----------------- NEW EXPERIMENT ----------------{(1, 0), (0, 2)}
10200
00000
20030
00000
00000
  (Down)
01000
00200
20030
00000
00000
  (Stay)
00000
01200
20030
00000
00000
  (Stay)
00000
00200
21030
00000
00000
  (Left)
00000
02000
20130
00000
00000
Reached Goal, took 4 steps