Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme.

Konstantin Avrachenkov Vivek S. Borkar H. P. Dolhare K. Patil

Published in: CoRR (2021)

Keyphrases

provably convergent
reinforcement learning
shape from shading
state space
policy gradient
detection scheme
optimal control
image gradient
model free
learning scheme
learning algorithm
function approximation
action selection
optimal policy
least squares
gradient information
search space
multi agent
gauss seidel