Training Recurrent Neurocontrollers for Real-Time Applications
Training Recurrent Neurocontrollers for Real-Time Applications
复制标题
DOI：
10.1109/tnn.2007.899521
复制
发表时间：
2007-07
影响因子：
--
通讯作者：
D. Prokhorov
中科院分区：
文献类型：
--
作者：
D. Prokhorov
在本文中，我们介绍了一种新的方法来训练递归神经控制器的实时应用。我们开始训练一个周期性神经控制器，以提高物理系统高保真模型的鲁棒性。对于训练，我们使用最近开发的无导数卡尔曼滤波器的方法，我们加强控制器的训练。在训练之后，我们固定了我们的递归神经控制器的权重，并将其部署在嵌入式环境中。然后，我们通过真实的调整其内部状态（短期记忆）而不是其权重（长期记忆）来对神经控制器进行额外的训练。这种实时训练是用同时扰动随机近似（SPSA）和自适应批评的新组合完成的。我们的批评者也是一个递归神经网络（RNN），它是通过随机元下降（SMD）训练的，以提高效率。我们的方法应用于两个重要的实际问题：电子油门控制和混合动力汽车控制，性能得到了明显的改善。
In this paper, we introduce a new approach to train recurrent neurocontrollers for real-time applications. We begin with training a recurrent neurocontroller for robustness on high-fidelity models of physical systems. For training, we use a recently developed derivative-free Kalman filter method which we enhance for controller training. After training, we fix weights of our recurrent neurocontroller and deploy it in an embedded environment. Then, we carry out additional training of the neurocontroller by adapting in real time its internal state (short-term memory), rather than its weights (long-term memory). Such real-time training is done with a new combination of simultaneous perturbation stochastic approximation (SPSA) and adaptive critic. Our critic is also a recurrent neural network (RNN), and it is trained by stochastic meta-descent (SMD) for increased efficiency. Our approach is applied to two important practical problems, electronic throttle control and hybrid electric vehicle control, with apparent performance improvement.