----------------- NEW EXPERIMENT ----------------{(0, 1), (0, 2)}
00000
03200
02120
00200
00000
  (Left)
00000
02000
02120
00200
00000
  (Stay)
00000
02100
02020
00200
00000
  (Stay)
00000
02100
02020
00200
00000
  (Left)
00000
23100
02020
00200
00000
Reached Goal, took 4 steps