----------------- NEW EXPERIMENT ----------------{(1, 2), (0, 1)}
03000
00200
02120
00200
00000
  (Left)
03000
02000
02120
00200
00000
  (Stay)
03000
02100
02020
00200
00000
  (Stay)
03100
02000
02020
00200
00000
Reached Goal, took 3 steps