CMA-TWEANN: Efficient optimization of neural networks via self-adaptation and seamless augmentation

Hirotaka Moriguchi, Shinichi Honiden

研究成果: Conference contribution

11 被引用数 (Scopus)

抄録

Neuroevolutionary algorithms are successful methods for optimizing neural networks, especially for learning a neural policy (controller) in reinforcement learning tasks. Their significant advantage over gradient-based algorithms is the capability to search network topology as well as connection weights. However, state-of-the-art topology evolving methods are known to be inefficient compared to weight evolving methods with an appropriately hand-tuned topology. This paper introduces a novel efficient algorithm called CMA-TWEANN for evolving both topology and weights. Its high efficiency is achieved by introducing efficient topological mutation operators and integrating a state-of-the-art function optimization algorithm for weight optimization. Experiments on benchmark reinforcement learning tasks demonstrate that CMA-TWEANN solves tasks significantly faster than existing topology evolving methods. Furthermore, it outperforms weight evolving techniques even when they are equipped with a hand-tuned topology. Additional experiments reveal how and why CMA-TWEANN is the best performing weight evolving method.

本文言語English
ホスト出版物のタイトルGECCO'12 - Proceedings of the 14th International Conference on Genetic and Evolutionary Computation
ページ903-910
ページ数8
DOI
出版ステータスPublished - 2012 8 13
外部発表はい
イベント14th International Conference on Genetic and Evolutionary Computation, GECCO'12 - Philadelphia, PA, United States
継続期間: 2012 7 72012 7 11

出版物シリーズ

名前GECCO'12 - Proceedings of the 14th International Conference on Genetic and Evolutionary Computation

Other

Other14th International Conference on Genetic and Evolutionary Computation, GECCO'12
CountryUnited States
CityPhiladelphia, PA
Period12/7/712/7/11

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Applied Mathematics

フィンガープリント 「CMA-TWEANN: Efficient optimization of neural networks via self-adaptation and seamless augmentation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル