期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS
卷 18, 期 4, 页码 1003-1015出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNN.2007.899521
关键词
neurocontroller; real-time adaptation; recurrent neural network (RNN); stochastic meta-descent (SMD); simultaneous perturbation stochastic approximation (SPSA); training for robustness
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据