Faustino J. Gomez,et al.  When Novelty Is Not Enough , 2011, EvoApplications.

[13]  Risto Miikkulainen,et al.  Using symmetry and evolutionary search to minimize sorting networks , 2013, J. Mach. Learn. Res..

[14]  Stéphane Doncieux,et al.  Encouraging Behavioral Diversity in Evolutionary Robotics: An Empirical Study , 2012, Evolutionary Computation.

[15]  Joel Lehman,et al.  Overcoming deception in evolution of cognitive behaviors , 2014, GECCO.

[16]  Darrell Whitley,et al.  The Island Model Genetic Algorithm: On Separability, Population Size and Convergence , 2015, CIT 2015.

[17]  Kenneth O. Stanley,et al.  Revising the evolutionary computation abstraction: minimal criteria novelty search , 2010, GECCO '10.

[18]  Christoph Salge,et al.  Empowerment - an Introduction , 2013, ArXiv.

[19]  Kenneth O. Stanley,et al.  Confronting the Challenge of Quality Diversity , 2015, GECCO.

[20]  Kenneth E. Batcher,et al.  Finding better sorting networks , 2009 .

[21]  A D Wissner-Gross,et al.  Causal entropic forces. , 2013, Physical review letters.

[22]  Una-May O'Reilly,et al.  EC-Star: A Massive-Scale, Hub and Spoke, Distributed Genetic Programming System , 2013 .

[23]  Una-May O'Reilly,et al.  Maintenance of a Long Running Distributed Genetic Programming System for Solving Problems Requiring Big Data , 2013, GPTP.

[24]  Antonio J. Rivera,et al.  GP-COACH: Genetic Programming-based learning of COmpact and ACcurate fuzzy rule-based classification systems for High-dimensional problems , 2010, Inf. Sci..

[25]  Kenneth O. Stanley,et al.  Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space , 2011, Evolutionary Computation.

[26]  H. P. de Vladar.  Why Greatness Cannot Be Planned: The Myth of the Objective , 2016, Leonardo.

[27]  Risto Miikkulainen,et al.  Estimating the Advantage of Age-Layering in Evolutionary Algorithms , 2016, GECCO.

[28]  Gregory Hornby,et al.  ALPS: the age-layered population structure for reducing the problem of premature convergence , 2006, GECCO.

[29]  Rüdiger Westermann,et al.  UberFlow: a GPU-based particle engine , 2004, SIGGRAPH '04.

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

[31]  Josh C. Bongard,et al.  Guarding against premature convergence while accelerating evolutionary search , 2010, GECCO '10.