arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.09403stat.MLcs.LG
收藏

马尔可夫链和MDP的混合学习

Learning Mixtures of Markov Chains and MDPs

University of Michigan(密歇根大学)

Chinmaya Kausik, Kevin Tan, Ambuj Tewari

摘要:

我们提出了一个学习混合的马尔可夫链和马尔可夫决策过程(MDP)从短的未标记的轨迹的算法。具体而言,我们的方法处理混合物的马尔可夫链与可选的控制输入通过经历一个多步骤的过程,涉及(1)子空间估计步骤,(2)谱聚类的轨迹使用“成对距离估计”,以及细化使用的期望最大化算法,(3)模型估计步骤,和(4)分类步骤,用于预测标签的新轨迹。我们提供端到端的性能保证,其中我们只明确要求轨迹的长度在状态数中是线性的,并且轨迹的数量在混合时间参数中是线性的。实验结果支持这些保证,其中,我们达到96.6%的平均准确度在gridworld中的两个MDP的混合物,优于随机初始化的期望最大化算法(73.2%的平均准确度)。

英文摘要:

We present an algorithm for learning mixtures of Markov chains and Markov decision processes (MDPs) from short unlabeled trajectories. Specifically, our method handles mixtures of Markov chains with optional control input by going through a multi-step process, involving (1) a subspace estimation step, (2) spectral clustering of trajectories using "pairwise distance estimators," along with refinement using the EM algorithm, (3) a model estimation step, and (4) a classification step for predicting labels of new trajectories. We provide end-to-end performance guarantees, where we only explicitly require the length of trajectories to be linear in the number of states and the number of trajectories to be linear in a mixing time parameter. Experimental results support these guarantees, where we attain 96.6% average accuracy on a mixture of two MDPs in gridworld, outperforming the EM algorithm with random initialization (73.2% average accuracy).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑