Abstract
Inspired by natural growing processes, we investigate how morphological changes can potentially help to lead and facilitate the task of learning to control a robot. We use the model of a tadpole that grows in four discrete stages into a frog. The control task to learn is to locomote to food positions that occur at random positions. We employ reinforcement learning, which is able to find a tail-driven swimming strategy for the tadpole stage that transitions into a leg-driven strategy for the frog. Furthermore, by using knowledge transferred from one growing stage to the next one, we were able to show that growing can benefit from guiding the controller optimization through morphological changes. The results suggest that learning time can be reduced compared to the cases when learning each stage individually from scratch.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bongard, J.: Morphological change in machines accelerates the evolution of robust behavior. PNAS 108(4), 1234–1239 (2011)
Skinner, B.: Science and Human Behavior. Simon and Schuster, New York City (1953)
Thrun, S.: Is learning the \(n^{\text{th}}\) thing any easier than learning the first?. In: NIPS, pp. 640–664 (1996)
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML, pp. 41–48 (2009)
Taylor, M., Stone, P.: Transfer learning for reinforcement learning domains: a survey. In: JMLR, pp. 1633–1685 (2009)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Juliani, A., et al.: Unity: a general platform for intelligent agents. arXiv preprint arXiv:1809.02627 (2018)
Tassava, R.A.: Forelimb spike regeneration in Xenopus laevis: testing for adaptiveness. JEZ-A 301(2), 150–159 (2004)
Abadi, M., et al.: A system for large-scale machine learning. In: USENIX, pp. 265–283 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, Y., Rossiter, J., Hauser, H. (2019). Learning in Growing Robots: Knowledge Transfer from Tadpole to Frog Robot. In: Martinez-Hernandez, U., et al. Biomimetic and Biohybrid Systems. Living Machines 2019. Lecture Notes in Computer Science(), vol 11556. Springer, Cham. https://doi.org/10.1007/978-3-030-24741-6_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-24741-6_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24740-9
Online ISBN: 978-3-030-24741-6
eBook Packages: Computer ScienceComputer Science (R0)