----------------- NEW EXPERIMENT ----------------{(0, 3), (2, 2)}
00000
00000
00000
20300
12000
  (Right)
00000
00000
00000
20300
10200
  (Stay)
00000
00000
00000
20300
01200
  (Stay)
00000
00000
00000
21300
00200
Reached Goal, took 3 steps