ABSTRACT
A central challenge to evolutionary computation is enabling techniques to evolve increasingly complex target end products. Frequently direct approaches that reward only the target end product itself are not successful because the path between the starting conditions and the target end product traverses through a complex fitness landscape, where the directly accessible intermediary states may be require deleterious or even simply neutral mutations. As such, a host of techniques have sprung up to support evolutionary computation techniques taking these paths. One technique is scaffolding where intermediary targets are used to provide a path from the starting state to the end state. While scaffolding can be successful within well-understood domains it also poses the challenge of identifying useful intermediaries. Within this paper we first identify some shortcomings of scaffolding approaches --- namely, that poorly selected intermediaries may in fact hurt the evolutionary computation's chance of producing the desired target end product. We then describe a light-weight approach to selecting intermediate scaffolding states that improve the efficacy of the evolutionary computation.
- Eric Bonabeau. 1999. Editor's introduction: stigmergy. Artificial Life 5, 2 (1999), 95--96. Google ScholarDigital Library
- Josh Bongard. 2011. Morphological change in machines accelerates the evolution of robust behavior. Proceedings of the National Academy of Sciences 108, 4 (2011), 1234--1239.Google ScholarCross Ref
- Josh C Bongard. 2011. Morphological and environmental scaffolding synergize when evolving robot controllers: artificial life/robotics/evolvable hardware. In Proceedings of the 13th annual conference on Genetic and evolutionary computation. ACM, 179--186. Google ScholarDigital Library
- Kalyanmoy Deb. 2014. Multi-objective optimization. In Search methodologies. Springer, 403--449.Google Scholar
- Jeffrey A Edlund, Nicolas Chaumont, Arend Hintze, Christof Koch, Giulio Tononi, and Christoph Adami. 2011. Integrated information increases with fitness in the evolution of animats. PLoS Comput Biol 7, 10 (2011), e1002236.Google ScholarCross Ref
- Diego Federici and Keith Downing. 2006. Evolution and development of a multi-cellular organism: scalability, resilience, and neutral complexification. Artificial life 12, 3 (2006), 381--409. Google ScholarDigital Library
- Heather J Goldsby, Rebecca L Young, Hans A Hofmann, and Arend Hintze. 2017. Increasing the complexity of solutions produced by an evolutionary developmental system. In Proceedings of the Genetic and Evolutionary Computation Conference Companion. ACM, 57--58. Google ScholarDigital Library
- Laura M Grabowski and Maganã Javier M. 2013. Building on Simplicity: Multi-stage Evolution of Digital Organisms. Artificial Life 14 (2013).Google Scholar
- Arend Hintze, Jeffrey A Edlund, Randal S Olson, David B Knoester, Jory Schossau, Larissa Albantakis, Ali Tehrani-Saleh, Peter Kvam, Leigh Sheneman, Heather Goldsby, et al. 2017. Markov brains: A technical introduction. arXiv preprint arXiv:1709.05601 (2017).Google Scholar
- Arend Hintze and Masoud Miromeni. 2014. Evolution of autonomous hierarchy formation and maintenance. In Proceedings of the 14th International Conference on the Synthesis and Simulation of Living Systems (ALIFE 14), New York, NY, USA, Vol. 30. Citeseer, 366--367.Google ScholarCross Ref
- John R Koza. 1992. Genetic programming: on the programming of computers by means of natural selection. Vol. 1. MIT Press. Google ScholarDigital Library
- Lars Marstaller, Arend Hintze, and Christoph Adami. 2013. The evolution of representation in simple cognitive networks. Neural computation 25, 8 (2013). 2079--2107. Google ScholarDigital Library
- Jens Niehaus and Wolfgang Banzhaf. 2003. More on computational effort statistics for genetic programming. In EuroGP. Springer, 164--172. Google ScholarDigital Library
- Randal S Olson, Arend Hintze, Fred C Dyer, David B Knoester, and Christoph Adami. 2013. Predator confusion is sufficient to evolve swarming behaviour. Journal of The Royal Society Interface 10, 85 (2013), 20130305.Google ScholarCross Ref
- Bjørn Østman, Arend Hintze, and Christoph Adami. 2011. Impact of epistasis and pleiotropy on evolutionary adaptation. Proceedings of the Royal Society of London B: Biological Sciences (2011), rspb20110870.Google Scholar
- Jory Schossau, Christoph Adami, and Arend Hintze. 2015. Information-theoretic neuro-correlates boost evolution of cognitive systems. Entropy 18, 1 (2015), 6.Google ScholarCross Ref
- Michael J Wiser, Noah Ribeck, and Richard E Lenski. 2013. Long-term dynamics of adaptation in asexual populations. Science (2013), 1243357.Google Scholar
Index Terms
- Serendipitous scaffolding to improve a genetic algorithm's speed and quality
Recommendations
Genetic algorithm with adaptive elitism-based immigrants for dynamic optimization problems
GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computationWe propose a genetic algorithm with adaptive elitism-based immigrants which tunes the balance between elitism-based immigrants and random immigrants by itself. Experimental results show that our genetic algorithm with adaptive elitism-based immigrants ...
Genetic fuzzy rules for DOPs
GECCO '12: Proceedings of the 14th annual conference companion on Genetic and evolutionary computationDynamic Optimization Problems (DOPs) are a defiance for Genetic Algorithms. In DOPs, a varied number of optima, either local or global, that dynamically change their position and shape in the search space. When applied to DOPs, the standard Genetic ...
A parameter-less genetic algorithm with customized crossover and mutation operators
GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computationGenetic algorithm is one of the well-known population based meta-heuristics. The reasonable performance of the algorithm on a wide variety of problems as well as its simplicity made this algorithm a first choice in lots of cases. However, the algorithm ...
Comments