Citation

BibTex format

@inproceedings{Cully:2018:10.1145/3205455.3205571,
author = {Cully, AHR and Demiris, Y},
doi = {10.1145/3205455.3205571},
publisher = {ACM},
title = {Hierarchical behavioral repertoires with unsupervised descriptors},
url = {http://dx.doi.org/10.1145/3205455.3205571},
year = {2018}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - 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.
AU - Cully,AHR
AU - Demiris,Y
DO - 10.1145/3205455.3205571
PB - ACM
PY - 2018///
TI - Hierarchical behavioral repertoires with unsupervised descriptors
UR - http://dx.doi.org/10.1145/3205455.3205571
UR - http://hdl.handle.net/10044/1/58755
ER -

Contact us

Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ

To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:

ai-speaker@imperial.ac.uk

To reach the network manager, Diana O'Malley - including to join the network - please contact:

ai-net-manager@imperial.ac.uk