Fastest Convergence for Q-learning.

Adithya M. Devraj Sean P. Meyn

Published in: CoRR (2017)

Keyphrases

stochastic approximation
reinforcement learning
cooperative
state space
function approximation

stochastic shortest path
times faster
learning algorithm
convergence proof
multi agent

convergence rate
iterative algorithms
learning rate
convergence speed

convergence theorem
data sets
database
monte carlo