Linear-quadratic approximation of optimal policy problems.

Pierpaolo Benigno Michael Woodford

Published in: J. Econ. Theory (2012)

Keyphrases

optimal policy
decision problems
finite horizon
markov decision processes
dynamic programming
sufficient conditions
finite state
long run
reinforcement learning
control policies
markov decision process
state space
infinite horizon
multistage
lost sales
learning algorithm
markov decision problems