Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming

标题
Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming
作者
关键词
-
出版物
MATHEMATICS OF OPERATIONS RESEARCH
Volume 37, Issue 1, Pages 66-94
出版商
Institute for Operations Research and the Management Sciences (INFORMS)
发表日期
2012-01-14
DOI
10.1287/moor.1110.0532

向作者/读者发起求助以获取更多资源

Find Funding. Review Successful Grants.

Explore over 25,000 new funding opportunities and over 6,000,000 successful grants.

Explore

Ask a Question. Answer a Question.

Quickly pose questions to the entire community. Debate answers and get clarity on the most important issues facing researchers.

Get Started