乐观的许多面孔:一个统一的方法The Many Faces of Optimism: a Unifying Approach |
|
课程网址: | http://videolectures.net/icml08_szita_mfo/ |
主讲教师: | Istvan Szita |
开课单位: | 洛夫大学 |
开课时间: | 2008-08-06 |
课程语种: | 英语 |
中文简介: | 在强化学习的框架内, 勘探开发困境一直是一个有趣而又尚未解决的问题。面对不确定性和模型构建的乐观在先进的勘探方法中发挥着核心作用。在这里, 我们集成了几个概念, 并获得了一个快速而简单的算法。结果表明, 该算法在多项式时间内找到了一个近乎最优的策略, 并给出了与上升算法相比该算法的鲁棒性和有效性的实验证据。 |
课程简介: | The exploration-exploitation dilemma has been an intriguing and unsolved problem within the framework of reinforcement learning. Optimism in the face of uncertainty and model building play central roles in advanced exploration methods. Here, we integrate several concepts and obtain a fast and simple algorithm. We show that the proposed algorithm finds a near-optimal policy in polynomial time, and give experimental evidence that it is robust and efficient compared to its ascendants. |
关 键 词: | 机器学习; 强化学习; 勘探开发困境 |
课程来源: | 视频讲座网 |
最后编审: | 2020-11-13:yumf |
阅读次数: | 61 |