George Velentzas
TitreCitée parAnnée
Active exploration and parameterized reinforcement learning applied to a simulated human-robot interaction task
M Khamassi, G Velentzas, T Tsitsimis, C Tzafestas
2017 First IEEE International Conference on Robotic Computing (IRC), 28-35, 2017
142017
Robot fast adaptation to changes in human engagement during simulated dynamic social interaction with active exploration in parameterized reinforcement learning
M Khamassi, G Velentzas, T Tsitsimis, C Tzafestas
IEEE Transactions on Cognitive and Developmental Systems 10 (4), 881-893, 2018
72018
Bio-inspired meta-learning for active exploration during non-stationary multi-armed bandit tasks
G Velentzas, C Tzafestas, M Khamassi
2017 Intelligent Systems Conference (IntelliSys), 661-669, 2017
42017
Adaptive reinforcement learning with active state-specific exploration for engagement maximization during simulated child-robot interaction
G Velentzas, T Tsitsimis, I Rañó, C Tzafestas, M Khamassi
Paladyn, Journal of Behavioral Robotics 9 (1), 235-253, 2018
12018
An extended framework for robot learning during child-robot interaction with human engagement as reward signal
M Khamassi, G Chalvatzaki, T Tsitsimis, G Velentzas, C Tzafestas
12018
Online adaptation to human engagement perturbations in simulated human-robot interaction using hybrid reinforcement learning
T Tsitsimis, G Velentzas, M Khamassi, C Tzafestas
12017
A framework for robot learning during child-robot interaction with human engagement as reward signal
M Khamassi, G Chalvatzaki, T Tsitsimis, G Velentzas, C Tzafestas
2018 27th IEEE International Symposium on Robot and Human Interactive …, 2018
2018
Bridging Computational Neuroscience and Machine Learning on Non-Stationary Multi-Armed Bandits
G Velentzas, C Tzafestas, M Khamassi
bioRxiv, 117598, 2017
2017
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–8