----------------- NEW EXPERIMENT ----------------{(0, 1), (2, 0)}
03000
00200
02120
00200
00000
  (Left)
03000
00200
20120
00200
00000
  (Down)
03000
00200
01020
20200
00000
  (Stay)
03000
01200
00020
20200
00000
Reached Goal, took 3 steps