Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning.

Adithya M. Devraj Sean P. Meyn

Published in: CoRR (2020)

Keyphrases

learning algorithm
reinforcement learning
learning process
prior knowledge
multi agent
neural network
supervised learning
action selection
data sets
active learning
unsupervised learning
mobile learning
covariance matrix
learning tasks
function approximation
td learning