Data-efficient neuroevolution with kernel-based surrogate models

作者: Adam Gaier , Jean-Baptiste Mouret , Alexander Asteroth

DOI: 10.1145/3205455.3205510

关键词: AlgorithmComputer scienceNetwork topologyNeuroevolutionSurrogate modelNeuroevolution of augmenting topologies

摘要: Surrogate-assistance approaches have long been used in computationally expensive domains to improve the data-efficiency of optimization algorithms. Neuroevolution, however …

参考文章(32)
Roberto Calandra, André Seyfarth, Jan Peters, Marc Peter Deisenroth, Bayesian optimization for learning gaits under uncertainty Annals of Mathematics and Artificial Intelligence. ,vol. 76, pp. 5- 23 ,(2016) , 10.1007/S10472-015-9463-9
Michel Neuhaus, Kaspar Riesen, Horst Bunke, Fast Suboptimal Algorithms for the Computation of Graph Edit Distance Lecture Notes in Computer Science. pp. 163- 172 ,(2006) , 10.1007/11815921_17
Antoine Cully, Jeff Clune, Danesh Tarapore, Jean-Baptiste Mouret, Robots that can adapt like animals Nature. ,vol. 521, pp. 503- 507 ,(2015) , 10.1038/NATURE14422
Anh Nguyen, Jason Yosinski, Jeff Clune, Deep neural networks are easily fooled: High confidence predictions for unrecognizable images computer vision and pattern recognition. pp. 427- 436 ,(2015) , 10.1109/CVPR.2015.7298640
Alberto Sanfeliu, King-Sun Fu, A distance measure between attributed relational graphs for pattern recognition systems man and cybernetics. ,vol. 13, pp. 353- 362 ,(1983) , 10.1109/TSMC.1983.6313167
Kenneth O. Stanley, Compositional pattern producing networks: A novel abstraction of development Genetic Programming and Evolvable Machines. ,vol. 8, pp. 131- 162 ,(2007) , 10.1007/S10710-007-9028-8
Stephane Doncieux, Nicolas Bredeche, Jean-Baptiste Mouret, Agoston E. (Gusz) Eiben, Evolutionary Robotics: What, Why, and Where to Frontiers in Robotics and AI. ,vol. 2, pp. 4- ,(2015) , 10.3389/FROBT.2015.00004