----------------- NEW EXPERIMENT ----------------{(1, 2), (2, 1)}
00000
00300
00000
00002
00021
  (Left)
00000
00300
00000
00002
00201
  (Stay)
00000
00300
00000
00002
00210
  (Stay)
00000
00300
00000
00012
00200
  (Stay)
00000
00300
00010
00002
00200
  (Stay)
00000
00300
00100
00002
00200
Reached Goal, took 5 steps