----------------- NEW EXPERIMENT ----------------{(0, 3), (1, 3)}
12000
00230
00000
00000
00000
  (Stay)
02000
10230
00000
00000
00000
  (Down)
02000
01030
00200
00000
00000
  (Stay)
02000
00130
00200
00000
00000
Reached Goal, took 3 steps