['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'mixed', '--seed', '2', '--data', '100000']
epoch: 0 training_loss 0.2016784379631281 test_loss: 0.15335066318511964
epoch: 1 training_loss 0.13271893486380576 test_loss: 0.11894470453262329
epoch: 2 training_loss 0.1257720248773694 test_loss: 0.12492566108703614
epoch: 3 training_loss 0.11346761997789144 test_loss: 0.13011224269866944
epoch: 4 training_loss 0.11699280941858888 test_loss: 0.11646695137023926
epoch: 5 training_loss 0.1112692422606051 test_loss: 0.11534348726272584
epoch: 6 training_loss 0.10938551407307387 test_loss: 0.11569256782531738
epoch: 7 training_loss 0.11776761056855321 test_loss: 0.13289629220962523
epoch: 8 training_loss 0.11782992012798786 test_loss: 0.12905237674713135
epoch: 9 training_loss 0.11400609370321035 test_loss: 0.11558105945587158
epoch: 10 training_loss 0.10600907888263464 test_loss: 0.10963062047958375
epoch: 11 training_loss 0.11263107240200043 test_loss: 0.11386982202529908
epoch: 12 training_loss 0.10366387709975243 test_loss: 0.10656527280807496
epoch: 13 training_loss 0.11109096195548773 test_loss: 0.09599496126174926
epoch: 14 training_loss 0.1058514704555273 test_loss: 0.1147795557975769
epoch: 15 training_loss 0.11194652911275625 test_loss: 0.1026195764541626
epoch: 16 training_loss 0.10125329701229929 test_loss: 0.11616209745407105
epoch: 17 training_loss 0.11025831403210759 test_loss: 0.11256078481674195
epoch: 18 training_loss 0.10491932690143585 test_loss: 0.09821326732635498
epoch: 19 training_loss 0.09837386842817068 test_loss: 0.11477738618850708
epoch: 20 training_loss 0.10408749217167497 test_loss: 0.1211250901222229
epoch: 21 training_loss 0.10112427223473787 test_loss: 0.13378212451934815
epoch: 22 training_loss 0.10960900280624628 test_loss: 0.11201434135437012
epoch: 23 training_loss 0.10815518487244845 test_loss: 0.10984188318252563
epoch: 24 training_loss 0.10923497669398785 test_loss: 0.10336048603057861
epoch: 25 training_loss 0.10298307150602341 test_loss: 0.11218701601028443
epoch: 26 training_loss 0.09728289723396301 test_loss: 0.09416143298149109
epoch: 27 training_loss 0.10849944416433573 test_loss: 0.10131629705429077
epoch: 28 training_loss 0.10652713384479284 test_loss: 0.10227411985397339
epoch: 29 training_loss 0.09715871373191476 test_loss: 0.1143600583076477
epoch: 30 training_loss 0.09754523038864135 test_loss: 0.12763465642929078
epoch: 31 training_loss 0.10391857609152794 test_loss: 0.1026993989944458
epoch: 32 training_loss 0.11143771763890982 test_loss: 0.10857511758804321
epoch: 33 training_loss 0.09208660259842873 test_loss: 0.09590935707092285
epoch: 34 training_loss 0.10317316461354493 test_loss: 0.11492295265197754
epoch: 35 training_loss 0.1077592233940959 test_loss: 0.11179009675979615
epoch: 36 training_loss 0.10834053694736212 test_loss: 0.10777286291122437
epoch: 37 training_loss 0.0985263060219586 test_loss: 0.09858917593955993
epoch: 38 training_loss 0.10973383765667677 test_loss: 0.1176874041557312
epoch: 39 training_loss 0.10502095207571983 test_loss: 0.10728969573974609
epoch: 40 training_loss 0.09962065318599343 test_loss: 0.09102578163146972
epoch: 41 training_loss 0.10637036610394716 test_loss: 0.11213014125823975
epoch: 42 training_loss 0.10145290987566113 test_loss: 0.10586239099502563
epoch: 43 training_loss 0.10186008114367723 test_loss: 0.09949137568473816
epoch: 44 training_loss 0.10197587791830301 test_loss: 0.09703787565231323
epoch: 45 training_loss 0.10263134254142642 test_loss: 0.11347842216491699
epoch: 46 training_loss 0.1060778628475964 test_loss: 0.10821137428283692
epoch: 47 training_loss 0.09967789510264993 test_loss: 0.10309115648269654
epoch: 48 training_loss 0.09947953946888446 test_loss: 0.1201178789138794
epoch: 49 training_loss 0.09970595937222243 test_loss: 0.11194840669631959
epoch: 50 training_loss 0.1047681512311101 test_loss: 0.10268669128417969
epoch: 51 training_loss 0.09330453971400857 test_loss: 0.10371485948562623
epoch: 52 training_loss 0.10110963903367519 test_loss: 0.1069491147994995
epoch: 53 training_loss 0.11097554344683885 test_loss: 0.10756255388259887
epoch: 54 training_loss 0.10545729760080576 test_loss: 0.09659079909324646
epoch: 55 training_loss 0.09928512454032898 test_loss: 0.10112899541854858
epoch: 56 training_loss 0.10153185930103063 test_loss: 0.10425373315811157
epoch: 57 training_loss 0.09837026985362173 test_loss: 0.1070937156677246
epoch: 58 training_loss 0.10063562657684087 test_loss: 0.10034736394882202
epoch: 59 training_loss 0.10149879707023501 test_loss: 0.10077919960021972
epoch: 60 training_loss 0.09687676269561052 test_loss: 0.10191807746887208
epoch: 61 training_loss 0.09772460650652647 test_loss: 0.10042988061904908
epoch: 62 training_loss 0.09691969761624933 test_loss: 0.09112194180488586
epoch: 63 training_loss 0.10112054008990526 test_loss: 0.09286459684371948
epoch: 64 training_loss 0.09927510306239128 test_loss: 0.10609101057052613
epoch: 65 training_loss 0.09656132807955146 test_loss: 0.10314117670059204
epoch: 66 training_loss 0.10020314197987318 test_loss: 0.09817028641700745
epoch: 67 training_loss 0.09937363162636757 test_loss: 0.11126185655593872
epoch: 68 training_loss 0.10767472062259913 test_loss: 0.1092952847480774
epoch: 69 training_loss 0.09907638128846884 test_loss: 0.11001484394073487
epoch: 70 training_loss 0.09811892025172711 test_loss: 0.11044995784759522
epoch: 71 training_loss 0.09612121436744929 test_loss: 0.10578049421310425
epoch: 72 training_loss 0.10174040807411075 test_loss: 0.11083711385726928
epoch: 73 training_loss 0.09722776651382446 test_loss: 0.08920358419418335
epoch: 74 training_loss 0.09763046436011791 test_loss: 0.10700033903121949
epoch: 75 training_loss 0.09767864096909762 test_loss: 0.09799822568893432
epoch: 76 training_loss 0.10678547259420157 test_loss: 0.09882145524024963
epoch: 77 training_loss 0.08995819080621004 test_loss: 0.0903737187385559
epoch: 78 training_loss 0.10483602944761515 test_loss: 0.10419474840164185
epoch: 79 training_loss 0.10565899502485991 test_loss: 0.10471099615097046
epoch: 80 training_loss 0.09692591428756714 test_loss: 0.10559272766113281
epoch: 81 training_loss 0.10195937965065241 test_loss: 0.09058302640914917
epoch: 82 training_loss 0.09742405788972974 test_loss: 0.10260776281356812
epoch: 83 training_loss 0.09922908145934344 test_loss: 0.09882994890213012
epoch: 84 training_loss 0.09963182874023914 test_loss: 0.0959052562713623
epoch: 85 training_loss 0.09360239908099174 test_loss: 0.1208906888961792
epoch: 86 training_loss 0.09738117322325707 test_loss: 0.10089536905288696
epoch: 87 training_loss 0.09311223274096847 test_loss: 0.13411920070648192
epoch: 88 training_loss 0.09572246886789798 test_loss: 0.10449646711349488
epoch: 89 training_loss 0.0998107571899891 test_loss: 0.10411719083786011
epoch: 90 training_loss 0.09944621507078409 test_loss: 0.10803362131118774
epoch: 91 training_loss 0.09685558980330825 test_loss: 0.10015324354171753
epoch: 92 training_loss 0.10306275758892297 test_loss: 0.10714479684829711
epoch: 93 training_loss 0.1087986421585083 test_loss: 0.11434928178787232
epoch: 94 training_loss 0.09887572916224599 test_loss: 0.10861042737960816
epoch: 95 training_loss 0.0984541455283761 test_loss: 0.09222633838653564
epoch: 96 training_loss 0.09860551111400127 test_loss: 0.07888244390487671
epoch: 97 training_loss 0.09859806364402175 test_loss: 0.09315929412841797
epoch: 98 training_loss 0.09819430697709322 test_loss: 0.10659765005111695
epoch: 99 training_loss 0.09959862595424056 test_loss: 0.09894710183143615
epoch: 100 training_loss 0.09624266466125846 test_loss: 0.10450873374938965
epoch: 101 training_loss 0.1032603912614286 test_loss: 0.10485860109329223
epoch: 102 training_loss 0.09967597078531981 test_loss: 0.10612330436706544
epoch: 103 training_loss 0.09988564807921647 test_loss: 0.10441913604736328
epoch: 104 training_loss 0.1005456094443798 test_loss: 0.10575541257858276
epoch: 105 training_loss 0.09792723704129458 test_loss: 0.10040475130081176
epoch: 106 training_loss 0.10229965623468161 test_loss: 0.09277502298355103
epoch: 107 training_loss 0.09794466447085143 test_loss: 0.09500847458839416
epoch: 108 training_loss 0.10058073457330466 test_loss: 0.09615707993507386
epoch: 109 training_loss 0.09931090027093888 test_loss: 0.12093499898910523
epoch: 110 training_loss 0.09353424483910203 test_loss: 0.10150015354156494
epoch: 111 training_loss 0.0927555214613676 test_loss: 0.1163595199584961
epoch: 112 training_loss 0.0956795803271234 test_loss: 0.10746098756790161
epoch: 113 training_loss 0.09835746794939042 test_loss: 0.10534236431121827
epoch: 114 training_loss 0.10293991807848216 test_loss: 0.08945518732070923
epoch: 115 training_loss 0.09527391972020269 test_loss: 0.11575863361358643
epoch: 116 training_loss 0.09499775141477584 test_loss: 0.11298115253448486
epoch: 117 training_loss 0.09551284115761519 test_loss: 0.09554434418678284
epoch: 118 training_loss 0.09175312463194132 test_loss: 0.0953179955482483
epoch: 119 training_loss 0.10338389575481415 test_loss: 0.09721927642822266
epoch: 120 training_loss 0.10144609346985817 test_loss: 0.09566667675971985
epoch: 121 training_loss 0.09637985907495022 test_loss: 0.09849859476089477
epoch: 122 training_loss 0.09405100297182799 test_loss: 0.09558935761451721
epoch: 123 training_loss 0.09650176484137774 test_loss: 0.09879485368728638
epoch: 124 training_loss 0.09454441440291703 test_loss: 0.09034268856048584
epoch: 125 training_loss 0.09456266662105918 test_loss: 0.09803657531738282
epoch: 126 training_loss 0.09369645707309246 test_loss: 0.11044412851333618
epoch: 127 training_loss 0.09376102276146411 test_loss: 0.10512750148773194
epoch: 128 training_loss 0.09594843534752727 test_loss: 0.08912968635559082
epoch: 129 training_loss 0.09489522656425833 test_loss: 0.08958722352981567
epoch: 130 training_loss 0.09614015089347959 test_loss: 0.09908980131149292
epoch: 131 training_loss 0.10650951124727726 test_loss: 0.1028053879737854
epoch: 132 training_loss 0.09286143029108644 test_loss: 0.09332582950592042
epoch: 133 training_loss 0.0960050356388092 test_loss: 0.1008725881576538
epoch: 134 training_loss 0.09570121681317686 test_loss: 0.08553119897842407
epoch: 135 training_loss 0.1052097118832171 test_loss: 0.09957462549209595
epoch: 136 training_loss 0.09500225769355893 test_loss: 0.10108861923217774
epoch: 137 training_loss 0.09997020849958062 test_loss: 0.10710383653640747
epoch: 138 training_loss 0.09894539888948202 test_loss: 0.09622111320495605
epoch: 139 training_loss 0.09944661585614085 test_loss: 0.11596419811248779
epoch: 140 training_loss 0.09446871813386679 test_loss: 0.09908116459846497
epoch: 141 training_loss 0.09746024779975414 test_loss: 0.10409277677536011
epoch: 142 training_loss 0.09668525900691748 test_loss: 0.10562657117843628
epoch: 143 training_loss 0.0994867510907352 test_loss: 0.10075325965881347
epoch: 144 training_loss 0.09728171274065972 test_loss: 0.10812458992004395
epoch: 145 training_loss 0.0966088667884469 test_loss: 0.11894457340240479
epoch: 146 training_loss 0.0933430465310812 test_loss: 0.09347341656684875
epoch: 147 training_loss 0.09600452654063701 test_loss: 0.10358748435974122
epoch: 148 training_loss 0.09615331759676338 test_loss: 0.08554421663284302
epoch: 149 training_loss 0.09616330839693546 test_loss: 0.10127770900726318
epoch: 0 training_loss 9.09567319393158 test_loss: 5.904584884643555
epoch: 1 training_loss 5.011233320236206 test_loss: 4.1668449401855465
epoch: 2 training_loss 3.83338525056839 test_loss: 3.5123504638671874
epoch: 3 training_loss 3.1758862709999085 test_loss: 2.8646242141723635
epoch: 4 training_loss 2.734882912635803 test_loss: 2.557456398010254
epoch: 5 training_loss 2.4468335032463076 test_loss: 2.337382125854492
epoch: 6 training_loss 2.199626659154892 test_loss: 2.159969139099121
epoch: 7 training_loss 2.0447604131698607 test_loss: 2.0213441848754883
epoch: 8 training_loss 1.9574897253513337 test_loss: 1.9674612045288087
epoch: 9 training_loss 1.9166030633449553 test_loss: 1.783877182006836
epoch: 10 training_loss 1.82212033867836 test_loss: 1.7677841186523438
epoch: 11 training_loss 1.692027404308319 test_loss: 1.7487648010253907
epoch: 12 training_loss 1.6666319537162781 test_loss: 1.770249366760254
epoch: 13 training_loss 1.6428731060028077 test_loss: 1.6725671768188477
epoch: 14 training_loss 1.6092209970951081 test_loss: 1.5805608749389648
epoch: 15 training_loss 1.5362101900577545 test_loss: 1.5713591575622559
epoch: 16 training_loss 1.493333123922348 test_loss: 1.4876588821411132
epoch: 17 training_loss 1.4943818950653076 test_loss: 1.4364261627197266
epoch: 18 training_loss 1.4593043208122254 test_loss: 1.4271763801574706
epoch: 19 training_loss 1.4125275599956513 test_loss: 1.3941942214965821
epoch: 20 training_loss 1.412948535680771 test_loss: 1.409851360321045
epoch: 21 training_loss 1.3709603798389436 test_loss: 1.3662978172302247
epoch: 22 training_loss 1.3060586905479432 test_loss: 1.3444087982177735
epoch: 23 training_loss 1.3190449118614196 test_loss: 1.3148179054260254
epoch: 24 training_loss 1.3104408526420592 test_loss: 1.3345206260681153
epoch: 25 training_loss 1.2619063133001327 test_loss: 1.317601776123047
epoch: 26 training_loss 1.2561315512657165 test_loss: 1.2936956405639648
epoch: 27 training_loss 1.2542540693283082 test_loss: 1.232685661315918
epoch: 28 training_loss 1.2240117478370667 test_loss: 1.242392349243164
epoch: 29 training_loss 1.2282034301757812 test_loss: 1.2457334518432617
epoch: 30 training_loss 1.209152203798294 test_loss: 1.1766341209411622
epoch: 31 training_loss 1.227223527431488 test_loss: 1.165803813934326
epoch: 32 training_loss 1.1834247118234635 test_loss: 1.1643759727478027
epoch: 33 training_loss 1.1651598262786864 test_loss: 1.1917499542236327
epoch: 34 training_loss 1.1715245473384857 test_loss: 1.202029323577881
epoch: 35 training_loss 1.1364686292409898 test_loss: 1.0946513175964356
epoch: 36 training_loss 1.1637692475318908 test_loss: 1.1380039215087892
epoch: 37 training_loss 1.1274346137046813 test_loss: 1.1984721183776856
epoch: 38 training_loss 1.1342455440759658 test_loss: 1.1898387908935546
epoch: 39 training_loss 1.1068262547254561 test_loss: 1.109098243713379
epoch: 40 training_loss 1.1072361588478088 test_loss: 1.0866490364074708
epoch: 41 training_loss 1.0931757003068925 test_loss: 1.0945467948913574
epoch: 42 training_loss 1.085029388666153 test_loss: 1.1110785484313965
epoch: 43 training_loss 1.0843811273574828 test_loss: 1.0619412422180177
epoch: 44 training_loss 1.0623531544208527 test_loss: 1.1150068283081054
epoch: 45 training_loss 1.0797575849294663 test_loss: 1.021497631072998
epoch: 46 training_loss 1.0626581984758376 test_loss: 1.0832502365112304
epoch: 47 training_loss 1.05698990046978 test_loss: 1.073070240020752
epoch: 48 training_loss 1.0492867189645767 test_loss: 1.0677451133728026
epoch: 49 training_loss 1.034137037396431 test_loss: 1.0208091735839844
epoch: 50 training_loss 1.0281920892000198 test_loss: 1.0439512252807617
epoch: 51 training_loss 1.0221701812744142 test_loss: 1.0920737266540528
epoch: 52 training_loss 1.013388964533806 test_loss: 1.0217571258544922
epoch: 53 training_loss 1.0106237983703614 test_loss: 1.0104159355163573
epoch: 54 training_loss 1.0090778464078902 test_loss: 1.0083410263061523
epoch: 55 training_loss 0.9907140529155731 test_loss: 0.976326847076416
epoch: 56 training_loss 0.9816245293617248 test_loss: 1.0204460144042968
epoch: 57 training_loss 0.9862029200792313 test_loss: 0.9912336349487305
epoch: 58 training_loss 0.9848077583312989 test_loss: 1.0144158363342286
epoch: 59 training_loss 0.9858675855398178 test_loss: 1.0241525650024415
epoch: 60 training_loss 0.9940851575136185 test_loss: 1.0208101272583008
epoch: 61 training_loss 0.9709493345022202 test_loss: 0.9703892707824707
epoch: 62 training_loss 0.9598027962446213 test_loss: 0.9664834022521973
epoch: 63 training_loss 0.9655670076608658 test_loss: 0.9984933853149414
epoch: 64 training_loss 0.9552140545845031 test_loss: 1.023562240600586
epoch: 65 training_loss 0.9425887840986252 test_loss: 0.9546428680419922
epoch: 66 training_loss 0.953249414563179 test_loss: 1.0006294250488281
epoch: 67 training_loss 0.957608444094658 test_loss: 0.9545113563537597
epoch: 68 training_loss 0.950619330406189 test_loss: 0.8978861808776856
epoch: 69 training_loss 0.9391759049892425 test_loss: 0.9396565437316895
epoch: 70 training_loss 0.9267348545789719 test_loss: 0.9157415390014648
epoch: 71 training_loss 0.9368811148405075 test_loss: 0.9137252807617188
epoch: 72 training_loss 0.9223163044452667 test_loss: 0.9451239585876465
epoch: 73 training_loss 0.9220449560880661 test_loss: 0.9908674240112305
epoch: 74 training_loss 0.9330004066228866 test_loss: 0.9486853599548339
epoch: 75 training_loss 0.9195320957899094 test_loss: 0.9300603866577148
epoch: 76 training_loss 0.9109901958703994 test_loss: 0.9940249443054199
epoch: 77 training_loss 0.9290363192558289 test_loss: 1.0053744316101074
epoch: 78 training_loss 0.9121872019767762 test_loss: 0.9063676834106446
epoch: 79 training_loss 0.9179863065481186 test_loss: 0.8717996597290039
epoch: 80 training_loss 0.9089950048923492 test_loss: 0.9552513122558594
epoch: 81 training_loss 0.9089465427398682 test_loss: 0.9086623191833496
epoch: 82 training_loss 0.8975200057029724 test_loss: 0.897775936126709
epoch: 83 training_loss 0.9167236876487732 test_loss: 0.9491190910339355
epoch: 84 training_loss 0.9121678549051285 test_loss: 0.908698844909668
epoch: 85 training_loss 0.8901651740074158 test_loss: 0.9117992401123047
epoch: 86 training_loss 0.8864234453439712 test_loss: 0.8610838890075684
epoch: 87 training_loss 0.8943161898851395 test_loss: 0.8973770141601562
epoch: 88 training_loss 0.8828703689575196 test_loss: 0.8743585586547852
epoch: 89 training_loss 0.875897325873375 test_loss: 0.8986881256103516
epoch: 90 training_loss 0.8954936492443085 test_loss: 0.9184536933898926
epoch: 91 training_loss 0.8680044823884964 test_loss: 0.8956151008605957
epoch: 92 training_loss 0.8750464785099029 test_loss: 0.9025455474853515
epoch: 93 training_loss 0.8767623269557953 test_loss: 0.8674650192260742
epoch: 94 training_loss 0.8659594124555587 test_loss: 0.8594144821166992
epoch: 95 training_loss 0.8627784359455108 test_loss: 0.9375845909118652
epoch: 96 training_loss 0.8840968155860901 test_loss: 0.8606989860534668
epoch: 97 training_loss 0.8750709837675095 test_loss: 0.8812007904052734
epoch: 98 training_loss 0.8454738903045654 test_loss: 0.8647181510925293
epoch: 99 training_loss 0.8430287069082261 test_loss: 0.8833043098449707
epoch: 100 training_loss 0.8557586914300919 test_loss: 0.8854856491088867
epoch: 101 training_loss 0.8494276404380798 test_loss: 0.8632266044616699
epoch: 102 training_loss 0.8388752865791321 test_loss: 0.8852436065673828
epoch: 103 training_loss 0.8387503212690354 test_loss: 0.8358735084533692
epoch: 104 training_loss 0.8358868050575257 test_loss: 0.8382058143615723
epoch: 105 training_loss 0.8457348942756653 test_loss: 0.8310176849365234
epoch: 106 training_loss 0.8360292136669158 test_loss: 0.8816512107849122
epoch: 107 training_loss 0.8358100712299347 test_loss: 0.8393375396728515
epoch: 108 training_loss 0.8350015664100647 test_loss: 0.8751495361328125
epoch: 109 training_loss 0.8506525719165802 test_loss: 0.8174970626831055
epoch: 110 training_loss 0.8434759867191315 test_loss: 0.8727928161621094
epoch: 111 training_loss 0.8227151381969452 test_loss: 0.8245065689086915
epoch: 112 training_loss 0.816345831155777 test_loss: 0.8903979301452637
epoch: 113 training_loss 0.8348545777797699 test_loss: 0.8218165397644043
epoch: 114 training_loss 0.8339618647098541 test_loss: 0.8267936706542969
epoch: 115 training_loss 0.8115613967180252 test_loss: 0.8334150314331055
epoch: 116 training_loss 0.81681660592556 test_loss: 0.8192460060119628
epoch: 117 training_loss 0.81131318628788 test_loss: 0.8448666572570801
epoch: 118 training_loss 0.8365488225221633 test_loss: 0.8422560691833496
epoch: 119 training_loss 0.8270067173242569 test_loss: 0.820770263671875
epoch: 120 training_loss 0.8095836812257766 test_loss: 0.7981629848480225
epoch: 121 training_loss 0.8304744470119476 test_loss: 0.8652082443237304
epoch: 122 training_loss 0.8127012932300568 test_loss: 0.8299617767333984
epoch: 123 training_loss 0.8070445972681045 test_loss: 0.8717842102050781
epoch: 124 training_loss 0.8271301847696304 test_loss: 0.8311939239501953
epoch: 125 training_loss 0.802413079738617 test_loss: 0.8401426315307617
epoch: 126 training_loss 0.7958901834487915 test_loss: 0.8330891609191895
epoch: 127 training_loss 0.8065049380064011 test_loss: 0.8540822029113769
epoch: 128 training_loss 0.815178582072258 test_loss: 0.8511228561401367
epoch: 129 training_loss 0.8161852592229843 test_loss: 0.8221902847290039
epoch: 130 training_loss 0.794804025888443 test_loss: 0.826991081237793
epoch: 131 training_loss 0.782617849111557 test_loss: 0.7801676750183105
epoch: 132 training_loss 0.810395570397377 test_loss: 0.8315928459167481
epoch: 133 training_loss 0.7768961560726165 test_loss: 0.7756393432617188
epoch: 134 training_loss 0.8066072714328766 test_loss: 0.8431488037109375
epoch: 135 training_loss 0.7778255695104599 test_loss: 0.8279664039611816
epoch: 136 training_loss 0.7723387557268143 test_loss: 0.8008837699890137
epoch: 137 training_loss 0.7847446620464325 test_loss: 0.8310521125793457
epoch: 138 training_loss 0.7996912354230881 test_loss: 0.7846180438995362
epoch: 139 training_loss 0.7773973309993744 test_loss: 0.7965049743652344
epoch: 140 training_loss 0.7730660271644593 test_loss: 0.7788298606872559
epoch: 141 training_loss 0.7936128497123718 test_loss: 0.7900135040283203
epoch: 142 training_loss 0.7921425867080688 test_loss: 0.7779511451721192
epoch: 143 training_loss 0.7803992062807084 test_loss: 0.7824490547180176
epoch: 144 training_loss 0.7632561856508255 test_loss: 0.8089071273803711
epoch: 145 training_loss 0.7865535724163055 test_loss: 0.7682075023651123
epoch: 146 training_loss 0.7728001618385315 test_loss: 0.7616553783416748
epoch: 147 training_loss 0.7685411125421524 test_loss: 0.7862149238586426
epoch: 148 training_loss 0.767165287733078 test_loss: 0.767692232131958
epoch: 149 training_loss 0.7643166023492813 test_loss: 0.7265972137451172
1943.6853993255252
episode: 0 training return: tensor(-328.5643, device='cuda:0')
episode: 1 training return: tensor(56.9167, device='cuda:0')
episode: 2 training return: tensor(-270.8210, device='cuda:0')
episode: 3 training return: tensor(-505.8073, device='cuda:0')
epoch: 1 test_true_pfm: 2929.076790871201 sim_pfm: 166.3806810360984
episode: 4 training return: tensor(-152.7666, device='cuda:0')
episode: 5 training return: tensor(-425.7426, device='cuda:0')
episode: 6 training return: tensor(-438.2135, device='cuda:0')
episode: 7 training return: tensor(-46.2305, device='cuda:0')
epoch: 2 test_true_pfm: 1509.7314762219958 sim_pfm: -403.10156158466515
episode: 8 training return: tensor(294.4528, device='cuda:0')
episode: 9 training return: tensor(107.1229, device='cuda:0')
episode: 10 training return: tensor(-458.1789, device='cuda:0')
episode: 11 training return: tensor(-434.6944, device='cuda:0')
epoch: 3 test_true_pfm: 1231.382310912654 sim_pfm: -456.0309940698401
episode: 12 training return: tensor(-448.6954, device='cuda:0')
episode: 13 training return: tensor(-448.4811, device='cuda:0')
episode: 14 training return: tensor(-489.8977, device='cuda:0')
episode: 15 training return: tensor(65.9175, device='cuda:0')
epoch: 4 test_true_pfm: 1186.43792078549 sim_pfm: -458.2630884279109
episode: 16 training return: tensor(-563.0602, device='cuda:0')
episode: 17 training return: tensor(-484.3993, device='cuda:0')
episode: 18 training return: tensor(-512.5217, device='cuda:0')
episode: 19 training return: tensor(-457.9367, device='cuda:0')
epoch: 5 test_true_pfm: 1207.0845272113702 sim_pfm: -460.0592927316611
episode: 20 training return: tensor(-452.2259, device='cuda:0')
episode: 21 training return: tensor(-454.0584, device='cuda:0')
episode: 22 training return: tensor(-329.0485, device='cuda:0')
episode: 23 training return: tensor(-455.3376, device='cuda:0')
epoch: 6 test_true_pfm: 1204.3269164392234 sim_pfm: -462.6698841965893
episode: 24 training return: tensor(-459.4061, device='cuda:0')
episode: 25 training return: tensor(-485.3728, device='cuda:0')
episode: 26 training return: tensor(-474.3712, device='cuda:0')
episode: 27 training return: tensor(-500.5317, device='cuda:0')
epoch: 7 test_true_pfm: 1210.82872141587 sim_pfm: -459.51718407733523
episode: 28 training return: tensor(-461.8238, device='cuda:0')
episode: 29 training return: tensor(-467.2603, device='cuda:0')
episode: 30 training return: tensor(-475.5840, device='cuda:0')
episode: 31 training return: tensor(-450.7743, device='cuda:0')
epoch: 8 test_true_pfm: 1216.9402998264889 sim_pfm: -456.6987399176384
episode: 32 training return: tensor(-449.9473, device='cuda:0')
episode: 33 training return: tensor(-443.3135, device='cuda:0')
episode: 34 training return: tensor(-316.4538, device='cuda:0')
episode: 35 training return: tensor(-454.5302, device='cuda:0')
epoch: 9 test_true_pfm: 1196.718915349299 sim_pfm: -463.52930148194235
episode: 36 training return: tensor(-398.8128, device='cuda:0')
episode: 37 training return: tensor(-273.6629, device='cuda:0')
episode: 38 training return: tensor(-443.1468, device='cuda:0')
episode: 39 training return: tensor(-472.3052, device='cuda:0')
epoch: 10 test_true_pfm: 1457.4941293590546 sim_pfm: -412.683240606304
episode: 40 training return: tensor(-432.0762, device='cuda:0')
episode: 41 training return: tensor(-359.0116, device='cuda:0')
episode: 42 training return: tensor(-452.2411, device='cuda:0')
episode: 43 training return: tensor(-365.5394, device='cuda:0')
epoch: 11 test_true_pfm: 1480.7287545238385 sim_pfm: -304.0111425165475
episode: 44 training return: tensor(-389.9900, device='cuda:0')
episode: 45 training return: tensor(-262.0564, device='cuda:0')
episode: 46 training return: tensor(-290.4923, device='cuda:0')
episode: 47 training return: tensor(-310.4729, device='cuda:0')
epoch: 12 test_true_pfm: 1452.4578187773968 sim_pfm: -362.38096302203485
episode: 48 training return: tensor(-449.4716, device='cuda:0')
episode: 49 training return: tensor(-428.7805, device='cuda:0')
episode: 50 training return: tensor(-334.2897, device='cuda:0')
episode: 51 training return: tensor(-264.9920, device='cuda:0')
epoch: 13 test_true_pfm: 1252.5274912400107 sim_pfm: -443.3506277022728
episode: 52 training return: tensor(-445.4485, device='cuda:0')
episode: 53 training return: tensor(-367.2091, device='cuda:0')
episode: 54 training return: tensor(-497.8108, device='cuda:0')
episode: 55 training return: tensor(-467.1792, device='cuda:0')
epoch: 14 test_true_pfm: 1378.1989761191692 sim_pfm: -344.60316252103075
episode: 56 training return: tensor(-282.2505, device='cuda:0')
episode: 57 training return: tensor(-345.0205, device='cuda:0')
episode: 58 training return: tensor(-476.7048, device='cuda:0')
episode: 59 training return: tensor(-46.1440, device='cuda:0')
epoch: 15 test_true_pfm: 1567.853951884598 sim_pfm: -296.4492784891433
episode: 60 training return: tensor(-391.4419, device='cuda:0')
episode: 61 training return: tensor(-494.8647, device='cuda:0')
episode: 62 training return: tensor(-287.9453, device='cuda:0')
episode: 63 training return: tensor(-437.2406, device='cuda:0')
epoch: 16 test_true_pfm: 2337.7500238450752 sim_pfm: -273.3556914053236
episode: 64 training return: tensor(-476.4183, device='cuda:0')
episode: 65 training return: tensor(-272.5326, device='cuda:0')
episode: 66 training return: tensor(-255.2784, device='cuda:0')
episode: 67 training return: tensor(-451.6888, device='cuda:0')
epoch: 17 test_true_pfm: 2624.231148465398 sim_pfm: 38.740657376513504
episode: 68 training return: tensor(-263.6978, device='cuda:0')
episode: 69 training return: tensor(-303.8947, device='cuda:0')
episode: 70 training return: tensor(-269.1293, device='cuda:0')
episode: 71 training return: tensor(-456.5796, device='cuda:0')
epoch: 18 test_true_pfm: 1734.550134802398 sim_pfm: -64.91779831432116
episode: 72 training return: tensor(-233.2158, device='cuda:0')
episode: 73 training return: tensor(-282.7112, device='cuda:0')
episode: 74 training return: tensor(-408.4074, device='cuda:0')
episode: 75 training return: tensor(-387.9964, device='cuda:0')
epoch: 19 test_true_pfm: 1808.081000731571 sim_pfm: -82.63671537374223
episode: 76 training return: tensor(-452.7461, device='cuda:0')
episode: 77 training return: tensor(-92.1456, device='cuda:0')
episode: 78 training return: tensor(-350.8956, device='cuda:0')
episode: 79 training return: tensor(-405.9026, device='cuda:0')
epoch: 20 test_true_pfm: 1541.603049196373 sim_pfm: -338.13581579807214
episode: 80 training return: tensor(-175.8230, device='cuda:0')
episode: 81 training return: tensor(-453.6060, device='cuda:0')
episode: 82 training return: tensor(-286.8078, device='cuda:0')
episode: 83 training return: tensor(-476.7614, device='cuda:0')
epoch: 21 test_true_pfm: 1756.4894640590567 sim_pfm: -326.7334705554725
episode: 84 training return: tensor(-392.7567, device='cuda:0')
episode: 85 training return: tensor(-434.5443, device='cuda:0')
episode: 86 training return: tensor(-334.7654, device='cuda:0')
episode: 87 training return: tensor(-248.9625, device='cuda:0')
epoch: 22 test_true_pfm: 1525.1392475705125 sim_pfm: -328.58303127259325
episode: 88 training return: tensor(-487.2907, device='cuda:0')
episode: 89 training return: tensor(-381.2566, device='cuda:0')
episode: 90 training return: tensor(-423.1027, device='cuda:0')
episode: 91 training return: tensor(-363.7468, device='cuda:0')
epoch: 23 test_true_pfm: 1580.2548809414045 sim_pfm: -280.3453785551246
episode: 92 training return: tensor(-279.7262, device='cuda:0')
episode: 93 training return: tensor(-290.8343, device='cuda:0')
episode: 94 training return: tensor(-457.4438, device='cuda:0')
episode: 95 training return: tensor(-450.1229, device='cuda:0')
epoch: 24 test_true_pfm: 1786.6181757488876 sim_pfm: -323.21473531331867
episode: 96 training return: tensor(-353.4715, device='cuda:0')
episode: 97 training return: tensor(-284.5706, device='cuda:0')
episode: 98 training return: tensor(-347.8340, device='cuda:0')
episode: 99 training return: tensor(-62.0933, device='cuda:0')
epoch: 25 test_true_pfm: 1529.6941519785025 sim_pfm: -351.026359636938
episode: 100 training return: tensor(-442.2474, device='cuda:0')
episode: 101 training return: tensor(-173.2374, device='cuda:0')
episode: 102 training return: tensor(-356.0095, device='cuda:0')
episode: 103 training return: tensor(-440.9344, device='cuda:0')
epoch: 26 test_true_pfm: 1426.806566462189 sim_pfm: -363.75225269716856
episode: 104 training return: tensor(-438.1799, device='cuda:0')
episode: 105 training return: tensor(-356.4636, device='cuda:0')
episode: 106 training return: tensor(-295.2921, device='cuda:0')
episode: 107 training return: tensor(-349.2164, device='cuda:0')
epoch: 27 test_true_pfm: 2495.424331877406 sim_pfm: -128.52392169030887
episode: 108 training return: tensor(-352.6115, device='cuda:0')
episode: 109 training return: tensor(-353.8678, device='cuda:0')
episode: 110 training return: tensor(-394.5707, device='cuda:0')
episode: 111 training return: tensor(-323.6418, device='cuda:0')
epoch: 28 test_true_pfm: 1551.0085597084483 sim_pfm: -254.27870618831366
episode: 112 training return: tensor(-453.5998, device='cuda:0')
episode: 113 training return: tensor(-446.8058, device='cuda:0')
episode: 114 training return: tensor(-69.3130, device='cuda:0')
episode: 115 training return: tensor(-309.4417, device='cuda:0')
epoch: 29 test_true_pfm: 1415.379302433429 sim_pfm: -405.14818922430277
episode: 116 training return: tensor(-426.8662, device='cuda:0')
episode: 117 training return: tensor(-423.8209, device='cuda:0')
episode: 118 training return: tensor(-477.7067, device='cuda:0')
episode: 119 training return: tensor(-493.2771, device='cuda:0')
epoch: 30 test_true_pfm: 1444.2091616127864 sim_pfm: -418.6429910386602
episode: 120 training return: tensor(327.5058, device='cuda:0')
episode: 121 training return: tensor(-433.6860, device='cuda:0')
episode: 122 training return: tensor(-351.4621, device='cuda:0')
episode: 123 training return: tensor(-311.8101, device='cuda:0')
epoch: 31 test_true_pfm: 1341.0921882147625 sim_pfm: -438.5575782665983
episode: 124 training return: tensor(-261.8917, device='cuda:0')
episode: 125 training return: tensor(-453.6459, device='cuda:0')
episode: 126 training return: tensor(-426.7987, device='cuda:0')
episode: 127 training return: tensor(-477.2013, device='cuda:0')
epoch: 32 test_true_pfm: 1553.589450852035 sim_pfm: -329.34832506991614
episode: 128 training return: tensor(-452.1145, device='cuda:0')
episode: 129 training return: tensor(-426.6328, device='cuda:0')
episode: 130 training return: tensor(-425.5693, device='cuda:0')
episode: 131 training return: tensor(-99.0706, device='cuda:0')
epoch: 33 test_true_pfm: 2537.8966894365276 sim_pfm: -80.3438000002255
episode: 132 training return: tensor(235.6713, device='cuda:0')
episode: 133 training return: tensor(-368.5217, device='cuda:0')
episode: 134 training return: tensor(-432.7184, device='cuda:0')
episode: 135 training return: tensor(-497.2100, device='cuda:0')
epoch: 34 test_true_pfm: 1601.8622203759096 sim_pfm: -380.7436653186257
episode: 136 training return: tensor(-350.4546, device='cuda:0')
episode: 137 training return: tensor(149.6502, device='cuda:0')
episode: 138 training return: tensor(-457.5277, device='cuda:0')
episode: 139 training return: tensor(-399.8460, device='cuda:0')
epoch: 35 test_true_pfm: 1607.602449172308 sim_pfm: -334.6768005276099
episode: 140 training return: tensor(-384.8301, device='cuda:0')
episode: 141 training return: tensor(-31.6802, device='cuda:0')
episode: 142 training return: tensor(-311.1862, device='cuda:0')
episode: 143 training return: tensor(-475.2246, device='cuda:0')
epoch: 36 test_true_pfm: 1686.537048548337 sim_pfm: -228.63908585597528
episode: 144 training return: tensor(-237.7919, device='cuda:0')
episode: 145 training return: tensor(216.1778, device='cuda:0')
episode: 146 training return: tensor(150.9393, device='cuda:0')
episode: 147 training return: tensor(-95.1363, device='cuda:0')
epoch: 37 test_true_pfm: 1773.4060123914849 sim_pfm: -304.8542362745502
episode: 148 training return: tensor(-148.3920, device='cuda:0')
episode: 149 training return: tensor(-433.5992, device='cuda:0')
episode: 150 training return: tensor(-475.1006, device='cuda:0')
episode: 151 training return: tensor(-463.2170, device='cuda:0')
epoch: 38 test_true_pfm: 1373.3965767608217 sim_pfm: -374.0109581069555
episode: 152 training return: tensor(-352.2781, device='cuda:0')
episode: 153 training return: tensor(-473.7543, device='cuda:0')
episode: 154 training return: tensor(296.8140, device='cuda:0')
episode: 155 training return: tensor(-247.2607, device='cuda:0')
epoch: 39 test_true_pfm: 1475.3641679006669 sim_pfm: -304.6025510953041
episode: 156 training return: tensor(-369.0378, device='cuda:0')
episode: 157 training return: tensor(-488.2480, device='cuda:0')
episode: 158 training return: tensor(-387.8372, device='cuda:0')
episode: 159 training return: tensor(-450.9589, device='cuda:0')
epoch: 40 test_true_pfm: 1566.896938801683 sim_pfm: -297.2056687286434
episode: 160 training return: tensor(-512.5466, device='cuda:0')
episode: 161 training return: tensor(-445.4987, device='cuda:0')
episode: 162 training return: tensor(-344.5861, device='cuda:0')
episode: 163 training return: tensor(-275.3159, device='cuda:0')
epoch: 41 test_true_pfm: 1450.6387557469245 sim_pfm: -316.0099420850941
episode: 164 training return: tensor(-458.6523, device='cuda:0')
episode: 165 training return: tensor(-332.4939, device='cuda:0')
episode: 166 training return: tensor(-277.1107, device='cuda:0')
episode: 167 training return: tensor(-285.9798, device='cuda:0')
epoch: 42 test_true_pfm: 1578.9614670958047 sim_pfm: -299.0415046689256
episode: 168 training return: tensor(-352.3517, device='cuda:0')
episode: 169 training return: tensor(-452.4527, device='cuda:0')
episode: 170 training return: tensor(-260.6975, device='cuda:0')
episode: 171 training return: tensor(-464.1667, device='cuda:0')
epoch: 43 test_true_pfm: 1838.5277696398155 sim_pfm: -258.37732728488237
episode: 172 training return: tensor(-103.1180, device='cuda:0')
episode: 173 training return: tensor(-24.2228, device='cuda:0')
episode: 174 training return: tensor(-428.4535, device='cuda:0')
episode: 175 training return: tensor(-453.8318, device='cuda:0')
epoch: 44 test_true_pfm: 1352.609789178666 sim_pfm: -422.40478671249
episode: 176 training return: tensor(-374.5381, device='cuda:0')
episode: 177 training return: tensor(-447.4333, device='cuda:0')
episode: 178 training return: tensor(-229.9785, device='cuda:0')
episode: 179 training return: tensor(-434.4839, device='cuda:0')
epoch: 45 test_true_pfm: 1516.9268376316668 sim_pfm: -290.1200252090736
episode: 180 training return: tensor(-405.3432, device='cuda:0')
episode: 181 training return: tensor(-492.2933, device='cuda:0')
episode: 182 training return: tensor(-98.1215, device='cuda:0')
episode: 183 training return: tensor(-383.0415, device='cuda:0')
epoch: 46 test_true_pfm: 2111.7501321365803 sim_pfm: -147.78665556624765
episode: 184 training return: tensor(-452.0094, device='cuda:0')
episode: 185 training return: tensor(-344.6921, device='cuda:0')
episode: 186 training return: tensor(-469.7879, device='cuda:0')
episode: 187 training return: tensor(-452.2814, device='cuda:0')
epoch: 47 test_true_pfm: 1274.6692732264705 sim_pfm: -366.79917497897986
episode: 188 training return: tensor(-319.5287, device='cuda:0')
episode: 189 training return: tensor(-374.9656, device='cuda:0')
episode: 190 training return: tensor(-443.0978, device='cuda:0')
episode: 191 training return: tensor(-296.6776, device='cuda:0')
epoch: 48 test_true_pfm: 2120.500877829096 sim_pfm: -320.3585765354801
episode: 192 training return: tensor(-358.8396, device='cuda:0')
episode: 193 training return: tensor(-275.6200, device='cuda:0')
episode: 194 training return: tensor(-453.0330, device='cuda:0')
episode: 195 training return: tensor(-82.6841, device='cuda:0')
epoch: 49 test_true_pfm: 1646.424840578197 sim_pfm: -355.091882159623
episode: 196 training return: tensor(-246.0147, device='cuda:0')
episode: 197 training return: tensor(-430.1774, device='cuda:0')
episode: 198 training return: tensor(-386.1847, device='cuda:0')
episode: 199 training return: tensor(-419.8467, device='cuda:0')
epoch: 50 test_true_pfm: 2243.8947185366965 sim_pfm: -209.6550104484195
episode: 200 training return: tensor(-317.1214, device='cuda:0')
episode: 201 training return: tensor(-335.5678, device='cuda:0')
episode: 202 training return: tensor(-142.9757, device='cuda:0')
episode: 203 training return: tensor(-270.7634, device='cuda:0')
epoch: 51 test_true_pfm: 1414.7463424563564 sim_pfm: -372.63927345753956
episode: 204 training return: tensor(-449.9525, device='cuda:0')
episode: 205 training return: tensor(-450.8600, device='cuda:0')
episode: 206 training return: tensor(-418.9322, device='cuda:0')
episode: 207 training return: tensor(-170.7270, device='cuda:0')
epoch: 52 test_true_pfm: 1611.760285302058 sim_pfm: -401.18190910325694
episode: 208 training return: tensor(-269.4393, device='cuda:0')
episode: 209 training return: tensor(-427.0224, device='cuda:0')
episode: 210 training return: tensor(-354.4693, device='cuda:0')
episode: 211 training return: tensor(-337.3367, device='cuda:0')
epoch: 53 test_true_pfm: 1476.326913360881 sim_pfm: -296.67160657187924
episode: 212 training return: tensor(-155.1286, device='cuda:0')
episode: 213 training return: tensor(-404.2866, device='cuda:0')
episode: 214 training return: tensor(-348.9543, device='cuda:0')
episode: 215 training return: tensor(-55.9000, device='cuda:0')
epoch: 54 test_true_pfm: 2168.9622456682555 sim_pfm: -128.85219211596996
episode: 216 training return: tensor(-466.4668, device='cuda:0')
episode: 217 training return: tensor(-453.3307, device='cuda:0')
episode: 218 training return: tensor(76.7654, device='cuda:0')
episode: 219 training return: tensor(-444.6682, device='cuda:0')
epoch: 55 test_true_pfm: 1489.0121694788552 sim_pfm: -372.6262913670701
episode: 220 training return: tensor(-423.9656, device='cuda:0')
episode: 221 training return: tensor(-212.2012, device='cuda:0')
episode: 222 training return: tensor(-280.6875, device='cuda:0')
episode: 223 training return: tensor(-448.3509, device='cuda:0')
epoch: 56 test_true_pfm: 1580.9203474056 sim_pfm: -333.5115469910864
episode: 224 training return: tensor(-451.4755, device='cuda:0')
episode: 225 training return: tensor(-382.7430, device='cuda:0')
episode: 226 training return: tensor(-477.5293, device='cuda:0')
episode: 227 training return: tensor(-301.8214, device='cuda:0')
epoch: 57 test_true_pfm: 1707.9434497509599 sim_pfm: -265.3898094285202
episode: 228 training return: tensor(-440.3738, device='cuda:0')
episode: 229 training return: tensor(-444.0544, device='cuda:0')
episode: 230 training return: tensor(-460.3210, device='cuda:0')
episode: 231 training return: tensor(-308.0467, device='cuda:0')
epoch: 58 test_true_pfm: 1411.5355496922105 sim_pfm: -339.3424814939499
episode: 232 training return: tensor(-450.5444, device='cuda:0')
episode: 233 training return: tensor(-256.6684, device='cuda:0')
episode: 234 training return: tensor(-380.6494, device='cuda:0')
episode: 235 training return: tensor(-351.8186, device='cuda:0')
epoch: 59 test_true_pfm: 1630.8606056248454 sim_pfm: -372.8232700951242
episode: 236 training return: tensor(-498.8673, device='cuda:0')
episode: 237 training return: tensor(-475.0538, device='cuda:0')
episode: 238 training return: tensor(-363.2886, device='cuda:0')
episode: 239 training return: tensor(-259.5923, device='cuda:0')
epoch: 60 test_true_pfm: 1309.4383721726936 sim_pfm: -344.90839398411725
episode: 240 training return: tensor(-408.0784, device='cuda:0')
episode: 241 training return: tensor(-438.3759, device='cuda:0')
episode: 242 training return: tensor(-428.7988, device='cuda:0')
episode: 243 training return: tensor(-381.3385, device='cuda:0')
epoch: 61 test_true_pfm: 1618.1688896872502 sim_pfm: -281.237013136968
episode: 244 training return: tensor(-254.0033, device='cuda:0')
episode: 245 training return: tensor(-330.8030, device='cuda:0')
episode: 246 training return: tensor(-168.0848, device='cuda:0')
episode: 247 training return: tensor(-227.1298, device='cuda:0')
epoch: 62 test_true_pfm: 1430.2523899782511 sim_pfm: -353.9492846687014
episode: 248 training return: tensor(-454.2060, device='cuda:0')
episode: 249 training return: tensor(-381.9991, device='cuda:0')
episode: 250 training return: tensor(56.2088, device='cuda:0')
episode: 251 training return: tensor(-459.7103, device='cuda:0')
epoch: 63 test_true_pfm: 1378.2601094508038 sim_pfm: -413.3413236211054
episode: 252 training return: tensor(-347.3345, device='cuda:0')
episode: 253 training return: tensor(-455.3628, device='cuda:0')
episode: 254 training return: tensor(-324.5329, device='cuda:0')
episode: 255 training return: tensor(-359.6318, device='cuda:0')
epoch: 64 test_true_pfm: 1301.3814488528476 sim_pfm: -417.819439094048
episode: 256 training return: tensor(-395.5399, device='cuda:0')
episode: 257 training return: tensor(-437.0093, device='cuda:0')
episode: 258 training return: tensor(-313.6490, device='cuda:0')
episode: 259 training return: tensor(-437.1880, device='cuda:0')
epoch: 65 test_true_pfm: 1285.4149492864847 sim_pfm: -420.3992229498302
episode: 260 training return: tensor(-456.4982, device='cuda:0')
episode: 261 training return: tensor(-459.4948, device='cuda:0')
episode: 262 training return: tensor(-405.3661, device='cuda:0')
episode: 263 training return: tensor(-449.7093, device='cuda:0')
epoch: 66 test_true_pfm: 1415.2374799914658 sim_pfm: -368.9083034802849
episode: 264 training return: tensor(-251.9986, device='cuda:0')
episode: 265 training return: tensor(-448.4260, device='cuda:0')
episode: 266 training return: tensor(-378.4789, device='cuda:0')
episode: 267 training return: tensor(-455.9639, device='cuda:0')
epoch: 67 test_true_pfm: 1297.1279779883891 sim_pfm: -390.4533799260001
episode: 268 training return: tensor(-461.7135, device='cuda:0')
episode: 269 training return: tensor(-349.3401, device='cuda:0')
episode: 270 training return: tensor(-327.8341, device='cuda:0')
episode: 271 training return: tensor(-488.5210, device='cuda:0')
epoch: 68 test_true_pfm: 1720.798591307451 sim_pfm: -288.07108892383985
episode: 272 training return: tensor(-456.8129, device='cuda:0')
episode: 273 training return: tensor(-451.6507, device='cuda:0')
episode: 274 training return: tensor(-273.1236, device='cuda:0')
episode: 275 training return: tensor(-339.9448, device='cuda:0')
epoch: 69 test_true_pfm: 1405.8087335832588 sim_pfm: -424.56804392207414
episode: 276 training return: tensor(-459.7154, device='cuda:0')
episode: 277 training return: tensor(-149.9518, device='cuda:0')
episode: 278 training return: tensor(-450.4963, device='cuda:0')
episode: 279 training return: tensor(-419.1422, device='cuda:0')
epoch: 70 test_true_pfm: 1292.5508012901612 sim_pfm: -407.3093340326256
episode: 280 training return: tensor(-366.1497, device='cuda:0')
episode: 281 training return: tensor(-290.2801, device='cuda:0')
episode: 282 training return: tensor(-459.4724, device='cuda:0')
episode: 283 training return: tensor(-450.5244, device='cuda:0')
epoch: 71 test_true_pfm: 1369.7849101900094 sim_pfm: -436.1276655113713
episode: 284 training return: tensor(-458.5682, device='cuda:0')
episode: 285 training return: tensor(-438.3432, device='cuda:0')
episode: 286 training return: tensor(-440.0564, device='cuda:0')
episode: 287 training return: tensor(-346.8799, device='cuda:0')
epoch: 72 test_true_pfm: 1458.2977713516882 sim_pfm: -325.63543955166824
episode: 288 training return: tensor(-212.4086, device='cuda:0')
episode: 289 training return: tensor(-376.3010, device='cuda:0')
episode: 290 training return: tensor(-429.2693, device='cuda:0')
episode: 291 training return: tensor(-350.2819, device='cuda:0')
epoch: 73 test_true_pfm: 1659.5134562867336 sim_pfm: -262.12896528032917
episode: 292 training return: tensor(-255.1788, device='cuda:0')
episode: 293 training return: tensor(-433.9925, device='cuda:0')
episode: 294 training return: tensor(-258.1119, device='cuda:0')
episode: 295 training return: tensor(-249.9120, device='cuda:0')
epoch: 74 test_true_pfm: 1275.702205145413 sim_pfm: -381.54124126552296
episode: 296 training return: tensor(-206.5741, device='cuda:0')
episode: 297 training return: tensor(-378.5637, device='cuda:0')
episode: 298 training return: tensor(-429.3499, device='cuda:0')
episode: 299 training return: tensor(-453.5484, device='cuda:0')
epoch: 75 test_true_pfm: 1708.2980676620552 sim_pfm: -321.54181594376377
episode: 300 training return: tensor(-103.8230, device='cuda:0')
episode: 301 training return: tensor(-460.4540, device='cuda:0')
episode: 302 training return: tensor(-350.1010, device='cuda:0')
episode: 303 training return: tensor(-381.2816, device='cuda:0')
epoch: 76 test_true_pfm: 1290.1354379583445 sim_pfm: -406.0220145234683
episode: 304 training return: tensor(-419.9346, device='cuda:0')
episode: 305 training return: tensor(-457.3673, device='cuda:0')
episode: 306 training return: tensor(-431.6514, device='cuda:0')
episode: 307 training return: tensor(-472.7915, device='cuda:0')
epoch: 77 test_true_pfm: 1269.2430647335475 sim_pfm: -436.9239952431526
episode: 308 training return: tensor(-387.2172, device='cuda:0')
episode: 309 training return: tensor(-423.3602, device='cuda:0')
episode: 310 training return: tensor(-253.2019, device='cuda:0')
episode: 311 training return: tensor(-389.5837, device='cuda:0')
epoch: 78 test_true_pfm: 1587.9077784132758 sim_pfm: -318.8217443843993
episode: 312 training return: tensor(-348.1663, device='cuda:0')
episode: 313 training return: tensor(-450.4930, device='cuda:0')
episode: 314 training return: tensor(-467.3451, device='cuda:0')
episode: 315 training return: tensor(-431.8414, device='cuda:0')
epoch: 79 test_true_pfm: 1333.5646677327352 sim_pfm: -420.3135511854198
episode: 316 training return: tensor(-356.5842, device='cuda:0')
episode: 317 training return: tensor(-457.9578, device='cuda:0')
episode: 318 training return: tensor(-352.4129, device='cuda:0')
episode: 319 training return: tensor(-343.6413, device='cuda:0')
epoch: 80 test_true_pfm: 1447.1252041564483 sim_pfm: -341.85485593639896
episode: 320 training return: tensor(-257.1177, device='cuda:0')
episode: 321 training return: tensor(-394.1725, device='cuda:0')
episode: 322 training return: tensor(-348.6915, device='cuda:0')
episode: 323 training return: tensor(-428.4406, device='cuda:0')
epoch: 81 test_true_pfm: 1370.5767829469794 sim_pfm: -379.7932033066366
episode: 324 training return: tensor(-452.8855, device='cuda:0')
episode: 325 training return: tensor(-379.5312, device='cuda:0')
episode: 326 training return: tensor(-477.7816, device='cuda:0')
episode: 327 training return: tensor(-374.7559, device='cuda:0')
epoch: 82 test_true_pfm: 1463.884422052264 sim_pfm: -400.06007939142484
episode: 328 training return: tensor(-443.7565, device='cuda:0')
episode: 329 training return: tensor(-429.1744, device='cuda:0')
episode: 330 training return: tensor(-150.9473, device='cuda:0')
episode: 331 training return: tensor(-249.5285, device='cuda:0')
epoch: 83 test_true_pfm: 1396.4086383377428 sim_pfm: -432.25052901140106
episode: 332 training return: tensor(-351.1913, device='cuda:0')
episode: 333 training return: tensor(-451.8395, device='cuda:0')
episode: 334 training return: tensor(-378.0243, device='cuda:0')
episode: 335 training return: tensor(-371.7800, device='cuda:0')
epoch: 84 test_true_pfm: 1583.9561045293078 sim_pfm: -330.8258695160427
episode: 336 training return: tensor(-447.3638, device='cuda:0')
episode: 337 training return: tensor(-372.1948, device='cuda:0')
episode: 338 training return: tensor(-497.5890, device='cuda:0')
episode: 339 training return: tensor(-351.2246, device='cuda:0')
epoch: 85 test_true_pfm: 1439.6653931101046 sim_pfm: -364.1457749262918
episode: 340 training return: tensor(-305.3310, device='cuda:0')
episode: 341 training return: tensor(-145.3433, device='cuda:0')
episode: 342 training return: tensor(-431.7312, device='cuda:0')
episode: 343 training return: tensor(-474.9732, device='cuda:0')
epoch: 86 test_true_pfm: 1299.8273511625705 sim_pfm: -395.5540838466647
episode: 344 training return: tensor(-154.9220, device='cuda:0')
episode: 345 training return: tensor(-461.2909, device='cuda:0')
episode: 346 training return: tensor(-251.0271, device='cuda:0')
episode: 347 training return: tensor(-391.0915, device='cuda:0')
epoch: 87 test_true_pfm: 1441.9093737869441 sim_pfm: -381.8302791578074
episode: 348 training return: tensor(-73.6668, device='cuda:0')
episode: 349 training return: tensor(-434.2845, device='cuda:0')
episode: 350 training return: tensor(-415.8713, device='cuda:0')
episode: 351 training return: tensor(-360.0130, device='cuda:0')
epoch: 88 test_true_pfm: 1519.986971648664 sim_pfm: -356.0658526751213
episode: 352 training return: tensor(-453.9750, device='cuda:0')
episode: 353 training return: tensor(-374.1699, device='cuda:0')
episode: 354 training return: tensor(-352.0289, device='cuda:0')
episode: 355 training return: tensor(-20.2169, device='cuda:0')
epoch: 89 test_true_pfm: 1506.1152209293439 sim_pfm: -363.3573949446824
episode: 356 training return: tensor(-351.2106, device='cuda:0')
episode: 357 training return: tensor(-475.1715, device='cuda:0')
episode: 358 training return: tensor(-400.4633, device='cuda:0')
episode: 359 training return: tensor(-453.1357, device='cuda:0')
epoch: 90 test_true_pfm: 1499.2675731670606 sim_pfm: -280.6056664040855
episode: 360 training return: tensor(-466.7065, device='cuda:0')
episode: 361 training return: tensor(-422.4930, device='cuda:0')
episode: 362 training return: tensor(-446.2466, device='cuda:0')
episode: 363 training return: tensor(-449.0928, device='cuda:0')
epoch: 91 test_true_pfm: 1460.1672269122473 sim_pfm: -342.1758185036015
episode: 364 training return: tensor(-429.4301, device='cuda:0')
episode: 365 training return: tensor(-472.4806, device='cuda:0')
episode: 366 training return: tensor(-435.2388, device='cuda:0')
episode: 367 training return: tensor(-465.1918, device='cuda:0')
epoch: 92 test_true_pfm: 1440.7716215431917 sim_pfm: -391.1117038306159
episode: 368 training return: tensor(-367.6444, device='cuda:0')
episode: 369 training return: tensor(-325.1128, device='cuda:0')
episode: 370 training return: tensor(-450.9909, device='cuda:0')
episode: 371 training return: tensor(-336.0390, device='cuda:0')
epoch: 93 test_true_pfm: 1350.9615552058788 sim_pfm: -410.8594306853677
episode: 372 training return: tensor(-470.6801, device='cuda:0')
episode: 373 training return: tensor(-453.9611, device='cuda:0')
episode: 374 training return: tensor(-419.5185, device='cuda:0')
episode: 375 training return: tensor(-457.9127, device='cuda:0')
epoch: 94 test_true_pfm: 1417.4903703857278 sim_pfm: -376.7064002382879
episode: 376 training return: tensor(-295.5456, device='cuda:0')
episode: 377 training return: tensor(-430.2646, device='cuda:0')
episode: 378 training return: tensor(-111.3887, device='cuda:0')
episode: 379 training return: tensor(-304.7536, device='cuda:0')
epoch: 95 test_true_pfm: 1434.0094109146985 sim_pfm: -380.02149840911926
episode: 380 training return: tensor(-313.0556, device='cuda:0')
episode: 381 training return: tensor(-417.9640, device='cuda:0')
episode: 382 training return: tensor(-418.8109, device='cuda:0')
episode: 383 training return: tensor(-425.6969, device='cuda:0')
epoch: 96 test_true_pfm: 1517.3668191713352 sim_pfm: -353.5615160319333
episode: 384 training return: tensor(-454.5552, device='cuda:0')
episode: 385 training return: tensor(-434.4578, device='cuda:0')
episode: 386 training return: tensor(-432.2707, device='cuda:0')
episode: 387 training return: tensor(-263.9594, device='cuda:0')
epoch: 97 test_true_pfm: 1469.484663343848 sim_pfm: -344.5831622031207
episode: 388 training return: tensor(-237.0732, device='cuda:0')
episode: 389 training return: tensor(-357.7039, device='cuda:0')
episode: 390 training return: tensor(-319.3318, device='cuda:0')
episode: 391 training return: tensor(-458.0985, device='cuda:0')
epoch: 98 test_true_pfm: 1443.5190161292849 sim_pfm: -396.04245930569596
episode: 392 training return: tensor(-114.8920, device='cuda:0')
episode: 393 training return: tensor(-447.5132, device='cuda:0')
episode: 394 training return: tensor(-382.5967, device='cuda:0')
episode: 395 training return: tensor(-454.7481, device='cuda:0')
epoch: 99 test_true_pfm: 1528.3544936840497 sim_pfm: -319.0396822364225
episode: 396 training return: tensor(-61.0396, device='cuda:0')
episode: 397 training return: tensor(-423.8148, device='cuda:0')
episode: 398 training return: tensor(-295.0667, device='cuda:0')
episode: 399 training return: tensor(-452.4019, device='cuda:0')
epoch: 100 test_true_pfm: 1509.1262716993078 sim_pfm: -389.52067175336805
episode: 400 training return: tensor(-452.9660, device='cuda:0')
episode: 401 training return: tensor(-246.2755, device='cuda:0')
episode: 402 training return: tensor(-247.4125, device='cuda:0')
episode: 403 training return: tensor(-440.0204, device='cuda:0')
epoch: 101 test_true_pfm: 1375.992419876881 sim_pfm: -409.9604413166332
episode: 404 training return: tensor(-462.2658, device='cuda:0')
episode: 405 training return: tensor(-305.4420, device='cuda:0')
episode: 406 training return: tensor(-427.3677, device='cuda:0')
episode: 407 training return: tensor(-452.7224, device='cuda:0')
epoch: 102 test_true_pfm: 1587.9488007747686 sim_pfm: -300.3493459985281
episode: 408 training return: tensor(-382.3316, device='cuda:0')
episode: 409 training return: tensor(-272.3036, device='cuda:0')
episode: 410 training return: tensor(-455.1020, device='cuda:0')
episode: 411 training return: tensor(-339.3573, device='cuda:0')
epoch: 103 test_true_pfm: 1518.6598359484099 sim_pfm: -385.65252683901537
episode: 412 training return: tensor(-277.2027, device='cuda:0')
episode: 413 training return: tensor(-429.2226, device='cuda:0')
episode: 414 training return: tensor(-435.8788, device='cuda:0')
episode: 415 training return: tensor(-438.0817, device='cuda:0')
epoch: 104 test_true_pfm: 1368.420313956399 sim_pfm: -420.7721785819158
episode: 416 training return: tensor(-458.6256, device='cuda:0')
episode: 417 training return: tensor(-335.4931, device='cuda:0')
episode: 418 training return: tensor(-379.4678, device='cuda:0')
episode: 419 training return: tensor(-454.6737, device='cuda:0')
epoch: 105 test_true_pfm: 1350.824851053435 sim_pfm: -407.1748977501023
episode: 420 training return: tensor(-430.1922, device='cuda:0')
episode: 421 training return: tensor(-378.3167, device='cuda:0')
episode: 422 training return: tensor(-350.3553, device='cuda:0')
episode: 423 training return: tensor(-277.2061, device='cuda:0')
epoch: 106 test_true_pfm: 1445.725698984277 sim_pfm: -370.7820824256244
episode: 424 training return: tensor(-369.0157, device='cuda:0')
episode: 425 training return: tensor(-431.7246, device='cuda:0')
episode: 426 training return: tensor(-477.5119, device='cuda:0')
episode: 427 training return: tensor(-415.3254, device='cuda:0')
epoch: 107 test_true_pfm: 1333.4753778547374 sim_pfm: -418.5487517514363
episode: 428 training return: tensor(-458.2618, device='cuda:0')
episode: 429 training return: tensor(-472.5144, device='cuda:0')
episode: 430 training return: tensor(-359.6849, device='cuda:0')
episode: 431 training return: tensor(-419.9421, device='cuda:0')
epoch: 108 test_true_pfm: 1664.2762281052208 sim_pfm: -278.71588166876853
episode: 432 training return: tensor(-399.0027, device='cuda:0')
episode: 433 training return: tensor(-272.2807, device='cuda:0')
episode: 434 training return: tensor(-418.7448, device='cuda:0')
episode: 435 training return: tensor(-461.0764, device='cuda:0')
epoch: 109 test_true_pfm: 1554.560404416172 sim_pfm: -376.2040390772745
episode: 436 training return: tensor(-24.0890, device='cuda:0')
episode: 437 training return: tensor(-488.9528, device='cuda:0')
episode: 438 training return: tensor(-375.7239, device='cuda:0')
episode: 439 training return: tensor(-462.9939, device='cuda:0')
epoch: 110 test_true_pfm: 1406.9533051398532 sim_pfm: -378.0893069242399
episode: 440 training return: tensor(-435.6072, device='cuda:0')
episode: 441 training return: tensor(-456.0261, device='cuda:0')
episode: 442 training return: tensor(-455.7905, device='cuda:0')
episode: 443 training return: tensor(-353.6101, device='cuda:0')
epoch: 111 test_true_pfm: 1481.116492039013 sim_pfm: -402.5372673005525
episode: 444 training return: tensor(-78.8422, device='cuda:0')
episode: 445 training return: tensor(-417.3246, device='cuda:0')
episode: 446 training return: tensor(-425.9394, device='cuda:0')
episode: 447 training return: tensor(-426.2480, device='cuda:0')
epoch: 112 test_true_pfm: 1484.2050167562636 sim_pfm: -393.122088529286
episode: 448 training return: tensor(-471.1855, device='cuda:0')
episode: 449 training return: tensor(-358.5823, device='cuda:0')
episode: 450 training return: tensor(-406.0502, device='cuda:0')
episode: 451 training return: tensor(-429.2426, device='cuda:0')
epoch: 113 test_true_pfm: 1360.2297102262717 sim_pfm: -392.19315667326254
episode: 452 training return: tensor(-449.0373, device='cuda:0')
episode: 453 training return: tensor(-419.5212, device='cuda:0')
episode: 454 training return: tensor(-292.2153, device='cuda:0')
episode: 455 training return: tensor(-175.5477, device='cuda:0')
epoch: 114 test_true_pfm: 1355.4452577670393 sim_pfm: -423.1428991802968
episode: 456 training return: tensor(-452.9331, device='cuda:0')
episode: 457 training return: tensor(-432.8509, device='cuda:0')
episode: 458 training return: tensor(-435.6172, device='cuda:0')
episode: 459 training return: tensor(-145.5708, device='cuda:0')
epoch: 115 test_true_pfm: 1528.1343528710186 sim_pfm: -329.12281109920394
episode: 460 training return: tensor(-416.8841, device='cuda:0')
episode: 461 training return: tensor(-405.9264, device='cuda:0')
episode: 462 training return: tensor(-351.3678, device='cuda:0')
episode: 463 training return: tensor(-382.1116, device='cuda:0')
epoch: 116 test_true_pfm: 1388.782220674154 sim_pfm: -385.13638089275145
episode: 464 training return: tensor(-327.1788, device='cuda:0')
episode: 465 training return: tensor(-277.9064, device='cuda:0')
episode: 466 training return: tensor(-445.2505, device='cuda:0')
episode: 467 training return: tensor(-240.9869, device='cuda:0')
epoch: 117 test_true_pfm: 1567.8102739802137 sim_pfm: -299.53935851956095
episode: 468 training return: tensor(-414.5519, device='cuda:0')
episode: 469 training return: tensor(-455.5340, device='cuda:0')
episode: 470 training return: tensor(-317.6317, device='cuda:0')
episode: 471 training return: tensor(-295.2471, device='cuda:0')
epoch: 118 test_true_pfm: 1370.4247212301223 sim_pfm: -381.2204075390085
episode: 472 training return: tensor(-328.0504, device='cuda:0')
episode: 473 training return: tensor(-458.6991, device='cuda:0')
episode: 474 training return: tensor(-287.7532, device='cuda:0')
episode: 475 training return: tensor(-422.1253, device='cuda:0')
epoch: 119 test_true_pfm: 1562.0348820396355 sim_pfm: -312.24942625824286
episode: 476 training return: tensor(-421.2813, device='cuda:0')
episode: 477 training return: tensor(-368.4496, device='cuda:0')
episode: 478 training return: tensor(-434.2769, device='cuda:0')
episode: 479 training return: tensor(-476.4229, device='cuda:0')
epoch: 120 test_true_pfm: 1456.0969339047533 sim_pfm: -366.9375098367843
episode: 480 training return: tensor(-236.2048, device='cuda:0')
episode: 481 training return: tensor(-449.5625, device='cuda:0')
episode: 482 training return: tensor(-455.9687, device='cuda:0')
episode: 483 training return: tensor(-419.8890, device='cuda:0')
epoch: 121 test_true_pfm: 1350.3689792191315 sim_pfm: -378.5365138768684
episode: 484 training return: tensor(-427.7012, device='cuda:0')
episode: 485 training return: tensor(-434.6194, device='cuda:0')
episode: 486 training return: tensor(-435.6830, device='cuda:0')
episode: 487 training return: tensor(-323.9981, device='cuda:0')
epoch: 122 test_true_pfm: 1319.873638963388 sim_pfm: -428.8861084651823
episode: 488 training return: tensor(-467.5678, device='cuda:0')
episode: 489 training return: tensor(-315.2363, device='cuda:0')
episode: 490 training return: tensor(-463.1772, device='cuda:0')
episode: 491 training return: tensor(-418.1139, device='cuda:0')
epoch: 123 test_true_pfm: 1323.979419667981 sim_pfm: -417.9959793534751
episode: 492 training return: tensor(-417.6913, device='cuda:0')
episode: 493 training return: tensor(-396.2864, device='cuda:0')
episode: 494 training return: tensor(-467.3043, device='cuda:0')
episode: 495 training return: tensor(-306.9894, device='cuda:0')
epoch: 124 test_true_pfm: 1345.1130794941598 sim_pfm: -411.7961350584325
episode: 496 training return: tensor(-361.2947, device='cuda:0')
episode: 497 training return: tensor(-425.0484, device='cuda:0')
episode: 498 training return: tensor(52.8178, device='cuda:0')
episode: 499 training return: tensor(-272.4762, device='cuda:0')
epoch: 125 test_true_pfm: 1374.9452894286405 sim_pfm: -386.4187216614373
episode: 500 training return: tensor(-365.7948, device='cuda:0')
episode: 501 training return: tensor(-283.8898, device='cuda:0')
episode: 502 training return: tensor(-464.7244, device='cuda:0')
episode: 503 training return: tensor(-483.7604, device='cuda:0')
epoch: 126 test_true_pfm: 1393.2835912803075 sim_pfm: -381.3155813883447
episode: 504 training return: tensor(-443.9009, device='cuda:0')
episode: 505 training return: tensor(-457.4457, device='cuda:0')
episode: 506 training return: tensor(-422.9427, device='cuda:0')
episode: 507 training return: tensor(-418.3816, device='cuda:0')
epoch: 127 test_true_pfm: 1744.0719048075844 sim_pfm: -366.57599532448995
episode: 508 training return: tensor(-451.6507, device='cuda:0')
episode: 509 training return: tensor(-433.3828, device='cuda:0')
episode: 510 training return: tensor(-431.3315, device='cuda:0')
episode: 511 training return: tensor(-371.3560, device='cuda:0')
epoch: 128 test_true_pfm: 1449.5900942158798 sim_pfm: -428.6905426090428
episode: 512 training return: tensor(-376.9121, device='cuda:0')
episode: 513 training return: tensor(-453.5439, device='cuda:0')
episode: 514 training return: tensor(-424.6277, device='cuda:0')
episode: 515 training return: tensor(-456.7534, device='cuda:0')
epoch: 129 test_true_pfm: 1349.0632565733124 sim_pfm: -439.6297094922823
episode: 516 training return: tensor(-475.1541, device='cuda:0')
episode: 517 training return: tensor(-424.1376, device='cuda:0')
episode: 518 training return: tensor(-263.1178, device='cuda:0')
episode: 519 training return: tensor(-406.9629, device='cuda:0')
epoch: 130 test_true_pfm: 1586.7686477513341 sim_pfm: -318.62259163769585
episode: 520 training return: tensor(-365.1888, device='cuda:0')
episode: 521 training return: tensor(-401.1223, device='cuda:0')
episode: 522 training return: tensor(-398.3551, device='cuda:0')
episode: 523 training return: tensor(20.0065, device='cuda:0')
epoch: 131 test_true_pfm: 1333.3234685150335 sim_pfm: -438.62400305992924
episode: 524 training return: tensor(-430.4456, device='cuda:0')
episode: 525 training return: tensor(-336.6707, device='cuda:0')
episode: 526 training return: tensor(-453.9732, device='cuda:0')
episode: 527 training return: tensor(-387.6975, device='cuda:0')
epoch: 132 test_true_pfm: 1527.3696382212604 sim_pfm: -341.47915272104245
episode: 528 training return: tensor(-351.5247, device='cuda:0')
episode: 529 training return: tensor(-340.8694, device='cuda:0')
episode: 530 training return: tensor(-356.4769, device='cuda:0')
episode: 531 training return: tensor(-238.8551, device='cuda:0')
epoch: 133 test_true_pfm: 1343.4296454877258 sim_pfm: -418.82312182243913
episode: 532 training return: tensor(-366.6669, device='cuda:0')
episode: 533 training return: tensor(-470.3513, device='cuda:0')
episode: 534 training return: tensor(-481.1444, device='cuda:0')
episode: 535 training return: tensor(-267.7619, device='cuda:0')
epoch: 134 test_true_pfm: 1378.5674698681644 sim_pfm: -397.90153767998953
episode: 536 training return: tensor(-340.7276, device='cuda:0')
episode: 537 training return: tensor(-230.6816, device='cuda:0')
episode: 538 training return: tensor(-354.4749, device='cuda:0')
episode: 539 training return: tensor(-497.4643, device='cuda:0')
epoch: 135 test_true_pfm: 1365.962304687623 sim_pfm: -375.3366818438905
episode: 540 training return: tensor(-357.5305, device='cuda:0')
episode: 541 training return: tensor(-456.4501, device='cuda:0')
episode: 542 training return: tensor(-330.9631, device='cuda:0')
episode: 543 training return: tensor(-462.2555, device='cuda:0')
epoch: 136 test_true_pfm: 1604.4142707600088 sim_pfm: -365.04258621359867
episode: 544 training return: tensor(-263.1748, device='cuda:0')
episode: 545 training return: tensor(-453.6156, device='cuda:0')
episode: 546 training return: tensor(-380.7770, device='cuda:0')
episode: 547 training return: tensor(-453.8359, device='cuda:0')
epoch: 137 test_true_pfm: 1701.3291907176917 sim_pfm: -280.6409986068805
episode: 548 training return: tensor(-338.8475, device='cuda:0')
episode: 549 training return: tensor(-455.1827, device='cuda:0')
episode: 550 training return: tensor(-256.0020, device='cuda:0')
episode: 551 training return: tensor(-282.1714, device='cuda:0')
epoch: 138 test_true_pfm: 1373.3233615319277 sim_pfm: -360.6562395657723
episode: 552 training return: tensor(-427.8129, device='cuda:0')
episode: 553 training return: tensor(-445.6605, device='cuda:0')
episode: 554 training return: tensor(-412.5767, device='cuda:0')
episode: 555 training return: tensor(-430.4418, device='cuda:0')
epoch: 139 test_true_pfm: 1331.1898486668176 sim_pfm: -429.6082061324075
episode: 556 training return: tensor(-441.3260, device='cuda:0')
episode: 557 training return: tensor(-418.0791, device='cuda:0')
episode: 558 training return: tensor(-347.9348, device='cuda:0')
episode: 559 training return: tensor(-493.7510, device='cuda:0')
epoch: 140 test_true_pfm: 1378.2742224136812 sim_pfm: -383.2491604066454
episode: 560 training return: tensor(-474.3471, device='cuda:0')
episode: 561 training return: tensor(-388.6584, device='cuda:0')
episode: 562 training return: tensor(-362.8780, device='cuda:0')
episode: 563 training return: tensor(-463.0302, device='cuda:0')
epoch: 141 test_true_pfm: 1409.2518144503772 sim_pfm: -433.02452283356496
episode: 564 training return: tensor(-457.7207, device='cuda:0')
episode: 565 training return: tensor(-352.2116, device='cuda:0')
episode: 566 training return: tensor(-422.6141, device='cuda:0')
episode: 567 training return: tensor(-432.4250, device='cuda:0')
epoch: 142 test_true_pfm: 1529.4153089202446 sim_pfm: -378.6639180717369
episode: 568 training return: tensor(-425.1191, device='cuda:0')
episode: 569 training return: tensor(-484.3883, device='cuda:0')
episode: 570 training return: tensor(-304.0363, device='cuda:0')
episode: 571 training return: tensor(-259.7338, device='cuda:0')
epoch: 143 test_true_pfm: 1834.9464881085125 sim_pfm: -120.75756010878831
episode: 572 training return: tensor(-422.0453, device='cuda:0')
episode: 573 training return: tensor(-412.4524, device='cuda:0')
episode: 574 training return: tensor(-439.4955, device='cuda:0')
episode: 575 training return: tensor(-451.1754, device='cuda:0')
epoch: 144 test_true_pfm: 1541.3244575354818 sim_pfm: -302.3033573233988
episode: 576 training return: tensor(-457.6854, device='cuda:0')
episode: 577 training return: tensor(-309.0773, device='cuda:0')
episode: 578 training return: tensor(-445.6688, device='cuda:0')
episode: 579 training return: tensor(-461.4289, device='cuda:0')
epoch: 145 test_true_pfm: 1312.7301687354272 sim_pfm: -431.1015947274864
episode: 580 training return: tensor(-374.6198, device='cuda:0')
episode: 581 training return: tensor(-269.5161, device='cuda:0')
episode: 582 training return: tensor(-353.2904, device='cuda:0')
episode: 583 training return: tensor(-456.6037, device='cuda:0')
epoch: 146 test_true_pfm: 1388.3321816225991 sim_pfm: -385.431207427755
episode: 584 training return: tensor(-473.0143, device='cuda:0')
episode: 585 training return: tensor(-448.7782, device='cuda:0')
episode: 586 training return: tensor(-446.5797, device='cuda:0')
episode: 587 training return: tensor(-331.4617, device='cuda:0')
epoch: 147 test_true_pfm: 1341.6879246221238 sim_pfm: -418.9578678778101
episode: 588 training return: tensor(-453.2254, device='cuda:0')
episode: 589 training return: tensor(-381.9344, device='cuda:0')
episode: 590 training return: tensor(-112.3005, device='cuda:0')
episode: 591 training return: tensor(-458.8483, device='cuda:0')
epoch: 148 test_true_pfm: 1392.663577393653 sim_pfm: -376.25735651950043
episode: 592 training return: tensor(-388.8973, device='cuda:0')
episode: 593 training return: tensor(-436.9465, device='cuda:0')
episode: 594 training return: tensor(-429.5678, device='cuda:0')
episode: 595 training return: tensor(-474.0742, device='cuda:0')
epoch: 149 test_true_pfm: 1450.8365292313076 sim_pfm: -382.96863304264843
episode: 596 training return: tensor(-419.5433, device='cuda:0')
episode: 597 training return: tensor(-400.0410, device='cuda:0')
episode: 598 training return: tensor(-392.5923, device='cuda:0')
episode: 599 training return: tensor(-272.9005, device='cuda:0')
epoch: 150 test_true_pfm: 1698.4718173561416 sim_pfm: -260.04447502518696
