----------------- NEW EXPERIMENT ----------------{(1, 2), (3, 2)}
03000
00000
00200
12000
00000
  (Stay)
03000
00000
10200
02000
00000
  (Stay)
03000
10000
00200
02000
00000
  (Stay)
03000
01000
00200
02000
00000
Reached Goal, took 3 steps