Access to the back of the store, basically if you can track them entering and leaving an employees only area.
But this requires a really good tracking algorithm and if you lose track you're going to have to fall back on some other properties.
If you use RNNs, then I think the solution is to use padding (zero padding) with max sequence length (that is the max number of words in a text) in order to tell your model to skip the zeros when possible. In that way, your model will try to learn a good representation of your input with fixed size. If you do not know this dimension, a solution may be to ...
Is there an AI technology out there or being developed that can
predict human behaviour ?
If it can predict (all) human behavior, it can act as an human, thus, it will be the first real (strong) AI. This has not happened yet.
I must remark that the question contains a lot of weakly defined terms. Fix these terms can help to work in the question subject:
Another good (although a bit old) and freely available online book (apart from the one suggested in this answer) is Neural Networks - A Systematic Introduction (1996) by Raul Rojas. This book contains several exercises at the end of each chapter and covers topics that you will not find in many online courses.
I think it's difficult to tell wich algorithm is "the best" or "the simplest".
I had the same issue of choosing the suited NLP algorithm for my dataset and I used :
Then I recommanded you to test many algorithms as you can to find the best for your needed.
Firstly, note that the Gaussian policies you describe are not equivalent to $\epsilon$-greedy, mainly for this reason: for a fixed policy, the policy's variance in the Gaussian case depends on the state, while in the $\epsilon$-greedy case it does not. Right off the bat, the Gaussian policy should achieve less regret than $\epsilon$-greedy.
Other approaches ...