Ilan Coulon
Results
2
comments of
Ilan Coulon
Hum, I would put it as a function defined in the default staterepresentation. Like a method that could take as an argument an array of variables we want to represent....
The reward could actually be the difference between the simple heuristic and the LearnedHeuristic? What is called "Delta" in the display during training. That would be better I think, since...