After executing the lines of code in Step 7, you will see the optimal policy values:
Optimal values:tensor([0.0000, 0.0021, 0.0052, 0.0092, 0.0129, 0.0174, 0.0231, 0.0278, 0.0323, 0.0377, 0.0435, 0.0504, 0.0577, 0.0652, 0.0695, 0.0744, 0.0807, 0.0866, 0.0942, 0.1031, 0.1087, 0.1160, 0.1259, 0.1336, 0.1441, 0.1600, 0.1631, 0.1677, 0.1738, 0.1794, 0.1861, 0.1946, 0.2017, 0.2084, 0.2165, 0.2252, 0.2355, 0.2465, 0.2579, 0.2643, 0.2716, 0.2810, 0.2899, 0.3013, 0.3147, 0.3230, 0.3339, 0.3488, 0.3604, 0.3762, 0.4000, 0.4031, 0.4077, 0.4138, 0.4194, 0.4261, 0.4346, 0.4417, 0.4484, 0.4565, 0.4652, 0.4755, 0.4865, 0.4979, 0.5043, 0.5116, 0.5210, 0.5299, 0.5413, 0.5547, 0.5630, 0.5740, 0.5888, 0.6004, 0.6162, 0.6400, 0.6446, 0.6516, ...
