图 书 馆
多项式时间内的近贝叶斯探测Near-Bayesian Exploration in Polynomial Time |
|
| 课程网址: | http://videolectures.net/icml09_kolter_nbept/ |
| 主讲教师: | J. Zico Kolter |
| 开课单位: | 卡内基梅隆大学 |
| 开课时间: | 2009-08-26 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We consider the exploration/exploitation problem in reinforcement learning (RL). The Bayesian approach to model-based RL offers an elegant solution to this problem, by considering a distribution over possible models and acting to maximize expected reward; unfortunately, the Bayesian solution is intractable for all but very restricted cases. In this paper we present a simple algorithm, and prove that with high probability it is able to perform epsilon-close to the true (intractable) optimal Bayesian policy after some small (polynomial in quantities describing the system) number of time steps. The algorithm and analysis are motivated by the so-called PAC-MDP approach, and extend such results into the setting of Bayesian RL. In this setting, we show that we are able to achieve lower sample complexity bounds than existing PAC-MDP algorithms, while using exploration strategies that are much greedier than the (extremely cautious) exploration strategies used by these existing algorithms. |
| 关 键 词: | 计算机科学; 强化学习; 贝叶斯 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-09-24：dingaq |
| 阅读次数: | 31 |