Academic Journal

Comparing lifetime learning methods for morphologically evolving robots

التفاصيل البيبلوغرافية
العنوان: Comparing lifetime learning methods for morphologically evolving robots
المؤلفون: Van Diggelen, Fuda, Ferrante, E., Eiben, A. E.
المصدر: Van Diggelen , F , Ferrante , E & Eiben , A E 2021 , Comparing lifetime learning methods for morphologically evolving robots . in GECCO 2021 : Proceedings of the 2021 Genetic and Evolutionary Computation Conference Companion . Association for Computing Machinery, Inc , pp. 93-94 , 2021 Genetic and Evolutionary Computation Conference, GECCO 2021 , Virtual, Online , France , 10/07/21 . https://doi.org/10.1145/3449726.3459530
بيانات النشر: Association for Computing Machinery, Inc
سنة النشر: 2021
مصطلحات موضوعية: evolutionary robotics, lifetime learning, morphological evolution
الوصف: The joint evolution of morphologies and controllers of robots leads to a problem: Even if the parents have well-matching bodies and brains, the stochastic recombination can break this match and cause a body-brain mismatch in their offspring. This can be mitigated by having newborn robots perform a learning process that optimizes their inherited brain quickly after birth. An adequate learning method should work on all possible robot morphologies and be efficient. In this paper we apply Bayesian Optimization and Differential Evolution as learning algorithms and compare them on a test suite of different robot bodies.
نوع الوثيقة: article in journal/newspaper
وصف الملف: application/pdf
اللغة: English
ردمك: 978-1-4503-8351-6
1-4503-8351-3
Relation: urn:ISBN:9781450383516
DOI: 10.1145/3449726.3459530
الاتاحة: https://research.vu.nl/en/publications/7d076b58-d8e1-436e-af67-6b10c5feaa63
https://doi.org/10.1145/3449726.3459530
https://hdl.handle.net/1871.1/7d076b58-d8e1-436e-af67-6b10c5feaa63
https://research.vu.nl/ws/files/153307398/Comparing_lifetime_learning_methods_for_morphologically_evolving_robots.pdf
http://www.scopus.com/inward/record.url?scp=85111016096&partnerID=8YFLogxK
http://www.scopus.com/inward/citedby.url?scp=85111016096&partnerID=8YFLogxK
Rights: info:eu-repo/semantics/openAccess
رقم الانضمام: edsbas.45CC6EC8
قاعدة البيانات: BASE
الوصف
ردمك:9781450383516
1450383513
DOI:10.1145/3449726.3459530