An important element of adaptive control is learning of the drifting parameters. As the process unfolds, additional information becomes available, which will provide learning for the purpose of control. This informati...
详细信息
An important element of adaptive control is learning of the drifting parameters. As the process unfolds, additional information becomes available, which will provide learning for the purpose of control. This information may come about accidentally through past control actions or as a result of active probing, which itself is a possible control policy. Thus learning is present, where it is accidental or deliberate. Since more learning may improve overall control performance, the probing signal may indirectly help in controlling the stochastic system. On the other hand, excessive probing should not be allowed even though it may promote learning because it is expensive in the sense that it will, in general, increase the expected cost performance of the system. A good control law must then regulate its adaptation (learning) in an optimal manner. An adaptive control method is called passively adaptive if learning is not planned in the manner described above; it is called actively adaptive if learning is planned and regulated for the purpose of final control. This paper gives an overview of adaptive control methods which were developed based on the concept of active learning for control purposes. Some comments on their practicality are also given.
In this paper, a learning controller model is applied to the on-line optimization of a general class of discrete stochastic control systems. Stochastic properties of the plant are unknown to the designer. Using the pl...
详细信息
In this paper, a learning controller model is applied to the on-line optimization of a general class of discrete stochastic control systems. Stochastic properties of the plant are unknown to the designer. Using the plant's output, the controller iteratively applys a reinforcementlearning algorithm to learn the optimum control policy while minimizing an expected performance index. A technique that accelerates learning and improves performance is discussed. Computer simulation results of the successful application of the learning controller model to several different cases are presented.
Despite the extensive literature on adaptive systems, relatively little progress has been made so far toward the development of a general theory of adaptation. Among the more promising and mathematically concrete appr...
详细信息
Despite the extensive literature on adaptive systems, relatively little progress has been made so far toward the development of a general theory of adaptation. Among the more promising and mathematically concrete approaches to the design of adaptive systems are the dynamicprogramming formulation due to Bellman and Kalaba, the empirical Bayes and stochastic approximation methods developed by Robbins, and the learning algorithms used in pattern recognition. The advantages and shortcomings of these approaches are pointed out and alternative points of view are briefly analyzed.
暂无评论