Hi @JavierAntoran @stratisMarkou,

First of all, thanks for making all of this code available - it's been great to look through!

Im currently spending some time trying to work through the Weight Uncertainty in Neural Networks in order to implement Bayes-by-Backprop. I was struggling to understand the difference between your implementation of `Bayes-by-Bac

As raised by #307, we should add better documentation of the distributions you can select for inputs to a problem.

Problem

Currently, conflicts created by the uncertainty module in the simulation is not preventable if the scheduler doesn't reschedule every tick. Instead, these kinds of conflicts lead to an early termination to reflect the real world: "if there's a crash in the airport, there's no way the airport will continue to function properly."

Solution

Therefore, we need a pilot behavior de

The error message for lolopy when java isn't installed is: ValueError: invalid literal for int() with base 10: b''

We should make a better error message for this issue, and probably print warnings if you're running on Windows and the confidence intervals are not likely to work.

There are several things in the code that are not done optimally (detection of facial images could be improved), or by using brute-force (serialization of gray and red rectangles used to represent decision ambiguity).