Title :
Learning control heuristics
Author :
Lambert, J. ; Levine, Martin
Author_Institution :
McGill University, Montreal, PQ, Canada
fDate :
12/1/1968 12:00:00 AM
Abstract :
The problem of defining a switching boundary for a learning control system using the concept of reinforcement of a subgoal is discussed. If the state space is quantized into sample set regions, it is shown that the boundary sets are unevenly reinforced because they do not lie symmetrically on the subgoal contours.
Keywords :
Learning control systems; Bang-bang control; Control systems; Encoding; Equations; Optimal control; Quantization; State-space methods; Testing; Transfer functions; Uncertainty;
Journal_Title :
Automatic Control, IEEE Transactions on
DOI :
10.1109/TAC.1968.1099059
