['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '3']
epoch: 0 training_loss 0.26263522416353224 test_loss: 0.18605889081954957
epoch: 1 training_loss 0.1564702573046088 test_loss: 0.14893344640731812
epoch: 2 training_loss 0.1410907969251275 test_loss: 0.15775293111801147
epoch: 3 training_loss 0.12831090681254864 test_loss: 0.11735749244689941
epoch: 4 training_loss 0.123503004796803 test_loss: 0.14324383735656737
epoch: 5 training_loss 0.11851813729852438 test_loss: 0.12486351728439331
epoch: 6 training_loss 0.11471592012792825 test_loss: 0.11335079669952393
epoch: 7 training_loss 0.11586089231073857 test_loss: 0.09617429971694946
epoch: 8 training_loss 0.1095944494754076 test_loss: 0.08960194587707519
epoch: 9 training_loss 0.10470190197229386 test_loss: 0.09513928294181824
epoch: 10 training_loss 0.10408527782186866 test_loss: 0.11913166046142579
epoch: 11 training_loss 0.10643876492977142 test_loss: 0.10969600677490235
epoch: 12 training_loss 0.10172196231782436 test_loss: 0.1027899980545044
epoch: 13 training_loss 0.10440281044691802 test_loss: 0.10383825302124024
epoch: 14 training_loss 0.09992041870951653 test_loss: 0.09786105155944824
epoch: 15 training_loss 0.0995064627379179 test_loss: 0.09445885419845582
epoch: 16 training_loss 0.09566221946850419 test_loss: 0.09399032592773438
epoch: 17 training_loss 0.09890782093629241 test_loss: 0.10489821434020996
epoch: 18 training_loss 0.10149861823767424 test_loss: 0.090907883644104
epoch: 19 training_loss 0.10868174500763417 test_loss: 0.10508551597595214
epoch: 20 training_loss 0.09509072661399841 test_loss: 0.09444828033447265
epoch: 21 training_loss 0.09714446660131217 test_loss: 0.09983856081962586
epoch: 22 training_loss 0.09814644521102309 test_loss: 0.11128855943679809
epoch: 23 training_loss 0.09983849287033081 test_loss: 0.10254833698272706
epoch: 24 training_loss 0.0941478193551302 test_loss: 0.08778111934661866
epoch: 25 training_loss 0.09768603563308716 test_loss: 0.08617913126945495
epoch: 26 training_loss 0.09935119833797217 test_loss: 0.08185083270072938
epoch: 27 training_loss 0.09080024361610413 test_loss: 0.10208392143249512
epoch: 28 training_loss 0.09672518368810415 test_loss: 0.11209096908569335
epoch: 29 training_loss 0.10505231365561485 test_loss: 0.09980408549308777
epoch: 30 training_loss 0.09944230072200298 test_loss: 0.08441755771636963
epoch: 31 training_loss 0.09145119111984969 test_loss: 0.09583038091659546
epoch: 32 training_loss 0.10369929578155279 test_loss: 0.11126394271850586
epoch: 33 training_loss 0.0973021549731493 test_loss: 0.09611204266548157
epoch: 34 training_loss 0.0947047346457839 test_loss: 0.09405727386474609
epoch: 35 training_loss 0.09347869090735912 test_loss: 0.08811533451080322
epoch: 36 training_loss 0.09146798493340612 test_loss: 0.09632961750030518
epoch: 37 training_loss 0.09384112430736423 test_loss: 0.09481090307235718
epoch: 38 training_loss 0.09475014122202992 test_loss: 0.08835316300392151
epoch: 39 training_loss 0.09194382276386022 test_loss: 0.08885566592216491
epoch: 40 training_loss 0.1005145826563239 test_loss: 0.0961245357990265
epoch: 41 training_loss 0.10354622080922127 test_loss: 0.09202260971069336
epoch: 42 training_loss 0.10042506963014602 test_loss: 0.07986328601837159
epoch: 43 training_loss 0.0963570580817759 test_loss: 0.09795101284980774
epoch: 44 training_loss 0.09673241985961795 test_loss: 0.08829676508903503
epoch: 45 training_loss 0.09886917296797038 test_loss: 0.10938553810119629
epoch: 46 training_loss 0.09362538171932101 test_loss: 0.09851423501968384
epoch: 47 training_loss 0.09837827401235699 test_loss: 0.10059467554092408
epoch: 48 training_loss 0.09944908475503325 test_loss: 0.10311135053634643
epoch: 49 training_loss 0.09502689559012652 test_loss: 0.09376078248023986
epoch: 50 training_loss 0.09210279027931392 test_loss: 0.10228891372680664
epoch: 51 training_loss 0.09320722173899412 test_loss: 0.08061574697494507
epoch: 52 training_loss 0.09285374753177165 test_loss: 0.10432968139648438
epoch: 53 training_loss 0.0900227129086852 test_loss: 0.08505438566207886
epoch: 54 training_loss 0.08777252238243818 test_loss: 0.08739755749702453
epoch: 55 training_loss 0.09133575264364481 test_loss: 0.08951725363731385
epoch: 56 training_loss 0.09018414424732328 test_loss: 0.09183886051177978
epoch: 57 training_loss 0.09327182110399007 test_loss: 0.08545721173286439
epoch: 58 training_loss 0.09446613298729062 test_loss: 0.08819517493247986
epoch: 59 training_loss 0.08926666513085366 test_loss: 0.09214015603065491
epoch: 60 training_loss 0.0889723650738597 test_loss: 0.09879688620567321
epoch: 61 training_loss 0.09586335524916649 test_loss: 0.09676938652992248
epoch: 62 training_loss 0.09900850005447864 test_loss: 0.0892974853515625
epoch: 63 training_loss 0.09589203407987952 test_loss: 0.07631253600120544
epoch: 64 training_loss 0.0870518146827817 test_loss: 0.10676882266998292
epoch: 65 training_loss 0.09518088465556503 test_loss: 0.0910581886768341
epoch: 66 training_loss 0.09045913301408291 test_loss: 0.09672276377677917
epoch: 67 training_loss 0.08975577298551798 test_loss: 0.08790923357009887
epoch: 68 training_loss 0.0914699925109744 test_loss: 0.08357696533203125
epoch: 69 training_loss 0.08315715856850148 test_loss: 0.08123477697372436
epoch: 70 training_loss 0.09467470195144415 test_loss: 0.09381684064865112
epoch: 71 training_loss 0.09266463994979858 test_loss: 0.09170288443565369
epoch: 72 training_loss 0.09355180202051998 test_loss: 0.0925191342830658
epoch: 73 training_loss 0.09399648541584611 test_loss: 0.09315972328186035
epoch: 74 training_loss 0.09371944075450302 test_loss: 0.0810574471950531
epoch: 75 training_loss 0.08993241043761373 test_loss: 0.08370193243026733
epoch: 76 training_loss 0.09471604762598872 test_loss: 0.10117193460464477
epoch: 77 training_loss 0.08802613982930779 test_loss: 0.0806286871433258
epoch: 78 training_loss 0.08645679827779532 test_loss: 0.09391835927963257
epoch: 79 training_loss 0.08834845522418618 test_loss: 0.09771549701690674
epoch: 80 training_loss 0.08788228437304496 test_loss: 0.09813550114631653
epoch: 81 training_loss 0.08930892260745167 test_loss: 0.08205737471580506
epoch: 82 training_loss 0.08698442485183477 test_loss: 0.07690380811691284
epoch: 83 training_loss 0.09232584001496434 test_loss: 0.09677883982658386
epoch: 84 training_loss 0.08536436531692743 test_loss: 0.08989700675010681
epoch: 85 training_loss 0.09268125982955099 test_loss: 0.09394590258598327
epoch: 86 training_loss 0.09242038315162063 test_loss: 0.08675556778907775
epoch: 87 training_loss 0.08710860091261566 test_loss: 0.10148385763168336
epoch: 88 training_loss 0.09212650215253233 test_loss: 0.08525270223617554
epoch: 89 training_loss 0.09553531602025032 test_loss: 0.08682332634925842
epoch: 90 training_loss 0.09344743136316538 test_loss: 0.08481550812721253
epoch: 91 training_loss 0.08654859574511647 test_loss: 0.08677095174789429
epoch: 92 training_loss 0.09030726987868548 test_loss: 0.09535894989967346
epoch: 93 training_loss 0.08513234343379736 test_loss: 0.09244210124015809
epoch: 94 training_loss 0.0910022395476699 test_loss: 0.08721159100532531
epoch: 95 training_loss 0.09318603361025453 test_loss: 0.09171502590179444
epoch: 96 training_loss 0.09266717330552637 test_loss: 0.09538208842277526
epoch: 97 training_loss 0.09091835539788008 test_loss: 0.09422343373298644
epoch: 98 training_loss 0.09290112052112817 test_loss: 0.10368902683258056
epoch: 99 training_loss 0.08735721105709672 test_loss: 0.09542027115821838
epoch: 100 training_loss 0.08783784018829464 test_loss: 0.094361811876297
epoch: 101 training_loss 0.09130793385207653 test_loss: 0.09890283942222595
epoch: 102 training_loss 0.0901500491797924 test_loss: 0.09500804543495178
epoch: 103 training_loss 0.08848751224577427 test_loss: 0.0925215721130371
epoch: 104 training_loss 0.09434958498924971 test_loss: 0.08700159192085266
epoch: 105 training_loss 0.08865019977092743 test_loss: 0.08989982604980469
epoch: 106 training_loss 0.08683547213673591 test_loss: 0.09955965876579284
epoch: 107 training_loss 0.09426327209919691 test_loss: 0.09088902473449707
epoch: 108 training_loss 0.0865742016211152 test_loss: 0.0885908544063568
epoch: 109 training_loss 0.08766996089369058 test_loss: 0.0967962086200714
epoch: 110 training_loss 0.08709325898438693 test_loss: 0.10536962747573853
epoch: 111 training_loss 0.085143224298954 test_loss: 0.09266441464424133
epoch: 112 training_loss 0.08749498592689633 test_loss: 0.08349276781082153
epoch: 113 training_loss 0.09410987697541713 test_loss: 0.07825320363044738
epoch: 114 training_loss 0.08408496925607324 test_loss: 0.08298395872116089
epoch: 115 training_loss 0.08946708474308253 test_loss: 0.10511068105697632
epoch: 116 training_loss 0.09241294596344232 test_loss: 0.09602281451225281
epoch: 117 training_loss 0.09090604884549976 test_loss: 0.08555373549461365
epoch: 118 training_loss 0.08923959724605084 test_loss: 0.09968936443328857
epoch: 119 training_loss 0.08966506199911237 test_loss: 0.0944496750831604
epoch: 120 training_loss 0.08767655743286014 test_loss: 0.10082492828369141
epoch: 121 training_loss 0.08327083423733711 test_loss: 0.08329201340675355
epoch: 122 training_loss 0.08610261011868715 test_loss: 0.08348191380500794
epoch: 123 training_loss 0.08999212237074972 test_loss: 0.08494279384613038
epoch: 124 training_loss 0.0830104137584567 test_loss: 0.09487541317939759
epoch: 125 training_loss 0.08553427493199706 test_loss: 0.08338708877563476
epoch: 126 training_loss 0.08601916793733835 test_loss: 0.08045082688331603
epoch: 127 training_loss 0.09024967756122351 test_loss: 0.09427902102470398
epoch: 128 training_loss 0.09025674117729068 test_loss: 0.08312135338783264
epoch: 129 training_loss 0.08947747901082038 test_loss: 0.07773706912994385
epoch: 130 training_loss 0.09021246809512377 test_loss: 0.0859605073928833
epoch: 131 training_loss 0.08965833773836493 test_loss: 0.08600882291793824
epoch: 132 training_loss 0.08347663505002856 test_loss: 0.08460625410079955
epoch: 133 training_loss 0.0806421947106719 test_loss: 0.09702466726303101
epoch: 134 training_loss 0.0864116607233882 test_loss: 0.08829368352890014
epoch: 135 training_loss 0.0903185617364943 test_loss: 0.08388238549232482
epoch: 136 training_loss 0.09529308827593923 test_loss: 0.10558425188064575
epoch: 137 training_loss 0.09096781791187823 test_loss: 0.09443023204803466
epoch: 138 training_loss 0.08941166389733553 test_loss: 0.0829727292060852
epoch: 139 training_loss 0.08404561959207058 test_loss: 0.08652674555778503
epoch: 140 training_loss 0.09533590087667107 test_loss: 0.09749364256858825
epoch: 141 training_loss 0.08332778360694647 test_loss: 0.09638298153877259
epoch: 142 training_loss 0.08439427530393004 test_loss: 0.0932542622089386
epoch: 143 training_loss 0.08944029171019792 test_loss: 0.07717159986495972
epoch: 144 training_loss 0.08582396954298019 test_loss: 0.10356706380844116
epoch: 145 training_loss 0.08664000389166177 test_loss: 0.08254027366638184
epoch: 146 training_loss 0.08453837364912033 test_loss: 0.08581193685531616
epoch: 147 training_loss 0.08315911505371332 test_loss: 0.0937791883945465
epoch: 148 training_loss 0.09037991039454937 test_loss: 0.09410862922668457
epoch: 149 training_loss 0.09141329742968082 test_loss: 0.09660177230834961
epoch: 0 training_loss 41.08994686126709 test_loss: 21.576506042480467
epoch: 1 training_loss 17.217831506729127 test_loss: 14.89034423828125
epoch: 2 training_loss 12.940981798171997 test_loss: 11.862261962890624
epoch: 3 training_loss 10.786204051971435 test_loss: 10.170999145507812
epoch: 4 training_loss 9.603422722816468 test_loss: 9.60499267578125
epoch: 5 training_loss 8.551933703422547 test_loss: 8.240929412841798
epoch: 6 training_loss 8.130478692054748 test_loss: 8.090556335449218
epoch: 7 training_loss 7.292576112747192 test_loss: 7.300563049316406
epoch: 8 training_loss 6.938910632133484 test_loss: 7.049293518066406
epoch: 9 training_loss 6.5823360490798954 test_loss: 6.682320404052734
epoch: 10 training_loss 6.0221958923339844 test_loss: 6.150041198730468
epoch: 11 training_loss 5.900833268165588 test_loss: 5.617523574829102
epoch: 12 training_loss 5.613743882179261 test_loss: 5.8370716094970705
epoch: 13 training_loss 5.520351495742798 test_loss: 5.484758377075195
epoch: 14 training_loss 5.231713337898254 test_loss: 5.565820693969727
epoch: 15 training_loss 5.146059155464172 test_loss: 5.048332595825196
epoch: 16 training_loss 5.052315399646759 test_loss: 5.154386901855469
epoch: 17 training_loss 4.8187268710136415 test_loss: 4.895592880249024
epoch: 18 training_loss 4.785360674858094 test_loss: 4.807077789306641
epoch: 19 training_loss 4.600764195919037 test_loss: 4.666723251342773
epoch: 20 training_loss 4.54290700674057 test_loss: 4.417947006225586
epoch: 21 training_loss 4.329875707626343 test_loss: 4.345211791992187
epoch: 22 training_loss 4.290100390911102 test_loss: 4.304536819458008
epoch: 23 training_loss 4.276441280841827 test_loss: 4.227478408813477
epoch: 24 training_loss 4.110150771141052 test_loss: 4.105957794189453
epoch: 25 training_loss 4.012837386131286 test_loss: 4.083252334594727
epoch: 26 training_loss 3.966755793094635 test_loss: 4.03895378112793
epoch: 27 training_loss 3.885693681240082 test_loss: 3.8357616424560548
epoch: 28 training_loss 3.9395190477371216 test_loss: 3.8646190643310545
epoch: 29 training_loss 3.8232967114448546 test_loss: 3.652009201049805
epoch: 30 training_loss 3.8067953038215636 test_loss: 3.752676010131836
epoch: 31 training_loss 3.7212493348121645 test_loss: 3.6423503875732424
epoch: 32 training_loss 3.6849669575691224 test_loss: 3.741830825805664
epoch: 33 training_loss 3.6788647508621217 test_loss: 3.518024444580078
epoch: 34 training_loss 3.587315685749054 test_loss: 3.5292743682861327
epoch: 35 training_loss 3.505945391654968 test_loss: 3.747038650512695
epoch: 36 training_loss 3.4038817954063414 test_loss: 3.5587226867675783
epoch: 37 training_loss 3.4180482268333434 test_loss: 3.422568511962891
epoch: 38 training_loss 3.447186141014099 test_loss: 3.590868377685547
epoch: 39 training_loss 3.300717794895172 test_loss: 3.304768371582031
epoch: 40 training_loss 3.372232966423035 test_loss: 3.1766822814941404
epoch: 41 training_loss 3.2755098295211793 test_loss: 3.3180801391601564
epoch: 42 training_loss 3.2605705738067625 test_loss: 3.1824459075927733
epoch: 43 training_loss 3.250132579803467 test_loss: 3.3145023345947267
epoch: 44 training_loss 3.1991101455688478 test_loss: 3.157457160949707
epoch: 45 training_loss 3.1631474709510803 test_loss: 3.30407600402832
epoch: 46 training_loss 3.154406750202179 test_loss: 3.067552185058594
epoch: 47 training_loss 3.1241117024421694 test_loss: 3.1698923110961914
epoch: 48 training_loss 3.053949279785156 test_loss: 3.0651878356933593
epoch: 49 training_loss 3.05784295797348 test_loss: 3.176848220825195
epoch: 50 training_loss 2.9961767101287844 test_loss: 3.1309745788574217
epoch: 51 training_loss 3.12851692199707 test_loss: 3.100792121887207
epoch: 52 training_loss 2.9898270058631895 test_loss: 2.9794517517089845
epoch: 53 training_loss 3.011326107978821 test_loss: 2.957870674133301
epoch: 54 training_loss 2.9592661905288695 test_loss: 2.866921615600586
epoch: 55 training_loss 2.8866931009292602 test_loss: 2.9586179733276365
epoch: 56 training_loss 2.8955227947235107 test_loss: 3.128994178771973
epoch: 57 training_loss 2.916606328487396 test_loss: 3.0575504302978516
epoch: 58 training_loss 2.8924897432327272 test_loss: 2.7978483200073243
epoch: 59 training_loss 2.8940371465682984 test_loss: 2.866647148132324
epoch: 60 training_loss 2.8465489411354064 test_loss: 2.9530410766601562
epoch: 61 training_loss 2.851716253757477 test_loss: 2.86461181640625
epoch: 62 training_loss 2.8463058710098266 test_loss: 2.941168785095215
epoch: 63 training_loss 2.785982174873352 test_loss: 2.8337326049804688
epoch: 64 training_loss 2.735570614337921 test_loss: 2.806456184387207
epoch: 65 training_loss 2.8062307381629945 test_loss: 2.7873912811279298
epoch: 66 training_loss 2.729794137477875 test_loss: 2.994780921936035
epoch: 67 training_loss 2.8092355632781985 test_loss: 2.8044687271118165
epoch: 68 training_loss 2.7284755659103395 test_loss: 2.7931528091430664
epoch: 69 training_loss 2.7487025332450865 test_loss: 2.616798210144043
epoch: 70 training_loss 2.7481077098846436 test_loss: 2.6922760009765625
epoch: 71 training_loss 2.7158177947998046 test_loss: 2.7708438873291015
epoch: 72 training_loss 2.6428813946247103 test_loss: 2.680625343322754
epoch: 73 training_loss 2.6244702196121215 test_loss: 2.688546371459961
epoch: 74 training_loss 2.6553941416740416 test_loss: 2.598150062561035
epoch: 75 training_loss 2.6543029379844665 test_loss: 2.6526613235473633
epoch: 76 training_loss 2.608125227689743 test_loss: 2.7339460372924806
epoch: 77 training_loss 2.6951144218444822 test_loss: 2.8382331848144533
epoch: 78 training_loss 2.6591507458686827 test_loss: 2.622850036621094
epoch: 79 training_loss 2.579723844528198 test_loss: 2.679214286804199
epoch: 80 training_loss 2.6076837944984437 test_loss: 2.6555126190185545
epoch: 81 training_loss 2.554504024982452 test_loss: 2.750353240966797
epoch: 82 training_loss 2.558835120201111 test_loss: 2.5104875564575195
epoch: 83 training_loss 2.5234977805614474 test_loss: 2.605364227294922
epoch: 84 training_loss 2.5826734578609467 test_loss: 2.603404998779297
epoch: 85 training_loss 2.579453444480896 test_loss: 2.5963016510009767
epoch: 86 training_loss 2.5649004864692686 test_loss: 2.585063171386719
epoch: 87 training_loss 2.5550317668914797 test_loss: 2.5776243209838867
epoch: 88 training_loss 2.519011690616608 test_loss: 2.58944091796875
epoch: 89 training_loss 2.5024260365962983 test_loss: 2.4540050506591795
epoch: 90 training_loss 2.5048419511318207 test_loss: 2.489527702331543
epoch: 91 training_loss 2.524197750091553 test_loss: 2.6096338272094726
epoch: 92 training_loss 2.471995532512665 test_loss: 2.626234245300293
epoch: 93 training_loss 2.468608568906784 test_loss: 2.5881607055664064
epoch: 94 training_loss 2.5421646177768706 test_loss: 2.462331008911133
epoch: 95 training_loss 2.4300303065776827 test_loss: 2.5727703094482424
epoch: 96 training_loss 2.4599495589733125 test_loss: 2.4858531951904297
epoch: 97 training_loss 2.428489031791687 test_loss: 2.514205551147461
epoch: 98 training_loss 2.464158623218536 test_loss: 2.428364372253418
epoch: 99 training_loss 2.4398534440994264 test_loss: 2.490849494934082
epoch: 100 training_loss 2.5070619416236877 test_loss: 2.397272491455078
epoch: 101 training_loss 2.433919404745102 test_loss: 2.377679443359375
epoch: 102 training_loss 2.3307332146167754 test_loss: 2.531228256225586
epoch: 103 training_loss 2.4059696900844574 test_loss: 2.3968233108520507
epoch: 104 training_loss 2.346128704547882 test_loss: 2.422079849243164
epoch: 105 training_loss 2.3917048728466033 test_loss: 2.4700164794921875
epoch: 106 training_loss 2.3307264387607574 test_loss: 2.3737585067749025
epoch: 107 training_loss 2.3546854043006897 test_loss: 2.419449806213379
epoch: 108 training_loss 2.4181378412246706 test_loss: 2.343534469604492
epoch: 109 training_loss 2.3991402065753937 test_loss: 2.536532974243164
epoch: 110 training_loss 2.3762250423431395 test_loss: 2.368912696838379
epoch: 111 training_loss 2.3061122560501097 test_loss: 2.4746282577514647
epoch: 112 training_loss 2.3883904886245726 test_loss: 2.379615592956543
epoch: 113 training_loss 2.3589655113220216 test_loss: 2.3866615295410156
epoch: 114 training_loss 2.3707087016105652 test_loss: 2.421809959411621
epoch: 115 training_loss 2.3486452043056487 test_loss: 2.383087921142578
epoch: 116 training_loss 2.326081396341324 test_loss: 2.2955043792724608
epoch: 117 training_loss 2.3089766085147856 test_loss: 2.304742431640625
epoch: 118 training_loss 2.319936283826828 test_loss: 2.350774574279785
epoch: 119 training_loss 2.242596390247345 test_loss: 2.3167734146118164
epoch: 120 training_loss 2.355385146141052 test_loss: 2.438632774353027
epoch: 121 training_loss 2.3156487929821012 test_loss: 2.4143720626831056
epoch: 122 training_loss 2.335397197008133 test_loss: 2.348634719848633
epoch: 123 training_loss 2.264312605857849 test_loss: 2.281298828125
epoch: 124 training_loss 2.2220461452007294 test_loss: 2.230076026916504
epoch: 125 training_loss 2.273963454961777 test_loss: 2.260204315185547
epoch: 126 training_loss 2.3225093758106232 test_loss: 2.3469518661499023
epoch: 127 training_loss 2.2890461707115173 test_loss: 2.2025735855102537
epoch: 128 training_loss 2.276185610294342 test_loss: 2.3484703063964845
epoch: 129 training_loss 2.282771006822586 test_loss: 2.372881317138672
epoch: 130 training_loss 2.2209389245510103 test_loss: 2.3454355239868163
epoch: 131 training_loss 2.239432462453842 test_loss: 2.229091835021973
epoch: 132 training_loss 2.210368325710297 test_loss: 2.349213218688965
epoch: 133 training_loss 2.263496745824814 test_loss: 2.3098072052001952
epoch: 134 training_loss 2.23692104101181 test_loss: 2.2864669799804687
epoch: 135 training_loss 2.2630473971366882 test_loss: 2.164169692993164
epoch: 136 training_loss 2.213732216358185 test_loss: 2.2336959838867188
epoch: 137 training_loss 2.221737809181213 test_loss: 2.2021902084350584
epoch: 138 training_loss 2.153937667608261 test_loss: 2.35677433013916
epoch: 139 training_loss 2.240189783573151 test_loss: 2.2832813262939453
epoch: 140 training_loss 2.206869592666626 test_loss: 2.3634851455688475
epoch: 141 training_loss 2.18740780711174 test_loss: 2.2003456115722657
epoch: 142 training_loss 2.209000555276871 test_loss: 2.135173225402832
epoch: 143 training_loss 2.188072820901871 test_loss: 2.2663032531738283
epoch: 144 training_loss 2.178695158958435 test_loss: 2.2538732528686523
epoch: 145 training_loss 2.161768846511841 test_loss: 2.271592712402344
epoch: 146 training_loss 2.193250994682312 test_loss: 2.2086963653564453
epoch: 147 training_loss 2.190455194711685 test_loss: 2.245921516418457
epoch: 148 training_loss 2.118839226961136 test_loss: 2.14846248626709
epoch: 149 training_loss 2.1723687195777894 test_loss: 2.1823471069335936
3104.833485639733
episode: 0 training return: tensor(323.6805, device='cuda:0')
episode: 1 training return: tensor(-206.9727, device='cuda:0')
episode: 2 training return: tensor(319.1415, device='cuda:0')
episode: 3 training return: tensor(285.8640, device='cuda:0')
epoch: 1 test_true_pfm: 3280.2763253792014 sim_pfm: 196.30162511232388
episode: 4 training return: tensor(279.7060, device='cuda:0')
episode: 5 training return: tensor(-175.7108, device='cuda:0')
episode: 6 training return: tensor(377.7776, device='cuda:0')
episode: 7 training return: tensor(392.5726, device='cuda:0')
epoch: 2 test_true_pfm: 2589.065991792469 sim_pfm: 146.57960489063407
episode: 8 training return: tensor(275.9474, device='cuda:0')
episode: 9 training return: tensor(-275.7794, device='cuda:0')
episode: 10 training return: tensor(-28.6897, device='cuda:0')
episode: 11 training return: tensor(-150.6671, device='cuda:0')
epoch: 3 test_true_pfm: 2780.5973333938146 sim_pfm: 22.121520729037
episode: 12 training return: tensor(-195.8746, device='cuda:0')
episode: 13 training return: tensor(-184.6961, device='cuda:0')
episode: 14 training return: tensor(144.8154, device='cuda:0')
episode: 15 training return: tensor(252.8451, device='cuda:0')
epoch: 4 test_true_pfm: 2478.1467100048253 sim_pfm: 248.24516753123802
episode: 16 training return: tensor(299.3468, device='cuda:0')
episode: 17 training return: tensor(244.1076, device='cuda:0')
episode: 18 training return: tensor(-272.9710, device='cuda:0')
episode: 19 training return: tensor(286.8137, device='cuda:0')
epoch: 5 test_true_pfm: 3354.7376377002183 sim_pfm: 169.03755363775417
episode: 20 training return: tensor(363.8687, device='cuda:0')
episode: 21 training return: tensor(286.6132, device='cuda:0')
episode: 22 training return: tensor(259.0921, device='cuda:0')
episode: 23 training return: tensor(195.5454, device='cuda:0')
epoch: 6 test_true_pfm: 2864.080973576071 sim_pfm: 207.21620243927464
episode: 24 training return: tensor(298.0084, device='cuda:0')
episode: 25 training return: tensor(246.5120, device='cuda:0')
episode: 26 training return: tensor(136.3556, device='cuda:0')
episode: 27 training return: tensor(233.0806, device='cuda:0')
epoch: 7 test_true_pfm: 1973.7028075393853 sim_pfm: 189.8798215717931
episode: 28 training return: tensor(-89.9054, device='cuda:0')
episode: 29 training return: tensor(-152.7830, device='cuda:0')
episode: 30 training return: tensor(282.1649, device='cuda:0')
episode: 31 training return: tensor(-171.6476, device='cuda:0')
epoch: 8 test_true_pfm: 2963.4122847796 sim_pfm: 6.685857960217011
episode: 32 training return: tensor(341.2568, device='cuda:0')
episode: 33 training return: tensor(-105.1487, device='cuda:0')
episode: 34 training return: tensor(231.3489, device='cuda:0')
episode: 35 training return: tensor(21.1002, device='cuda:0')
epoch: 9 test_true_pfm: 3423.797658361403 sim_pfm: 188.45815260432815
episode: 36 training return: tensor(355.5939, device='cuda:0')
episode: 37 training return: tensor(-95.4640, device='cuda:0')
episode: 38 training return: tensor(-171.0872, device='cuda:0')
episode: 39 training return: tensor(-139.9483, device='cuda:0')
epoch: 10 test_true_pfm: 3453.8634736462936 sim_pfm: 315.565321965958
episode: 40 training return: tensor(-94.9596, device='cuda:0')
episode: 41 training return: tensor(171.4437, device='cuda:0')
episode: 42 training return: tensor(290.9431, device='cuda:0')
episode: 43 training return: tensor(-150.4905, device='cuda:0')
epoch: 11 test_true_pfm: 2496.805022433256 sim_pfm: 249.77642794997277
episode: 44 training return: tensor(-88.6015, device='cuda:0')
episode: 45 training return: tensor(286.6637, device='cuda:0')
episode: 46 training return: tensor(-289.2911, device='cuda:0')
episode: 47 training return: tensor(-238.1349, device='cuda:0')
epoch: 12 test_true_pfm: 3174.749859028519 sim_pfm: 3.478361639640449
episode: 48 training return: tensor(252.7754, device='cuda:0')
episode: 49 training return: tensor(268.0786, device='cuda:0')
episode: 50 training return: tensor(94.3969, device='cuda:0')
episode: 51 training return: tensor(-161.9903, device='cuda:0')
epoch: 13 test_true_pfm: 2329.275212790626 sim_pfm: 73.95279327807172
episode: 52 training return: tensor(24.8562, device='cuda:0')
episode: 53 training return: tensor(274.0969, device='cuda:0')
episode: 54 training return: tensor(229.3405, device='cuda:0')
episode: 55 training return: tensor(354.4337, device='cuda:0')
epoch: 14 test_true_pfm: 2411.1308524964775 sim_pfm: 316.18109878272907
episode: 56 training return: tensor(46.5870, device='cuda:0')
episode: 57 training return: tensor(250.2158, device='cuda:0')
episode: 58 training return: tensor(182.8658, device='cuda:0')
episode: 59 training return: tensor(312.6812, device='cuda:0')
epoch: 15 test_true_pfm: 3153.5266549816224 sim_pfm: 217.7351027781357
episode: 60 training return: tensor(298.5313, device='cuda:0')
episode: 61 training return: tensor(225.1346, device='cuda:0')
episode: 62 training return: tensor(297.9184, device='cuda:0')
episode: 63 training return: tensor(293.0376, device='cuda:0')
epoch: 16 test_true_pfm: 3357.933908960223 sim_pfm: 339.74103772474336
episode: 64 training return: tensor(-139.5605, device='cuda:0')
episode: 65 training return: tensor(333.7335, device='cuda:0')
episode: 66 training return: tensor(236.2567, device='cuda:0')
episode: 67 training return: tensor(-167.7354, device='cuda:0')
epoch: 17 test_true_pfm: 3376.116084630599 sim_pfm: 119.81562247707431
episode: 68 training return: tensor(253.2163, device='cuda:0')
episode: 69 training return: tensor(315.2386, device='cuda:0')
episode: 70 training return: tensor(190.6448, device='cuda:0')
episode: 71 training return: tensor(249.0667, device='cuda:0')
epoch: 18 test_true_pfm: 3291.4663189881558 sim_pfm: 290.83781007370754
episode: 72 training return: tensor(307.4667, device='cuda:0')
episode: 73 training return: tensor(280.0977, device='cuda:0')
episode: 74 training return: tensor(-272.3310, device='cuda:0')
episode: 75 training return: tensor(280.5964, device='cuda:0')
epoch: 19 test_true_pfm: 3196.622173523922 sim_pfm: 298.45626284258714
episode: 76 training return: tensor(211.4150, device='cuda:0')
episode: 77 training return: tensor(317.3101, device='cuda:0')
episode: 78 training return: tensor(340.2104, device='cuda:0')
episode: 79 training return: tensor(-11.6376, device='cuda:0')
epoch: 20 test_true_pfm: 3343.944480897835 sim_pfm: 290.0207622347419
episode: 80 training return: tensor(196.1531, device='cuda:0')
episode: 81 training return: tensor(325.6106, device='cuda:0')
episode: 82 training return: tensor(-155.4032, device='cuda:0')
episode: 83 training return: tensor(186.7624, device='cuda:0')
epoch: 21 test_true_pfm: 3341.7084830016015 sim_pfm: 313.9603925665918
episode: 84 training return: tensor(102.6898, device='cuda:0')
episode: 85 training return: tensor(281.5251, device='cuda:0')
episode: 86 training return: tensor(115.2153, device='cuda:0')
episode: 87 training return: tensor(281.2035, device='cuda:0')
epoch: 22 test_true_pfm: 3309.508389674162 sim_pfm: 281.70336705991457
episode: 88 training return: tensor(293.8196, device='cuda:0')
episode: 89 training return: tensor(133.9944, device='cuda:0')
episode: 90 training return: tensor(348.1975, device='cuda:0')
episode: 91 training return: tensor(71.2090, device='cuda:0')
epoch: 23 test_true_pfm: 3322.3013101625497 sim_pfm: 222.7578187934414
episode: 92 training return: tensor(242.3930, device='cuda:0')
episode: 93 training return: tensor(288.1515, device='cuda:0')
episode: 94 training return: tensor(271.8669, device='cuda:0')
episode: 95 training return: tensor(308.2873, device='cuda:0')
epoch: 24 test_true_pfm: 3326.3699083576757 sim_pfm: 121.87486292119138
episode: 96 training return: tensor(231.2445, device='cuda:0')
episode: 97 training return: tensor(-142.6802, device='cuda:0')
episode: 98 training return: tensor(327.3292, device='cuda:0')
episode: 99 training return: tensor(321.6390, device='cuda:0')
epoch: 25 test_true_pfm: 3291.242556486303 sim_pfm: 242.60556026672324
episode: 100 training return: tensor(251.3462, device='cuda:0')
episode: 101 training return: tensor(289.3822, device='cuda:0')
episode: 102 training return: tensor(-129.2987, device='cuda:0')
episode: 103 training return: tensor(272.9747, device='cuda:0')
epoch: 26 test_true_pfm: 3378.62112933601 sim_pfm: 219.43436377382992
episode: 104 training return: tensor(287.4781, device='cuda:0')
episode: 105 training return: tensor(376.5829, device='cuda:0')
episode: 106 training return: tensor(343.2010, device='cuda:0')
episode: 107 training return: tensor(287.2436, device='cuda:0')
epoch: 27 test_true_pfm: 3359.1475894185423 sim_pfm: 101.436349414289
episode: 108 training return: tensor(347.5327, device='cuda:0')
episode: 109 training return: tensor(266.2841, device='cuda:0')
episode: 110 training return: tensor(343.7701, device='cuda:0')
episode: 111 training return: tensor(103.9713, device='cuda:0')
epoch: 28 test_true_pfm: 3378.7338557539756 sim_pfm: 314.41430602114025
episode: 112 training return: tensor(-287.6115, device='cuda:0')
episode: 113 training return: tensor(227.2928, device='cuda:0')
episode: 114 training return: tensor(-75.0854, device='cuda:0')
episode: 115 training return: tensor(173.4880, device='cuda:0')
epoch: 29 test_true_pfm: 3347.1019136430864 sim_pfm: 332.61656085349387
episode: 116 training return: tensor(210.0906, device='cuda:0')
episode: 117 training return: tensor(316.0763, device='cuda:0')
episode: 118 training return: tensor(25.2942, device='cuda:0')
episode: 119 training return: tensor(378.2897, device='cuda:0')
epoch: 30 test_true_pfm: 3183.441155906193 sim_pfm: 253.68794500204967
episode: 120 training return: tensor(306.8284, device='cuda:0')
episode: 121 training return: tensor(316.8533, device='cuda:0')
episode: 122 training return: tensor(199.8149, device='cuda:0')
episode: 123 training return: tensor(311.9994, device='cuda:0')
epoch: 31 test_true_pfm: 2936.1239003262976 sim_pfm: 286.48436827406596
episode: 124 training return: tensor(302.2809, device='cuda:0')
episode: 125 training return: tensor(-110.6916, device='cuda:0')
episode: 126 training return: tensor(322.2233, device='cuda:0')
episode: 127 training return: tensor(262.9118, device='cuda:0')
epoch: 32 test_true_pfm: 3158.563933872207 sim_pfm: 340.0148714804479
episode: 128 training return: tensor(141.2732, device='cuda:0')
episode: 129 training return: tensor(339.4446, device='cuda:0')
episode: 130 training return: tensor(408.6872, device='cuda:0')
episode: 131 training return: tensor(302.8621, device='cuda:0')
epoch: 33 test_true_pfm: 2515.1748370064474 sim_pfm: 252.51590443314248
episode: 132 training return: tensor(-135.2364, device='cuda:0')
episode: 133 training return: tensor(-28.9121, device='cuda:0')
episode: 134 training return: tensor(346.4515, device='cuda:0')
episode: 135 training return: tensor(311.8641, device='cuda:0')
epoch: 34 test_true_pfm: 3200.1554255488377 sim_pfm: 338.9574163746147
episode: 136 training return: tensor(250.8508, device='cuda:0')
episode: 137 training return: tensor(345.2305, device='cuda:0')
episode: 138 training return: tensor(-63.8595, device='cuda:0')
episode: 139 training return: tensor(378.2024, device='cuda:0')
epoch: 35 test_true_pfm: 2913.969390537608 sim_pfm: 316.67016522347694
episode: 140 training return: tensor(-11.0375, device='cuda:0')
episode: 141 training return: tensor(253.0761, device='cuda:0')
episode: 142 training return: tensor(238.3012, device='cuda:0')
episode: 143 training return: tensor(298.5374, device='cuda:0')
epoch: 36 test_true_pfm: 3443.3281093089936 sim_pfm: 350.2680363870847
episode: 144 training return: tensor(118.8823, device='cuda:0')
episode: 145 training return: tensor(316.0425, device='cuda:0')
episode: 146 training return: tensor(-2.1360, device='cuda:0')
episode: 147 training return: tensor(-77.2916, device='cuda:0')
epoch: 37 test_true_pfm: 3381.996116186103 sim_pfm: 300.8242864756127
episode: 148 training return: tensor(288.1769, device='cuda:0')
episode: 149 training return: tensor(301.6937, device='cuda:0')
episode: 150 training return: tensor(273.7482, device='cuda:0')
episode: 151 training return: tensor(322.3771, device='cuda:0')
epoch: 38 test_true_pfm: 3341.440268980506 sim_pfm: 324.67422552604694
episode: 152 training return: tensor(140.9078, device='cuda:0')
episode: 153 training return: tensor(45.1707, device='cuda:0')
episode: 154 training return: tensor(-138.6043, device='cuda:0')
episode: 155 training return: tensor(303.2470, device='cuda:0')
epoch: 39 test_true_pfm: 3361.274751692252 sim_pfm: 245.49877467018086
episode: 156 training return: tensor(292.6397, device='cuda:0')
episode: 157 training return: tensor(226.5075, device='cuda:0')
episode: 158 training return: tensor(330.7171, device='cuda:0')
episode: 159 training return: tensor(137.9371, device='cuda:0')
epoch: 40 test_true_pfm: 3376.620848872046 sim_pfm: 290.3770530402932
episode: 160 training return: tensor(-13.1816, device='cuda:0')
episode: 161 training return: tensor(315.8304, device='cuda:0')
episode: 162 training return: tensor(276.2658, device='cuda:0')
episode: 163 training return: tensor(312.7975, device='cuda:0')
epoch: 41 test_true_pfm: 3332.4507397465386 sim_pfm: 304.3028126580369
episode: 164 training return: tensor(-123.6252, device='cuda:0')
episode: 165 training return: tensor(245.6579, device='cuda:0')
episode: 166 training return: tensor(360.7178, device='cuda:0')
episode: 167 training return: tensor(338.6366, device='cuda:0')
epoch: 42 test_true_pfm: 3390.380639979932 sim_pfm: 347.90073374980904
episode: 168 training return: tensor(331.8728, device='cuda:0')
episode: 169 training return: tensor(302.8412, device='cuda:0')
episode: 170 training return: tensor(249.7565, device='cuda:0')
episode: 171 training return: tensor(185.9280, device='cuda:0')
epoch: 43 test_true_pfm: 3394.4467113206647 sim_pfm: 315.1355086818609
episode: 172 training return: tensor(370.0706, device='cuda:0')
episode: 173 training return: tensor(246.2689, device='cuda:0')
episode: 174 training return: tensor(323.7015, device='cuda:0')
episode: 175 training return: tensor(367.5062, device='cuda:0')
epoch: 44 test_true_pfm: 3461.606007137732 sim_pfm: 369.5269661198836
episode: 176 training return: tensor(-439.9456, device='cuda:0')
episode: 177 training return: tensor(356.3127, device='cuda:0')
episode: 178 training return: tensor(313.5287, device='cuda:0')
episode: 179 training return: tensor(311.4326, device='cuda:0')
epoch: 45 test_true_pfm: 3387.464366203954 sim_pfm: 340.8624053149251
episode: 180 training return: tensor(339.6043, device='cuda:0')
episode: 181 training return: tensor(206.0322, device='cuda:0')
episode: 182 training return: tensor(348.3752, device='cuda:0')
episode: 183 training return: tensor(-82.9953, device='cuda:0')
epoch: 46 test_true_pfm: 3371.4555919146574 sim_pfm: 279.78431896595674
episode: 184 training return: tensor(266.2523, device='cuda:0')
episode: 185 training return: tensor(300.7695, device='cuda:0')
episode: 186 training return: tensor(305.9128, device='cuda:0')
episode: 187 training return: tensor(329.0486, device='cuda:0')
epoch: 47 test_true_pfm: 3424.0926224219584 sim_pfm: 324.91654636287905
episode: 188 training return: tensor(346.2174, device='cuda:0')
episode: 189 training return: tensor(346.1965, device='cuda:0')
episode: 190 training return: tensor(426.7842, device='cuda:0')
episode: 191 training return: tensor(292.5135, device='cuda:0')
epoch: 48 test_true_pfm: 3355.3132969211533 sim_pfm: 337.74675648327684
episode: 192 training return: tensor(342.0335, device='cuda:0')
episode: 193 training return: tensor(213.0701, device='cuda:0')
episode: 194 training return: tensor(247.0757, device='cuda:0')
episode: 195 training return: tensor(344.1694, device='cuda:0')
epoch: 49 test_true_pfm: 3381.018186681915 sim_pfm: 344.65315997901297
episode: 196 training return: tensor(323.7448, device='cuda:0')
episode: 197 training return: tensor(189.5710, device='cuda:0')
episode: 198 training return: tensor(326.6762, device='cuda:0')
episode: 199 training return: tensor(321.9664, device='cuda:0')
epoch: 50 test_true_pfm: 3399.139036425786 sim_pfm: 316.9555241414055
episode: 200 training return: tensor(298.1421, device='cuda:0')
episode: 201 training return: tensor(373.7173, device='cuda:0')
episode: 202 training return: tensor(339.2943, device='cuda:0')
episode: 203 training return: tensor(-99.1365, device='cuda:0')
epoch: 51 test_true_pfm: 3416.496085405741 sim_pfm: 197.50860361929517
episode: 204 training return: tensor(338.5438, device='cuda:0')
episode: 205 training return: tensor(81.0649, device='cuda:0')
episode: 206 training return: tensor(343.6001, device='cuda:0')
episode: 207 training return: tensor(292.5042, device='cuda:0')
epoch: 52 test_true_pfm: 3360.932863245472 sim_pfm: 353.23182387258083
episode: 208 training return: tensor(326.5666, device='cuda:0')
episode: 209 training return: tensor(286.4573, device='cuda:0')
episode: 210 training return: tensor(263.1989, device='cuda:0')
episode: 211 training return: tensor(294.1497, device='cuda:0')
epoch: 53 test_true_pfm: 3113.885217222911 sim_pfm: 279.2147555804889
episode: 212 training return: tensor(-145.7081, device='cuda:0')
episode: 213 training return: tensor(-178.5854, device='cuda:0')
episode: 214 training return: tensor(-102.8718, device='cuda:0')
episode: 215 training return: tensor(-138.0666, device='cuda:0')
epoch: 54 test_true_pfm: 3405.9096498617223 sim_pfm: 337.60141229015426
episode: 216 training return: tensor(412.2631, device='cuda:0')
episode: 217 training return: tensor(264.1029, device='cuda:0')
episode: 218 training return: tensor(312.4471, device='cuda:0')
episode: 219 training return: tensor(352.4174, device='cuda:0')
epoch: 55 test_true_pfm: 3385.7693587543604 sim_pfm: 298.91708379925694
episode: 220 training return: tensor(312.6767, device='cuda:0')
episode: 221 training return: tensor(336.1297, device='cuda:0')
episode: 222 training return: tensor(151.3720, device='cuda:0')
episode: 223 training return: tensor(295.5400, device='cuda:0')
epoch: 56 test_true_pfm: 3435.8176359727545 sim_pfm: 311.3738406896591
episode: 224 training return: tensor(328.7355, device='cuda:0')
episode: 225 training return: tensor(170.3315, device='cuda:0')
episode: 226 training return: tensor(280.7390, device='cuda:0')
episode: 227 training return: tensor(340.4705, device='cuda:0')
epoch: 57 test_true_pfm: 3092.3613777940395 sim_pfm: -3.3933984666849333
episode: 228 training return: tensor(337.6494, device='cuda:0')
episode: 229 training return: tensor(287.1007, device='cuda:0')
episode: 230 training return: tensor(306.3955, device='cuda:0')
episode: 231 training return: tensor(307.8750, device='cuda:0')
epoch: 58 test_true_pfm: 3384.58990098987 sim_pfm: 352.4424557763268
episode: 232 training return: tensor(290.3911, device='cuda:0')
episode: 233 training return: tensor(333.1596, device='cuda:0')
episode: 234 training return: tensor(327.8891, device='cuda:0')
episode: 235 training return: tensor(360.0570, device='cuda:0')
epoch: 59 test_true_pfm: 3384.4507920918063 sim_pfm: 352.9525307823981
episode: 236 training return: tensor(326.9235, device='cuda:0')
episode: 237 training return: tensor(336.9915, device='cuda:0')
episode: 238 training return: tensor(347.4521, device='cuda:0')
episode: 239 training return: tensor(390.7969, device='cuda:0')
epoch: 60 test_true_pfm: 3389.5963612915907 sim_pfm: 274.2162038088233
episode: 240 training return: tensor(326.6445, device='cuda:0')
episode: 241 training return: tensor(287.2911, device='cuda:0')
episode: 242 training return: tensor(309.2393, device='cuda:0')
episode: 243 training return: tensor(289.6227, device='cuda:0')
epoch: 61 test_true_pfm: 3355.7056858482683 sim_pfm: 349.32278596852365
episode: 244 training return: tensor(286.1726, device='cuda:0')
episode: 245 training return: tensor(354.7849, device='cuda:0')
episode: 246 training return: tensor(374.7560, device='cuda:0')
episode: 247 training return: tensor(278.4066, device='cuda:0')
epoch: 62 test_true_pfm: 3437.5318998792104 sim_pfm: 327.69091309885454
episode: 248 training return: tensor(327.3790, device='cuda:0')
episode: 249 training return: tensor(333.4756, device='cuda:0')
episode: 250 training return: tensor(336.7179, device='cuda:0')
episode: 251 training return: tensor(-48.1080, device='cuda:0')
epoch: 63 test_true_pfm: 3373.244632164358 sim_pfm: 187.48370629156125
episode: 252 training return: tensor(176.8029, device='cuda:0')
episode: 253 training return: tensor(-60.2974, device='cuda:0')
episode: 254 training return: tensor(296.1004, device='cuda:0')
episode: 255 training return: tensor(314.0485, device='cuda:0')
epoch: 64 test_true_pfm: 2998.287922902595 sim_pfm: 327.4659854569084
episode: 256 training return: tensor(111.7960, device='cuda:0')
episode: 257 training return: tensor(257.2953, device='cuda:0')
episode: 258 training return: tensor(303.4963, device='cuda:0')
episode: 259 training return: tensor(391.8813, device='cuda:0')
epoch: 65 test_true_pfm: 2695.9899016390605 sim_pfm: 309.8964149598323
episode: 260 training return: tensor(187.9303, device='cuda:0')
episode: 261 training return: tensor(330.5695, device='cuda:0')
episode: 262 training return: tensor(362.4137, device='cuda:0')
episode: 263 training return: tensor(382.7936, device='cuda:0')
epoch: 66 test_true_pfm: 3341.165091779209 sim_pfm: 346.62070791926817
episode: 264 training return: tensor(332.8784, device='cuda:0')
episode: 265 training return: tensor(326.5467, device='cuda:0')
episode: 266 training return: tensor(270.6233, device='cuda:0')
episode: 267 training return: tensor(381.9814, device='cuda:0')
epoch: 67 test_true_pfm: 3397.0438529283906 sim_pfm: 212.6584065859788
episode: 268 training return: tensor(396.6946, device='cuda:0')
episode: 269 training return: tensor(298.7500, device='cuda:0')
episode: 270 training return: tensor(303.4998, device='cuda:0')
episode: 271 training return: tensor(328.1057, device='cuda:0')
epoch: 68 test_true_pfm: 3393.685197419158 sim_pfm: 315.5080847288288
episode: 272 training return: tensor(345.8206, device='cuda:0')
episode: 273 training return: tensor(-268.8223, device='cuda:0')
episode: 274 training return: tensor(328.8305, device='cuda:0')
episode: 275 training return: tensor(365.1360, device='cuda:0')
epoch: 69 test_true_pfm: 3278.601865329311 sim_pfm: 317.65675129929633
episode: 276 training return: tensor(173.0071, device='cuda:0')
episode: 277 training return: tensor(300.9362, device='cuda:0')
episode: 278 training return: tensor(277.8096, device='cuda:0')
episode: 279 training return: tensor(331.7300, device='cuda:0')
epoch: 70 test_true_pfm: 3409.8356098647873 sim_pfm: 341.2156425546952
episode: 280 training return: tensor(336.0131, device='cuda:0')
episode: 281 training return: tensor(10.6205, device='cuda:0')
episode: 282 training return: tensor(166.2923, device='cuda:0')
episode: 283 training return: tensor(62.6109, device='cuda:0')
epoch: 71 test_true_pfm: 3411.2854012638286 sim_pfm: 343.9146457007543
episode: 284 training return: tensor(255.1778, device='cuda:0')
episode: 285 training return: tensor(351.5287, device='cuda:0')
episode: 286 training return: tensor(330.1402, device='cuda:0')
episode: 287 training return: tensor(346.0232, device='cuda:0')
epoch: 72 test_true_pfm: 3388.6108136047224 sim_pfm: 334.0889466793257
episode: 288 training return: tensor(329.4968, device='cuda:0')
episode: 289 training return: tensor(-131.5542, device='cuda:0')
episode: 290 training return: tensor(295.2593, device='cuda:0')
episode: 291 training return: tensor(-225.0077, device='cuda:0')
epoch: 73 test_true_pfm: 3374.816025043172 sim_pfm: 296.17117774352664
episode: 292 training return: tensor(259.0318, device='cuda:0')
episode: 293 training return: tensor(298.6767, device='cuda:0')
episode: 294 training return: tensor(252.7179, device='cuda:0')
episode: 295 training return: tensor(394.9159, device='cuda:0')
epoch: 74 test_true_pfm: 3063.8338928190265 sim_pfm: 300.6659085916278
episode: 296 training return: tensor(310.2621, device='cuda:0')
episode: 297 training return: tensor(331.9082, device='cuda:0')
episode: 298 training return: tensor(345.3606, device='cuda:0')
episode: 299 training return: tensor(-29.3832, device='cuda:0')
epoch: 75 test_true_pfm: 3396.056777898157 sim_pfm: 312.8854963988997
episode: 300 training return: tensor(326.3606, device='cuda:0')
episode: 301 training return: tensor(371.8413, device='cuda:0')
episode: 302 training return: tensor(283.5917, device='cuda:0')
episode: 303 training return: tensor(-145.8231, device='cuda:0')
epoch: 76 test_true_pfm: 3408.2628799063295 sim_pfm: 319.98975889759214
episode: 304 training return: tensor(255.2468, device='cuda:0')
episode: 305 training return: tensor(-175.9848, device='cuda:0')
episode: 306 training return: tensor(287.4163, device='cuda:0')
episode: 307 training return: tensor(310.5503, device='cuda:0')
epoch: 77 test_true_pfm: 3410.961068922874 sim_pfm: 359.1435133097111
episode: 308 training return: tensor(339.9849, device='cuda:0')
episode: 309 training return: tensor(241.7879, device='cuda:0')
episode: 310 training return: tensor(302.3327, device='cuda:0')
episode: 311 training return: tensor(365.9141, device='cuda:0')
epoch: 78 test_true_pfm: 3348.4377346882125 sim_pfm: 337.8635214481037
episode: 312 training return: tensor(354.0870, device='cuda:0')
episode: 313 training return: tensor(357.0062, device='cuda:0')
episode: 314 training return: tensor(341.7413, device='cuda:0')
episode: 315 training return: tensor(349.8029, device='cuda:0')
epoch: 79 test_true_pfm: 3032.6717352623778 sim_pfm: -36.42255365011321
episode: 316 training return: tensor(315.1234, device='cuda:0')
episode: 317 training return: tensor(215.0074, device='cuda:0')
episode: 318 training return: tensor(38.3346, device='cuda:0')
episode: 319 training return: tensor(225.7713, device='cuda:0')
epoch: 80 test_true_pfm: 3520.9527862399896 sim_pfm: 359.0585852559113
episode: 320 training return: tensor(399.2844, device='cuda:0')
episode: 321 training return: tensor(75.0246, device='cuda:0')
episode: 322 training return: tensor(300.3213, device='cuda:0')
episode: 323 training return: tensor(-117.1898, device='cuda:0')
epoch: 81 test_true_pfm: 3264.2968821666086 sim_pfm: 316.17240625879884
episode: 324 training return: tensor(330.7662, device='cuda:0')
episode: 325 training return: tensor(331.3837, device='cuda:0')
episode: 326 training return: tensor(378.3310, device='cuda:0')
episode: 327 training return: tensor(303.9259, device='cuda:0')
epoch: 82 test_true_pfm: 3362.5959049972685 sim_pfm: 368.53005458639626
episode: 328 training return: tensor(311.0462, device='cuda:0')
episode: 329 training return: tensor(304.4771, device='cuda:0')
episode: 330 training return: tensor(247.2136, device='cuda:0')
episode: 331 training return: tensor(-60.0086, device='cuda:0')
epoch: 83 test_true_pfm: 2906.367695874534 sim_pfm: 309.46356616385555
episode: 332 training return: tensor(224.1921, device='cuda:0')
episode: 333 training return: tensor(106.6176, device='cuda:0')
episode: 334 training return: tensor(298.2882, device='cuda:0')
episode: 335 training return: tensor(323.2822, device='cuda:0')
epoch: 84 test_true_pfm: 3433.009778087579 sim_pfm: 294.8937001184483
episode: 336 training return: tensor(294.6484, device='cuda:0')
episode: 337 training return: tensor(306.4744, device='cuda:0')
episode: 338 training return: tensor(293.7069, device='cuda:0')
episode: 339 training return: tensor(372.0387, device='cuda:0')
epoch: 85 test_true_pfm: 3450.2724256619767 sim_pfm: 338.1811623353472
episode: 340 training return: tensor(265.5448, device='cuda:0')
episode: 341 training return: tensor(263.2748, device='cuda:0')
episode: 342 training return: tensor(341.9057, device='cuda:0')
episode: 343 training return: tensor(293.8750, device='cuda:0')
epoch: 86 test_true_pfm: 3097.796412972672 sim_pfm: 288.5831699107366
episode: 344 training return: tensor(283.0206, device='cuda:0')
episode: 345 training return: tensor(356.5911, device='cuda:0')
episode: 346 training return: tensor(281.9401, device='cuda:0')
episode: 347 training return: tensor(349.3106, device='cuda:0')
epoch: 87 test_true_pfm: 3345.8521783335377 sim_pfm: 298.62265021473286
episode: 348 training return: tensor(336.8969, device='cuda:0')
episode: 349 training return: tensor(351.8526, device='cuda:0')
episode: 350 training return: tensor(255.1447, device='cuda:0')
episode: 351 training return: tensor(304.0277, device='cuda:0')
epoch: 88 test_true_pfm: 3408.593692849439 sim_pfm: 343.99590883157606
episode: 352 training return: tensor(327.3524, device='cuda:0')
episode: 353 training return: tensor(214.8262, device='cuda:0')
episode: 354 training return: tensor(287.2982, device='cuda:0')
episode: 355 training return: tensor(351.3195, device='cuda:0')
epoch: 89 test_true_pfm: 3349.270508497188 sim_pfm: 325.7273029142719
episode: 356 training return: tensor(294.0477, device='cuda:0')
episode: 357 training return: tensor(381.4130, device='cuda:0')
episode: 358 training return: tensor(293.5221, device='cuda:0')
episode: 359 training return: tensor(304.9300, device='cuda:0')
epoch: 90 test_true_pfm: 3357.1716113400926 sim_pfm: 366.65588122587843
episode: 360 training return: tensor(313.8800, device='cuda:0')
episode: 361 training return: tensor(281.9976, device='cuda:0')
episode: 362 training return: tensor(307.7110, device='cuda:0')
episode: 363 training return: tensor(311.6106, device='cuda:0')
epoch: 91 test_true_pfm: 3398.86351716036 sim_pfm: 303.28443184378557
episode: 364 training return: tensor(-279.3327, device='cuda:0')
episode: 365 training return: tensor(319.4624, device='cuda:0')
episode: 366 training return: tensor(305.8629, device='cuda:0')
episode: 367 training return: tensor(311.7033, device='cuda:0')
epoch: 92 test_true_pfm: 3326.111094001957 sim_pfm: 342.9627077402547
episode: 368 training return: tensor(330.4744, device='cuda:0')
episode: 369 training return: tensor(300.3230, device='cuda:0')
episode: 370 training return: tensor(336.9308, device='cuda:0')
episode: 371 training return: tensor(341.8127, device='cuda:0')
epoch: 93 test_true_pfm: 3401.8906576429595 sim_pfm: 335.7580687000397
episode: 372 training return: tensor(335.2279, device='cuda:0')
episode: 373 training return: tensor(247.7348, device='cuda:0')
episode: 374 training return: tensor(360.5615, device='cuda:0')
episode: 375 training return: tensor(325.2857, device='cuda:0')
epoch: 94 test_true_pfm: 3127.855393735934 sim_pfm: 332.2862906923983
episode: 376 training return: tensor(349.2603, device='cuda:0')
episode: 377 training return: tensor(206.0204, device='cuda:0')
episode: 378 training return: tensor(307.1618, device='cuda:0')
episode: 379 training return: tensor(147.4014, device='cuda:0')
epoch: 95 test_true_pfm: 3443.889203210023 sim_pfm: 335.05109644071973
episode: 380 training return: tensor(335.3429, device='cuda:0')
episode: 381 training return: tensor(315.5755, device='cuda:0')
episode: 382 training return: tensor(324.6687, device='cuda:0')
episode: 383 training return: tensor(265.9670, device='cuda:0')
epoch: 96 test_true_pfm: 3344.2915876146744 sim_pfm: 358.7481393466781
episode: 384 training return: tensor(395.7075, device='cuda:0')
episode: 385 training return: tensor(325.8813, device='cuda:0')
episode: 386 training return: tensor(305.1396, device='cuda:0')
episode: 387 training return: tensor(312.4678, device='cuda:0')
epoch: 97 test_true_pfm: 3410.257530705591 sim_pfm: 274.7219199091293
episode: 388 training return: tensor(379.4595, device='cuda:0')
episode: 389 training return: tensor(319.6942, device='cuda:0')
episode: 390 training return: tensor(284.6270, device='cuda:0')
episode: 391 training return: tensor(287.4381, device='cuda:0')
epoch: 98 test_true_pfm: 3428.436689834476 sim_pfm: 297.4791338894186
episode: 392 training return: tensor(265.2202, device='cuda:0')
episode: 393 training return: tensor(365.0440, device='cuda:0')
episode: 394 training return: tensor(327.8419, device='cuda:0')
episode: 395 training return: tensor(152.9399, device='cuda:0')
epoch: 99 test_true_pfm: 3402.1109588386475 sim_pfm: 353.3158194000134
episode: 396 training return: tensor(268.0188, device='cuda:0')
episode: 397 training return: tensor(344.4648, device='cuda:0')
episode: 398 training return: tensor(332.2531, device='cuda:0')
episode: 399 training return: tensor(304.1972, device='cuda:0')
epoch: 100 test_true_pfm: 3417.1123709889525 sim_pfm: 278.51554218718474
episode: 400 training return: tensor(309.3804, device='cuda:0')
episode: 401 training return: tensor(295.4229, device='cuda:0')
episode: 402 training return: tensor(308.6965, device='cuda:0')
episode: 403 training return: tensor(310.4479, device='cuda:0')
epoch: 101 test_true_pfm: 3393.6439516898754 sim_pfm: 341.2308083682631
episode: 404 training return: tensor(359.0872, device='cuda:0')
episode: 405 training return: tensor(346.3018, device='cuda:0')
episode: 406 training return: tensor(320.8154, device='cuda:0')
episode: 407 training return: tensor(296.9588, device='cuda:0')
epoch: 102 test_true_pfm: 3425.353167450104 sim_pfm: 377.1700646627578
episode: 408 training return: tensor(358.8773, device='cuda:0')
episode: 409 training return: tensor(284.4308, device='cuda:0')
episode: 410 training return: tensor(382.1983, device='cuda:0')
episode: 411 training return: tensor(352.8896, device='cuda:0')
epoch: 103 test_true_pfm: 3373.237357387076 sim_pfm: 348.00806174658163
episode: 412 training return: tensor(277.0121, device='cuda:0')
episode: 413 training return: tensor(315.6893, device='cuda:0')
episode: 414 training return: tensor(68.6819, device='cuda:0')
episode: 415 training return: tensor(333.2773, device='cuda:0')
epoch: 104 test_true_pfm: 3402.0824417990066 sim_pfm: 301.5970856074321
episode: 416 training return: tensor(344.3578, device='cuda:0')
episode: 417 training return: tensor(323.4995, device='cuda:0')
episode: 418 training return: tensor(-140.9427, device='cuda:0')
episode: 419 training return: tensor(337.1489, device='cuda:0')
epoch: 105 test_true_pfm: 3465.4568560712705 sim_pfm: 383.3758862623169
episode: 420 training return: tensor(352.5226, device='cuda:0')
episode: 421 training return: tensor(309.9888, device='cuda:0')
episode: 422 training return: tensor(297.0569, device='cuda:0')
episode: 423 training return: tensor(331.3051, device='cuda:0')
epoch: 106 test_true_pfm: 2989.8947435797622 sim_pfm: 210.56346994735455
episode: 424 training return: tensor(293.7343, device='cuda:0')
episode: 425 training return: tensor(262.7653, device='cuda:0')
episode: 426 training return: tensor(306.6049, device='cuda:0')
episode: 427 training return: tensor(283.4797, device='cuda:0')
epoch: 107 test_true_pfm: 3436.7593115451095 sim_pfm: 359.78321176956524
episode: 428 training return: tensor(328.8834, device='cuda:0')
episode: 429 training return: tensor(323.2143, device='cuda:0')
episode: 430 training return: tensor(297.1109, device='cuda:0')
episode: 431 training return: tensor(352.2468, device='cuda:0')
epoch: 108 test_true_pfm: 3407.27590147214 sim_pfm: 330.79459121732117
episode: 432 training return: tensor(340.0785, device='cuda:0')
episode: 433 training return: tensor(338.8015, device='cuda:0')
episode: 434 training return: tensor(263.4589, device='cuda:0')
episode: 435 training return: tensor(283.3620, device='cuda:0')
epoch: 109 test_true_pfm: 3388.924492533822 sim_pfm: 355.24618011462735
episode: 436 training return: tensor(17.5045, device='cuda:0')
episode: 437 training return: tensor(319.0253, device='cuda:0')
episode: 438 training return: tensor(333.9027, device='cuda:0')
episode: 439 training return: tensor(319.2460, device='cuda:0')
epoch: 110 test_true_pfm: 3372.5715429617667 sim_pfm: 343.0000054082775
episode: 440 training return: tensor(301.8448, device='cuda:0')
episode: 441 training return: tensor(393.6488, device='cuda:0')
episode: 442 training return: tensor(286.2467, device='cuda:0')
episode: 443 training return: tensor(298.3065, device='cuda:0')
epoch: 111 test_true_pfm: 3416.980123061816 sim_pfm: 339.1762570323772
episode: 444 training return: tensor(351.1031, device='cuda:0')
episode: 445 training return: tensor(-74.8372, device='cuda:0')
episode: 446 training return: tensor(179.4422, device='cuda:0')
episode: 447 training return: tensor(359.7894, device='cuda:0')
epoch: 112 test_true_pfm: 3407.6742271281087 sim_pfm: 361.74174781970214
episode: 448 training return: tensor(369.7633, device='cuda:0')
episode: 449 training return: tensor(362.7047, device='cuda:0')
episode: 450 training return: tensor(336.2521, device='cuda:0')
episode: 451 training return: tensor(312.3468, device='cuda:0')
epoch: 113 test_true_pfm: 3027.49962697352 sim_pfm: 322.1754343862024
episode: 452 training return: tensor(331.9183, device='cuda:0')
episode: 453 training return: tensor(39.2248, device='cuda:0')
episode: 454 training return: tensor(295.9807, device='cuda:0')
episode: 455 training return: tensor(170.4314, device='cuda:0')
epoch: 114 test_true_pfm: 3474.4655949476205 sim_pfm: 365.822440178735
episode: 456 training return: tensor(311.3455, device='cuda:0')
episode: 457 training return: tensor(247.6038, device='cuda:0')
episode: 458 training return: tensor(336.2367, device='cuda:0')
episode: 459 training return: tensor(315.9678, device='cuda:0')
epoch: 115 test_true_pfm: 3427.5508867442563 sim_pfm: 356.1800831192425
episode: 460 training return: tensor(302.8675, device='cuda:0')
episode: 461 training return: tensor(321.3503, device='cuda:0')
episode: 462 training return: tensor(351.5664, device='cuda:0')
episode: 463 training return: tensor(313.1756, device='cuda:0')
epoch: 116 test_true_pfm: 2027.8108733723084 sim_pfm: 350.7950434196003
episode: 464 training return: tensor(278.1205, device='cuda:0')
episode: 465 training return: tensor(328.9203, device='cuda:0')
episode: 466 training return: tensor(342.9840, device='cuda:0')
episode: 467 training return: tensor(375.4341, device='cuda:0')
epoch: 117 test_true_pfm: 3400.192067085893 sim_pfm: 351.41741419999744
episode: 468 training return: tensor(37.9899, device='cuda:0')
episode: 469 training return: tensor(286.1280, device='cuda:0')
episode: 470 training return: tensor(375.8375, device='cuda:0')
episode: 471 training return: tensor(361.7185, device='cuda:0')
epoch: 118 test_true_pfm: 3403.5130825083384 sim_pfm: 293.0634305043107
episode: 472 training return: tensor(390.2035, device='cuda:0')
episode: 473 training return: tensor(301.4033, device='cuda:0')
episode: 474 training return: tensor(319.9518, device='cuda:0')
episode: 475 training return: tensor(287.3839, device='cuda:0')
epoch: 119 test_true_pfm: 3417.964644409432 sim_pfm: 341.93697906227317
episode: 476 training return: tensor(307.9873, device='cuda:0')
episode: 477 training return: tensor(100.8668, device='cuda:0')
episode: 478 training return: tensor(313.6186, device='cuda:0')
episode: 479 training return: tensor(311.2059, device='cuda:0')
epoch: 120 test_true_pfm: 3416.699416726118 sim_pfm: 308.75239267082844
episode: 480 training return: tensor(316.2748, device='cuda:0')
episode: 481 training return: tensor(-126.5181, device='cuda:0')
episode: 482 training return: tensor(353.0024, device='cuda:0')
episode: 483 training return: tensor(293.8226, device='cuda:0')
epoch: 121 test_true_pfm: 3202.4716942432683 sim_pfm: 298.0837162961737
episode: 484 training return: tensor(285.6399, device='cuda:0')
episode: 485 training return: tensor(362.0668, device='cuda:0')
episode: 486 training return: tensor(361.4909, device='cuda:0')
episode: 487 training return: tensor(347.1986, device='cuda:0')
epoch: 122 test_true_pfm: 3410.6599873519467 sim_pfm: 340.29450628215756
episode: 488 training return: tensor(344.4310, device='cuda:0')
episode: 489 training return: tensor(325.3255, device='cuda:0')
episode: 490 training return: tensor(350.3036, device='cuda:0')
episode: 491 training return: tensor(314.3190, device='cuda:0')
epoch: 123 test_true_pfm: 3328.2523712354373 sim_pfm: 265.44168868598837
episode: 492 training return: tensor(372.5165, device='cuda:0')
episode: 493 training return: tensor(286.2018, device='cuda:0')
episode: 494 training return: tensor(292.4480, device='cuda:0')
episode: 495 training return: tensor(290.3909, device='cuda:0')
epoch: 124 test_true_pfm: 3304.921854636303 sim_pfm: 300.6426747586229
episode: 496 training return: tensor(179.1665, device='cuda:0')
episode: 497 training return: tensor(376.9738, device='cuda:0')
episode: 498 training return: tensor(288.9926, device='cuda:0')
episode: 499 training return: tensor(155.6880, device='cuda:0')
epoch: 125 test_true_pfm: 3111.6654068966254 sim_pfm: 352.80372731005383
episode: 500 training return: tensor(-117.8562, device='cuda:0')
episode: 501 training return: tensor(313.1177, device='cuda:0')
episode: 502 training return: tensor(309.1377, device='cuda:0')
episode: 503 training return: tensor(325.9358, device='cuda:0')
epoch: 126 test_true_pfm: 3430.6203838468778 sim_pfm: 352.65789847343694
episode: 504 training return: tensor(298.9975, device='cuda:0')
episode: 505 training return: tensor(355.5403, device='cuda:0')
episode: 506 training return: tensor(365.2279, device='cuda:0')
episode: 507 training return: tensor(323.0412, device='cuda:0')
epoch: 127 test_true_pfm: 3441.289206185578 sim_pfm: 350.24166065605823
episode: 508 training return: tensor(312.2335, device='cuda:0')
episode: 509 training return: tensor(317.2942, device='cuda:0')
episode: 510 training return: tensor(383.8779, device='cuda:0')
episode: 511 training return: tensor(329.0808, device='cuda:0')
epoch: 128 test_true_pfm: 3382.6428043159904 sim_pfm: 377.5449177804985
episode: 512 training return: tensor(335.4453, device='cuda:0')
episode: 513 training return: tensor(331.8746, device='cuda:0')
episode: 514 training return: tensor(309.2304, device='cuda:0')
episode: 515 training return: tensor(143.1801, device='cuda:0')
epoch: 129 test_true_pfm: 3461.6108084497537 sim_pfm: 351.4010114968114
episode: 516 training return: tensor(244.5094, device='cuda:0')
episode: 517 training return: tensor(323.7775, device='cuda:0')
episode: 518 training return: tensor(323.9561, device='cuda:0')
episode: 519 training return: tensor(329.9288, device='cuda:0')
epoch: 130 test_true_pfm: 3457.035956138738 sim_pfm: 364.7575225320179
episode: 520 training return: tensor(317.5631, device='cuda:0')
episode: 521 training return: tensor(359.4347, device='cuda:0')
episode: 522 training return: tensor(338.8000, device='cuda:0')
episode: 523 training return: tensor(3.3871, device='cuda:0')
epoch: 131 test_true_pfm: 3362.2223652513603 sim_pfm: 335.0076510686583
episode: 524 training return: tensor(336.7178, device='cuda:0')
episode: 525 training return: tensor(329.9348, device='cuda:0')
episode: 526 training return: tensor(361.1005, device='cuda:0')
episode: 527 training return: tensor(318.6983, device='cuda:0')
epoch: 132 test_true_pfm: 3379.1123218622565 sim_pfm: 302.5604115392974
episode: 528 training return: tensor(291.8008, device='cuda:0')
episode: 529 training return: tensor(204.6171, device='cuda:0')
episode: 530 training return: tensor(329.0597, device='cuda:0')
episode: 531 training return: tensor(340.9019, device='cuda:0')
epoch: 133 test_true_pfm: 2481.4603926610107 sim_pfm: 178.26695252200201
episode: 532 training return: tensor(312.7130, device='cuda:0')
episode: 533 training return: tensor(299.3105, device='cuda:0')
episode: 534 training return: tensor(58.4798, device='cuda:0')
episode: 535 training return: tensor(325.8403, device='cuda:0')
epoch: 134 test_true_pfm: 3397.8067507392957 sim_pfm: 367.0176466174501
episode: 536 training return: tensor(313.2039, device='cuda:0')
episode: 537 training return: tensor(305.4647, device='cuda:0')
episode: 538 training return: tensor(294.3766, device='cuda:0')
episode: 539 training return: tensor(295.4480, device='cuda:0')
epoch: 135 test_true_pfm: 3419.157206148484 sim_pfm: 373.14537205269636
episode: 540 training return: tensor(362.8124, device='cuda:0')
episode: 541 training return: tensor(367.0770, device='cuda:0')
episode: 542 training return: tensor(348.0648, device='cuda:0')
episode: 543 training return: tensor(355.2067, device='cuda:0')
epoch: 136 test_true_pfm: 3409.014621170396 sim_pfm: 325.21148626886617
episode: 544 training return: tensor(238.6940, device='cuda:0')
episode: 545 training return: tensor(297.5509, device='cuda:0')
episode: 546 training return: tensor(331.7043, device='cuda:0')
episode: 547 training return: tensor(351.2280, device='cuda:0')
epoch: 137 test_true_pfm: 3389.5512147398967 sim_pfm: 357.6992439672176
episode: 548 training return: tensor(379.6545, device='cuda:0')
episode: 549 training return: tensor(285.1876, device='cuda:0')
episode: 550 training return: tensor(284.4879, device='cuda:0')
episode: 551 training return: tensor(308.8243, device='cuda:0')
epoch: 138 test_true_pfm: 3265.0089214533787 sim_pfm: 391.25671119679464
episode: 552 training return: tensor(332.5032, device='cuda:0')
episode: 553 training return: tensor(334.7388, device='cuda:0')
episode: 554 training return: tensor(350.5886, device='cuda:0')
episode: 555 training return: tensor(355.2392, device='cuda:0')
epoch: 139 test_true_pfm: 3454.745848065779 sim_pfm: 306.88782481773524
episode: 556 training return: tensor(338.8387, device='cuda:0')
episode: 557 training return: tensor(327.2048, device='cuda:0')
episode: 558 training return: tensor(394.0078, device='cuda:0')
episode: 559 training return: tensor(345.1768, device='cuda:0')
epoch: 140 test_true_pfm: 3453.898692434435 sim_pfm: 378.1866198349647
episode: 560 training return: tensor(318.1317, device='cuda:0')
episode: 561 training return: tensor(358.8795, device='cuda:0')
episode: 562 training return: tensor(351.0166, device='cuda:0')
episode: 563 training return: tensor(344.1869, device='cuda:0')
epoch: 141 test_true_pfm: 3483.5626897820644 sim_pfm: 359.123211803555
episode: 564 training return: tensor(371.3540, device='cuda:0')
episode: 565 training return: tensor(378.3724, device='cuda:0')
episode: 566 training return: tensor(308.6012, device='cuda:0')
episode: 567 training return: tensor(293.3570, device='cuda:0')
epoch: 142 test_true_pfm: 3417.6184961032845 sim_pfm: 336.74038069367333
episode: 568 training return: tensor(349.3758, device='cuda:0')
episode: 569 training return: tensor(329.1638, device='cuda:0')
episode: 570 training return: tensor(294.2211, device='cuda:0')
episode: 571 training return: tensor(272.2325, device='cuda:0')
epoch: 143 test_true_pfm: 3436.930159237178 sim_pfm: 340.57210266592057
episode: 572 training return: tensor(315.8920, device='cuda:0')
episode: 573 training return: tensor(322.5011, device='cuda:0')
episode: 574 training return: tensor(364.3548, device='cuda:0')
episode: 575 training return: tensor(72.0144, device='cuda:0')
epoch: 144 test_true_pfm: 3447.9279822562735 sim_pfm: 359.38328490635223
episode: 576 training return: tensor(357.0818, device='cuda:0')
episode: 577 training return: tensor(357.8457, device='cuda:0')
episode: 578 training return: tensor(-54.7601, device='cuda:0')
episode: 579 training return: tensor(338.4591, device='cuda:0')
epoch: 145 test_true_pfm: 3441.1585687384927 sim_pfm: 338.276616842777
episode: 580 training return: tensor(285.7454, device='cuda:0')
episode: 581 training return: tensor(362.9126, device='cuda:0')
episode: 582 training return: tensor(304.6627, device='cuda:0')
episode: 583 training return: tensor(373.4649, device='cuda:0')
epoch: 146 test_true_pfm: 3427.510737021983 sim_pfm: 359.1363119104353
episode: 584 training return: tensor(362.5703, device='cuda:0')
episode: 585 training return: tensor(347.3536, device='cuda:0')
episode: 586 training return: tensor(364.6653, device='cuda:0')
episode: 587 training return: tensor(326.2929, device='cuda:0')
epoch: 147 test_true_pfm: 3397.3618185440696 sim_pfm: 335.9211185010111
episode: 588 training return: tensor(291.0929, device='cuda:0')
episode: 589 training return: tensor(290.4626, device='cuda:0')
episode: 590 training return: tensor(194.2323, device='cuda:0')
episode: 591 training return: tensor(360.6339, device='cuda:0')
epoch: 148 test_true_pfm: 3495.4423617280195 sim_pfm: 416.566421610148
episode: 592 training return: tensor(380.7707, device='cuda:0')
episode: 593 training return: tensor(354.0512, device='cuda:0')
episode: 594 training return: tensor(316.1620, device='cuda:0')
episode: 595 training return: tensor(423.4496, device='cuda:0')
epoch: 149 test_true_pfm: 3296.389201546868 sim_pfm: 350.92354608485283
episode: 596 training return: tensor(283.9670, device='cuda:0')
episode: 597 training return: tensor(315.9875, device='cuda:0')
episode: 598 training return: tensor(322.6068, device='cuda:0')
episode: 599 training return: tensor(276.9315, device='cuda:0')
epoch: 150 test_true_pfm: 3041.933533968258 sim_pfm: 346.78854534980684
