Behavioral Repertoire Learning in Robotics
Antoine Cully
ISIR, Université Pierre et Marie Curie-Paris 6,
CNRS UMR 7222
4 place Jussieu, F-75252, Paris Cedex 05,
France
cully@isir.upmc.fr
Jean-Baptiste Mouret
ISIR, Université Pierre et Marie Curie-Paris 6,
CNRS UMR 7222
4 place Jussieu, F-75252, Paris Cedex 05,
France
mouret@isir.upmc.fr
ABSTRACT
Learning in robotics typically involves choosing a simple goal
(e.g. walking) and assessing the performance of each con-
troller with regard to this task (e.g. walking speed). How-
ever, learning advanced, input-driven controllers (e.g. walk-
ing in each direction) requires testing each controller on a
large sample of the possible input signals. This costly pro-
cess makes difficult to learn useful low-level controllers in
robotics.
Here we introduce BR-Evolution, a new evolutionary learn-
ing technique that generates a behavioral repertoire by tak-
ing advantage of the candidate solutions that are usually
discarded. Instead of evolving a single, general controller,
BR-evolution thus evolves a collection of simple controllers,
one for each variant of the target behavior; to distinguish
similar controllers, it uses a performance objective that al-
lows it to produce a collection of diverse but high-performing
behaviors. We evaluated this new technique by evolving gait
controllers for a simulated hexapod robot. Results show that
a single run of the EA quickly finds a collection of controllers
that allows the robot to reach each point of the reachable
space. Overall, BR-Evolution opens a new kind of learning
algorithm that simultaneously optimizes all the achievable
behaviors of a robot.