图 书 馆
基于有限视界的马尔可夫决策过程中的拉格朗日对偶分解Lagrange Dual Decomposition for Finite Horizon Markov Decision Processes |
|
| 课程网址: | http://videolectures.net/ecmlpkdd2011_furmston_lagrange/ |
| 主讲教师: | Thomas Furmston |
| 开课单位: | 伦敦大学学院 |
| 开课时间: | 2011-11-30 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Solving finite-horizon Markov Decision Processes with stationary policies is a computationally difficult problem. Our dynamic dual decomposition approach uses Lagrange duality to decouple this hard problem into a sequence of tractable sub-problems. The resulting procedure is a straightforward modification of standard non-stationary Markov Decision Process solvers and gives an upper-bound on the total expected reward. The empirical performance of the method suggests that not only is it a rapidly convergent algorithm, but that it also performs favourably compared to standard planning algorithms such as policy gradients and lower-bound procedures such as Expectation Maximisation. |
| 关 键 词: | 平稳策略; 马尔可夫决策; 双重分解 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-10-22：chenxin |
| 阅读次数: | 114 |