Hierarchical Behavioral Repertoires with Unsupervised Descriptors

File Description SizeFormat 
hierarchical-behavioral-repertoires_small.pdfFile embargoed until 01 January 100001.27 MBAdobe PDF    Request a copy
Title: Hierarchical Behavioral Repertoires with Unsupervised Descriptors
Authors: Cully, AHR
Demiris, Y
Item Type: Conference Paper
Abstract: Enabling artificial agents to automatically learn complex, versatile and high-performing behaviors is a long-lasting challenge. This paper presents a step in this direction with hierarchical behavioral repertoires that stack several behavioral repertoires to generate sophisticated behaviors. Each repertoire of this architecture uses the lower repertoires to create complex behaviors as sequences of simpler ones, while only the lowest repertoire directly controls the agent's movements. This paper also introduces a novel approach to automatically define behavioral descriptors thanks to an unsupervised neural network that organizes the produced high-level behaviors. The experiments show that the proposed architecture enables a robot to learn how to draw digits in an unsupervised manner after having learned to draw lines and arcs. Compared to traditional behavioral repertoires, the proposed architecture reduces the dimensionality of the optimization problems by orders of magnitude and provides behaviors with a twice better fitness. More importantly, it enables the transfer of knowledge between robots: a hierarchical repertoire evolved for a robotic arm to draw digits can be transferred to a humanoid robot by simply changing the lowest layer of the hierarchy. This enables the humanoid to draw digits although it has never been trained for this task.
Issue Date: 31-Dec-2018
Date of Acceptance: 24-Mar-2018
DOI: 10.1145/3205455.3205571
Publisher: ACM
Journal / Book Title: Genetic and Evolutionary Computation Conference 2018
Copyright Statement: This paper is embargoed until publication.
Sponsor/Funder: Commission of the European Communities
Funder's Grant Number: 643783
Conference Name: Genetic and Evolutionary Computation Conference 2018
Keywords: cs.RO
Publication Status: Accepted
Start Date: 2018-07-14
Finish Date: 2018-07-19
Conference Place: Kyoto, Japan
Embargo Date: publication subject to indefinite embargo
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx