Discrete-Time Optimal Control via Local Policy Iteration Adaptive Dynamic Programming.

Qinglai Wei Derong Liu Qiao Lin Ruizhuo Song

Published in: IEEE Trans. Cybern. (2017)

Keyphrases

optimal control
policy iteration
dynamic programming
optimal control problems
infinite horizon
markov decision processes
actor critic
linear quadratic

control problems
optimal policy
feedback control
reinforcement learning
approximate dynamic programming
finite state
markov decision problems
average cost

policy evaluation
control law
linear programming
average reward
stereo matching
state space
control strategy
linear program

multistage
markov decision process
data mining
markov chain
adaptive control
production planning
fixed point