图 书 馆
分区的线性规划逼近问题Partitioned Linear Programming Approximations for MDPs |
|
| 课程网址: | http://videolectures.net/uai08_kveton_plpa/ |
| 主讲教师: | Branislav Kveton |
| 开课单位: | Adobe公司 |
| 开课时间: | 2008-07-30 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Approximate linear programming (ALP) is an efficient approach to solving large factored Markov decision processes (MDPs). The main idea of the method is to approximate the optimal value function by a set of basis functions and optimize their weights by linear programming (LP). This paper proposes a new ALP approximation. Comparing to the standard ALP formulation, we decompose the constraint space into a set of low-dimensional spaces. This structure allows for solving the new LP efficiently. In particular, the constraints of the LP can be satisfied in a compact form without an exponential dependence on the tree width of ALP constraints. We study both practical and theoretical aspects of the proposed approach. Moreover, we demonstrate its scale-up potential on an MDP with more than 2100 states. |
| 关 键 词: | 近似线性规划; 大保理马尔可夫决策; 低维空间 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-19：cxin |
| 阅读次数: | 48 |