A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation.

Pan Xu Quanquan Gu

Published in: ICML (2020)

Keyphrases

function approximation
reinforcement learning
neural network
model free
radial basis function
temporal difference learning
temporal difference
reinforcement learning algorithms
function approximators
temporal difference learning algorithms
mackey glass
genetic algorithm
optimal policy
learning tasks
tile coding