----------------- NEW EXPERIMENT ----------------{(3, 4), (2, 1)}
00000
00200
02120
30200
00000
  (Left)
00000
00200
20120
30200
00000
  (Stay)
00000
00200
21020
30200
00000
  (Stay)
00000
00200
20020
31200
00000
Reached Goal, took 3 steps