Login / Signup
Feature-Modell-geführtes Online Reinforcement Learning für Selbst-adaptive Systeme.
Andreas Metzger
Clément Quinton
Zoltán Ádám Mann
Luciano Baresi
Klaus Pohl
Published in:
Software Engineering (2021)
Keyphrases
</>
reinforcement learning
online learning
function approximation
feature vectors
learning capabilities
real time
optimal control
learning process
database
multi agent
multiscale
relevance feedback
feature set
information retrieval
machine learning
neural network
temporal difference learning