Abstract— We propose to improve the locomotive performance of humanoid robots by using approximated biped stepping and walking dynamics with reinforcement learning (RL). Although...
Jun Morimoto, Christopher G. Atkeson, Gen Endo, Go...
The efficient use of network capacity in shared restoration schemes strongly depends upon the path selection procedure. In this paper we propose and evaluate path selection algorit...
Chadi Assi, Ahmad Khalil, Nasir Ghani, Abdallah Sh...
Traffic engineering of IP networks requires the characterization and modeling of network traffic on multiple time scales due to the existence of several statistical properties that...
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Abstract. Many evolutionary algorithm applications involve either fitness functions with high time complexity or large dimensionality (hence very many fitness evaluations will typi...