----------------- NEW EXPERIMENT ----------------{(1, 2), (0, 2)}
10200
00000
20300
00000
00000
  (Stay)
00200
10000
20300
00000
00000
  (Stay)
00200
01000
20300
00000
00000
  (Stay)
00200
00000
21300
00000
00000
Reached Goal, took 3 steps