The place on Earth from which you can, in theory, see further than any other is between an unnamed Himalayan ridge near the Indian-Chinese border and Pik Dankova in Kyrgyzstan. It is just over 530km.
Extending Direct Nash Optimization for Regularized Preferences | HackerNoon
The extension of the Direct Nash Optimization (DNO) framework includes handling regularized preferences, distinguishing it from Nash-MD by utilizing smoothed policies for better guarantees.