----------------- NEW EXPERIMENT ----------------{(0, 1), (0, 2)}
03000
00000
02010
20000
00000
  (Stay)
03000
00000
02100
20000
00000
  (Stay)
03000
00100
02000
20000
00000
  (Stay)
03000
01000
02000
20000
00000
Reached Goal, took 3 steps