Importance of parameter settings on the benefits of robot-to-robot learning in evolutionary robotics

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Robot-to-robot learning, a specific case of social learning in robotics, enables multiple robots to share learned skills while completing a task. The literature offers various statements of its benefits. Robots using this type of social learning can reach a higher performance, an increased learning speed, or both, compared to robots using individual learning only. No general explanation has been advanced for the difference in observations, which make the results highly dependent on the particular system and parameter setting. In this paper, we perform a detailed analysis into the effects of robot-to-robot learning. As a result, we show that this type of social learning can reduce the sensitivity of the learning process to the choice of parameters in two ways. First, robot-to-robot learning can reduce the number of bad performing individuals in the population. Second, robot-to-robot learning can increase the chance of having a successful run, where success is defined as the presence of a high performing individual. Additionally, we show that robot-to-robot learning results in an increased learning speed for almost all parameter settings. Our results indicate that robot-to-robot learning is a powerful mechanism which leads to benefits in both performance and learning speed.

Original languageEnglish
Article number10
Pages (from-to)1-11
Number of pages11
JournalFrontiers Robotics AI
Volume6
Issue numberMARCH
DOIs
Publication statusPublished - 4 Mar 2019

Fingerprint

Robot learning
Robotics
Robots

Keywords

  • Evolutionary algorithms
  • Evolutionary robotics
  • Neural networks
  • Parameter tuning
  • Robot-to-robot learning
  • Social learning

Cite this

@article{afeb125ebaa9421981670c757dd08d13,
title = "Importance of parameter settings on the benefits of robot-to-robot learning in evolutionary robotics",
abstract = "Robot-to-robot learning, a specific case of social learning in robotics, enables multiple robots to share learned skills while completing a task. The literature offers various statements of its benefits. Robots using this type of social learning can reach a higher performance, an increased learning speed, or both, compared to robots using individual learning only. No general explanation has been advanced for the difference in observations, which make the results highly dependent on the particular system and parameter setting. In this paper, we perform a detailed analysis into the effects of robot-to-robot learning. As a result, we show that this type of social learning can reduce the sensitivity of the learning process to the choice of parameters in two ways. First, robot-to-robot learning can reduce the number of bad performing individuals in the population. Second, robot-to-robot learning can increase the chance of having a successful run, where success is defined as the presence of a high performing individual. Additionally, we show that robot-to-robot learning results in an increased learning speed for almost all parameter settings. Our results indicate that robot-to-robot learning is a powerful mechanism which leads to benefits in both performance and learning speed.",
keywords = "Evolutionary algorithms, Evolutionary robotics, Neural networks, Parameter tuning, Robot-to-robot learning, Social learning",
author = "Jacqueline Heinerman and Evert Haasdijk and Eiben, {A. E.}",
year = "2019",
month = "3",
day = "4",
doi = "10.3389/frobt.2019.00010",
language = "English",
volume = "6",
pages = "1--11",
journal = "Frontiers in Robotics and AI",
issn = "2296-9144",
publisher = "Frontiers Media",
number = "MARCH",

}

Importance of parameter settings on the benefits of robot-to-robot learning in evolutionary robotics. / Heinerman, Jacqueline; Haasdijk, Evert; Eiben, A. E.

In: Frontiers Robotics AI, Vol. 6, No. MARCH, 10, 04.03.2019, p. 1-11.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Importance of parameter settings on the benefits of robot-to-robot learning in evolutionary robotics

AU - Heinerman, Jacqueline

AU - Haasdijk, Evert

AU - Eiben, A. E.

PY - 2019/3/4

Y1 - 2019/3/4

N2 - Robot-to-robot learning, a specific case of social learning in robotics, enables multiple robots to share learned skills while completing a task. The literature offers various statements of its benefits. Robots using this type of social learning can reach a higher performance, an increased learning speed, or both, compared to robots using individual learning only. No general explanation has been advanced for the difference in observations, which make the results highly dependent on the particular system and parameter setting. In this paper, we perform a detailed analysis into the effects of robot-to-robot learning. As a result, we show that this type of social learning can reduce the sensitivity of the learning process to the choice of parameters in two ways. First, robot-to-robot learning can reduce the number of bad performing individuals in the population. Second, robot-to-robot learning can increase the chance of having a successful run, where success is defined as the presence of a high performing individual. Additionally, we show that robot-to-robot learning results in an increased learning speed for almost all parameter settings. Our results indicate that robot-to-robot learning is a powerful mechanism which leads to benefits in both performance and learning speed.

AB - Robot-to-robot learning, a specific case of social learning in robotics, enables multiple robots to share learned skills while completing a task. The literature offers various statements of its benefits. Robots using this type of social learning can reach a higher performance, an increased learning speed, or both, compared to robots using individual learning only. No general explanation has been advanced for the difference in observations, which make the results highly dependent on the particular system and parameter setting. In this paper, we perform a detailed analysis into the effects of robot-to-robot learning. As a result, we show that this type of social learning can reduce the sensitivity of the learning process to the choice of parameters in two ways. First, robot-to-robot learning can reduce the number of bad performing individuals in the population. Second, robot-to-robot learning can increase the chance of having a successful run, where success is defined as the presence of a high performing individual. Additionally, we show that robot-to-robot learning results in an increased learning speed for almost all parameter settings. Our results indicate that robot-to-robot learning is a powerful mechanism which leads to benefits in both performance and learning speed.

KW - Evolutionary algorithms

KW - Evolutionary robotics

KW - Neural networks

KW - Parameter tuning

KW - Robot-to-robot learning

KW - Social learning

UR - http://www.scopus.com/inward/record.url?scp=85064663307&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064663307&partnerID=8YFLogxK

U2 - 10.3389/frobt.2019.00010

DO - 10.3389/frobt.2019.00010

M3 - Article

VL - 6

SP - 1

EP - 11

JO - Frontiers in Robotics and AI

JF - Frontiers in Robotics and AI

SN - 2296-9144

IS - MARCH

M1 - 10

ER -