图 书 馆
因子MDP中的乐观初始化和贪婪导致多项式时间学习Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs |
|
| 课程网址: | https://videolectures.net/videos/icml09_szita_oigl |
| 主讲教师: | Istvan Szita |
| 开课单位: | 会议 |
| 开课时间: | 2009-08-26 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | In this paper we propose an algorithm for polynomial-time reinforcement learning in factored Markov decision processes (FMDPs). The factored optimistic initial model (FOIM) algorithm, maintains an empirical model of the FMDP in a conventional way, and always follows a greedy policy with respect to its model. The only trick of the algorithm is that the model is initialized optimistically. We prove that with suitable initialization (i) FOIM converges to the fixed point of approximate value iteration (AVI); (ii) the number of steps when the agent makes non-near-optimal decisions (with respect to the solution of AVI) is polynomial in all relevant quantities; (iii) the per-step costs of the algorithm are also polynomial. To our best knowledge, FOIM is the first algorithm with these properties. |
| 关 键 词: | 初始模型; 决策过程; 最优决策 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2025-04-25：liyq |
| 最后编审: | 2025-04-25：liyq |
| 阅读次数: | 10 |