----------------- NEW EXPERIMENT ----------------{(3, 1), (2, 2)}
03000
00200
02120
00200
00000
  (Left)
03000
00200
20120
00200
00000
  (Stay)
03000
00200
21020
00200
00000
  (Stay)
03000
01200
20020
00200
00000
Reached Goal, took 3 steps