Title :
A Policy Improvement Method in Constrained Stochastic Dynamic Programming
Author :
Chang, Hyeong Soo
Author_Institution :
Dept. of Comput. Sci. & Eng., Sogang Univ., Seoul
Abstract :
This note presents a formal method of improving a given base-policy such that the performance of the resulting policy is no worse than that of the base-policy at all states in constrained stochastic dynamic programming. We consider finite horizon and discounted infinite horizon cases. The improvement method induces a policy iteration-type algorithm that converges to a local optimal policy
Keywords :
Markov processes; dynamic programming; set theory; stochastic programming; constrained Markov decision process; constrained stochastic dynamic programming; discounted infinite horizon cases; finite horizon cases; policy iteration-type algorithm; Business; Cost function; Dynamic programming; Equations; Infinite horizon; Intelligent robots; Optimal control; Probability distribution; Random variables; Stochastic processes; Constrained Markov decision process; dynamic programming; policy improvement; policy iteration;
Journal_Title :
Automatic Control, IEEE Transactions on
DOI :
10.1109/TAC.2006.880801
