2
$\begingroup$

Not talking about the actual moon lander, but an old game that was inspired by it (see screenshot).

Suppose I wanted to write a program that "plays" this game:

  • Can only operate the vertical thruster (on/off)
  • Does not know how much thrust is produced
  • Does not know about the vehicle's inertia, weight, etc.
  • Does know its current velocity / height from the ground
  • The program's only goal would be to aim for a descent of 10 pixels / second

What kind of algorithm would I use for this? E.g. the program would hit the thruster for 1s, evaluate its effect, if descent is too fast, try again for 2s, if it's too slow, wait for 1s, and so on.

I think that some sort of simple table-based Machine Learning algorithm would work. But it's been a few years since I took the computer learning class as a student.

What are your suggestions?

moon lander

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.