['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '4', '--data', '3000']
epoch: 0 training_loss 0.25520966231822967 test_loss: 0.10116450786590576
epoch: 1 training_loss 0.20370854675769806 test_loss: 0.09382543563842774
epoch: 2 training_loss 0.19742414176464082 test_loss: 0.09346804022789001
epoch: 3 training_loss 0.19032965317368508 test_loss: 0.09307878613471984
epoch: 4 training_loss 0.18706557095050813 test_loss: 0.0889914333820343
epoch: 5 training_loss 0.1846512421965599 test_loss: 0.09138266444206238
epoch: 6 training_loss 0.17662342093884945 test_loss: 0.08674193024635315
epoch: 7 training_loss 0.1808213111758232 test_loss: 0.09329965710639954
epoch: 8 training_loss 0.18171367540955544 test_loss: 0.09182148575782775
epoch: 9 training_loss 0.19003395214676858 test_loss: 0.09726915359497071
epoch: 10 training_loss 0.1791874285787344 test_loss: 0.09538652300834656
epoch: 11 training_loss 0.17411606945097446 test_loss: 0.09152130484580993
epoch: 12 training_loss 0.18209991939365863 test_loss: 0.09081576466560363
epoch: 13 training_loss 0.17728730194270612 test_loss: 0.09332609176635742
epoch: 14 training_loss 0.17842540815472602 test_loss: 0.09133756160736084
epoch: 15 training_loss 0.18114670060575008 test_loss: 0.09640680551528931
epoch: 16 training_loss 0.17218653053045274 test_loss: 0.09202921390533447
epoch: 17 training_loss 0.17450256533920766 test_loss: 0.09235053062438965
epoch: 18 training_loss 0.16732952520251274 test_loss: 0.09556507468223571
epoch: 19 training_loss 0.16996715046465397 test_loss: 0.09150056838989258
epoch: 20 training_loss 0.17632269896566868 test_loss: 0.09215678572654724
epoch: 21 training_loss 0.1699801652878523 test_loss: 0.09102843403816223
epoch: 22 training_loss 0.16857424043118954 test_loss: 0.09224656224250793
epoch: 23 training_loss 0.17048234306275845 test_loss: 0.091989403963089
epoch: 24 training_loss 0.172799461632967 test_loss: 0.09138062596321106
epoch: 25 training_loss 0.1766593647748232 test_loss: 0.0928175389766693
epoch: 26 training_loss 0.16652634032070637 test_loss: 0.09138619899749756
epoch: 27 training_loss 0.17884560845792294 test_loss: 0.09057155847549439
epoch: 28 training_loss 0.17596844516694546 test_loss: 0.09371973276138305
epoch: 29 training_loss 0.17026923932135105 test_loss: 0.09432343244552613
epoch: 30 training_loss 0.173893451616168 test_loss: 0.09142830967903137
epoch: 31 training_loss 0.1671599069982767 test_loss: 0.09773555994033814
epoch: 32 training_loss 0.17078415207564832 test_loss: 0.09858962893486023
epoch: 33 training_loss 0.1727598513662815 test_loss: 0.09111313223838806
epoch: 34 training_loss 0.17117023669183254 test_loss: 0.09760447740554809
epoch: 35 training_loss 0.16528296694159508 test_loss: 0.09918320775032044
epoch: 36 training_loss 0.16533556070178748 test_loss: 0.0992009162902832
epoch: 37 training_loss 0.16420914515852927 test_loss: 0.09719055891036987
epoch: 38 training_loss 0.16269099861383438 test_loss: 0.09470677375793457
epoch: 39 training_loss 0.15880498439073562 test_loss: 0.09125632047653198
epoch: 40 training_loss 0.173913089632988 test_loss: 0.09812950491905212
epoch: 41 training_loss 0.1648243624716997 test_loss: 0.09470086097717285
epoch: 42 training_loss 0.17190187565982343 test_loss: 0.09492489099502563
epoch: 43 training_loss 0.16623564191162588 test_loss: 0.09134178757667541
epoch: 44 training_loss 0.16591823272407055 test_loss: 0.09574846625328064
epoch: 45 training_loss 0.15854978546500206 test_loss: 0.10038771629333496
epoch: 46 training_loss 0.16081553153693676 test_loss: 0.1007953405380249
epoch: 47 training_loss 0.16234537720680237 test_loss: 0.09880058765411377
epoch: 48 training_loss 0.16628843180835248 test_loss: 0.09305369853973389
epoch: 49 training_loss 0.1496709981560707 test_loss: 0.09421658515930176
epoch: 50 training_loss 0.1588141417503357 test_loss: 0.09604448676109315
epoch: 51 training_loss 0.15929341576993467 test_loss: 0.09493736028671265
epoch: 52 training_loss 0.15444984704256057 test_loss: 0.0952660858631134
epoch: 53 training_loss 0.16099044993519784 test_loss: 0.09537612795829772
epoch: 54 training_loss 0.1580312418937683 test_loss: 0.09638514518737792
epoch: 55 training_loss 0.15819732800126077 test_loss: 0.09545783400535583
epoch: 56 training_loss 0.16170150093734265 test_loss: 0.09628723859786988
epoch: 57 training_loss 0.16146001614630223 test_loss: 0.09788976907730103
epoch: 58 training_loss 0.1566328564286232 test_loss: 0.09887479543685913
epoch: 59 training_loss 0.15578587897121907 test_loss: 0.10021952390670777
epoch: 60 training_loss 0.1512682317942381 test_loss: 0.10127713680267333
epoch: 61 training_loss 0.15883418798446655 test_loss: 0.10463775396347046
epoch: 62 training_loss 0.1603995855897665 test_loss: 0.09893088936805725
epoch: 63 training_loss 0.15180771365761758 test_loss: 0.09768656492233277
epoch: 64 training_loss 0.15759024575352668 test_loss: 0.10011636018753052
epoch: 65 training_loss 0.15429996084421874 test_loss: 0.1006844162940979
epoch: 66 training_loss 0.1475547958537936 test_loss: 0.0963750958442688
epoch: 67 training_loss 0.15898332983255387 test_loss: 0.10048433542251586
epoch: 68 training_loss 0.15364985845983029 test_loss: 0.10026886463165283
epoch: 69 training_loss 0.14783539764583112 test_loss: 0.10509706735610962
epoch: 70 training_loss 0.1503606431186199 test_loss: 0.10430330038070679
epoch: 71 training_loss 0.14538274690508843 test_loss: 0.10326138734817505
epoch: 72 training_loss 0.14246460892260074 test_loss: 0.10842877626419067
epoch: 73 training_loss 0.14742225244641305 test_loss: 0.11111533641815186
epoch: 74 training_loss 0.14219171032309533 test_loss: 0.10698583126068115
epoch: 75 training_loss 0.14351899776607752 test_loss: 0.09997128844261169
epoch: 76 training_loss 0.13705467898398638 test_loss: 0.10052366256713867
epoch: 77 training_loss 0.14669446811079978 test_loss: 0.10734032392501831
epoch: 78 training_loss 0.14380031354725362 test_loss: 0.10285658836364746
epoch: 79 training_loss 0.1409205761551857 test_loss: 0.11356112957000733
epoch: 80 training_loss 0.13601924382150174 test_loss: 0.11293253898620606
epoch: 81 training_loss 0.13796866539865732 test_loss: 0.10704452991485595
epoch: 82 training_loss 0.1342187685519457 test_loss: 0.11287999153137207
epoch: 83 training_loss 0.13177166055887937 test_loss: 0.11334826946258544
epoch: 84 training_loss 0.13727297019213439 test_loss: 0.11633977890014649
epoch: 85 training_loss 0.14578015483915807 test_loss: 0.10576740503311158
epoch: 86 training_loss 0.13655115261673928 test_loss: 0.10968445539474488
epoch: 87 training_loss 0.1337734770029783 test_loss: 0.10827220678329467
epoch: 88 training_loss 0.12586300797760486 test_loss: 0.11359198093414306
epoch: 89 training_loss 0.1352270876429975 test_loss: 0.11095448732376098
epoch: 90 training_loss 0.13970696546137332 test_loss: 0.10997873544692993
epoch: 91 training_loss 0.1239189551025629 test_loss: 0.10680932998657226
epoch: 92 training_loss 0.12780949108302594 test_loss: 0.11344442367553711
epoch: 93 training_loss 0.1378518656641245 test_loss: 0.10889205932617188
epoch: 94 training_loss 0.13690163254737853 test_loss: 0.11486828327178955
epoch: 95 training_loss 0.13502413861453533 test_loss: 0.11508926153182983
epoch: 96 training_loss 0.13126309044659137 test_loss: 0.1107375144958496
epoch: 97 training_loss 0.1276698412746191 test_loss: 0.1253404974937439
epoch: 98 training_loss 0.13614898279309273 test_loss: 0.11783097982406616
epoch: 99 training_loss 0.1220812764391303 test_loss: 0.12028168439865113
epoch: 100 training_loss 0.1274599277228117 test_loss: 0.12010869979858399
epoch: 101 training_loss 0.13267073832452297 test_loss: 0.11145670413970947
epoch: 102 training_loss 0.1301484454423189 test_loss: 0.11686400175094605
epoch: 103 training_loss 0.12475544784218073 test_loss: 0.1180822491645813
epoch: 104 training_loss 0.1216397710889578 test_loss: 0.11563652753829956
epoch: 105 training_loss 0.1286599899828434 test_loss: 0.11308821439743041
epoch: 106 training_loss 0.12484388999640941 test_loss: 0.12211390733718872
epoch: 107 training_loss 0.1224774444103241 test_loss: 0.12327592372894287
epoch: 108 training_loss 0.1200258495286107 test_loss: 0.12611271142959596
epoch: 109 training_loss 0.1111908315680921 test_loss: 0.12490577697753906
epoch: 110 training_loss 0.11900505527853966 test_loss: 0.12496380805969239
epoch: 111 training_loss 0.1158713062480092 test_loss: 0.11998131275177001
epoch: 112 training_loss 0.11341182727366686 test_loss: 0.12489569187164307
epoch: 113 training_loss 0.11255461655557156 test_loss: 0.14404963254928588
epoch: 114 training_loss 0.11118411764502525 test_loss: 0.14021991491317748
epoch: 115 training_loss 0.10776323601603507 test_loss: 0.1331459879875183
epoch: 116 training_loss 0.11104627452790737 test_loss: 0.13625482320785523
epoch: 117 training_loss 0.11196031454950571 test_loss: 0.12800204753875732
epoch: 118 training_loss 0.10641940981149674 test_loss: 0.13301842212677
epoch: 119 training_loss 0.10889846917241812 test_loss: 0.14401508569717408
epoch: 120 training_loss 0.1064969409815967 test_loss: 0.14496546983718872
epoch: 121 training_loss 0.10495718725025655 test_loss: 0.148714816570282
epoch: 122 training_loss 0.09644510179758072 test_loss: 0.14875261783599852
epoch: 123 training_loss 0.09730410594493151 test_loss: 0.14143656492233275
epoch: 124 training_loss 0.10551885314285755 test_loss: 0.14056395292282103
epoch: 125 training_loss 0.10270612675696611 test_loss: 0.14412279129028321
epoch: 126 training_loss 0.09102817993611097 test_loss: 0.14106634855270386
epoch: 127 training_loss 0.09645060710608959 test_loss: 0.15158947706222534
epoch: 128 training_loss 0.09653702083975077 test_loss: 0.14609383344650267
epoch: 129 training_loss 0.0983337390422821 test_loss: 0.15507063865661622
epoch: 130 training_loss 0.09449433725327254 test_loss: 0.1580992341041565
epoch: 131 training_loss 0.08590954329818487 test_loss: 0.13820592164993287
epoch: 132 training_loss 0.09628498813137412 test_loss: 0.14342557191848754
epoch: 133 training_loss 0.08686677142977714 test_loss: 0.1544480323791504
epoch: 134 training_loss 0.08740755666047334 test_loss: 0.14210309982299804
epoch: 135 training_loss 0.0820060962997377 test_loss: 0.1433052897453308
epoch: 136 training_loss 0.09369617585092783 test_loss: 0.15517337322235109
epoch: 137 training_loss 0.07961565060541034 test_loss: 0.16423988342285156
epoch: 138 training_loss 0.08295806447044014 test_loss: 0.1598174452781677
epoch: 139 training_loss 0.0869466246291995 test_loss: 0.16085472106933593
epoch: 140 training_loss 0.08333890445530415 test_loss: 0.15991066694259642
epoch: 141 training_loss 0.07813282208517194 test_loss: 0.16198618412017823
epoch: 142 training_loss 0.07838520092889667 test_loss: 0.16257385015487671
epoch: 143 training_loss 0.07791957071051002 test_loss: 0.1601828455924988
epoch: 144 training_loss 0.07188094021752477 test_loss: 0.16819214820861816
epoch: 145 training_loss 0.07648726908490061 test_loss: 0.16262882947921753
epoch: 146 training_loss 0.0744983945414424 test_loss: 0.16668176651000977
epoch: 147 training_loss 0.07689441626891494 test_loss: 0.173794424533844
epoch: 148 training_loss 0.06766275374218822 test_loss: 0.16856598854064941
epoch: 149 training_loss 0.07893954252824187 test_loss: 0.17070070505142212
epoch: 0 training_loss 9.56849462032318 test_loss: 2.5998760223388673
epoch: 1 training_loss 4.425135133266449 test_loss: 1.6138200759887695
epoch: 2 training_loss 2.966247899532318 test_loss: 1.2009108543395997
epoch: 3 training_loss 2.2977752161026 test_loss: 0.9692337989807129
epoch: 4 training_loss 1.8790003395080566 test_loss: 0.8329227447509766
epoch: 5 training_loss 1.6600136649608612 test_loss: 0.7525527954101563
epoch: 6 training_loss 1.5116664016246795 test_loss: 0.6864623069763184
epoch: 7 training_loss 1.3864461398124694 test_loss: 0.6495209217071534
epoch: 8 training_loss 1.2766890406608582 test_loss: 0.6082676887512207
epoch: 9 training_loss 1.1897550535202026 test_loss: 0.5718284606933594
epoch: 10 training_loss 1.151811692714691 test_loss: 0.5420734405517578
epoch: 11 training_loss 1.0828401392698288 test_loss: 0.5157050609588623
epoch: 12 training_loss 1.056330679655075 test_loss: 0.5009108066558838
epoch: 13 training_loss 1.0191513139009476 test_loss: 0.48402581214904783
epoch: 14 training_loss 0.969566992521286 test_loss: 0.47333493232727053
epoch: 15 training_loss 0.9553936266899109 test_loss: 0.4573707580566406
epoch: 16 training_loss 0.925064034461975 test_loss: 0.4464268207550049
epoch: 17 training_loss 0.9127291417121888 test_loss: 0.43296208381652834
epoch: 18 training_loss 0.8793831312656403 test_loss: 0.4240452766418457
epoch: 19 training_loss 0.8503478091955184 test_loss: 0.43604426383972167
epoch: 20 training_loss 0.8393321228027344 test_loss: 0.42391486167907716
epoch: 21 training_loss 0.8410287100076675 test_loss: 0.40404505729675294
epoch: 22 training_loss 0.8151055151224136 test_loss: 0.40661144256591797
epoch: 23 training_loss 0.7938402765989303 test_loss: 0.39323503971099855
epoch: 24 training_loss 0.7939688074588775 test_loss: 0.39062635898590087
epoch: 25 training_loss 0.7736223393678665 test_loss: 0.38701767921447755
epoch: 26 training_loss 0.7768554335832596 test_loss: 0.37952699661254885
epoch: 27 training_loss 0.754613026380539 test_loss: 0.3685486316680908
epoch: 28 training_loss 0.7380653578042984 test_loss: 0.38028504848480227
epoch: 29 training_loss 0.7439858937263488 test_loss: 0.364793586730957
epoch: 30 training_loss 0.7309629058837891 test_loss: 0.3681023120880127
epoch: 31 training_loss 0.719202111363411 test_loss: 0.35842645168304443
epoch: 32 training_loss 0.7196435290575027 test_loss: 0.3577486276626587
epoch: 33 training_loss 0.7084286004304886 test_loss: 0.3529313325881958
epoch: 34 training_loss 0.6903028953075409 test_loss: 0.3496809482574463
epoch: 35 training_loss 0.7061111229658127 test_loss: 0.37757372856140137
epoch: 36 training_loss 0.6966717493534088 test_loss: 0.3385604381561279
epoch: 37 training_loss 0.6840858405828476 test_loss: 0.3434509038925171
epoch: 38 training_loss 0.6776474553346634 test_loss: 0.34164421558380126
epoch: 39 training_loss 0.6775151842832565 test_loss: 0.3395676851272583
epoch: 40 training_loss 0.6647778344154358 test_loss: 0.3366447925567627
epoch: 41 training_loss 0.6598564678430557 test_loss: 0.3232020616531372
epoch: 42 training_loss 0.645948514342308 test_loss: 0.323742413520813
epoch: 43 training_loss 0.6493912649154663 test_loss: 0.3214291572570801
epoch: 44 training_loss 0.6386638224124909 test_loss: 0.32281558513641356
epoch: 45 training_loss 0.6418988120555877 test_loss: 0.3183748245239258
epoch: 46 training_loss 0.6517807173728943 test_loss: 0.327449369430542
epoch: 47 training_loss 0.6319200026988984 test_loss: 0.31336510181427
epoch: 48 training_loss 0.6242820596694947 test_loss: 0.3115678310394287
epoch: 49 training_loss 0.6260372579097748 test_loss: 0.3076659679412842
epoch: 50 training_loss 0.6226525133848191 test_loss: 0.30581817626953123
epoch: 51 training_loss 0.6085196304321289 test_loss: 0.31094751358032224
epoch: 52 training_loss 0.6228870111703873 test_loss: 0.3288299560546875
epoch: 53 training_loss 0.6117424923181534 test_loss: 0.30129940509796144
epoch: 54 training_loss 0.6066819417476654 test_loss: 0.3078444480895996
epoch: 55 training_loss 0.6134405732154846 test_loss: 0.2985291719436646
epoch: 56 training_loss 0.5947291225194931 test_loss: 0.3061843395233154
epoch: 57 training_loss 0.6062384355068207 test_loss: 0.30782973766326904
epoch: 58 training_loss 0.608474452495575 test_loss: 0.2961691617965698
epoch: 59 training_loss 0.5788773429393769 test_loss: 0.30075411796569823
epoch: 60 training_loss 0.6027616649866104 test_loss: 0.291115403175354
epoch: 61 training_loss 0.582603143453598 test_loss: 0.29126548767089844
epoch: 62 training_loss 0.5922452008724213 test_loss: 0.2929529190063477
epoch: 63 training_loss 0.576465682387352 test_loss: 0.2954581260681152
epoch: 64 training_loss 0.587916345000267 test_loss: 0.2939003467559814
epoch: 65 training_loss 0.5805978918075562 test_loss: 0.29329533576965333
epoch: 66 training_loss 0.579407725930214 test_loss: 0.28800809383392334
epoch: 67 training_loss 0.575836210846901 test_loss: 0.2864335536956787
epoch: 68 training_loss 0.567622361779213 test_loss: 0.30705320835113525
epoch: 69 training_loss 0.5829367458820343 test_loss: 0.28678529262542723
epoch: 70 training_loss 0.5617487463355064 test_loss: 0.29038980007171633
epoch: 71 training_loss 0.5674555104970932 test_loss: 0.2887056589126587
epoch: 72 training_loss 0.5683402702212333 test_loss: 0.28621060848236085
epoch: 73 training_loss 0.5653425866365432 test_loss: 0.2791292190551758
epoch: 74 training_loss 0.560300703048706 test_loss: 0.2839240550994873
epoch: 75 training_loss 0.5641208690404892 test_loss: 0.28567681312561033
epoch: 76 training_loss 0.5584141871333123 test_loss: 0.28028135299682616
epoch: 77 training_loss 0.5623518800735474 test_loss: 0.2846315622329712
epoch: 78 training_loss 0.5498402273654938 test_loss: 0.28462278842926025
epoch: 79 training_loss 0.562084813117981 test_loss: 0.28412301540374757
epoch: 80 training_loss 0.5500362458825111 test_loss: 0.27735798358917235
epoch: 81 training_loss 0.5437857258319855 test_loss: 0.28535850048065187
epoch: 82 training_loss 0.5605902516841889 test_loss: 0.27784018516540526
epoch: 83 training_loss 0.5475601598620414 test_loss: 0.2803088665008545
epoch: 84 training_loss 0.540049766600132 test_loss: 0.27259149551391604
epoch: 85 training_loss 0.5449649465084075 test_loss: 0.27022249698638917
epoch: 86 training_loss 0.5423851373791695 test_loss: 0.27240452766418455
epoch: 87 training_loss 0.5423353639245033 test_loss: 0.2772470235824585
epoch: 88 training_loss 0.5509370279312134 test_loss: 0.27151339054107665
epoch: 89 training_loss 0.5344860559701919 test_loss: 0.2767076015472412
epoch: 90 training_loss 0.5487406438589096 test_loss: 0.27118966579437254
epoch: 91 training_loss 0.5349488401412964 test_loss: 0.2970318078994751
epoch: 92 training_loss 0.5312076964974404 test_loss: 0.26799066066741944
epoch: 93 training_loss 0.550250218808651 test_loss: 0.2832261800765991
epoch: 94 training_loss 0.5392615547776223 test_loss: 0.27106831073760984
epoch: 95 training_loss 0.5236982515454293 test_loss: 0.2682470798492432
epoch: 96 training_loss 0.5233708330988884 test_loss: 0.277207088470459
epoch: 97 training_loss 0.5246339443325997 test_loss: 0.2659489393234253
epoch: 98 training_loss 0.5330175170302391 test_loss: 0.2774440050125122
epoch: 99 training_loss 0.5278619676828384 test_loss: 0.2655292510986328
epoch: 100 training_loss 0.5200351625680923 test_loss: 0.26559398174285886
epoch: 101 training_loss 0.5285642391443253 test_loss: 0.2661142826080322
epoch: 102 training_loss 0.5202298554778099 test_loss: 0.2640981197357178
epoch: 103 training_loss 0.5289011490345001 test_loss: 0.2651794910430908
epoch: 104 training_loss 0.5276013562083244 test_loss: 0.27136328220367434
epoch: 105 training_loss 0.5306513178348541 test_loss: 0.2579846143722534
epoch: 106 training_loss 0.5209655967354775 test_loss: 0.26231744289398196
epoch: 107 training_loss 0.5242924082279206 test_loss: 0.2616302013397217
epoch: 108 training_loss 0.5168369147181511 test_loss: 0.26137940883636473
epoch: 109 training_loss 0.5189987325668335 test_loss: 0.26769835948944093
epoch: 110 training_loss 0.5257453465461731 test_loss: 0.277325177192688
epoch: 111 training_loss 0.5157351517677307 test_loss: 0.26131319999694824
epoch: 112 training_loss 0.524252741932869 test_loss: 0.2738654375076294
epoch: 113 training_loss 0.5026212072372437 test_loss: 0.25550060272216796
epoch: 114 training_loss 0.5239962977170944 test_loss: 0.26643445491790774
epoch: 115 training_loss 0.5107559421658516 test_loss: 0.2575176954269409
epoch: 116 training_loss 0.5044473683834076 test_loss: 0.25779118537902834
epoch: 117 training_loss 0.5130435130000115 test_loss: 0.2567862033843994
epoch: 118 training_loss 0.5103163760900498 test_loss: 0.2547802448272705
epoch: 119 training_loss 0.5054243722558022 test_loss: 0.2555164575576782
epoch: 120 training_loss 0.504357850253582 test_loss: 0.2567834615707397
epoch: 121 training_loss 0.5143298554420471 test_loss: 0.26099252700805664
epoch: 122 training_loss 0.5136361557245255 test_loss: 0.25026142597198486
epoch: 123 training_loss 0.50223975867033 test_loss: 0.25675551891326903
epoch: 124 training_loss 0.5052139872312545 test_loss: 0.2527614593505859
epoch: 125 training_loss 0.5054883438348771 test_loss: 0.25540544986724856
epoch: 126 training_loss 0.4999241265654564 test_loss: 0.25927884578704835
epoch: 127 training_loss 0.4943484953045845 test_loss: 0.2551776170730591
epoch: 128 training_loss 0.4998000806570053 test_loss: 0.2750441074371338
epoch: 129 training_loss 0.5021294304728507 test_loss: 0.2495363473892212
epoch: 130 training_loss 0.49378574162721633 test_loss: 0.2545109033584595
epoch: 131 training_loss 0.49902709662914274 test_loss: 0.248962140083313
epoch: 132 training_loss 0.5001887747645378 test_loss: 0.25349905490875246
epoch: 133 training_loss 0.497962581217289 test_loss: 0.2514551877975464
epoch: 134 training_loss 0.49651823490858077 test_loss: 0.2539623022079468
epoch: 135 training_loss 0.5012563946843147 test_loss: 0.24757862091064453
epoch: 136 training_loss 0.503485010266304 test_loss: 0.2653858184814453
epoch: 137 training_loss 0.5034595263004303 test_loss: 0.26144793033599856
epoch: 138 training_loss 0.4944131705164909 test_loss: 0.2466059446334839
epoch: 139 training_loss 0.49242882430553436 test_loss: 0.24725720882415772
epoch: 140 training_loss 0.49707485616207125 test_loss: 0.2568276643753052
epoch: 141 training_loss 0.4937029603123665 test_loss: 0.24882020950317382
epoch: 142 training_loss 0.4816660219430923 test_loss: 0.25624966621398926
epoch: 143 training_loss 0.4936534401774406 test_loss: 0.2486701488494873
epoch: 144 training_loss 0.48813948422670367 test_loss: 0.2522813081741333
epoch: 145 training_loss 0.49577373325824736 test_loss: 0.246100115776062
epoch: 146 training_loss 0.4922352406382561 test_loss: 0.24252138137817383
epoch: 147 training_loss 0.48411042243242264 test_loss: 0.24698362350463868
epoch: 148 training_loss 0.4878114467859268 test_loss: 0.2485874652862549
epoch: 149 training_loss 0.4830639761686325 test_loss: 0.24201276302337646
1765.291351561348
episode: 0 training return: tensor(-24.2377, device='cuda:0')
episode: 1 training return: tensor(9.6254, device='cuda:0')
episode: 2 training return: tensor(12.6997, device='cuda:0')
episode: 3 training return: tensor(-99.0025, device='cuda:0')
epoch: 1 test_true_pfm: 1921.6159110370393 sim_pfm: -177.29498295804174
episode: 4 training return: tensor(55.0831, device='cuda:0')
episode: 5 training return: tensor(-93.5466, device='cuda:0')
episode: 6 training return: tensor(-178.9219, device='cuda:0')
episode: 7 training return: tensor(-185.1184, device='cuda:0')
epoch: 2 test_true_pfm: 1644.6799314710022 sim_pfm: -170.6321579706855
episode: 8 training return: tensor(-93.5852, device='cuda:0')
episode: 9 training return: tensor(-262.9556, device='cuda:0')
episode: 10 training return: tensor(171.5906, device='cuda:0')
episode: 11 training return: tensor(-81.4891, device='cuda:0')
epoch: 3 test_true_pfm: 1725.6931837923457 sim_pfm: -129.1743023848782
episode: 12 training return: tensor(-23.0224, device='cuda:0')
episode: 13 training return: tensor(-177.7247, device='cuda:0')
episode: 14 training return: tensor(95.8940, device='cuda:0')
episode: 15 training return: tensor(43.7357, device='cuda:0')
epoch: 4 test_true_pfm: 1473.5994543952672 sim_pfm: -57.05730351234282
episode: 16 training return: tensor(52.5371, device='cuda:0')
episode: 17 training return: tensor(-6.3036, device='cuda:0')
episode: 18 training return: tensor(138.9662, device='cuda:0')
episode: 19 training return: tensor(-81.4831, device='cuda:0')
epoch: 5 test_true_pfm: 1419.1936556009634 sim_pfm: -237.04371169532533
episode: 20 training return: tensor(16.7418, device='cuda:0')
episode: 21 training return: tensor(-118.1656, device='cuda:0')
episode: 22 training return: tensor(148.5298, device='cuda:0')
episode: 23 training return: tensor(-134.6564, device='cuda:0')
epoch: 6 test_true_pfm: 2029.7588611345718 sim_pfm: -124.16323571812245
episode: 24 training return: tensor(68.0345, device='cuda:0')
episode: 25 training return: tensor(-157.3769, device='cuda:0')
episode: 26 training return: tensor(166.1923, device='cuda:0')
episode: 27 training return: tensor(-125.7262, device='cuda:0')
epoch: 7 test_true_pfm: 1624.8257615052914 sim_pfm: -88.02821337844944
episode: 28 training return: tensor(-72.8039, device='cuda:0')
episode: 29 training return: tensor(-145.3096, device='cuda:0')
episode: 30 training return: tensor(-159.4996, device='cuda:0')
episode: 31 training return: tensor(-234.2082, device='cuda:0')
epoch: 8 test_true_pfm: 1644.523524790419 sim_pfm: -32.80033758034309
episode: 32 training return: tensor(-85.1465, device='cuda:0')
episode: 33 training return: tensor(-58.5727, device='cuda:0')
episode: 34 training return: tensor(118.3125, device='cuda:0')
episode: 35 training return: tensor(66.7228, device='cuda:0')
epoch: 9 test_true_pfm: 1812.826011328452 sim_pfm: 172.55337202061978
episode: 36 training return: tensor(278.8750, device='cuda:0')
episode: 37 training return: tensor(435.8632, device='cuda:0')
episode: 38 training return: tensor(14.2361, device='cuda:0')
episode: 39 training return: tensor(346.8188, device='cuda:0')
epoch: 10 test_true_pfm: 1791.7983420040157 sim_pfm: -99.83705254795495
episode: 40 training return: tensor(-5.1710, device='cuda:0')
episode: 41 training return: tensor(-51.1407, device='cuda:0')
episode: 42 training return: tensor(66.8264, device='cuda:0')
episode: 43 training return: tensor(-57.5793, device='cuda:0')
epoch: 11 test_true_pfm: 1948.7886428494505 sim_pfm: -124.87531629240645
episode: 44 training return: tensor(-35.9201, device='cuda:0')
episode: 45 training return: tensor(188.8079, device='cuda:0')
episode: 46 training return: tensor(-60.9118, device='cuda:0')
episode: 47 training return: tensor(69.8751, device='cuda:0')
epoch: 12 test_true_pfm: 2505.292093512078 sim_pfm: 125.44768741671578
episode: 48 training return: tensor(57.3105, device='cuda:0')
episode: 49 training return: tensor(-47.7548, device='cuda:0')
episode: 50 training return: tensor(-69.3337, device='cuda:0')
episode: 51 training return: tensor(308.1466, device='cuda:0')
epoch: 13 test_true_pfm: 2331.5522460924954 sim_pfm: -79.70649612710501
episode: 52 training return: tensor(-49.2625, device='cuda:0')
episode: 53 training return: tensor(-37.8098, device='cuda:0')
episode: 54 training return: tensor(72.2806, device='cuda:0')
episode: 55 training return: tensor(-69.9004, device='cuda:0')
epoch: 14 test_true_pfm: 2476.2846117245017 sim_pfm: 138.3361018979243
episode: 56 training return: tensor(216.1344, device='cuda:0')
episode: 57 training return: tensor(19.7750, device='cuda:0')
episode: 58 training return: tensor(46.7917, device='cuda:0')
episode: 59 training return: tensor(166.1974, device='cuda:0')
epoch: 15 test_true_pfm: 2136.211252532224 sim_pfm: 79.18099281813677
episode: 60 training return: tensor(84.1936, device='cuda:0')
episode: 61 training return: tensor(-80.8718, device='cuda:0')
episode: 62 training return: tensor(86.6310, device='cuda:0')
episode: 63 training return: tensor(0.8639, device='cuda:0')
epoch: 16 test_true_pfm: 2533.116552918406 sim_pfm: 14.759014493242526
episode: 64 training return: tensor(-151.0415, device='cuda:0')
episode: 65 training return: tensor(401.1276, device='cuda:0')
episode: 66 training return: tensor(177.7864, device='cuda:0')
episode: 67 training return: tensor(100.6446, device='cuda:0')
epoch: 17 test_true_pfm: 1606.4773534335957 sim_pfm: 15.464179870827744
episode: 68 training return: tensor(370.9878, device='cuda:0')
episode: 69 training return: tensor(99.0302, device='cuda:0')
episode: 70 training return: tensor(-148.4758, device='cuda:0')
episode: 71 training return: tensor(21.8168, device='cuda:0')
epoch: 18 test_true_pfm: 1966.895198727966 sim_pfm: -146.06752351019531
episode: 72 training return: tensor(-16.0762, device='cuda:0')
episode: 73 training return: tensor(92.7894, device='cuda:0')
episode: 74 training return: tensor(-106.6640, device='cuda:0')
episode: 75 training return: tensor(377.2016, device='cuda:0')
epoch: 19 test_true_pfm: 2000.143389543907 sim_pfm: 129.02855970389405
episode: 76 training return: tensor(-141.9418, device='cuda:0')
episode: 77 training return: tensor(135.5392, device='cuda:0')
episode: 78 training return: tensor(164.7730, device='cuda:0')
episode: 79 training return: tensor(74.5741, device='cuda:0')
epoch: 20 test_true_pfm: 2333.179142515845 sim_pfm: 39.06774652174985
episode: 80 training return: tensor(2.6418, device='cuda:0')
episode: 81 training return: tensor(-53.5092, device='cuda:0')
episode: 82 training return: tensor(-45.0915, device='cuda:0')
episode: 83 training return: tensor(115.2773, device='cuda:0')
epoch: 21 test_true_pfm: 2143.5459317242553 sim_pfm: -96.580602042377
episode: 84 training return: tensor(324.2834, device='cuda:0')
episode: 85 training return: tensor(247.2220, device='cuda:0')
episode: 86 training return: tensor(-53.9949, device='cuda:0')
episode: 87 training return: tensor(-19.0556, device='cuda:0')
epoch: 22 test_true_pfm: 2504.3214748750142 sim_pfm: 202.7512367905389
episode: 88 training return: tensor(-198.3986, device='cuda:0')
episode: 89 training return: tensor(-11.0379, device='cuda:0')
episode: 90 training return: tensor(70.5585, device='cuda:0')
episode: 91 training return: tensor(96.8007, device='cuda:0')
epoch: 23 test_true_pfm: 1837.378190668759 sim_pfm: 101.82147668614441
episode: 92 training return: tensor(-311.8935, device='cuda:0')
episode: 93 training return: tensor(-187.4093, device='cuda:0')
episode: 94 training return: tensor(227.0220, device='cuda:0')
episode: 95 training return: tensor(-139.9129, device='cuda:0')
epoch: 24 test_true_pfm: 1833.8584513672001 sim_pfm: 186.63134786543864
episode: 96 training return: tensor(186.3098, device='cuda:0')
episode: 97 training return: tensor(-108.0256, device='cuda:0')
episode: 98 training return: tensor(-104.1987, device='cuda:0')
episode: 99 training return: tensor(-147.5584, device='cuda:0')
epoch: 25 test_true_pfm: 2494.578967561482 sim_pfm: 79.3787155620812
episode: 100 training return: tensor(-9.7269, device='cuda:0')
episode: 101 training return: tensor(-133.5749, device='cuda:0')
episode: 102 training return: tensor(111.4859, device='cuda:0')
episode: 103 training return: tensor(-3.2787, device='cuda:0')
epoch: 26 test_true_pfm: 2379.959301619982 sim_pfm: 177.1416728324839
episode: 104 training return: tensor(148.2028, device='cuda:0')
episode: 105 training return: tensor(-55.9407, device='cuda:0')
episode: 106 training return: tensor(-62.4348, device='cuda:0')
episode: 107 training return: tensor(379.1465, device='cuda:0')
epoch: 27 test_true_pfm: 2493.160061504955 sim_pfm: 253.03781889524544
episode: 108 training return: tensor(73.6507, device='cuda:0')
episode: 109 training return: tensor(100.6801, device='cuda:0')
episode: 110 training return: tensor(-203.0749, device='cuda:0')
episode: 111 training return: tensor(365.4491, device='cuda:0')
epoch: 28 test_true_pfm: 1862.2691392080997 sim_pfm: -62.83909709332511
episode: 112 training return: tensor(383.9048, device='cuda:0')
episode: 113 training return: tensor(417.0827, device='cuda:0')
episode: 114 training return: tensor(99.2826, device='cuda:0')
episode: 115 training return: tensor(-46.8625, device='cuda:0')
epoch: 29 test_true_pfm: 2219.8657237047905 sim_pfm: 119.07349581738042
episode: 116 training return: tensor(65.9629, device='cuda:0')
episode: 117 training return: tensor(72.8858, device='cuda:0')
episode: 118 training return: tensor(-120.4162, device='cuda:0')
episode: 119 training return: tensor(-38.9143, device='cuda:0')
epoch: 30 test_true_pfm: 2316.8719552420475 sim_pfm: -54.366936332449164
episode: 120 training return: tensor(-54.0699, device='cuda:0')
episode: 121 training return: tensor(-49.6029, device='cuda:0')
episode: 122 training return: tensor(3.9746, device='cuda:0')
episode: 123 training return: tensor(-60.6882, device='cuda:0')
epoch: 31 test_true_pfm: 1905.5133801698682 sim_pfm: -45.435670108534396
episode: 124 training return: tensor(15.1584, device='cuda:0')
episode: 125 training return: tensor(278.7736, device='cuda:0')
episode: 126 training return: tensor(88.8719, device='cuda:0')
episode: 127 training return: tensor(147.7522, device='cuda:0')
epoch: 32 test_true_pfm: 3210.5200630401887 sim_pfm: 58.26300553565185
episode: 128 training return: tensor(-108.4267, device='cuda:0')
episode: 129 training return: tensor(-65.8810, device='cuda:0')
episode: 130 training return: tensor(97.1281, device='cuda:0')
episode: 131 training return: tensor(103.8220, device='cuda:0')
epoch: 33 test_true_pfm: 2815.8737208162947 sim_pfm: -10.391535837979367
episode: 132 training return: tensor(20.6230, device='cuda:0')
episode: 133 training return: tensor(151.6059, device='cuda:0')
episode: 134 training return: tensor(173.3270, device='cuda:0')
episode: 135 training return: tensor(-91.1469, device='cuda:0')
epoch: 34 test_true_pfm: 2206.880328564333 sim_pfm: 130.01493413288458
episode: 136 training return: tensor(-89.4035, device='cuda:0')
episode: 137 training return: tensor(97.1500, device='cuda:0')
episode: 138 training return: tensor(102.7458, device='cuda:0')
episode: 139 training return: tensor(160.1598, device='cuda:0')
epoch: 35 test_true_pfm: 2298.3068353294207 sim_pfm: 154.56623523810413
episode: 140 training return: tensor(39.9498, device='cuda:0')
episode: 141 training return: tensor(22.2561, device='cuda:0')
episode: 142 training return: tensor(123.3366, device='cuda:0')
episode: 143 training return: tensor(167.8697, device='cuda:0')
epoch: 36 test_true_pfm: 2096.274309717763 sim_pfm: 295.3192417399259
episode: 144 training return: tensor(-133.3320, device='cuda:0')
episode: 145 training return: tensor(-34.7112, device='cuda:0')
episode: 146 training return: tensor(68.2524, device='cuda:0')
episode: 147 training return: tensor(88.3089, device='cuda:0')
epoch: 37 test_true_pfm: 1943.8557506548998 sim_pfm: 104.6861006069618
episode: 148 training return: tensor(-58.3501, device='cuda:0')
episode: 149 training return: tensor(-38.9919, device='cuda:0')
episode: 150 training return: tensor(35.4977, device='cuda:0')
episode: 151 training return: tensor(-29.1085, device='cuda:0')
epoch: 38 test_true_pfm: 1850.400602814909 sim_pfm: 107.11452820558527
episode: 152 training return: tensor(88.3736, device='cuda:0')
episode: 153 training return: tensor(154.5280, device='cuda:0')
episode: 154 training return: tensor(-127.4082, device='cuda:0')
episode: 155 training return: tensor(184.2906, device='cuda:0')
epoch: 39 test_true_pfm: 2026.6375181446463 sim_pfm: 260.7870209432731
episode: 156 training return: tensor(159.8292, device='cuda:0')
episode: 157 training return: tensor(114.3496, device='cuda:0')
episode: 158 training return: tensor(-1.8166, device='cuda:0')
episode: 159 training return: tensor(306.1514, device='cuda:0')
epoch: 40 test_true_pfm: 2349.1579841362195 sim_pfm: 162.3910848911813
episode: 160 training return: tensor(-131.8184, device='cuda:0')
episode: 161 training return: tensor(101.7913, device='cuda:0')
episode: 162 training return: tensor(5.7072, device='cuda:0')
episode: 163 training return: tensor(-29.0364, device='cuda:0')
epoch: 41 test_true_pfm: 1993.1332730191532 sim_pfm: 197.0628317624893
episode: 164 training return: tensor(-99.8429, device='cuda:0')
episode: 165 training return: tensor(-37.9101, device='cuda:0')
episode: 166 training return: tensor(371.4007, device='cuda:0')
episode: 167 training return: tensor(48.3707, device='cuda:0')
epoch: 42 test_true_pfm: 1965.2010657819767 sim_pfm: 116.23674713810517
episode: 168 training return: tensor(391.1299, device='cuda:0')
episode: 169 training return: tensor(144.7527, device='cuda:0')
episode: 170 training return: tensor(-31.3372, device='cuda:0')
episode: 171 training return: tensor(104.7872, device='cuda:0')
epoch: 43 test_true_pfm: 1917.0546568719044 sim_pfm: 150.1589952596211
episode: 172 training return: tensor(288.5163, device='cuda:0')
episode: 173 training return: tensor(-6.1266, device='cuda:0')
episode: 174 training return: tensor(242.6714, device='cuda:0')
episode: 175 training return: tensor(362.1709, device='cuda:0')
epoch: 44 test_true_pfm: 2326.453048308393 sim_pfm: -61.95027921845516
episode: 176 training return: tensor(202.5765, device='cuda:0')
episode: 177 training return: tensor(-148.7328, device='cuda:0')
episode: 178 training return: tensor(-42.7995, device='cuda:0')
episode: 179 training return: tensor(80.3176, device='cuda:0')
epoch: 45 test_true_pfm: 2062.1745669904976 sim_pfm: -3.771964470099192
episode: 180 training return: tensor(92.2145, device='cuda:0')
episode: 181 training return: tensor(-11.9359, device='cuda:0')
episode: 182 training return: tensor(24.9572, device='cuda:0')
episode: 183 training return: tensor(-54.6966, device='cuda:0')
epoch: 46 test_true_pfm: 2412.215017034531 sim_pfm: 109.65181964440853
episode: 184 training return: tensor(-44.8036, device='cuda:0')
episode: 185 training return: tensor(223.0981, device='cuda:0')
episode: 186 training return: tensor(20.3262, device='cuda:0')
episode: 187 training return: tensor(133.6668, device='cuda:0')
epoch: 47 test_true_pfm: 2193.2908072312616 sim_pfm: 165.7444790400623
episode: 188 training return: tensor(91.0442, device='cuda:0')
episode: 189 training return: tensor(22.7623, device='cuda:0')
episode: 190 training return: tensor(57.2705, device='cuda:0')
episode: 191 training return: tensor(-25.2075, device='cuda:0')
epoch: 48 test_true_pfm: 1823.3539201807953 sim_pfm: 34.12296702902919
episode: 192 training return: tensor(109.8616, device='cuda:0')
episode: 193 training return: tensor(69.5879, device='cuda:0')
episode: 194 training return: tensor(-14.1659, device='cuda:0')
episode: 195 training return: tensor(84.7001, device='cuda:0')
epoch: 49 test_true_pfm: 1924.1270285635935 sim_pfm: 66.9286207955253
episode: 196 training return: tensor(160.8633, device='cuda:0')
episode: 197 training return: tensor(-10.2571, device='cuda:0')
episode: 198 training return: tensor(25.8611, device='cuda:0')
episode: 199 training return: tensor(7.7394, device='cuda:0')
epoch: 50 test_true_pfm: 2087.093677549939 sim_pfm: 0.9878653681759412
episode: 200 training return: tensor(-104.7741, device='cuda:0')
episode: 201 training return: tensor(222.4146, device='cuda:0')
episode: 202 training return: tensor(91.9432, device='cuda:0')
episode: 203 training return: tensor(-41.1579, device='cuda:0')
epoch: 51 test_true_pfm: 2860.860044788651 sim_pfm: 120.44682968371005
episode: 204 training return: tensor(-124.8031, device='cuda:0')
episode: 205 training return: tensor(-68.8962, device='cuda:0')
episode: 206 training return: tensor(-5.6107, device='cuda:0')
episode: 207 training return: tensor(18.1390, device='cuda:0')
epoch: 52 test_true_pfm: 2009.9584276321011 sim_pfm: -73.88018516697532
episode: 208 training return: tensor(-57.7878, device='cuda:0')
episode: 209 training return: tensor(-23.6159, device='cuda:0')
episode: 210 training return: tensor(345.6688, device='cuda:0')
episode: 211 training return: tensor(-60.2257, device='cuda:0')
epoch: 53 test_true_pfm: 2128.5772690346726 sim_pfm: -0.6907358198659495
episode: 212 training return: tensor(-50.4036, device='cuda:0')
episode: 213 training return: tensor(356.9580, device='cuda:0')
episode: 214 training return: tensor(92.8481, device='cuda:0')
episode: 215 training return: tensor(28.7374, device='cuda:0')
epoch: 54 test_true_pfm: 2253.3126176960636 sim_pfm: 78.80331572552677
episode: 216 training return: tensor(-16.5604, device='cuda:0')
episode: 217 training return: tensor(246.5017, device='cuda:0')
episode: 218 training return: tensor(433.1295, device='cuda:0')
episode: 219 training return: tensor(426.5877, device='cuda:0')
epoch: 55 test_true_pfm: 2901.0437949590246 sim_pfm: 166.89562249858864
episode: 220 training return: tensor(102.0676, device='cuda:0')
episode: 221 training return: tensor(67.6585, device='cuda:0')
episode: 222 training return: tensor(112.1489, device='cuda:0')
episode: 223 training return: tensor(131.1419, device='cuda:0')
epoch: 56 test_true_pfm: 2405.5611872683803 sim_pfm: 143.29035170112425
episode: 224 training return: tensor(289.5191, device='cuda:0')
episode: 225 training return: tensor(59.3512, device='cuda:0')
episode: 226 training return: tensor(-75.4987, device='cuda:0')
episode: 227 training return: tensor(-120.3055, device='cuda:0')
epoch: 57 test_true_pfm: 2409.5402343984256 sim_pfm: 130.30523991428586
episode: 228 training return: tensor(163.6186, device='cuda:0')
episode: 229 training return: tensor(5.6575, device='cuda:0')
episode: 230 training return: tensor(2.1131, device='cuda:0')
episode: 231 training return: tensor(236.1045, device='cuda:0')
epoch: 58 test_true_pfm: 2530.0173259465405 sim_pfm: 70.64401429212496
episode: 232 training return: tensor(37.8824, device='cuda:0')
episode: 233 training return: tensor(44.6995, device='cuda:0')
episode: 234 training return: tensor(-30.8604, device='cuda:0')
episode: 235 training return: tensor(49.7851, device='cuda:0')
epoch: 59 test_true_pfm: 2892.0363824250285 sim_pfm: 65.13460919404558
episode: 236 training return: tensor(-67.3572, device='cuda:0')
episode: 237 training return: tensor(-133.9503, device='cuda:0')
episode: 238 training return: tensor(62.3610, device='cuda:0')
episode: 239 training return: tensor(75.8596, device='cuda:0')
epoch: 60 test_true_pfm: 1858.4786590353444 sim_pfm: 98.12778141081799
episode: 240 training return: tensor(248.7644, device='cuda:0')
episode: 241 training return: tensor(387.2822, device='cuda:0')
episode: 242 training return: tensor(309.0589, device='cuda:0')
episode: 243 training return: tensor(81.3269, device='cuda:0')
epoch: 61 test_true_pfm: 1966.2761645014236 sim_pfm: 237.90984423392607
episode: 244 training return: tensor(22.0280, device='cuda:0')
episode: 245 training return: tensor(-30.2072, device='cuda:0')
episode: 246 training return: tensor(1.2606, device='cuda:0')
episode: 247 training return: tensor(18.6110, device='cuda:0')
epoch: 62 test_true_pfm: 2260.7079365750396 sim_pfm: -15.844856511704469
episode: 248 training return: tensor(112.7438, device='cuda:0')
episode: 249 training return: tensor(179.6250, device='cuda:0')
episode: 250 training return: tensor(-65.4460, device='cuda:0')
episode: 251 training return: tensor(66.9450, device='cuda:0')
epoch: 63 test_true_pfm: 2014.6647812280298 sim_pfm: 127.69295925059123
episode: 252 training return: tensor(18.5593, device='cuda:0')
episode: 253 training return: tensor(132.2902, device='cuda:0')
episode: 254 training return: tensor(323.6505, device='cuda:0')
episode: 255 training return: tensor(386.2697, device='cuda:0')
epoch: 64 test_true_pfm: 2458.043233930944 sim_pfm: 98.56057527721471
episode: 256 training return: tensor(-9.1304, device='cuda:0')
episode: 257 training return: tensor(-83.6743, device='cuda:0')
episode: 258 training return: tensor(378.5758, device='cuda:0')
episode: 259 training return: tensor(204.1648, device='cuda:0')
epoch: 65 test_true_pfm: 2221.2951529897787 sim_pfm: -47.99523317096949
episode: 260 training return: tensor(213.6518, device='cuda:0')
episode: 261 training return: tensor(31.9913, device='cuda:0')
episode: 262 training return: tensor(237.2928, device='cuda:0')
episode: 263 training return: tensor(61.3039, device='cuda:0')
epoch: 66 test_true_pfm: 1983.1475840664014 sim_pfm: 118.82642642131152
episode: 264 training return: tensor(38.3722, device='cuda:0')
episode: 265 training return: tensor(-30.0232, device='cuda:0')
episode: 266 training return: tensor(86.9411, device='cuda:0')
episode: 267 training return: tensor(-48.4440, device='cuda:0')
epoch: 67 test_true_pfm: 2492.258994451002 sim_pfm: 186.87427603273923
episode: 268 training return: tensor(-32.1563, device='cuda:0')
episode: 269 training return: tensor(-129.8052, device='cuda:0')
episode: 270 training return: tensor(-92.9547, device='cuda:0')
episode: 271 training return: tensor(27.7936, device='cuda:0')
epoch: 68 test_true_pfm: 2037.0568775942127 sim_pfm: 167.804118476129
episode: 272 training return: tensor(-96.9169, device='cuda:0')
episode: 273 training return: tensor(201.0559, device='cuda:0')
episode: 274 training return: tensor(75.8126, device='cuda:0')
episode: 275 training return: tensor(15.7334, device='cuda:0')
epoch: 69 test_true_pfm: 1884.0118120294828 sim_pfm: 110.88051250770029
episode: 276 training return: tensor(-24.2375, device='cuda:0')
episode: 277 training return: tensor(-1.5887, device='cuda:0')
episode: 278 training return: tensor(17.8523, device='cuda:0')
episode: 279 training return: tensor(16.2801, device='cuda:0')
epoch: 70 test_true_pfm: 2012.8604255012226 sim_pfm: 119.08459994268681
episode: 280 training return: tensor(-33.6741, device='cuda:0')
episode: 281 training return: tensor(87.0140, device='cuda:0')
episode: 282 training return: tensor(-10.3225, device='cuda:0')
episode: 283 training return: tensor(258.4017, device='cuda:0')
epoch: 71 test_true_pfm: 2101.1926203565185 sim_pfm: 92.2178343340541
episode: 284 training return: tensor(78.6467, device='cuda:0')
episode: 285 training return: tensor(11.2609, device='cuda:0')
episode: 286 training return: tensor(104.3886, device='cuda:0')
episode: 287 training return: tensor(-14.9961, device='cuda:0')
epoch: 72 test_true_pfm: 2784.671101681672 sim_pfm: 135.8031874525283
episode: 288 training return: tensor(11.6149, device='cuda:0')
episode: 289 training return: tensor(-228.6226, device='cuda:0')
episode: 290 training return: tensor(91.7188, device='cuda:0')
episode: 291 training return: tensor(18.7064, device='cuda:0')
epoch: 73 test_true_pfm: 2303.7715660480403 sim_pfm: 165.7602775276755
episode: 292 training return: tensor(-91.2998, device='cuda:0')
episode: 293 training return: tensor(103.4677, device='cuda:0')
episode: 294 training return: tensor(-96.7695, device='cuda:0')
episode: 295 training return: tensor(247.7455, device='cuda:0')
epoch: 74 test_true_pfm: 1962.81187587579 sim_pfm: 291.8909343279277
episode: 296 training return: tensor(27.6437, device='cuda:0')
episode: 297 training return: tensor(383.9859, device='cuda:0')
episode: 298 training return: tensor(159.7609, device='cuda:0')
episode: 299 training return: tensor(163.2267, device='cuda:0')
epoch: 75 test_true_pfm: 2248.4302709164904 sim_pfm: 53.2030911592689
episode: 300 training return: tensor(33.3646, device='cuda:0')
episode: 301 training return: tensor(-14.3103, device='cuda:0')
episode: 302 training return: tensor(-8.7142, device='cuda:0')
episode: 303 training return: tensor(195.1638, device='cuda:0')
epoch: 76 test_true_pfm: 2173.879418913472 sim_pfm: 43.958302233717404
episode: 304 training return: tensor(162.0615, device='cuda:0')
episode: 305 training return: tensor(110.0164, device='cuda:0')
episode: 306 training return: tensor(39.0827, device='cuda:0')
episode: 307 training return: tensor(3.0921, device='cuda:0')
epoch: 77 test_true_pfm: 2063.9297939099483 sim_pfm: 307.6310968550485
episode: 308 training return: tensor(15.4456, device='cuda:0')
episode: 309 training return: tensor(43.2566, device='cuda:0')
episode: 310 training return: tensor(326.5859, device='cuda:0')
episode: 311 training return: tensor(66.5864, device='cuda:0')
epoch: 78 test_true_pfm: 2368.95597435031 sim_pfm: 226.44782979179095
episode: 312 training return: tensor(98.1404, device='cuda:0')
episode: 313 training return: tensor(-79.2271, device='cuda:0')
episode: 314 training return: tensor(57.0017, device='cuda:0')
episode: 315 training return: tensor(28.3630, device='cuda:0')
epoch: 79 test_true_pfm: 2368.116028866426 sim_pfm: -4.814886279714604
episode: 316 training return: tensor(206.7441, device='cuda:0')
episode: 317 training return: tensor(-3.9550, device='cuda:0')
episode: 318 training return: tensor(117.8497, device='cuda:0')
episode: 319 training return: tensor(-11.4532, device='cuda:0')
epoch: 80 test_true_pfm: 1978.6159731502387 sim_pfm: -49.293664356926456
episode: 320 training return: tensor(13.2502, device='cuda:0')
episode: 321 training return: tensor(181.8859, device='cuda:0')
episode: 322 training return: tensor(50.6028, device='cuda:0')
episode: 323 training return: tensor(247.0143, device='cuda:0')
epoch: 81 test_true_pfm: 2461.693220825184 sim_pfm: 312.1473260516941
episode: 324 training return: tensor(-19.3283, device='cuda:0')
episode: 325 training return: tensor(156.2821, device='cuda:0')
episode: 326 training return: tensor(178.1275, device='cuda:0')
episode: 327 training return: tensor(-42.9700, device='cuda:0')
epoch: 82 test_true_pfm: 1754.1658543146011 sim_pfm: 132.0897783349113
episode: 328 training return: tensor(201.8676, device='cuda:0')
episode: 329 training return: tensor(-91.5408, device='cuda:0')
episode: 330 training return: tensor(14.0988, device='cuda:0')
episode: 331 training return: tensor(421.3208, device='cuda:0')
epoch: 83 test_true_pfm: 2567.1512663162525 sim_pfm: 225.33104668774953
episode: 332 training return: tensor(39.6646, device='cuda:0')
episode: 333 training return: tensor(264.1029, device='cuda:0')
episode: 334 training return: tensor(223.6255, device='cuda:0')
episode: 335 training return: tensor(144.0521, device='cuda:0')
epoch: 84 test_true_pfm: 1995.4273344079782 sim_pfm: 97.6552953189627
episode: 336 training return: tensor(-17.2886, device='cuda:0')
episode: 337 training return: tensor(425.2360, device='cuda:0')
episode: 338 training return: tensor(238.9913, device='cuda:0')
episode: 339 training return: tensor(46.2504, device='cuda:0')
epoch: 85 test_true_pfm: 1959.954914120962 sim_pfm: 60.24235760883312
episode: 340 training return: tensor(-4.6731, device='cuda:0')
episode: 341 training return: tensor(148.8945, device='cuda:0')
episode: 342 training return: tensor(81.8179, device='cuda:0')
episode: 343 training return: tensor(12.1493, device='cuda:0')
epoch: 86 test_true_pfm: 2117.0853151688902 sim_pfm: 115.04600636203152
episode: 344 training return: tensor(-83.8590, device='cuda:0')
episode: 345 training return: tensor(408.6184, device='cuda:0')
episode: 346 training return: tensor(127.5488, device='cuda:0')
episode: 347 training return: tensor(-8.5572, device='cuda:0')
epoch: 87 test_true_pfm: 1816.7832605632284 sim_pfm: 137.4807141798277
episode: 348 training return: tensor(88.8654, device='cuda:0')
episode: 349 training return: tensor(-12.8414, device='cuda:0')
episode: 350 training return: tensor(109.0027, device='cuda:0')
episode: 351 training return: tensor(-163.2330, device='cuda:0')
epoch: 88 test_true_pfm: 1748.2147414853832 sim_pfm: 233.48481429777652
episode: 352 training return: tensor(83.9757, device='cuda:0')
episode: 353 training return: tensor(101.5663, device='cuda:0')
episode: 354 training return: tensor(125.5543, device='cuda:0')
episode: 355 training return: tensor(69.1635, device='cuda:0')
epoch: 89 test_true_pfm: 1877.3747574764996 sim_pfm: 43.689384073843634
episode: 356 training return: tensor(-13.2428, device='cuda:0')
episode: 357 training return: tensor(-3.6386, device='cuda:0')
episode: 358 training return: tensor(322.1444, device='cuda:0')
episode: 359 training return: tensor(44.5880, device='cuda:0')
epoch: 90 test_true_pfm: 1637.878145681947 sim_pfm: 160.88794325909112
episode: 360 training return: tensor(68.3146, device='cuda:0')
episode: 361 training return: tensor(382.5670, device='cuda:0')
episode: 362 training return: tensor(263.1183, device='cuda:0')
episode: 363 training return: tensor(202.7419, device='cuda:0')
epoch: 91 test_true_pfm: 1736.4347041130707 sim_pfm: 76.08365571029329
episode: 364 training return: tensor(97.2867, device='cuda:0')
episode: 365 training return: tensor(-5.1758, device='cuda:0')
episode: 366 training return: tensor(214.0406, device='cuda:0')
episode: 367 training return: tensor(246.3461, device='cuda:0')
epoch: 92 test_true_pfm: 2010.443179722581 sim_pfm: 111.18606588190111
episode: 368 training return: tensor(114.8482, device='cuda:0')
episode: 369 training return: tensor(14.4163, device='cuda:0')
episode: 370 training return: tensor(34.3275, device='cuda:0')
episode: 371 training return: tensor(72.1728, device='cuda:0')
epoch: 93 test_true_pfm: 2235.7938817727863 sim_pfm: 206.0074843488983
episode: 372 training return: tensor(194.1227, device='cuda:0')
episode: 373 training return: tensor(-76.4275, device='cuda:0')
episode: 374 training return: tensor(-23.8317, device='cuda:0')
episode: 375 training return: tensor(176.5759, device='cuda:0')
epoch: 94 test_true_pfm: 2302.6474385731744 sim_pfm: 268.1408739191247
episode: 376 training return: tensor(223.6955, device='cuda:0')
episode: 377 training return: tensor(1.9574, device='cuda:0')
episode: 378 training return: tensor(43.6986, device='cuda:0')
episode: 379 training return: tensor(162.2678, device='cuda:0')
epoch: 95 test_true_pfm: 1941.610697584425 sim_pfm: 131.0822682570239
episode: 380 training return: tensor(126.0030, device='cuda:0')
episode: 381 training return: tensor(114.4606, device='cuda:0')
episode: 382 training return: tensor(57.7796, device='cuda:0')
episode: 383 training return: tensor(-88.4978, device='cuda:0')
epoch: 96 test_true_pfm: 2474.073973633695 sim_pfm: 200.39557239611167
episode: 384 training return: tensor(214.2670, device='cuda:0')
episode: 385 training return: tensor(81.4258, device='cuda:0')
episode: 386 training return: tensor(165.8639, device='cuda:0')
episode: 387 training return: tensor(106.4242, device='cuda:0')
epoch: 97 test_true_pfm: 2788.9472889550457 sim_pfm: 157.7917885655382
episode: 388 training return: tensor(-0.1090, device='cuda:0')
episode: 389 training return: tensor(20.7195, device='cuda:0')
episode: 390 training return: tensor(-15.9424, device='cuda:0')
episode: 391 training return: tensor(450.5493, device='cuda:0')
epoch: 98 test_true_pfm: 2248.9400049598967 sim_pfm: 200.89000263305692
episode: 392 training return: tensor(62.3441, device='cuda:0')
episode: 393 training return: tensor(41.9382, device='cuda:0')
episode: 394 training return: tensor(-36.0284, device='cuda:0')
episode: 395 training return: tensor(9.0264, device='cuda:0')
epoch: 99 test_true_pfm: 2420.335661229921 sim_pfm: 171.29787537833909
episode: 396 training return: tensor(100.0465, device='cuda:0')
episode: 397 training return: tensor(336.0640, device='cuda:0')
episode: 398 training return: tensor(147.3440, device='cuda:0')
episode: 399 training return: tensor(211.0869, device='cuda:0')
epoch: 100 test_true_pfm: 2125.1208604580384 sim_pfm: 327.83790819352726
episode: 400 training return: tensor(190.6226, device='cuda:0')
episode: 401 training return: tensor(-30.2694, device='cuda:0')
episode: 402 training return: tensor(91.2805, device='cuda:0')
episode: 403 training return: tensor(-33.0026, device='cuda:0')
epoch: 101 test_true_pfm: 2731.2790630193117 sim_pfm: 141.10763967608605
episode: 404 training return: tensor(169.2616, device='cuda:0')
episode: 405 training return: tensor(193.9316, device='cuda:0')
episode: 406 training return: tensor(296.3447, device='cuda:0')
episode: 407 training return: tensor(411.3159, device='cuda:0')
epoch: 102 test_true_pfm: 2710.0799255289753 sim_pfm: 180.99988069338724
episode: 408 training return: tensor(197.6486, device='cuda:0')
episode: 409 training return: tensor(293.4790, device='cuda:0')
episode: 410 training return: tensor(-59.8016, device='cuda:0')
episode: 411 training return: tensor(186.1800, device='cuda:0')
epoch: 103 test_true_pfm: 1848.33240739001 sim_pfm: 46.73558759066509
episode: 412 training return: tensor(400.8741, device='cuda:0')
episode: 413 training return: tensor(-25.4266, device='cuda:0')
episode: 414 training return: tensor(42.4340, device='cuda:0')
episode: 415 training return: tensor(18.9146, device='cuda:0')
epoch: 104 test_true_pfm: 1798.2527931425466 sim_pfm: 227.47753334471295
episode: 416 training return: tensor(-45.4415, device='cuda:0')
episode: 417 training return: tensor(400.7207, device='cuda:0')
episode: 418 training return: tensor(396.7928, device='cuda:0')
episode: 419 training return: tensor(-63.1603, device='cuda:0')
epoch: 105 test_true_pfm: 2488.974529373443 sim_pfm: 211.3501717329491
episode: 420 training return: tensor(-9.1800, device='cuda:0')
episode: 421 training return: tensor(21.6088, device='cuda:0')
episode: 422 training return: tensor(31.6084, device='cuda:0')
episode: 423 training return: tensor(360.3989, device='cuda:0')
epoch: 106 test_true_pfm: 2159.740810232204 sim_pfm: 114.56859602472589
episode: 424 training return: tensor(355.6231, device='cuda:0')
episode: 425 training return: tensor(218.7629, device='cuda:0')
episode: 426 training return: tensor(36.7999, device='cuda:0')
episode: 427 training return: tensor(69.8067, device='cuda:0')
epoch: 107 test_true_pfm: 2399.4839463450403 sim_pfm: 71.59891553763494
episode: 428 training return: tensor(273.9224, device='cuda:0')
episode: 429 training return: tensor(35.5859, device='cuda:0')
episode: 430 training return: tensor(131.8576, device='cuda:0')
episode: 431 training return: tensor(81.5742, device='cuda:0')
epoch: 108 test_true_pfm: 2992.1155685149993 sim_pfm: 190.10551114615131
episode: 432 training return: tensor(372.8317, device='cuda:0')
episode: 433 training return: tensor(27.4906, device='cuda:0')
episode: 434 training return: tensor(266.7977, device='cuda:0')
episode: 435 training return: tensor(254.0567, device='cuda:0')
epoch: 109 test_true_pfm: 1920.5633064054484 sim_pfm: 144.9667011387161
episode: 436 training return: tensor(216.4380, device='cuda:0')
episode: 437 training return: tensor(127.1459, device='cuda:0')
episode: 438 training return: tensor(31.9424, device='cuda:0')
episode: 439 training return: tensor(53.8714, device='cuda:0')
epoch: 110 test_true_pfm: 1775.16406313064 sim_pfm: 91.1012151055232
episode: 440 training return: tensor(-35.3746, device='cuda:0')
episode: 441 training return: tensor(-52.4236, device='cuda:0')
episode: 442 training return: tensor(-84.5200, device='cuda:0')
episode: 443 training return: tensor(-38.6116, device='cuda:0')
epoch: 111 test_true_pfm: 1806.3108283086156 sim_pfm: 125.26442746437776
episode: 444 training return: tensor(84.8646, device='cuda:0')
episode: 445 training return: tensor(282.0589, device='cuda:0')
episode: 446 training return: tensor(136.6509, device='cuda:0')
episode: 447 training return: tensor(79.8754, device='cuda:0')
epoch: 112 test_true_pfm: 2251.9990854990524 sim_pfm: 224.15582656679908
episode: 448 training return: tensor(244.2131, device='cuda:0')
episode: 449 training return: tensor(178.0838, device='cuda:0')
episode: 450 training return: tensor(46.9905, device='cuda:0')
episode: 451 training return: tensor(116.9918, device='cuda:0')
epoch: 113 test_true_pfm: 2217.9598473099595 sim_pfm: 162.7347430465161
episode: 452 training return: tensor(469.6050, device='cuda:0')
episode: 453 training return: tensor(13.0003, device='cuda:0')
episode: 454 training return: tensor(84.6226, device='cuda:0')
episode: 455 training return: tensor(193.8659, device='cuda:0')
epoch: 114 test_true_pfm: 2195.6227171598316 sim_pfm: 75.5515619253274
episode: 456 training return: tensor(216.2912, device='cuda:0')
episode: 457 training return: tensor(10.5508, device='cuda:0')
episode: 458 training return: tensor(-174.7251, device='cuda:0')
episode: 459 training return: tensor(84.4227, device='cuda:0')
epoch: 115 test_true_pfm: 2027.1398984820942 sim_pfm: 111.82580547953451
episode: 460 training return: tensor(324.5220, device='cuda:0')
episode: 461 training return: tensor(28.9337, device='cuda:0')
episode: 462 training return: tensor(314.6525, device='cuda:0')
episode: 463 training return: tensor(17.8633, device='cuda:0')
epoch: 116 test_true_pfm: 2118.4115181001257 sim_pfm: 209.9605511674114
episode: 464 training return: tensor(91.7254, device='cuda:0')
episode: 465 training return: tensor(144.6608, device='cuda:0')
episode: 466 training return: tensor(-66.3362, device='cuda:0')
episode: 467 training return: tensor(91.2308, device='cuda:0')
epoch: 117 test_true_pfm: 1769.5893862258124 sim_pfm: 177.05663570012743
episode: 468 training return: tensor(-10.7902, device='cuda:0')
episode: 469 training return: tensor(309.1638, device='cuda:0')
episode: 470 training return: tensor(22.2475, device='cuda:0')
episode: 471 training return: tensor(38.7073, device='cuda:0')
epoch: 118 test_true_pfm: 2025.035672078259 sim_pfm: 344.61561600727146
episode: 472 training return: tensor(14.2605, device='cuda:0')
episode: 473 training return: tensor(37.5356, device='cuda:0')
episode: 474 training return: tensor(-7.2555, device='cuda:0')
episode: 475 training return: tensor(21.6933, device='cuda:0')
epoch: 119 test_true_pfm: 2344.4410966936225 sim_pfm: 155.74761646978246
episode: 476 training return: tensor(363.4193, device='cuda:0')
episode: 477 training return: tensor(66.3990, device='cuda:0')
episode: 478 training return: tensor(109.5653, device='cuda:0')
episode: 479 training return: tensor(152.2933, device='cuda:0')
epoch: 120 test_true_pfm: 1848.8766044449756 sim_pfm: 121.71882937305297
episode: 480 training return: tensor(-100.5719, device='cuda:0')
episode: 481 training return: tensor(45.2830, device='cuda:0')
episode: 482 training return: tensor(75.0266, device='cuda:0')
episode: 483 training return: tensor(29.8272, device='cuda:0')
epoch: 121 test_true_pfm: 2189.79224806208 sim_pfm: 211.18090544575048
episode: 484 training return: tensor(164.6907, device='cuda:0')
episode: 485 training return: tensor(57.2413, device='cuda:0')
episode: 486 training return: tensor(96.5778, device='cuda:0')
episode: 487 training return: tensor(165.7984, device='cuda:0')
epoch: 122 test_true_pfm: 2101.242251191356 sim_pfm: 198.4984640418164
episode: 488 training return: tensor(214.0098, device='cuda:0')
episode: 489 training return: tensor(-13.0536, device='cuda:0')
episode: 490 training return: tensor(41.6880, device='cuda:0')
episode: 491 training return: tensor(49.5298, device='cuda:0')
epoch: 123 test_true_pfm: 2121.448912938556 sim_pfm: 346.06519733864116
episode: 492 training return: tensor(143.3124, device='cuda:0')
episode: 493 training return: tensor(194.4984, device='cuda:0')
episode: 494 training return: tensor(30.7377, device='cuda:0')
episode: 495 training return: tensor(264.0229, device='cuda:0')
epoch: 124 test_true_pfm: 1808.438332167431 sim_pfm: 169.214436813083
episode: 496 training return: tensor(41.3216, device='cuda:0')
episode: 497 training return: tensor(-43.4278, device='cuda:0')
episode: 498 training return: tensor(-7.9110, device='cuda:0')
episode: 499 training return: tensor(102.7554, device='cuda:0')
epoch: 125 test_true_pfm: 2293.797508059872 sim_pfm: 88.99423705550726
episode: 500 training return: tensor(-21.5938, device='cuda:0')
episode: 501 training return: tensor(126.2175, device='cuda:0')
episode: 502 training return: tensor(194.5138, device='cuda:0')
episode: 503 training return: tensor(-53.3929, device='cuda:0')
epoch: 126 test_true_pfm: 2540.148155020558 sim_pfm: 224.63872980950205
episode: 504 training return: tensor(191.9983, device='cuda:0')
episode: 505 training return: tensor(237.1788, device='cuda:0')
episode: 506 training return: tensor(-89.6979, device='cuda:0')
episode: 507 training return: tensor(94.1249, device='cuda:0')
epoch: 127 test_true_pfm: 2309.9746874793736 sim_pfm: 198.34833336122878
episode: 508 training return: tensor(151.5711, device='cuda:0')
episode: 509 training return: tensor(17.9757, device='cuda:0')
episode: 510 training return: tensor(51.4474, device='cuda:0')
episode: 511 training return: tensor(72.1454, device='cuda:0')
epoch: 128 test_true_pfm: 1745.8604539274518 sim_pfm: 115.74993051941662
episode: 512 training return: tensor(181.6936, device='cuda:0')
episode: 513 training return: tensor(111.2808, device='cuda:0')
episode: 514 training return: tensor(154.9109, device='cuda:0')
episode: 515 training return: tensor(148.9701, device='cuda:0')
epoch: 129 test_true_pfm: 1664.6082684916819 sim_pfm: 177.27515888900962
episode: 516 training return: tensor(27.4020, device='cuda:0')
episode: 517 training return: tensor(152.2500, device='cuda:0')
episode: 518 training return: tensor(315.4767, device='cuda:0')
episode: 519 training return: tensor(-17.0954, device='cuda:0')
epoch: 130 test_true_pfm: 2313.596579198716 sim_pfm: 145.41448608857658
episode: 520 training return: tensor(3.5524, device='cuda:0')
episode: 521 training return: tensor(73.9691, device='cuda:0')
episode: 522 training return: tensor(220.8300, device='cuda:0')
episode: 523 training return: tensor(61.4158, device='cuda:0')
epoch: 131 test_true_pfm: 2091.0839075582944 sim_pfm: 228.77516463429978
episode: 524 training return: tensor(119.6771, device='cuda:0')
episode: 525 training return: tensor(202.4474, device='cuda:0')
episode: 526 training return: tensor(133.6662, device='cuda:0')
episode: 527 training return: tensor(106.0435, device='cuda:0')
epoch: 132 test_true_pfm: 1740.813969859113 sim_pfm: 121.84685026796069
episode: 528 training return: tensor(65.5775, device='cuda:0')
episode: 529 training return: tensor(80.1052, device='cuda:0')
episode: 530 training return: tensor(-42.5975, device='cuda:0')
episode: 531 training return: tensor(380.8608, device='cuda:0')
epoch: 133 test_true_pfm: 2427.6718266182356 sim_pfm: 99.31655366841005
episode: 532 training return: tensor(148.2874, device='cuda:0')
episode: 533 training return: tensor(351.1405, device='cuda:0')
episode: 534 training return: tensor(45.0202, device='cuda:0')
episode: 535 training return: tensor(-85.7861, device='cuda:0')
epoch: 134 test_true_pfm: 2400.7673973806864 sim_pfm: 136.84870858706805
episode: 536 training return: tensor(200.4196, device='cuda:0')
episode: 537 training return: tensor(-79.2725, device='cuda:0')
episode: 538 training return: tensor(-31.2460, device='cuda:0')
episode: 539 training return: tensor(17.7753, device='cuda:0')
epoch: 135 test_true_pfm: 2239.7975098946904 sim_pfm: 178.298026506401
episode: 540 training return: tensor(24.1416, device='cuda:0')
episode: 541 training return: tensor(425.0033, device='cuda:0')
episode: 542 training return: tensor(102.5540, device='cuda:0')
episode: 543 training return: tensor(400.3785, device='cuda:0')
epoch: 136 test_true_pfm: 2907.011545415464 sim_pfm: 232.28960796333072
episode: 544 training return: tensor(114.4141, device='cuda:0')
episode: 545 training return: tensor(89.8967, device='cuda:0')
episode: 546 training return: tensor(89.7392, device='cuda:0')
episode: 547 training return: tensor(101.2520, device='cuda:0')
epoch: 137 test_true_pfm: 2474.7652063547544 sim_pfm: 210.2735482485247
episode: 548 training return: tensor(118.0631, device='cuda:0')
episode: 549 training return: tensor(283.5050, device='cuda:0')
episode: 550 training return: tensor(58.9978, device='cuda:0')
episode: 551 training return: tensor(207.5196, device='cuda:0')
epoch: 138 test_true_pfm: 1799.113345673319 sim_pfm: 202.20054068459044
episode: 552 training return: tensor(209.1181, device='cuda:0')
episode: 553 training return: tensor(170.5378, device='cuda:0')
episode: 554 training return: tensor(117.1797, device='cuda:0')
episode: 555 training return: tensor(44.6741, device='cuda:0')
epoch: 139 test_true_pfm: 2047.6294932468452 sim_pfm: 231.9575616484702
episode: 556 training return: tensor(-73.8454, device='cuda:0')
episode: 557 training return: tensor(43.9547, device='cuda:0')
episode: 558 training return: tensor(55.6844, device='cuda:0')
episode: 559 training return: tensor(130.2665, device='cuda:0')
epoch: 140 test_true_pfm: 2175.569741583716 sim_pfm: 275.5212356863776
episode: 560 training return: tensor(206.3147, device='cuda:0')
episode: 561 training return: tensor(-27.7262, device='cuda:0')
episode: 562 training return: tensor(304.8323, device='cuda:0')
episode: 563 training return: tensor(222.9321, device='cuda:0')
epoch: 141 test_true_pfm: 1704.82304607518 sim_pfm: 232.27437231507307
episode: 564 training return: tensor(369.9529, device='cuda:0')
episode: 565 training return: tensor(38.2859, device='cuda:0')
episode: 566 training return: tensor(153.7746, device='cuda:0')
episode: 567 training return: tensor(93.6495, device='cuda:0')
epoch: 142 test_true_pfm: 2149.3893943672147 sim_pfm: 106.17389074006739
episode: 568 training return: tensor(6.5810, device='cuda:0')
episode: 569 training return: tensor(93.5108, device='cuda:0')
episode: 570 training return: tensor(413.1148, device='cuda:0')
episode: 571 training return: tensor(454.4632, device='cuda:0')
epoch: 143 test_true_pfm: 2729.9828958176317 sim_pfm: 139.88731452514185
episode: 572 training return: tensor(299.5316, device='cuda:0')
episode: 573 training return: tensor(31.9227, device='cuda:0')
episode: 574 training return: tensor(429.5590, device='cuda:0')
episode: 575 training return: tensor(52.2070, device='cuda:0')
epoch: 144 test_true_pfm: 2847.519294935102 sim_pfm: 202.17240869965948
episode: 576 training return: tensor(149.9422, device='cuda:0')
episode: 577 training return: tensor(-50.9127, device='cuda:0')
episode: 578 training return: tensor(38.5347, device='cuda:0')
episode: 579 training return: tensor(5.1324, device='cuda:0')
epoch: 145 test_true_pfm: 2001.5090818417993 sim_pfm: 180.84947061367953
episode: 580 training return: tensor(68.2549, device='cuda:0')
episode: 581 training return: tensor(-7.6751, device='cuda:0')
episode: 582 training return: tensor(369.6963, device='cuda:0')
episode: 583 training return: tensor(212.0694, device='cuda:0')
epoch: 146 test_true_pfm: 1834.133771475704 sim_pfm: 123.15426328630808
episode: 584 training return: tensor(434.0870, device='cuda:0')
episode: 585 training return: tensor(378.7119, device='cuda:0')
episode: 586 training return: tensor(357.4557, device='cuda:0')
episode: 587 training return: tensor(169.0191, device='cuda:0')
epoch: 147 test_true_pfm: 2354.490864057268 sim_pfm: 154.6044559306853
episode: 588 training return: tensor(411.2260, device='cuda:0')
episode: 589 training return: tensor(7.1456, device='cuda:0')
episode: 590 training return: tensor(26.0506, device='cuda:0')
episode: 591 training return: tensor(134.2912, device='cuda:0')
epoch: 148 test_true_pfm: 2091.0538446133173 sim_pfm: 160.74015186935625
episode: 592 training return: tensor(313.9551, device='cuda:0')
episode: 593 training return: tensor(328.0746, device='cuda:0')
episode: 594 training return: tensor(418.9737, device='cuda:0')
episode: 595 training return: tensor(76.1427, device='cuda:0')
epoch: 149 test_true_pfm: 1701.4604917911136 sim_pfm: 155.55143130081706
episode: 596 training return: tensor(29.4129, device='cuda:0')
episode: 597 training return: tensor(52.1284, device='cuda:0')
episode: 598 training return: tensor(224.0703, device='cuda:0')
episode: 599 training return: tensor(95.0082, device='cuda:0')
epoch: 150 test_true_pfm: 2435.2777529016676 sim_pfm: 263.5612380929815
