✦ LIBER ✦

A policy improvement method for constrained average Markov decision processes

✍ Scribed by Hyeong Soo Chang

Publisher: Elsevier Science
Year: 2007
Tongue: English
Weight: 136 KB
Volume: 35
Category: Article
ISSN: 0167-6377
DOI: 10.1016/j.orl.2006.09.003

No coin nor oath required. For personal study only.

✦ Synopsis

This brief paper presents a policy improvement method for constrained Markov decision processes (MDPs) with average cost criterion under an ergodicity assumption, extending Howard's policy improvement for MDPs. The improvement method induces a policy iteration-type algorithm that converges to a local optimal policy.

📜 SIMILAR VOLUMES

Comments on: “A policy improvement metho

Comments on: “A policy improvement method for constrained average Markov decision processes” [Oper. Res. Lett. 35 (2007) 434–438]

✍ Yasemin Serin 📂 Article 📅 2009 🏛 Elsevier Science 🌐 English ⚖ 307 KB

Policy iteration and Newton-Raphson meth

Policy iteration and Newton-Raphson methods for Markov decision processes under average cost criterion

✍ Masamitsu Ohnishi 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 570 KB

A new condition for the existence of opt

A new condition for the existence of optimal stationary policies in average cost Markov decision processes

✍ Linn I. Sennott 📂 Article 📅 1986 🏛 Elsevier Science 🌐 English ⚖ 490 KB

Conditions for existence of average and

Conditions for existence of average and Blackwell optimal stationary policies in denumerable Markov decision processes

✍ J.B Lasserre 📂 Article 📅 1988 🏛 Elsevier Science 🌐 English ⚖ 504 KB

Finite state approximations for denumera

Finite state approximations for denumerable-state infinite horizon contracted Markov decision processes: The policy space method

✍ D.J White 📂 Article 📅 1979 🏛 Elsevier Science 🌐 English ⚖ 411 KB