— This paper demonstrates a learning mechanism for complex tasks. Such tasks may be inherently expensive to learn in terms of training time and/or cost of obtaining each training...
— This paper proposes a learning framework for a CPG-based biped locomotion controller using a policy gradient method. Our goal in this study is to develop an efficient learning...
Takamitsu Matsubara, Jun Morimoto, Jun Nakanishi, ...
Courseware increasingly consists of generic information and communication tools. These offer a plethora of functionalities, but their usefulness to a particular learning community ...
A novel method to improve the generalization performance of the Minimum Classification Error (MCE) / Generalized Probabilistic Descent (GPD) learning is proposed. The MCE/GPD learn...
The paper presents an evaluation method for e-learning platforms, based on different types of measurements collected in logs of interactions during learning sessions, and on the an...
Vlad Posea, Dan Mihaila, Stefan Trausan-Matu, Vale...