Air Traffic Reschedualing [1]. The algorithm is using hard constraints rather than soley relying on machine learning. I believe that the paper is essentially describing a SAT solver strategy that is used by a machine learning algorithm. The agorithm should also great for employee reschedualing, or any kind of reschedualing where you want to find the nearest solution anytime the last known solution is invalidated by a state change.

[1] https://www.researchgate.net/publication/259823636_Addressin...