BriefGPT.xyz
Apr, 2017
驾驶员行为模仿的同时策略学习和潜在状态推断
Simultaneous Policy Learning and Latent State Inference for Imitating Driver Behavior
HTML
PDF
Jeremy Morton, Mykel J. Kochenderfer
TL;DR
本研究提出了一种基于学习驾驶员模型的方法，该模型能够考虑不能直接观测到的变量，并学习区分四类不同驾驶员行为的编码。通过该方法，得到的驾驶策略在模拟真实驾驶行为方面比基准方法更为有效，并且策略选择的行为明显受到所提供的潜变量设置的影响。
Abstract
In this work, we propose a method for learning
driver models
that account for variables that cannot be observed directly. When trained on a synthetic dataset, our models are able to learn encodings for
vehicle trajector
→