AutoLR: An Evolutionary Approach to Learning Rate Policies.

Pedro Carvalho Nuno Lourenço Filipe Assunção Penousal Machado

Published in: CoRR (2020)

Keyphrases

learning rate
discount factor
learning algorithm
convergence rate
error function
rapid convergence
hidden layer
multilayer neural networks
optimal policy
adaptive learning rate
activation function
training algorithm
convergence speed
reward function
convergence theorem
markov decision processes
delta bar delta