['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'behavior', '--traj', 'medium', '--seed', '2', '--data', '10000']
epoch: 0 training_loss 0.3091599203646183 test_loss: 0.21376233100891112
epoch: 1 training_loss 0.16162563912570477 test_loss: 0.1830069303512573
epoch: 2 training_loss 0.13866564203053713 test_loss: 0.12860153913497924
epoch: 3 training_loss 0.11740668535232544 test_loss: 0.1395420551300049
epoch: 4 training_loss 0.12159125540405512 test_loss: 0.14465919733047486
epoch: 5 training_loss 0.10583634816110134 test_loss: 0.13363970518112184
epoch: 6 training_loss 0.11489808032289148 test_loss: 0.1334315061569214
epoch: 7 training_loss 0.10304253246635199 test_loss: 0.1368871212005615
epoch: 8 training_loss 0.10555953120812774 test_loss: 0.14114618301391602
epoch: 9 training_loss 0.09878789618611336 test_loss: 0.12569433450698853
epoch: 10 training_loss 0.09764804964885115 test_loss: 0.13105504512786864
epoch: 11 training_loss 0.09722046518698335 test_loss: 0.13554147481918336
epoch: 12 training_loss 0.0942236934415996 test_loss: 0.12545040845870972
epoch: 13 training_loss 0.09215698266401887 test_loss: 0.10851631164550782
epoch: 14 training_loss 0.10310054291039705 test_loss: 0.12829008102416992
epoch: 15 training_loss 0.09002790872007609 test_loss: 0.13838720321655273
epoch: 16 training_loss 0.09495813395828008 test_loss: 0.12199686765670777
epoch: 17 training_loss 0.08832074277102947 test_loss: 0.1354892611503601
epoch: 18 training_loss 0.08614013113081455 test_loss: 0.13741718530654906
epoch: 19 training_loss 0.09579283736646176 test_loss: 0.12004902362823486
epoch: 20 training_loss 0.09252825610339642 test_loss: 0.12711771726608276
epoch: 21 training_loss 0.08588695446029306 test_loss: 0.12156789302825928
epoch: 22 training_loss 0.09146277081221342 test_loss: 0.12859804630279542
epoch: 23 training_loss 0.0901493720151484 test_loss: 0.12073584794998168
epoch: 24 training_loss 0.09282708821818232 test_loss: 0.1400009274482727
epoch: 25 training_loss 0.08437887281179428 test_loss: 0.1299823045730591
epoch: 26 training_loss 0.08842835837975144 test_loss: 0.12105239629745483
epoch: 27 training_loss 0.0821254753228277 test_loss: 0.12053375244140625
epoch: 28 training_loss 0.07658514643087982 test_loss: 0.12985821962356567
epoch: 29 training_loss 0.0870149284787476 test_loss: 0.1441499710083008
epoch: 30 training_loss 0.09086856627836823 test_loss: 0.11798309087753296
epoch: 31 training_loss 0.08181135058403015 test_loss: 0.14239548444747924
epoch: 32 training_loss 0.08076445313170552 test_loss: 0.13213083744049073
epoch: 33 training_loss 0.08333876177668571 test_loss: 0.13704363107681275
epoch: 34 training_loss 0.08060100190341472 test_loss: 0.12353303432464599
epoch: 35 training_loss 0.0735485227778554 test_loss: 0.13686611652374267
epoch: 36 training_loss 0.07611865431070328 test_loss: 0.14041467905044555
epoch: 37 training_loss 0.07750487455166877 test_loss: 0.13251529932022094
epoch: 38 training_loss 0.07368112791329623 test_loss: 0.1301257848739624
epoch: 39 training_loss 0.07581700624898076 test_loss: 0.1412285804748535
epoch: 40 training_loss 0.08148251542821526 test_loss: 0.1408070683479309
epoch: 41 training_loss 0.09105558641254902 test_loss: 0.1352417588233948
epoch: 42 training_loss 0.079395551122725 test_loss: 0.14181329011917115
epoch: 43 training_loss 0.0706525649363175 test_loss: 0.1316244125366211
epoch: 44 training_loss 0.07897816782817245 test_loss: 0.12657307386398314
epoch: 45 training_loss 0.07104852914810181 test_loss: 0.12959052324295045
epoch: 46 training_loss 0.07209815409965813 test_loss: 0.15491535663604736
epoch: 47 training_loss 0.0737626552209258 test_loss: 0.154765522480011
epoch: 48 training_loss 0.06878143083304167 test_loss: 0.14733158349990844
epoch: 49 training_loss 0.07140766248106957 test_loss: 0.14560534954071044
epoch: 50 training_loss 0.07172592882998288 test_loss: 0.13468953371047973
epoch: 51 training_loss 0.07461714211851359 test_loss: 0.1429246783256531
epoch: 52 training_loss 0.06906892156228422 test_loss: 0.1370256781578064
epoch: 53 training_loss 0.06615645781159402 test_loss: 0.16389604806900024
epoch: 54 training_loss 0.07119273034855723 test_loss: 0.14253820180892945
epoch: 55 training_loss 0.0730247338488698 test_loss: 0.14401429891586304
epoch: 56 training_loss 0.06627055364660919 test_loss: 0.13684824705123902
epoch: 57 training_loss 0.07042619744315744 test_loss: 0.16345748901367188
epoch: 58 training_loss 0.0651863509695977 test_loss: 0.14592769145965576
epoch: 59 training_loss 0.06919191777706146 test_loss: 0.1567307949066162
epoch: 60 training_loss 0.06945620509795844 test_loss: 0.14305427074432372
epoch: 61 training_loss 0.06835359016433358 test_loss: 0.13725812435150148
epoch: 62 training_loss 0.06422587305307388 test_loss: 0.16550956964492797
epoch: 63 training_loss 0.06513611939735711 test_loss: 0.16072432994842528
epoch: 64 training_loss 0.06620823910459876 test_loss: 0.16303551197052002
epoch: 65 training_loss 0.06753422695212066 test_loss: 0.13766229152679443
epoch: 66 training_loss 0.06069612048566341 test_loss: 0.15421745777130128
epoch: 67 training_loss 0.05965555981267243 test_loss: 0.1366780161857605
epoch: 68 training_loss 0.05973747994750738 test_loss: 0.16826659440994263
epoch: 69 training_loss 0.054270642902702095 test_loss: 0.16053268909454346
epoch: 70 training_loss 0.05724819993600249 test_loss: 0.1698209524154663
epoch: 71 training_loss 0.05957707466557622 test_loss: 0.15039807558059692
epoch: 72 training_loss 0.06332944320980459 test_loss: 0.1670174479484558
epoch: 73 training_loss 0.05862602372653782 test_loss: 0.15467122793197632
epoch: 74 training_loss 0.06592429421842098 test_loss: 0.16257007122039796
epoch: 75 training_loss 0.06131850890815258 test_loss: 0.16063276529312134
epoch: 76 training_loss 0.057599382046610116 test_loss: 0.15094729661941528
epoch: 77 training_loss 0.06041887334547937 test_loss: 0.16325229406356812
epoch: 78 training_loss 0.059958151066675784 test_loss: 0.1661340355873108
epoch: 79 training_loss 0.05577202768065035 test_loss: 0.14774786233901976
epoch: 80 training_loss 0.06219472663477063 test_loss: 0.1538083553314209
epoch: 81 training_loss 0.05653380357660353 test_loss: 0.17266526222229003
epoch: 82 training_loss 0.05908421841450036 test_loss: 0.15664180517196655
epoch: 83 training_loss 0.055708718039095405 test_loss: 0.15658071041107177
epoch: 84 training_loss 0.05428031479939818 test_loss: 0.1733143448829651
epoch: 85 training_loss 0.051232756292447446 test_loss: 0.1520559549331665
epoch: 86 training_loss 0.05224015565123409 test_loss: 0.1447167754173279
epoch: 87 training_loss 0.05231939263641834 test_loss: 0.17315824031829835
epoch: 88 training_loss 0.05206249203532934 test_loss: 0.16141784191131592
epoch: 89 training_loss 0.05209305954165757 test_loss: 0.17404452562332154
epoch: 90 training_loss 0.0582135390304029 test_loss: 0.15336432456970214
epoch: 91 training_loss 0.04551491489633918 test_loss: 0.17360997200012207
epoch: 92 training_loss 0.05224889822304249 test_loss: 0.16405614614486694
epoch: 93 training_loss 0.055401349486783144 test_loss: 0.17706072330474854
epoch: 94 training_loss 0.04962446382269263 test_loss: 0.17119143009185792
epoch: 95 training_loss 0.04566490474157035 test_loss: 0.15020757913589478
epoch: 96 training_loss 0.04527125812601298 test_loss: 0.16484992504119872
epoch: 97 training_loss 0.04376208472065628 test_loss: 0.17646534442901612
epoch: 98 training_loss 0.0514583445712924 test_loss: 0.18480172157287597
epoch: 99 training_loss 0.04929065733216703 test_loss: 0.16227418184280396
epoch: 100 training_loss 0.043753123339265586 test_loss: 0.16844167709350585
epoch: 101 training_loss 0.04182235833257437 test_loss: 0.16862181425094605
epoch: 102 training_loss 0.04323541170917451 test_loss: 0.1769964337348938
epoch: 103 training_loss 0.05144176404923201 test_loss: 0.1835349440574646
epoch: 104 training_loss 0.04642861916217953 test_loss: 0.1647396445274353
epoch: 105 training_loss 0.04486809626221657 test_loss: 0.19396545886993408
epoch: 106 training_loss 0.04501377837732434 test_loss: 0.19253482818603515
epoch: 107 training_loss 0.03837475121021271 test_loss: 0.15886822938919068
epoch: 108 training_loss 0.045454609598964454 test_loss: 0.19099297523498535
epoch: 109 training_loss 0.04450791286304593 test_loss: 0.15617603063583374
epoch: 110 training_loss 0.041258521019481124 test_loss: 0.18801335096359253
epoch: 111 training_loss 0.043934742212295534 test_loss: 0.1702327847480774
epoch: 112 training_loss 0.04093636479228735 test_loss: 0.17114228010177612
epoch: 113 training_loss 0.043549971748143436 test_loss: 0.18150856494903564
epoch: 114 training_loss 0.04220095591619611 test_loss: 0.17195265293121337
epoch: 115 training_loss 0.040869472334161404 test_loss: 0.15684714317321777
epoch: 116 training_loss 0.04124021797440946 test_loss: 0.19056131839752197
epoch: 117 training_loss 0.03823920336551964 test_loss: 0.18358352184295654
epoch: 118 training_loss 0.038966634562239054 test_loss: 0.19851723909378052
epoch: 119 training_loss 0.040572514459490776 test_loss: 0.1778339385986328
epoch: 120 training_loss 0.03986580757424235 test_loss: 0.16809542179107667
epoch: 121 training_loss 0.040503436760045586 test_loss: 0.17584600448608398
epoch: 122 training_loss 0.03649811270646751 test_loss: 0.18169646263122557
epoch: 123 training_loss 0.031098884493112565 test_loss: 0.1819373846054077
epoch: 124 training_loss 0.04008655242621899 test_loss: 0.18233414888381957
epoch: 125 training_loss 0.04631555840373039 test_loss: 0.19220423698425293
epoch: 126 training_loss 0.041558106672018764 test_loss: 0.16898921728134156
epoch: 127 training_loss 0.0438658959325403 test_loss: 0.1921355366706848
epoch: 128 training_loss 0.042022663550451395 test_loss: 0.1834994673728943
epoch: 129 training_loss 0.03442854213528335 test_loss: 0.19020031690597533
epoch: 130 training_loss 0.034267152538523075 test_loss: 0.1813194751739502
epoch: 131 training_loss 0.035226546386256816 test_loss: 0.19343883991241456
epoch: 132 training_loss 0.030545009565539658 test_loss: 0.14270532131195068
epoch: 133 training_loss 0.02854304503649473 test_loss: 0.18768022060394288
epoch: 134 training_loss 0.03292380418162793 test_loss: 0.1921548843383789
epoch: 135 training_loss 0.03118689713999629 test_loss: 0.1921411633491516
epoch: 136 training_loss 0.03492585700005293 test_loss: 0.17248069047927855
epoch: 137 training_loss 0.0405173278413713 test_loss: 0.18476297855377197
epoch: 138 training_loss 0.03855077504646033 test_loss: 0.16744199991226197
epoch: 139 training_loss 0.03308714212384075 test_loss: 0.19714484214782715
epoch: 140 training_loss 0.03146441516466439 test_loss: 0.15597046613693238
epoch: 141 training_loss 0.03285249595530331 test_loss: 0.16215691566467286
epoch: 142 training_loss 0.03364513533655554 test_loss: 0.2028282642364502
epoch: 143 training_loss 0.029821086623705924 test_loss: 0.19328426122665404
epoch: 144 training_loss 0.034572844814974815 test_loss: 0.17936327457427978
epoch: 145 training_loss 0.03099389508366585 test_loss: 0.2013951301574707
epoch: 146 training_loss 0.02837919124402106 test_loss: 0.19383482933044432
epoch: 147 training_loss 0.03372751918621361 test_loss: 0.19950461387634277
epoch: 148 training_loss 0.03021125993691385 test_loss: 0.1906668186187744
epoch: 149 training_loss 0.026259694574400784 test_loss: 0.1757982850074768
epoch: 0 training_loss 51.9698390007019 test_loss: 24.860331726074218
epoch: 1 training_loss 19.15919804573059 test_loss: 15.39410400390625
epoch: 2 training_loss 13.305049304962159 test_loss: 11.665292358398437
epoch: 3 training_loss 10.69157009124756 test_loss: 9.675215148925782
epoch: 4 training_loss 9.061483850479126 test_loss: 8.345722961425782
epoch: 5 training_loss 7.721834363937378 test_loss: 7.545184326171875
epoch: 6 training_loss 6.872164340019226 test_loss: 6.3064933776855465
epoch: 7 training_loss 6.179661664962769 test_loss: 5.783528137207031
epoch: 8 training_loss 5.479935789108277 test_loss: 5.247077178955078
epoch: 9 training_loss 4.983901362419129 test_loss: 4.85169677734375
epoch: 10 training_loss 4.697641885280609 test_loss: 4.608089828491211
epoch: 11 training_loss 4.362653563022613 test_loss: 4.248472213745117
epoch: 12 training_loss 4.120822260379791 test_loss: 4.0179588317871096
epoch: 13 training_loss 3.9244449496269227 test_loss: 3.8121166229248047
epoch: 14 training_loss 3.776694676876068 test_loss: 3.662640380859375
epoch: 15 training_loss 3.559447729587555 test_loss: 3.5559207916259767
epoch: 16 training_loss 3.438638439178467 test_loss: 3.3927082061767577
epoch: 17 training_loss 3.3685999155044555 test_loss: 3.3419120788574217
epoch: 18 training_loss 3.181961426734924 test_loss: 3.138291358947754
epoch: 19 training_loss 3.117034957408905 test_loss: 3.0724069595336916
epoch: 20 training_loss 3.001244156360626 test_loss: 2.9529443740844727
epoch: 21 training_loss 3.03028222322464 test_loss: 2.9212373733520507
epoch: 22 training_loss 2.9070923852920534 test_loss: 2.8112436294555665
epoch: 23 training_loss 2.787049663066864 test_loss: 2.7649906158447264
epoch: 24 training_loss 2.755892262458801 test_loss: 2.744438362121582
epoch: 25 training_loss 2.6901428937911986 test_loss: 2.691660690307617
epoch: 26 training_loss 2.657856147289276 test_loss: 2.603546905517578
epoch: 27 training_loss 2.5238418769836426 test_loss: 2.563889503479004
epoch: 28 training_loss 2.5056248116493225 test_loss: 2.5046628952026366
epoch: 29 training_loss 2.4368280959129334 test_loss: 2.430324172973633
epoch: 30 training_loss 2.3951250600814817 test_loss: 2.4292457580566404
epoch: 31 training_loss 2.4220264959335327 test_loss: 2.3317901611328127
epoch: 32 training_loss 2.29566663980484 test_loss: 2.325360107421875
epoch: 33 training_loss 2.2817070078849793 test_loss: 2.302484893798828
epoch: 34 training_loss 2.2540789365768434 test_loss: 2.3023672103881836
epoch: 35 training_loss 2.2022673892974853 test_loss: 2.2204706192016603
epoch: 36 training_loss 2.2609742975234983 test_loss: 2.2170642852783202
epoch: 37 training_loss 2.221101896762848 test_loss: 2.2424222946166994
epoch: 38 training_loss 2.161095644235611 test_loss: 2.199607276916504
epoch: 39 training_loss 2.1509199929237366 test_loss: 2.1475345611572267
epoch: 40 training_loss 2.072818292379379 test_loss: 2.0862459182739257
epoch: 41 training_loss 2.0880138528347016 test_loss: 2.1004001617431642
epoch: 42 training_loss 2.0500225496292113 test_loss: 2.0810064315795898
epoch: 43 training_loss 2.110358556509018 test_loss: 2.040328788757324
epoch: 44 training_loss 2.0499931740760804 test_loss: 2.056509017944336
epoch: 45 training_loss 2.0305987906455996 test_loss: 2.0243783950805665
epoch: 46 training_loss 1.9971066308021546 test_loss: 2.0468711853027344
epoch: 47 training_loss 1.9983951818943024 test_loss: 2.0429922103881837
epoch: 48 training_loss 2.0015982234478 test_loss: 1.9726112365722657
epoch: 49 training_loss 1.9779277348518371 test_loss: 1.970871353149414
epoch: 50 training_loss 2.001415021419525 test_loss: 1.971458625793457
epoch: 51 training_loss 1.9714976382255553 test_loss: 2.0201480865478514
epoch: 52 training_loss 1.9811886775493621 test_loss: 1.9534767150878907
epoch: 53 training_loss 1.9194582247734069 test_loss: 1.9318220138549804
epoch: 54 training_loss 1.8759675908088684 test_loss: 1.8780879974365234
epoch: 55 training_loss 1.9045079922676087 test_loss: 1.852716064453125
epoch: 56 training_loss 1.9075274848937989 test_loss: 1.8757774353027343
epoch: 57 training_loss 1.8863939142227173 test_loss: 1.830825424194336
epoch: 58 training_loss 1.846528000831604 test_loss: 1.8716978073120116
epoch: 59 training_loss 1.8474697041511536 test_loss: 1.8565408706665039
epoch: 60 training_loss 1.8771012032032013 test_loss: 1.7768199920654297
epoch: 61 training_loss 1.8538910639286041 test_loss: 1.8102344512939452
epoch: 62 training_loss 1.8547977495193482 test_loss: 1.8492729187011718
epoch: 63 training_loss 1.8056767189502716 test_loss: 1.8182819366455079
epoch: 64 training_loss 1.868278650045395 test_loss: 1.8064300537109375
epoch: 65 training_loss 1.7818031108379364 test_loss: 1.789790725708008
epoch: 66 training_loss 1.83183203458786 test_loss: 1.8070276260375977
epoch: 67 training_loss 1.759188675880432 test_loss: 1.7570667266845703
epoch: 68 training_loss 1.7648311758041382 test_loss: 1.8011072158813477
epoch: 69 training_loss 1.763125479221344 test_loss: 1.780238723754883
epoch: 70 training_loss 1.741127324104309 test_loss: 1.7544248580932618
epoch: 71 training_loss 1.716105672121048 test_loss: 1.7610498428344727
epoch: 72 training_loss 1.7370717239379883 test_loss: 1.7413354873657227
epoch: 73 training_loss 1.7332455480098725 test_loss: 1.764131736755371
epoch: 74 training_loss 1.7058184838294983 test_loss: 1.7262266159057618
epoch: 75 training_loss 1.6944165873527526 test_loss: 1.6728937149047851
epoch: 76 training_loss 1.7118739187717438 test_loss: 1.7424013137817382
epoch: 77 training_loss 1.6782598972320557 test_loss: 1.7162385940551759
epoch: 78 training_loss 1.7128791344165801 test_loss: 1.7234928131103515
epoch: 79 training_loss 1.6778651034832002 test_loss: 1.6617155075073242
epoch: 80 training_loss 1.6582117784023285 test_loss: 1.6779335021972657
epoch: 81 training_loss 1.6547875475883485 test_loss: 1.6640106201171876
epoch: 82 training_loss 1.666367508172989 test_loss: 1.6580957412719726
epoch: 83 training_loss 1.6351661455631257 test_loss: 1.6876607894897462
epoch: 84 training_loss 1.6728163397312164 test_loss: 1.6701784133911133
epoch: 85 training_loss 1.6502328777313233 test_loss: 1.6383358001708985
epoch: 86 training_loss 1.631319614648819 test_loss: 1.6460426330566407
epoch: 87 training_loss 1.6177422106266022 test_loss: 1.6421674728393554
epoch: 88 training_loss 1.6244364404678344 test_loss: 1.6685226440429688
epoch: 89 training_loss 1.6601629662513733 test_loss: 1.639118766784668
epoch: 90 training_loss 1.6156512129306793 test_loss: 1.7023286819458008
epoch: 91 training_loss 1.6367015600204469 test_loss: 1.617380142211914
epoch: 92 training_loss 1.6046264791488647 test_loss: 1.617026138305664
epoch: 93 training_loss 1.6293105816841125 test_loss: 1.5866107940673828
epoch: 94 training_loss 1.5929941534996033 test_loss: 1.6448205947875976
epoch: 95 training_loss 1.5842168748378753 test_loss: 1.6238340377807616
epoch: 96 training_loss 1.5904673278331756 test_loss: 1.6603654861450194
epoch: 97 training_loss 1.5719426953792572 test_loss: 1.6157289505004884
epoch: 98 training_loss 1.5611243343353272 test_loss: 1.6162834167480469
epoch: 99 training_loss 1.5730812132358551 test_loss: 1.5883798599243164
epoch: 100 training_loss 1.5668174862861632 test_loss: 1.597633457183838
epoch: 101 training_loss 1.568436918258667 test_loss: 1.6238384246826172
epoch: 102 training_loss 1.5620132565498352 test_loss: 1.5997588157653808
epoch: 103 training_loss 1.5810846948623658 test_loss: 1.5785141944885255
epoch: 104 training_loss 1.563138633966446 test_loss: 1.608238983154297
epoch: 105 training_loss 1.527575787305832 test_loss: 1.5615365028381347
epoch: 106 training_loss 1.5386657905578613 test_loss: 1.5733976364135742
epoch: 107 training_loss 1.516018670797348 test_loss: 1.5855945587158202
epoch: 108 training_loss 1.559042263031006 test_loss: 1.5949076652526855
epoch: 109 training_loss 1.5253529608249665 test_loss: 1.5781731605529785
epoch: 110 training_loss 1.5497208857536315 test_loss: 1.5728760719299317
epoch: 111 training_loss 1.5416504549980163 test_loss: 1.5747970581054687
epoch: 112 training_loss 1.5201821386814118 test_loss: 1.572598361968994
epoch: 113 training_loss 1.524442949295044 test_loss: 1.534735870361328
epoch: 114 training_loss 1.5250780558586121 test_loss: 1.5505444526672363
epoch: 115 training_loss 1.510987298488617 test_loss: 1.5673731803894042
epoch: 116 training_loss 1.5197261834144593 test_loss: 1.5557925224304199
epoch: 117 training_loss 1.526248254776001 test_loss: 1.5283770561218262
epoch: 118 training_loss 1.5040272057056427 test_loss: 1.5413186073303222
epoch: 119 training_loss 1.5083015656471253 test_loss: 1.5760534286499024
epoch: 120 training_loss 1.5193714439868926 test_loss: 1.5354476928710938
epoch: 121 training_loss 1.4861916923522949 test_loss: 1.5426010131835937
epoch: 122 training_loss 1.4901729130744934 test_loss: 1.5228466987609863
epoch: 123 training_loss 1.5135700917243957 test_loss: 1.488167953491211
epoch: 124 training_loss 1.489624115228653 test_loss: 1.5395381927490235
epoch: 125 training_loss 1.4898502707481385 test_loss: 1.512306308746338
epoch: 126 training_loss 1.4845696675777436 test_loss: 1.5425033569335938
epoch: 127 training_loss 1.4539329171180726 test_loss: 1.4877216339111328
epoch: 128 training_loss 1.487734136581421 test_loss: 1.5332894325256348
epoch: 129 training_loss 1.4770669388771056 test_loss: 1.533524990081787
epoch: 130 training_loss 1.4673132443428039 test_loss: 1.5209131240844727
epoch: 131 training_loss 1.4641817617416382 test_loss: 1.5075175285339355
epoch: 132 training_loss 1.4713345623016358 test_loss: 1.515913200378418
epoch: 133 training_loss 1.4941679728031159 test_loss: 1.4928160667419434
epoch: 134 training_loss 1.4553501391410828 test_loss: 1.5043312072753907
epoch: 135 training_loss 1.4473569810390472 test_loss: 1.4975125312805175
epoch: 136 training_loss 1.4775923776626587 test_loss: 1.5046191215515137
epoch: 137 training_loss 1.4712702238559723 test_loss: 1.4714497566223144
epoch: 138 training_loss 1.446038739681244 test_loss: 1.481590175628662
epoch: 139 training_loss 1.4610647523403169 test_loss: 1.5234747886657716
epoch: 140 training_loss 1.4597567999362946 test_loss: 1.4752636909484864
epoch: 141 training_loss 1.4394896352291107 test_loss: 1.5166768074035644
epoch: 142 training_loss 1.4515588581562042 test_loss: 1.4722442626953125
epoch: 143 training_loss 1.4389185893535614 test_loss: 1.4608229637145995
epoch: 144 training_loss 1.4598660361766815 test_loss: 1.4771729469299317
epoch: 145 training_loss 1.4513468062877655 test_loss: 1.4671412467956544
epoch: 146 training_loss 1.4290690207481385 test_loss: 1.4669432640075684
epoch: 147 training_loss 1.4450494682788848 test_loss: 1.472957706451416
epoch: 148 training_loss 1.4305954384803772 test_loss: 1.5135242462158203
epoch: 149 training_loss 1.4210429275035859 test_loss: 1.482604694366455
5112.955104391807
episode: 0 training return: tensor(-119.5622, device='cuda:0')
episode: 1 training return: tensor(155.1453, device='cuda:0')
episode: 2 training return: tensor(-71.6485, device='cuda:0')
episode: 3 training return: tensor(-103.5089, device='cuda:0')
epoch: 1 test_true_pfm: 5117.0975604036685 sim_pfm: 94.28838828679484
episode: 4 training return: tensor(-148.6637, device='cuda:0')
episode: 5 training return: tensor(78.4397, device='cuda:0')
episode: 6 training return: tensor(147.9605, device='cuda:0')
episode: 7 training return: tensor(22.4252, device='cuda:0')
epoch: 2 test_true_pfm: 5074.005585996089 sim_pfm: 202.57247655730075
episode: 8 training return: tensor(117.6201, device='cuda:0')
episode: 9 training return: tensor(22.7093, device='cuda:0')
episode: 10 training return: tensor(106.0181, device='cuda:0')
episode: 11 training return: tensor(9.7002, device='cuda:0')
epoch: 3 test_true_pfm: 5217.588507473226 sim_pfm: 175.96367003788086
episode: 12 training return: tensor(9.7887, device='cuda:0')
episode: 13 training return: tensor(-48.6228, device='cuda:0')
episode: 14 training return: tensor(49.3390, device='cuda:0')
episode: 15 training return: tensor(91.9931, device='cuda:0')
epoch: 4 test_true_pfm: 5056.91494300879 sim_pfm: 42.63867498730542
episode: 16 training return: tensor(111.2431, device='cuda:0')
episode: 17 training return: tensor(88.7370, device='cuda:0')
episode: 18 training return: tensor(101.4326, device='cuda:0')
episode: 19 training return: tensor(22.9616, device='cuda:0')
epoch: 5 test_true_pfm: 5148.838189103252 sim_pfm: 141.5373349977696
episode: 20 training return: tensor(243.2334, device='cuda:0')
episode: 21 training return: tensor(-32.9053, device='cuda:0')
episode: 22 training return: tensor(98.1999, device='cuda:0')
episode: 23 training return: tensor(111.3135, device='cuda:0')
epoch: 6 test_true_pfm: 5189.730258722192 sim_pfm: 134.16367725414844
episode: 24 training return: tensor(-65.2877, device='cuda:0')
episode: 25 training return: tensor(292.5934, device='cuda:0')
episode: 26 training return: tensor(107.7615, device='cuda:0')
episode: 27 training return: tensor(49.0486, device='cuda:0')
epoch: 7 test_true_pfm: 5069.056434935159 sim_pfm: 116.464813964325
episode: 28 training return: tensor(43.4595, device='cuda:0')
episode: 29 training return: tensor(140.5158, device='cuda:0')
episode: 30 training return: tensor(-44.6096, device='cuda:0')
episode: 31 training return: tensor(22.5426, device='cuda:0')
epoch: 8 test_true_pfm: 5218.279233737336 sim_pfm: 122.98271691213206
episode: 32 training return: tensor(-98.4377, device='cuda:0')
episode: 33 training return: tensor(119.8770, device='cuda:0')
episode: 34 training return: tensor(-60.8617, device='cuda:0')
episode: 35 training return: tensor(164.6453, device='cuda:0')
epoch: 9 test_true_pfm: 5008.7250835294335 sim_pfm: 164.09525045373206
episode: 36 training return: tensor(47.6092, device='cuda:0')
episode: 37 training return: tensor(143.0939, device='cuda:0')
episode: 38 training return: tensor(189.1478, device='cuda:0')
episode: 39 training return: tensor(276.1018, device='cuda:0')
epoch: 10 test_true_pfm: 5130.821996606616 sim_pfm: 139.45281117999306
episode: 40 training return: tensor(138.7034, device='cuda:0')
episode: 41 training return: tensor(130.4634, device='cuda:0')
episode: 42 training return: tensor(234.6123, device='cuda:0')
episode: 43 training return: tensor(116.8823, device='cuda:0')
epoch: 11 test_true_pfm: 5058.392358060647 sim_pfm: 228.63660331780557
episode: 44 training return: tensor(291.4892, device='cuda:0')
episode: 45 training return: tensor(196.5328, device='cuda:0')
episode: 46 training return: tensor(142.3761, device='cuda:0')
episode: 47 training return: tensor(111.8497, device='cuda:0')
epoch: 12 test_true_pfm: 5222.43560786824 sim_pfm: 266.6133953530031
episode: 48 training return: tensor(156.5022, device='cuda:0')
episode: 49 training return: tensor(98.6107, device='cuda:0')
episode: 50 training return: tensor(131.3928, device='cuda:0')
episode: 51 training return: tensor(198.9018, device='cuda:0')
epoch: 13 test_true_pfm: 4828.434836652705 sim_pfm: 222.80626876314636
episode: 52 training return: tensor(246.8434, device='cuda:0')
episode: 53 training return: tensor(84.7763, device='cuda:0')
episode: 54 training return: tensor(92.4998, device='cuda:0')
episode: 55 training return: tensor(11.8511, device='cuda:0')
epoch: 14 test_true_pfm: 5192.729328176589 sim_pfm: 243.55882256264644
episode: 56 training return: tensor(164.6627, device='cuda:0')
episode: 57 training return: tensor(261.0582, device='cuda:0')
episode: 58 training return: tensor(-41.5311, device='cuda:0')
episode: 59 training return: tensor(183.7255, device='cuda:0')
epoch: 15 test_true_pfm: 5208.028188853849 sim_pfm: 197.31889939090857
episode: 60 training return: tensor(106.7645, device='cuda:0')
episode: 61 training return: tensor(213.0976, device='cuda:0')
episode: 62 training return: tensor(234.1492, device='cuda:0')
episode: 63 training return: tensor(143.6425, device='cuda:0')
epoch: 16 test_true_pfm: 5265.515936954937 sim_pfm: 251.74207627400756
episode: 64 training return: tensor(140.3409, device='cuda:0')
episode: 65 training return: tensor(170.1099, device='cuda:0')
episode: 66 training return: tensor(120.4961, device='cuda:0')
episode: 67 training return: tensor(304.6717, device='cuda:0')
epoch: 17 test_true_pfm: 5319.567219129564 sim_pfm: 296.3509797025666
episode: 68 training return: tensor(113.7094, device='cuda:0')
episode: 69 training return: tensor(272.7214, device='cuda:0')
episode: 70 training return: tensor(100.5053, device='cuda:0')
episode: 71 training return: tensor(258.4918, device='cuda:0')
epoch: 18 test_true_pfm: 5255.100914500897 sim_pfm: 213.374580594711
episode: 72 training return: tensor(212.8783, device='cuda:0')
episode: 73 training return: tensor(268.7745, device='cuda:0')
episode: 74 training return: tensor(-46.2507, device='cuda:0')
episode: 75 training return: tensor(161.9281, device='cuda:0')
epoch: 19 test_true_pfm: 5344.470797109781 sim_pfm: 330.46585938474163
episode: 76 training return: tensor(198.0019, device='cuda:0')
episode: 77 training return: tensor(260.1240, device='cuda:0')
episode: 78 training return: tensor(105.6009, device='cuda:0')
episode: 79 training return: tensor(140.3918, device='cuda:0')
epoch: 20 test_true_pfm: 5334.434721340094 sim_pfm: 241.50860590056982
episode: 80 training return: tensor(120.8177, device='cuda:0')
episode: 81 training return: tensor(267.4343, device='cuda:0')
episode: 82 training return: tensor(232.4796, device='cuda:0')
episode: 83 training return: tensor(180.0527, device='cuda:0')
epoch: 21 test_true_pfm: 5295.647499096227 sim_pfm: 401.66317638130084
episode: 84 training return: tensor(300.9412, device='cuda:0')
episode: 85 training return: tensor(255.6268, device='cuda:0')
episode: 86 training return: tensor(233.6759, device='cuda:0')
episode: 87 training return: tensor(298.6018, device='cuda:0')
epoch: 22 test_true_pfm: 5278.529190138043 sim_pfm: 411.86096626520157
episode: 88 training return: tensor(242.2021, device='cuda:0')
episode: 89 training return: tensor(255.3205, device='cuda:0')
episode: 90 training return: tensor(276.7784, device='cuda:0')
episode: 91 training return: tensor(175.7410, device='cuda:0')
epoch: 23 test_true_pfm: 5410.305241451623 sim_pfm: 419.8286721437471
episode: 92 training return: tensor(258.9208, device='cuda:0')
episode: 93 training return: tensor(239.5051, device='cuda:0')
episode: 94 training return: tensor(175.9580, device='cuda:0')
episode: 95 training return: tensor(196.3407, device='cuda:0')
epoch: 24 test_true_pfm: 5407.154366076759 sim_pfm: 388.4335924604481
episode: 96 training return: tensor(325.3273, device='cuda:0')
episode: 97 training return: tensor(298.2185, device='cuda:0')
episode: 98 training return: tensor(309.4530, device='cuda:0')
episode: 99 training return: tensor(282.1760, device='cuda:0')
epoch: 25 test_true_pfm: 5364.411233993543 sim_pfm: 392.4401823793111
episode: 100 training return: tensor(239.5926, device='cuda:0')
episode: 101 training return: tensor(216.5775, device='cuda:0')
episode: 102 training return: tensor(364.1788, device='cuda:0')
episode: 103 training return: tensor(344.2819, device='cuda:0')
epoch: 26 test_true_pfm: 5369.8633715700935 sim_pfm: 398.9065487886546
episode: 104 training return: tensor(333.0198, device='cuda:0')
episode: 105 training return: tensor(420.8533, device='cuda:0')
episode: 106 training return: tensor(326.2893, device='cuda:0')
episode: 107 training return: tensor(183.7339, device='cuda:0')
epoch: 27 test_true_pfm: 5385.0925553247425 sim_pfm: 293.90486108749366
episode: 108 training return: tensor(163.9311, device='cuda:0')
episode: 109 training return: tensor(338.2369, device='cuda:0')
episode: 110 training return: tensor(355.0804, device='cuda:0')
episode: 111 training return: tensor(195.4562, device='cuda:0')
epoch: 28 test_true_pfm: 5396.89661300954 sim_pfm: 401.1089158981728
episode: 112 training return: tensor(437.2338, device='cuda:0')
episode: 113 training return: tensor(108.5447, device='cuda:0')
episode: 114 training return: tensor(252.6101, device='cuda:0')
episode: 115 training return: tensor(265.7384, device='cuda:0')
epoch: 29 test_true_pfm: 5374.057884399946 sim_pfm: 423.8101944279818
episode: 116 training return: tensor(107.2556, device='cuda:0')
episode: 117 training return: tensor(337.4153, device='cuda:0')
episode: 118 training return: tensor(242.6382, device='cuda:0')
episode: 119 training return: tensor(371.6529, device='cuda:0')
epoch: 30 test_true_pfm: 5471.5251806309925 sim_pfm: 482.9272183935197
episode: 120 training return: tensor(448.3805, device='cuda:0')
episode: 121 training return: tensor(274.8802, device='cuda:0')
episode: 122 training return: tensor(395.5438, device='cuda:0')
episode: 123 training return: tensor(277.9171, device='cuda:0')
epoch: 31 test_true_pfm: 5500.007400466428 sim_pfm: 424.6874429230714
episode: 124 training return: tensor(259.9328, device='cuda:0')
episode: 125 training return: tensor(370.1474, device='cuda:0')
episode: 126 training return: tensor(277.4149, device='cuda:0')
episode: 127 training return: tensor(284.8689, device='cuda:0')
epoch: 32 test_true_pfm: 5369.652205946675 sim_pfm: 370.54849231809686
episode: 128 training return: tensor(465.2201, device='cuda:0')
episode: 129 training return: tensor(307.1589, device='cuda:0')
episode: 130 training return: tensor(288.5399, device='cuda:0')
episode: 131 training return: tensor(358.2173, device='cuda:0')
epoch: 33 test_true_pfm: 5482.194803773575 sim_pfm: 460.02057441098924
episode: 132 training return: tensor(299.9190, device='cuda:0')
episode: 133 training return: tensor(319.0275, device='cuda:0')
episode: 134 training return: tensor(451.1824, device='cuda:0')
episode: 135 training return: tensor(411.9825, device='cuda:0')
epoch: 34 test_true_pfm: 5410.66742425248 sim_pfm: 514.7287552750204
episode: 136 training return: tensor(313.8079, device='cuda:0')
episode: 137 training return: tensor(243.0563, device='cuda:0')
episode: 138 training return: tensor(341.9029, device='cuda:0')
episode: 139 training return: tensor(204.2616, device='cuda:0')
epoch: 35 test_true_pfm: 5467.08643062404 sim_pfm: 449.0362891782618
episode: 140 training return: tensor(374.5791, device='cuda:0')
episode: 141 training return: tensor(443.4668, device='cuda:0')
episode: 142 training return: tensor(272.4386, device='cuda:0')
episode: 143 training return: tensor(352.0241, device='cuda:0')
epoch: 36 test_true_pfm: 5449.063782316157 sim_pfm: 465.1296810434724
episode: 144 training return: tensor(324.5828, device='cuda:0')
episode: 145 training return: tensor(405.4387, device='cuda:0')
episode: 146 training return: tensor(174.5866, device='cuda:0')
episode: 147 training return: tensor(339.7375, device='cuda:0')
epoch: 37 test_true_pfm: 5621.322545052487 sim_pfm: 406.8679017990362
episode: 148 training return: tensor(289.9144, device='cuda:0')
episode: 149 training return: tensor(474.8406, device='cuda:0')
episode: 150 training return: tensor(321.9285, device='cuda:0')
episode: 151 training return: tensor(473.3445, device='cuda:0')
epoch: 38 test_true_pfm: 5441.028338356082 sim_pfm: 478.5375340702788
episode: 152 training return: tensor(504.4138, device='cuda:0')
episode: 153 training return: tensor(470.3753, device='cuda:0')
episode: 154 training return: tensor(282.3698, device='cuda:0')
episode: 155 training return: tensor(428.0610, device='cuda:0')
epoch: 39 test_true_pfm: 5424.529704398601 sim_pfm: 417.2016892432778
episode: 156 training return: tensor(256.0333, device='cuda:0')
episode: 157 training return: tensor(392.1547, device='cuda:0')
episode: 158 training return: tensor(203.7549, device='cuda:0')
episode: 159 training return: tensor(408.3585, device='cuda:0')
epoch: 40 test_true_pfm: 5487.763079669129 sim_pfm: 464.41850974282715
episode: 160 training return: tensor(302.6113, device='cuda:0')
episode: 161 training return: tensor(431.2731, device='cuda:0')
episode: 162 training return: tensor(200.3163, device='cuda:0')
episode: 163 training return: tensor(333.9810, device='cuda:0')
epoch: 41 test_true_pfm: 5505.36297893766 sim_pfm: 434.08794187458506
episode: 164 training return: tensor(203.4889, device='cuda:0')
episode: 165 training return: tensor(341.9245, device='cuda:0')
episode: 166 training return: tensor(280.8384, device='cuda:0')
episode: 167 training return: tensor(236.7173, device='cuda:0')
epoch: 42 test_true_pfm: 5532.615167007282 sim_pfm: 458.3790926632646
episode: 168 training return: tensor(291.1872, device='cuda:0')
episode: 169 training return: tensor(237.1688, device='cuda:0')
episode: 170 training return: tensor(393.4525, device='cuda:0')
episode: 171 training return: tensor(385.2396, device='cuda:0')
epoch: 43 test_true_pfm: 5506.210006244801 sim_pfm: 465.8650749078952
episode: 172 training return: tensor(312.8267, device='cuda:0')
episode: 173 training return: tensor(345.4606, device='cuda:0')
episode: 174 training return: tensor(450.9464, device='cuda:0')
episode: 175 training return: tensor(445.6147, device='cuda:0')
epoch: 44 test_true_pfm: 5372.4148451678075 sim_pfm: 551.9194216816686
episode: 176 training return: tensor(431.2115, device='cuda:0')
episode: 177 training return: tensor(243.9294, device='cuda:0')
episode: 178 training return: tensor(549.6842, device='cuda:0')
episode: 179 training return: tensor(415.1177, device='cuda:0')
epoch: 45 test_true_pfm: 5553.533665849016 sim_pfm: 497.15083637096296
episode: 180 training return: tensor(365.7342, device='cuda:0')
episode: 181 training return: tensor(498.5662, device='cuda:0')
episode: 182 training return: tensor(326.6395, device='cuda:0')
episode: 183 training return: tensor(407.6001, device='cuda:0')
epoch: 46 test_true_pfm: 5558.796397853956 sim_pfm: 502.4405922808219
episode: 184 training return: tensor(395.3777, device='cuda:0')
episode: 185 training return: tensor(300.5157, device='cuda:0')
episode: 186 training return: tensor(436.7351, device='cuda:0')
episode: 187 training return: tensor(414.2384, device='cuda:0')
epoch: 47 test_true_pfm: 5491.1932025477245 sim_pfm: 470.69963082205504
episode: 188 training return: tensor(410.9395, device='cuda:0')
episode: 189 training return: tensor(391.5347, device='cuda:0')
episode: 190 training return: tensor(466.9375, device='cuda:0')
episode: 191 training return: tensor(393.9750, device='cuda:0')
epoch: 48 test_true_pfm: 5548.960684323279 sim_pfm: 556.5876383270758
episode: 192 training return: tensor(268.3637, device='cuda:0')
episode: 193 training return: tensor(425.4342, device='cuda:0')
episode: 194 training return: tensor(385.9165, device='cuda:0')
episode: 195 training return: tensor(313.5683, device='cuda:0')
epoch: 49 test_true_pfm: 5559.289316638321 sim_pfm: 466.8966890290806
episode: 196 training return: tensor(403.2753, device='cuda:0')
episode: 197 training return: tensor(335.7994, device='cuda:0')
episode: 198 training return: tensor(302.6798, device='cuda:0')
episode: 199 training return: tensor(411.8936, device='cuda:0')
epoch: 50 test_true_pfm: 5533.30154241751 sim_pfm: 473.3678500308888
episode: 200 training return: tensor(401.7926, device='cuda:0')
episode: 201 training return: tensor(370.0256, device='cuda:0')
episode: 202 training return: tensor(336.6658, device='cuda:0')
episode: 203 training return: tensor(300.2782, device='cuda:0')
epoch: 51 test_true_pfm: 5441.743192905912 sim_pfm: 491.96389133141685
episode: 204 training return: tensor(292.2357, device='cuda:0')
episode: 205 training return: tensor(348.5088, device='cuda:0')
episode: 206 training return: tensor(422.4333, device='cuda:0')
episode: 207 training return: tensor(326.4579, device='cuda:0')
epoch: 52 test_true_pfm: 5442.876096456536 sim_pfm: 405.3545425841585
episode: 208 training return: tensor(303.7345, device='cuda:0')
episode: 209 training return: tensor(333.2330, device='cuda:0')
episode: 210 training return: tensor(460.1822, device='cuda:0')
episode: 211 training return: tensor(348.0614, device='cuda:0')
epoch: 53 test_true_pfm: 5572.968470609099 sim_pfm: 532.337289122593
episode: 212 training return: tensor(446.1985, device='cuda:0')
episode: 213 training return: tensor(460.9664, device='cuda:0')
episode: 214 training return: tensor(262.7199, device='cuda:0')
episode: 215 training return: tensor(536.2004, device='cuda:0')
epoch: 54 test_true_pfm: 5523.535580258159 sim_pfm: 459.3015628943297
episode: 216 training return: tensor(326.5270, device='cuda:0')
episode: 217 training return: tensor(407.2730, device='cuda:0')
episode: 218 training return: tensor(418.5908, device='cuda:0')
episode: 219 training return: tensor(342.9892, device='cuda:0')
epoch: 55 test_true_pfm: 5518.7427064159165 sim_pfm: 484.5533869715873
episode: 220 training return: tensor(431.4925, device='cuda:0')
episode: 221 training return: tensor(438.9975, device='cuda:0')
episode: 222 training return: tensor(530.8447, device='cuda:0')
episode: 223 training return: tensor(386.1740, device='cuda:0')
epoch: 56 test_true_pfm: 5458.351630671758 sim_pfm: 493.59854780007544
episode: 224 training return: tensor(576.3994, device='cuda:0')
episode: 225 training return: tensor(467.6032, device='cuda:0')
episode: 226 training return: tensor(532.7498, device='cuda:0')
episode: 227 training return: tensor(441.4913, device='cuda:0')
epoch: 57 test_true_pfm: 5671.639789681646 sim_pfm: 530.7854346832415
episode: 228 training return: tensor(434.0786, device='cuda:0')
episode: 229 training return: tensor(465.1168, device='cuda:0')
episode: 230 training return: tensor(544.8959, device='cuda:0')
episode: 231 training return: tensor(243.0946, device='cuda:0')
epoch: 58 test_true_pfm: 5558.384295935615 sim_pfm: 511.6158583293436
episode: 232 training return: tensor(490.7270, device='cuda:0')
episode: 233 training return: tensor(459.8805, device='cuda:0')
episode: 234 training return: tensor(387.5680, device='cuda:0')
episode: 235 training return: tensor(362.7419, device='cuda:0')
epoch: 59 test_true_pfm: 5657.344241009 sim_pfm: 500.61758000357077
episode: 236 training return: tensor(278.0852, device='cuda:0')
episode: 237 training return: tensor(441.2155, device='cuda:0')
episode: 238 training return: tensor(461.7050, device='cuda:0')
episode: 239 training return: tensor(424.9043, device='cuda:0')
epoch: 60 test_true_pfm: 5492.2582563436035 sim_pfm: 572.2976421909407
episode: 240 training return: tensor(351.4256, device='cuda:0')
episode: 241 training return: tensor(409.8692, device='cuda:0')
episode: 242 training return: tensor(484.7991, device='cuda:0')
episode: 243 training return: tensor(323.3555, device='cuda:0')
epoch: 61 test_true_pfm: 5547.799307261026 sim_pfm: 610.813085505506
episode: 244 training return: tensor(453.0128, device='cuda:0')
episode: 245 training return: tensor(377.6152, device='cuda:0')
episode: 246 training return: tensor(298.9331, device='cuda:0')
episode: 247 training return: tensor(321.1840, device='cuda:0')
epoch: 62 test_true_pfm: 5506.920653927096 sim_pfm: 407.5031394677547
episode: 248 training return: tensor(365.5465, device='cuda:0')
episode: 249 training return: tensor(395.4534, device='cuda:0')
episode: 250 training return: tensor(405.5349, device='cuda:0')
episode: 251 training return: tensor(315.0171, device='cuda:0')
epoch: 63 test_true_pfm: 5521.775525607718 sim_pfm: 514.0210489120024
episode: 252 training return: tensor(509.8222, device='cuda:0')
episode: 253 training return: tensor(296.8029, device='cuda:0')
episode: 254 training return: tensor(337.8360, device='cuda:0')
episode: 255 training return: tensor(391.4000, device='cuda:0')
epoch: 64 test_true_pfm: 5651.9895330607915 sim_pfm: 520.5549186718417
episode: 256 training return: tensor(368.5621, device='cuda:0')
episode: 257 training return: tensor(433.3212, device='cuda:0')
episode: 258 training return: tensor(359.0579, device='cuda:0')
episode: 259 training return: tensor(474.1848, device='cuda:0')
epoch: 65 test_true_pfm: 5576.923117584295 sim_pfm: 550.0662412840562
episode: 260 training return: tensor(478.1357, device='cuda:0')
episode: 261 training return: tensor(498.2599, device='cuda:0')
episode: 262 training return: tensor(478.5301, device='cuda:0')
episode: 263 training return: tensor(446.1605, device='cuda:0')
epoch: 66 test_true_pfm: 5500.336100494231 sim_pfm: 488.89669023267925
episode: 264 training return: tensor(397.1971, device='cuda:0')
episode: 265 training return: tensor(542.3300, device='cuda:0')
episode: 266 training return: tensor(533.2073, device='cuda:0')
episode: 267 training return: tensor(300.8008, device='cuda:0')
epoch: 67 test_true_pfm: 5622.207486762199 sim_pfm: 560.6139256453607
episode: 268 training return: tensor(411.5852, device='cuda:0')
episode: 269 training return: tensor(520.2510, device='cuda:0')
episode: 270 training return: tensor(506.3614, device='cuda:0')
episode: 271 training return: tensor(419.5403, device='cuda:0')
epoch: 68 test_true_pfm: 5644.384117981932 sim_pfm: 490.7052742058101
episode: 272 training return: tensor(439.3201, device='cuda:0')
episode: 273 training return: tensor(436.0411, device='cuda:0')
episode: 274 training return: tensor(546.1030, device='cuda:0')
episode: 275 training return: tensor(482.0618, device='cuda:0')
epoch: 69 test_true_pfm: 5715.500033366375 sim_pfm: 548.6326079013912
episode: 276 training return: tensor(379.2939, device='cuda:0')
episode: 277 training return: tensor(422.6571, device='cuda:0')
episode: 278 training return: tensor(415.0571, device='cuda:0')
episode: 279 training return: tensor(439.1079, device='cuda:0')
epoch: 70 test_true_pfm: 5650.881285876759 sim_pfm: 586.3302329558064
episode: 280 training return: tensor(420.3924, device='cuda:0')
episode: 281 training return: tensor(431.5826, device='cuda:0')
episode: 282 training return: tensor(319.7829, device='cuda:0')
episode: 283 training return: tensor(481.5703, device='cuda:0')
epoch: 71 test_true_pfm: 5694.443178502023 sim_pfm: 552.2487838702897
episode: 284 training return: tensor(393.9314, device='cuda:0')
episode: 285 training return: tensor(374.9201, device='cuda:0')
episode: 286 training return: tensor(479.2479, device='cuda:0')
episode: 287 training return: tensor(419.9328, device='cuda:0')
epoch: 72 test_true_pfm: 5618.173270941542 sim_pfm: 496.9271821007521
episode: 288 training return: tensor(366.1037, device='cuda:0')
episode: 289 training return: tensor(458.0831, device='cuda:0')
episode: 290 training return: tensor(501.8717, device='cuda:0')
episode: 291 training return: tensor(529.1326, device='cuda:0')
epoch: 73 test_true_pfm: 5652.230162572785 sim_pfm: 478.29255371533026
episode: 292 training return: tensor(533.4376, device='cuda:0')
episode: 293 training return: tensor(454.1797, device='cuda:0')
episode: 294 training return: tensor(540.6397, device='cuda:0')
episode: 295 training return: tensor(520.1826, device='cuda:0')
epoch: 74 test_true_pfm: 5615.189160430319 sim_pfm: 542.8327337600446
episode: 296 training return: tensor(510.1253, device='cuda:0')
episode: 297 training return: tensor(449.5654, device='cuda:0')
episode: 298 training return: tensor(417.9062, device='cuda:0')
episode: 299 training return: tensor(565.3325, device='cuda:0')
epoch: 75 test_true_pfm: 5580.196483051136 sim_pfm: 527.333559575025
episode: 300 training return: tensor(432.5413, device='cuda:0')
episode: 301 training return: tensor(497.9643, device='cuda:0')
episode: 302 training return: tensor(556.1466, device='cuda:0')
episode: 303 training return: tensor(512.7399, device='cuda:0')
epoch: 76 test_true_pfm: 5592.223158276031 sim_pfm: 569.8561396934869
episode: 304 training return: tensor(536.9976, device='cuda:0')
episode: 305 training return: tensor(361.4350, device='cuda:0')
episode: 306 training return: tensor(517.4891, device='cuda:0')
episode: 307 training return: tensor(465.5574, device='cuda:0')
epoch: 77 test_true_pfm: 5610.058357320641 sim_pfm: 519.1561153705892
episode: 308 training return: tensor(458.3859, device='cuda:0')
episode: 309 training return: tensor(578.7330, device='cuda:0')
episode: 310 training return: tensor(511.9383, device='cuda:0')
episode: 311 training return: tensor(366.4993, device='cuda:0')
epoch: 78 test_true_pfm: 5585.388498922927 sim_pfm: 543.580698242217
episode: 312 training return: tensor(527.2014, device='cuda:0')
episode: 313 training return: tensor(426.1267, device='cuda:0')
episode: 314 training return: tensor(503.7878, device='cuda:0')
episode: 315 training return: tensor(515.2287, device='cuda:0')
epoch: 79 test_true_pfm: 5563.514031643502 sim_pfm: 550.2076422114236
episode: 316 training return: tensor(558.9839, device='cuda:0')
episode: 317 training return: tensor(543.4180, device='cuda:0')
episode: 318 training return: tensor(482.6695, device='cuda:0')
episode: 319 training return: tensor(508.1153, device='cuda:0')
epoch: 80 test_true_pfm: 5590.1012005430275 sim_pfm: 597.7153796328834
episode: 320 training return: tensor(548.9380, device='cuda:0')
episode: 321 training return: tensor(418.9272, device='cuda:0')
episode: 322 training return: tensor(437.5201, device='cuda:0')
episode: 323 training return: tensor(450.1601, device='cuda:0')
epoch: 81 test_true_pfm: 5696.878439442332 sim_pfm: 600.2669006068027
episode: 324 training return: tensor(549.8764, device='cuda:0')
episode: 325 training return: tensor(466.6625, device='cuda:0')
episode: 326 training return: tensor(426.4850, device='cuda:0')
episode: 327 training return: tensor(577.0050, device='cuda:0')
epoch: 82 test_true_pfm: 5619.467599573524 sim_pfm: 523.6623140515682
episode: 328 training return: tensor(539.4350, device='cuda:0')
episode: 329 training return: tensor(501.4258, device='cuda:0')
episode: 330 training return: tensor(443.9929, device='cuda:0')
episode: 331 training return: tensor(369.8194, device='cuda:0')
epoch: 83 test_true_pfm: 5631.354240405416 sim_pfm: 606.9206605685564
episode: 332 training return: tensor(493.0743, device='cuda:0')
episode: 333 training return: tensor(433.0796, device='cuda:0')
episode: 334 training return: tensor(504.2002, device='cuda:0')
episode: 335 training return: tensor(517.0671, device='cuda:0')
epoch: 84 test_true_pfm: 5729.828412169849 sim_pfm: 551.3558507346703
episode: 336 training return: tensor(431.1960, device='cuda:0')
episode: 337 training return: tensor(528.3816, device='cuda:0')
episode: 338 training return: tensor(484.5958, device='cuda:0')
episode: 339 training return: tensor(395.1406, device='cuda:0')
epoch: 85 test_true_pfm: 5668.557876734587 sim_pfm: 610.3136932785856
episode: 340 training return: tensor(574.0388, device='cuda:0')
episode: 341 training return: tensor(459.3230, device='cuda:0')
episode: 342 training return: tensor(533.2637, device='cuda:0')
episode: 343 training return: tensor(425.6853, device='cuda:0')
epoch: 86 test_true_pfm: 5787.992539982446 sim_pfm: 554.3202734611308
episode: 344 training return: tensor(550.9634, device='cuda:0')
episode: 345 training return: tensor(364.3239, device='cuda:0')
episode: 346 training return: tensor(525.4512, device='cuda:0')
episode: 347 training return: tensor(454.4012, device='cuda:0')
epoch: 87 test_true_pfm: 5662.096086531762 sim_pfm: 527.5440258133458
episode: 348 training return: tensor(375.5472, device='cuda:0')
episode: 349 training return: tensor(416.3080, device='cuda:0')
episode: 350 training return: tensor(545.0023, device='cuda:0')
episode: 351 training return: tensor(493.5241, device='cuda:0')
epoch: 88 test_true_pfm: 5663.808716113759 sim_pfm: 555.5185471303606
episode: 352 training return: tensor(503.4612, device='cuda:0')
episode: 353 training return: tensor(560.9562, device='cuda:0')
episode: 354 training return: tensor(469.7889, device='cuda:0')
episode: 355 training return: tensor(452.5341, device='cuda:0')
epoch: 89 test_true_pfm: 5668.692509919387 sim_pfm: 626.3536939113789
episode: 356 training return: tensor(449.2639, device='cuda:0')
episode: 357 training return: tensor(470.1198, device='cuda:0')
episode: 358 training return: tensor(372.1813, device='cuda:0')
episode: 359 training return: tensor(477.1541, device='cuda:0')
epoch: 90 test_true_pfm: 5633.252958256031 sim_pfm: 509.82736362105544
episode: 360 training return: tensor(463.8277, device='cuda:0')
episode: 361 training return: tensor(500.8466, device='cuda:0')
episode: 362 training return: tensor(506.3782, device='cuda:0')
episode: 363 training return: tensor(525.7131, device='cuda:0')
epoch: 91 test_true_pfm: 5609.716546138164 sim_pfm: 512.4739090669124
episode: 364 training return: tensor(444.4945, device='cuda:0')
episode: 365 training return: tensor(480.8474, device='cuda:0')
episode: 366 training return: tensor(437.2780, device='cuda:0')
episode: 367 training return: tensor(486.6849, device='cuda:0')
epoch: 92 test_true_pfm: 5627.191123450942 sim_pfm: 589.3159954658671
episode: 368 training return: tensor(386.2488, device='cuda:0')
episode: 369 training return: tensor(524.2328, device='cuda:0')
episode: 370 training return: tensor(609.0244, device='cuda:0')
episode: 371 training return: tensor(507.2507, device='cuda:0')
epoch: 93 test_true_pfm: 5627.847629046311 sim_pfm: 589.3730971415256
episode: 372 training return: tensor(542.6252, device='cuda:0')
episode: 373 training return: tensor(375.2482, device='cuda:0')
episode: 374 training return: tensor(403.5947, device='cuda:0')
episode: 375 training return: tensor(464.3900, device='cuda:0')
epoch: 94 test_true_pfm: 5675.897824625589 sim_pfm: 548.1389626086069
episode: 376 training return: tensor(434.8422, device='cuda:0')
episode: 377 training return: tensor(590.6956, device='cuda:0')
episode: 378 training return: tensor(592.2900, device='cuda:0')
episode: 379 training return: tensor(513.0093, device='cuda:0')
epoch: 95 test_true_pfm: 5695.795348027362 sim_pfm: 618.0011766865306
episode: 380 training return: tensor(479.3363, device='cuda:0')
episode: 381 training return: tensor(509.6765, device='cuda:0')
episode: 382 training return: tensor(370.9327, device='cuda:0')
episode: 383 training return: tensor(454.5064, device='cuda:0')
epoch: 96 test_true_pfm: 5763.330885086684 sim_pfm: 574.8927989873142
episode: 384 training return: tensor(518.4868, device='cuda:0')
episode: 385 training return: tensor(412.2084, device='cuda:0')
episode: 386 training return: tensor(573.2953, device='cuda:0')
episode: 387 training return: tensor(597.6173, device='cuda:0')
epoch: 97 test_true_pfm: 5718.058005448874 sim_pfm: 642.213145645801
episode: 388 training return: tensor(514.2612, device='cuda:0')
episode: 389 training return: tensor(418.9701, device='cuda:0')
episode: 390 training return: tensor(533.7913, device='cuda:0')
episode: 391 training return: tensor(436.8956, device='cuda:0')
epoch: 98 test_true_pfm: 5688.207278393097 sim_pfm: 593.3856789075071
episode: 392 training return: tensor(481.3148, device='cuda:0')
episode: 393 training return: tensor(379.9376, device='cuda:0')
episode: 394 training return: tensor(637.7974, device='cuda:0')
episode: 395 training return: tensor(578.0108, device='cuda:0')
epoch: 99 test_true_pfm: 5566.214929724029 sim_pfm: 621.0559306969711
episode: 396 training return: tensor(346.8174, device='cuda:0')
episode: 397 training return: tensor(596.3896, device='cuda:0')
episode: 398 training return: tensor(483.3420, device='cuda:0')
episode: 399 training return: tensor(337.0331, device='cuda:0')
epoch: 100 test_true_pfm: 5722.446503200645 sim_pfm: 511.8563331802143
episode: 400 training return: tensor(304.2093, device='cuda:0')
episode: 401 training return: tensor(473.1666, device='cuda:0')
episode: 402 training return: tensor(443.6089, device='cuda:0')
episode: 403 training return: tensor(421.7380, device='cuda:0')
epoch: 101 test_true_pfm: 5720.061274245499 sim_pfm: 617.3020698748684
episode: 404 training return: tensor(381.6108, device='cuda:0')
episode: 405 training return: tensor(486.0953, device='cuda:0')
episode: 406 training return: tensor(600.6759, device='cuda:0')
episode: 407 training return: tensor(465.3984, device='cuda:0')
epoch: 102 test_true_pfm: 5673.960891037498 sim_pfm: 609.8925069650286
episode: 408 training return: tensor(430.0786, device='cuda:0')
episode: 409 training return: tensor(569.3109, device='cuda:0')
episode: 410 training return: tensor(491.1918, device='cuda:0')
episode: 411 training return: tensor(434.2283, device='cuda:0')
epoch: 103 test_true_pfm: 5714.597355222628 sim_pfm: 647.4256515169594
episode: 412 training return: tensor(339.8708, device='cuda:0')
episode: 413 training return: tensor(497.2144, device='cuda:0')
episode: 414 training return: tensor(456.9739, device='cuda:0')
episode: 415 training return: tensor(441.9722, device='cuda:0')
epoch: 104 test_true_pfm: 5630.529769711879 sim_pfm: 592.7567541341317
episode: 416 training return: tensor(427.2801, device='cuda:0')
episode: 417 training return: tensor(455.2509, device='cuda:0')
episode: 418 training return: tensor(543.3747, device='cuda:0')
episode: 419 training return: tensor(528.4191, device='cuda:0')
epoch: 105 test_true_pfm: 5683.329239528532 sim_pfm: 603.4006782937795
episode: 420 training return: tensor(596.9680, device='cuda:0')
episode: 421 training return: tensor(466.8787, device='cuda:0')
episode: 422 training return: tensor(554.5134, device='cuda:0')
episode: 423 training return: tensor(579.3231, device='cuda:0')
epoch: 106 test_true_pfm: 5701.0451087267575 sim_pfm: 599.4187181905532
episode: 424 training return: tensor(530.4539, device='cuda:0')
episode: 425 training return: tensor(651.9055, device='cuda:0')
episode: 426 training return: tensor(448.3885, device='cuda:0')
episode: 427 training return: tensor(609.7015, device='cuda:0')
epoch: 107 test_true_pfm: 5660.630313417333 sim_pfm: 580.989014962106
episode: 428 training return: tensor(478.5008, device='cuda:0')
episode: 429 training return: tensor(607.8643, device='cuda:0')
episode: 430 training return: tensor(474.0476, device='cuda:0')
episode: 431 training return: tensor(477.1804, device='cuda:0')
epoch: 108 test_true_pfm: 5674.531557746595 sim_pfm: 615.4009045422621
episode: 432 training return: tensor(608.9742, device='cuda:0')
episode: 433 training return: tensor(441.0495, device='cuda:0')
episode: 434 training return: tensor(429.0334, device='cuda:0')
episode: 435 training return: tensor(495.8907, device='cuda:0')
epoch: 109 test_true_pfm: 5649.18861972915 sim_pfm: 603.7728702723786
episode: 436 training return: tensor(368.4328, device='cuda:0')
episode: 437 training return: tensor(389.6331, device='cuda:0')
episode: 438 training return: tensor(677.9720, device='cuda:0')
episode: 439 training return: tensor(560.4576, device='cuda:0')
epoch: 110 test_true_pfm: 5673.814109800181 sim_pfm: 637.4954631027067
episode: 440 training return: tensor(401.0187, device='cuda:0')
episode: 441 training return: tensor(405.8084, device='cuda:0')
episode: 442 training return: tensor(466.2382, device='cuda:0')
episode: 443 training return: tensor(401.0925, device='cuda:0')
epoch: 111 test_true_pfm: 5573.301962007805 sim_pfm: 690.7578373436118
episode: 444 training return: tensor(569.1523, device='cuda:0')
episode: 445 training return: tensor(422.5807, device='cuda:0')
episode: 446 training return: tensor(390.3728, device='cuda:0')
episode: 447 training return: tensor(434.0538, device='cuda:0')
epoch: 112 test_true_pfm: 5684.623041643491 sim_pfm: 652.2003456732103
episode: 448 training return: tensor(511.9034, device='cuda:0')
episode: 449 training return: tensor(481.5211, device='cuda:0')
episode: 450 training return: tensor(543.1531, device='cuda:0')
episode: 451 training return: tensor(558.0331, device='cuda:0')
epoch: 113 test_true_pfm: 5643.120418724461 sim_pfm: 678.8988284392593
episode: 452 training return: tensor(481.7256, device='cuda:0')
episode: 453 training return: tensor(517.4821, device='cuda:0')
episode: 454 training return: tensor(485.4356, device='cuda:0')
episode: 455 training return: tensor(480.7247, device='cuda:0')
epoch: 114 test_true_pfm: 5679.700535277454 sim_pfm: 611.1886944282256
episode: 456 training return: tensor(501.2926, device='cuda:0')
episode: 457 training return: tensor(584.4068, device='cuda:0')
episode: 458 training return: tensor(538.1782, device='cuda:0')
episode: 459 training return: tensor(526.6746, device='cuda:0')
epoch: 115 test_true_pfm: 5605.299695077494 sim_pfm: 586.2719344604217
episode: 460 training return: tensor(507.3999, device='cuda:0')
episode: 461 training return: tensor(550.0252, device='cuda:0')
episode: 462 training return: tensor(597.1806, device='cuda:0')
episode: 463 training return: tensor(459.1665, device='cuda:0')
epoch: 116 test_true_pfm: 5671.070458203582 sim_pfm: 577.4901886742251
episode: 464 training return: tensor(494.1777, device='cuda:0')
episode: 465 training return: tensor(457.8462, device='cuda:0')
episode: 466 training return: tensor(587.5409, device='cuda:0')
episode: 467 training return: tensor(501.4066, device='cuda:0')
epoch: 117 test_true_pfm: 5785.8258567042685 sim_pfm: 602.7665642206945
episode: 468 training return: tensor(402.6655, device='cuda:0')
episode: 469 training return: tensor(452.1661, device='cuda:0')
episode: 470 training return: tensor(341.4190, device='cuda:0')
episode: 471 training return: tensor(589.3095, device='cuda:0')
epoch: 118 test_true_pfm: 5725.941408124195 sim_pfm: 610.6312386106583
episode: 472 training return: tensor(476.4190, device='cuda:0')
episode: 473 training return: tensor(518.8993, device='cuda:0')
episode: 474 training return: tensor(560.7027, device='cuda:0')
episode: 475 training return: tensor(591.0609, device='cuda:0')
epoch: 119 test_true_pfm: 5608.843567695839 sim_pfm: 583.7855071488302
episode: 476 training return: tensor(520.2403, device='cuda:0')
episode: 477 training return: tensor(522.1916, device='cuda:0')
episode: 478 training return: tensor(524.8572, device='cuda:0')
episode: 479 training return: tensor(441.5765, device='cuda:0')
epoch: 120 test_true_pfm: 5654.017020867744 sim_pfm: 616.3197439236877
episode: 480 training return: tensor(409.6317, device='cuda:0')
episode: 481 training return: tensor(557.2322, device='cuda:0')
episode: 482 training return: tensor(547.4559, device='cuda:0')
episode: 483 training return: tensor(524.1007, device='cuda:0')
epoch: 121 test_true_pfm: 5627.7231729589985 sim_pfm: 577.3770645012459
episode: 484 training return: tensor(483.0116, device='cuda:0')
episode: 485 training return: tensor(406.6405, device='cuda:0')
episode: 486 training return: tensor(473.1623, device='cuda:0')
episode: 487 training return: tensor(487.0529, device='cuda:0')
epoch: 122 test_true_pfm: 5669.291311082292 sim_pfm: 654.7617754809326
episode: 488 training return: tensor(518.8839, device='cuda:0')
episode: 489 training return: tensor(583.5958, device='cuda:0')
episode: 490 training return: tensor(561.7003, device='cuda:0')
episode: 491 training return: tensor(592.0046, device='cuda:0')
epoch: 123 test_true_pfm: 5754.313482770012 sim_pfm: 594.7464080268983
episode: 492 training return: tensor(620.0542, device='cuda:0')
episode: 493 training return: tensor(526.2624, device='cuda:0')
episode: 494 training return: tensor(536.1199, device='cuda:0')
episode: 495 training return: tensor(434.1573, device='cuda:0')
epoch: 124 test_true_pfm: 5757.925510893451 sim_pfm: 615.5461683704829
episode: 496 training return: tensor(473.2820, device='cuda:0')
episode: 497 training return: tensor(553.8851, device='cuda:0')
episode: 498 training return: tensor(426.9197, device='cuda:0')
episode: 499 training return: tensor(614.0709, device='cuda:0')
epoch: 125 test_true_pfm: 5697.48810627505 sim_pfm: 596.3191784333516
episode: 500 training return: tensor(471.7850, device='cuda:0')
episode: 501 training return: tensor(448.8011, device='cuda:0')
episode: 502 training return: tensor(410.5302, device='cuda:0')
episode: 503 training return: tensor(282.9814, device='cuda:0')
epoch: 126 test_true_pfm: 5726.366428957609 sim_pfm: 622.1746845145341
episode: 504 training return: tensor(554.8100, device='cuda:0')
episode: 505 training return: tensor(527.7220, device='cuda:0')
episode: 506 training return: tensor(524.7538, device='cuda:0')
episode: 507 training return: tensor(487.7399, device='cuda:0')
epoch: 127 test_true_pfm: 5683.084878367543 sim_pfm: 561.4290542037537
episode: 508 training return: tensor(473.5048, device='cuda:0')
episode: 509 training return: tensor(497.2820, device='cuda:0')
episode: 510 training return: tensor(438.5320, device='cuda:0')
episode: 511 training return: tensor(529.2938, device='cuda:0')
epoch: 128 test_true_pfm: 5630.435324190582 sim_pfm: 586.9724417060303
episode: 512 training return: tensor(575.6613, device='cuda:0')
episode: 513 training return: tensor(457.7205, device='cuda:0')
episode: 514 training return: tensor(470.5611, device='cuda:0')
episode: 515 training return: tensor(520.8325, device='cuda:0')
epoch: 129 test_true_pfm: 5718.861770868895 sim_pfm: 549.8097729600073
episode: 516 training return: tensor(546.9908, device='cuda:0')
episode: 517 training return: tensor(589.6604, device='cuda:0')
episode: 518 training return: tensor(546.2347, device='cuda:0')
episode: 519 training return: tensor(496.3483, device='cuda:0')
epoch: 130 test_true_pfm: 5586.106834567894 sim_pfm: 601.3594467156994
episode: 520 training return: tensor(404.1506, device='cuda:0')
episode: 521 training return: tensor(451.3800, device='cuda:0')
episode: 522 training return: tensor(513.3480, device='cuda:0')
episode: 523 training return: tensor(557.7886, device='cuda:0')
epoch: 131 test_true_pfm: 5708.536745267877 sim_pfm: 651.0645344088165
episode: 524 training return: tensor(466.4189, device='cuda:0')
episode: 525 training return: tensor(488.7830, device='cuda:0')
episode: 526 training return: tensor(431.0242, device='cuda:0')
episode: 527 training return: tensor(593.0791, device='cuda:0')
epoch: 132 test_true_pfm: 5680.940724856487 sim_pfm: 596.352314706106
episode: 528 training return: tensor(471.7544, device='cuda:0')
episode: 529 training return: tensor(377.6761, device='cuda:0')
episode: 530 training return: tensor(363.6230, device='cuda:0')
episode: 531 training return: tensor(555.6565, device='cuda:0')
epoch: 133 test_true_pfm: 5706.830036173084 sim_pfm: 633.735152175262
episode: 532 training return: tensor(327.4994, device='cuda:0')
episode: 533 training return: tensor(516.5854, device='cuda:0')
episode: 534 training return: tensor(355.7360, device='cuda:0')
episode: 535 training return: tensor(508.1803, device='cuda:0')
epoch: 134 test_true_pfm: 5720.170055057616 sim_pfm: 559.9866704104934
episode: 536 training return: tensor(487.6574, device='cuda:0')
episode: 537 training return: tensor(541.4261, device='cuda:0')
episode: 538 training return: tensor(514.9008, device='cuda:0')
episode: 539 training return: tensor(409.9378, device='cuda:0')
epoch: 135 test_true_pfm: 5643.036160362983 sim_pfm: 631.3228934126286
episode: 540 training return: tensor(457.5614, device='cuda:0')
episode: 541 training return: tensor(363.6788, device='cuda:0')
episode: 542 training return: tensor(485.3677, device='cuda:0')
episode: 543 training return: tensor(499.2281, device='cuda:0')
epoch: 136 test_true_pfm: 5708.0969251239685 sim_pfm: 589.1576820599148
episode: 544 training return: tensor(639.7454, device='cuda:0')
episode: 545 training return: tensor(444.5550, device='cuda:0')
episode: 546 training return: tensor(527.2584, device='cuda:0')
episode: 547 training return: tensor(414.9026, device='cuda:0')
epoch: 137 test_true_pfm: 5676.048111001467 sim_pfm: 646.727611599946
episode: 548 training return: tensor(525.5743, device='cuda:0')
episode: 549 training return: tensor(499.7401, device='cuda:0')
episode: 550 training return: tensor(489.3298, device='cuda:0')
episode: 551 training return: tensor(431.0829, device='cuda:0')
epoch: 138 test_true_pfm: 5727.115697078182 sim_pfm: 657.9008825430647
episode: 552 training return: tensor(451.3125, device='cuda:0')
episode: 553 training return: tensor(458.6195, device='cuda:0')
episode: 554 training return: tensor(513.9579, device='cuda:0')
episode: 555 training return: tensor(476.6775, device='cuda:0')
epoch: 139 test_true_pfm: 5701.215954840558 sim_pfm: 585.7286502430507
episode: 556 training return: tensor(597.7458, device='cuda:0')
episode: 557 training return: tensor(538.1963, device='cuda:0')
episode: 558 training return: tensor(500.5526, device='cuda:0')
episode: 559 training return: tensor(464.6064, device='cuda:0')
epoch: 140 test_true_pfm: 5646.501551360878 sim_pfm: 658.0930466380474
episode: 560 training return: tensor(438.8898, device='cuda:0')
episode: 561 training return: tensor(456.9081, device='cuda:0')
episode: 562 training return: tensor(407.6411, device='cuda:0')
episode: 563 training return: tensor(466.4021, device='cuda:0')
epoch: 141 test_true_pfm: 5791.185611204135 sim_pfm: 598.0572218654366
episode: 564 training return: tensor(590.1112, device='cuda:0')
episode: 565 training return: tensor(455.9237, device='cuda:0')
episode: 566 training return: tensor(508.4313, device='cuda:0')
episode: 567 training return: tensor(492.2122, device='cuda:0')
epoch: 142 test_true_pfm: 5623.594832762927 sim_pfm: 626.6288198925322
episode: 568 training return: tensor(406.8316, device='cuda:0')
episode: 569 training return: tensor(256.7260, device='cuda:0')
episode: 570 training return: tensor(386.9706, device='cuda:0')
episode: 571 training return: tensor(485.0733, device='cuda:0')
epoch: 143 test_true_pfm: 5649.956608519208 sim_pfm: 528.4778168787403
episode: 572 training return: tensor(503.7995, device='cuda:0')
episode: 573 training return: tensor(389.8113, device='cuda:0')
episode: 574 training return: tensor(533.8242, device='cuda:0')
episode: 575 training return: tensor(522.6638, device='cuda:0')
epoch: 144 test_true_pfm: 5757.455031237325 sim_pfm: 595.1005672797522
episode: 576 training return: tensor(609.2867, device='cuda:0')
episode: 577 training return: tensor(512.6189, device='cuda:0')
episode: 578 training return: tensor(599.4246, device='cuda:0')
episode: 579 training return: tensor(490.1928, device='cuda:0')
epoch: 145 test_true_pfm: 5642.341600765877 sim_pfm: 544.1412627215614
episode: 580 training return: tensor(419.3708, device='cuda:0')
episode: 581 training return: tensor(416.4638, device='cuda:0')
episode: 582 training return: tensor(474.1869, device='cuda:0')
episode: 583 training return: tensor(572.6824, device='cuda:0')
epoch: 146 test_true_pfm: 5642.817759124016 sim_pfm: 583.362906876253
episode: 584 training return: tensor(574.4762, device='cuda:0')
episode: 585 training return: tensor(594.8591, device='cuda:0')
episode: 586 training return: tensor(517.0015, device='cuda:0')
episode: 587 training return: tensor(485.3872, device='cuda:0')
epoch: 147 test_true_pfm: 5702.046559968146 sim_pfm: 637.1414846402282
episode: 588 training return: tensor(266.3822, device='cuda:0')
episode: 589 training return: tensor(496.5607, device='cuda:0')
episode: 590 training return: tensor(645.5074, device='cuda:0')
episode: 591 training return: tensor(501.8826, device='cuda:0')
epoch: 148 test_true_pfm: 5684.0261166807695 sim_pfm: 612.9980330650384
episode: 592 training return: tensor(493.2246, device='cuda:0')
episode: 593 training return: tensor(510.7569, device='cuda:0')
episode: 594 training return: tensor(505.9811, device='cuda:0')
episode: 595 training return: tensor(484.8997, device='cuda:0')
epoch: 149 test_true_pfm: 5685.154716385248 sim_pfm: 655.3239706210637
episode: 596 training return: tensor(343.7800, device='cuda:0')
episode: 597 training return: tensor(470.4888, device='cuda:0')
episode: 598 training return: tensor(527.7177, device='cuda:0')
episode: 599 training return: tensor(328.4275, device='cuda:0')
epoch: 150 test_true_pfm: 5567.262999275513 sim_pfm: 613.0939716456536
