Parameter Critic: a Model Free Variance Reduction Method Through Imperishable Samples.

Juan Cerviño Harshat Kumar Alejandro Ribeiro

Published in: CoRR (2020)

Keyphrases

model free
reduction method
reinforcement learning algorithms
temporal difference
function approximation
reinforcement learning
selection algorithm
policy iteration
data sets
knowledge base
training data
variance reduction
machine learning
genetic algorithm
search algorithm
least squares