TY - GEN
T1 - Balancing Exploration and Exploitation
T2 - International Workshop on Human-Friendly Robotics
AU - Houbre, Quentin
AU - Angleraud, Alexandre
AU - Pieters, Roel
N1 - JUFOID=88693
PY - 2021
Y1 - 2021
N2 - The learning of sensorimotor contingencies is essential for the development of early cognition. Here, we investigate how such process takes place on a neural level. We propose a theoretical concept for learning sensorimotor contingencies based on motor babbling with a robotic arm and dynamic neural fields. The robot learns to perform sequences of motor commands in order to perceive visual activation from a baby mobile toy. First, the robot explores the different sensorimotor outcomes, then autonomously decides to utilize (or not) the experience already gathered. Moreover, we introduce a neural mechanism inspired by recent neuroscience research that supports the switch between exploration and exploitation. The complete model relies on dynamic field theory, which consists of a set of interconnected dynamical systems. In time, the robot demonstrates a behavior toward the exploitation of previously learned sensorimotor contingencies and thus selecting actions that induce high visual activation.
AB - The learning of sensorimotor contingencies is essential for the development of early cognition. Here, we investigate how such process takes place on a neural level. We propose a theoretical concept for learning sensorimotor contingencies based on motor babbling with a robotic arm and dynamic neural fields. The robot learns to perform sequences of motor commands in order to perceive visual activation from a baby mobile toy. First, the robot explores the different sensorimotor outcomes, then autonomously decides to utilize (or not) the experience already gathered. Moreover, we introduce a neural mechanism inspired by recent neuroscience research that supports the switch between exploration and exploitation. The complete model relies on dynamic field theory, which consists of a set of interconnected dynamical systems. In time, the robot demonstrates a behavior toward the exploitation of previously learned sensorimotor contingencies and thus selecting actions that induce high visual activation.
KW - Developmental robotics
KW - Dynamic field theory
KW - Neural networks
KW - Sensorimotor contingencies
U2 - 10.1007/978-3-030-71356-0_5
DO - 10.1007/978-3-030-71356-0_5
M3 - Conference contribution
AN - SCOPUS:85107019979
SN - 978-3-030-71355-3
SN - 978-3-030-71358-4
T3 - Springer Proceedings in Advanced Robotics
SP - 59
EP - 73
BT - Human-Friendly Robotics 2020
A2 - Saveriano, Matteo
A2 - Renaudo, Erwan
A2 - Rodríguez-Sánchez, Antonio
A2 - Piater, Justus
PB - Springer
Y2 - 1 October 2020 through 2 October 2020
ER -