Approximate Dynamic Programming II:Algorithms

相似文件 换一批

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Warren B. Powell  December 8, 2009
Approximate dynamic programming is a powerful class of algorithmic strategies for solving stochastic
optimization problems where optimal decisions can be characterized using Bellman's optimality equa-
tion, but where the characteristics of the problem make solving Bellman's equation computationally
intractable. This brief chapter provides an introduction to the basic concepts of approximate dy-
namic programming while building bridges between the different erent communities that have contributed
to this field. We cover basic approximate value iteration (temporal difference learning), policy ap-
proximation, and a brief introduction to strategies for approximating value functions. We cover
Q-learning, and the use of the post-decision state for solving problems with vector-valued decisions.
The approximate linear programming method is introduced, along with a discussion of stepsize se-
lection issues. The presentation closes with a discussion of some practical issues that arise in the
implementation of ADP techniques.

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Programming Approximate Algorithms Algorithm Dynamic Programming Dynamic Approximate

坑了，10个币，google直接有免费现成的。

http://www.castlelab.princeton.edu/Papers/EORMS-ADP_Algorithms_Dec72009.pdf