Sign in
Error Bound Analysis of Q-Function for Discounted Optimal Control Problems With Policy Iteration.
Pengfei Yan
Ding Wang
Hongliang Li
Derong Liu
Published in:
IEEE Trans. Syst. Man Cybern. Syst. (2017)
Keyphrases
</>
error bounds
markov decision processes
policy iteration
theoretical analysis
optimal control
infinite horizon
optical flow
sample path
real valued
learning rate
finite state
average reward
optimal control problems