Improving RL Power for On-Line Evolution of Gaits in Modular Robots

Milan Jelisavcic, Matteo De Carlo, Evert Haasdijk, A.E. Eiben

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

This paper addresses the problem of on-line gait learning in modular robots whose shape is not known in advance. The best algorithm for this problem known to us is a reinforcement learning method, called RL PoWER. In this study we revisit the original RL PoWER algorithm and observe that in essence it is a specific evolutionary algorithm. Based on this insight we propose two modifications of the main search operators and compare the quality of the evolved gaits when either or both of these modified operators are employed. The results show that using 2-parent crossover as well as mutation with self- adaptive step-sizes can significantly improve the performance of the original algorithm.
Original languageEnglish
Title of host publication2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Pages1-8
Number of pages8
ISBN (Electronic)978-1-5090-4240-1
DOIs
Publication statusPublished - 6 Dec 2016
Event2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 - Athens, Greece
Duration: 6 Dec 20169 Dec 2016

Conference

Conference2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
CountryGreece
CityAthens
Period6/12/169/12/16

Fingerprint Dive into the research topics of 'Improving RL Power for On-Line Evolution of Gaits in Modular Robots'. Together they form a unique fingerprint.

  • Cite this

    Jelisavcic, M., De Carlo, M., Haasdijk, E., & Eiben, A. E. (2016). Improving RL Power for On-Line Evolution of Gaits in Modular Robots. In 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 (pp. 1-8). [7850166] Institute of Electrical and Electronics Engineers, Inc.. https://doi.org/10.1109/SSCI.2016.7850166