----------------- NEW EXPERIMENT ----------------{(4, 1), (1, 4)}
10200
00000
20300
00000
00000
  (Down)
00200
10000
00300
20000
00000
  (Stay)
00200
01000
00300
20000
00000
  (Stay)
00200
00000
01300
20000
00000
Reached Goal, took 3 steps