Tyrone Hou, Mark Bestavros, Brian Siao, Sean Zhang
Robust Airborne Collision Avoidance through Dynamic Programming
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.207.7337&rep=rep1&type=pdf
Policy Compression for Aircraft Collision Avoidance Systems
https://web.stanford.edu/group/sisl/references/2016/julian2016.pdf
Reinforcement Learning: An Introduction
http://ufal.mff.cuni.cz/~straka/courses/npfl114/2016/sutton-bookdraft2016sep.pdf