Apprenticeship learning in an incompatible feature space
Apprenticeship learning in an incompatible feature space
复制标题
DOI：
10.1109/icra.2017.7989113
复制
发表时间：
2017-05
期刊：
影响因子：
--
通讯作者：
Gakuto Masuyama;K. Umeda
中科院分区：
文献类型：
--
作者：
Gakuto Masuyama;K. Umeda
本研究提出了一种新的学徒学习方法，使学习者能够利用不兼容的特征空间中观察到的演示。假设专家和学习者遵循不同的马尔可夫决策过程（MDP），通过估计映射函数得到Agent空间中演示的特征期望.使用条件密度估计技术以封闭形式表示特征期望。所提出的方法很有用，因为它有望减轻为学徒学习显式指定异构MDP的对应关系的棘手过程。此外，该方法不需要任何采样方法来近似代理特征空间上的积分。一个模拟是用来证明所提出的方法在三个领域中，它是不可能直接比较的专家和学习者的功能的有效性。
This study presents a novel apprenticeship learning method to enable a learner to utilize demonstrations observed in an incompatible feature space. It is assumed that an expert and a learner follow non-identical Markov decision processes (MDPs), and a mapping function is estimated to obtain feature expectation of the demonstrations in an agent space. A conditional density estimation technique is used to represent the feature expectation in closed-form. The proposed method is useful because it is expected to alleviate intractable processes to explicitly specify correspondence of heterogeneous MDPs for apprenticeship learning. Additionally, the method does not require any sampling method to approximate integrals over an agent feature space. A simulation is used to demonstrate the validity of the proposed method in three domains in which it is not possible to directly compare the features of the expert and learner.