0


学习部分可观察的动态系统之间的差异

Learning the Difference between Partially Observable Dynamical Systems
课程网址: http://videolectures.net/ecmlpkdd09_laviolette_ldbp/  
主讲教师: François Laviolette
开课单位: 拉瓦尔大学
开课时间: 信息不详。欢迎您在右侧留言补充。
课程语种: 英语
中文简介:
我们提出了一种新的方法来估计两个部分可观测动力系统之间的差异。我们假设一个人可以通过执行操作和接收观察来与系统交互。关键思想是在待比较系统的基础上定义一个马尔可夫决策过程（MDP），这样，MDP初始状态的最佳值可以解释为系统之间的分歧（或不同）。这种差异可以通过强化学习方法来估计。此外，最优策略将包含有关最能区分系统的操作的信息。实验结果表明，该方法既能检测大、小的差异，又能比较不同内部结构的系统。
课程简介: We propose a new approach for estimating the difference between two partially observable dynamical systems. We assume that one can interact with the systems by performing actions and receiving observations. The key idea is to define a Markov Decision Process (MDP) based on the systems to be compared, in such a way that the optimal value of the MDP initial state can be interpreted as a divergence (or dissimilarity) between the systems. This dissimilarity can then be estimated by reinforcement learning methods. Moreover, the optimal policy will contain information about the actions which most distinguish the systems. Empirical results show that this approach is useful in detecting both big and small differences, as well as in comparing systems with different internal structure.
关 键 词: 机器学习; 动力系统; 马尔科夫决策过程（MDP）
课程来源: 视频讲座网
最后编审: 2019-12-05：cwx
阅读次数: 27

纠错/补充/评论/留言
评论/留言 纠错/补充
验证算术题： 1 + 6 =