基于开关密度网络的混合系统辨识
Hybrid system identification using switching density networks
摘要：
行为克隆是模仿学习的一种常用策略，在受限领域中非常有效。然而，在环境的动态可能是依赖于状态和变化的情况下，行为克隆会对模型容量和所需的演示次数造成负担。本文介绍了开关密度网络，它依赖于混合系统辨识的分类重新参数化。这导致包括分类层的网络，该分类层之后是回归层。我们使用开关密度网络来预测混合控制律的参数，当以输入状态为条件时，混合控制律由开关层切换以产生不同的控制器输出。这项工作显示了如何切换密度网络可以用于混合系统辨识在各种任务，成功地识别关键的关节角度的目标，使操纵任务，同时学习基于图像的目标分类器和回归网络，预测关节角度从图像。我们还表明，他们可以集群的相空间的倒立摆，确定的平衡，自旋和泵控制器需要解决这个任务。开关密度网络可能很难训练，但我们引入了一个交叉熵正则化损失，稳定训练。
英文摘要：
Behaviour cloning is a commonly used strategy for imitation learning and can be extremely effective in constrained domains. However, in cases where the dynamics of an environment may be state dependent and varying, behaviour cloning places a burden on model capacity and the number of demonstrations required. This paper introduces switching density networks, which rely on a categorical reparametrisation for hybrid system identification. This results in a network comprising a classification layer that is followed by a regression layer. We use switching density networks to predict the parameters of hybrid control laws, which are toggled by a switching layer to produce different controller outputs, when conditioned on an input state. This work shows how switching density networks can be used for hybrid system identification in a variety of tasks, successfully identifying the key joint angle goals that make up manipulation tasks, while simultaneously learning image-based goal classifiers and regression networks that predict joint angles from images. We also show that they can cluster the phase space of an inverted pendulum, identifying the balance, spin and pump controllers required to solve this task. Switching density networks can be difficult to train, but we introduce a cross entropy regularisation loss that stabilises training.
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。
