['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'brac', '--traj', 'expert', '--seed', '3', '--data', '100000']
epoch: 0 training_loss 1.3592962539196014 test_loss: -5.509480285644531
epoch: 1 training_loss -7.465003781318664 test_loss: -9.088146209716797
epoch: 2 training_loss -9.699251713752746 test_loss: -10.314258575439453
epoch: 3 training_loss -10.777424116134643 test_loss: -11.1503662109375
epoch: 4 training_loss -11.388553657531737 test_loss: -11.693466949462891
epoch: 5 training_loss -12.030744762420655 test_loss: -12.331768798828126
epoch: 6 training_loss -12.442616882324218 test_loss: -12.928169250488281
epoch: 7 training_loss -12.71806315422058 test_loss: -12.93432159423828
epoch: 8 training_loss -12.913562898635865 test_loss: -13.255763244628906
epoch: 9 training_loss -13.22985050201416 test_loss: -13.602587890625
epoch: 10 training_loss -13.528563270568847 test_loss: -13.715238952636719
epoch: 11 training_loss -13.551088275909423 test_loss: -13.646778869628907
epoch: 12 training_loss -13.749844913482667 test_loss: -13.762564086914063
epoch: 13 training_loss -13.83618740081787 test_loss: -13.893272399902344
epoch: 14 training_loss -14.077182445526123 test_loss: -14.154986572265624
epoch: 15 training_loss -14.079283809661865 test_loss: -14.181423950195313
epoch: 16 training_loss -14.227555170059205 test_loss: -14.322366333007812
epoch: 17 training_loss -14.424616746902466 test_loss: -14.136703491210938
epoch: 18 training_loss -14.460447235107422 test_loss: -14.597029113769532
epoch: 19 training_loss -14.526670055389404 test_loss: -14.637733459472656
epoch: 20 training_loss -14.61285758972168 test_loss: -14.6885498046875
epoch: 21 training_loss -14.680602149963379 test_loss: -14.84320068359375
epoch: 22 training_loss -14.756351318359375 test_loss: -14.938148498535156
epoch: 23 training_loss -14.819457759857178 test_loss: -14.7058837890625
epoch: 24 training_loss -14.842371034622193 test_loss: -14.934840393066406
epoch: 25 training_loss -14.986635942459106 test_loss: -14.894084167480468
epoch: 26 training_loss -14.99027105331421 test_loss: -14.837577819824219
epoch: 27 training_loss -14.991951417922973 test_loss: -15.145854187011718
epoch: 28 training_loss -15.056719493865966 test_loss: -15.1220458984375
epoch: 29 training_loss -15.055041904449462 test_loss: -15.051686096191407
epoch: 30 training_loss -15.182042541503906 test_loss: -15.116319274902343
epoch: 31 training_loss -15.176225576400757 test_loss: -15.193235778808594
epoch: 32 training_loss -15.241602230072022 test_loss: -15.225151062011719
epoch: 33 training_loss -15.271978263854981 test_loss: -15.457562255859376
epoch: 34 training_loss -15.297799892425537 test_loss: -15.3468505859375
epoch: 35 training_loss -15.311061296463013 test_loss: -15.551251220703126
epoch: 36 training_loss -15.429864072799683 test_loss: -15.442349243164063
epoch: 37 training_loss -15.425025234222412 test_loss: -15.419450378417968
epoch: 38 training_loss -15.415275793075562 test_loss: -15.586477661132813
epoch: 39 training_loss -15.542855939865113 test_loss: -15.492320251464843
epoch: 40 training_loss -15.613212690353393 test_loss: -15.712649536132812
epoch: 41 training_loss -15.511177377700806 test_loss: -15.568170166015625
epoch: 42 training_loss -15.557553262710572 test_loss: -15.673199462890626
epoch: 43 training_loss -15.60265082359314 test_loss: -15.522065734863281
epoch: 44 training_loss -15.570447969436646 test_loss: -15.791293334960937
epoch: 45 training_loss -15.590832118988038 test_loss: -15.463850402832032
epoch: 46 training_loss -15.631034603118897 test_loss: -15.74451904296875
epoch: 47 training_loss -15.75842514038086 test_loss: -15.621194458007812
epoch: 48 training_loss -15.69384259223938 test_loss: -15.536941528320312
epoch: 49 training_loss -15.676940927505493 test_loss: -15.631080627441406
epoch: 50 training_loss -15.694217929840088 test_loss: -15.817201232910156
epoch: 51 training_loss -15.757734270095826 test_loss: -15.770948791503907
epoch: 52 training_loss -15.786047401428222 test_loss: -15.87445526123047
epoch: 53 training_loss -15.781546773910522 test_loss: -15.786640930175782
epoch: 54 training_loss -15.830700368881226 test_loss: -15.881436157226563
epoch: 55 training_loss -15.86126491546631 test_loss: -15.935676574707031
epoch: 56 training_loss -15.815090703964234 test_loss: -15.976359558105468
epoch: 57 training_loss -15.837699098587036 test_loss: -16.065394592285156
epoch: 58 training_loss -15.95932074546814 test_loss: -16.046664428710937
epoch: 59 training_loss -15.926017789840698 test_loss: -15.852009582519532
epoch: 60 training_loss -15.91138442993164 test_loss: -16.11885223388672
epoch: 61 training_loss -15.98432508468628 test_loss: -16.02268829345703
epoch: 62 training_loss -16.01265016555786 test_loss: -15.836628723144532
epoch: 63 training_loss -16.001570606231688 test_loss: -15.901345825195312
epoch: 64 training_loss -16.041427602767943 test_loss: -16.050517272949218
epoch: 65 training_loss -15.995546579360962 test_loss: -16.079936218261718
epoch: 66 training_loss -16.03715905189514 test_loss: -15.935760498046875
epoch: 67 training_loss -16.094296827316285 test_loss: -15.88184814453125
epoch: 68 training_loss -16.05033661842346 test_loss: -15.953834533691406
epoch: 69 training_loss -16.100122299194336 test_loss: -16.246327209472657
epoch: 70 training_loss -16.016841220855714 test_loss: -16.04564666748047
epoch: 71 training_loss -16.129686880111695 test_loss: -16.22646484375
epoch: 72 training_loss -16.084054479599 test_loss: -16.048362731933594
epoch: 73 training_loss -16.146926956176756 test_loss: -16.035047912597655
epoch: 74 training_loss -16.08375715255737 test_loss: -16.220469665527343
epoch: 75 training_loss -16.149046726226807 test_loss: -16.127557373046876
epoch: 76 training_loss -16.24329891204834 test_loss: -16.174966430664064
epoch: 77 training_loss -16.188703737258912 test_loss: -16.224946594238283
epoch: 78 training_loss -16.12262366294861 test_loss: -15.9265869140625
epoch: 79 training_loss -16.247756309509278 test_loss: -16.36708221435547
epoch: 80 training_loss -16.21642683982849 test_loss: -16.32808837890625
epoch: 81 training_loss -16.205945634841918 test_loss: -16.247117614746095
epoch: 82 training_loss -16.141052265167236 test_loss: -16.239073181152342
epoch: 83 training_loss -16.179719305038454 test_loss: -16.26964111328125
epoch: 84 training_loss -16.282106399536133 test_loss: -16.262863159179688
epoch: 85 training_loss -16.256266403198243 test_loss: -16.091754150390624
epoch: 86 training_loss -16.15202299118042 test_loss: -16.21118621826172
epoch: 87 training_loss -16.29117569923401 test_loss: -16.150418090820313
epoch: 88 training_loss -16.356411590576172 test_loss: -16.31456604003906
epoch: 89 training_loss -16.29786608695984 test_loss: -16.295909118652343
epoch: 90 training_loss -16.348333883285523 test_loss: -16.3973388671875
epoch: 91 training_loss -16.409469175338746 test_loss: -16.358033752441408
epoch: 92 training_loss -16.360585803985597 test_loss: -16.35149688720703
epoch: 93 training_loss -16.38842855453491 test_loss: -16.37284698486328
epoch: 94 training_loss -16.30576596260071 test_loss: -16.369732666015626
epoch: 95 training_loss -16.38947546005249 test_loss: -16.47156219482422
epoch: 96 training_loss -16.354220695495606 test_loss: -16.494921875
epoch: 97 training_loss -16.37147071838379 test_loss: -16.410246276855467
epoch: 98 training_loss -16.432207946777343 test_loss: -16.315797424316408
epoch: 99 training_loss -16.43178918838501 test_loss: -16.269972229003905
epoch: 100 training_loss -16.465166778564452 test_loss: -16.47185363769531
epoch: 101 training_loss -16.42544080734253 test_loss: -16.57288055419922
epoch: 102 training_loss -16.423553981781005 test_loss: -16.510687255859374
epoch: 103 training_loss -16.406334562301637 test_loss: -16.611959838867186
epoch: 104 training_loss -16.43458416938782 test_loss: -16.617108154296876
epoch: 105 training_loss -16.45452290534973 test_loss: -16.494242858886718
epoch: 106 training_loss -16.483665895462035 test_loss: -16.610504150390625
epoch: 107 training_loss -16.44405779838562 test_loss: -16.461802673339843
epoch: 108 training_loss -16.44560112953186 test_loss: -16.561238098144532
epoch: 109 training_loss -16.512477550506592 test_loss: -16.660813903808595
epoch: 110 training_loss -16.51768871307373 test_loss: -16.639247131347656
epoch: 111 training_loss -16.522562475204467 test_loss: -16.532342529296876
epoch: 112 training_loss -16.47925498008728 test_loss: -16.49846496582031
epoch: 113 training_loss -16.455204906463624 test_loss: -16.59796600341797
epoch: 114 training_loss -16.48193296432495 test_loss: -16.488433837890625
epoch: 115 training_loss -16.505824451446532 test_loss: -16.64762725830078
epoch: 116 training_loss -16.543289279937746 test_loss: -16.565284729003906
epoch: 117 training_loss -16.552919330596925 test_loss: -16.488798522949217
epoch: 118 training_loss -16.49477642059326 test_loss: -16.687347412109375
epoch: 119 training_loss -16.610911540985107 test_loss: -16.599322509765624
epoch: 120 training_loss -16.623336353302 test_loss: -16.58735046386719
epoch: 121 training_loss -16.56667818069458 test_loss: -16.413523864746093
epoch: 122 training_loss -16.669657745361327 test_loss: -16.62749481201172
epoch: 123 training_loss -16.656045780181884 test_loss: -16.677549743652342
epoch: 124 training_loss -16.62802861213684 test_loss: -16.498785400390624
epoch: 125 training_loss -16.57526967048645 test_loss: -16.686712646484374
epoch: 126 training_loss -16.578440656661986 test_loss: -16.667880249023437
epoch: 127 training_loss -16.58602801322937 test_loss: -16.632371520996095
epoch: 128 training_loss -16.611701469421387 test_loss: -16.497630310058593
epoch: 129 training_loss -16.595143175125123 test_loss: -16.782608032226562
epoch: 130 training_loss -16.630961923599244 test_loss: -16.666549682617188
epoch: 131 training_loss -16.695563402175903 test_loss: -16.6823486328125
epoch: 132 training_loss -16.62720764160156 test_loss: -16.750538635253907
epoch: 133 training_loss -16.598525199890137 test_loss: -16.77790985107422
epoch: 134 training_loss -16.665655498504638 test_loss: -16.676185607910156
epoch: 135 training_loss -16.68972490310669 test_loss: -16.768934631347655
epoch: 136 training_loss -16.71358165740967 test_loss: -16.688427734375
epoch: 137 training_loss -16.702717304229736 test_loss: -16.71741638183594
epoch: 138 training_loss -16.763639793395996 test_loss: -16.516586303710938
epoch: 139 training_loss -16.773676061630248 test_loss: -16.62818603515625
epoch: 140 training_loss -16.72594038963318 test_loss: -16.896617126464843
epoch: 141 training_loss -16.73926387786865 test_loss: -16.714192199707032
epoch: 142 training_loss -16.692262506484987 test_loss: -16.74090118408203
epoch: 143 training_loss -16.699485874176027 test_loss: -16.664096069335937
epoch: 144 training_loss -16.72906064033508 test_loss: -16.88939514160156
epoch: 145 training_loss -16.713000736236573 test_loss: -16.570277404785156
epoch: 146 training_loss -16.742598638534545 test_loss: -16.658601379394533
epoch: 147 training_loss -16.77907795906067 test_loss: -16.826448059082033
epoch: 148 training_loss -16.734302358627318 test_loss: -16.66619873046875
epoch: 149 training_loss -16.79040391921997 test_loss: -16.85858154296875
11.141339628123749
episode: 0 training return: tensor(-5430.1548, device='cuda:0')
episode: 1 training return: tensor(-6.0205e+09, device='cuda:0')
episode: 2 training return: tensor(-8.0090e+11, device='cuda:0')
episode: 3 training return: tensor(-9409.9219, device='cuda:0')
epoch: 1 test_true_pfm: -121.34168308118298
episode: 4 training return: tensor(-6.0882e+11, device='cuda:0')
episode: 5 training return: tensor(-4281.5806, device='cuda:0')
episode: 6 training return: tensor(-4927.9282, device='cuda:0')
episode: 7 training return: tensor(-1.3759e+11, device='cuda:0')
epoch: 2 test_true_pfm: 235.81422919597878
episode: 8 training return: tensor(-2.6760e+19, device='cuda:0')
episode: 9 training return: tensor(-7.1703e+09, device='cuda:0')
episode: 10 training return: tensor(-4066.2639, device='cuda:0')
episode: 11 training return: tensor(-6600.1196, device='cuda:0')
epoch: 3 test_true_pfm: -125.51730121393128
episode: 12 training return: tensor(-364762.2500, device='cuda:0')
episode: 13 training return: tensor(-4491.1655, device='cuda:0')
episode: 14 training return: tensor(-4302.5020, device='cuda:0')
episode: 15 training return: tensor(-360818.1875, device='cuda:0')
epoch: 4 test_true_pfm: 2.0408589521013405
episode: 16 training return: tensor(-5264.2959, device='cuda:0')
episode: 17 training return: tensor(-3860.1260, device='cuda:0')
episode: 18 training return: tensor(-7606.7417, device='cuda:0')
episode: 19 training return: tensor(-2.0457e+09, device='cuda:0')
epoch: 5 test_true_pfm: 130.97151660453378
episode: 20 training return: tensor(-683885.6250, device='cuda:0')
episode: 21 training return: tensor(-6042.7007, device='cuda:0')
episode: 22 training return: tensor(-1.8864e+10, device='cuda:0')
episode: 23 training return: tensor(-424443.2188, device='cuda:0')
epoch: 6 test_true_pfm: -144.90330454011436
episode: 24 training return: tensor(-2.2649e+10, device='cuda:0')
episode: 25 training return: tensor(-2.1114e+09, device='cuda:0')
episode: 26 training return: tensor(-224770.5000, device='cuda:0')
episode: 27 training return: tensor(-5074.9546, device='cuda:0')
epoch: 7 test_true_pfm: 15.578942912930321
episode: 28 training return: tensor(-731226.4375, device='cuda:0')
episode: 29 training return: tensor(-47828.4062, device='cuda:0')
episode: 30 training return: tensor(-7400.3779, device='cuda:0')
episode: 31 training return: tensor(-3.4415e+09, device='cuda:0')
epoch: 8 test_true_pfm: -30.239330135339458
episode: 32 training return: tensor(-7032.3140, device='cuda:0')
episode: 33 training return: tensor(-4562.0420, device='cuda:0')
episode: 34 training return: tensor(-183244., device='cuda:0')
episode: 35 training return: tensor(-3.2290e+09, device='cuda:0')
epoch: 9 test_true_pfm: -118.8371300388413
episode: 36 training return: tensor(-298553.5000, device='cuda:0')
episode: 37 training return: tensor(-5999.8291, device='cuda:0')
episode: 38 training return: tensor(-5666.6226, device='cuda:0')
episode: 39 training return: tensor(-92959.2812, device='cuda:0')
epoch: 10 test_true_pfm: -48.64295561708078
episode: 40 training return: tensor(-18366.3555, device='cuda:0')
episode: 41 training return: tensor(-4919.6733, device='cuda:0')
episode: 42 training return: tensor(-4877.1069, device='cuda:0')
episode: 43 training return: tensor(-952116.6250, device='cuda:0')
epoch: 11 test_true_pfm: 174.1562310574753
episode: 44 training return: tensor(-6394.6074, device='cuda:0')
episode: 45 training return: tensor(-8.4785e+09, device='cuda:0')
episode: 46 training return: tensor(-5762.6880, device='cuda:0')
episode: 47 training return: tensor(-6909.9419, device='cuda:0')
epoch: 12 test_true_pfm: -104.37433825884405
episode: 48 training return: tensor(-1.3013e+12, device='cuda:0')
episode: 49 training return: tensor(-5480.6660, device='cuda:0')
episode: 50 training return: tensor(-545645.1250, device='cuda:0')
episode: 51 training return: tensor(-2.2789e+11, device='cuda:0')
epoch: 13 test_true_pfm: -114.95185004164095
episode: 52 training return: tensor(-3.5314e+12, device='cuda:0')
episode: 53 training return: tensor(-216264.5156, device='cuda:0')
episode: 54 training return: tensor(-7346.3574, device='cuda:0')
episode: 55 training return: tensor(-2.1886e+09, device='cuda:0')
epoch: 14 test_true_pfm: -78.67724753574834
episode: 56 training return: tensor(-1.6868e+09, device='cuda:0')
episode: 57 training return: tensor(-6550.9741, device='cuda:0')
episode: 58 training return: tensor(-734453.8750, device='cuda:0')
episode: 59 training return: tensor(-4218.5928, device='cuda:0')
epoch: 15 test_true_pfm: 80.50624384728265
episode: 60 training return: tensor(-3.3822e+09, device='cuda:0')
episode: 61 training return: tensor(-1.7141e+09, device='cuda:0')
episode: 62 training return: tensor(-5383.0483, device='cuda:0')
episode: 63 training return: tensor(-4.8085e+12, device='cuda:0')
epoch: 16 test_true_pfm: -21.386856078904724
episode: 64 training return: tensor(-318978.2500, device='cuda:0')
episode: 65 training return: tensor(-10062.0645, device='cuda:0')
episode: 66 training return: tensor(-5932.5059, device='cuda:0')
episode: 67 training return: tensor(-4.7746e+10, device='cuda:0')
epoch: 17 test_true_pfm: 86.1775092501146
episode: 68 training return: tensor(-57922.7852, device='cuda:0')
episode: 69 training return: tensor(-5436.6890, device='cuda:0')
episode: 70 training return: tensor(-127022.3594, device='cuda:0')
episode: 71 training return: tensor(-27897.9023, device='cuda:0')
epoch: 18 test_true_pfm: 212.9951534306111
episode: 72 training return: tensor(-6971.0996, device='cuda:0')
episode: 73 training return: tensor(-1279038.5000, device='cuda:0')
episode: 74 training return: tensor(-3.2640e+09, device='cuda:0')
episode: 75 training return: tensor(-17955.5176, device='cuda:0')
epoch: 19 test_true_pfm: -131.70670489489456
episode: 76 training return: tensor(-29990.7949, device='cuda:0')
episode: 77 training return: tensor(-159082.7969, device='cuda:0')
episode: 78 training return: tensor(-259723.4375, device='cuda:0')
episode: 79 training return: tensor(-3.3780e+09, device='cuda:0')
epoch: 20 test_true_pfm: 209.77356340956075
episode: 80 training return: tensor(-6.8099e+11, device='cuda:0')
episode: 81 training return: tensor(-4.8101e+08, device='cuda:0')
episode: 82 training return: tensor(-5519.2661, device='cuda:0')
episode: 83 training return: tensor(-7446.4058, device='cuda:0')
epoch: 21 test_true_pfm: -37.7588063023128
episode: 84 training return: tensor(-6225.7739, device='cuda:0')
episode: 85 training return: tensor(-947684.6250, device='cuda:0')
episode: 86 training return: tensor(-448325.0938, device='cuda:0')
episode: 87 training return: tensor(-41506.9023, device='cuda:0')
epoch: 22 test_true_pfm: -97.63285114787853
episode: 88 training return: tensor(-5117.5977, device='cuda:0')
episode: 89 training return: tensor(-4887.6470, device='cuda:0')
episode: 90 training return: tensor(-1523481.1250, device='cuda:0')
episode: 91 training return: tensor(-45869.0430, device='cuda:0')
epoch: 23 test_true_pfm: 96.4995247571796
episode: 92 training return: tensor(-13744.1553, device='cuda:0')
episode: 93 training return: tensor(-372186.8125, device='cuda:0')
episode: 94 training return: tensor(-3.3136e+09, device='cuda:0')
episode: 95 training return: tensor(-5384.2764, device='cuda:0')
epoch: 24 test_true_pfm: 66.39148645345936
episode: 96 training return: tensor(-4.1550e+08, device='cuda:0')
episode: 97 training return: tensor(-4.8477e+10, device='cuda:0')
episode: 98 training return: tensor(-4608.3989, device='cuda:0')
episode: 99 training return: tensor(-7.1082e+12, device='cuda:0')
epoch: 25 test_true_pfm: 18.739844080032118
episode: 100 training return: tensor(-5677.8335, device='cuda:0')
episode: 101 training return: tensor(-1.7922e+11, device='cuda:0')
episode: 102 training return: tensor(-1.5885e+16, device='cuda:0')
episode: 103 training return: tensor(-5.6813e+09, device='cuda:0')
epoch: 26 test_true_pfm: 88.31055907392046
episode: 104 training return: tensor(-3.8911e+09, device='cuda:0')
episode: 105 training return: tensor(-9248.5908, device='cuda:0')
episode: 106 training return: tensor(-2.4430e+09, device='cuda:0')
episode: 107 training return: tensor(-9.5315e+09, device='cuda:0')
epoch: 27 test_true_pfm: -144.02704450121516
episode: 108 training return: tensor(-2.3926e+11, device='cuda:0')
episode: 109 training return: tensor(-326192.8750, device='cuda:0')
episode: 110 training return: tensor(-8037.3652, device='cuda:0')
episode: 111 training return: tensor(-872815.6875, device='cuda:0')
epoch: 28 test_true_pfm: -32.98115048021807
episode: 112 training return: tensor(-352690.1250, device='cuda:0')
episode: 113 training return: tensor(-506546.1250, device='cuda:0')
episode: 114 training return: tensor(-61580216., device='cuda:0')
episode: 115 training return: tensor(-7855.7310, device='cuda:0')
epoch: 29 test_true_pfm: 162.04376062440517
episode: 116 training return: tensor(-5272.8735, device='cuda:0')
episode: 117 training return: tensor(-6.2428e+12, device='cuda:0')
episode: 118 training return: tensor(-27144.2598, device='cuda:0')
episode: 119 training return: tensor(-10347.4941, device='cuda:0')
epoch: 30 test_true_pfm: -4.498039017641844
episode: 120 training return: tensor(-7921.6152, device='cuda:0')
episode: 121 training return: tensor(-10955.5508, device='cuda:0')
episode: 122 training return: tensor(-3.7421e+11, device='cuda:0')
episode: 123 training return: tensor(-605354.1875, device='cuda:0')
epoch: 31 test_true_pfm: -15.041243131930422
episode: 124 training return: tensor(-141263.8438, device='cuda:0')
episode: 125 training return: tensor(-355783.3438, device='cuda:0')
episode: 126 training return: tensor(-111759.9609, device='cuda:0')
episode: 127 training return: tensor(-199081.9531, device='cuda:0')
epoch: 32 test_true_pfm: -51.832297933896314
episode: 128 training return: tensor(-207871.1719, device='cuda:0')
episode: 129 training return: tensor(-127846.5469, device='cuda:0')
episode: 130 training return: tensor(-4.8137e+10, device='cuda:0')
episode: 131 training return: tensor(-6714.3159, device='cuda:0')
epoch: 33 test_true_pfm: -24.900676264376358
episode: 132 training return: tensor(-5412.7974, device='cuda:0')
episode: 133 training return: tensor(-7530.3696, device='cuda:0')
episode: 134 training return: tensor(-1.2991e+11, device='cuda:0')
episode: 135 training return: tensor(-7.8781e+12, device='cuda:0')
epoch: 34 test_true_pfm: -32.11385838873375
episode: 136 training return: tensor(-6452.8848, device='cuda:0')
episode: 137 training return: tensor(-415042.8438, device='cuda:0')
episode: 138 training return: tensor(-2.4311e+10, device='cuda:0')
episode: 139 training return: tensor(-208550.3281, device='cuda:0')
epoch: 35 test_true_pfm: -1.6747164869440165
episode: 140 training return: tensor(-5281.3525, device='cuda:0')
episode: 141 training return: tensor(-4427.6553, device='cuda:0')
episode: 142 training return: tensor(-5242.9785, device='cuda:0')
episode: 143 training return: tensor(-5745.0664, device='cuda:0')
epoch: 36 test_true_pfm: -100.62051560589457
episode: 144 training return: tensor(-4593.1919, device='cuda:0')
episode: 145 training return: tensor(-5461.1353, device='cuda:0')
episode: 146 training return: tensor(-8.5002e+08, device='cuda:0')
episode: 147 training return: tensor(-5396.5522, device='cuda:0')
epoch: 37 test_true_pfm: -4.823277281098531
episode: 148 training return: tensor(-1.4933e+12, device='cuda:0')
episode: 149 training return: tensor(-5372.1689, device='cuda:0')
episode: 150 training return: tensor(-4.2926e+09, device='cuda:0')
episode: 151 training return: tensor(-8943.7871, device='cuda:0')
epoch: 38 test_true_pfm: -52.15026693166005
episode: 152 training return: tensor(-4778.9907, device='cuda:0')
episode: 153 training return: tensor(-4.8141e+10, device='cuda:0')
episode: 154 training return: tensor(-197663.2500, device='cuda:0')
episode: 155 training return: tensor(-9684.7734, device='cuda:0')
epoch: 39 test_true_pfm: 42.71595608979754
episode: 156 training return: tensor(-4551.7310, device='cuda:0')
episode: 157 training return: tensor(-335931.9375, device='cuda:0')
episode: 158 training return: tensor(-144884.0938, device='cuda:0')
episode: 159 training return: tensor(-4.6944e+08, device='cuda:0')
epoch: 40 test_true_pfm: -63.90258794022407
episode: 160 training return: tensor(-4597.6460, device='cuda:0')
episode: 161 training return: tensor(-5278.1016, device='cuda:0')
episode: 162 training return: tensor(-5016.4941, device='cuda:0')
episode: 163 training return: tensor(-142083.0781, device='cuda:0')
epoch: 41 test_true_pfm: -161.08628149313327
episode: 164 training return: tensor(-1327384.8750, device='cuda:0')
episode: 165 training return: tensor(-5131.4053, device='cuda:0')
episode: 166 training return: tensor(-2.0477e+11, device='cuda:0')
episode: 167 training return: tensor(-3.7232e+09, device='cuda:0')
epoch: 42 test_true_pfm: 36.7922282195114
episode: 168 training return: tensor(-311073., device='cuda:0')
episode: 169 training return: tensor(-9592.4775, device='cuda:0')
episode: 170 training return: tensor(-5.5162e+12, device='cuda:0')
episode: 171 training return: tensor(-981913.4375, device='cuda:0')
epoch: 43 test_true_pfm: -112.2898366431284
episode: 172 training return: tensor(-235593.8594, device='cuda:0')
episode: 173 training return: tensor(-3.2812e+11, device='cuda:0')
episode: 174 training return: tensor(-4.2258e+09, device='cuda:0')
episode: 175 training return: tensor(-1086985.2500, device='cuda:0')
epoch: 44 test_true_pfm: -97.52130492106521
episode: 176 training return: tensor(-4905.7935, device='cuda:0')
episode: 177 training return: tensor(-4958.1802, device='cuda:0')
episode: 178 training return: tensor(-7040.9429, device='cuda:0')
episode: 179 training return: tensor(-2.9534e+10, device='cuda:0')
epoch: 45 test_true_pfm: -41.548849703644464
episode: 180 training return: tensor(-4335.9907, device='cuda:0')
episode: 181 training return: tensor(-637522.8125, device='cuda:0')
episode: 182 training return: tensor(-5100.2861, device='cuda:0')
episode: 183 training return: tensor(-8029.9136, device='cuda:0')
epoch: 46 test_true_pfm: -71.89413873827759
episode: 184 training return: tensor(-14304.2256, device='cuda:0')
episode: 185 training return: tensor(-1.5394e+10, device='cuda:0')
episode: 186 training return: tensor(-52118.9531, device='cuda:0')
episode: 187 training return: tensor(-5696.2192, device='cuda:0')
epoch: 47 test_true_pfm: -69.16890902311093
episode: 188 training return: tensor(-24142.9062, device='cuda:0')
episode: 189 training return: tensor(-209797.4531, device='cuda:0')
episode: 190 training return: tensor(-5.5666e+12, device='cuda:0')
episode: 191 training return: tensor(-8865.7881, device='cuda:0')
epoch: 48 test_true_pfm: 31.09217833740212
episode: 192 training return: tensor(-22056.9414, device='cuda:0')
episode: 193 training return: tensor(-9.5415e+09, device='cuda:0')
episode: 194 training return: tensor(-4518.7070, device='cuda:0')
episode: 195 training return: tensor(-56563.4883, device='cuda:0')
epoch: 49 test_true_pfm: -31.591430116069194
episode: 196 training return: tensor(-2.4895e+11, device='cuda:0')
episode: 197 training return: tensor(-5500.5269, device='cuda:0')
episode: 198 training return: tensor(-9644.0449, device='cuda:0')
episode: 199 training return: tensor(-150351.7812, device='cuda:0')
epoch: 50 test_true_pfm: -28.203970221509262
episode: 200 training return: tensor(-5745.1841, device='cuda:0')
episode: 201 training return: tensor(-2.7210e+10, device='cuda:0')
episode: 202 training return: tensor(-4630.5190, device='cuda:0')
episode: 203 training return: tensor(-5337.8970, device='cuda:0')
epoch: 51 test_true_pfm: -54.57606940724895
episode: 204 training return: tensor(-86566.7734, device='cuda:0')
episode: 205 training return: tensor(-5668.1621, device='cuda:0')
episode: 206 training return: tensor(-1.3769e+09, device='cuda:0')
episode: 207 training return: tensor(-7.4276e+08, device='cuda:0')
epoch: 52 test_true_pfm: 11.484086087507558
episode: 208 training return: tensor(-7863.4062, device='cuda:0')
episode: 209 training return: tensor(-4348.1768, device='cuda:0')
episode: 210 training return: tensor(-1.4835e+10, device='cuda:0')
episode: 211 training return: tensor(-11236.3398, device='cuda:0')
epoch: 53 test_true_pfm: -108.53310859534848
episode: 212 training return: tensor(-6.9504e+10, device='cuda:0')
episode: 213 training return: tensor(-6940.1187, device='cuda:0')
episode: 214 training return: tensor(-278148.0938, device='cuda:0')
episode: 215 training return: tensor(-5684868.5000, device='cuda:0')
epoch: 54 test_true_pfm: -13.061255394784128
episode: 216 training return: tensor(-5345.2012, device='cuda:0')
episode: 217 training return: tensor(-178752.6094, device='cuda:0')
episode: 218 training return: tensor(-8066.8779, device='cuda:0')
episode: 219 training return: tensor(-8040.5562, device='cuda:0')
epoch: 55 test_true_pfm: 139.79862955687577
episode: 220 training return: tensor(-5556.3960, device='cuda:0')
episode: 221 training return: tensor(-4676.8013, device='cuda:0')
episode: 222 training return: tensor(-4801.1626, device='cuda:0')
episode: 223 training return: tensor(-4542.7964, device='cuda:0')
epoch: 56 test_true_pfm: -11.305436798176288
episode: 224 training return: tensor(-8.2650e+12, device='cuda:0')
episode: 225 training return: tensor(-5164.2515, device='cuda:0')
episode: 226 training return: tensor(-2.8994e+09, device='cuda:0')
episode: 227 training return: tensor(-4742.8931, device='cuda:0')
epoch: 57 test_true_pfm: 40.39848714313095
episode: 228 training return: tensor(-5.2811e+12, device='cuda:0')
episode: 229 training return: tensor(-6447.3745, device='cuda:0')
episode: 230 training return: tensor(-5285.8394, device='cuda:0')
episode: 231 training return: tensor(-5676.6499, device='cuda:0')
epoch: 58 test_true_pfm: 16.00715067967685
episode: 232 training return: tensor(-5830.0156, device='cuda:0')
episode: 233 training return: tensor(-81539.2969, device='cuda:0')
episode: 234 training return: tensor(-6080.4741, device='cuda:0')
episode: 235 training return: tensor(-1.3335e+10, device='cuda:0')
epoch: 59 test_true_pfm: 80.48633473980586
episode: 236 training return: tensor(-1.5960e+09, device='cuda:0')
episode: 237 training return: tensor(-4.7355e+12, device='cuda:0')
episode: 238 training return: tensor(-1.7545e+12, device='cuda:0')
episode: 239 training return: tensor(-4934.7690, device='cuda:0')
epoch: 60 test_true_pfm: -93.86204451139344
episode: 240 training return: tensor(-7061.3999, device='cuda:0')
episode: 241 training return: tensor(-3.3340e+11, device='cuda:0')
episode: 242 training return: tensor(-5.2973e+10, device='cuda:0')
episode: 243 training return: tensor(-2.1146e+10, device='cuda:0')
epoch: 61 test_true_pfm: 7.461963085665833
episode: 244 training return: tensor(-6189.8867, device='cuda:0')
episode: 245 training return: tensor(-5.1886e+09, device='cuda:0')
episode: 246 training return: tensor(-231104.7656, device='cuda:0')
episode: 247 training return: tensor(-2.5893e+09, device='cuda:0')
epoch: 62 test_true_pfm: 40.373631922894376
episode: 248 training return: tensor(-4375.4756, device='cuda:0')
episode: 249 training return: tensor(-6993.9297, device='cuda:0')
episode: 250 training return: tensor(-1.6852e+11, device='cuda:0')
episode: 251 training return: tensor(-2.0773e+11, device='cuda:0')
epoch: 63 test_true_pfm: -6.214079493415884
episode: 252 training return: tensor(-7546.8267, device='cuda:0')
episode: 253 training return: tensor(-4.0874e+09, device='cuda:0')
episode: 254 training return: tensor(-2.6304e+12, device='cuda:0')
episode: 255 training return: tensor(-2.4816e+09, device='cuda:0')
epoch: 64 test_true_pfm: -65.13554486581283
episode: 256 training return: tensor(-1182386.7500, device='cuda:0')
episode: 257 training return: tensor(-3.5930e+09, device='cuda:0')
episode: 258 training return: tensor(-819784.5625, device='cuda:0')
episode: 259 training return: tensor(-4319.4004, device='cuda:0')
epoch: 65 test_true_pfm: 48.2609030819366
episode: 260 training return: tensor(-4.3505e+12, device='cuda:0')
episode: 261 training return: tensor(-4374.6025, device='cuda:0')
episode: 262 training return: tensor(-4.7291e+09, device='cuda:0')
episode: 263 training return: tensor(-4696.4312, device='cuda:0')
epoch: 66 test_true_pfm: 13.154761315431804
episode: 264 training return: tensor(-1.4473e+11, device='cuda:0')
episode: 265 training return: tensor(-6167.5938, device='cuda:0')
episode: 266 training return: tensor(-5.6173e+09, device='cuda:0')
episode: 267 training return: tensor(-5037.8940, device='cuda:0')
epoch: 67 test_true_pfm: 93.6641196462039
episode: 268 training return: tensor(-10630.4854, device='cuda:0')
episode: 269 training return: tensor(-3.3824e+09, device='cuda:0')
episode: 270 training return: tensor(-119252.5547, device='cuda:0')
episode: 271 training return: tensor(-8575.7373, device='cuda:0')
epoch: 68 test_true_pfm: -39.50664019943772
episode: 272 training return: tensor(-3.5189e+09, device='cuda:0')
episode: 273 training return: tensor(-735532.3750, device='cuda:0')
episode: 274 training return: tensor(-4.7855e+12, device='cuda:0')
episode: 275 training return: tensor(-5470.7090, device='cuda:0')
epoch: 69 test_true_pfm: -110.95632236490542
episode: 276 training return: tensor(-1.1545e+13, device='cuda:0')
episode: 277 training return: tensor(-975339.8125, device='cuda:0')
episode: 278 training return: tensor(-14117.1006, device='cuda:0')
episode: 279 training return: tensor(-8326.2715, device='cuda:0')
epoch: 70 test_true_pfm: 124.79769169041849
episode: 280 training return: tensor(-31360.9551, device='cuda:0')
episode: 281 training return: tensor(-16260.7393, device='cuda:0')
episode: 282 training return: tensor(-5.3217e+12, device='cuda:0')
episode: 283 training return: tensor(-1008307.1250, device='cuda:0')
epoch: 71 test_true_pfm: 39.15847276270909
episode: 284 training return: tensor(-4734.9531, device='cuda:0')
episode: 285 training return: tensor(-3.3436e+09, device='cuda:0')
episode: 286 training return: tensor(-4621.9424, device='cuda:0')
episode: 287 training return: tensor(-5242.5532, device='cuda:0')
epoch: 72 test_true_pfm: 42.95437179529204
episode: 288 training return: tensor(-1.7723e+10, device='cuda:0')
episode: 289 training return: tensor(-2.7675e+09, device='cuda:0')
episode: 290 training return: tensor(-5091.8442, device='cuda:0')
episode: 291 training return: tensor(-48381.6914, device='cuda:0')
epoch: 73 test_true_pfm: 159.56323804185922
episode: 292 training return: tensor(-155207.1875, device='cuda:0')
episode: 293 training return: tensor(-6.3212e+08, device='cuda:0')
episode: 294 training return: tensor(-3.9032e+12, device='cuda:0')
episode: 295 training return: tensor(-6295.6323, device='cuda:0')
epoch: 74 test_true_pfm: -32.8841020677413
episode: 296 training return: tensor(-6551.8467, device='cuda:0')
episode: 297 training return: tensor(-1.6076e+08, device='cuda:0')
episode: 298 training return: tensor(-6197.6406, device='cuda:0')
episode: 299 training return: tensor(-6685.3755, device='cuda:0')
epoch: 75 test_true_pfm: 21.3480251308645
episode: 300 training return: tensor(-6547.8794, device='cuda:0')
episode: 301 training return: tensor(-63103.1094, device='cuda:0')
episode: 302 training return: tensor(-4.6904e+12, device='cuda:0')
episode: 303 training return: tensor(-6058.6392, device='cuda:0')
epoch: 76 test_true_pfm: 65.49950356414652
episode: 304 training return: tensor(-369631.8438, device='cuda:0')
episode: 305 training return: tensor(-5853.8501, device='cuda:0')
episode: 306 training return: tensor(-3.0059e+11, device='cuda:0')
episode: 307 training return: tensor(-5.2153e+10, device='cuda:0')
epoch: 77 test_true_pfm: -254.40424363236954
episode: 308 training return: tensor(-9103.9258, device='cuda:0')
episode: 309 training return: tensor(-5.0468e+12, device='cuda:0')
episode: 310 training return: tensor(-4930.2744, device='cuda:0')
episode: 311 training return: tensor(-2.7677e+10, device='cuda:0')
epoch: 78 test_true_pfm: 56.16646571798702
episode: 312 training return: tensor(-10558.0557, device='cuda:0')
episode: 313 training return: tensor(-5204.4922, device='cuda:0')
episode: 314 training return: tensor(-4921.5327, device='cuda:0')
episode: 315 training return: tensor(-5984.1914, device='cuda:0')
epoch: 79 test_true_pfm: -167.400568048633
episode: 316 training return: tensor(-445686.9062, device='cuda:0')
episode: 317 training return: tensor(-6140.4160, device='cuda:0')
episode: 318 training return: tensor(-5789.5273, device='cuda:0')
episode: 319 training return: tensor(-224372.1094, device='cuda:0')
epoch: 80 test_true_pfm: 71.23731792321396
episode: 320 training return: tensor(-11486.1943, device='cuda:0')
episode: 321 training return: tensor(-2.0259e+09, device='cuda:0')
episode: 322 training return: tensor(-7212.1528, device='cuda:0')
episode: 323 training return: tensor(-7911.3359, device='cuda:0')
epoch: 81 test_true_pfm: 32.33123549821906
episode: 324 training return: tensor(-3.9072e+09, device='cuda:0')
episode: 325 training return: tensor(-7917.1924, device='cuda:0')
episode: 326 training return: tensor(-7107.0430, device='cuda:0')
episode: 327 training return: tensor(-184512.9844, device='cuda:0')
epoch: 82 test_true_pfm: -112.74219802449784
episode: 328 training return: tensor(-2.8448e+09, device='cuda:0')
episode: 329 training return: tensor(-1.7587e+09, device='cuda:0')
episode: 330 training return: tensor(-381557.9688, device='cuda:0')
episode: 331 training return: tensor(-19249.8691, device='cuda:0')
epoch: 83 test_true_pfm: 14.600506428772988
episode: 332 training return: tensor(-2.3814e+12, device='cuda:0')
episode: 333 training return: tensor(-289369.6562, device='cuda:0')
episode: 334 training return: tensor(-100674.4141, device='cuda:0')
episode: 335 training return: tensor(-2.3901e+09, device='cuda:0')
epoch: 84 test_true_pfm: 37.19603545864577
episode: 336 training return: tensor(-5406.6016, device='cuda:0')
episode: 337 training return: tensor(-960228., device='cuda:0')
episode: 338 training return: tensor(-5827.4121, device='cuda:0')
episode: 339 training return: tensor(-5.0536e+09, device='cuda:0')
epoch: 85 test_true_pfm: -39.68529754139791
episode: 340 training return: tensor(-5665.4336, device='cuda:0')
episode: 341 training return: tensor(-4235.4585, device='cuda:0')
episode: 342 training return: tensor(-4606524.5000, device='cuda:0')
episode: 343 training return: tensor(-2.1437e+10, device='cuda:0')
epoch: 86 test_true_pfm: -66.41071019861816
episode: 344 training return: tensor(-4.6488e+12, device='cuda:0')
episode: 345 training return: tensor(-4542.7222, device='cuda:0')
episode: 346 training return: tensor(-95573072., device='cuda:0')
episode: 347 training return: tensor(-2.2453e+11, device='cuda:0')
epoch: 87 test_true_pfm: -48.25487556292595
episode: 348 training return: tensor(-336259.3750, device='cuda:0')
episode: 349 training return: tensor(-257144.2344, device='cuda:0')
episode: 350 training return: tensor(-258238.1562, device='cuda:0')
episode: 351 training return: tensor(-118495.7188, device='cuda:0')
epoch: 88 test_true_pfm: 56.69563093343928
episode: 352 training return: tensor(-6882.6562, device='cuda:0')
episode: 353 training return: tensor(-1.6708e+11, device='cuda:0')
episode: 354 training return: tensor(-20447.0684, device='cuda:0')
episode: 355 training return: tensor(-4777.9556, device='cuda:0')
epoch: 89 test_true_pfm: -264.73518864618654
episode: 356 training return: tensor(-2.9643e+09, device='cuda:0')
episode: 357 training return: tensor(-5871.1567, device='cuda:0')
episode: 358 training return: tensor(-1.2921e+09, device='cuda:0')
episode: 359 training return: tensor(-3.2983e+09, device='cuda:0')
epoch: 90 test_true_pfm: 36.66107254265882
episode: 360 training return: tensor(-4.7969e+09, device='cuda:0')
episode: 361 training return: tensor(-6944.1313, device='cuda:0')
episode: 362 training return: tensor(-24454.9160, device='cuda:0')
episode: 363 training return: tensor(-4.7638e+09, device='cuda:0')
epoch: 91 test_true_pfm: -168.1266860896658
episode: 364 training return: tensor(-647898.0625, device='cuda:0')
episode: 365 training return: tensor(-5625.9053, device='cuda:0')
episode: 366 training return: tensor(-756882.0625, device='cuda:0')
episode: 367 training return: tensor(-6951.7861, device='cuda:0')
epoch: 92 test_true_pfm: 82.56670618922224
episode: 368 training return: tensor(-1023464.4375, device='cuda:0')
episode: 369 training return: tensor(-201782.4844, device='cuda:0')
episode: 370 training return: tensor(-5830.2627, device='cuda:0')
episode: 371 training return: tensor(-5937.0283, device='cuda:0')
epoch: 93 test_true_pfm: 85.00669702484028
episode: 372 training return: tensor(-4285.2466, device='cuda:0')
episode: 373 training return: tensor(-5075.3701, device='cuda:0')
episode: 374 training return: tensor(-5833.0044, device='cuda:0')
episode: 375 training return: tensor(-5117.7183, device='cuda:0')
epoch: 94 test_true_pfm: -33.52532910225075
episode: 376 training return: tensor(-59595.7070, device='cuda:0')
episode: 377 training return: tensor(-26628.9141, device='cuda:0')
episode: 378 training return: tensor(-2.8601e+09, device='cuda:0')
episode: 379 training return: tensor(-2.2357e+10, device='cuda:0')
epoch: 95 test_true_pfm: -80.903583853663
episode: 380 training return: tensor(-1250299.7500, device='cuda:0')
episode: 381 training return: tensor(-5.4799e+09, device='cuda:0')
episode: 382 training return: tensor(-2.0376e+11, device='cuda:0')
episode: 383 training return: tensor(-90543.6719, device='cuda:0')
epoch: 96 test_true_pfm: 6.250908845237237
episode: 384 training return: tensor(-1.8694e+09, device='cuda:0')
episode: 385 training return: tensor(-4599.1987, device='cuda:0')
episode: 386 training return: tensor(-5178.4941, device='cuda:0')
episode: 387 training return: tensor(-99356.9062, device='cuda:0')
epoch: 97 test_true_pfm: 133.62244694472744
episode: 388 training return: tensor(-20737.8203, device='cuda:0')
episode: 389 training return: tensor(-5135.2876, device='cuda:0')
episode: 390 training return: tensor(-59297.8203, device='cuda:0')
episode: 391 training return: tensor(-114530.5391, device='cuda:0')
epoch: 98 test_true_pfm: -42.09774954853583
episode: 392 training return: tensor(-1.2465e+12, device='cuda:0')
episode: 393 training return: tensor(-7604.4131, device='cuda:0')
episode: 394 training return: tensor(-6049.3203, device='cuda:0')
episode: 395 training return: tensor(-689108.3750, device='cuda:0')
epoch: 99 test_true_pfm: -126.02312173207595
episode: 396 training return: tensor(-1.8659e+09, device='cuda:0')
episode: 397 training return: tensor(-58563072., device='cuda:0')
episode: 398 training return: tensor(-4659.3687, device='cuda:0')
episode: 399 training return: tensor(-1830018.2500, device='cuda:0')
epoch: 100 test_true_pfm: -11.35513594640553
episode: 400 training return: tensor(-6.9448e+08, device='cuda:0')
episode: 401 training return: tensor(-5.1897e+08, device='cuda:0')
episode: 402 training return: tensor(-1.3994e+13, device='cuda:0')
episode: 403 training return: tensor(-5858.2495, device='cuda:0')
epoch: 101 test_true_pfm: 62.11883012499627
episode: 404 training return: tensor(-756547.2500, device='cuda:0')
episode: 405 training return: tensor(-6.9587e+10, device='cuda:0')
episode: 406 training return: tensor(-2.3645e+09, device='cuda:0')
episode: 407 training return: tensor(-4390.3560, device='cuda:0')
epoch: 102 test_true_pfm: -61.01223125936675
episode: 408 training return: tensor(-5536.4844, device='cuda:0')
episode: 409 training return: tensor(-131551.6562, device='cuda:0')
episode: 410 training return: tensor(-6.7603e+09, device='cuda:0')
episode: 411 training return: tensor(-3.1203e+10, device='cuda:0')
epoch: 103 test_true_pfm: 74.80160708823897
episode: 412 training return: tensor(-774403.3125, device='cuda:0')
episode: 413 training return: tensor(-4906.5527, device='cuda:0')
episode: 414 training return: tensor(-446742.3750, device='cuda:0')
episode: 415 training return: tensor(-4.0383e+09, device='cuda:0')
epoch: 104 test_true_pfm: -144.31246368541198
episode: 416 training return: tensor(-6.8833e+09, device='cuda:0')
episode: 417 training return: tensor(-160630.7031, device='cuda:0')
episode: 418 training return: tensor(-8246.8037, device='cuda:0')
episode: 419 training return: tensor(-1246140.2500, device='cuda:0')
epoch: 105 test_true_pfm: 156.79564778508885
episode: 420 training return: tensor(-151714.4062, device='cuda:0')
episode: 421 training return: tensor(-5735.0381, device='cuda:0')
episode: 422 training return: tensor(-2.0057e+09, device='cuda:0')
episode: 423 training return: tensor(-4884.2383, device='cuda:0')
epoch: 106 test_true_pfm: -24.143765150323443
episode: 424 training return: tensor(-7505.0669, device='cuda:0')
episode: 425 training return: tensor(-5271.4360, device='cuda:0')
episode: 426 training return: tensor(-10419.1445, device='cuda:0')
episode: 427 training return: tensor(-53226.5469, device='cuda:0')
epoch: 107 test_true_pfm: 107.75111179849874
episode: 428 training return: tensor(-2.2908e+10, device='cuda:0')
episode: 429 training return: tensor(-27561.7324, device='cuda:0')
episode: 430 training return: tensor(-5392.4385, device='cuda:0')
episode: 431 training return: tensor(-3.5136e+12, device='cuda:0')
epoch: 108 test_true_pfm: -67.48164371425948
episode: 432 training return: tensor(-1073012., device='cuda:0')
episode: 433 training return: tensor(-1.5922e+12, device='cuda:0')
episode: 434 training return: tensor(-6580.0039, device='cuda:0')
episode: 435 training return: tensor(-6911.4463, device='cuda:0')
epoch: 109 test_true_pfm: 3.9953886191915395
episode: 436 training return: tensor(-207444.4375, device='cuda:0')
episode: 437 training return: tensor(-5503.5947, device='cuda:0')
episode: 438 training return: tensor(-90934.4531, device='cuda:0')
episode: 439 training return: tensor(-3.4576e+09, device='cuda:0')
epoch: 110 test_true_pfm: -51.64123134374336
episode: 440 training return: tensor(-5180.5117, device='cuda:0')
episode: 441 training return: tensor(-1.3049e+11, device='cuda:0')
episode: 442 training return: tensor(-9.3143e+08, device='cuda:0')
episode: 443 training return: tensor(-4720.5879, device='cuda:0')
epoch: 111 test_true_pfm: -19.00704717076552
episode: 444 training return: tensor(-2.4620e+12, device='cuda:0')
episode: 445 training return: tensor(-877039.8750, device='cuda:0')
episode: 446 training return: tensor(-829222.3125, device='cuda:0')
episode: 447 training return: tensor(-5388.8750, device='cuda:0')
epoch: 112 test_true_pfm: -68.5826278120994
episode: 448 training return: tensor(-47708.4609, device='cuda:0')
episode: 449 training return: tensor(-209317., device='cuda:0')
episode: 450 training return: tensor(-2.1016e+10, device='cuda:0')
episode: 451 training return: tensor(-1.9742e+09, device='cuda:0')
epoch: 113 test_true_pfm: -114.34978493961624
episode: 452 training return: tensor(-6713.0308, device='cuda:0')
episode: 453 training return: tensor(-8548.5068, device='cuda:0')
episode: 454 training return: tensor(-6228.1768, device='cuda:0')
episode: 455 training return: tensor(-912099.9375, device='cuda:0')
epoch: 114 test_true_pfm: -110.39942989415077
episode: 456 training return: tensor(-611290.3125, device='cuda:0')
episode: 457 training return: tensor(-5819.4131, device='cuda:0')
episode: 458 training return: tensor(-5.9109e+08, device='cuda:0')
episode: 459 training return: tensor(-5018.1504, device='cuda:0')
epoch: 115 test_true_pfm: -22.149638910597872
episode: 460 training return: tensor(-1.7323e+12, device='cuda:0')
episode: 461 training return: tensor(-3.6033e+09, device='cuda:0')
episode: 462 training return: tensor(-4383.8657, device='cuda:0')
episode: 463 training return: tensor(-21060.0723, device='cuda:0')
epoch: 116 test_true_pfm: -158.22169996889005
episode: 464 training return: tensor(-3.1938e+10, device='cuda:0')
episode: 465 training return: tensor(-4.5366e+10, device='cuda:0')
episode: 466 training return: tensor(-2677344., device='cuda:0')
episode: 467 training return: tensor(-9.0168e+10, device='cuda:0')
epoch: 117 test_true_pfm: -49.079542574110384
episode: 468 training return: tensor(-4.4271e+09, device='cuda:0')
episode: 469 training return: tensor(-116256.4297, device='cuda:0')
episode: 470 training return: tensor(-12320.4434, device='cuda:0')
episode: 471 training return: tensor(-2.6384e+10, device='cuda:0')
epoch: 118 test_true_pfm: -93.07271477670537
episode: 472 training return: tensor(-2.3518e+09, device='cuda:0')
episode: 473 training return: tensor(-5.8014e+09, device='cuda:0')
episode: 474 training return: tensor(-5091.9473, device='cuda:0')
episode: 475 training return: tensor(-3.0844e+10, device='cuda:0')
epoch: 119 test_true_pfm: -127.87853782135795
episode: 476 training return: tensor(-3.2127e+09, device='cuda:0')
episode: 477 training return: tensor(-5738.4785, device='cuda:0')
episode: 478 training return: tensor(-5.6919e+11, device='cuda:0')
episode: 479 training return: tensor(-6099.4165, device='cuda:0')
epoch: 120 test_true_pfm: -71.0573523978353
episode: 480 training return: tensor(-6774.0649, device='cuda:0')
episode: 481 training return: tensor(-949924.5000, device='cuda:0')
episode: 482 training return: tensor(-6933.8198, device='cuda:0')
episode: 483 training return: tensor(-6321.8560, device='cuda:0')
epoch: 121 test_true_pfm: -53.71870585452624
episode: 484 training return: tensor(-11539.8105, device='cuda:0')
episode: 485 training return: tensor(-3.3161e+11, device='cuda:0')
episode: 486 training return: tensor(-126583.8516, device='cuda:0')
episode: 487 training return: tensor(-2.2779e+10, device='cuda:0')
epoch: 122 test_true_pfm: -39.20280279598953
episode: 488 training return: tensor(-5004.2109, device='cuda:0')
episode: 489 training return: tensor(-2.0350e+11, device='cuda:0')
episode: 490 training return: tensor(-21763.3867, device='cuda:0')
episode: 491 training return: tensor(-5096.8467, device='cuda:0')
epoch: 123 test_true_pfm: 4.6953465432441375
episode: 492 training return: tensor(-12641.4004, device='cuda:0')
episode: 493 training return: tensor(-4651.6353, device='cuda:0')
episode: 494 training return: tensor(-5.2785e+12, device='cuda:0')
episode: 495 training return: tensor(-87256.6250, device='cuda:0')
epoch: 124 test_true_pfm: -21.3503345554376
episode: 496 training return: tensor(-3.7751e+09, device='cuda:0')
episode: 497 training return: tensor(-35836.8008, device='cuda:0')
episode: 498 training return: tensor(-2315830.5000, device='cuda:0')
episode: 499 training return: tensor(-6172.3511, device='cuda:0')
epoch: 125 test_true_pfm: 59.885721924379055
episode: 500 training return: tensor(-2.3923e+16, device='cuda:0')
episode: 501 training return: tensor(-2.6389e+09, device='cuda:0')
episode: 502 training return: tensor(-1225633.5000, device='cuda:0')
episode: 503 training return: tensor(-4.9366e+10, device='cuda:0')
epoch: 126 test_true_pfm: -45.75597561503714
episode: 504 training return: tensor(-12401.9971, device='cuda:0')
episode: 505 training return: tensor(-4516.8271, device='cuda:0')
episode: 506 training return: tensor(-4302.7842, device='cuda:0')
episode: 507 training return: tensor(-6195.6309, device='cuda:0')
epoch: 127 test_true_pfm: -210.82725135253372
episode: 508 training return: tensor(-5.7215e+08, device='cuda:0')
episode: 509 training return: tensor(-4545.6660, device='cuda:0')
episode: 510 training return: tensor(-544018.8125, device='cuda:0')
episode: 511 training return: tensor(-1510526.8750, device='cuda:0')
epoch: 128 test_true_pfm: -66.25868983175008
episode: 512 training return: tensor(-694342.8125, device='cuda:0')
episode: 513 training return: tensor(-4856.8110, device='cuda:0')
episode: 514 training return: tensor(-18579.5449, device='cuda:0')
episode: 515 training return: tensor(-4778.3721, device='cuda:0')
epoch: 129 test_true_pfm: 53.255450883839764
episode: 516 training return: tensor(-1.7515e+09, device='cuda:0')
episode: 517 training return: tensor(-384636.5000, device='cuda:0')
episode: 518 training return: tensor(-11738.1328, device='cuda:0')
episode: 519 training return: tensor(-6.6041e+10, device='cuda:0')
epoch: 130 test_true_pfm: -47.772638482519675
episode: 520 training return: tensor(-670643.8750, device='cuda:0')
episode: 521 training return: tensor(-6151768., device='cuda:0')
episode: 522 training return: tensor(-63183.5977, device='cuda:0')
episode: 523 training return: tensor(-1.5993e+09, device='cuda:0')
epoch: 131 test_true_pfm: 72.96726448992497
episode: 524 training return: tensor(-6018.5156, device='cuda:0')
episode: 525 training return: tensor(-241556.5781, device='cuda:0')
episode: 526 training return: tensor(-357399.5000, device='cuda:0')
episode: 527 training return: tensor(-5170.7075, device='cuda:0')
epoch: 132 test_true_pfm: -67.29095166071578
episode: 528 training return: tensor(-4993.0498, device='cuda:0')
episode: 529 training return: tensor(-6293.0312, device='cuda:0')
episode: 530 training return: tensor(-1.4325e+09, device='cuda:0')
episode: 531 training return: tensor(-4.3714e+12, device='cuda:0')
epoch: 133 test_true_pfm: -35.880936967424844
episode: 532 training return: tensor(-3.1779e+12, device='cuda:0')
episode: 533 training return: tensor(-6310.4521, device='cuda:0')
episode: 534 training return: tensor(-5.0924e+08, device='cuda:0')
episode: 535 training return: tensor(-3.1584e+09, device='cuda:0')
epoch: 134 test_true_pfm: -84.82295980907396
episode: 536 training return: tensor(-549596., device='cuda:0')
episode: 537 training return: tensor(-1.3890e+12, device='cuda:0')
episode: 538 training return: tensor(-34064.9844, device='cuda:0')
episode: 539 training return: tensor(-603761.6250, device='cuda:0')
epoch: 135 test_true_pfm: -49.859501085537126
episode: 540 training return: tensor(-4521.0049, device='cuda:0')
episode: 541 training return: tensor(-3.8066e+09, device='cuda:0')
episode: 542 training return: tensor(-2.2660e+09, device='cuda:0')
episode: 543 training return: tensor(-3.5944e+11, device='cuda:0')
epoch: 136 test_true_pfm: -44.904137003019535
episode: 544 training return: tensor(-2554371.5000, device='cuda:0')
episode: 545 training return: tensor(-4827.3618, device='cuda:0')
episode: 546 training return: tensor(-8213.9443, device='cuda:0')
episode: 547 training return: tensor(-47825.5469, device='cuda:0')
epoch: 137 test_true_pfm: -11.628477621710426
episode: 548 training return: tensor(-8.8547e+11, device='cuda:0')
episode: 549 training return: tensor(-5741.0410, device='cuda:0')
episode: 550 training return: tensor(-9984887., device='cuda:0')
episode: 551 training return: tensor(-2.3092e+08, device='cuda:0')
epoch: 138 test_true_pfm: -35.16114214496896
episode: 552 training return: tensor(-136500., device='cuda:0')
episode: 553 training return: tensor(-2.1619e+10, device='cuda:0')
episode: 554 training return: tensor(-6209.2793, device='cuda:0')
episode: 555 training return: tensor(-5890.1758, device='cuda:0')
epoch: 139 test_true_pfm: -55.22815108491804
episode: 556 training return: tensor(-4586.9707, device='cuda:0')
episode: 557 training return: tensor(-7198.1421, device='cuda:0')
episode: 558 training return: tensor(-8.3814e+10, device='cuda:0')
episode: 559 training return: tensor(-7423.6235, device='cuda:0')
epoch: 140 test_true_pfm: 119.17823053838754
episode: 560 training return: tensor(-5130.8003, device='cuda:0')
episode: 561 training return: tensor(-2.9398e+10, device='cuda:0')
episode: 562 training return: tensor(-4749.6338, device='cuda:0')
episode: 563 training return: tensor(-960033.1250, device='cuda:0')
epoch: 141 test_true_pfm: -186.54977179935557
episode: 564 training return: tensor(-485143.1875, device='cuda:0')
episode: 565 training return: tensor(-2.4302e+09, device='cuda:0')
episode: 566 training return: tensor(-5702.5659, device='cuda:0')
episode: 567 training return: tensor(-59076.4766, device='cuda:0')
epoch: 142 test_true_pfm: -30.291283345469548
episode: 568 training return: tensor(-776869.8125, device='cuda:0')
episode: 569 training return: tensor(-2.1541e+10, device='cuda:0')
episode: 570 training return: tensor(-1.0282e+11, device='cuda:0')
episode: 571 training return: tensor(-41322.9336, device='cuda:0')
epoch: 143 test_true_pfm: 89.68630620555184
episode: 572 training return: tensor(-5.2639e+12, device='cuda:0')
episode: 573 training return: tensor(-6137.4961, device='cuda:0')
episode: 574 training return: tensor(-849162.3125, device='cuda:0')
episode: 575 training return: tensor(-3.4523e+09, device='cuda:0')
epoch: 144 test_true_pfm: -200.16924886814869
episode: 576 training return: tensor(-2.9301e+09, device='cuda:0')
episode: 577 training return: tensor(-702021.5000, device='cuda:0')
episode: 578 training return: tensor(-1.9634e+10, device='cuda:0')
episode: 579 training return: tensor(-272120.2500, device='cuda:0')
epoch: 145 test_true_pfm: 66.9481801710212
episode: 580 training return: tensor(-2.5369e+10, device='cuda:0')
episode: 581 training return: tensor(-5.1796e+12, device='cuda:0')
episode: 582 training return: tensor(-2.6439e+12, device='cuda:0')
episode: 583 training return: tensor(-185099.4688, device='cuda:0')
epoch: 146 test_true_pfm: -141.45126810342836
episode: 584 training return: tensor(-1331598.6250, device='cuda:0')
episode: 585 training return: tensor(-2.4108e+10, device='cuda:0')
episode: 586 training return: tensor(-56534496., device='cuda:0')
episode: 587 training return: tensor(-2.4680e+09, device='cuda:0')
epoch: 147 test_true_pfm: -237.98671576476872
episode: 588 training return: tensor(-5762.7700, device='cuda:0')
episode: 589 training return: tensor(-6785.5635, device='cuda:0')
episode: 590 training return: tensor(-1.8741e+09, device='cuda:0')
episode: 591 training return: tensor(-1328231.5000, device='cuda:0')
epoch: 148 test_true_pfm: 91.67367820012102
episode: 592 training return: tensor(-2.9998e+09, device='cuda:0')
episode: 593 training return: tensor(-9.6888e+08, device='cuda:0')
episode: 594 training return: tensor(-1.3320e+09, device='cuda:0')
episode: 595 training return: tensor(-1.7833e+09, device='cuda:0')
epoch: 149 test_true_pfm: -47.90015984898806
episode: 596 training return: tensor(-60395.0469, device='cuda:0')
episode: 597 training return: tensor(-478752.7500, device='cuda:0')
episode: 598 training return: tensor(-13569.1328, device='cuda:0')
episode: 599 training return: tensor(-518128.3750, device='cuda:0')
epoch: 150 test_true_pfm: 30.84338837934833
