----------------- NEW EXPERIMENT ----------------{(2, 2)}
00000
00000
00300
00002
00021
  (Left)
00000
00000
00300
00002
00201
  (Stay)
00000
00000
00300
00002
00210
  (Stay)
00000
00000
00300
00012
00200
  (Stay)
00000
00000
00300
00102
00200
Reached Goal, took 4 steps