Deep Reinforcement Learning using Cyclical Learning Rates.

Ralf Gulde Marc Tuscher Akos Csiszar Oliver Riedel Alexander Verl

Published in: CoRR (2020)

Keyphrases

learning rate
reinforcement learning
learning algorithm
convergence rate
function approximation
covering numbers
convergence speed
gaussian kernels
uniform convergence
supervised learning
convergence theorem
active learning
learning process
multi class
learning tasks
machine learning
training data
weight vector