Having now obtained the npv, a more business-like measurement must be implemented.
A warehouse manager, for example, will tell you the following:
- Your reinforcement learning program looks satisfactory (Chapter 1, Become an Adaptive Thinker)
- The reward matrix generated by the McCulloch-Pitts neurons works very well (Chapter 2, Think Like a Machine)
- The convergence values of the system look nice
- The results on this dataset look satisfactory
But then, the manager will always come up with a killer question, How can you prove that this will work with other datasets in the future?
The only way to be sure that this whole system works is to run thousands of datasets with hundreds of thousands ...
