['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'brac', '--traj', 'expert', '--seed', '4', '--data', '100000']
epoch: 0 training_loss 1.049102051369846 test_loss: -1.2088499069213867
epoch: 1 training_loss -1.7290216588974 test_loss: -2.620478630065918
epoch: 2 training_loss -3.287747688293457 test_loss: -3.8141494750976563
epoch: 3 training_loss -4.1686871004104615 test_loss: -4.49786491394043
epoch: 4 training_loss -4.749893717765808 test_loss: -4.932266616821289
epoch: 5 training_loss -5.176454687118531 test_loss: -5.345330429077149
epoch: 6 training_loss -5.481145710945129 test_loss: -5.476806259155273
epoch: 7 training_loss -5.620197291374207 test_loss: -5.670308685302734
epoch: 8 training_loss -5.85654926776886 test_loss: -5.837125396728515
epoch: 9 training_loss -5.996323094367981 test_loss: -6.0732982635498045
epoch: 10 training_loss -6.07812180519104 test_loss: -6.134186935424805
epoch: 11 training_loss -6.209431076049805 test_loss: -6.299811935424804
epoch: 12 training_loss -6.316848545074463 test_loss: -6.408945465087891
epoch: 13 training_loss -6.419012126922607 test_loss: -6.450202178955078
epoch: 14 training_loss -6.461297497749329 test_loss: -6.550630187988281
epoch: 15 training_loss -6.559496932029724 test_loss: -6.5655677795410154
epoch: 16 training_loss -6.5951583957672115 test_loss: -6.709004211425781
epoch: 17 training_loss -6.706414246559143 test_loss: -6.730052185058594
epoch: 18 training_loss -6.7231174039840695 test_loss: -6.652961730957031
epoch: 19 training_loss -6.776100111007691 test_loss: -6.811810302734375
epoch: 20 training_loss -6.853837661743164 test_loss: -6.867242431640625
epoch: 21 training_loss -6.900660862922669 test_loss: -6.913775634765625
epoch: 22 training_loss -6.904466557502746 test_loss: -7.031371307373047
epoch: 23 training_loss -6.923101172447205 test_loss: -7.037747192382812
epoch: 24 training_loss -6.986887202262879 test_loss: -7.040337371826172
epoch: 25 training_loss -7.039785103797913 test_loss: -7.038023376464844
epoch: 26 training_loss -7.041835265159607 test_loss: -7.161235809326172
epoch: 27 training_loss -7.120720491409302 test_loss: -7.063587188720703
epoch: 28 training_loss -7.134542956352234 test_loss: -7.109648132324219
epoch: 29 training_loss -7.19893639087677 test_loss: -7.186003112792969
epoch: 30 training_loss -7.209939522743225 test_loss: -7.208849334716797
epoch: 31 training_loss -7.205110468864441 test_loss: -7.1942497253417965
epoch: 32 training_loss -7.266145787239075 test_loss: -7.259833526611328
epoch: 33 training_loss -7.246195268630982 test_loss: -7.202548217773438
epoch: 34 training_loss -7.293319320678711 test_loss: -7.362667846679687
epoch: 35 training_loss -7.307365627288818 test_loss: -7.375888824462891
epoch: 36 training_loss -7.354471774101257 test_loss: -7.383250427246094
epoch: 37 training_loss -7.369123129844666 test_loss: -7.4139656066894535
epoch: 38 training_loss -7.356520237922669 test_loss: -7.411294555664062
epoch: 39 training_loss -7.432437891960144 test_loss: -7.3546875
epoch: 40 training_loss -7.413271408081055 test_loss: -7.4472801208496096
epoch: 41 training_loss -7.446451277732849 test_loss: -7.5160362243652346
epoch: 42 training_loss -7.461835165023803 test_loss: -7.462464904785156
epoch: 43 training_loss -7.4859135675430295 test_loss: -7.507208251953125
epoch: 44 training_loss -7.496116094589233 test_loss: -7.515486145019532
epoch: 45 training_loss -7.50457841873169 test_loss: -7.445868682861328
epoch: 46 training_loss -7.507241320610047 test_loss: -7.528469848632812
epoch: 47 training_loss -7.490900526046753 test_loss: -7.529690551757812
epoch: 48 training_loss -7.541254997253418 test_loss: -7.561644744873047
epoch: 49 training_loss -7.579979834556579 test_loss: -7.607551574707031
epoch: 50 training_loss -7.57308454990387 test_loss: -7.575736236572266
epoch: 51 training_loss -7.575092849731445 test_loss: -7.544956970214844
epoch: 52 training_loss -7.610262055397033 test_loss: -7.636599731445313
epoch: 53 training_loss -7.629540553092957 test_loss: -7.649331665039062
epoch: 54 training_loss -7.641347045898438 test_loss: -7.632755279541016
epoch: 55 training_loss -7.620215373039246 test_loss: -7.632249450683593
epoch: 56 training_loss -7.637256898880005 test_loss: -7.693568420410156
epoch: 57 training_loss -7.64461166381836 test_loss: -7.677893829345703
epoch: 58 training_loss -7.6626271677017215 test_loss: -7.576750946044922
epoch: 59 training_loss -7.642243051528931 test_loss: -7.702719116210938
epoch: 60 training_loss -7.650510578155518 test_loss: -7.709505462646485
epoch: 61 training_loss -7.739752912521363 test_loss: -7.675467681884766
epoch: 62 training_loss -7.694259514808655 test_loss: -7.7321022033691404
epoch: 63 training_loss -7.6807253503799435 test_loss: -7.753684234619141
epoch: 64 training_loss -7.75691514968872 test_loss: -7.816066741943359
epoch: 65 training_loss -7.768601894378662 test_loss: -7.800091552734375
epoch: 66 training_loss -7.7128632402420045 test_loss: -7.716085815429688
epoch: 67 training_loss -7.713918151855469 test_loss: -7.739707183837891
epoch: 68 training_loss -7.76255202293396 test_loss: -7.656073760986328
epoch: 69 training_loss -7.7440379619598385 test_loss: -7.822936248779297
epoch: 70 training_loss -7.779432110786438 test_loss: -7.813368225097657
epoch: 71 training_loss -7.768495502471924 test_loss: -7.712802886962891
epoch: 72 training_loss -7.794980449676514 test_loss: -7.695818328857422
epoch: 73 training_loss -7.823517327308655 test_loss: -7.762031555175781
epoch: 74 training_loss -7.808305053710938 test_loss: -7.818850708007813
epoch: 75 training_loss -7.788482780456543 test_loss: -7.836415100097656
epoch: 76 training_loss -7.842667002677917 test_loss: -7.868167877197266
epoch: 77 training_loss -7.815407619476319 test_loss: -7.86987075805664
epoch: 78 training_loss -7.857505850791931 test_loss: -7.871907806396484
epoch: 79 training_loss -7.815292954444885 test_loss: -7.830667114257812
epoch: 80 training_loss -7.87225163936615 test_loss: -7.867819213867188
epoch: 81 training_loss -7.867477498054504 test_loss: -7.8541709899902346
epoch: 82 training_loss -7.884248061180115 test_loss: -7.821428680419922
epoch: 83 training_loss -7.875080189704895 test_loss: -7.824739837646485
epoch: 84 training_loss -7.882608113288879 test_loss: -7.85711441040039
epoch: 85 training_loss -7.842664732933044 test_loss: -7.86417236328125
epoch: 86 training_loss -7.886624331474304 test_loss: -7.8056480407714846
epoch: 87 training_loss -7.911152853965759 test_loss: -7.893119812011719
epoch: 88 training_loss -7.914110798835754 test_loss: -7.948170471191406
epoch: 89 training_loss -7.92014326095581 test_loss: -7.905681610107422
epoch: 90 training_loss -7.9123928213119505 test_loss: -7.909239196777344
epoch: 91 training_loss -7.934709963798523 test_loss: -8.002041625976563
epoch: 92 training_loss -7.925087370872498 test_loss: -7.882669067382812
epoch: 93 training_loss -7.944712119102478 test_loss: -7.9413810729980465
epoch: 94 training_loss -7.931135005950928 test_loss: -7.944805145263672
epoch: 95 training_loss -7.957309994697571 test_loss: -8.000577545166015
epoch: 96 training_loss -7.9417195129394536 test_loss: -7.878387451171875
epoch: 97 training_loss -7.959239339828491 test_loss: -7.993119812011718
epoch: 98 training_loss -7.9795812892913816 test_loss: -8.019761657714843
epoch: 99 training_loss -7.957859444618225 test_loss: -7.991115570068359
epoch: 100 training_loss -7.976361584663391 test_loss: -7.9906669616699215
epoch: 101 training_loss -8.008983216285706 test_loss: -8.043733978271485
epoch: 102 training_loss -7.932640347480774 test_loss: -7.917705535888672
epoch: 103 training_loss -7.983472414016724 test_loss: -8.034546661376954
epoch: 104 training_loss -7.9863359022140505 test_loss: -7.990840911865234
epoch: 105 training_loss -7.952910203933715 test_loss: -8.029081726074219
epoch: 106 training_loss -8.029434900283814 test_loss: -7.967071533203125
epoch: 107 training_loss -8.012170448303223 test_loss: -8.003790283203125
epoch: 108 training_loss -7.9780161094665525 test_loss: -8.047489166259766
epoch: 109 training_loss -8.04374993801117 test_loss: -8.089376068115234
epoch: 110 training_loss -8.016201205253601 test_loss: -7.9717041015625
epoch: 111 training_loss -8.007073202133178 test_loss: -8.022240447998048
epoch: 112 training_loss -8.012350029945374 test_loss: -8.056917572021485
epoch: 113 training_loss -8.04458565711975 test_loss: -8.057719421386718
epoch: 114 training_loss -8.062955350875855 test_loss: -8.042582702636718
epoch: 115 training_loss -8.035880460739136 test_loss: -8.024986267089844
epoch: 116 training_loss -8.065947470664979 test_loss: -8.085476684570313
epoch: 117 training_loss -8.071433029174806 test_loss: -8.094070434570312
epoch: 118 training_loss -8.0819669008255 test_loss: -8.067112731933594
epoch: 119 training_loss -8.066766395568848 test_loss: -8.027790069580078
epoch: 120 training_loss -8.06858976840973 test_loss: -8.029875946044921
epoch: 121 training_loss -8.05536581516266 test_loss: -8.067273712158203
epoch: 122 training_loss -8.072255954742431 test_loss: -8.083003997802734
epoch: 123 training_loss -8.104796290397644 test_loss: -8.117501831054687
epoch: 124 training_loss -8.072850208282471 test_loss: -8.01660614013672
epoch: 125 training_loss -8.075864448547364 test_loss: -8.053013610839844
epoch: 126 training_loss -8.071077971458434 test_loss: -8.092499542236329
epoch: 127 training_loss -8.084536366462707 test_loss: -8.159957122802734
epoch: 128 training_loss -8.110731105804444 test_loss: -8.11973876953125
epoch: 129 training_loss -8.086772623062133 test_loss: -8.053646087646484
epoch: 130 training_loss -8.118659973144531 test_loss: -8.082665252685548
epoch: 131 training_loss -8.14584409236908 test_loss: -8.178212738037109
epoch: 132 training_loss -8.150201449394226 test_loss: -8.149884796142578
epoch: 133 training_loss -8.104092569351197 test_loss: -8.151557159423827
epoch: 134 training_loss -8.14504280090332 test_loss: -8.037251281738282
epoch: 135 training_loss -8.106143836975098 test_loss: -8.099431610107422
epoch: 136 training_loss -8.135510568618775 test_loss: -8.156732940673828
epoch: 137 training_loss -8.13557165145874 test_loss: -8.170609283447266
epoch: 138 training_loss -8.155271162986756 test_loss: -8.125601196289063
epoch: 139 training_loss -8.122793412208557 test_loss: -8.131584167480469
epoch: 140 training_loss -8.161834902763367 test_loss: -8.161071014404296
epoch: 141 training_loss -8.167049465179444 test_loss: -8.197630310058594
epoch: 142 training_loss -8.163633437156678 test_loss: -8.14049072265625
epoch: 143 training_loss -8.124479122161866 test_loss: -8.138311767578125
epoch: 144 training_loss -8.153483271598816 test_loss: -8.03427963256836
epoch: 145 training_loss -8.192522673606872 test_loss: -8.19957275390625
epoch: 146 training_loss -8.16300564289093 test_loss: -8.170247650146484
epoch: 147 training_loss -8.156411423683167 test_loss: -8.205739593505859
epoch: 148 training_loss -8.157382898330688 test_loss: -8.06447982788086
epoch: 149 training_loss -8.166721529960633 test_loss: -8.178807067871094
2974.2496809479962
episode: 0 training return: tensor(-1.5622e+16, device='cuda:0')
episode: 1 training return: tensor(-1.0990e+15, device='cuda:0')
episode: 2 training return: tensor(-5.6804e+14, device='cuda:0')
episode: 3 training return: tensor(-1.1979e+11, device='cuda:0')
epoch: 1 test_true_pfm: 44.97396510178455
episode: 4 training return: tensor(-5.2845e+08, device='cuda:0')
episode: 5 training return: tensor(-2.1133e+19, device='cuda:0')
episode: 6 training return: tensor(-7.4033e+09, device='cuda:0')
episode: 7 training return: tensor(-5.1722e+15, device='cuda:0')
epoch: 2 test_true_pfm: 44.53552426685252
episode: 8 training return: tensor(-2.3949e+19, device='cuda:0')
episode: 9 training return: tensor(-1.2911e+14, device='cuda:0')
episode: 10 training return: tensor(-3.4865e+19, device='cuda:0')
episode: 11 training return: tensor(-4.0508e+19, device='cuda:0')
epoch: 3 test_true_pfm: 44.74789791907557
episode: 12 training return: tensor(-4.0237e+19, device='cuda:0')
episode: 13 training return: tensor(-3.9559e+19, device='cuda:0')
episode: 14 training return: tensor(-3.9983e+19, device='cuda:0')
episode: 15 training return: tensor(-4.0180e+19, device='cuda:0')
epoch: 4 test_true_pfm: 45.19170359699376
episode: 16 training return: tensor(-3.9817e+19, device='cuda:0')
episode: 17 training return: tensor(-4.0439e+19, device='cuda:0')
episode: 18 training return: tensor(-4.2423e+19, device='cuda:0')
episode: 19 training return: tensor(-3.9920e+19, device='cuda:0')
epoch: 5 test_true_pfm: 44.83908319454909
episode: 20 training return: tensor(-4.0862e+19, device='cuda:0')
episode: 21 training return: tensor(-3.9548e+19, device='cuda:0')
episode: 22 training return: tensor(-4.0317e+19, device='cuda:0')
episode: 23 training return: tensor(-4.0979e+19, device='cuda:0')
epoch: 6 test_true_pfm: 44.512321887615485
episode: 24 training return: tensor(-3.9748e+19, device='cuda:0')
episode: 25 training return: tensor(-4.1954e+19, device='cuda:0')
episode: 26 training return: tensor(-4.2489e+19, device='cuda:0')
episode: 27 training return: tensor(-4.0168e+19, device='cuda:0')
epoch: 7 test_true_pfm: 43.99401302124037
episode: 28 training return: tensor(-4.0060e+19, device='cuda:0')
episode: 29 training return: tensor(-4.0014e+19, device='cuda:0')
episode: 30 training return: tensor(-4.0235e+19, device='cuda:0')
episode: 31 training return: tensor(-4.0125e+19, device='cuda:0')
epoch: 8 test_true_pfm: 44.931235495682415
episode: 32 training return: tensor(-3.9621e+19, device='cuda:0')
episode: 33 training return: tensor(-4.0071e+19, device='cuda:0')
episode: 34 training return: tensor(-3.9753e+19, device='cuda:0')
episode: 35 training return: tensor(-4.0286e+19, device='cuda:0')
epoch: 9 test_true_pfm: 45.655155151001274
episode: 36 training return: tensor(-4.0341e+19, device='cuda:0')
episode: 37 training return: tensor(-4.0496e+19, device='cuda:0')
episode: 38 training return: tensor(-3.9117e+19, device='cuda:0')
episode: 39 training return: tensor(-4.0272e+19, device='cuda:0')
epoch: 10 test_true_pfm: 46.281806267358654
episode: 40 training return: tensor(-3.9958e+19, device='cuda:0')
episode: 41 training return: tensor(-4.0111e+19, device='cuda:0')
episode: 42 training return: tensor(-3.9656e+19, device='cuda:0')
episode: 43 training return: tensor(-3.9541e+19, device='cuda:0')
epoch: 11 test_true_pfm: 47.13510472863379
episode: 44 training return: tensor(-4.1803e+19, device='cuda:0')
episode: 45 training return: tensor(-4.0511e+19, device='cuda:0')
episode: 46 training return: tensor(-4.1708e+19, device='cuda:0')
episode: 47 training return: tensor(-4.0531e+19, device='cuda:0')
epoch: 12 test_true_pfm: 46.376885407566
episode: 48 training return: tensor(-4.0700e+19, device='cuda:0')
episode: 49 training return: tensor(-3.9768e+19, device='cuda:0')
episode: 50 training return: tensor(-4.0528e+19, device='cuda:0')
episode: 51 training return: tensor(-4.0395e+19, device='cuda:0')
epoch: 13 test_true_pfm: 42.46906099169025
episode: 52 training return: tensor(-3.9661e+19, device='cuda:0')
episode: 53 training return: tensor(-4.0248e+19, device='cuda:0')
episode: 54 training return: tensor(-3.9646e+19, device='cuda:0')
episode: 55 training return: tensor(-3.8812e+19, device='cuda:0')
epoch: 14 test_true_pfm: 48.177345757201344
episode: 56 training return: tensor(-4.2340e+19, device='cuda:0')
episode: 57 training return: tensor(-3.9923e+19, device='cuda:0')
episode: 58 training return: tensor(-4.1731e+19, device='cuda:0')
episode: 59 training return: tensor(-4.0788e+19, device='cuda:0')
epoch: 15 test_true_pfm: 46.37966326479283
episode: 60 training return: tensor(-3.9693e+19, device='cuda:0')
episode: 61 training return: tensor(-3.9295e+19, device='cuda:0')
episode: 62 training return: tensor(-4.2357e+19, device='cuda:0')
episode: 63 training return: tensor(-4.0265e+19, device='cuda:0')
epoch: 16 test_true_pfm: 45.959158518158375
episode: 64 training return: tensor(-3.9481e+19, device='cuda:0')
episode: 65 training return: tensor(-3.9685e+19, device='cuda:0')
episode: 66 training return: tensor(-3.9654e+19, device='cuda:0')
episode: 67 training return: tensor(-3.9826e+19, device='cuda:0')
epoch: 17 test_true_pfm: 43.69845995308872
episode: 68 training return: tensor(-3.9824e+19, device='cuda:0')
episode: 69 training return: tensor(-3.9230e+19, device='cuda:0')
episode: 70 training return: tensor(-3.9787e+19, device='cuda:0')
episode: 71 training return: tensor(-3.9843e+19, device='cuda:0')
epoch: 18 test_true_pfm: 44.6829493471713
episode: 72 training return: tensor(-4.0580e+19, device='cuda:0')
episode: 73 training return: tensor(-4.0140e+19, device='cuda:0')
episode: 74 training return: tensor(-4.0477e+19, device='cuda:0')
episode: 75 training return: tensor(-3.9913e+19, device='cuda:0')
epoch: 19 test_true_pfm: 43.270849494184155
episode: 76 training return: tensor(-3.9847e+19, device='cuda:0')
episode: 77 training return: tensor(-3.9750e+19, device='cuda:0')
episode: 78 training return: tensor(-4.0426e+19, device='cuda:0')
episode: 79 training return: tensor(-3.9359e+19, device='cuda:0')
epoch: 20 test_true_pfm: 45.04306376858569
episode: 80 training return: tensor(-3.9608e+19, device='cuda:0')
episode: 81 training return: tensor(-3.8934e+19, device='cuda:0')
episode: 82 training return: tensor(-3.9873e+19, device='cuda:0')
episode: 83 training return: tensor(-3.9723e+19, device='cuda:0')
epoch: 21 test_true_pfm: 46.82742755134428
episode: 84 training return: tensor(-4.2901e+19, device='cuda:0')
episode: 85 training return: tensor(-4.0618e+19, device='cuda:0')
episode: 86 training return: tensor(-4.0317e+19, device='cuda:0')
episode: 87 training return: tensor(-4.0404e+19, device='cuda:0')
epoch: 22 test_true_pfm: 43.91979780595839
episode: 88 training return: tensor(-4.0451e+19, device='cuda:0')
episode: 89 training return: tensor(-4.1813e+19, device='cuda:0')
episode: 90 training return: tensor(-4.0437e+19, device='cuda:0')
episode: 91 training return: tensor(-3.9473e+19, device='cuda:0')
epoch: 23 test_true_pfm: 45.884168748253366
episode: 92 training return: tensor(-3.9880e+19, device='cuda:0')
episode: 93 training return: tensor(-4.0892e+19, device='cuda:0')
episode: 94 training return: tensor(-4.0269e+19, device='cuda:0')
episode: 95 training return: tensor(-3.9326e+19, device='cuda:0')
epoch: 24 test_true_pfm: 46.02987633501391
episode: 96 training return: tensor(-3.9459e+19, device='cuda:0')
episode: 97 training return: tensor(-3.9911e+19, device='cuda:0')
episode: 98 training return: tensor(-3.9263e+19, device='cuda:0')
episode: 99 training return: tensor(-3.9642e+19, device='cuda:0')
epoch: 25 test_true_pfm: 46.5436500998625
episode: 100 training return: tensor(-3.9237e+19, device='cuda:0')
episode: 101 training return: tensor(-3.9765e+19, device='cuda:0')
episode: 102 training return: tensor(-3.9638e+19, device='cuda:0')
episode: 103 training return: tensor(-3.9056e+19, device='cuda:0')
epoch: 26 test_true_pfm: 42.63148504886044
episode: 104 training return: tensor(-3.9175e+19, device='cuda:0')
episode: 105 training return: tensor(-4.0493e+19, device='cuda:0')
episode: 106 training return: tensor(-3.9680e+19, device='cuda:0')
episode: 107 training return: tensor(-3.9824e+19, device='cuda:0')
epoch: 27 test_true_pfm: 46.73455742755186
episode: 108 training return: tensor(-4.0433e+19, device='cuda:0')
episode: 109 training return: tensor(-4.2151e+19, device='cuda:0')
episode: 110 training return: tensor(-4.0723e+19, device='cuda:0')
episode: 111 training return: tensor(-3.9610e+19, device='cuda:0')
epoch: 28 test_true_pfm: 46.497103265996934
episode: 112 training return: tensor(-4.0371e+19, device='cuda:0')
episode: 113 training return: tensor(-4.0240e+19, device='cuda:0')
episode: 114 training return: tensor(-4.0171e+19, device='cuda:0')
episode: 115 training return: tensor(-4.0350e+19, device='cuda:0')
epoch: 29 test_true_pfm: 43.86280232549254
episode: 116 training return: tensor(-4.2001e+19, device='cuda:0')
episode: 117 training return: tensor(-3.9832e+19, device='cuda:0')
episode: 118 training return: tensor(-4.0534e+19, device='cuda:0')
episode: 119 training return: tensor(-4.0555e+19, device='cuda:0')
epoch: 30 test_true_pfm: 44.992250963918
episode: 120 training return: tensor(-3.9983e+19, device='cuda:0')
episode: 121 training return: tensor(-3.9163e+19, device='cuda:0')
episode: 122 training return: tensor(-3.9517e+19, device='cuda:0')
episode: 123 training return: tensor(-4.1756e+19, device='cuda:0')
epoch: 31 test_true_pfm: 44.71913852470849
episode: 124 training return: tensor(-3.8891e+19, device='cuda:0')
episode: 125 training return: tensor(-3.9721e+19, device='cuda:0')
episode: 126 training return: tensor(-3.9925e+19, device='cuda:0')
episode: 127 training return: tensor(-4.0006e+19, device='cuda:0')
epoch: 32 test_true_pfm: 45.32754971657575
episode: 128 training return: tensor(-3.9132e+19, device='cuda:0')
episode: 129 training return: tensor(-3.9543e+19, device='cuda:0')
episode: 130 training return: tensor(-4.0718e+19, device='cuda:0')
episode: 131 training return: tensor(-4.1967e+19, device='cuda:0')
epoch: 33 test_true_pfm: 45.11287722895501
episode: 132 training return: tensor(-3.8902e+19, device='cuda:0')
episode: 133 training return: tensor(-3.9294e+19, device='cuda:0')
episode: 134 training return: tensor(-4.0350e+19, device='cuda:0')
episode: 135 training return: tensor(-3.9528e+19, device='cuda:0')
epoch: 34 test_true_pfm: 45.74689317882336
episode: 136 training return: tensor(-3.9078e+19, device='cuda:0')
episode: 137 training return: tensor(-4.3154e+19, device='cuda:0')
episode: 138 training return: tensor(-4.0583e+19, device='cuda:0')
episode: 139 training return: tensor(-3.9859e+19, device='cuda:0')
epoch: 35 test_true_pfm: 44.25411270545319
episode: 140 training return: tensor(-4.1892e+19, device='cuda:0')
episode: 141 training return: tensor(-3.9199e+19, device='cuda:0')
episode: 142 training return: tensor(-3.9067e+19, device='cuda:0')
episode: 143 training return: tensor(-3.9863e+19, device='cuda:0')
epoch: 36 test_true_pfm: 45.435965567824816
episode: 144 training return: tensor(-4.0331e+19, device='cuda:0')
episode: 145 training return: tensor(-4.1225e+19, device='cuda:0')
episode: 146 training return: tensor(-4.0335e+19, device='cuda:0')
episode: 147 training return: tensor(-4.0054e+19, device='cuda:0')
epoch: 37 test_true_pfm: 44.98242917075095
episode: 148 training return: tensor(-3.9436e+19, device='cuda:0')
episode: 149 training return: tensor(-3.9583e+19, device='cuda:0')
episode: 150 training return: tensor(-3.9630e+19, device='cuda:0')
episode: 151 training return: tensor(-3.9594e+19, device='cuda:0')
epoch: 38 test_true_pfm: 45.05020592797067
episode: 152 training return: tensor(-3.9208e+19, device='cuda:0')
episode: 153 training return: tensor(-3.9077e+19, device='cuda:0')
episode: 154 training return: tensor(-4.0423e+19, device='cuda:0')
episode: 155 training return: tensor(-4.0140e+19, device='cuda:0')
epoch: 39 test_true_pfm: 47.61278734898321
episode: 156 training return: tensor(-4.0554e+19, device='cuda:0')
episode: 157 training return: tensor(-3.9434e+19, device='cuda:0')
episode: 158 training return: tensor(-3.9914e+19, device='cuda:0')
episode: 159 training return: tensor(-3.9535e+19, device='cuda:0')
epoch: 40 test_true_pfm: 45.955943247519805
episode: 160 training return: tensor(-4.0246e+19, device='cuda:0')
episode: 161 training return: tensor(-1.4052e+15, device='cuda:0')
episode: 162 training return: tensor(-4.0487e+19, device='cuda:0')
episode: 163 training return: tensor(-4.0305e+19, device='cuda:0')
epoch: 41 test_true_pfm: 44.88382448335661
episode: 164 training return: tensor(-3.9862e+19, device='cuda:0')
episode: 165 training return: tensor(-4.1319e+19, device='cuda:0')
episode: 166 training return: tensor(-4.0942e+19, device='cuda:0')
episode: 167 training return: tensor(-3.9501e+19, device='cuda:0')
epoch: 42 test_true_pfm: 46.62129240153778
episode: 168 training return: tensor(-4.0427e+19, device='cuda:0')
episode: 169 training return: tensor(-4.0595e+19, device='cuda:0')
episode: 170 training return: tensor(-3.9577e+19, device='cuda:0')
episode: 171 training return: tensor(-3.9588e+19, device='cuda:0')
epoch: 43 test_true_pfm: 46.25718809863904
episode: 172 training return: tensor(-4.0210e+19, device='cuda:0')
episode: 173 training return: tensor(-3.9575e+19, device='cuda:0')
episode: 174 training return: tensor(-4.0590e+19, device='cuda:0')
episode: 175 training return: tensor(-4.0983e+19, device='cuda:0')
epoch: 44 test_true_pfm: 69.71466589466911
episode: 176 training return: tensor(-4.7231e+19, device='cuda:0')
episode: 177 training return: tensor(-4.0532e+19, device='cuda:0')
episode: 178 training return: tensor(-3.9529e+19, device='cuda:0')
episode: 179 training return: tensor(-3.9581e+19, device='cuda:0')
epoch: 45 test_true_pfm: 45.942151379983464
episode: 180 training return: tensor(-3.9582e+19, device='cuda:0')
episode: 181 training return: tensor(-4.0161e+19, device='cuda:0')
episode: 182 training return: tensor(-3.3861e+19, device='cuda:0')
episode: 183 training return: tensor(-4.0294e+19, device='cuda:0')
epoch: 46 test_true_pfm: 45.372136780405675
episode: 184 training return: tensor(-3.9564e+19, device='cuda:0')
episode: 185 training return: tensor(-3.9803e+19, device='cuda:0')
episode: 186 training return: tensor(-4.0525e+19, device='cuda:0')
episode: 187 training return: tensor(-4.1228e+21, device='cuda:0')
epoch: 47 test_true_pfm: 45.88161639750127
episode: 188 training return: tensor(-4.0127e+19, device='cuda:0')
episode: 189 training return: tensor(-3.9343e+19, device='cuda:0')
episode: 190 training return: tensor(-3.9318e+19, device='cuda:0')
episode: 191 training return: tensor(-3.9645e+19, device='cuda:0')
epoch: 48 test_true_pfm: 46.99252733960383
episode: 192 training return: tensor(-4.0346e+19, device='cuda:0')
episode: 193 training return: tensor(-3.9237e+19, device='cuda:0')
episode: 194 training return: tensor(-4.0830e+19, device='cuda:0')
episode: 195 training return: tensor(-4.0594e+19, device='cuda:0')
epoch: 49 test_true_pfm: 47.63031873742042
episode: 196 training return: tensor(-4.0596e+19, device='cuda:0')
episode: 197 training return: tensor(-3.9794e+19, device='cuda:0')
episode: 198 training return: tensor(-3.9141e+19, device='cuda:0')
episode: 199 training return: tensor(-3.9736e+19, device='cuda:0')
epoch: 50 test_true_pfm: 46.128036351325655
episode: 200 training return: tensor(-4.1477e+19, device='cuda:0')
episode: 201 training return: tensor(-3.9545e+19, device='cuda:0')
episode: 202 training return: tensor(-3.9517e+19, device='cuda:0')
episode: 203 training return: tensor(-3.8982e+19, device='cuda:0')
epoch: 51 test_true_pfm: 46.232081203028436
episode: 204 training return: tensor(-4.0272e+19, device='cuda:0')
episode: 205 training return: tensor(-4.0108e+19, device='cuda:0')
episode: 206 training return: tensor(-3.9148e+19, device='cuda:0')
episode: 207 training return: tensor(-3.9418e+19, device='cuda:0')
epoch: 52 test_true_pfm: 46.357073173845656
episode: 208 training return: tensor(-3.9117e+19, device='cuda:0')
episode: 209 training return: tensor(-3.9351e+19, device='cuda:0')
episode: 210 training return: tensor(-3.9805e+19, device='cuda:0')
episode: 211 training return: tensor(-4.0171e+19, device='cuda:0')
epoch: 53 test_true_pfm: 44.95784766051355
episode: 212 training return: tensor(-4.0234e+19, device='cuda:0')
episode: 213 training return: tensor(-3.9332e+19, device='cuda:0')
episode: 214 training return: tensor(-4.0411e+19, device='cuda:0')
episode: 215 training return: tensor(-3.9464e+19, device='cuda:0')
epoch: 54 test_true_pfm: 44.86596981152797
episode: 216 training return: tensor(-4.0236e+19, device='cuda:0')
episode: 217 training return: tensor(-3.9852e+19, device='cuda:0')
episode: 218 training return: tensor(-3.9359e+19, device='cuda:0')
episode: 219 training return: tensor(-3.9381e+19, device='cuda:0')
epoch: 55 test_true_pfm: 46.73701408199522
episode: 220 training return: tensor(-4.0511e+19, device='cuda:0')
episode: 221 training return: tensor(-3.9964e+19, device='cuda:0')
episode: 222 training return: tensor(-3.9629e+19, device='cuda:0')
episode: 223 training return: tensor(-5.7154e+19, device='cuda:0')
epoch: 56 test_true_pfm: 43.98246859900939
episode: 224 training return: tensor(-3.8973e+19, device='cuda:0')
episode: 225 training return: tensor(-4.0527e+19, device='cuda:0')
episode: 226 training return: tensor(-3.9449e+19, device='cuda:0')
episode: 227 training return: tensor(-3.9815e+19, device='cuda:0')
epoch: 57 test_true_pfm: 45.74778999421636
episode: 228 training return: tensor(-4.0662e+19, device='cuda:0')
episode: 229 training return: tensor(-3.9416e+19, device='cuda:0')
episode: 230 training return: tensor(-4.0111e+19, device='cuda:0')
episode: 231 training return: tensor(-4.1701e+19, device='cuda:0')
epoch: 58 test_true_pfm: 47.62132660001104
episode: 232 training return: tensor(-4.0377e+19, device='cuda:0')
episode: 233 training return: tensor(-4.0055e+19, device='cuda:0')
episode: 234 training return: tensor(-4.0045e+19, device='cuda:0')
episode: 235 training return: tensor(-4.0303e+19, device='cuda:0')
epoch: 59 test_true_pfm: 44.83717735407663
episode: 236 training return: tensor(-3.9398e+19, device='cuda:0')
episode: 237 training return: tensor(-4.2357e+19, device='cuda:0')
episode: 238 training return: tensor(-3.9400e+19, device='cuda:0')
episode: 239 training return: tensor(-1.7932e+15, device='cuda:0')
epoch: 60 test_true_pfm: 44.741042281283036
episode: 240 training return: tensor(-4.0851e+19, device='cuda:0')
episode: 241 training return: tensor(-4.0078e+19, device='cuda:0')
episode: 242 training return: tensor(-4.7646e+19, device='cuda:0')
episode: 243 training return: tensor(-3.1635e+14, device='cuda:0')
epoch: 61 test_true_pfm: 46.15066791948451
episode: 244 training return: tensor(-3.8991e+19, device='cuda:0')
episode: 245 training return: tensor(-4.0649e+19, device='cuda:0')
episode: 246 training return: tensor(-4.0463e+19, device='cuda:0')
episode: 247 training return: tensor(-3.9653e+19, device='cuda:0')
epoch: 62 test_true_pfm: 44.849478567514865
episode: 248 training return: tensor(-4.0593e+19, device='cuda:0')
episode: 249 training return: tensor(-4.1341e+19, device='cuda:0')
episode: 250 training return: tensor(-4.0333e+19, device='cuda:0')
episode: 251 training return: tensor(-4.0824e+19, device='cuda:0')
epoch: 63 test_true_pfm: 43.18443672644221
episode: 252 training return: tensor(-4.1054e+19, device='cuda:0')
episode: 253 training return: tensor(-4.0111e+19, device='cuda:0')
episode: 254 training return: tensor(-4.0407e+19, device='cuda:0')
episode: 255 training return: tensor(-3.9794e+19, device='cuda:0')
epoch: 64 test_true_pfm: 45.64775567176914
episode: 256 training return: tensor(-4.0487e+19, device='cuda:0')
episode: 257 training return: tensor(-4.0077e+19, device='cuda:0')
episode: 258 training return: tensor(-3.9430e+19, device='cuda:0')
episode: 259 training return: tensor(-4.0082e+19, device='cuda:0')
epoch: 65 test_true_pfm: 44.23682398521728
episode: 260 training return: tensor(-3.8700e+19, device='cuda:0')
episode: 261 training return: tensor(-3.9881e+19, device='cuda:0')
episode: 262 training return: tensor(-3.9456e+19, device='cuda:0')
episode: 263 training return: tensor(-4.0044e+19, device='cuda:0')
epoch: 66 test_true_pfm: 6.770547774620019
episode: 264 training return: tensor(-4.2862e+19, device='cuda:0')
episode: 265 training return: tensor(-4.2572e+19, device='cuda:0')
episode: 266 training return: tensor(-6.8604e+19, device='cuda:0')
episode: 267 training return: tensor(-3.7801e+19, device='cuda:0')
epoch: 67 test_true_pfm: 43.218916390546326
episode: 268 training return: tensor(-4.0112e+19, device='cuda:0')
episode: 269 training return: tensor(-5.2985e+19, device='cuda:0')
episode: 270 training return: tensor(-4.0097e+19, device='cuda:0')
episode: 271 training return: tensor(-3.9860e+19, device='cuda:0')
epoch: 68 test_true_pfm: 46.00424512077591
episode: 272 training return: tensor(-4.0601e+19, device='cuda:0')
episode: 273 training return: tensor(-4.0000e+19, device='cuda:0')
episode: 274 training return: tensor(-4.0129e+19, device='cuda:0')
episode: 275 training return: tensor(-4.0296e+19, device='cuda:0')
epoch: 69 test_true_pfm: 43.766831562869335
episode: 276 training return: tensor(-3.9971e+19, device='cuda:0')
episode: 277 training return: tensor(-3.9690e+19, device='cuda:0')
episode: 278 training return: tensor(-3.9307e+19, device='cuda:0')
episode: 279 training return: tensor(-4.0183e+19, device='cuda:0')
epoch: 70 test_true_pfm: 43.23097191748718
episode: 280 training return: tensor(-3.9752e+19, device='cuda:0')
episode: 281 training return: tensor(-3.9399e+19, device='cuda:0')
episode: 282 training return: tensor(-4.1508e+19, device='cuda:0')
episode: 283 training return: tensor(-3.9200e+19, device='cuda:0')
epoch: 71 test_true_pfm: 42.53529846053087
episode: 284 training return: tensor(-4.1565e+19, device='cuda:0')
episode: 285 training return: tensor(-6.6776e+19, device='cuda:0')
episode: 286 training return: tensor(-4.0793e+19, device='cuda:0')
episode: 287 training return: tensor(-8.0734e+19, device='cuda:0')
epoch: 72 test_true_pfm: 47.878478544233396
episode: 288 training return: tensor(-3.8745e+19, device='cuda:0')
episode: 289 training return: tensor(-5.9685e+19, device='cuda:0')
episode: 290 training return: tensor(-3.9279e+19, device='cuda:0')
episode: 291 training return: tensor(-4.3125e+19, device='cuda:0')
epoch: 73 test_true_pfm: 44.739475843498575
episode: 292 training return: tensor(-3.9782e+19, device='cuda:0')
episode: 293 training return: tensor(-4.0287e+19, device='cuda:0')
episode: 294 training return: tensor(-4.0003e+19, device='cuda:0')
episode: 295 training return: tensor(-4.0369e+19, device='cuda:0')
epoch: 74 test_true_pfm: 43.73317400039104
episode: 296 training return: tensor(-3.9887e+19, device='cuda:0')
episode: 297 training return: tensor(-4.0079e+19, device='cuda:0')
episode: 298 training return: tensor(-3.9775e+19, device='cuda:0')
episode: 299 training return: tensor(-4.0239e+19, device='cuda:0')
epoch: 75 test_true_pfm: 44.50149824132828
episode: 300 training return: tensor(-3.9064e+19, device='cuda:0')
episode: 301 training return: tensor(-3.8779e+19, device='cuda:0')
episode: 302 training return: tensor(-4.1524e+19, device='cuda:0')
episode: 303 training return: tensor(-3.9346e+19, device='cuda:0')
epoch: 76 test_true_pfm: 45.15891886945348
episode: 304 training return: tensor(-3.9189e+19, device='cuda:0')
episode: 305 training return: tensor(-3.9590e+19, device='cuda:0')
episode: 306 training return: tensor(-4.0260e+19, device='cuda:0')
episode: 307 training return: tensor(-2.9434e+19, device='cuda:0')
epoch: 77 test_true_pfm: -47.87048666995008
episode: 308 training return: tensor(-3.9249e+19, device='cuda:0')
episode: 309 training return: tensor(-3.9885e+19, device='cuda:0')
episode: 310 training return: tensor(-3.3784e+19, device='cuda:0')
episode: 311 training return: tensor(-3.9396e+14, device='cuda:0')
epoch: 78 test_true_pfm: 45.088713609158646
episode: 312 training return: tensor(-4.1276e+19, device='cuda:0')
episode: 313 training return: tensor(-4.1416e+19, device='cuda:0')
episode: 314 training return: tensor(-5.0432e+19, device='cuda:0')
episode: 315 training return: tensor(-2.3231e+19, device='cuda:0')
epoch: 79 test_true_pfm: 18.550800439845602
episode: 316 training return: tensor(-3.3397e+19, device='cuda:0')
episode: 317 training return: tensor(-4.0304e+19, device='cuda:0')
episode: 318 training return: tensor(-4.2379e+19, device='cuda:0')
episode: 319 training return: tensor(-3.9041e+19, device='cuda:0')
epoch: 80 test_true_pfm: 42.69719188400767
episode: 320 training return: tensor(-3.9777e+19, device='cuda:0')
episode: 321 training return: tensor(-3.9118e+19, device='cuda:0')
episode: 322 training return: tensor(-4.0208e+19, device='cuda:0')
episode: 323 training return: tensor(-4.2248e+19, device='cuda:0')
epoch: 81 test_true_pfm: 45.6726451578611
episode: 324 training return: tensor(-4.0848e+19, device='cuda:0')
episode: 325 training return: tensor(-3.9674e+19, device='cuda:0')
episode: 326 training return: tensor(-4.2456e+19, device='cuda:0')
episode: 327 training return: tensor(-3.9593e+19, device='cuda:0')
epoch: 82 test_true_pfm: 61.93581352849472
episode: 328 training return: tensor(-4.2888e+19, device='cuda:0')
episode: 329 training return: tensor(-4.2430e+19, device='cuda:0')
episode: 330 training return: tensor(-4.0804e+19, device='cuda:0')
episode: 331 training return: tensor(-3.8818e+19, device='cuda:0')
epoch: 83 test_true_pfm: 50.55379391147351
episode: 332 training return: tensor(-8.5506e+19, device='cuda:0')
episode: 333 training return: tensor(-3.2173e+14, device='cuda:0')
episode: 334 training return: tensor(-4.0459e+19, device='cuda:0')
episode: 335 training return: tensor(-4.0205e+19, device='cuda:0')
epoch: 84 test_true_pfm: 44.8110057628943
episode: 336 training return: tensor(-3.9825e+19, device='cuda:0')
episode: 337 training return: tensor(-3.9359e+19, device='cuda:0')
episode: 338 training return: tensor(-3.9545e+19, device='cuda:0')
episode: 339 training return: tensor(-4.2296e+19, device='cuda:0')
epoch: 85 test_true_pfm: 118.83715624421427
episode: 340 training return: tensor(-5.2672e+19, device='cuda:0')
episode: 341 training return: tensor(-4.0638e+19, device='cuda:0')
episode: 342 training return: tensor(-2.8231e+19, device='cuda:0')
episode: 343 training return: tensor(-4.1353e+19, device='cuda:0')
epoch: 86 test_true_pfm: 83.64215182581854
episode: 344 training return: tensor(-5.4302e+19, device='cuda:0')
episode: 345 training return: tensor(-6.1557e+19, device='cuda:0')
episode: 346 training return: tensor(-3.9668e+19, device='cuda:0')
episode: 347 training return: tensor(-4.0368e+19, device='cuda:0')
epoch: 87 test_true_pfm: 45.856655389586
episode: 348 training return: tensor(-4.0353e+19, device='cuda:0')
episode: 349 training return: tensor(-4.0375e+19, device='cuda:0')
episode: 350 training return: tensor(-4.0560e+19, device='cuda:0')
episode: 351 training return: tensor(-3.8948e+19, device='cuda:0')
epoch: 88 test_true_pfm: 45.51068488929986
episode: 352 training return: tensor(-3.9590e+19, device='cuda:0')
episode: 353 training return: tensor(-3.9937e+19, device='cuda:0')
episode: 354 training return: tensor(-3.9945e+19, device='cuda:0')
episode: 355 training return: tensor(-5.7907e+19, device='cuda:0')
epoch: 89 test_true_pfm: 44.88104624221103
episode: 356 training return: tensor(-4.2824e+19, device='cuda:0')
episode: 357 training return: tensor(-3.9725e+19, device='cuda:0')
episode: 358 training return: tensor(-4.0542e+19, device='cuda:0')
episode: 359 training return: tensor(-4.0758e+19, device='cuda:0')
epoch: 90 test_true_pfm: 46.42134611760368
episode: 360 training return: tensor(-3.9938e+19, device='cuda:0')
episode: 361 training return: tensor(-4.0951e+19, device='cuda:0')
episode: 362 training return: tensor(-3.9887e+19, device='cuda:0')
episode: 363 training return: tensor(-3.9029e+19, device='cuda:0')
epoch: 91 test_true_pfm: 43.89224275424875
episode: 364 training return: tensor(-3.9885e+19, device='cuda:0')
episode: 365 training return: tensor(-3.9507e+19, device='cuda:0')
episode: 366 training return: tensor(-4.0493e+19, device='cuda:0')
episode: 367 training return: tensor(-3.0137e+14, device='cuda:0')
epoch: 92 test_true_pfm: 19.873558493065396
episode: 368 training return: tensor(-3.3689e+19, device='cuda:0')
episode: 369 training return: tensor(-3.4010e+19, device='cuda:0')
episode: 370 training return: tensor(-3.3744e+19, device='cuda:0')
episode: 371 training return: tensor(-3.3363e+19, device='cuda:0')
epoch: 93 test_true_pfm: 19.3617544118654
episode: 372 training return: tensor(-3.3214e+19, device='cuda:0')
episode: 373 training return: tensor(-3.3696e+19, device='cuda:0')
episode: 374 training return: tensor(-3.3654e+19, device='cuda:0')
episode: 375 training return: tensor(-3.3100e+19, device='cuda:0')
epoch: 94 test_true_pfm: 61.51675717493659
episode: 376 training return: tensor(-3.0251e+19, device='cuda:0')
episode: 377 training return: tensor(-3.9902e+19, device='cuda:0')
episode: 378 training return: tensor(-4.0610e+19, device='cuda:0')
episode: 379 training return: tensor(-4.0642e+19, device='cuda:0')
epoch: 95 test_true_pfm: 49.28781007786264
episode: 380 training return: tensor(-3.8837e+19, device='cuda:0')
episode: 381 training return: tensor(-1.2242e+16, device='cuda:0')
episode: 382 training return: tensor(-2.2168e+19, device='cuda:0')
episode: 383 training return: tensor(-4.0308e+19, device='cuda:0')
epoch: 96 test_true_pfm: 43.96272437783339
episode: 384 training return: tensor(-4.0174e+19, device='cuda:0')
episode: 385 training return: tensor(-4.0071e+19, device='cuda:0')
episode: 386 training return: tensor(-3.0144e+19, device='cuda:0')
episode: 387 training return: tensor(-3.9501e+19, device='cuda:0')
epoch: 97 test_true_pfm: 19.992537608468513
episode: 388 training return: tensor(-3.3549e+19, device='cuda:0')
episode: 389 training return: tensor(-3.8771e+19, device='cuda:0')
episode: 390 training return: tensor(-3.9583e+19, device='cuda:0')
episode: 391 training return: tensor(-3.4933e+19, device='cuda:0')
epoch: 98 test_true_pfm: 47.88623944138328
episode: 392 training return: tensor(-5.9384e+19, device='cuda:0')
episode: 393 training return: tensor(-5.8597e+19, device='cuda:0')
episode: 394 training return: tensor(-3.9299e+19, device='cuda:0')
episode: 395 training return: tensor(-4.0392e+19, device='cuda:0')
epoch: 99 test_true_pfm: 44.598154765840036
episode: 396 training return: tensor(-4.0312e+19, device='cuda:0')
episode: 397 training return: tensor(-4.0993e+19, device='cuda:0')
episode: 398 training return: tensor(-4.3323e+19, device='cuda:0')
episode: 399 training return: tensor(-4.2088e+19, device='cuda:0')
epoch: 100 test_true_pfm: 46.459807219219435
episode: 400 training return: tensor(-4.0166e+19, device='cuda:0')
episode: 401 training return: tensor(-3.9895e+19, device='cuda:0')
episode: 402 training return: tensor(-4.0500e+19, device='cuda:0')
episode: 403 training return: tensor(-3.9305e+19, device='cuda:0')
epoch: 101 test_true_pfm: 84.63780970441324
episode: 404 training return: tensor(-4.0401e+19, device='cuda:0')
episode: 405 training return: tensor(-4.0082e+19, device='cuda:0')
episode: 406 training return: tensor(-4.0665e+19, device='cuda:0')
episode: 407 training return: tensor(-4.0379e+19, device='cuda:0')
epoch: 102 test_true_pfm: 20.014410941556363
episode: 408 training return: tensor(-3.3790e+19, device='cuda:0')
episode: 409 training return: tensor(-3.8765e+19, device='cuda:0')
episode: 410 training return: tensor(-4.2181e+19, device='cuda:0')
episode: 411 training return: tensor(-2.5030e+19, device='cuda:0')
epoch: 103 test_true_pfm: 42.992693349972164
episode: 412 training return: tensor(-4.1616e+19, device='cuda:0')
episode: 413 training return: tensor(-4.0022e+19, device='cuda:0')
episode: 414 training return: tensor(-3.9350e+19, device='cuda:0')
episode: 415 training return: tensor(-4.1289e+19, device='cuda:0')
epoch: 104 test_true_pfm: 45.069906825398085
episode: 416 training return: tensor(-3.9910e+19, device='cuda:0')
episode: 417 training return: tensor(-4.0648e+19, device='cuda:0')
episode: 418 training return: tensor(-3.9316e+19, device='cuda:0')
episode: 419 training return: tensor(-4.0816e+19, device='cuda:0')
epoch: 105 test_true_pfm: 44.35490077536499
episode: 420 training return: tensor(-1.8549e+19, device='cuda:0')
episode: 421 training return: tensor(-3.9608e+19, device='cuda:0')
episode: 422 training return: tensor(-3.9791e+19, device='cuda:0')
episode: 423 training return: tensor(-4.0642e+19, device='cuda:0')
epoch: 106 test_true_pfm: 46.81075016481342
episode: 424 training return: tensor(-3.9418e+19, device='cuda:0')
episode: 425 training return: tensor(-3.9571e+19, device='cuda:0')
episode: 426 training return: tensor(-3.9389e+19, device='cuda:0')
episode: 427 training return: tensor(-3.9570e+19, device='cuda:0')
epoch: 107 test_true_pfm: 44.36630930532931
episode: 428 training return: tensor(-4.0691e+19, device='cuda:0')
episode: 429 training return: tensor(-3.8918e+19, device='cuda:0')
episode: 430 training return: tensor(-4.0206e+19, device='cuda:0')
episode: 431 training return: tensor(-3.9883e+19, device='cuda:0')
epoch: 108 test_true_pfm: 44.760995990004574
episode: 432 training return: tensor(-3.9646e+19, device='cuda:0')
episode: 433 training return: tensor(-4.0217e+19, device='cuda:0')
episode: 434 training return: tensor(-4.0185e+19, device='cuda:0')
episode: 435 training return: tensor(-3.8096e+19, device='cuda:0')
epoch: 109 test_true_pfm: 38.3064266704231
episode: 436 training return: tensor(-3.8628e+19, device='cuda:0')
episode: 437 training return: tensor(-3.8167e+19, device='cuda:0')
episode: 438 training return: tensor(-3.9460e+19, device='cuda:0')
episode: 439 training return: tensor(-4.0080e+19, device='cuda:0')
epoch: 110 test_true_pfm: 45.69443461383795
episode: 440 training return: tensor(-3.8893e+19, device='cuda:0')
episode: 441 training return: tensor(-4.2197e+19, device='cuda:0')
episode: 442 training return: tensor(-3.9688e+19, device='cuda:0')
episode: 443 training return: tensor(-3.8999e+19, device='cuda:0')
epoch: 111 test_true_pfm: 47.11974505990142
episode: 444 training return: tensor(-3.9775e+19, device='cuda:0')
episode: 445 training return: tensor(-5.3373e+19, device='cuda:0')
episode: 446 training return: tensor(-3.3282e+19, device='cuda:0')
episode: 447 training return: tensor(-5.7455e+19, device='cuda:0')
epoch: 112 test_true_pfm: 47.19204812351969
episode: 448 training return: tensor(-3.9953e+19, device='cuda:0')
episode: 449 training return: tensor(-4.0029e+19, device='cuda:0')
episode: 450 training return: tensor(-4.1125e+19, device='cuda:0')
episode: 451 training return: tensor(-4.0247e+19, device='cuda:0')
epoch: 113 test_true_pfm: 46.41054557876013
episode: 452 training return: tensor(-3.8630e+19, device='cuda:0')
episode: 453 training return: tensor(-4.0457e+19, device='cuda:0')
episode: 454 training return: tensor(-4.1253e+19, device='cuda:0')
episode: 455 training return: tensor(-4.0492e+19, device='cuda:0')
epoch: 114 test_true_pfm: 45.93988208090735
episode: 456 training return: tensor(-4.0500e+19, device='cuda:0')
episode: 457 training return: tensor(-3.9671e+19, device='cuda:0')
episode: 458 training return: tensor(-3.9894e+19, device='cuda:0')
episode: 459 training return: tensor(-4.8219e+19, device='cuda:0')
epoch: 115 test_true_pfm: 46.523484157493975
episode: 460 training return: tensor(-4.0678e+19, device='cuda:0')
episode: 461 training return: tensor(-3.9637e+19, device='cuda:0')
episode: 462 training return: tensor(-4.1822e+19, device='cuda:0')
episode: 463 training return: tensor(-3.9494e+19, device='cuda:0')
epoch: 116 test_true_pfm: -70.28098156578008
episode: 464 training return: tensor(-2.1944e+19, device='cuda:0')
episode: 465 training return: tensor(-2.6844e+19, device='cuda:0')
episode: 466 training return: tensor(-1.2822e+19, device='cuda:0')
episode: 467 training return: tensor(-3.9191e+19, device='cuda:0')
epoch: 117 test_true_pfm: -5.440251981771361
episode: 468 training return: tensor(-3.0205e+14, device='cuda:0')
episode: 469 training return: tensor(-4.0752e+19, device='cuda:0')
episode: 470 training return: tensor(-4.0861e+19, device='cuda:0')
episode: 471 training return: tensor(-3.9355e+19, device='cuda:0')
epoch: 118 test_true_pfm: 83.02486692342907
episode: 472 training return: tensor(-7.1731e+19, device='cuda:0')
episode: 473 training return: tensor(-4.0003e+19, device='cuda:0')
episode: 474 training return: tensor(-3.9487e+19, device='cuda:0')
episode: 475 training return: tensor(-4.0292e+19, device='cuda:0')
epoch: 119 test_true_pfm: 43.56685346562188
episode: 476 training return: tensor(-3.8984e+19, device='cuda:0')
episode: 477 training return: tensor(-3.9436e+19, device='cuda:0')
episode: 478 training return: tensor(-4.0783e+19, device='cuda:0')
episode: 479 training return: tensor(-4.2134e+19, device='cuda:0')
epoch: 120 test_true_pfm: 36.09757753451677
episode: 480 training return: tensor(-3.3084e+19, device='cuda:0')
episode: 481 training return: tensor(-4.0959e+19, device='cuda:0')
episode: 482 training return: tensor(-4.0617e+19, device='cuda:0')
episode: 483 training return: tensor(-3.8952e+19, device='cuda:0')
epoch: 121 test_true_pfm: 44.35423659788365
episode: 484 training return: tensor(-4.0373e+19, device='cuda:0')
episode: 485 training return: tensor(-3.9307e+19, device='cuda:0')
episode: 486 training return: tensor(-4.0222e+19, device='cuda:0')
episode: 487 training return: tensor(-4.0457e+19, device='cuda:0')
epoch: 122 test_true_pfm: 47.344811845908
episode: 488 training return: tensor(-5.7260e+19, device='cuda:0')
episode: 489 training return: tensor(-4.0165e+19, device='cuda:0')
episode: 490 training return: tensor(-6.1228e+18, device='cuda:0')
episode: 491 training return: tensor(-3.9499e+19, device='cuda:0')
epoch: 123 test_true_pfm: 42.79523065410979
episode: 492 training return: tensor(-4.1210e+19, device='cuda:0')
episode: 493 training return: tensor(-2.7643e+15, device='cuda:0')
episode: 494 training return: tensor(-8.1948e+19, device='cuda:0')
episode: 495 training return: tensor(-3.1948e+19, device='cuda:0')
epoch: 124 test_true_pfm: 45.446493218142145
episode: 496 training return: tensor(-3.8869e+19, device='cuda:0')
episode: 497 training return: tensor(-3.9277e+19, device='cuda:0')
episode: 498 training return: tensor(-3.9995e+19, device='cuda:0')
episode: 499 training return: tensor(-3.9907e+19, device='cuda:0')
epoch: 125 test_true_pfm: 46.886484869604686
episode: 500 training return: tensor(-4.2310e+19, device='cuda:0')
episode: 501 training return: tensor(-3.9498e+19, device='cuda:0')
episode: 502 training return: tensor(-4.1095e+19, device='cuda:0')
episode: 503 training return: tensor(-1.8159e+19, device='cuda:0')
epoch: 126 test_true_pfm: 91.06196715152278
episode: 504 training return: tensor(-2.9042e+19, device='cuda:0')
episode: 505 training return: tensor(-3.9413e+19, device='cuda:0')
episode: 506 training return: tensor(-4.0394e+19, device='cuda:0')
episode: 507 training return: tensor(-3.9991e+19, device='cuda:0')
epoch: 127 test_true_pfm: 44.783303751545645
episode: 508 training return: tensor(-4.0583e+19, device='cuda:0')
episode: 509 training return: tensor(-4.0061e+19, device='cuda:0')
episode: 510 training return: tensor(-4.0384e+19, device='cuda:0')
episode: 511 training return: tensor(-4.0161e+19, device='cuda:0')
epoch: 128 test_true_pfm: 45.31542662873682
episode: 512 training return: tensor(-3.8734e+19, device='cuda:0')
episode: 513 training return: tensor(-6.1603e+15, device='cuda:0')
episode: 514 training return: tensor(-4.1063e+19, device='cuda:0')
episode: 515 training return: tensor(-4.0455e+19, device='cuda:0')
epoch: 129 test_true_pfm: 37.63046656020499
episode: 516 training return: tensor(-4.1479e+19, device='cuda:0')
episode: 517 training return: tensor(-3.9815e+19, device='cuda:0')
episode: 518 training return: tensor(-4.0531e+19, device='cuda:0')
episode: 519 training return: tensor(-4.0084e+19, device='cuda:0')
epoch: 130 test_true_pfm: 45.31932671875945
episode: 520 training return: tensor(-7.3807e+19, device='cuda:0')
episode: 521 training return: tensor(-3.9274e+19, device='cuda:0')
episode: 522 training return: tensor(-4.0062e+19, device='cuda:0')
episode: 523 training return: tensor(-3.9494e+19, device='cuda:0')
epoch: 131 test_true_pfm: 45.418826845774866
episode: 524 training return: tensor(-4.0609e+19, device='cuda:0')
episode: 525 training return: tensor(-4.1372e+19, device='cuda:0')
episode: 526 training return: tensor(-4.2170e+19, device='cuda:0')
episode: 527 training return: tensor(-6.7777e+19, device='cuda:0')
epoch: 132 test_true_pfm: 45.34048038859703
episode: 528 training return: tensor(-3.9779e+19, device='cuda:0')
episode: 529 training return: tensor(-8.1876e+19, device='cuda:0')
episode: 530 training return: tensor(-3.7811e+19, device='cuda:0')
episode: 531 training return: tensor(-3.0979e+19, device='cuda:0')
epoch: 133 test_true_pfm: 48.15684295973461
episode: 532 training return: tensor(-3.9555e+19, device='cuda:0')
episode: 533 training return: tensor(-3.9231e+19, device='cuda:0')
episode: 534 training return: tensor(-1.1037e+20, device='cuda:0')
episode: 535 training return: tensor(-4.6419e+19, device='cuda:0')
epoch: 134 test_true_pfm: 46.70931226433498
episode: 536 training return: tensor(-3.9411e+19, device='cuda:0')
episode: 537 training return: tensor(-3.9199e+19, device='cuda:0')
episode: 538 training return: tensor(-3.9253e+19, device='cuda:0')
episode: 539 training return: tensor(-3.9400e+19, device='cuda:0')
epoch: 135 test_true_pfm: 45.664027851883844
episode: 540 training return: tensor(-4.0796e+19, device='cuda:0')
episode: 541 training return: tensor(-3.9665e+19, device='cuda:0')
episode: 542 training return: tensor(-4.2231e+19, device='cuda:0')
episode: 543 training return: tensor(-3.9713e+19, device='cuda:0')
epoch: 136 test_true_pfm: 15.743461133439764
episode: 544 training return: tensor(-4.1319e+19, device='cuda:0')
episode: 545 training return: tensor(-4.0381e+19, device='cuda:0')
episode: 546 training return: tensor(-3.9244e+19, device='cuda:0')
episode: 547 training return: tensor(-4.0511e+19, device='cuda:0')
epoch: 137 test_true_pfm: 46.045718296571174
episode: 548 training return: tensor(-4.0322e+19, device='cuda:0')
episode: 549 training return: tensor(-3.9838e+19, device='cuda:0')
episode: 550 training return: tensor(-3.9522e+19, device='cuda:0')
episode: 551 training return: tensor(-4.0124e+19, device='cuda:0')
epoch: 138 test_true_pfm: 44.611313844335136
episode: 552 training return: tensor(-4.0458e+19, device='cuda:0')
episode: 553 training return: tensor(-4.2932e+19, device='cuda:0')
episode: 554 training return: tensor(-4.0314e+19, device='cuda:0')
episode: 555 training return: tensor(-4.6385e+19, device='cuda:0')
epoch: 139 test_true_pfm: 46.167358369565534
episode: 556 training return: tensor(-5.6828e+19, device='cuda:0')
episode: 557 training return: tensor(-5.6726e+19, device='cuda:0')
episode: 558 training return: tensor(-7.8412e+19, device='cuda:0')
episode: 559 training return: tensor(-4.5477e+19, device='cuda:0')
epoch: 140 test_true_pfm: 80.41531551183101
episode: 560 training return: tensor(-3.8398e+19, device='cuda:0')
episode: 561 training return: tensor(-2.6772e+19, device='cuda:0')
episode: 562 training return: tensor(-5.1412e+19, device='cuda:0')
episode: 563 training return: tensor(-3.6259e+19, device='cuda:0')
epoch: 141 test_true_pfm: 72.01590533568161
episode: 564 training return: tensor(-3.2230e+19, device='cuda:0')
episode: 565 training return: tensor(-4.1192e+19, device='cuda:0')
episode: 566 training return: tensor(-3.4776e+19, device='cuda:0')
episode: 567 training return: tensor(-2.3848e+19, device='cuda:0')
epoch: 142 test_true_pfm: 44.75870712497181
episode: 568 training return: tensor(-3.8810e+19, device='cuda:0')
episode: 569 training return: tensor(-3.9232e+19, device='cuda:0')
episode: 570 training return: tensor(-3.9918e+19, device='cuda:0')
episode: 571 training return: tensor(-4.2846e+19, device='cuda:0')
epoch: 143 test_true_pfm: 45.794617619547914
episode: 572 training return: tensor(-4.0163e+19, device='cuda:0')
episode: 573 training return: tensor(-4.0885e+19, device='cuda:0')
episode: 574 training return: tensor(-3.9755e+19, device='cuda:0')
episode: 575 training return: tensor(-4.8375e+19, device='cuda:0')
epoch: 144 test_true_pfm: 46.34545431023489
episode: 576 training return: tensor(-4.0013e+19, device='cuda:0')
episode: 577 training return: tensor(-3.9403e+19, device='cuda:0')
episode: 578 training return: tensor(-3.3590e+19, device='cuda:0')
episode: 579 training return: tensor(-3.2923e+19, device='cuda:0')
epoch: 145 test_true_pfm: 75.5160821437879
episode: 580 training return: tensor(-3.4114e+19, device='cuda:0')
episode: 581 training return: tensor(-3.9967e+19, device='cuda:0')
episode: 582 training return: tensor(-4.1471e+19, device='cuda:0')
episode: 583 training return: tensor(-3.8907e+19, device='cuda:0')
epoch: 146 test_true_pfm: 87.61179005642583
episode: 584 training return: tensor(-8.0109e+19, device='cuda:0')
episode: 585 training return: tensor(-4.1230e+19, device='cuda:0')
episode: 586 training return: tensor(-4.0078e+19, device='cuda:0')
episode: 587 training return: tensor(-4.0277e+19, device='cuda:0')
epoch: 147 test_true_pfm: 46.56524253637207
episode: 588 training return: tensor(-3.9461e+19, device='cuda:0')
episode: 589 training return: tensor(-3.9514e+19, device='cuda:0')
episode: 590 training return: tensor(-4.0338e+19, device='cuda:0')
episode: 591 training return: tensor(-4.0971e+19, device='cuda:0')
epoch: 148 test_true_pfm: 47.00223728544507
episode: 592 training return: tensor(-4.0103e+19, device='cuda:0')
episode: 593 training return: tensor(-4.0010e+19, device='cuda:0')
episode: 594 training return: tensor(-4.0057e+19, device='cuda:0')
episode: 595 training return: tensor(-4.0355e+19, device='cuda:0')
epoch: 149 test_true_pfm: 46.57295270234102
episode: 596 training return: tensor(-4.0296e+19, device='cuda:0')
episode: 597 training return: tensor(-3.9815e+19, device='cuda:0')
episode: 598 training return: tensor(-4.0385e+19, device='cuda:0')
episode: 599 training return: tensor(-3.9637e+19, device='cuda:0')
epoch: 150 test_true_pfm: 45.290158476220405
