----------------- NEW EXPERIMENT ----------------{(1, 4), (0, 4)}
00300
00000
02020
01000
00000
  (Stay)
00300
00000
02020
00100
00000
  (Down)
00300
00000
02100
00020
00000
  (Stay)
00300
00100
02000
00020
00000
Reached Goal, took 3 steps