Value iteration and adaptive optimal output regulation with assured convergence rate

2022 ◽  
Vol 121 ◽  
pp. 105042
Author(s):  
Yi Jiang ◽  
Weinan Gao ◽  
Jing Na ◽  
Di Zhang ◽  
Timo T. Hämäläinen ◽  
...  
Keyword(s):  
Convergence Rate ◽  
Output Regulation ◽  
Value Iteration ◽  
Optimal Output

Geometric convergence of value-iteration in multichain Markov decision problems

1979 ◽  
Vol 11 (01) ◽  
pp. 188-217 ◽  
Author(s):  
P. J. Schweitzer ◽  
A. Federgruen
Keyword(s):  
Convergence Rate ◽  
Iteration Method ◽  
Chain Structure ◽  
Decision Problems ◽  
Value Iteration ◽  
Convergence Factor ◽  
Markov Decision Problems ◽  
Geometric Convergence ◽  
Markov Decision ◽  
Maximal Gain

This paper considers undiscounted Markov decision problems. With no restriction (on either the periodicity or chain structure of the problem) we show that the value iteration method for finding maximal gain policies exhibits a geometric rate of convergence, whenever convergence occurs. In addition, we study the behaviour of the value-iteration operator; we give bounds for the number of steps needed for contraction, describe the ultimate behaviour of the convergence factor and give conditions for the existence of a uniform convergence rate.

On optimal output regulation for linear systems

2003 ◽  
Vol 76 (4) ◽  
pp. 319-333 ◽  
Author(s):  
Ali Saberi ◽  
Anton A. Stoorvogel ◽  
Peddapullaiah Sannuti ◽  
Guoyong Shi
Keyword(s):  
Linear Systems ◽  
Output Regulation ◽  
Optimal Output

Balanced realization for state-space identification and optimal output regulation

AIChE Journal ◽  
1995 ◽  
Vol 41 (5) ◽  
pp. 1217-1228
Author(s):  
W. Fred Ramirez ◽  
Jan M. Maciejowski
Keyword(s):  
State Space ◽  
Output Regulation ◽  
Balanced Realization ◽  
Optimal Output
Sign in / Sign up

Export Citation Format

Share Document