Reducing trials by thinning-out in skill discovery

Authors:
Hayato Kobayashi;Kohei Hatano;Akira Ishino;Ayumi Shinohara
Affiliations:
Graduate School of Information Science, Tohoku University, Japan;Department of Informatics, Kyushu University, Japan;Graduate School of Information Science, Tohoku University, Japan;Graduate School of Information Science, Tohoku University, Japan
Venue:
DS'07 Proceedings of the 10th international conference on Discovery science
Year:
2007

Citing 6
Cited 0

Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms

Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Accelerating the Convergence of Evolutionary Algorithms by Fitness Landscape Approximation

PPSN V Proceedings of the 5th International Conference on Parallel Problem Solving from Nature
Machine learning for fast quadrupedal locomotion

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Distributed probabilistic model-building genetic algorithm

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI
Learning to kick the ball using back to reality

RoboCup 2004

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a new concept, thinning-out, for reducing the number of trials in skill discovery. Thinning-out means to skip over such trials that are unlikely to improve discovering results, in the same way as "pruning" in a search tree. We show that our thinningout technique significantly reduces the number of trials. In addition, we apply thinning-out to the discovery of good physical motions by legged robots in a simulation environment. By using thinning-out, our virtual robots can discover sophisticated motions that is much different from the initial motion in a reasonable amount of trials.