Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM (JACM)
What size net gives valid generalization?
Neural Computation
A menu of designs for reinforcement learning over time
Neural networks for control
Statistical theory of learning curves under entropic loss criterion
Neural Computation
Neurocontrol: towards an industrial control methodology
Neurocontrol: towards an industrial control methodology
Identification criteria and lower bounds for perceptron-like learning rules
Neural Computation
Adaptation and Learning in Automatic Systems
Adaptation and Learning in Automatic Systems
Hi-index | 0.00 |
Neurocontrol algorithms can be operated in a batch mode or an incremental mode. Furthermore, some of them have variants with and without an explicit plant model. These variants exhibit fundamentally different behavior with regard to the volume of data necessary for convergence. To assess this difference, simplified algorithms in a discrete state space using the dynamic programming framework are analyzed: a batch algorithm, and two incremental algorithms with and without a plant model. Analysis shows that the batch algorithm is the fastest, while the two incremental algorithms (in particular the model-free variant) are considerably slower, measured in expected number of samples to convergence.