['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '1', '--data', '30000', '--sub']
epoch: 0 training_loss 0.28848781682550906 test_loss: 0.19726577997207642
epoch: 1 training_loss 0.1624799881130457 test_loss: 0.15489718914031983
epoch: 2 training_loss 0.14262752052396535 test_loss: 0.15491341352462767
epoch: 3 training_loss 0.1348598722741008 test_loss: 0.14180024862289428
epoch: 4 training_loss 0.12574206680059433 test_loss: 0.11214028596878052
epoch: 5 training_loss 0.11307210091501474 test_loss: 0.09829457998275756
epoch: 6 training_loss 0.12277034167200326 test_loss: 0.10833251476287842
epoch: 7 training_loss 0.10776374513283372 test_loss: 0.11129914522171021
epoch: 8 training_loss 0.11027647968381643 test_loss: 0.11984515190124512
epoch: 9 training_loss 0.1094812286645174 test_loss: 0.1222827672958374
epoch: 10 training_loss 0.10922431096434593 test_loss: 0.1183418869972229
epoch: 11 training_loss 0.10186157770454883 test_loss: 0.09495329856872559
epoch: 12 training_loss 0.10462220894172787 test_loss: 0.10656365156173705
epoch: 13 training_loss 0.1044227659329772 test_loss: 0.10032509565353394
epoch: 14 training_loss 0.1012629595771432 test_loss: 0.09443517923355102
epoch: 15 training_loss 0.11110857460647822 test_loss: 0.11062936782836914
epoch: 16 training_loss 0.09744975695386529 test_loss: 0.10994327068328857
epoch: 17 training_loss 0.1011370499804616 test_loss: 0.10452151298522949
epoch: 18 training_loss 0.09703291833400726 test_loss: 0.10658104419708252
epoch: 19 training_loss 0.09877471785992384 test_loss: 0.1043657660484314
epoch: 20 training_loss 0.10623701613396407 test_loss: 0.09808571934700012
epoch: 21 training_loss 0.09932445485144853 test_loss: 0.0999366283416748
epoch: 22 training_loss 0.09403306210413576 test_loss: 0.10223236083984374
epoch: 23 training_loss 0.0923735786229372 test_loss: 0.09647554159164429
epoch: 24 training_loss 0.10155095864087343 test_loss: 0.08794453740119934
epoch: 25 training_loss 0.09598278801888227 test_loss: 0.10557678937911988
epoch: 26 training_loss 0.10156471967697143 test_loss: 0.10593599081039429
epoch: 27 training_loss 0.09341755682602525 test_loss: 0.10698510408401489
epoch: 28 training_loss 0.09032698044553399 test_loss: 0.08640406727790832
epoch: 29 training_loss 0.09651811879128218 test_loss: 0.09001199603080749
epoch: 30 training_loss 0.09685052026063204 test_loss: 0.09848438501358033
epoch: 31 training_loss 0.10322300456464291 test_loss: 0.09442049264907837
epoch: 32 training_loss 0.09937080826610327 test_loss: 0.0911403775215149
epoch: 33 training_loss 0.09095759309828282 test_loss: 0.09701303243637086
epoch: 34 training_loss 0.08941648982465267 test_loss: 0.10349876880645752
epoch: 35 training_loss 0.09426245709881187 test_loss: 0.10148712396621704
epoch: 36 training_loss 0.08541227716952562 test_loss: 0.08954319357872009
epoch: 37 training_loss 0.09532471489161252 test_loss: 0.09298326373100281
epoch: 38 training_loss 0.09535464433953166 test_loss: 0.08793995380401612
epoch: 39 training_loss 0.09638316482305527 test_loss: 0.0950016975402832
epoch: 40 training_loss 0.08859978040680289 test_loss: 0.09994820356369019
epoch: 41 training_loss 0.09428307361900806 test_loss: 0.09355754256248475
epoch: 42 training_loss 0.0949603126756847 test_loss: 0.08562524318695068
epoch: 43 training_loss 0.09065476635470987 test_loss: 0.08568127155303955
epoch: 44 training_loss 0.08951575791463257 test_loss: 0.10060070753097534
epoch: 45 training_loss 0.09511009687557817 test_loss: 0.08702723979949951
epoch: 46 training_loss 0.09609380494803191 test_loss: 0.09554449915885925
epoch: 47 training_loss 0.09152483595535159 test_loss: 0.09284510612487792
epoch: 48 training_loss 0.09348685525357724 test_loss: 0.09881370663642883
epoch: 49 training_loss 0.09196066172793507 test_loss: 0.09941272139549255
epoch: 50 training_loss 0.09221101170405746 test_loss: 0.08334105014801026
epoch: 51 training_loss 0.0979344792291522 test_loss: 0.09384958148002624
epoch: 52 training_loss 0.09577175494283438 test_loss: 0.0877537727355957
epoch: 53 training_loss 0.08572320051491261 test_loss: 0.09126493930816651
epoch: 54 training_loss 0.09056636322289706 test_loss: 0.08568003177642822
epoch: 55 training_loss 0.08540826097130776 test_loss: 0.09230612516403199
epoch: 56 training_loss 0.08624336389824748 test_loss: 0.07862344980239869
epoch: 57 training_loss 0.09037225319072605 test_loss: 0.08628633022308349
epoch: 58 training_loss 0.09031641427427531 test_loss: 0.09444345235824585
epoch: 59 training_loss 0.09320459797978402 test_loss: 0.08471317291259765
epoch: 60 training_loss 0.0925491552054882 test_loss: 0.09157446622848511
epoch: 61 training_loss 0.0917273622751236 test_loss: 0.08523843288421631
epoch: 62 training_loss 0.08917467763647437 test_loss: 0.09047881364822388
epoch: 63 training_loss 0.08959587873890996 test_loss: 0.10018928050994873
epoch: 64 training_loss 0.09978759329766035 test_loss: 0.0875230610370636
epoch: 65 training_loss 0.089569486733526 test_loss: 0.09253460764884949
epoch: 66 training_loss 0.0828248145338148 test_loss: 0.09293640851974487
epoch: 67 training_loss 0.0860727284476161 test_loss: 0.09722902178764344
epoch: 68 training_loss 0.09047846408560872 test_loss: 0.09453363418579101
epoch: 69 training_loss 0.08279339693486691 test_loss: 0.08818609714508056
epoch: 70 training_loss 0.08496911177411676 test_loss: 0.09109379649162293
epoch: 71 training_loss 0.09257255516946315 test_loss: 0.08397719264030457
epoch: 72 training_loss 0.09029958458617329 test_loss: 0.09766442179679871
epoch: 73 training_loss 0.07788227223791182 test_loss: 0.09893502593040467
epoch: 74 training_loss 0.08950829461216926 test_loss: 0.0821608543395996
epoch: 75 training_loss 0.09159639898687601 test_loss: 0.08930912017822265
epoch: 76 training_loss 0.09036573644727469 test_loss: 0.10277460813522339
epoch: 77 training_loss 0.08376407761126757 test_loss: 0.11189979314804077
epoch: 78 training_loss 0.09037764770910144 test_loss: 0.09600064158439636
epoch: 79 training_loss 0.09154735637828708 test_loss: 0.09364145398139953
epoch: 80 training_loss 0.08519092613831163 test_loss: 0.08560149073600769
epoch: 81 training_loss 0.0866550125926733 test_loss: 0.09583641886711121
epoch: 82 training_loss 0.08542980102822184 test_loss: 0.09040658473968506
epoch: 83 training_loss 0.08597360912710428 test_loss: 0.09675627946853638
epoch: 84 training_loss 0.08785505704581738 test_loss: 0.08378799557685852
epoch: 85 training_loss 0.08745559165254235 test_loss: 0.0991672158241272
epoch: 86 training_loss 0.08721194367855788 test_loss: 0.0981919527053833
epoch: 87 training_loss 0.08161725195124746 test_loss: 0.10420122146606445
epoch: 88 training_loss 0.08603657057508826 test_loss: 0.09553957581520081
epoch: 89 training_loss 0.08151771165430546 test_loss: 0.1110229730606079
epoch: 90 training_loss 0.08008382312953471 test_loss: 0.10296844244003296
epoch: 91 training_loss 0.08271376382559538 test_loss: 0.0934264600276947
epoch: 92 training_loss 0.07928300078958272 test_loss: 0.09275658130645752
epoch: 93 training_loss 0.08885743265971541 test_loss: 0.09691832065582276
epoch: 94 training_loss 0.0908808122202754 test_loss: 0.09331154227256774
epoch: 95 training_loss 0.08294313214719296 test_loss: 0.09761079549789428
epoch: 96 training_loss 0.08415921291336417 test_loss: 0.09117773771286011
epoch: 97 training_loss 0.08817304180935025 test_loss: 0.09317342042922974
epoch: 98 training_loss 0.08943971594795584 test_loss: 0.09308500289916992
epoch: 99 training_loss 0.08518767742440105 test_loss: 0.09807442426681519
epoch: 100 training_loss 0.08406626004725695 test_loss: 0.10498149394989013
epoch: 101 training_loss 0.08172504410147667 test_loss: 0.08774344921112061
epoch: 102 training_loss 0.08259939091280102 test_loss: 0.09213384985923767
epoch: 103 training_loss 0.08549858247861267 test_loss: 0.08719751238822937
epoch: 104 training_loss 0.08725328173488378 test_loss: 0.08888878226280213
epoch: 105 training_loss 0.07830647550523281 test_loss: 0.10627038478851318
epoch: 106 training_loss 0.07969291053712368 test_loss: 0.08926265239715576
epoch: 107 training_loss 0.08748005692847073 test_loss: 0.08246825933456421
epoch: 108 training_loss 0.08935178326442837 test_loss: 0.08185735940933228
epoch: 109 training_loss 0.08426077779382467 test_loss: 0.08673549890518188
epoch: 110 training_loss 0.081042855726555 test_loss: 0.0916456401348114
epoch: 111 training_loss 0.0863076238706708 test_loss: 0.09811485409736634
epoch: 112 training_loss 0.07881595407612622 test_loss: 0.09670624732971192
epoch: 113 training_loss 0.08238598940894008 test_loss: 0.09520028829574585
epoch: 114 training_loss 0.08406245555728674 test_loss: 0.09969149231910705
epoch: 115 training_loss 0.08225116603076459 test_loss: 0.098975670337677
epoch: 116 training_loss 0.09071320738643408 test_loss: 0.08904606103897095
epoch: 117 training_loss 0.09138121534138918 test_loss: 0.0850946307182312
epoch: 118 training_loss 0.08436817651614546 test_loss: 0.08664442300796509
epoch: 119 training_loss 0.08676632715389132 test_loss: 0.10082123279571534
epoch: 120 training_loss 0.07939214961603284 test_loss: 0.09229773283004761
epoch: 121 training_loss 0.08499695697799325 test_loss: 0.11129999160766602
epoch: 122 training_loss 0.08827181855216622 test_loss: 0.10604790449142457
epoch: 123 training_loss 0.08577359803020954 test_loss: 0.08382616639137268
epoch: 124 training_loss 0.08142894186079502 test_loss: 0.0930277943611145
epoch: 125 training_loss 0.08696553906425834 test_loss: 0.09472052454948425
epoch: 126 training_loss 0.08002106914296746 test_loss: 0.10334402322769165
epoch: 127 training_loss 0.08870682677254081 test_loss: 0.10504103899002075
epoch: 128 training_loss 0.08402152005583048 test_loss: 0.08928661346435547
epoch: 129 training_loss 0.08346460293978453 test_loss: 0.09262619614601135
epoch: 130 training_loss 0.08226841069757938 test_loss: 0.10671180486679077
epoch: 131 training_loss 0.07513313811272383 test_loss: 0.08763235807418823
epoch: 132 training_loss 0.0844185072556138 test_loss: 0.10771667957305908
epoch: 133 training_loss 0.07732188355177641 test_loss: 0.08482664823532104
epoch: 134 training_loss 0.08944576984271407 test_loss: 0.08946257829666138
epoch: 135 training_loss 0.0860905398055911 test_loss: 0.10635749101638795
epoch: 136 training_loss 0.07977480981498956 test_loss: 0.10350381135940552
epoch: 137 training_loss 0.07946477698162198 test_loss: 0.10076777935028076
epoch: 138 training_loss 0.08608284456655384 test_loss: 0.09048047065734863
epoch: 139 training_loss 0.07849742854014038 test_loss: 0.09297049641609192
epoch: 140 training_loss 0.08231058226898312 test_loss: 0.09641795754432678
epoch: 141 training_loss 0.07959480823948979 test_loss: 0.09516382217407227
epoch: 142 training_loss 0.0835104518570006 test_loss: 0.09283034205436706
epoch: 143 training_loss 0.08377294413745404 test_loss: 0.089279705286026
epoch: 144 training_loss 0.08119266906753182 test_loss: 0.10641227960586548
epoch: 145 training_loss 0.0776500928774476 test_loss: 0.10001190900802612
epoch: 146 training_loss 0.07450366672128439 test_loss: 0.11492502689361572
epoch: 147 training_loss 0.07899793829768896 test_loss: 0.09631838202476502
epoch: 148 training_loss 0.07848839685320855 test_loss: 0.10337913036346436
epoch: 149 training_loss 0.08292939551174641 test_loss: 0.09324287176132202
epoch: 0 training_loss 40.049550762176516 test_loss: 21.58949432373047
epoch: 1 training_loss 17.107266607284547 test_loss: 13.463499450683594
epoch: 2 training_loss 12.358658895492553 test_loss: 11.322954559326172
epoch: 3 training_loss 10.237129707336425 test_loss: 9.392096710205077
epoch: 4 training_loss 8.953793783187866 test_loss: 8.835314178466797
epoch: 5 training_loss 8.006386289596557 test_loss: 7.668721008300781
epoch: 6 training_loss 7.411938099861145 test_loss: 7.369718933105469
epoch: 7 training_loss 6.899736118316651 test_loss: 6.557231140136719
epoch: 8 training_loss 6.4871590709686275 test_loss: 6.376021957397461
epoch: 9 training_loss 6.067681350708008 test_loss: 5.911120986938476
epoch: 10 training_loss 5.790965418815613 test_loss: 6.014753341674805
epoch: 11 training_loss 5.737031364440918 test_loss: 5.6883087158203125
epoch: 12 training_loss 5.318202614784241 test_loss: 5.323408889770508
epoch: 13 training_loss 5.344848289489746 test_loss: 5.184464645385742
epoch: 14 training_loss 4.972139844894409 test_loss: 5.215156173706054
epoch: 15 training_loss 4.965366587638855 test_loss: 4.564716339111328
epoch: 16 training_loss 4.742245552539825 test_loss: 4.922589874267578
epoch: 17 training_loss 4.716138272285462 test_loss: 4.554795455932617
epoch: 18 training_loss 4.528549582958221 test_loss: 4.662015914916992
epoch: 19 training_loss 4.372369315624237 test_loss: 4.437422561645508
epoch: 20 training_loss 4.18883180141449 test_loss: 4.219499969482422
epoch: 21 training_loss 4.049944758415222 test_loss: 4.409156417846679
epoch: 22 training_loss 3.979137887954712 test_loss: 4.243399047851563
epoch: 23 training_loss 4.058802051544189 test_loss: 4.094795989990234
epoch: 24 training_loss 3.9453010678291323 test_loss: 4.137991333007813
epoch: 25 training_loss 3.938642449378967 test_loss: 3.9697250366210937
epoch: 26 training_loss 3.8420315265655516 test_loss: 3.923033905029297
epoch: 27 training_loss 3.7633976984024047 test_loss: 3.7365463256835936
epoch: 28 training_loss 3.686818106174469 test_loss: 4.072012329101563
epoch: 29 training_loss 3.6028161740303037 test_loss: 3.8169349670410155
epoch: 30 training_loss 3.5974934315681457 test_loss: 3.6474037170410156
epoch: 31 training_loss 3.5625358057022094 test_loss: 3.6928054809570314
epoch: 32 training_loss 3.5086203145980837 test_loss: 3.721719741821289
epoch: 33 training_loss 3.4719601035118104 test_loss: 3.538747787475586
epoch: 34 training_loss 3.398627212047577 test_loss: 3.478135681152344
epoch: 35 training_loss 3.333605873584747 test_loss: 3.366066741943359
epoch: 36 training_loss 3.345285487174988 test_loss: 3.5441818237304688
epoch: 37 training_loss 3.3378427052497863 test_loss: 3.466116714477539
epoch: 38 training_loss 3.2628099966049193 test_loss: 3.3827877044677734
epoch: 39 training_loss 3.255496664047241 test_loss: 3.353063201904297
epoch: 40 training_loss 3.2312451100349424 test_loss: 3.356944274902344
epoch: 41 training_loss 3.175906791687012 test_loss: 3.304346466064453
epoch: 42 training_loss 3.1156317090988157 test_loss: 3.222442626953125
epoch: 43 training_loss 3.0952491927146912 test_loss: 3.1129404067993165
epoch: 44 training_loss 3.092771899700165 test_loss: 3.2207733154296876
epoch: 45 training_loss 3.117976806163788 test_loss: 3.16906681060791
epoch: 46 training_loss 3.0268367290496827 test_loss: 3.0014675140380858
epoch: 47 training_loss 3.006752908229828 test_loss: 3.134379005432129
epoch: 48 training_loss 3.058275969028473 test_loss: 3.154868507385254
epoch: 49 training_loss 2.95094783782959 test_loss: 3.076340675354004
epoch: 50 training_loss 2.901875057220459 test_loss: 2.9496795654296877
epoch: 51 training_loss 2.9896570658683777 test_loss: 2.991373634338379
epoch: 52 training_loss 2.90369692325592 test_loss: 2.836918067932129
epoch: 53 training_loss 2.8533642435073854 test_loss: 2.997725486755371
epoch: 54 training_loss 2.837067030668259 test_loss: 2.9670339584350587
epoch: 55 training_loss 2.8612823057174683 test_loss: 3.0247608184814454
epoch: 56 training_loss 2.8617894220352174 test_loss: 2.856494331359863
epoch: 57 training_loss 2.8610298919677732 test_loss: 2.797707748413086
epoch: 58 training_loss 2.760825617313385 test_loss: 2.917815589904785
epoch: 59 training_loss 2.840224950313568 test_loss: 2.8914512634277343
epoch: 60 training_loss 2.8140050911903383 test_loss: 2.8606380462646483
epoch: 61 training_loss 2.766066871881485 test_loss: 2.894414710998535
epoch: 62 training_loss 2.7454260194301607 test_loss: 2.6620105743408202
epoch: 63 training_loss 2.69225457072258 test_loss: 2.810835266113281
epoch: 64 training_loss 2.646730363368988 test_loss: 2.820928955078125
epoch: 65 training_loss 2.7265594840049743 test_loss: 2.8222993850708007
epoch: 66 training_loss 2.6250701332092286 test_loss: 3.011391830444336
epoch: 67 training_loss 2.6408907413482665 test_loss: 2.820327949523926
epoch: 68 training_loss 2.676186378002167 test_loss: 2.748984718322754
epoch: 69 training_loss 2.635252991914749 test_loss: 2.8481813430786134
epoch: 70 training_loss 2.5995184540748597 test_loss: 2.796618843078613
epoch: 71 training_loss 2.575019338130951 test_loss: 2.7323226928710938
epoch: 72 training_loss 2.5710974609851838 test_loss: 2.876902389526367
epoch: 73 training_loss 2.574281916618347 test_loss: 2.6796136856079102
epoch: 74 training_loss 2.5718087673187258 test_loss: 2.717451477050781
epoch: 75 training_loss 2.6025398993492126 test_loss: 2.6690717697143556
epoch: 76 training_loss 2.6018796372413635 test_loss: 2.6784353256225586
epoch: 77 training_loss 2.5230925452709196 test_loss: 2.6947120666503905
epoch: 78 training_loss 2.5505199646949768 test_loss: 2.6700113296508787
epoch: 79 training_loss 2.5394067668914797 test_loss: 2.668041801452637
epoch: 80 training_loss 2.5349178874492644 test_loss: 2.5616973876953124
epoch: 81 training_loss 2.5366207325458525 test_loss: 2.741824913024902
epoch: 82 training_loss 2.493499816656113 test_loss: 2.71829776763916
epoch: 83 training_loss 2.517060078382492 test_loss: 2.5012081146240233
epoch: 84 training_loss 2.4710369229316713 test_loss: 2.619925308227539
epoch: 85 training_loss 2.4671621704101563 test_loss: 2.5055702209472654
epoch: 86 training_loss 2.469676623344421 test_loss: 2.5700847625732424
epoch: 87 training_loss 2.488302049636841 test_loss: 2.5872051239013674
epoch: 88 training_loss 2.439446277618408 test_loss: 2.576847457885742
epoch: 89 training_loss 2.370995203256607 test_loss: 2.497376251220703
epoch: 90 training_loss 2.4559974193573 test_loss: 2.4409889221191405
epoch: 91 training_loss 2.5339537930488585 test_loss: 2.586078071594238
epoch: 92 training_loss 2.3834651672840117 test_loss: 2.737481880187988
epoch: 93 training_loss 2.4202560245990754 test_loss: 2.5432193756103514
epoch: 94 training_loss 2.3960024380683898 test_loss: 2.5871871948242187
epoch: 95 training_loss 2.4345818984508516 test_loss: 2.5045167922973635
epoch: 96 training_loss 2.4633950543403627 test_loss: 2.472911262512207
epoch: 97 training_loss 2.3658049583435057 test_loss: 2.306039237976074
epoch: 98 training_loss 2.3486191749572756 test_loss: 2.4312700271606444
epoch: 99 training_loss 2.3884584403038023 test_loss: 2.4682472229003904
epoch: 100 training_loss 2.3253291392326356 test_loss: 2.415757179260254
epoch: 101 training_loss 2.300127581357956 test_loss: 2.5988224029541014
epoch: 102 training_loss 2.3738131809234617 test_loss: 2.4477367401123047
epoch: 103 training_loss 2.377651778459549 test_loss: 2.3923019409179687
epoch: 104 training_loss 2.2920806121826174 test_loss: 2.517713737487793
epoch: 105 training_loss 2.3730013823509215 test_loss: 2.411201286315918
epoch: 106 training_loss 2.348021231889725 test_loss: 2.526986312866211
epoch: 107 training_loss 2.2875356006622316 test_loss: 2.384465980529785
epoch: 108 training_loss 2.3496164262294768 test_loss: 2.5155805587768554
epoch: 109 training_loss 2.292903926372528 test_loss: 2.4740285873413086
epoch: 110 training_loss 2.246948094367981 test_loss: 2.4103815078735353
epoch: 111 training_loss 2.290335395336151 test_loss: 2.482695198059082
epoch: 112 training_loss 2.2902215230464935 test_loss: 2.369181442260742
epoch: 113 training_loss 2.285533933639526 test_loss: 2.4866510391235352
epoch: 114 training_loss 2.214621624946594 test_loss: 2.41656379699707
epoch: 115 training_loss 2.2699119305610655 test_loss: 2.4419580459594727
epoch: 116 training_loss 2.272558778524399 test_loss: 2.3679670333862304
epoch: 117 training_loss 2.352607947587967 test_loss: 2.4184602737426757
epoch: 118 training_loss 2.2401467072963714 test_loss: 2.3797977447509764
epoch: 119 training_loss 2.2444330632686613 test_loss: 2.3761451721191404
epoch: 120 training_loss 2.303076289892197 test_loss: 2.3679885864257812
epoch: 121 training_loss 2.2816097068786623 test_loss: 2.343711090087891
epoch: 122 training_loss 2.2284897339344023 test_loss: 2.2791404724121094
epoch: 123 training_loss 2.277999883890152 test_loss: 2.341765213012695
epoch: 124 training_loss 2.2255645644664765 test_loss: 2.3488132476806642
epoch: 125 training_loss 2.2252300322055816 test_loss: 2.334570121765137
epoch: 126 training_loss 2.2713417172431947 test_loss: 2.373691368103027
epoch: 127 training_loss 2.1946525919437407 test_loss: 2.226808547973633
epoch: 128 training_loss 2.2406673419475553 test_loss: 2.3741212844848634
epoch: 129 training_loss 2.2373912394046784 test_loss: 2.4427972793579102
epoch: 130 training_loss 2.251829673051834 test_loss: 2.388632965087891
epoch: 131 training_loss 2.196603581905365 test_loss: 2.333724594116211
epoch: 132 training_loss 2.253178471326828 test_loss: 2.36850528717041
epoch: 133 training_loss 2.220922771692276 test_loss: 2.240347480773926
epoch: 134 training_loss 2.1523507726192475 test_loss: 2.212152290344238
epoch: 135 training_loss 2.195125290155411 test_loss: 2.2871641159057616
epoch: 136 training_loss 2.1977929162979124 test_loss: 2.299746513366699
epoch: 137 training_loss 2.1665225398540495 test_loss: 2.27032356262207
epoch: 138 training_loss 2.193736045360565 test_loss: 2.228434753417969
epoch: 139 training_loss 2.1533292615413666 test_loss: 2.1778955459594727
epoch: 140 training_loss 2.2192618477344515 test_loss: 2.205551338195801
epoch: 141 training_loss 2.160975687503815 test_loss: 2.22607364654541
epoch: 142 training_loss 2.161859560012817 test_loss: 2.3626808166503905
epoch: 143 training_loss 2.208629664182663 test_loss: 2.293476676940918
epoch: 144 training_loss 2.17364155292511 test_loss: 2.3174001693725588
epoch: 145 training_loss 2.177487553358078 test_loss: 2.359610939025879
epoch: 146 training_loss 2.159969531297684 test_loss: 2.20662841796875
epoch: 147 training_loss 2.1876089668273924 test_loss: 2.220135307312012
epoch: 148 training_loss 2.1770445239543914 test_loss: 2.2267267227172853
epoch: 149 training_loss 2.118054918050766 test_loss: 2.325663757324219
2842.9407096364407
episode: 0 training return: tensor(67.4489, device='cuda:0')
episode: 1 training return: tensor(324.3073, device='cuda:0')
episode: 2 training return: tensor(309.1589, device='cuda:0')
episode: 3 training return: tensor(43.0210, device='cuda:0')
epoch: 1 test_true_pfm: 2907.457547554281 sim_pfm: 128.1335508741322
episode: 4 training return: tensor(175.9582, device='cuda:0')
episode: 5 training return: tensor(279.9156, device='cuda:0')
episode: 6 training return: tensor(391.6479, device='cuda:0')
episode: 7 training return: tensor(-325.2779, device='cuda:0')
epoch: 2 test_true_pfm: 3387.5106477920594 sim_pfm: 280.5053943998161
episode: 8 training return: tensor(284.0827, device='cuda:0')
episode: 9 training return: tensor(267.5833, device='cuda:0')
episode: 10 training return: tensor(406.6436, device='cuda:0')
episode: 11 training return: tensor(381.5851, device='cuda:0')
epoch: 3 test_true_pfm: 3440.5051884436853 sim_pfm: 444.19934637180995
episode: 12 training return: tensor(296.0931, device='cuda:0')
episode: 13 training return: tensor(384.2002, device='cuda:0')
episode: 14 training return: tensor(378.1008, device='cuda:0')
episode: 15 training return: tensor(354.4599, device='cuda:0')
epoch: 4 test_true_pfm: 3359.9272783306074 sim_pfm: 398.61374237792916
episode: 16 training return: tensor(407.0738, device='cuda:0')
episode: 17 training return: tensor(70.9471, device='cuda:0')
episode: 18 training return: tensor(326.2149, device='cuda:0')
episode: 19 training return: tensor(373.1866, device='cuda:0')
epoch: 5 test_true_pfm: 3363.0958664591885 sim_pfm: 362.3856549314417
episode: 20 training return: tensor(330.5620, device='cuda:0')
episode: 21 training return: tensor(365.0350, device='cuda:0')
episode: 22 training return: tensor(416.2292, device='cuda:0')
episode: 23 training return: tensor(-49.9913, device='cuda:0')
epoch: 6 test_true_pfm: 3076.312617536065 sim_pfm: 242.8088140283944
episode: 24 training return: tensor(380.9306, device='cuda:0')
episode: 25 training return: tensor(303.9924, device='cuda:0')
episode: 26 training return: tensor(71.0553, device='cuda:0')
episode: 27 training return: tensor(376.7658, device='cuda:0')
epoch: 7 test_true_pfm: 3400.780364722196 sim_pfm: 271.2817252490592
episode: 28 training return: tensor(374.5453, device='cuda:0')
episode: 29 training return: tensor(29.2893, device='cuda:0')
episode: 30 training return: tensor(367.3641, device='cuda:0')
episode: 31 training return: tensor(365.7395, device='cuda:0')
epoch: 8 test_true_pfm: 3067.3570014561215 sim_pfm: 396.51279965330224
episode: 32 training return: tensor(416.4856, device='cuda:0')
episode: 33 training return: tensor(111.1656, device='cuda:0')
episode: 34 training return: tensor(397.0362, device='cuda:0')
episode: 35 training return: tensor(318.3184, device='cuda:0')
epoch: 9 test_true_pfm: 3301.087491444108 sim_pfm: 377.1266503809117
episode: 36 training return: tensor(349.8522, device='cuda:0')
episode: 37 training return: tensor(233.0209, device='cuda:0')
episode: 38 training return: tensor(-48.0693, device='cuda:0')
episode: 39 training return: tensor(289.4588, device='cuda:0')
epoch: 10 test_true_pfm: 2996.786117635869 sim_pfm: 309.6748351021185
episode: 40 training return: tensor(412.4719, device='cuda:0')
episode: 41 training return: tensor(216.2603, device='cuda:0')
episode: 42 training return: tensor(421.5226, device='cuda:0')
episode: 43 training return: tensor(169.6261, device='cuda:0')
epoch: 11 test_true_pfm: 3409.817464591974 sim_pfm: 397.65325486727914
episode: 44 training return: tensor(417.7508, device='cuda:0')
episode: 45 training return: tensor(378.2903, device='cuda:0')
episode: 46 training return: tensor(374.5081, device='cuda:0')
episode: 47 training return: tensor(343.4732, device='cuda:0')
epoch: 12 test_true_pfm: 3398.7797257842685 sim_pfm: 377.3098283308791
episode: 48 training return: tensor(383.5890, device='cuda:0')
episode: 49 training return: tensor(320.2780, device='cuda:0')
episode: 50 training return: tensor(373.3461, device='cuda:0')
episode: 51 training return: tensor(53.0378, device='cuda:0')
epoch: 13 test_true_pfm: 3337.8249377486377 sim_pfm: 265.3400396987272
episode: 52 training return: tensor(168.6247, device='cuda:0')
episode: 53 training return: tensor(338.6892, device='cuda:0')
episode: 54 training return: tensor(182.7090, device='cuda:0')
episode: 55 training return: tensor(340.5668, device='cuda:0')
epoch: 14 test_true_pfm: 2820.551023770701 sim_pfm: 422.09339670282014
episode: 56 training return: tensor(5.6932, device='cuda:0')
episode: 57 training return: tensor(362.2817, device='cuda:0')
episode: 58 training return: tensor(479.7501, device='cuda:0')
episode: 59 training return: tensor(283.1722, device='cuda:0')
epoch: 15 test_true_pfm: 2842.3876687962606 sim_pfm: 298.0404625861168
episode: 60 training return: tensor(155.1987, device='cuda:0')
episode: 61 training return: tensor(-130.5141, device='cuda:0')
episode: 62 training return: tensor(317.1036, device='cuda:0')
episode: 63 training return: tensor(345.1812, device='cuda:0')
epoch: 16 test_true_pfm: 3357.5984994334285 sim_pfm: 294.5777109756309
episode: 64 training return: tensor(-146.5177, device='cuda:0')
episode: 65 training return: tensor(362.5351, device='cuda:0')
episode: 66 training return: tensor(374.5373, device='cuda:0')
episode: 67 training return: tensor(377.7162, device='cuda:0')
epoch: 17 test_true_pfm: 3342.37792176839 sim_pfm: 288.35714281676337
episode: 68 training return: tensor(18.3774, device='cuda:0')
episode: 69 training return: tensor(386.7813, device='cuda:0')
episode: 70 training return: tensor(333.1292, device='cuda:0')
episode: 71 training return: tensor(-255.7241, device='cuda:0')
epoch: 18 test_true_pfm: 3291.7769871542127 sim_pfm: 49.33392081836549
episode: 72 training return: tensor(360.2551, device='cuda:0')
episode: 73 training return: tensor(387.7129, device='cuda:0')
episode: 74 training return: tensor(327.9044, device='cuda:0')
episode: 75 training return: tensor(378.4138, device='cuda:0')
epoch: 19 test_true_pfm: 3191.1667307428493 sim_pfm: 362.430895511158
episode: 76 training return: tensor(115.3551, device='cuda:0')
episode: 77 training return: tensor(391.3779, device='cuda:0')
episode: 78 training return: tensor(378.0417, device='cuda:0')
episode: 79 training return: tensor(362.8173, device='cuda:0')
epoch: 20 test_true_pfm: 3171.751387915416 sim_pfm: 378.549920027154
episode: 80 training return: tensor(377.0174, device='cuda:0')
episode: 81 training return: tensor(207.5375, device='cuda:0')
episode: 82 training return: tensor(379.2733, device='cuda:0')
episode: 83 training return: tensor(362.0615, device='cuda:0')
epoch: 21 test_true_pfm: 2993.9701289244226 sim_pfm: 298.9833889233608
episode: 84 training return: tensor(413.3107, device='cuda:0')
episode: 85 training return: tensor(326.9438, device='cuda:0')
episode: 86 training return: tensor(365.0150, device='cuda:0')
episode: 87 training return: tensor(256.3353, device='cuda:0')
epoch: 22 test_true_pfm: 3175.815049869265 sim_pfm: 245.4186608212864
episode: 88 training return: tensor(411.5596, device='cuda:0')
episode: 89 training return: tensor(204.5800, device='cuda:0')
episode: 90 training return: tensor(435.5444, device='cuda:0')
episode: 91 training return: tensor(394.4280, device='cuda:0')
epoch: 23 test_true_pfm: 3358.109788391585 sim_pfm: 85.52384933426704
episode: 92 training return: tensor(309.8059, device='cuda:0')
episode: 93 training return: tensor(192.4453, device='cuda:0')
episode: 94 training return: tensor(356.8205, device='cuda:0')
episode: 95 training return: tensor(357.9458, device='cuda:0')
epoch: 24 test_true_pfm: 3359.1623966671264 sim_pfm: 367.9077063561029
episode: 96 training return: tensor(378.2218, device='cuda:0')
episode: 97 training return: tensor(389.2875, device='cuda:0')
episode: 98 training return: tensor(351.3471, device='cuda:0')
episode: 99 training return: tensor(385.7737, device='cuda:0')
epoch: 25 test_true_pfm: 3385.8465516873935 sim_pfm: 363.860138777236
episode: 100 training return: tensor(387.5234, device='cuda:0')
episode: 101 training return: tensor(383.2359, device='cuda:0')
episode: 102 training return: tensor(57.8138, device='cuda:0')
episode: 103 training return: tensor(-51.9338, device='cuda:0')
epoch: 26 test_true_pfm: 3391.205680567941 sim_pfm: 435.06618529805564
episode: 104 training return: tensor(401.0728, device='cuda:0')
episode: 105 training return: tensor(435.5944, device='cuda:0')
episode: 106 training return: tensor(422.2573, device='cuda:0')
episode: 107 training return: tensor(357.5956, device='cuda:0')
epoch: 27 test_true_pfm: 3409.438519246169 sim_pfm: 408.2394205209469
episode: 108 training return: tensor(421.3570, device='cuda:0')
episode: 109 training return: tensor(-458.5539, device='cuda:0')
episode: 110 training return: tensor(402.5331, device='cuda:0')
episode: 111 training return: tensor(327.2453, device='cuda:0')
epoch: 28 test_true_pfm: 3401.3658311044037 sim_pfm: 389.5769700128585
episode: 112 training return: tensor(409.6353, device='cuda:0')
episode: 113 training return: tensor(403.0134, device='cuda:0')
episode: 114 training return: tensor(433.4636, device='cuda:0')
episode: 115 training return: tensor(388.1924, device='cuda:0')
epoch: 29 test_true_pfm: 3401.4314922578437 sim_pfm: 413.63733984037145
episode: 116 training return: tensor(418.7916, device='cuda:0')
episode: 117 training return: tensor(411.4086, device='cuda:0')
episode: 118 training return: tensor(461.4706, device='cuda:0')
episode: 119 training return: tensor(109.1930, device='cuda:0')
epoch: 30 test_true_pfm: 3492.188535830974 sim_pfm: 442.29462338836555
episode: 120 training return: tensor(387.8927, device='cuda:0')
episode: 121 training return: tensor(404.0449, device='cuda:0')
episode: 122 training return: tensor(425.6705, device='cuda:0')
episode: 123 training return: tensor(452.6411, device='cuda:0')
epoch: 31 test_true_pfm: 3436.710135833286 sim_pfm: 379.37202580824186
episode: 124 training return: tensor(411.7012, device='cuda:0')
episode: 125 training return: tensor(430.4429, device='cuda:0')
episode: 126 training return: tensor(405.3249, device='cuda:0')
episode: 127 training return: tensor(416.8134, device='cuda:0')
epoch: 32 test_true_pfm: 3406.6460905206186 sim_pfm: 452.6853202423469
episode: 128 training return: tensor(321.4222, device='cuda:0')
episode: 129 training return: tensor(411.8655, device='cuda:0')
episode: 130 training return: tensor(362.9757, device='cuda:0')
episode: 131 training return: tensor(403.8095, device='cuda:0')
epoch: 33 test_true_pfm: 3462.1631854396396 sim_pfm: 444.9129495295929
episode: 132 training return: tensor(413.4036, device='cuda:0')
episode: 133 training return: tensor(363.3628, device='cuda:0')
episode: 134 training return: tensor(503.8183, device='cuda:0')
episode: 135 training return: tensor(376.7112, device='cuda:0')
epoch: 34 test_true_pfm: 3424.0390213676487 sim_pfm: 443.3673514101053
episode: 136 training return: tensor(407.2838, device='cuda:0')
episode: 137 training return: tensor(313.7990, device='cuda:0')
episode: 138 training return: tensor(432.2163, device='cuda:0')
episode: 139 training return: tensor(428.6412, device='cuda:0')
epoch: 35 test_true_pfm: 3484.505709555248 sim_pfm: 467.13694058416877
episode: 140 training return: tensor(419.1978, device='cuda:0')
episode: 141 training return: tensor(370.0357, device='cuda:0')
episode: 142 training return: tensor(389.1431, device='cuda:0')
episode: 143 training return: tensor(407.1756, device='cuda:0')
epoch: 36 test_true_pfm: 3462.9887895483675 sim_pfm: 467.1442196873638
episode: 144 training return: tensor(432.0166, device='cuda:0')
episode: 145 training return: tensor(448.8038, device='cuda:0')
episode: 146 training return: tensor(469.3660, device='cuda:0')
episode: 147 training return: tensor(385.9910, device='cuda:0')
epoch: 37 test_true_pfm: 3433.467549354778 sim_pfm: 443.47076276260003
episode: 148 training return: tensor(425.4077, device='cuda:0')
episode: 149 training return: tensor(450.2124, device='cuda:0')
episode: 150 training return: tensor(387.6531, device='cuda:0')
episode: 151 training return: tensor(392.2820, device='cuda:0')
epoch: 38 test_true_pfm: 3407.4234115225336 sim_pfm: 436.0749516609164
episode: 152 training return: tensor(428.7595, device='cuda:0')
episode: 153 training return: tensor(329.9599, device='cuda:0')
episode: 154 training return: tensor(459.2325, device='cuda:0')
episode: 155 training return: tensor(398.2211, device='cuda:0')
epoch: 39 test_true_pfm: 3494.846097109788 sim_pfm: 458.39750664203893
episode: 156 training return: tensor(452.2835, device='cuda:0')
episode: 157 training return: tensor(432.3307, device='cuda:0')
episode: 158 training return: tensor(382.0044, device='cuda:0')
episode: 159 training return: tensor(-84.6855, device='cuda:0')
epoch: 40 test_true_pfm: 3386.8228448669215 sim_pfm: 415.1359794853682
episode: 160 training return: tensor(389.9356, device='cuda:0')
episode: 161 training return: tensor(459.4919, device='cuda:0')
episode: 162 training return: tensor(434.7375, device='cuda:0')
episode: 163 training return: tensor(415.6424, device='cuda:0')
epoch: 41 test_true_pfm: 3246.203604739076 sim_pfm: 449.8896608614984
episode: 164 training return: tensor(495.1277, device='cuda:0')
episode: 165 training return: tensor(466.9143, device='cuda:0')
episode: 166 training return: tensor(440.4886, device='cuda:0')
episode: 167 training return: tensor(405.9475, device='cuda:0')
epoch: 42 test_true_pfm: 3437.674548806417 sim_pfm: 420.8633147897199
episode: 168 training return: tensor(469.0623, device='cuda:0')
episode: 169 training return: tensor(474.2863, device='cuda:0')
episode: 170 training return: tensor(457.8069, device='cuda:0')
episode: 171 training return: tensor(354.8974, device='cuda:0')
epoch: 43 test_true_pfm: 3408.3417193363766 sim_pfm: 428.30185045831604
episode: 172 training return: tensor(438.7325, device='cuda:0')
episode: 173 training return: tensor(438.2743, device='cuda:0')
episode: 174 training return: tensor(58.8971, device='cuda:0')
episode: 175 training return: tensor(447.3651, device='cuda:0')
epoch: 44 test_true_pfm: 3431.5095776641197 sim_pfm: 439.0952130043491
episode: 176 training return: tensor(425.5320, device='cuda:0')
episode: 177 training return: tensor(406.6390, device='cuda:0')
episode: 178 training return: tensor(340.6386, device='cuda:0')
episode: 179 training return: tensor(428.4331, device='cuda:0')
epoch: 45 test_true_pfm: 3450.744335972128 sim_pfm: 405.6648004198602
episode: 180 training return: tensor(270.3256, device='cuda:0')
episode: 181 training return: tensor(440.8612, device='cuda:0')
episode: 182 training return: tensor(391.5973, device='cuda:0')
episode: 183 training return: tensor(245.1745, device='cuda:0')
epoch: 46 test_true_pfm: 3491.243379446428 sim_pfm: 420.1739495275736
episode: 184 training return: tensor(396.7631, device='cuda:0')
episode: 185 training return: tensor(475.3658, device='cuda:0')
episode: 186 training return: tensor(367.0646, device='cuda:0')
episode: 187 training return: tensor(373.7224, device='cuda:0')
epoch: 47 test_true_pfm: 3448.3963833159632 sim_pfm: 452.7522493151676
episode: 188 training return: tensor(437.3985, device='cuda:0')
episode: 189 training return: tensor(401.5635, device='cuda:0')
episode: 190 training return: tensor(461.5261, device='cuda:0')
episode: 191 training return: tensor(345.7229, device='cuda:0')
epoch: 48 test_true_pfm: 3397.5589228953686 sim_pfm: 427.29117725991335
episode: 192 training return: tensor(423.0631, device='cuda:0')
episode: 193 training return: tensor(382.7798, device='cuda:0')
episode: 194 training return: tensor(416.8356, device='cuda:0')
episode: 195 training return: tensor(424.2295, device='cuda:0')
epoch: 49 test_true_pfm: 3386.2803475240435 sim_pfm: 429.69595364958514
episode: 196 training return: tensor(428.3954, device='cuda:0')
episode: 197 training return: tensor(417.5428, device='cuda:0')
episode: 198 training return: tensor(373.9123, device='cuda:0')
episode: 199 training return: tensor(433.5211, device='cuda:0')
epoch: 50 test_true_pfm: 3478.1268841199158 sim_pfm: 419.67981888726354
episode: 200 training return: tensor(456.5269, device='cuda:0')
episode: 201 training return: tensor(431.7434, device='cuda:0')
episode: 202 training return: tensor(444.3590, device='cuda:0')
episode: 203 training return: tensor(405.0415, device='cuda:0')
epoch: 51 test_true_pfm: 3436.246683427334 sim_pfm: 425.8423388340743
episode: 204 training return: tensor(433.1635, device='cuda:0')
episode: 205 training return: tensor(454.0521, device='cuda:0')
episode: 206 training return: tensor(467.4257, device='cuda:0')
episode: 207 training return: tensor(388.4163, device='cuda:0')
epoch: 52 test_true_pfm: 3439.9943983122575 sim_pfm: 459.2921525690278
episode: 208 training return: tensor(448.8842, device='cuda:0')
episode: 209 training return: tensor(392.5933, device='cuda:0')
episode: 210 training return: tensor(436.5004, device='cuda:0')
episode: 211 training return: tensor(331.3385, device='cuda:0')
epoch: 53 test_true_pfm: 3308.2181622772664 sim_pfm: 441.6211284509627
episode: 212 training return: tensor(443.8919, device='cuda:0')
episode: 213 training return: tensor(460.7676, device='cuda:0')
episode: 214 training return: tensor(465.8495, device='cuda:0')
episode: 215 training return: tensor(333.8072, device='cuda:0')
epoch: 54 test_true_pfm: 3428.7521130950013 sim_pfm: 459.38638123177225
episode: 216 training return: tensor(332.5103, device='cuda:0')
episode: 217 training return: tensor(449.3315, device='cuda:0')
episode: 218 training return: tensor(426.3467, device='cuda:0')
episode: 219 training return: tensor(428.6541, device='cuda:0')
epoch: 55 test_true_pfm: 3429.4361653053897 sim_pfm: 383.15328606800176
episode: 220 training return: tensor(440.0578, device='cuda:0')
episode: 221 training return: tensor(413.1870, device='cuda:0')
episode: 222 training return: tensor(421.5993, device='cuda:0')
episode: 223 training return: tensor(448.6861, device='cuda:0')
epoch: 56 test_true_pfm: 3444.195339275286 sim_pfm: 456.93624523336376
episode: 224 training return: tensor(345.6336, device='cuda:0')
episode: 225 training return: tensor(442.0784, device='cuda:0')
episode: 226 training return: tensor(486.7294, device='cuda:0')
episode: 227 training return: tensor(412.0127, device='cuda:0')
epoch: 57 test_true_pfm: 3414.8036507321413 sim_pfm: 443.7934781780156
episode: 228 training return: tensor(461.8616, device='cuda:0')
episode: 229 training return: tensor(405.9223, device='cuda:0')
episode: 230 training return: tensor(474.6042, device='cuda:0')
episode: 231 training return: tensor(388.7465, device='cuda:0')
epoch: 58 test_true_pfm: 3386.337302129936 sim_pfm: 460.89661204861477
episode: 232 training return: tensor(379.3927, device='cuda:0')
episode: 233 training return: tensor(396.5729, device='cuda:0')
episode: 234 training return: tensor(453.3266, device='cuda:0')
episode: 235 training return: tensor(474.9973, device='cuda:0')
epoch: 59 test_true_pfm: 3438.3813843796265 sim_pfm: 468.9629240631475
episode: 236 training return: tensor(410.7930, device='cuda:0')
episode: 237 training return: tensor(471.3299, device='cuda:0')
episode: 238 training return: tensor(424.2151, device='cuda:0')
episode: 239 training return: tensor(312.1573, device='cuda:0')
epoch: 60 test_true_pfm: 3476.514495577971 sim_pfm: 450.0508116065951
episode: 240 training return: tensor(451.6219, device='cuda:0')
episode: 241 training return: tensor(396.4196, device='cuda:0')
episode: 242 training return: tensor(462.9424, device='cuda:0')
episode: 243 training return: tensor(448.1188, device='cuda:0')
epoch: 61 test_true_pfm: 3464.397517108568 sim_pfm: 464.6553968069493
episode: 244 training return: tensor(396.3051, device='cuda:0')
episode: 245 training return: tensor(379.6979, device='cuda:0')
episode: 246 training return: tensor(422.0553, device='cuda:0')
episode: 247 training return: tensor(425.7221, device='cuda:0')
epoch: 62 test_true_pfm: 3419.7158648428813 sim_pfm: 410.32575634559424
episode: 248 training return: tensor(359.9560, device='cuda:0')
episode: 249 training return: tensor(471.9837, device='cuda:0')
episode: 250 training return: tensor(443.4579, device='cuda:0')
episode: 251 training return: tensor(404.8193, device='cuda:0')
epoch: 63 test_true_pfm: 3411.5792550867504 sim_pfm: 477.0187663846106
episode: 252 training return: tensor(477.0421, device='cuda:0')
episode: 253 training return: tensor(456.2978, device='cuda:0')
episode: 254 training return: tensor(438.5993, device='cuda:0')
episode: 255 training return: tensor(257.4405, device='cuda:0')
epoch: 64 test_true_pfm: 3442.6355223329956 sim_pfm: 484.9734429998013
episode: 256 training return: tensor(418.3374, device='cuda:0')
episode: 257 training return: tensor(402.2748, device='cuda:0')
episode: 258 training return: tensor(413.9186, device='cuda:0')
episode: 259 training return: tensor(439.6492, device='cuda:0')
epoch: 65 test_true_pfm: 3476.617215166341 sim_pfm: 471.1554205301606
episode: 260 training return: tensor(424.2555, device='cuda:0')
episode: 261 training return: tensor(434.9624, device='cuda:0')
episode: 262 training return: tensor(472.2445, device='cuda:0')
episode: 263 training return: tensor(421.5166, device='cuda:0')
epoch: 66 test_true_pfm: 3222.3389070396065 sim_pfm: 428.98023781746934
episode: 264 training return: tensor(434.6490, device='cuda:0')
episode: 265 training return: tensor(418.5380, device='cuda:0')
episode: 266 training return: tensor(397.7824, device='cuda:0')
episode: 267 training return: tensor(398.1760, device='cuda:0')
epoch: 67 test_true_pfm: 3491.3528499557274 sim_pfm: 464.40353133300476
episode: 268 training return: tensor(412.6663, device='cuda:0')
episode: 269 training return: tensor(370.3177, device='cuda:0')
episode: 270 training return: tensor(404.1339, device='cuda:0')
episode: 271 training return: tensor(413.3348, device='cuda:0')
epoch: 68 test_true_pfm: 3434.26527359401 sim_pfm: 466.2531129290389
episode: 272 training return: tensor(465.9519, device='cuda:0')
episode: 273 training return: tensor(470.6529, device='cuda:0')
episode: 274 training return: tensor(441.0842, device='cuda:0')
episode: 275 training return: tensor(385.0158, device='cuda:0')
epoch: 69 test_true_pfm: 3456.372369743118 sim_pfm: 448.43021969407954
episode: 276 training return: tensor(428.3777, device='cuda:0')
episode: 277 training return: tensor(456.7063, device='cuda:0')
episode: 278 training return: tensor(428.0122, device='cuda:0')
episode: 279 training return: tensor(354.0429, device='cuda:0')
epoch: 70 test_true_pfm: 3462.8714873719305 sim_pfm: 473.1967605346969
episode: 280 training return: tensor(320.6466, device='cuda:0')
episode: 281 training return: tensor(420.8010, device='cuda:0')
episode: 282 training return: tensor(450.5076, device='cuda:0')
episode: 283 training return: tensor(403.4913, device='cuda:0')
epoch: 71 test_true_pfm: 3388.774031336287 sim_pfm: 461.02516492057475
episode: 284 training return: tensor(489.0056, device='cuda:0')
episode: 285 training return: tensor(446.6855, device='cuda:0')
episode: 286 training return: tensor(434.4580, device='cuda:0')
episode: 287 training return: tensor(395.8027, device='cuda:0')
epoch: 72 test_true_pfm: 3462.699843098612 sim_pfm: 436.59202008424717
episode: 288 training return: tensor(449.4810, device='cuda:0')
episode: 289 training return: tensor(418.7607, device='cuda:0')
episode: 290 training return: tensor(413.8901, device='cuda:0')
episode: 291 training return: tensor(473.2017, device='cuda:0')
epoch: 73 test_true_pfm: 3422.009517878376 sim_pfm: 440.46952350365854
episode: 292 training return: tensor(377.2875, device='cuda:0')
episode: 293 training return: tensor(398.8217, device='cuda:0')
episode: 294 training return: tensor(441.5459, device='cuda:0')
episode: 295 training return: tensor(436.0888, device='cuda:0')
epoch: 74 test_true_pfm: 3397.2386594137547 sim_pfm: 401.7010780887601
episode: 296 training return: tensor(379.7569, device='cuda:0')
episode: 297 training return: tensor(392.5730, device='cuda:0')
episode: 298 training return: tensor(439.2740, device='cuda:0')
episode: 299 training return: tensor(403.1603, device='cuda:0')
epoch: 75 test_true_pfm: 3487.8231391596964 sim_pfm: 468.1020320939327
episode: 300 training return: tensor(406.9447, device='cuda:0')
episode: 301 training return: tensor(436.1566, device='cuda:0')
episode: 302 training return: tensor(453.6364, device='cuda:0')
episode: 303 training return: tensor(245.1367, device='cuda:0')
epoch: 76 test_true_pfm: 3412.311645014408 sim_pfm: 475.5851475095163
episode: 304 training return: tensor(487.3164, device='cuda:0')
episode: 305 training return: tensor(389.4156, device='cuda:0')
episode: 306 training return: tensor(476.6835, device='cuda:0')
episode: 307 training return: tensor(400.7271, device='cuda:0')
epoch: 77 test_true_pfm: 3447.455472640678 sim_pfm: 480.11450238040806
episode: 308 training return: tensor(391.1052, device='cuda:0')
episode: 309 training return: tensor(426.3001, device='cuda:0')
episode: 310 training return: tensor(447.4426, device='cuda:0')
episode: 311 training return: tensor(432.5614, device='cuda:0')
epoch: 78 test_true_pfm: 3447.8415650844213 sim_pfm: 453.62335848847096
episode: 312 training return: tensor(459.3911, device='cuda:0')
episode: 313 training return: tensor(402.2685, device='cuda:0')
episode: 314 training return: tensor(444.2350, device='cuda:0')
episode: 315 training return: tensor(457.6172, device='cuda:0')
epoch: 79 test_true_pfm: 3459.657003483862 sim_pfm: 427.73027739459457
episode: 316 training return: tensor(430.9481, device='cuda:0')
episode: 317 training return: tensor(395.1397, device='cuda:0')
episode: 318 training return: tensor(435.2554, device='cuda:0')
episode: 319 training return: tensor(388.8672, device='cuda:0')
epoch: 80 test_true_pfm: 3495.4068108686283 sim_pfm: 450.31479272188153
episode: 320 training return: tensor(352.2374, device='cuda:0')
episode: 321 training return: tensor(462.6654, device='cuda:0')
episode: 322 training return: tensor(434.3347, device='cuda:0')
episode: 323 training return: tensor(364.2446, device='cuda:0')
epoch: 81 test_true_pfm: 3465.9504988328795 sim_pfm: 389.3963818657891
episode: 324 training return: tensor(420.2197, device='cuda:0')
episode: 325 training return: tensor(369.8265, device='cuda:0')
episode: 326 training return: tensor(448.2913, device='cuda:0')
episode: 327 training return: tensor(423.9838, device='cuda:0')
epoch: 82 test_true_pfm: 3447.82060784137 sim_pfm: 453.08273474511225
episode: 328 training return: tensor(245.6579, device='cuda:0')
episode: 329 training return: tensor(427.9210, device='cuda:0')
episode: 330 training return: tensor(410.2985, device='cuda:0')
episode: 331 training return: tensor(433.9474, device='cuda:0')
epoch: 83 test_true_pfm: 3400.83661772919 sim_pfm: 431.69180568524945
episode: 332 training return: tensor(391.4164, device='cuda:0')
episode: 333 training return: tensor(483.1224, device='cuda:0')
episode: 334 training return: tensor(438.6089, device='cuda:0')
episode: 335 training return: tensor(402.4055, device='cuda:0')
epoch: 84 test_true_pfm: 3493.016492079294 sim_pfm: 479.15736467509606
episode: 336 training return: tensor(455.4476, device='cuda:0')
episode: 337 training return: tensor(466.6044, device='cuda:0')
episode: 338 training return: tensor(446.3240, device='cuda:0')
episode: 339 training return: tensor(388.9775, device='cuda:0')
epoch: 85 test_true_pfm: 3484.6553011883734 sim_pfm: 426.0215195704756
episode: 340 training return: tensor(437.5595, device='cuda:0')
episode: 341 training return: tensor(375.5526, device='cuda:0')
episode: 342 training return: tensor(347.5098, device='cuda:0')
episode: 343 training return: tensor(429.5349, device='cuda:0')
epoch: 86 test_true_pfm: 3486.6634559622094 sim_pfm: 429.12081898911856
episode: 344 training return: tensor(147.9863, device='cuda:0')
episode: 345 training return: tensor(437.8286, device='cuda:0')
episode: 346 training return: tensor(435.2766, device='cuda:0')
episode: 347 training return: tensor(470.9714, device='cuda:0')
epoch: 87 test_true_pfm: 3484.2065315074856 sim_pfm: 456.77580963874544
episode: 348 training return: tensor(412.6801, device='cuda:0')
episode: 349 training return: tensor(401.3819, device='cuda:0')
episode: 350 training return: tensor(458.8149, device='cuda:0')
episode: 351 training return: tensor(433.8925, device='cuda:0')
epoch: 88 test_true_pfm: 3480.5039552635917 sim_pfm: 451.065753646583
episode: 352 training return: tensor(416.8318, device='cuda:0')
episode: 353 training return: tensor(430.8090, device='cuda:0')
episode: 354 training return: tensor(452.2173, device='cuda:0')
episode: 355 training return: tensor(466.8584, device='cuda:0')
epoch: 89 test_true_pfm: 3480.0165710754936 sim_pfm: 499.87320589332376
episode: 356 training return: tensor(429.9001, device='cuda:0')
episode: 357 training return: tensor(411.5725, device='cuda:0')
episode: 358 training return: tensor(463.6573, device='cuda:0')
episode: 359 training return: tensor(299.3508, device='cuda:0')
epoch: 90 test_true_pfm: 3444.348263296161 sim_pfm: 427.42263747530524
episode: 360 training return: tensor(423.7411, device='cuda:0')
episode: 361 training return: tensor(435.4520, device='cuda:0')
episode: 362 training return: tensor(462.2552, device='cuda:0')
episode: 363 training return: tensor(444.2911, device='cuda:0')
epoch: 91 test_true_pfm: 3451.1049479651697 sim_pfm: 418.0681773951219
episode: 364 training return: tensor(460.1979, device='cuda:0')
episode: 365 training return: tensor(406.8325, device='cuda:0')
episode: 366 training return: tensor(475.3610, device='cuda:0')
episode: 367 training return: tensor(478.8445, device='cuda:0')
epoch: 92 test_true_pfm: 3509.7686210284787 sim_pfm: 498.40175112870446
episode: 368 training return: tensor(407.2505, device='cuda:0')
episode: 369 training return: tensor(439.0694, device='cuda:0')
episode: 370 training return: tensor(280.0793, device='cuda:0')
episode: 371 training return: tensor(470.9525, device='cuda:0')
epoch: 93 test_true_pfm: 3445.2020399630146 sim_pfm: 454.4412555928381
episode: 372 training return: tensor(514.7572, device='cuda:0')
episode: 373 training return: tensor(414.9059, device='cuda:0')
episode: 374 training return: tensor(483.1937, device='cuda:0')
episode: 375 training return: tensor(419.2180, device='cuda:0')
epoch: 94 test_true_pfm: 3488.3471568290065 sim_pfm: 478.48138139267877
episode: 376 training return: tensor(211.4230, device='cuda:0')
episode: 377 training return: tensor(390.2846, device='cuda:0')
episode: 378 training return: tensor(466.6071, device='cuda:0')
episode: 379 training return: tensor(427.4296, device='cuda:0')
epoch: 95 test_true_pfm: 3482.1652527481087 sim_pfm: 467.7434223277184
episode: 380 training return: tensor(442.5187, device='cuda:0')
episode: 381 training return: tensor(386.4859, device='cuda:0')
episode: 382 training return: tensor(416.1854, device='cuda:0')
episode: 383 training return: tensor(175.6635, device='cuda:0')
epoch: 96 test_true_pfm: 3468.2179931664427 sim_pfm: 450.7257108912939
episode: 384 training return: tensor(472.2691, device='cuda:0')
episode: 385 training return: tensor(428.5749, device='cuda:0')
episode: 386 training return: tensor(433.2580, device='cuda:0')
episode: 387 training return: tensor(434.0818, device='cuda:0')
epoch: 97 test_true_pfm: 3474.48078059617 sim_pfm: 493.7675295114944
episode: 388 training return: tensor(411.1568, device='cuda:0')
episode: 389 training return: tensor(452.0911, device='cuda:0')
episode: 390 training return: tensor(417.6612, device='cuda:0')
episode: 391 training return: tensor(441.8144, device='cuda:0')
epoch: 98 test_true_pfm: 3470.0009153507744 sim_pfm: 471.40953516203444
episode: 392 training return: tensor(445.4518, device='cuda:0')
episode: 393 training return: tensor(471.9366, device='cuda:0')
episode: 394 training return: tensor(475.7716, device='cuda:0')
episode: 395 training return: tensor(451.5174, device='cuda:0')
epoch: 99 test_true_pfm: 3427.121860982855 sim_pfm: 460.5300876031882
episode: 396 training return: tensor(479.5079, device='cuda:0')
episode: 397 training return: tensor(447.8428, device='cuda:0')
episode: 398 training return: tensor(453.6866, device='cuda:0')
episode: 399 training return: tensor(433.7694, device='cuda:0')
epoch: 100 test_true_pfm: 3434.326820949591 sim_pfm: 434.2266064809907
episode: 400 training return: tensor(385.7440, device='cuda:0')
episode: 401 training return: tensor(484.0034, device='cuda:0')
episode: 402 training return: tensor(386.2272, device='cuda:0')
episode: 403 training return: tensor(439.7150, device='cuda:0')
epoch: 101 test_true_pfm: 3496.2115845196404 sim_pfm: 476.1500973881145
episode: 404 training return: tensor(503.0681, device='cuda:0')
episode: 405 training return: tensor(440.2074, device='cuda:0')
episode: 406 training return: tensor(338.9538, device='cuda:0')
episode: 407 training return: tensor(373.1597, device='cuda:0')
epoch: 102 test_true_pfm: 3397.5626319835105 sim_pfm: 460.82545362176216
episode: 408 training return: tensor(420.4702, device='cuda:0')
episode: 409 training return: tensor(426.7440, device='cuda:0')
episode: 410 training return: tensor(463.0998, device='cuda:0')
episode: 411 training return: tensor(393.7950, device='cuda:0')
epoch: 103 test_true_pfm: 3497.5225571933465 sim_pfm: 478.6361688369264
episode: 412 training return: tensor(389.7566, device='cuda:0')
episode: 413 training return: tensor(413.0003, device='cuda:0')
episode: 414 training return: tensor(409.8149, device='cuda:0')
episode: 415 training return: tensor(477.2815, device='cuda:0')
epoch: 104 test_true_pfm: 3477.0689082013055 sim_pfm: 486.24429021288717
episode: 416 training return: tensor(445.4413, device='cuda:0')
episode: 417 training return: tensor(457.5393, device='cuda:0')
episode: 418 training return: tensor(403.9725, device='cuda:0')
episode: 419 training return: tensor(442.4120, device='cuda:0')
epoch: 105 test_true_pfm: 3469.729187521671 sim_pfm: 468.74228748322156
episode: 420 training return: tensor(435.7069, device='cuda:0')
episode: 421 training return: tensor(238.1950, device='cuda:0')
episode: 422 training return: tensor(422.1959, device='cuda:0')
episode: 423 training return: tensor(447.5762, device='cuda:0')
epoch: 106 test_true_pfm: 3494.174767197264 sim_pfm: 463.73649447376374
episode: 424 training return: tensor(382.1429, device='cuda:0')
episode: 425 training return: tensor(401.1696, device='cuda:0')
episode: 426 training return: tensor(447.9059, device='cuda:0')
episode: 427 training return: tensor(458.2668, device='cuda:0')
epoch: 107 test_true_pfm: 3440.6107645303296 sim_pfm: 468.8020838540203
episode: 428 training return: tensor(453.3060, device='cuda:0')
episode: 429 training return: tensor(450.5195, device='cuda:0')
episode: 430 training return: tensor(428.5295, device='cuda:0')
episode: 431 training return: tensor(380.4046, device='cuda:0')
epoch: 108 test_true_pfm: 3463.612462845656 sim_pfm: 473.3152101173182
episode: 432 training return: tensor(441.7967, device='cuda:0')
episode: 433 training return: tensor(459.9088, device='cuda:0')
episode: 434 training return: tensor(423.1658, device='cuda:0')
episode: 435 training return: tensor(406.7528, device='cuda:0')
epoch: 109 test_true_pfm: 3517.7275648428677 sim_pfm: 441.6777278335455
episode: 436 training return: tensor(453.5778, device='cuda:0')
episode: 437 training return: tensor(462.9501, device='cuda:0')
episode: 438 training return: tensor(435.4221, device='cuda:0')
episode: 439 training return: tensor(472.9077, device='cuda:0')
epoch: 110 test_true_pfm: 3506.202425390637 sim_pfm: 441.18897681989864
episode: 440 training return: tensor(376.2193, device='cuda:0')
episode: 441 training return: tensor(402.0962, device='cuda:0')
episode: 442 training return: tensor(445.7305, device='cuda:0')
episode: 443 training return: tensor(501.2361, device='cuda:0')
epoch: 111 test_true_pfm: 3467.888765878403 sim_pfm: 474.956127752647
episode: 444 training return: tensor(434.4082, device='cuda:0')
episode: 445 training return: tensor(468.0212, device='cuda:0')
episode: 446 training return: tensor(488.0618, device='cuda:0')
episode: 447 training return: tensor(380.3996, device='cuda:0')
epoch: 112 test_true_pfm: 3502.7098489182804 sim_pfm: 470.5224744978671
episode: 448 training return: tensor(427.3730, device='cuda:0')
episode: 449 training return: tensor(525.8815, device='cuda:0')
episode: 450 training return: tensor(435.6163, device='cuda:0')
episode: 451 training return: tensor(446.0611, device='cuda:0')
epoch: 113 test_true_pfm: 3458.3111243256394 sim_pfm: 473.884020593289
episode: 452 training return: tensor(423.0114, device='cuda:0')
episode: 453 training return: tensor(431.9806, device='cuda:0')
episode: 454 training return: tensor(462.0467, device='cuda:0')
episode: 455 training return: tensor(473.5047, device='cuda:0')
epoch: 114 test_true_pfm: 3473.2421269508764 sim_pfm: 487.4137965264963
episode: 456 training return: tensor(470.5571, device='cuda:0')
episode: 457 training return: tensor(475.9734, device='cuda:0')
episode: 458 training return: tensor(480.1675, device='cuda:0')
episode: 459 training return: tensor(363.6388, device='cuda:0')
epoch: 115 test_true_pfm: 3430.7999701907825 sim_pfm: 476.6979900888594
episode: 460 training return: tensor(457.0956, device='cuda:0')
episode: 461 training return: tensor(456.1909, device='cuda:0')
episode: 462 training return: tensor(433.3365, device='cuda:0')
episode: 463 training return: tensor(489.3852, device='cuda:0')
epoch: 116 test_true_pfm: 3503.11468772754 sim_pfm: 445.9890738155227
episode: 464 training return: tensor(443.9997, device='cuda:0')
episode: 465 training return: tensor(453.8900, device='cuda:0')
episode: 466 training return: tensor(403.8138, device='cuda:0')
episode: 467 training return: tensor(471.1512, device='cuda:0')
epoch: 117 test_true_pfm: 3494.3488486660367 sim_pfm: 376.4133053628223
episode: 468 training return: tensor(494.0054, device='cuda:0')
episode: 469 training return: tensor(434.8248, device='cuda:0')
episode: 470 training return: tensor(451.6394, device='cuda:0')
episode: 471 training return: tensor(419.1767, device='cuda:0')
epoch: 118 test_true_pfm: 3462.9682049988965 sim_pfm: 445.2754155492876
episode: 472 training return: tensor(502.6298, device='cuda:0')
episode: 473 training return: tensor(452.3041, device='cuda:0')
episode: 474 training return: tensor(503.1021, device='cuda:0')
episode: 475 training return: tensor(479.2890, device='cuda:0')
epoch: 119 test_true_pfm: 3484.866382339985 sim_pfm: 465.1976005505615
episode: 476 training return: tensor(432.9066, device='cuda:0')
episode: 477 training return: tensor(417.0654, device='cuda:0')
episode: 478 training return: tensor(452.8721, device='cuda:0')
episode: 479 training return: tensor(451.9099, device='cuda:0')
epoch: 120 test_true_pfm: 3482.882552578307 sim_pfm: 487.26905442851904
episode: 480 training return: tensor(395.9606, device='cuda:0')
episode: 481 training return: tensor(448.1473, device='cuda:0')
episode: 482 training return: tensor(437.8018, device='cuda:0')
episode: 483 training return: tensor(396.1080, device='cuda:0')
epoch: 121 test_true_pfm: 3510.4858928706035 sim_pfm: 480.97799816883827
episode: 484 training return: tensor(466.7005, device='cuda:0')
episode: 485 training return: tensor(450.0540, device='cuda:0')
episode: 486 training return: tensor(464.0081, device='cuda:0')
episode: 487 training return: tensor(424.7307, device='cuda:0')
epoch: 122 test_true_pfm: 3519.2728404891004 sim_pfm: 468.82044467525947
episode: 488 training return: tensor(438.4030, device='cuda:0')
episode: 489 training return: tensor(440.3676, device='cuda:0')
episode: 490 training return: tensor(444.8496, device='cuda:0')
episode: 491 training return: tensor(482.4232, device='cuda:0')
epoch: 123 test_true_pfm: 3535.505727102404 sim_pfm: 500.85652650821913
episode: 492 training return: tensor(489.4128, device='cuda:0')
episode: 493 training return: tensor(504.8367, device='cuda:0')
episode: 494 training return: tensor(448.8902, device='cuda:0')
episode: 495 training return: tensor(480.6602, device='cuda:0')
epoch: 124 test_true_pfm: 3476.823775526396 sim_pfm: 491.385221281768
episode: 496 training return: tensor(399.2921, device='cuda:0')
episode: 497 training return: tensor(459.5933, device='cuda:0')
episode: 498 training return: tensor(451.7177, device='cuda:0')
episode: 499 training return: tensor(358.4968, device='cuda:0')
epoch: 125 test_true_pfm: 3491.5224156755953 sim_pfm: 479.189125399309
episode: 500 training return: tensor(437.7296, device='cuda:0')
episode: 501 training return: tensor(430.9304, device='cuda:0')
episode: 502 training return: tensor(395.3144, device='cuda:0')
episode: 503 training return: tensor(463.3450, device='cuda:0')
epoch: 126 test_true_pfm: 3463.1186225487713 sim_pfm: 471.080573788553
episode: 504 training return: tensor(471.2236, device='cuda:0')
episode: 505 training return: tensor(468.8733, device='cuda:0')
episode: 506 training return: tensor(463.2647, device='cuda:0')
episode: 507 training return: tensor(455.3297, device='cuda:0')
epoch: 127 test_true_pfm: 3498.6149011211187 sim_pfm: 489.66120020579547
episode: 508 training return: tensor(453.2466, device='cuda:0')
episode: 509 training return: tensor(435.2840, device='cuda:0')
episode: 510 training return: tensor(471.5073, device='cuda:0')
episode: 511 training return: tensor(434.2168, device='cuda:0')
epoch: 128 test_true_pfm: 3494.5343885743264 sim_pfm: 488.205211194756
episode: 512 training return: tensor(474.5985, device='cuda:0')
episode: 513 training return: tensor(478.5226, device='cuda:0')
episode: 514 training return: tensor(460.0281, device='cuda:0')
episode: 515 training return: tensor(481.8813, device='cuda:0')
epoch: 129 test_true_pfm: 3450.0793132640865 sim_pfm: 490.8813605089963
episode: 516 training return: tensor(474.3873, device='cuda:0')
episode: 517 training return: tensor(475.9561, device='cuda:0')
episode: 518 training return: tensor(230.4155, device='cuda:0')
episode: 519 training return: tensor(407.6150, device='cuda:0')
epoch: 130 test_true_pfm: 3499.406987956114 sim_pfm: 476.14024033669074
episode: 520 training return: tensor(398.7459, device='cuda:0')
episode: 521 training return: tensor(380.0130, device='cuda:0')
episode: 522 training return: tensor(517.3555, device='cuda:0')
episode: 523 training return: tensor(480.6109, device='cuda:0')
epoch: 131 test_true_pfm: 3481.3426060844995 sim_pfm: 491.45212464989163
episode: 524 training return: tensor(483.2496, device='cuda:0')
episode: 525 training return: tensor(343.8522, device='cuda:0')
episode: 526 training return: tensor(427.2195, device='cuda:0')
episode: 527 training return: tensor(468.0337, device='cuda:0')
epoch: 132 test_true_pfm: 3485.241230266636 sim_pfm: 470.73753987020854
episode: 528 training return: tensor(288.8847, device='cuda:0')
episode: 529 training return: tensor(482.1890, device='cuda:0')
episode: 530 training return: tensor(448.5822, device='cuda:0')
episode: 531 training return: tensor(378.6289, device='cuda:0')
epoch: 133 test_true_pfm: 3479.4566618134763 sim_pfm: 488.83877795003355
episode: 532 training return: tensor(457.3120, device='cuda:0')
episode: 533 training return: tensor(444.9486, device='cuda:0')
episode: 534 training return: tensor(434.4110, device='cuda:0')
episode: 535 training return: tensor(479.0570, device='cuda:0')
epoch: 134 test_true_pfm: 3459.5849846796445 sim_pfm: 485.1262781386807
episode: 536 training return: tensor(470.1433, device='cuda:0')
episode: 537 training return: tensor(446.8983, device='cuda:0')
episode: 538 training return: tensor(451.1610, device='cuda:0')
episode: 539 training return: tensor(402.7942, device='cuda:0')
epoch: 135 test_true_pfm: 3516.609127913638 sim_pfm: 469.6731715139176
episode: 540 training return: tensor(436.7576, device='cuda:0')
episode: 541 training return: tensor(440.3460, device='cuda:0')
episode: 542 training return: tensor(482.6760, device='cuda:0')
episode: 543 training return: tensor(471.5800, device='cuda:0')
epoch: 136 test_true_pfm: 3516.473575021038 sim_pfm: 484.46255460678367
episode: 544 training return: tensor(489.5078, device='cuda:0')
episode: 545 training return: tensor(489.0470, device='cuda:0')
episode: 546 training return: tensor(483.3827, device='cuda:0')
episode: 547 training return: tensor(468.6861, device='cuda:0')
epoch: 137 test_true_pfm: 3530.1635472332805 sim_pfm: 489.9193257438989
episode: 548 training return: tensor(476.8382, device='cuda:0')
episode: 549 training return: tensor(458.5139, device='cuda:0')
episode: 550 training return: tensor(460.8182, device='cuda:0')
episode: 551 training return: tensor(450.0566, device='cuda:0')
epoch: 138 test_true_pfm: 3445.0648922111327 sim_pfm: 472.7876080769929
episode: 552 training return: tensor(413.4448, device='cuda:0')
episode: 553 training return: tensor(441.6677, device='cuda:0')
episode: 554 training return: tensor(433.6935, device='cuda:0')
episode: 555 training return: tensor(420.3535, device='cuda:0')
epoch: 139 test_true_pfm: 3529.6475559014166 sim_pfm: 498.15351889420225
episode: 556 training return: tensor(379.1830, device='cuda:0')
episode: 557 training return: tensor(456.6678, device='cuda:0')
episode: 558 training return: tensor(424.0729, device='cuda:0')
episode: 559 training return: tensor(422.7919, device='cuda:0')
epoch: 140 test_true_pfm: 3490.3338227463114 sim_pfm: 457.5504823470449
episode: 560 training return: tensor(462.1809, device='cuda:0')
episode: 561 training return: tensor(420.6010, device='cuda:0')
episode: 562 training return: tensor(480.5926, device='cuda:0')
episode: 563 training return: tensor(486.3672, device='cuda:0')
epoch: 141 test_true_pfm: 3483.7373508307523 sim_pfm: 469.6201964565553
episode: 564 training return: tensor(517.4118, device='cuda:0')
episode: 565 training return: tensor(416.8207, device='cuda:0')
episode: 566 training return: tensor(442.0110, device='cuda:0')
episode: 567 training return: tensor(465.8854, device='cuda:0')
epoch: 142 test_true_pfm: 3506.3612495632515 sim_pfm: 495.03896767426824
episode: 568 training return: tensor(454.8893, device='cuda:0')
episode: 569 training return: tensor(471.0698, device='cuda:0')
episode: 570 training return: tensor(475.3094, device='cuda:0')
episode: 571 training return: tensor(443.6624, device='cuda:0')
epoch: 143 test_true_pfm: 3513.832886468122 sim_pfm: 497.99743645743
episode: 572 training return: tensor(486.3954, device='cuda:0')
episode: 573 training return: tensor(483.3611, device='cuda:0')
episode: 574 training return: tensor(491.3175, device='cuda:0')
episode: 575 training return: tensor(466.5477, device='cuda:0')
epoch: 144 test_true_pfm: 3494.799389871023 sim_pfm: 465.2233216462191
episode: 576 training return: tensor(440.5551, device='cuda:0')
episode: 577 training return: tensor(455.0659, device='cuda:0')
episode: 578 training return: tensor(425.1187, device='cuda:0')
episode: 579 training return: tensor(485.2864, device='cuda:0')
epoch: 145 test_true_pfm: 3526.7333275907617 sim_pfm: 495.5859513452451
episode: 580 training return: tensor(442.1594, device='cuda:0')
episode: 581 training return: tensor(466.1084, device='cuda:0')
episode: 582 training return: tensor(428.7545, device='cuda:0')
episode: 583 training return: tensor(481.0795, device='cuda:0')
epoch: 146 test_true_pfm: 3526.1392955092792 sim_pfm: 479.8106184945597
episode: 584 training return: tensor(459.7792, device='cuda:0')
episode: 585 training return: tensor(501.1964, device='cuda:0')
episode: 586 training return: tensor(423.6353, device='cuda:0')
episode: 587 training return: tensor(491.5036, device='cuda:0')
epoch: 147 test_true_pfm: 3490.793657368157 sim_pfm: 473.9053921054195
episode: 588 training return: tensor(420.0104, device='cuda:0')
episode: 589 training return: tensor(438.3334, device='cuda:0')
episode: 590 training return: tensor(380.3106, device='cuda:0')
episode: 591 training return: tensor(483.5103, device='cuda:0')
epoch: 148 test_true_pfm: 3507.2680178984756 sim_pfm: 482.21588363337406
episode: 592 training return: tensor(489.6095, device='cuda:0')
episode: 593 training return: tensor(442.8546, device='cuda:0')
episode: 594 training return: tensor(467.5231, device='cuda:0')
episode: 595 training return: tensor(468.5375, device='cuda:0')
epoch: 149 test_true_pfm: 3491.997757724308 sim_pfm: 494.1523425401053
episode: 596 training return: tensor(427.2995, device='cuda:0')
episode: 597 training return: tensor(549.5086, device='cuda:0')
episode: 598 training return: tensor(439.8902, device='cuda:0')
episode: 599 training return: tensor(464.7888, device='cuda:0')
epoch: 150 test_true_pfm: 3438.0005656552526 sim_pfm: 481.3265274656199
