A policy iteration heuristic for constrained discounted controlled Markov Chains

作者：Chang Hyeong Soo^*

来源：Optimization Letters, 2012, 6(7): 1573-1577.

DOI：10.1007/s11590-011-0338-7

• Constrained Markov decision process
• Policy iteration
• Policy improvement

This brief paper presents a policy-improvement method of generating a feasible stochastic policy (pi) over tilde from a given feasible stochastic base-policy pi such that (pi) over tilde improves all of the feasible policies %26quot;induced%26quot; from pi for infinite-horizon constrained discounted controlled Markov chains (CMCs). A policy-iteration heuristic for approximately solving constrained discounted CMCs is developed from this improvement method.

• 出版日期2012-10