['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'brac', '--traj', 'expert', '--seed', '3', '--data', '100000']
epoch: 0 training_loss 4.530844778232276 test_loss: 0.12285938262939453
epoch: 1 training_loss -1.5774719357490539 test_loss: -2.731883239746094
epoch: 2 training_loss -3.566017807722092 test_loss: -4.110676956176758
epoch: 3 training_loss -4.706734807491302 test_loss: -5.145015716552734
epoch: 4 training_loss -5.578643870353699 test_loss: -5.964890670776367
epoch: 5 training_loss -6.40620292186737 test_loss: -6.720635986328125
epoch: 6 training_loss -6.99507474899292 test_loss: -7.23675537109375
epoch: 7 training_loss -7.505102534294128 test_loss: -7.617256927490234
epoch: 8 training_loss -7.81346821308136 test_loss: -7.943735504150391
epoch: 9 training_loss -8.21689124584198 test_loss: -8.41824722290039
epoch: 10 training_loss -8.561156649589538 test_loss: -8.500641632080079
epoch: 11 training_loss -8.82665379524231 test_loss: -8.868350219726562
epoch: 12 training_loss -9.117160711288452 test_loss: -9.176931762695313
epoch: 13 training_loss -9.37668417930603 test_loss: -9.454200744628906
epoch: 14 training_loss -9.59010293006897 test_loss: -9.674971008300782
epoch: 15 training_loss -9.838537225723266 test_loss: -9.809033203125
epoch: 16 training_loss -10.12321349143982 test_loss: -9.974614715576172
epoch: 17 training_loss -10.24587869644165 test_loss: -10.25972900390625
epoch: 18 training_loss -10.35870153427124 test_loss: -10.473265838623046
epoch: 19 training_loss -10.637880878448486 test_loss: -10.764148712158203
epoch: 20 training_loss -10.718831510543824 test_loss: -10.878787231445312
epoch: 21 training_loss -10.799988498687744 test_loss: -10.84655303955078
epoch: 22 training_loss -11.080099439620971 test_loss: -11.122323608398437
epoch: 23 training_loss -11.210957717895507 test_loss: -11.344589996337891
epoch: 24 training_loss -11.349903450012206 test_loss: -11.174684143066406
epoch: 25 training_loss -11.516064319610596 test_loss: -11.56896743774414
epoch: 26 training_loss -11.60117000579834 test_loss: -11.707315063476562
epoch: 27 training_loss -11.79869125366211 test_loss: -11.841336822509765
epoch: 28 training_loss -11.860676908493042 test_loss: -11.67565689086914
epoch: 29 training_loss -12.038904848098754 test_loss: -12.15353012084961
epoch: 30 training_loss -12.083939323425293 test_loss: -12.02138442993164
epoch: 31 training_loss -12.23401086807251 test_loss: -12.022662353515624
epoch: 32 training_loss -12.34683557510376 test_loss: -12.315938568115234
epoch: 33 training_loss -12.41041898727417 test_loss: -12.43589096069336
epoch: 34 training_loss -12.48932867050171 test_loss: -12.481822204589843
epoch: 35 training_loss -12.571548194885255 test_loss: -12.729449462890624
epoch: 36 training_loss -12.6821661567688 test_loss: -12.672119903564454
epoch: 37 training_loss -12.743281126022339 test_loss: -12.767836761474609
epoch: 38 training_loss -12.765015439987183 test_loss: -12.765328216552735
epoch: 39 training_loss -12.920864124298095 test_loss: -12.838096618652344
epoch: 40 training_loss -12.949170951843263 test_loss: -13.033906555175781
epoch: 41 training_loss -13.044169263839722 test_loss: -12.872129821777344
epoch: 42 training_loss -13.113952684402467 test_loss: -12.999066162109376
epoch: 43 training_loss -13.118855457305909 test_loss: -13.037519836425782
epoch: 44 training_loss -13.247328252792359 test_loss: -13.1590087890625
epoch: 45 training_loss -13.294452695846557 test_loss: -13.370491027832031
epoch: 46 training_loss -13.377579488754272 test_loss: -13.491949462890625
epoch: 47 training_loss -13.428223648071288 test_loss: -13.425003051757812
epoch: 48 training_loss -13.499991321563721 test_loss: -13.508558654785157
epoch: 49 training_loss -13.462608699798585 test_loss: -13.541197204589844
epoch: 50 training_loss -13.605647678375243 test_loss: -13.464657592773438
epoch: 51 training_loss -13.716912364959716 test_loss: -13.676014709472657
epoch: 52 training_loss -13.628950109481812 test_loss: -13.456480407714844
epoch: 53 training_loss -13.688585643768311 test_loss: -13.478460693359375
epoch: 54 training_loss -13.711223793029784 test_loss: -13.667837524414063
epoch: 55 training_loss -13.753122873306275 test_loss: -13.866790771484375
epoch: 56 training_loss -13.774859352111816 test_loss: -13.953872680664062
epoch: 57 training_loss -13.913793725967407 test_loss: -13.78887481689453
epoch: 58 training_loss -13.838817930221557 test_loss: -13.899166870117188
epoch: 59 training_loss -13.978397254943848 test_loss: -13.9345458984375
epoch: 60 training_loss -13.943055181503295 test_loss: -13.87503662109375
epoch: 61 training_loss -13.955867776870727 test_loss: -14.05550537109375
epoch: 62 training_loss -14.108426704406739 test_loss: -14.035472106933593
epoch: 63 training_loss -14.096823139190674 test_loss: -14.130319213867187
epoch: 64 training_loss -14.0968004322052 test_loss: -14.192457580566407
epoch: 65 training_loss -14.132563724517823 test_loss: -14.155868530273438
epoch: 66 training_loss -14.12410964012146 test_loss: -14.259910583496094
epoch: 67 training_loss -14.247754001617432 test_loss: -14.155241394042969
epoch: 68 training_loss -14.305669574737548 test_loss: -14.41080322265625
epoch: 69 training_loss -14.289990844726562 test_loss: -14.386558532714844
epoch: 70 training_loss -14.306774559020996 test_loss: -14.163285827636718
epoch: 71 training_loss -14.298831176757812 test_loss: -14.233251953125
epoch: 72 training_loss -14.355415277481079 test_loss: -14.485247802734374
epoch: 73 training_loss -14.40242992401123 test_loss: -14.453892517089844
epoch: 74 training_loss -14.434975128173829 test_loss: -14.534796142578125
epoch: 75 training_loss -14.417913761138916 test_loss: -14.590582275390625
epoch: 76 training_loss -14.514111089706422 test_loss: -14.51658935546875
epoch: 77 training_loss -14.499727230072022 test_loss: -14.400216674804687
epoch: 78 training_loss -14.583041353225708 test_loss: -14.664944458007813
epoch: 79 training_loss -14.54347508430481 test_loss: -14.755599975585938
epoch: 80 training_loss -14.583929796218872 test_loss: -14.470591735839843
epoch: 81 training_loss -14.652992668151855 test_loss: -14.48131103515625
epoch: 82 training_loss -14.687801685333252 test_loss: -14.83209686279297
epoch: 83 training_loss -14.659013671875 test_loss: -14.686122131347656
epoch: 84 training_loss -14.733877096176148 test_loss: -14.611997985839844
epoch: 85 training_loss -14.758299207687378 test_loss: -14.9775390625
epoch: 86 training_loss -14.776112871170044 test_loss: -14.496440124511718
epoch: 87 training_loss -14.716615552902221 test_loss: -14.754275512695312
epoch: 88 training_loss -14.684691820144653 test_loss: -14.715411376953124
epoch: 89 training_loss -14.735767707824706 test_loss: -14.967678833007813
epoch: 90 training_loss -14.846801300048828 test_loss: -14.804484558105468
epoch: 91 training_loss -14.882260675430297 test_loss: -14.698252868652343
epoch: 92 training_loss -14.82675594329834 test_loss: -14.873612976074218
epoch: 93 training_loss -14.800316553115845 test_loss: -14.856451416015625
epoch: 94 training_loss -14.910304555892944 test_loss: -14.739532470703125
epoch: 95 training_loss -14.924216566085816 test_loss: -14.863017272949218
epoch: 96 training_loss -14.905108366012573 test_loss: -14.957502746582032
epoch: 97 training_loss -15.002898092269897 test_loss: -14.89134521484375
epoch: 98 training_loss -14.94205919265747 test_loss: -14.893142700195312
epoch: 99 training_loss -15.03636053085327 test_loss: -14.939521789550781
epoch: 100 training_loss -14.963623991012573 test_loss: -14.966989135742187
epoch: 101 training_loss -14.995281810760497 test_loss: -14.952734375
epoch: 102 training_loss -14.986580171585082 test_loss: -15.080424499511718
epoch: 103 training_loss -15.015404119491578 test_loss: -15.260623168945312
epoch: 104 training_loss -15.099586505889892 test_loss: -15.134925842285156
epoch: 105 training_loss -14.975734224319458 test_loss: -15.018060302734375
epoch: 106 training_loss -15.176752166748047 test_loss: -15.151959228515626
epoch: 107 training_loss -15.131893491744995 test_loss: -15.127960205078125
epoch: 108 training_loss -15.134182109832764 test_loss: -15.058004760742188
epoch: 109 training_loss -15.125557498931885 test_loss: -15.318612670898437
epoch: 110 training_loss -15.158375997543335 test_loss: -15.170304870605468
epoch: 111 training_loss -15.161950263977051 test_loss: -15.345037841796875
epoch: 112 training_loss -15.189402894973755 test_loss: -15.348245239257812
epoch: 113 training_loss -15.2400750541687 test_loss: -15.246173095703124
epoch: 114 training_loss -15.192558040618897 test_loss: -15.140476989746094
epoch: 115 training_loss -15.172072811126709 test_loss: -15.338929748535156
epoch: 116 training_loss -15.26943962097168 test_loss: -15.309942626953125
epoch: 117 training_loss -15.19480917930603 test_loss: -15.28260498046875
epoch: 118 training_loss -15.33871106147766 test_loss: -15.12585906982422
epoch: 119 training_loss -15.310119953155517 test_loss: -15.209185791015624
epoch: 120 training_loss -15.273675012588502 test_loss: -15.244375610351563
epoch: 121 training_loss -15.351668558120728 test_loss: -15.386907958984375
epoch: 122 training_loss -15.370408906936646 test_loss: -15.34423370361328
epoch: 123 training_loss -15.312102832794189 test_loss: -15.402742004394531
epoch: 124 training_loss -15.375348949432373 test_loss: -15.427403259277344
epoch: 125 training_loss -15.308575916290284 test_loss: -15.473640441894531
epoch: 126 training_loss -15.36367124557495 test_loss: -15.456317138671874
epoch: 127 training_loss -15.414373025894164 test_loss: -15.268252563476562
epoch: 128 training_loss -15.3052858543396 test_loss: -15.42757568359375
epoch: 129 training_loss -15.458452863693237 test_loss: -15.182571411132812
epoch: 130 training_loss -15.420452346801758 test_loss: -15.461013793945312
epoch: 131 training_loss -15.35055661201477 test_loss: -15.394244384765624
epoch: 132 training_loss -15.498705711364746 test_loss: -15.653602600097656
epoch: 133 training_loss -15.362875194549561 test_loss: -15.353767395019531
epoch: 134 training_loss -15.44718111038208 test_loss: -15.555364990234375
epoch: 135 training_loss -15.409951057434082 test_loss: -15.282191467285156
epoch: 136 training_loss -15.47799524307251 test_loss: -15.474208068847656
epoch: 137 training_loss -15.530149517059327 test_loss: -15.53782958984375
epoch: 138 training_loss -15.48956455230713 test_loss: -15.393409729003906
epoch: 139 training_loss -15.563781414031983 test_loss: -15.524055480957031
epoch: 140 training_loss -15.555746202468873 test_loss: -15.461978149414062
epoch: 141 training_loss -15.579120397567749 test_loss: -15.496267700195313
epoch: 142 training_loss -15.513600692749023 test_loss: -15.326019287109375
epoch: 143 training_loss -15.494066352844237 test_loss: -15.489056396484376
epoch: 144 training_loss -15.50026198387146 test_loss: -15.610520935058593
epoch: 145 training_loss -15.639321060180665 test_loss: -15.587033081054688
epoch: 146 training_loss -15.592826929092407 test_loss: -15.59176025390625
epoch: 147 training_loss -15.518098163604737 test_loss: -15.46431884765625
epoch: 148 training_loss -15.61906032562256 test_loss: -15.640414428710937
epoch: 149 training_loss -15.741764001846313 test_loss: -15.69849853515625
6547.676569152385
episode: 0 training return: tensor(-3789.0042, device='cuda:0')
episode: 1 training return: tensor(-4549.7344, device='cuda:0')
episode: 2 training return: tensor(-4010.8135, device='cuda:0')
episode: 3 training return: tensor(-3026.3845, device='cuda:0')
epoch: 1 test_true_pfm: -133.3091722467899
episode: 4 training return: tensor(-4022.7092, device='cuda:0')
episode: 5 training return: tensor(-4123.3184, device='cuda:0')
episode: 6 training return: tensor(-3966.3606, device='cuda:0')
episode: 7 training return: tensor(-3281.0691, device='cuda:0')
epoch: 2 test_true_pfm: -133.2150605834062
episode: 8 training return: tensor(-4201.4243, device='cuda:0')
episode: 9 training return: tensor(-3637.0364, device='cuda:0')
episode: 10 training return: tensor(-2104.1191, device='cuda:0')
episode: 11 training return: tensor(-2171.3721, device='cuda:0')
epoch: 3 test_true_pfm: -69.8553334282743
episode: 12 training return: tensor(-2154.7942, device='cuda:0')
episode: 13 training return: tensor(-2121.4487, device='cuda:0')
episode: 14 training return: tensor(-2112.2563, device='cuda:0')
episode: 15 training return: tensor(-1913.4126, device='cuda:0')
epoch: 4 test_true_pfm: -14.12481286739496
episode: 16 training return: tensor(-2040.9114, device='cuda:0')
episode: 17 training return: tensor(-2069.2153, device='cuda:0')
episode: 18 training return: tensor(-2071.5605, device='cuda:0')
episode: 19 training return: tensor(-1870.3481, device='cuda:0')
epoch: 5 test_true_pfm: -52.868077921689654
episode: 20 training return: tensor(-1867.5664, device='cuda:0')
episode: 21 training return: tensor(-1887.9818, device='cuda:0')
episode: 22 training return: tensor(-1904.2747, device='cuda:0')
episode: 23 training return: tensor(-1892.7593, device='cuda:0')
epoch: 6 test_true_pfm: -2.7596203438433684
episode: 24 training return: tensor(-1880.8346, device='cuda:0')
episode: 25 training return: tensor(-1873.7390, device='cuda:0')
episode: 26 training return: tensor(-1875.1047, device='cuda:0')
episode: 27 training return: tensor(-1860.5142, device='cuda:0')
epoch: 7 test_true_pfm: -25.335455358662927
episode: 28 training return: tensor(-1861.3759, device='cuda:0')
episode: 29 training return: tensor(-1880.4208, device='cuda:0')
episode: 30 training return: tensor(-1883.1387, device='cuda:0')
episode: 31 training return: tensor(-1872.7555, device='cuda:0')
epoch: 8 test_true_pfm: -21.88592113630514
episode: 32 training return: tensor(-1878.6118, device='cuda:0')
episode: 33 training return: tensor(-1871.2399, device='cuda:0')
episode: 34 training return: tensor(-1891.1490, device='cuda:0')
episode: 35 training return: tensor(-1880.3639, device='cuda:0')
epoch: 9 test_true_pfm: -15.189076516954515
episode: 36 training return: tensor(-1883.8256, device='cuda:0')
episode: 37 training return: tensor(-1863.9801, device='cuda:0')
episode: 38 training return: tensor(-1869.2971, device='cuda:0')
episode: 39 training return: tensor(-1874.5414, device='cuda:0')
epoch: 10 test_true_pfm: -15.597379446543618
episode: 40 training return: tensor(-1884.4412, device='cuda:0')
episode: 41 training return: tensor(-1873.2722, device='cuda:0')
episode: 42 training return: tensor(-1862.0498, device='cuda:0')
episode: 43 training return: tensor(-1888.7026, device='cuda:0')
epoch: 11 test_true_pfm: -11.036981611755408
episode: 44 training return: tensor(-1872.5865, device='cuda:0')
episode: 45 training return: tensor(-1873.2142, device='cuda:0')
episode: 46 training return: tensor(-1893.8854, device='cuda:0')
episode: 47 training return: tensor(-1877.8552, device='cuda:0')
epoch: 12 test_true_pfm: -15.667409989557648
episode: 48 training return: tensor(-1888.5607, device='cuda:0')
episode: 49 training return: tensor(-1886.0416, device='cuda:0')
episode: 50 training return: tensor(-1877.3079, device='cuda:0')
episode: 51 training return: tensor(-1891.6393, device='cuda:0')
epoch: 13 test_true_pfm: -13.481414977609681
episode: 52 training return: tensor(-1872.4398, device='cuda:0')
episode: 53 training return: tensor(-1875.1033, device='cuda:0')
episode: 54 training return: tensor(-1876.4369, device='cuda:0')
episode: 55 training return: tensor(-1887.7566, device='cuda:0')
epoch: 14 test_true_pfm: -7.56563424955091
episode: 56 training return: tensor(-1894.8280, device='cuda:0')
episode: 57 training return: tensor(-1881.9152, device='cuda:0')
episode: 58 training return: tensor(-1899.7164, device='cuda:0')
episode: 59 training return: tensor(-1872.1721, device='cuda:0')
epoch: 15 test_true_pfm: -8.032209124953061
episode: 60 training return: tensor(-1885.7656, device='cuda:0')
episode: 61 training return: tensor(-1895.9553, device='cuda:0')
episode: 62 training return: tensor(-1884.7627, device='cuda:0')
episode: 63 training return: tensor(-1878.2308, device='cuda:0')
epoch: 16 test_true_pfm: -6.789864711181621
episode: 64 training return: tensor(-1869.8701, device='cuda:0')
episode: 65 training return: tensor(-1885.6802, device='cuda:0')
episode: 66 training return: tensor(-1876.4634, device='cuda:0')
episode: 67 training return: tensor(-1864.0681, device='cuda:0')
epoch: 17 test_true_pfm: -2.761769664265202
episode: 68 training return: tensor(-1879.5421, device='cuda:0')
episode: 69 training return: tensor(-1873.5024, device='cuda:0')
episode: 70 training return: tensor(-1890.3496, device='cuda:0')
episode: 71 training return: tensor(-1884.4108, device='cuda:0')
epoch: 18 test_true_pfm: -7.958221558418043
episode: 72 training return: tensor(-1878.1996, device='cuda:0')
episode: 73 training return: tensor(-1881.8336, device='cuda:0')
episode: 74 training return: tensor(-1868.0518, device='cuda:0')
episode: 75 training return: tensor(-1874.9252, device='cuda:0')
epoch: 19 test_true_pfm: -3.0279900364328216
episode: 76 training return: tensor(-1872.3083, device='cuda:0')
episode: 77 training return: tensor(-1874.0557, device='cuda:0')
episode: 78 training return: tensor(-1886.6344, device='cuda:0')
episode: 79 training return: tensor(-1878.1115, device='cuda:0')
epoch: 20 test_true_pfm: -3.5488718380831243
episode: 80 training return: tensor(-1886.5735, device='cuda:0')
episode: 81 training return: tensor(-1898.3116, device='cuda:0')
episode: 82 training return: tensor(-1879.3424, device='cuda:0')
episode: 83 training return: tensor(-1891.9189, device='cuda:0')
epoch: 21 test_true_pfm: -7.322004344071083
episode: 84 training return: tensor(-1894.0457, device='cuda:0')
episode: 85 training return: tensor(-1880.9016, device='cuda:0')
episode: 86 training return: tensor(-1877.9861, device='cuda:0')
episode: 87 training return: tensor(-1882.2800, device='cuda:0')
epoch: 22 test_true_pfm: -5.1683719715721645
episode: 88 training return: tensor(-1895.0763, device='cuda:0')
episode: 89 training return: tensor(-1908.4447, device='cuda:0')
episode: 90 training return: tensor(-1897.4166, device='cuda:0')
episode: 91 training return: tensor(-1893.9862, device='cuda:0')
epoch: 23 test_true_pfm: -11.818497216730776
episode: 92 training return: tensor(-1886.5092, device='cuda:0')
episode: 93 training return: tensor(-1883.2545, device='cuda:0')
episode: 94 training return: tensor(-1889.5928, device='cuda:0')
episode: 95 training return: tensor(-1882.5079, device='cuda:0')
epoch: 24 test_true_pfm: -7.386121417329744
episode: 96 training return: tensor(-1899.2760, device='cuda:0')
episode: 97 training return: tensor(-1882.2600, device='cuda:0')
episode: 98 training return: tensor(-1887.4476, device='cuda:0')
episode: 99 training return: tensor(-1873.8640, device='cuda:0')
epoch: 25 test_true_pfm: -10.673649126027728
episode: 100 training return: tensor(-1879.8462, device='cuda:0')
episode: 101 training return: tensor(-1881.3193, device='cuda:0')
episode: 102 training return: tensor(-1902.7780, device='cuda:0')
episode: 103 training return: tensor(-1883.9734, device='cuda:0')
epoch: 26 test_true_pfm: -12.342390640769885
episode: 104 training return: tensor(-1884.9414, device='cuda:0')
episode: 105 training return: tensor(-1886.5204, device='cuda:0')
episode: 106 training return: tensor(-1893.4448, device='cuda:0')
episode: 107 training return: tensor(-1895.6105, device='cuda:0')
epoch: 27 test_true_pfm: -9.381934330285338
episode: 108 training return: tensor(-1872.0853, device='cuda:0')
episode: 109 training return: tensor(-1886.5964, device='cuda:0')
episode: 110 training return: tensor(-1888.0065, device='cuda:0')
episode: 111 training return: tensor(-1886.4808, device='cuda:0')
epoch: 28 test_true_pfm: -7.347463950211014
episode: 112 training return: tensor(-1890.9103, device='cuda:0')
episode: 113 training return: tensor(-1889.2489, device='cuda:0')
episode: 114 training return: tensor(-1872.4031, device='cuda:0')
episode: 115 training return: tensor(-1895.7751, device='cuda:0')
epoch: 29 test_true_pfm: -11.248309360099482
episode: 116 training return: tensor(-1884.1268, device='cuda:0')
episode: 117 training return: tensor(-1905.0200, device='cuda:0')
episode: 118 training return: tensor(-1870.0093, device='cuda:0')
episode: 119 training return: tensor(-1877.1783, device='cuda:0')
epoch: 30 test_true_pfm: -9.951020662657053
episode: 120 training return: tensor(-1870.0654, device='cuda:0')
episode: 121 training return: tensor(-1874.3535, device='cuda:0')
episode: 122 training return: tensor(-1871.4113, device='cuda:0')
episode: 123 training return: tensor(-1911.2212, device='cuda:0')
epoch: 31 test_true_pfm: -10.12264527814851
episode: 124 training return: tensor(-1883.6796, device='cuda:0')
episode: 125 training return: tensor(-1891.1962, device='cuda:0')
episode: 126 training return: tensor(-1885.1029, device='cuda:0')
episode: 127 training return: tensor(-1873.8895, device='cuda:0')
epoch: 32 test_true_pfm: -3.7438950893478022
episode: 128 training return: tensor(-1856.1909, device='cuda:0')
episode: 129 training return: tensor(-1877.2441, device='cuda:0')
episode: 130 training return: tensor(-1874.4673, device='cuda:0')
episode: 131 training return: tensor(-1887.8956, device='cuda:0')
epoch: 33 test_true_pfm: -8.898807081654306
episode: 132 training return: tensor(-1894.5251, device='cuda:0')
episode: 133 training return: tensor(-1882.7932, device='cuda:0')
episode: 134 training return: tensor(-1891.5344, device='cuda:0')
episode: 135 training return: tensor(-1859.5353, device='cuda:0')
epoch: 34 test_true_pfm: -6.6577534996732455
episode: 136 training return: tensor(-1874.4797, device='cuda:0')
episode: 137 training return: tensor(-1900.4391, device='cuda:0')
episode: 138 training return: tensor(-1870.3965, device='cuda:0')
episode: 139 training return: tensor(-1895.1947, device='cuda:0')
epoch: 35 test_true_pfm: -10.80365646734712
episode: 140 training return: tensor(-1869.7681, device='cuda:0')
episode: 141 training return: tensor(-1871.7181, device='cuda:0')
episode: 142 training return: tensor(-1876.1722, device='cuda:0')
episode: 143 training return: tensor(-1875.6445, device='cuda:0')
epoch: 36 test_true_pfm: -9.352287063826779
episode: 144 training return: tensor(-1884.3851, device='cuda:0')
episode: 145 training return: tensor(-1886.6482, device='cuda:0')
episode: 146 training return: tensor(-1876.2013, device='cuda:0')
episode: 147 training return: tensor(-1869.8350, device='cuda:0')
epoch: 37 test_true_pfm: -8.53860584367883
episode: 148 training return: tensor(-1878.0228, device='cuda:0')
episode: 149 training return: tensor(-1913.2012, device='cuda:0')
episode: 150 training return: tensor(-1863.9491, device='cuda:0')
episode: 151 training return: tensor(-1877.9647, device='cuda:0')
epoch: 38 test_true_pfm: -12.107822596384672
episode: 152 training return: tensor(-1879.2092, device='cuda:0')
episode: 153 training return: tensor(-1869.9803, device='cuda:0')
episode: 154 training return: tensor(-1880.7788, device='cuda:0')
episode: 155 training return: tensor(-1886.1975, device='cuda:0')
epoch: 39 test_true_pfm: -11.011117548101538
episode: 156 training return: tensor(-1874.7281, device='cuda:0')
episode: 157 training return: tensor(-1888.9315, device='cuda:0')
episode: 158 training return: tensor(-1874.0059, device='cuda:0')
episode: 159 training return: tensor(-1872.7220, device='cuda:0')
epoch: 40 test_true_pfm: -9.139058382027741
episode: 160 training return: tensor(-1877.4468, device='cuda:0')
episode: 161 training return: tensor(-1872.6331, device='cuda:0')
episode: 162 training return: tensor(-1863.5887, device='cuda:0')
episode: 163 training return: tensor(-1871.1227, device='cuda:0')
epoch: 41 test_true_pfm: -11.075468701202203
episode: 164 training return: tensor(-1870.8909, device='cuda:0')
episode: 165 training return: tensor(-1887.4622, device='cuda:0')
episode: 166 training return: tensor(-1872.1528, device='cuda:0')
episode: 167 training return: tensor(-1874.9590, device='cuda:0')
epoch: 42 test_true_pfm: -17.98363082754823
episode: 168 training return: tensor(-1869.5486, device='cuda:0')
episode: 169 training return: tensor(-1877.2755, device='cuda:0')
episode: 170 training return: tensor(-1870.4042, device='cuda:0')
episode: 171 training return: tensor(-1893.6902, device='cuda:0')
epoch: 43 test_true_pfm: -15.63689519399392
episode: 172 training return: tensor(-1883.2025, device='cuda:0')
episode: 173 training return: tensor(-1881.0126, device='cuda:0')
episode: 174 training return: tensor(-1880.2328, device='cuda:0')
episode: 175 training return: tensor(-1875.0641, device='cuda:0')
epoch: 44 test_true_pfm: -13.205694130251894
episode: 176 training return: tensor(-1887.5609, device='cuda:0')
episode: 177 training return: tensor(-1868.8087, device='cuda:0')
episode: 178 training return: tensor(-1865.1698, device='cuda:0')
episode: 179 training return: tensor(-1889.6910, device='cuda:0')
epoch: 45 test_true_pfm: -14.262173929709535
episode: 180 training return: tensor(-1863.4928, device='cuda:0')
episode: 181 training return: tensor(-1870.3079, device='cuda:0')
episode: 182 training return: tensor(-1870.6527, device='cuda:0')
episode: 183 training return: tensor(-1878.8145, device='cuda:0')
epoch: 46 test_true_pfm: -10.207438470452367
episode: 184 training return: tensor(-1892.8282, device='cuda:0')
episode: 185 training return: tensor(-1883.9039, device='cuda:0')
episode: 186 training return: tensor(-1889.1388, device='cuda:0')
episode: 187 training return: tensor(-1876.8964, device='cuda:0')
epoch: 47 test_true_pfm: -19.018180844152884
episode: 188 training return: tensor(-1861.2091, device='cuda:0')
episode: 189 training return: tensor(-1880.4926, device='cuda:0')
episode: 190 training return: tensor(-1856.0791, device='cuda:0')
episode: 191 training return: tensor(-1878.8578, device='cuda:0')
epoch: 48 test_true_pfm: -15.746895643216888
episode: 192 training return: tensor(-1862.2528, device='cuda:0')
episode: 193 training return: tensor(-1878.3540, device='cuda:0')
episode: 194 training return: tensor(-1864.5758, device='cuda:0')
episode: 195 training return: tensor(-1873.2252, device='cuda:0')
epoch: 49 test_true_pfm: -13.463989576789563
episode: 196 training return: tensor(-1870.7878, device='cuda:0')
episode: 197 training return: tensor(-1885.3611, device='cuda:0')
episode: 198 training return: tensor(-1872.6748, device='cuda:0')
episode: 199 training return: tensor(-1878.2384, device='cuda:0')
epoch: 50 test_true_pfm: -15.473035540934447
episode: 200 training return: tensor(-1870.9877, device='cuda:0')
episode: 201 training return: tensor(-1865.1455, device='cuda:0')
episode: 202 training return: tensor(-1883.2659, device='cuda:0')
episode: 203 training return: tensor(-1874.2380, device='cuda:0')
epoch: 51 test_true_pfm: -12.933696407105813
episode: 204 training return: tensor(-1882.4333, device='cuda:0')
episode: 205 training return: tensor(-1886.3536, device='cuda:0')
episode: 206 training return: tensor(-1891.1237, device='cuda:0')
episode: 207 training return: tensor(-1876.9574, device='cuda:0')
epoch: 52 test_true_pfm: -10.984154624779677
episode: 208 training return: tensor(-1881.8602, device='cuda:0')
episode: 209 training return: tensor(-1875.5988, device='cuda:0')
episode: 210 training return: tensor(-1863.9875, device='cuda:0')
episode: 211 training return: tensor(-1861.1980, device='cuda:0')
epoch: 53 test_true_pfm: -11.595831936758804
episode: 212 training return: tensor(-1891.4766, device='cuda:0')
episode: 213 training return: tensor(-1861.5859, device='cuda:0')
episode: 214 training return: tensor(-1852.5913, device='cuda:0')
episode: 215 training return: tensor(-1879.5142, device='cuda:0')
epoch: 54 test_true_pfm: -6.915680134649283
episode: 216 training return: tensor(-1860.4768, device='cuda:0')
episode: 217 training return: tensor(-1870.4495, device='cuda:0')
episode: 218 training return: tensor(-1879.4279, device='cuda:0')
episode: 219 training return: tensor(-1874.7439, device='cuda:0')
epoch: 55 test_true_pfm: -7.838717461550189
episode: 220 training return: tensor(-1895.2639, device='cuda:0')
episode: 221 training return: tensor(-1866.2999, device='cuda:0')
episode: 222 training return: tensor(-1865.9177, device='cuda:0')
episode: 223 training return: tensor(-1875.7053, device='cuda:0')
epoch: 56 test_true_pfm: -12.910673146971355
episode: 224 training return: tensor(-1863.9175, device='cuda:0')
episode: 225 training return: tensor(-1862.1910, device='cuda:0')
episode: 226 training return: tensor(-1857.9039, device='cuda:0')
episode: 227 training return: tensor(-1857.5188, device='cuda:0')
epoch: 57 test_true_pfm: -11.821933068894387
episode: 228 training return: tensor(-1889.3612, device='cuda:0')
episode: 229 training return: tensor(-1887.9309, device='cuda:0')
episode: 230 training return: tensor(-1878.4670, device='cuda:0')
episode: 231 training return: tensor(-1859.3640, device='cuda:0')
epoch: 58 test_true_pfm: -11.485429718705559
episode: 232 training return: tensor(-1878.4911, device='cuda:0')
episode: 233 training return: tensor(-1902.1799, device='cuda:0')
episode: 234 training return: tensor(-1865.4580, device='cuda:0')
episode: 235 training return: tensor(-1880.2377, device='cuda:0')
epoch: 59 test_true_pfm: -11.224399830927979
episode: 236 training return: tensor(-1879.0104, device='cuda:0')
episode: 237 training return: tensor(-1878.1946, device='cuda:0')
episode: 238 training return: tensor(-1884.0194, device='cuda:0')
episode: 239 training return: tensor(-1871.1749, device='cuda:0')
epoch: 60 test_true_pfm: -12.343343654647358
episode: 240 training return: tensor(-1870.1040, device='cuda:0')
episode: 241 training return: tensor(-1881.0278, device='cuda:0')
episode: 242 training return: tensor(-1863.6333, device='cuda:0')
episode: 243 training return: tensor(-1872.1224, device='cuda:0')
epoch: 61 test_true_pfm: -17.475366238100456
episode: 244 training return: tensor(-1881.5925, device='cuda:0')
episode: 245 training return: tensor(-1880.0309, device='cuda:0')
episode: 246 training return: tensor(-1864.8431, device='cuda:0')
episode: 247 training return: tensor(-1893.5951, device='cuda:0')
epoch: 62 test_true_pfm: -12.526372663266693
episode: 248 training return: tensor(-1860.3602, device='cuda:0')
episode: 249 training return: tensor(-1865.5717, device='cuda:0')
episode: 250 training return: tensor(-1868.7861, device='cuda:0')
episode: 251 training return: tensor(-1869.7925, device='cuda:0')
epoch: 63 test_true_pfm: -13.651236009869343
episode: 252 training return: tensor(-1861.9254, device='cuda:0')
episode: 253 training return: tensor(-1867.7560, device='cuda:0')
episode: 254 training return: tensor(-1890.0033, device='cuda:0')
episode: 255 training return: tensor(-1849.6320, device='cuda:0')
epoch: 64 test_true_pfm: -11.101154780346079
episode: 256 training return: tensor(-1849.0370, device='cuda:0')
episode: 257 training return: tensor(-1859.4963, device='cuda:0')
episode: 258 training return: tensor(-1854.9990, device='cuda:0')
episode: 259 training return: tensor(-1880.0977, device='cuda:0')
epoch: 65 test_true_pfm: -8.0760753868541
episode: 260 training return: tensor(-1871.5026, device='cuda:0')
episode: 261 training return: tensor(-1879.6202, device='cuda:0')
episode: 262 training return: tensor(-1860.2054, device='cuda:0')
episode: 263 training return: tensor(-1868.3776, device='cuda:0')
epoch: 66 test_true_pfm: -4.446811965883357
episode: 264 training return: tensor(-1872.4468, device='cuda:0')
episode: 265 training return: tensor(-1884.5743, device='cuda:0')
episode: 266 training return: tensor(-1862.5830, device='cuda:0')
episode: 267 training return: tensor(-1865.1704, device='cuda:0')
epoch: 67 test_true_pfm: -13.514571325099084
episode: 268 training return: tensor(-1878.4908, device='cuda:0')
episode: 269 training return: tensor(-1883.1685, device='cuda:0')
episode: 270 training return: tensor(-1885.3462, device='cuda:0')
episode: 271 training return: tensor(-1869.5269, device='cuda:0')
epoch: 68 test_true_pfm: -15.873391049387806
episode: 272 training return: tensor(-1881.6157, device='cuda:0')
episode: 273 training return: tensor(-1867.2220, device='cuda:0')
episode: 274 training return: tensor(-1874.7365, device='cuda:0')
episode: 275 training return: tensor(-1874.1870, device='cuda:0')
epoch: 69 test_true_pfm: -11.4526354233804
episode: 276 training return: tensor(-1900.9418, device='cuda:0')
episode: 277 training return: tensor(-1890.0671, device='cuda:0')
episode: 278 training return: tensor(-1861.7434, device='cuda:0')
episode: 279 training return: tensor(-1875.9277, device='cuda:0')
epoch: 70 test_true_pfm: -8.776028628778418
episode: 280 training return: tensor(-1884.9875, device='cuda:0')
episode: 281 training return: tensor(-1859.6333, device='cuda:0')
episode: 282 training return: tensor(-1850.8187, device='cuda:0')
episode: 283 training return: tensor(-1854.8589, device='cuda:0')
epoch: 71 test_true_pfm: -12.103384276442931
episode: 284 training return: tensor(-1852.9397, device='cuda:0')
episode: 285 training return: tensor(-1870.4424, device='cuda:0')
episode: 286 training return: tensor(-1863.4426, device='cuda:0')
episode: 287 training return: tensor(-1867.5029, device='cuda:0')
epoch: 72 test_true_pfm: -16.474411879363856
episode: 288 training return: tensor(-1861.4177, device='cuda:0')
episode: 289 training return: tensor(-1874.0585, device='cuda:0')
episode: 290 training return: tensor(-1872.1770, device='cuda:0')
episode: 291 training return: tensor(-1882.0479, device='cuda:0')
epoch: 73 test_true_pfm: -13.980012880639817
episode: 292 training return: tensor(-1858.0913, device='cuda:0')
episode: 293 training return: tensor(-1860.4977, device='cuda:0')
episode: 294 training return: tensor(-1875.4801, device='cuda:0')
episode: 295 training return: tensor(-2104.6946, device='cuda:0')
epoch: 74 test_true_pfm: -12.119911068647474
episode: 296 training return: tensor(-1867.2880, device='cuda:0')
episode: 297 training return: tensor(-1864.9393, device='cuda:0')
episode: 298 training return: tensor(-1863.1544, device='cuda:0')
episode: 299 training return: tensor(-1865.3477, device='cuda:0')
epoch: 75 test_true_pfm: -11.988308536121366
episode: 300 training return: tensor(-1874.7927, device='cuda:0')
episode: 301 training return: tensor(-1875.6490, device='cuda:0')
episode: 302 training return: tensor(-1866.0527, device='cuda:0')
episode: 303 training return: tensor(-1855.5233, device='cuda:0')
epoch: 76 test_true_pfm: -14.887599215282146
episode: 304 training return: tensor(-1863.0542, device='cuda:0')
episode: 305 training return: tensor(-1882.2285, device='cuda:0')
episode: 306 training return: tensor(-1861.4011, device='cuda:0')
episode: 307 training return: tensor(-1852.6901, device='cuda:0')
epoch: 77 test_true_pfm: -11.645146535896906
episode: 308 training return: tensor(-1862.8330, device='cuda:0')
episode: 309 training return: tensor(-1876.6827, device='cuda:0')
episode: 310 training return: tensor(-1870.7445, device='cuda:0')
episode: 311 training return: tensor(-1870.3518, device='cuda:0')
epoch: 78 test_true_pfm: -14.41593763707097
episode: 312 training return: tensor(-1882.7665, device='cuda:0')
episode: 313 training return: tensor(-1876.9656, device='cuda:0')
episode: 314 training return: tensor(-1877.3669, device='cuda:0')
episode: 315 training return: tensor(-1860.1736, device='cuda:0')
epoch: 79 test_true_pfm: -14.129945313889229
episode: 316 training return: tensor(-1878.1506, device='cuda:0')
episode: 317 training return: tensor(-1882.4558, device='cuda:0')
episode: 318 training return: tensor(-1866.6587, device='cuda:0')
episode: 319 training return: tensor(-1878.8468, device='cuda:0')
epoch: 80 test_true_pfm: -15.9563032007689
episode: 320 training return: tensor(-1873.0715, device='cuda:0')
episode: 321 training return: tensor(-1862.1490, device='cuda:0')
episode: 322 training return: tensor(-1873.2603, device='cuda:0')
episode: 323 training return: tensor(-1869.2231, device='cuda:0')
epoch: 81 test_true_pfm: -13.48435142784156
episode: 324 training return: tensor(-1877.1066, device='cuda:0')
episode: 325 training return: tensor(-1897.0504, device='cuda:0')
episode: 326 training return: tensor(-1868.3303, device='cuda:0')
episode: 327 training return: tensor(-1858.5000, device='cuda:0')
epoch: 82 test_true_pfm: -13.125884986477255
episode: 328 training return: tensor(-1891.2217, device='cuda:0')
episode: 329 training return: tensor(-1877.5732, device='cuda:0')
episode: 330 training return: tensor(-1858.9625, device='cuda:0')
episode: 331 training return: tensor(-1862.8875, device='cuda:0')
epoch: 83 test_true_pfm: -17.147873181163654
episode: 332 training return: tensor(-1873.6089, device='cuda:0')
episode: 333 training return: tensor(-1881.8435, device='cuda:0')
episode: 334 training return: tensor(-1869.2073, device='cuda:0')
episode: 335 training return: tensor(-1850.0338, device='cuda:0')
epoch: 84 test_true_pfm: -15.755207483260785
episode: 336 training return: tensor(-1874.8934, device='cuda:0')
episode: 337 training return: tensor(-1843.1216, device='cuda:0')
episode: 338 training return: tensor(-1870.7919, device='cuda:0')
episode: 339 training return: tensor(-1865.9614, device='cuda:0')
epoch: 85 test_true_pfm: -16.860949313450956
episode: 340 training return: tensor(-1871.8368, device='cuda:0')
episode: 341 training return: tensor(-1868.8331, device='cuda:0')
episode: 342 training return: tensor(-1865.1700, device='cuda:0')
episode: 343 training return: tensor(-1867.2094, device='cuda:0')
epoch: 86 test_true_pfm: -15.510557523191414
episode: 344 training return: tensor(-1871.1418, device='cuda:0')
episode: 345 training return: tensor(-1869.9940, device='cuda:0')
episode: 346 training return: tensor(-1860.3824, device='cuda:0')
episode: 347 training return: tensor(-1867.9418, device='cuda:0')
epoch: 87 test_true_pfm: -19.912477873930385
episode: 348 training return: tensor(-1873.9735, device='cuda:0')
episode: 349 training return: tensor(-1857.2208, device='cuda:0')
episode: 350 training return: tensor(-1869.8247, device='cuda:0')
episode: 351 training return: tensor(-1874.9323, device='cuda:0')
epoch: 88 test_true_pfm: -16.58065486886535
episode: 352 training return: tensor(-1864.5645, device='cuda:0')
episode: 353 training return: tensor(-1871.8416, device='cuda:0')
episode: 354 training return: tensor(-1868.3010, device='cuda:0')
episode: 355 training return: tensor(-1871.3734, device='cuda:0')
epoch: 89 test_true_pfm: -11.031224163707838
episode: 356 training return: tensor(-1872.3198, device='cuda:0')
episode: 357 training return: tensor(-1861.5286, device='cuda:0')
episode: 358 training return: tensor(-1881.1438, device='cuda:0')
episode: 359 training return: tensor(-1858.7999, device='cuda:0')
epoch: 90 test_true_pfm: -13.582636394919916
episode: 360 training return: tensor(-1867.3933, device='cuda:0')
episode: 361 training return: tensor(-1860.2939, device='cuda:0')
episode: 362 training return: tensor(-1876.7499, device='cuda:0')
episode: 363 training return: tensor(-1882.4243, device='cuda:0')
epoch: 91 test_true_pfm: -18.51786366185136
episode: 364 training return: tensor(-1906.9977, device='cuda:0')
episode: 365 training return: tensor(-1865.5405, device='cuda:0')
episode: 366 training return: tensor(-1868.8467, device='cuda:0')
episode: 367 training return: tensor(-1876.2610, device='cuda:0')
epoch: 92 test_true_pfm: -16.64492152957425
episode: 368 training return: tensor(-1884.8997, device='cuda:0')
episode: 369 training return: tensor(-1856.0428, device='cuda:0')
episode: 370 training return: tensor(-1865.5433, device='cuda:0')
episode: 371 training return: tensor(-1871.5660, device='cuda:0')
epoch: 93 test_true_pfm: -12.430670462365576
episode: 372 training return: tensor(-1886.1191, device='cuda:0')
episode: 373 training return: tensor(-1875.0269, device='cuda:0')
episode: 374 training return: tensor(-1886.8812, device='cuda:0')
episode: 375 training return: tensor(-1872.5599, device='cuda:0')
epoch: 94 test_true_pfm: -16.38546755312103
episode: 376 training return: tensor(-1870.0176, device='cuda:0')
episode: 377 training return: tensor(-1876.4243, device='cuda:0')
episode: 378 training return: tensor(-1866.1566, device='cuda:0')
episode: 379 training return: tensor(-1874.8336, device='cuda:0')
epoch: 95 test_true_pfm: -15.856846024764438
episode: 380 training return: tensor(-1896.7925, device='cuda:0')
episode: 381 training return: tensor(-1864.9041, device='cuda:0')
episode: 382 training return: tensor(-1885.8920, device='cuda:0')
episode: 383 training return: tensor(-1875.8124, device='cuda:0')
epoch: 96 test_true_pfm: -10.747607579777842
episode: 384 training return: tensor(-1876.3187, device='cuda:0')
episode: 385 training return: tensor(-1861.1510, device='cuda:0')
episode: 386 training return: tensor(-1895.0857, device='cuda:0')
episode: 387 training return: tensor(-1884.4420, device='cuda:0')
epoch: 97 test_true_pfm: -12.995252365634377
episode: 388 training return: tensor(-1869.8352, device='cuda:0')
episode: 389 training return: tensor(-1861.9298, device='cuda:0')
episode: 390 training return: tensor(-1872.8174, device='cuda:0')
episode: 391 training return: tensor(-1877.1589, device='cuda:0')
epoch: 98 test_true_pfm: -13.430877079711728
episode: 392 training return: tensor(-1861.5610, device='cuda:0')
episode: 393 training return: tensor(-1860.6494, device='cuda:0')
episode: 394 training return: tensor(-1885.4127, device='cuda:0')
episode: 395 training return: tensor(-1884.5138, device='cuda:0')
epoch: 99 test_true_pfm: -13.872180267306673
episode: 396 training return: tensor(-1872.5764, device='cuda:0')
episode: 397 training return: tensor(-1862.0691, device='cuda:0')
episode: 398 training return: tensor(-1883.9869, device='cuda:0')
episode: 399 training return: tensor(-1866.7369, device='cuda:0')
epoch: 100 test_true_pfm: -14.693929052763096
episode: 400 training return: tensor(-1867.0918, device='cuda:0')
episode: 401 training return: tensor(-1895.9728, device='cuda:0')
episode: 402 training return: tensor(-1882.4043, device='cuda:0')
episode: 403 training return: tensor(-1855.9677, device='cuda:0')
epoch: 101 test_true_pfm: -22.36762474940329
episode: 404 training return: tensor(-1872.2848, device='cuda:0')
episode: 405 training return: tensor(-1875.2659, device='cuda:0')
episode: 406 training return: tensor(-1845.5070, device='cuda:0')
episode: 407 training return: tensor(-1877.3127, device='cuda:0')
epoch: 102 test_true_pfm: -17.015327885353503
episode: 408 training return: tensor(-1855.2292, device='cuda:0')
episode: 409 training return: tensor(-1865.0988, device='cuda:0')
episode: 410 training return: tensor(-1875.2421, device='cuda:0')
episode: 411 training return: tensor(-1868.4521, device='cuda:0')
epoch: 103 test_true_pfm: -15.53485325633948
episode: 412 training return: tensor(-1866.7545, device='cuda:0')
episode: 413 training return: tensor(-1869.9902, device='cuda:0')
episode: 414 training return: tensor(-1866.6539, device='cuda:0')
episode: 415 training return: tensor(-1882.2590, device='cuda:0')
epoch: 104 test_true_pfm: -14.158532274565275
episode: 416 training return: tensor(-1865.0605, device='cuda:0')
episode: 417 training return: tensor(-1881.1151, device='cuda:0')
episode: 418 training return: tensor(-1868.7621, device='cuda:0')
episode: 419 training return: tensor(-1884.1685, device='cuda:0')
epoch: 105 test_true_pfm: -11.870688623060518
episode: 420 training return: tensor(-1880.5693, device='cuda:0')
episode: 421 training return: tensor(-1869.3296, device='cuda:0')
episode: 422 training return: tensor(-1861.6710, device='cuda:0')
episode: 423 training return: tensor(-1868.0963, device='cuda:0')
epoch: 106 test_true_pfm: -9.33767242117713
episode: 424 training return: tensor(-1869.1608, device='cuda:0')
episode: 425 training return: tensor(-1872.6113, device='cuda:0')
episode: 426 training return: tensor(-1862.4498, device='cuda:0')
episode: 427 training return: tensor(-1860.5168, device='cuda:0')
epoch: 107 test_true_pfm: -12.660877503297877
episode: 428 training return: tensor(-1887.0292, device='cuda:0')
episode: 429 training return: tensor(-1858.0355, device='cuda:0')
episode: 430 training return: tensor(-1873.4386, device='cuda:0')
episode: 431 training return: tensor(-1867.6110, device='cuda:0')
epoch: 108 test_true_pfm: -11.444458965709003
episode: 432 training return: tensor(-1866.4137, device='cuda:0')
episode: 433 training return: tensor(-1883.8638, device='cuda:0')
episode: 434 training return: tensor(-1862.1837, device='cuda:0')
episode: 435 training return: tensor(-1861.6183, device='cuda:0')
epoch: 109 test_true_pfm: -19.69230100710084
episode: 436 training return: tensor(-1874.5210, device='cuda:0')
episode: 437 training return: tensor(-1868.9445, device='cuda:0')
episode: 438 training return: tensor(-1870.6526, device='cuda:0')
episode: 439 training return: tensor(-1872.0730, device='cuda:0')
epoch: 110 test_true_pfm: -18.50547361273058
episode: 440 training return: tensor(-1865.4810, device='cuda:0')
episode: 441 training return: tensor(-1855.4464, device='cuda:0')
episode: 442 training return: tensor(-1858.9017, device='cuda:0')
episode: 443 training return: tensor(-1870.5806, device='cuda:0')
epoch: 111 test_true_pfm: -8.212821136082916
episode: 444 training return: tensor(-1860.5215, device='cuda:0')
episode: 445 training return: tensor(-1877.1758, device='cuda:0')
episode: 446 training return: tensor(-1863.6097, device='cuda:0')
episode: 447 training return: tensor(-1863.3317, device='cuda:0')
epoch: 112 test_true_pfm: -14.435329847770845
episode: 448 training return: tensor(-1863.5204, device='cuda:0')
episode: 449 training return: tensor(-1875.6187, device='cuda:0')
episode: 450 training return: tensor(-1871.8372, device='cuda:0')
episode: 451 training return: tensor(-1864.2565, device='cuda:0')
epoch: 113 test_true_pfm: -9.075951037150967
episode: 452 training return: tensor(-1869.9478, device='cuda:0')
episode: 453 training return: tensor(-1862.1624, device='cuda:0')
episode: 454 training return: tensor(-1869.9889, device='cuda:0')
episode: 455 training return: tensor(-1878.2549, device='cuda:0')
epoch: 114 test_true_pfm: -19.77525019385291
episode: 456 training return: tensor(-1875.6305, device='cuda:0')
episode: 457 training return: tensor(-1864.0514, device='cuda:0')
episode: 458 training return: tensor(-1885.8809, device='cuda:0')
episode: 459 training return: tensor(-1868.5946, device='cuda:0')
epoch: 115 test_true_pfm: -9.925121034897034
episode: 460 training return: tensor(-1881.8173, device='cuda:0')
episode: 461 training return: tensor(-1876.0880, device='cuda:0')
episode: 462 training return: tensor(-1879.8591, device='cuda:0')
episode: 463 training return: tensor(-1872.4447, device='cuda:0')
epoch: 116 test_true_pfm: -19.508888678101144
episode: 464 training return: tensor(-1872.8005, device='cuda:0')
episode: 465 training return: tensor(-1880.7499, device='cuda:0')
episode: 466 training return: tensor(-1886.3921, device='cuda:0')
episode: 467 training return: tensor(-1863.8668, device='cuda:0')
epoch: 117 test_true_pfm: -17.821771254255097
episode: 468 training return: tensor(-1863.9139, device='cuda:0')
episode: 469 training return: tensor(-1866.1290, device='cuda:0')
episode: 470 training return: tensor(-1881.7847, device='cuda:0')
episode: 471 training return: tensor(-1870.6180, device='cuda:0')
epoch: 118 test_true_pfm: -12.989217642331605
episode: 472 training return: tensor(-1869.8397, device='cuda:0')
episode: 473 training return: tensor(-1859.6403, device='cuda:0')
episode: 474 training return: tensor(-1864.3895, device='cuda:0')
episode: 475 training return: tensor(-1870.8917, device='cuda:0')
epoch: 119 test_true_pfm: -16.674372622261686
episode: 476 training return: tensor(-1866.8751, device='cuda:0')
episode: 477 training return: tensor(-1878.4517, device='cuda:0')
episode: 478 training return: tensor(-1867.5469, device='cuda:0')
episode: 479 training return: tensor(-1873.1508, device='cuda:0')
epoch: 120 test_true_pfm: -17.604268134003416
episode: 480 training return: tensor(-1885.1481, device='cuda:0')
episode: 481 training return: tensor(-1867.4856, device='cuda:0')
episode: 482 training return: tensor(-1852.6438, device='cuda:0')
episode: 483 training return: tensor(-1843.1400, device='cuda:0')
epoch: 121 test_true_pfm: -14.761721185501008
episode: 484 training return: tensor(-1858.1553, device='cuda:0')
episode: 485 training return: tensor(-1871.6987, device='cuda:0')
episode: 486 training return: tensor(-1849.5752, device='cuda:0')
episode: 487 training return: tensor(-1866.7848, device='cuda:0')
epoch: 122 test_true_pfm: -14.880036736805167
episode: 488 training return: tensor(-1885.7145, device='cuda:0')
episode: 489 training return: tensor(-1857.8961, device='cuda:0')
episode: 490 training return: tensor(-1853.6135, device='cuda:0')
episode: 491 training return: tensor(-1855.2107, device='cuda:0')
epoch: 123 test_true_pfm: -19.482838485594034
episode: 492 training return: tensor(-1862.4236, device='cuda:0')
episode: 493 training return: tensor(-1860.2115, device='cuda:0')
episode: 494 training return: tensor(-1873.1556, device='cuda:0')
episode: 495 training return: tensor(-1870.8303, device='cuda:0')
epoch: 124 test_true_pfm: -9.429574622680214
episode: 496 training return: tensor(-1851.0867, device='cuda:0')
episode: 497 training return: tensor(-1860.7593, device='cuda:0')
episode: 498 training return: tensor(-1861.8434, device='cuda:0')
episode: 499 training return: tensor(-1872.1526, device='cuda:0')
epoch: 125 test_true_pfm: -13.765054611152422
episode: 500 training return: tensor(-1873.5009, device='cuda:0')
episode: 501 training return: tensor(-1850.3795, device='cuda:0')
episode: 502 training return: tensor(-1878.3744, device='cuda:0')
episode: 503 training return: tensor(-1875.3154, device='cuda:0')
epoch: 126 test_true_pfm: -11.409722057760616
episode: 504 training return: tensor(-1876.3104, device='cuda:0')
episode: 505 training return: tensor(-1881.8394, device='cuda:0')
episode: 506 training return: tensor(-1871.7303, device='cuda:0')
episode: 507 training return: tensor(-1874.1230, device='cuda:0')
epoch: 127 test_true_pfm: -12.654901381264844
episode: 508 training return: tensor(-1877.0010, device='cuda:0')
episode: 509 training return: tensor(-1867.9862, device='cuda:0')
episode: 510 training return: tensor(-1873.5653, device='cuda:0')
episode: 511 training return: tensor(-1878.3160, device='cuda:0')
epoch: 128 test_true_pfm: -14.476057402769799
episode: 512 training return: tensor(-1877.2949, device='cuda:0')
episode: 513 training return: tensor(-1885.1753, device='cuda:0')
episode: 514 training return: tensor(-1876.8729, device='cuda:0')
episode: 515 training return: tensor(-1860.5958, device='cuda:0')
epoch: 129 test_true_pfm: -11.126349551555123
episode: 516 training return: tensor(-1869.6808, device='cuda:0')
episode: 517 training return: tensor(-1877.5223, device='cuda:0')
episode: 518 training return: tensor(-1865.8674, device='cuda:0')
episode: 519 training return: tensor(-1879.1062, device='cuda:0')
epoch: 130 test_true_pfm: -13.379455751200572
episode: 520 training return: tensor(-1876.7124, device='cuda:0')
episode: 521 training return: tensor(-1852.5687, device='cuda:0')
episode: 522 training return: tensor(-1869.3989, device='cuda:0')
episode: 523 training return: tensor(-1885.1307, device='cuda:0')
epoch: 131 test_true_pfm: -7.921564943667565
episode: 524 training return: tensor(-1903.3552, device='cuda:0')
episode: 525 training return: tensor(-1869.0498, device='cuda:0')
episode: 526 training return: tensor(-1872.5366, device='cuda:0')
episode: 527 training return: tensor(-1882.0874, device='cuda:0')
epoch: 132 test_true_pfm: -6.821061568422466
episode: 528 training return: tensor(-1884.0215, device='cuda:0')
episode: 529 training return: tensor(-1867.0486, device='cuda:0')
episode: 530 training return: tensor(-1878.6473, device='cuda:0')
episode: 531 training return: tensor(-1860.7837, device='cuda:0')
epoch: 133 test_true_pfm: -8.957162042410783
episode: 532 training return: tensor(-1859.0918, device='cuda:0')
episode: 533 training return: tensor(-1874.9679, device='cuda:0')
episode: 534 training return: tensor(-1872.0198, device='cuda:0')
episode: 535 training return: tensor(-1892.4170, device='cuda:0')
epoch: 134 test_true_pfm: -6.719907274730095
episode: 536 training return: tensor(-1876.8167, device='cuda:0')
episode: 537 training return: tensor(-1863.3721, device='cuda:0')
episode: 538 training return: tensor(-1875.2727, device='cuda:0')
episode: 539 training return: tensor(-1865.4772, device='cuda:0')
epoch: 135 test_true_pfm: -12.20311540101713
episode: 540 training return: tensor(-1865.5605, device='cuda:0')
episode: 541 training return: tensor(-1864.1163, device='cuda:0')
episode: 542 training return: tensor(-1875.4717, device='cuda:0')
episode: 543 training return: tensor(-1871.5109, device='cuda:0')
epoch: 136 test_true_pfm: -12.712327600173369
episode: 544 training return: tensor(-1885.0864, device='cuda:0')
episode: 545 training return: tensor(-1865.9650, device='cuda:0')
episode: 546 training return: tensor(-1892.0995, device='cuda:0')
episode: 547 training return: tensor(-1865.0898, device='cuda:0')
epoch: 137 test_true_pfm: -12.178503224111864
episode: 548 training return: tensor(-1877.1854, device='cuda:0')
episode: 549 training return: tensor(-1861.2554, device='cuda:0')
episode: 550 training return: tensor(-1859.4760, device='cuda:0')
episode: 551 training return: tensor(-1874.5363, device='cuda:0')
epoch: 138 test_true_pfm: -12.441922862528896
episode: 552 training return: tensor(-1858.5922, device='cuda:0')
episode: 553 training return: tensor(-1862.9905, device='cuda:0')
episode: 554 training return: tensor(-1861.5737, device='cuda:0')
episode: 555 training return: tensor(-1865.4510, device='cuda:0')
epoch: 139 test_true_pfm: -13.173312439242311
episode: 556 training return: tensor(-1867.4349, device='cuda:0')
episode: 557 training return: tensor(-1848.6719, device='cuda:0')
episode: 558 training return: tensor(-1860.0364, device='cuda:0')
episode: 559 training return: tensor(-1859.4429, device='cuda:0')
epoch: 140 test_true_pfm: -14.357028134598048
episode: 560 training return: tensor(-1859.0292, device='cuda:0')
episode: 561 training return: tensor(-1871.9624, device='cuda:0')
episode: 562 training return: tensor(-1867.5728, device='cuda:0')
episode: 563 training return: tensor(-1868.7726, device='cuda:0')
epoch: 141 test_true_pfm: -15.011864466969774
episode: 564 training return: tensor(-1879.6256, device='cuda:0')
episode: 565 training return: tensor(-1867.8368, device='cuda:0')
episode: 566 training return: tensor(-1862.5317, device='cuda:0')
episode: 567 training return: tensor(-1884.6614, device='cuda:0')
epoch: 142 test_true_pfm: -14.229615284857113
episode: 568 training return: tensor(-1845.1042, device='cuda:0')
episode: 569 training return: tensor(-1858.2725, device='cuda:0')
episode: 570 training return: tensor(-1878.5382, device='cuda:0')
episode: 571 training return: tensor(-1878.8123, device='cuda:0')
epoch: 143 test_true_pfm: -17.243282136457207
episode: 572 training return: tensor(-1860.0735, device='cuda:0')
episode: 573 training return: tensor(-1858.1195, device='cuda:0')
episode: 574 training return: tensor(-1871.2384, device='cuda:0')
episode: 575 training return: tensor(-1855.6207, device='cuda:0')
epoch: 144 test_true_pfm: -20.12178106582087
episode: 576 training return: tensor(-1860.8315, device='cuda:0')
episode: 577 training return: tensor(-1865.7274, device='cuda:0')
episode: 578 training return: tensor(-1878.3143, device='cuda:0')
episode: 579 training return: tensor(-1866.6373, device='cuda:0')
epoch: 145 test_true_pfm: -16.47820449714312
episode: 580 training return: tensor(-1848.1141, device='cuda:0')
episode: 581 training return: tensor(-1864.1490, device='cuda:0')
episode: 582 training return: tensor(-1868.7024, device='cuda:0')
episode: 583 training return: tensor(-1857.2854, device='cuda:0')
epoch: 146 test_true_pfm: -8.499948340166364
episode: 584 training return: tensor(-1862.3351, device='cuda:0')
episode: 585 training return: tensor(-1873.5212, device='cuda:0')
episode: 586 training return: tensor(-1854.0958, device='cuda:0')
episode: 587 training return: tensor(-1880.6498, device='cuda:0')
epoch: 147 test_true_pfm: -21.015448661836786
episode: 588 training return: tensor(-1865.5503, device='cuda:0')
episode: 589 training return: tensor(-1854.6287, device='cuda:0')
episode: 590 training return: tensor(-1863.3119, device='cuda:0')
episode: 591 training return: tensor(-1858.0302, device='cuda:0')
epoch: 148 test_true_pfm: -14.673881817672935
episode: 592 training return: tensor(-1870.0150, device='cuda:0')
episode: 593 training return: tensor(-1864.4226, device='cuda:0')
episode: 594 training return: tensor(-1872.3643, device='cuda:0')
episode: 595 training return: tensor(-1854.4225, device='cuda:0')
epoch: 149 test_true_pfm: -13.959784401221777
episode: 596 training return: tensor(-1861.8356, device='cuda:0')
episode: 597 training return: tensor(-1860.8735, device='cuda:0')
episode: 598 training return: tensor(-1866.3638, device='cuda:0')
episode: 599 training return: tensor(-1855.1030, device='cuda:0')
epoch: 150 test_true_pfm: -7.539561061659854
