Intelligent Questionnaires Using Approximate Dynamic Programming.

Frédéric Logé Erwan Le Pennec Habiboulaye Amadou Boubacar

Published in: i-com (2021)

Keyphrases

approximate dynamic programming
linear program
reinforcement learning
stochastic dynamic programming
dynamic programming
step size
factored mdps
policy iteration
neural network
control policy
cost function
linear programming
markov decision processes
fixed point
average cost