['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'mixed', '--seed', '4', '--data', '100000']
epoch: 0 training_loss 0.2374754860252142 test_loss: 0.14535735845565795
epoch: 1 training_loss 0.1363300169631839 test_loss: 0.12263562679290771
epoch: 2 training_loss 0.13371157351881266 test_loss: 0.09095951914787292
epoch: 3 training_loss 0.10445829389616847 test_loss: 0.11368858814239502
epoch: 4 training_loss 0.11370771534740926 test_loss: 0.11922870874404908
epoch: 5 training_loss 0.10246644169092178 test_loss: 0.1086118459701538
epoch: 6 training_loss 0.11140607126057148 test_loss: 0.10120782852172852
epoch: 7 training_loss 0.09259449204429984 test_loss: 0.09503101110458374
epoch: 8 training_loss 0.10224764805287123 test_loss: 0.10988261699676513
epoch: 9 training_loss 0.10530881449580193 test_loss: 0.10413659811019897
epoch: 10 training_loss 0.09244134260341524 test_loss: 0.091841322183609
epoch: 11 training_loss 0.09421441629529 test_loss: 0.1068924069404602
epoch: 12 training_loss 0.09097804607823491 test_loss: 0.08569779992103577
epoch: 13 training_loss 0.08642197400331497 test_loss: 0.07678737640380859
epoch: 14 training_loss 0.089262878280133 test_loss: 0.07596352696418762
epoch: 15 training_loss 0.08759735343977809 test_loss: 0.09292492866516114
epoch: 16 training_loss 0.08722337810322642 test_loss: 0.09525445699691773
epoch: 17 training_loss 0.08662855768576265 test_loss: 0.08978675007820129
epoch: 18 training_loss 0.09083508534356952 test_loss: 0.08098152279853821
epoch: 19 training_loss 0.08653633838519453 test_loss: 0.09136226773262024
epoch: 20 training_loss 0.08917717583477497 test_loss: 0.1049993872642517
epoch: 21 training_loss 0.08827863838523627 test_loss: 0.08169724345207215
epoch: 22 training_loss 0.08855454966425896 test_loss: 0.08764885663986206
epoch: 23 training_loss 0.08538799831643701 test_loss: 0.08665528297424316
epoch: 24 training_loss 0.08651259323582053 test_loss: 0.08147813677787781
epoch: 25 training_loss 0.079400873798877 test_loss: 0.10221947431564331
epoch: 26 training_loss 0.09195553915575147 test_loss: 0.08208816051483155
epoch: 27 training_loss 0.08545645128935575 test_loss: 0.09711686968803405
epoch: 28 training_loss 0.08396351071074605 test_loss: 0.09513669610023498
epoch: 29 training_loss 0.08331936538219452 test_loss: 0.09243720769882202
epoch: 30 training_loss 0.08146688947454095 test_loss: 0.08551398515701295
epoch: 31 training_loss 0.08867980966344476 test_loss: 0.08106217980384826
epoch: 32 training_loss 0.08798385059460997 test_loss: 0.07653310894966125
epoch: 33 training_loss 0.08126731413416564 test_loss: 0.09663579463958741
epoch: 34 training_loss 0.08406446037814021 test_loss: 0.08611093759536743
epoch: 35 training_loss 0.08747286435216665 test_loss: 0.08632333278656006
epoch: 36 training_loss 0.08379824394360184 test_loss: 0.08687003850936889
epoch: 37 training_loss 0.08085892505012453 test_loss: 0.0796838104724884
epoch: 38 training_loss 0.07965532599017024 test_loss: 0.09023072719573974
epoch: 39 training_loss 0.07748784055933357 test_loss: 0.08986662030220031
epoch: 40 training_loss 0.08017926884815096 test_loss: 0.10450234413146972
epoch: 41 training_loss 0.08118293516337871 test_loss: 0.09278696775436401
epoch: 42 training_loss 0.0784169264510274 test_loss: 0.0957068681716919
epoch: 43 training_loss 0.08148395420983434 test_loss: 0.08504832983016967
epoch: 44 training_loss 0.08115841638296843 test_loss: 0.07756781578063965
epoch: 45 training_loss 0.07982221014797687 test_loss: 0.07562010288238526
epoch: 46 training_loss 0.07928776144981384 test_loss: 0.09375931024551391
epoch: 47 training_loss 0.08410572722554206 test_loss: 0.08128809332847595
epoch: 48 training_loss 0.08480293150991201 test_loss: 0.07374365329742431
epoch: 49 training_loss 0.07668716946616769 test_loss: 0.07721755504608155
epoch: 50 training_loss 0.08633451052010059 test_loss: 0.07963901162147521
epoch: 51 training_loss 0.07649489143863321 test_loss: 0.07606667280197144
epoch: 52 training_loss 0.07403345908969641 test_loss: 0.08479593992233277
epoch: 53 training_loss 0.07875568056479096 test_loss: 0.07092695236206055
epoch: 54 training_loss 0.07778512777760625 test_loss: 0.09514582753181458
epoch: 55 training_loss 0.09192058889195323 test_loss: 0.087640380859375
epoch: 56 training_loss 0.08403593379072845 test_loss: 0.0799221932888031
epoch: 57 training_loss 0.07849809525534511 test_loss: 0.07190138697624207
epoch: 58 training_loss 0.08188178619369864 test_loss: 0.07720631957054139
epoch: 59 training_loss 0.0708681520447135 test_loss: 0.07517927885055542
epoch: 60 training_loss 0.08358506208285689 test_loss: 0.0719946265220642
epoch: 61 training_loss 0.07669523272663355 test_loss: 0.08216084241867065
epoch: 62 training_loss 0.08132389416918158 test_loss: 0.0921256959438324
epoch: 63 training_loss 0.07495407483540475 test_loss: 0.0810667872428894
epoch: 64 training_loss 0.07853485252708196 test_loss: 0.08708171248435974
epoch: 65 training_loss 0.08226614227518439 test_loss: 0.07275629043579102
epoch: 66 training_loss 0.08316862588748336 test_loss: 0.07609713077545166
epoch: 67 training_loss 0.07645629433915019 test_loss: 0.07024329304695129
epoch: 68 training_loss 0.08061720921657979 test_loss: 0.070942622423172
epoch: 69 training_loss 0.08004606133326889 test_loss: 0.0925600528717041
epoch: 70 training_loss 0.08341292969882488 test_loss: 0.06844836473464966
epoch: 71 training_loss 0.0852080554701388 test_loss: 0.07989373803138733
epoch: 72 training_loss 0.08463583078235387 test_loss: 0.077877676486969
epoch: 73 training_loss 0.07747785702347755 test_loss: 0.09251071810722351
epoch: 74 training_loss 0.07687436489388347 test_loss: 0.07896711230278015
epoch: 75 training_loss 0.07299851229414343 test_loss: 0.08114826679229736
epoch: 76 training_loss 0.08452828889712691 test_loss: 0.07720466256141663
epoch: 77 training_loss 0.07722753427922725 test_loss: 0.07342683076858521
epoch: 78 training_loss 0.07545492238365113 test_loss: 0.07718786597251892
epoch: 79 training_loss 0.07982245435938239 test_loss: 0.08347280025482177
epoch: 80 training_loss 0.07010851236060262 test_loss: 0.06826067566871644
epoch: 81 training_loss 0.07205743294209242 test_loss: 0.06709468364715576
epoch: 82 training_loss 0.08026263242587447 test_loss: 0.06772258877754211
epoch: 83 training_loss 0.08165116507560015 test_loss: 0.09208288192749023
epoch: 84 training_loss 0.08017517562955617 test_loss: 0.06079326868057251
epoch: 85 training_loss 0.08099444841966033 test_loss: 0.07206069231033325
epoch: 86 training_loss 0.07440354701131582 test_loss: 0.1004603385925293
epoch: 87 training_loss 0.07829780319705605 test_loss: 0.0725085973739624
epoch: 88 training_loss 0.08595968967303634 test_loss: 0.08088624477386475
epoch: 89 training_loss 0.07755012704059482 test_loss: 0.08972411155700684
epoch: 90 training_loss 0.07775887657888234 test_loss: 0.08521768450737
epoch: 91 training_loss 0.07765207255259156 test_loss: 0.08213029503822326
epoch: 92 training_loss 0.08178388763219119 test_loss: 0.07290565371513366
epoch: 93 training_loss 0.07932566346600652 test_loss: 0.07554154396057129
epoch: 94 training_loss 0.07475518687628209 test_loss: 0.07947412133216858
epoch: 95 training_loss 0.07975399086251855 test_loss: 0.07671042084693909
epoch: 96 training_loss 0.0766049094311893 test_loss: 0.07837445139884949
epoch: 97 training_loss 0.07572968401014805 test_loss: 0.06695774793624878
epoch: 98 training_loss 0.08420264538377524 test_loss: 0.08432855010032654
epoch: 99 training_loss 0.0843543983437121 test_loss: 0.07214336991310119
epoch: 100 training_loss 0.07498634830117226 test_loss: 0.061205160617828366
epoch: 101 training_loss 0.0756662217155099 test_loss: 0.08301770091056823
epoch: 102 training_loss 0.07877330748364329 test_loss: 0.07748445272445678
epoch: 103 training_loss 0.07138766643591225 test_loss: 0.08227446675300598
epoch: 104 training_loss 0.07459393113851548 test_loss: 0.07311046719551087
epoch: 105 training_loss 0.08159397576004267 test_loss: 0.06937697529792786
epoch: 106 training_loss 0.08153044048696756 test_loss: 0.0637441098690033
epoch: 107 training_loss 0.07851155374199152 test_loss: 0.0810038685798645
epoch: 108 training_loss 0.07483764346688986 test_loss: 0.07976357936859131
epoch: 109 training_loss 0.07954504493623972 test_loss: 0.06932256221771241
epoch: 110 training_loss 0.08507035536691547 test_loss: 0.07405074238777161
epoch: 111 training_loss 0.07611410999670624 test_loss: 0.07109876871109008
epoch: 112 training_loss 0.07574738373979926 test_loss: 0.0680823028087616
epoch: 113 training_loss 0.0781811492331326 test_loss: 0.06503627896308899
epoch: 114 training_loss 0.08835225645452738 test_loss: 0.08282197117805482
epoch: 115 training_loss 0.07967400386929512 test_loss: 0.07359523773193359
epoch: 116 training_loss 0.07893553703092039 test_loss: 0.072537761926651
epoch: 117 training_loss 0.07951526845805347 test_loss: 0.07073702216148377
epoch: 118 training_loss 0.07629827169701457 test_loss: 0.08444324731826783
epoch: 119 training_loss 0.08022680588066577 test_loss: 0.09223726391792297
epoch: 120 training_loss 0.06478212302550673 test_loss: 0.07469123005867004
epoch: 121 training_loss 0.07550501519814133 test_loss: 0.09192740321159362
epoch: 122 training_loss 0.07212536113336682 test_loss: 0.06908524036407471
epoch: 123 training_loss 0.07795128505676985 test_loss: 0.062432289123535156
epoch: 124 training_loss 0.08238581533543765 test_loss: 0.08245654106140136
epoch: 125 training_loss 0.0761551017127931 test_loss: 0.07534599900245667
epoch: 126 training_loss 0.07743043070659042 test_loss: 0.08279502987861634
epoch: 127 training_loss 0.07730798313394188 test_loss: 0.08899319171905518
epoch: 128 training_loss 0.07750930728390813 test_loss: 0.06410669684410095
epoch: 129 training_loss 0.07863204693421721 test_loss: 0.0712369978427887
epoch: 130 training_loss 0.06997804364189505 test_loss: 0.08166503310203552
epoch: 131 training_loss 0.07415499900467694 test_loss: 0.09113794565200806
epoch: 132 training_loss 0.07834824284538627 test_loss: 0.07713744044303894
epoch: 133 training_loss 0.07618726039305329 test_loss: 0.08199735879898071
epoch: 134 training_loss 0.07197102019563317 test_loss: 0.07259944677352906
epoch: 135 training_loss 0.081977743441239 test_loss: 0.0811097800731659
epoch: 136 training_loss 0.08208170771598816 test_loss: 0.0695579469203949
epoch: 137 training_loss 0.07804765617474914 test_loss: 0.07969371676445007
epoch: 138 training_loss 0.06969917256385089 test_loss: 0.07228707671165466
epoch: 139 training_loss 0.07567466769367456 test_loss: 0.06904941201210021
epoch: 140 training_loss 0.07524400346912444 test_loss: 0.08391327261924744
epoch: 141 training_loss 0.07192028809338807 test_loss: 0.09088279604911804
epoch: 142 training_loss 0.0762252165004611 test_loss: 0.07054795026779175
epoch: 143 training_loss 0.0804986225720495 test_loss: 0.08189520835876465
epoch: 144 training_loss 0.07766816396266223 test_loss: 0.06517603993415833
epoch: 145 training_loss 0.07578173778019845 test_loss: 0.08787154555320739
epoch: 146 training_loss 0.07726101661100984 test_loss: 0.0666281521320343
epoch: 147 training_loss 0.0757449490018189 test_loss: 0.08447136878967285
epoch: 148 training_loss 0.0809969989489764 test_loss: 0.07839317917823792
epoch: 149 training_loss 0.07482517579570412 test_loss: 0.07974056005477906
epoch: 0 training_loss 40.24797966003418 test_loss: 21.73839569091797
epoch: 1 training_loss 17.16209114074707 test_loss: 14.239886474609374
epoch: 2 training_loss 12.90699670791626 test_loss: 12.020570373535156
epoch: 3 training_loss 10.771870322227478 test_loss: 9.865436553955078
epoch: 4 training_loss 9.496565175056457 test_loss: 9.08857421875
epoch: 5 training_loss 8.792236914634705 test_loss: 8.447979736328126
epoch: 6 training_loss 8.00210144996643 test_loss: 7.969931030273438
epoch: 7 training_loss 7.412527093887329 test_loss: 7.261852264404297
epoch: 8 training_loss 7.09220588684082 test_loss: 7.040596771240234
epoch: 9 training_loss 6.637030873298645 test_loss: 6.960215759277344
epoch: 10 training_loss 6.497340788841248 test_loss: 5.949263000488282
epoch: 11 training_loss 6.1754169845581055 test_loss: 6.186021423339843
epoch: 12 training_loss 6.036592922210693 test_loss: 5.921976470947266
epoch: 13 training_loss 5.722513289451599 test_loss: 5.600149154663086
epoch: 14 training_loss 5.526681823730469 test_loss: 5.654241561889648
epoch: 15 training_loss 5.534580698013306 test_loss: 5.323147964477539
epoch: 16 training_loss 5.285329418182373 test_loss: 4.929774475097656
epoch: 17 training_loss 5.125404276847839 test_loss: 5.177946853637695
epoch: 18 training_loss 5.04219199180603 test_loss: 5.129234695434571
epoch: 19 training_loss 4.855451321601867 test_loss: 5.091811752319336
epoch: 20 training_loss 4.784475843906403 test_loss: 4.928619384765625
epoch: 21 training_loss 4.713875479698181 test_loss: 4.507967758178711
epoch: 22 training_loss 4.700987713336945 test_loss: 4.590141677856446
epoch: 23 training_loss 4.598932416439056 test_loss: 4.468064498901367
epoch: 24 training_loss 4.461123189926147 test_loss: 4.692100143432617
epoch: 25 training_loss 4.476400513648986 test_loss: 4.3396240234375
epoch: 26 training_loss 4.338940546512604 test_loss: 4.17907943725586
epoch: 27 training_loss 4.273161368370056 test_loss: 4.530765533447266
epoch: 28 training_loss 4.290044469833374 test_loss: 4.31860122680664
epoch: 29 training_loss 4.103798336982727 test_loss: 4.037936782836914
epoch: 30 training_loss 4.079820439815522 test_loss: 4.220784378051758
epoch: 31 training_loss 4.011220898628235 test_loss: 3.906721496582031
epoch: 32 training_loss 4.054614703655243 test_loss: 4.0602153778076175
epoch: 33 training_loss 3.941804537773132 test_loss: 3.8782470703125
epoch: 34 training_loss 3.984754900932312 test_loss: 3.8786865234375
epoch: 35 training_loss 3.844315412044525 test_loss: 3.9196235656738283
epoch: 36 training_loss 3.8947659707069398 test_loss: 3.6601207733154295
epoch: 37 training_loss 3.85264200925827 test_loss: 3.741265869140625
epoch: 38 training_loss 3.7631726455688477 test_loss: 3.765224075317383
epoch: 39 training_loss 3.727815365791321 test_loss: 3.6675357818603516
epoch: 40 training_loss 3.6927997970581057 test_loss: 3.5690589904785157
epoch: 41 training_loss 3.64502466917038 test_loss: 3.7783782958984373
epoch: 42 training_loss 3.640878155231476 test_loss: 3.5383533477783202
epoch: 43 training_loss 3.6191960692405702 test_loss: 3.3660694122314454
epoch: 44 training_loss 3.5935088396072388 test_loss: 3.4779529571533203
epoch: 45 training_loss 3.566142885684967 test_loss: 3.3872196197509767
epoch: 46 training_loss 3.4966218662261963 test_loss: 3.6355205535888673
epoch: 47 training_loss 3.4291161489486695 test_loss: 3.4615104675292967
epoch: 48 training_loss 3.483374297618866 test_loss: 3.6999916076660155
epoch: 49 training_loss 3.324677290916443 test_loss: 3.489480972290039
epoch: 50 training_loss 3.4039563393592833 test_loss: 3.480052185058594
epoch: 51 training_loss 3.283533775806427 test_loss: 3.314793014526367
epoch: 52 training_loss 3.3511594700813294 test_loss: 3.3932071685791017
epoch: 53 training_loss 3.2282244205474853 test_loss: 3.265725326538086
epoch: 54 training_loss 3.283232772350311 test_loss: 3.371246337890625
epoch: 55 training_loss 3.287591497898102 test_loss: 3.255657958984375
epoch: 56 training_loss 3.335921685695648 test_loss: 3.1063678741455076
epoch: 57 training_loss 3.2283955693244932 test_loss: 3.5013885498046875
epoch: 58 training_loss 3.2468787121772764 test_loss: 3.286691665649414
epoch: 59 training_loss 3.2187411856651305 test_loss: 3.316495895385742
epoch: 60 training_loss 3.142414026260376 test_loss: 3.1559045791625975
epoch: 61 training_loss 3.1778393816947936 test_loss: 3.261666107177734
epoch: 62 training_loss 3.1262345361709594 test_loss: 3.235438919067383
epoch: 63 training_loss 3.081395275592804 test_loss: 3.219875717163086
epoch: 64 training_loss 3.0887165594100954 test_loss: 3.0166385650634764
epoch: 65 training_loss 3.118910596370697 test_loss: 3.1123266220092773
epoch: 66 training_loss 3.038240554332733 test_loss: 3.1419937133789064
epoch: 67 training_loss 3.060749945640564 test_loss: 3.0869623184204102
epoch: 68 training_loss 3.0053912234306335 test_loss: 3.0534820556640625
epoch: 69 training_loss 3.0466186571121217 test_loss: 2.9514835357666014
epoch: 70 training_loss 2.950742757320404 test_loss: 3.0548833847045898
epoch: 71 training_loss 3.0918609929084777 test_loss: 3.1881841659545898
epoch: 72 training_loss 3.018112199306488 test_loss: 3.011615753173828
epoch: 73 training_loss 2.9677039766311646 test_loss: 3.045062255859375
epoch: 74 training_loss 2.980729994773865 test_loss: 3.0480672836303713
epoch: 75 training_loss 2.9533368158340454 test_loss: 2.86797981262207
epoch: 76 training_loss 2.8839374876022337 test_loss: 3.0727279663085936
epoch: 77 training_loss 3.044089422225952 test_loss: 2.8632200241088865
epoch: 78 training_loss 2.88252925157547 test_loss: 2.994695854187012
epoch: 79 training_loss 2.920037431716919 test_loss: 2.8044578552246096
epoch: 80 training_loss 2.8996116948127746 test_loss: 2.9500247955322267
epoch: 81 training_loss 2.8579629468917847 test_loss: 3.034238815307617
epoch: 82 training_loss 2.8648894453048706 test_loss: 2.7068918228149412
epoch: 83 training_loss 2.825188068151474 test_loss: 2.8387628555297852
epoch: 84 training_loss 2.827272093296051 test_loss: 2.8175485610961912
epoch: 85 training_loss 2.818843116760254 test_loss: 2.8610361099243162
epoch: 86 training_loss 2.851636917591095 test_loss: 2.8003381729125976
epoch: 87 training_loss 2.8548532509803772 test_loss: 3.0116649627685548
epoch: 88 training_loss 2.9059308052062987 test_loss: 2.8189418792724608
epoch: 89 training_loss 2.7362100148200987 test_loss: 3.025956726074219
epoch: 90 training_loss 2.801470739841461 test_loss: 2.9236888885498047
epoch: 91 training_loss 2.8424132466316223 test_loss: 2.6498157501220705
epoch: 92 training_loss 2.7131853318214416 test_loss: 2.849307060241699
epoch: 93 training_loss 2.7518294072151184 test_loss: 2.8340221405029298
epoch: 94 training_loss 2.778802659511566 test_loss: 2.6931997299194337
epoch: 95 training_loss 2.706499536037445 test_loss: 2.6714555740356447
epoch: 96 training_loss 2.7333319318294524 test_loss: 2.780336380004883
epoch: 97 training_loss 2.7567069578170775 test_loss: 2.8390899658203126
epoch: 98 training_loss 2.678791581392288 test_loss: 2.933406448364258
epoch: 99 training_loss 2.734768047332764 test_loss: 2.7620702743530274
epoch: 100 training_loss 2.686224572658539 test_loss: 2.7119884490966797
epoch: 101 training_loss 2.667809990644455 test_loss: 2.690755081176758
epoch: 102 training_loss 2.6879621613025666 test_loss: 2.851116180419922
epoch: 103 training_loss 2.642017126083374 test_loss: 2.647997283935547
epoch: 104 training_loss 2.670461949110031 test_loss: 2.68360595703125
epoch: 105 training_loss 2.595423730611801 test_loss: 2.616294097900391
epoch: 106 training_loss 2.6283196532726287 test_loss: 2.6443851470947264
epoch: 107 training_loss 2.5835397338867185 test_loss: 2.6499460220336912
epoch: 108 training_loss 2.632966537475586 test_loss: 2.6787269592285154
epoch: 109 training_loss 2.6106341660022734 test_loss: 2.574276161193848
epoch: 110 training_loss 2.6428141927719118 test_loss: 2.5796792984008787
epoch: 111 training_loss 2.6190694296360015 test_loss: 2.684163475036621
epoch: 112 training_loss 2.611681126356125 test_loss: 2.7789480209350588
epoch: 113 training_loss 2.637929902076721 test_loss: 2.543750190734863
epoch: 114 training_loss 2.639557602405548 test_loss: 2.835788917541504
epoch: 115 training_loss 2.6266282200813293 test_loss: 2.571142387390137
epoch: 116 training_loss 2.6295155334472655 test_loss: 2.6766407012939455
epoch: 117 training_loss 2.58759504199028 test_loss: 2.5296747207641603
epoch: 118 training_loss 2.617147020101547 test_loss: 2.540213203430176
epoch: 119 training_loss 2.536884970664978 test_loss: 2.7166147232055664
epoch: 120 training_loss 2.557432086467743 test_loss: 2.716506004333496
epoch: 121 training_loss 2.5782468724250793 test_loss: 2.6068639755249023
epoch: 122 training_loss 2.5779086780548095 test_loss: 2.4099637985229494
epoch: 123 training_loss 2.5166399264335633 test_loss: 2.5345029830932617
epoch: 124 training_loss 2.525758501291275 test_loss: 2.5637807846069336
epoch: 125 training_loss 2.582931720018387 test_loss: 2.524647903442383
epoch: 126 training_loss 2.521855208873749 test_loss: 2.4806798934936523
epoch: 127 training_loss 2.538786104917526 test_loss: 2.578965187072754
epoch: 128 training_loss 2.5036426293849945 test_loss: 2.550024223327637
epoch: 129 training_loss 2.496111654043198 test_loss: 2.4804203033447267
epoch: 130 training_loss 2.5428926444053648 test_loss: 2.4767112731933594
epoch: 131 training_loss 2.596953572034836 test_loss: 2.6324092864990236
epoch: 132 training_loss 2.5164986944198606 test_loss: 2.5455581665039064
epoch: 133 training_loss 2.5161848783493044 test_loss: 2.551011085510254
epoch: 134 training_loss 2.5315817534923553 test_loss: 2.5578447341918946
epoch: 135 training_loss 2.508664934635162 test_loss: 2.5121078491210938
epoch: 136 training_loss 2.4991670179367067 test_loss: 2.580506706237793
epoch: 137 training_loss 2.4605693006515503 test_loss: 2.4115812301635744
epoch: 138 training_loss 2.426997421979904 test_loss: 2.4370855331420898
epoch: 139 training_loss 2.402859944105148 test_loss: 2.4661228179931642
epoch: 140 training_loss 2.4276889038085936 test_loss: 2.5417303085327148
epoch: 141 training_loss 2.443015090227127 test_loss: 2.4678718566894533
epoch: 142 training_loss 2.481107977628708 test_loss: 2.4944305419921875
epoch: 143 training_loss 2.470204038619995 test_loss: 2.5288717269897463
epoch: 144 training_loss 2.447988623380661 test_loss: 2.4295812606811524
epoch: 145 training_loss 2.438766839504242 test_loss: 2.4874143600463867
epoch: 146 training_loss 2.3877587497234343 test_loss: 2.3958492279052734
epoch: 147 training_loss 2.405363118648529 test_loss: 2.375309181213379
epoch: 148 training_loss 2.3794283485412597 test_loss: 2.293609046936035
epoch: 149 training_loss 2.398130546808243 test_loss: 2.3460575103759767
3732.2437732442254
episode: 0 training return: tensor(129.9012, device='cuda:0')
episode: 1 training return: tensor(62.5106, device='cuda:0')
episode: 2 training return: tensor(272.5179, device='cuda:0')
episode: 3 training return: tensor(66.7349, device='cuda:0')
epoch: 1 test_true_pfm: 3552.107958984811 sim_pfm: 195.41416291512238
episode: 4 training return: tensor(101.4974, device='cuda:0')
episode: 5 training return: tensor(226.5134, device='cuda:0')
episode: 6 training return: tensor(303.0658, device='cuda:0')
episode: 7 training return: tensor(185.3463, device='cuda:0')
epoch: 2 test_true_pfm: 3741.6474816060254 sim_pfm: 241.5663191182733
episode: 8 training return: tensor(96.6244, device='cuda:0')
episode: 9 training return: tensor(264.1917, device='cuda:0')
episode: 10 training return: tensor(173.1270, device='cuda:0')
episode: 11 training return: tensor(280.8596, device='cuda:0')
epoch: 3 test_true_pfm: 3747.0332287190845 sim_pfm: 274.3761860278416
episode: 12 training return: tensor(176.3184, device='cuda:0')
episode: 13 training return: tensor(159.0358, device='cuda:0')
episode: 14 training return: tensor(0.0898, device='cuda:0')
episode: 15 training return: tensor(-731.4171, device='cuda:0')
epoch: 4 test_true_pfm: 3734.6274036804266 sim_pfm: 187.36471535265446
episode: 16 training return: tensor(268.2009, device='cuda:0')
episode: 17 training return: tensor(325.2835, device='cuda:0')
episode: 18 training return: tensor(13.6712, device='cuda:0')
episode: 19 training return: tensor(344.6390, device='cuda:0')
epoch: 5 test_true_pfm: 3698.3939901424856 sim_pfm: 113.60627106280299
episode: 20 training return: tensor(275.0549, device='cuda:0')
episode: 21 training return: tensor(194.7487, device='cuda:0')
episode: 22 training return: tensor(215.2612, device='cuda:0')
episode: 23 training return: tensor(243.5623, device='cuda:0')
epoch: 6 test_true_pfm: 3706.126806489463 sim_pfm: 139.10176195480744
episode: 24 training return: tensor(212.9622, device='cuda:0')
episode: 25 training return: tensor(115.4599, device='cuda:0')
episode: 26 training return: tensor(162.3319, device='cuda:0')
episode: 27 training return: tensor(337.0205, device='cuda:0')
epoch: 7 test_true_pfm: 3802.820939068643 sim_pfm: 269.4252412578401
episode: 28 training return: tensor(361.7339, device='cuda:0')
episode: 29 training return: tensor(329.3163, device='cuda:0')
episode: 30 training return: tensor(88.5332, device='cuda:0')
episode: 31 training return: tensor(-6.3388, device='cuda:0')
epoch: 8 test_true_pfm: 3839.3079869068183 sim_pfm: 399.7702425531655
episode: 32 training return: tensor(203.6638, device='cuda:0')
episode: 33 training return: tensor(373.9547, device='cuda:0')
episode: 34 training return: tensor(108.6336, device='cuda:0')
episode: 35 training return: tensor(202.7641, device='cuda:0')
epoch: 9 test_true_pfm: 3981.3438962390496 sim_pfm: 235.8691294323653
episode: 36 training return: tensor(211.7061, device='cuda:0')
episode: 37 training return: tensor(310.8517, device='cuda:0')
episode: 38 training return: tensor(383.8594, device='cuda:0')
episode: 39 training return: tensor(163.7855, device='cuda:0')
epoch: 10 test_true_pfm: 3930.416799506926 sim_pfm: 225.76958601700608
episode: 40 training return: tensor(246.6667, device='cuda:0')
episode: 41 training return: tensor(324.3073, device='cuda:0')
episode: 42 training return: tensor(217.3229, device='cuda:0')
episode: 43 training return: tensor(365.0287, device='cuda:0')
epoch: 11 test_true_pfm: 3897.6503863596718 sim_pfm: 373.8211981723628
episode: 44 training return: tensor(332.6570, device='cuda:0')
episode: 45 training return: tensor(338.8430, device='cuda:0')
episode: 46 training return: tensor(380.2616, device='cuda:0')
episode: 47 training return: tensor(281.8801, device='cuda:0')
epoch: 12 test_true_pfm: 3919.0761060921454 sim_pfm: 180.94632571551483
episode: 48 training return: tensor(403.4965, device='cuda:0')
episode: 49 training return: tensor(341.5191, device='cuda:0')
episode: 50 training return: tensor(139.8504, device='cuda:0')
episode: 51 training return: tensor(170.1213, device='cuda:0')
epoch: 13 test_true_pfm: 3974.577704120637 sim_pfm: 292.0630605797148
episode: 52 training return: tensor(323.3934, device='cuda:0')
episode: 53 training return: tensor(377.1108, device='cuda:0')
episode: 54 training return: tensor(143.9537, device='cuda:0')
episode: 55 training return: tensor(370.2418, device='cuda:0')
epoch: 14 test_true_pfm: 3997.3773339573527 sim_pfm: 339.12131864236045
episode: 56 training return: tensor(301.5233, device='cuda:0')
episode: 57 training return: tensor(268.1261, device='cuda:0')
episode: 58 training return: tensor(138.1612, device='cuda:0')
episode: 59 training return: tensor(70.6077, device='cuda:0')
epoch: 15 test_true_pfm: 3982.522317396435 sim_pfm: 394.09429321135394
episode: 60 training return: tensor(357.4561, device='cuda:0')
episode: 61 training return: tensor(290.7751, device='cuda:0')
episode: 62 training return: tensor(402.2221, device='cuda:0')
episode: 63 training return: tensor(185.2917, device='cuda:0')
epoch: 16 test_true_pfm: 3992.706000117754 sim_pfm: 351.4715937061313
episode: 64 training return: tensor(225.9822, device='cuda:0')
episode: 65 training return: tensor(206.0502, device='cuda:0')
episode: 66 training return: tensor(340.4125, device='cuda:0')
episode: 67 training return: tensor(-508.9178, device='cuda:0')
epoch: 17 test_true_pfm: 3686.979947598628 sim_pfm: 332.0691596047157
episode: 68 training return: tensor(348.4872, device='cuda:0')
episode: 69 training return: tensor(149.8909, device='cuda:0')
episode: 70 training return: tensor(176.8257, device='cuda:0')
episode: 71 training return: tensor(248.5538, device='cuda:0')
epoch: 18 test_true_pfm: 3999.666090770157 sim_pfm: 340.1249714951264
episode: 72 training return: tensor(230.6245, device='cuda:0')
episode: 73 training return: tensor(276.7549, device='cuda:0')
episode: 74 training return: tensor(295.4510, device='cuda:0')
episode: 75 training return: tensor(140.7317, device='cuda:0')
epoch: 19 test_true_pfm: 3846.3383353478844 sim_pfm: 309.7765422320711
episode: 76 training return: tensor(-634.9119, device='cuda:0')
episode: 77 training return: tensor(204.6202, device='cuda:0')
episode: 78 training return: tensor(279.2485, device='cuda:0')
episode: 79 training return: tensor(251.0564, device='cuda:0')
epoch: 20 test_true_pfm: 3914.8146015411016 sim_pfm: 321.89320657250937
episode: 80 training return: tensor(16.2924, device='cuda:0')
episode: 81 training return: tensor(385.5387, device='cuda:0')
episode: 82 training return: tensor(389.2118, device='cuda:0')
episode: 83 training return: tensor(207.6990, device='cuda:0')
epoch: 21 test_true_pfm: 3893.135612419353 sim_pfm: 313.88355221490684
episode: 84 training return: tensor(115.4688, device='cuda:0')
episode: 85 training return: tensor(202.2894, device='cuda:0')
episode: 86 training return: tensor(343.4503, device='cuda:0')
episode: 87 training return: tensor(115.5230, device='cuda:0')
epoch: 22 test_true_pfm: 3923.0999313457796 sim_pfm: 269.6016302378072
episode: 88 training return: tensor(372.7088, device='cuda:0')
episode: 89 training return: tensor(144.1240, device='cuda:0')
episode: 90 training return: tensor(275.4729, device='cuda:0')
episode: 91 training return: tensor(363.4698, device='cuda:0')
epoch: 23 test_true_pfm: 3969.714648640493 sim_pfm: 360.0079394914986
episode: 92 training return: tensor(173.0895, device='cuda:0')
episode: 93 training return: tensor(96.2946, device='cuda:0')
episode: 94 training return: tensor(8.3307, device='cuda:0')
episode: 95 training return: tensor(293.6512, device='cuda:0')
epoch: 24 test_true_pfm: 3781.459985323169 sim_pfm: 321.143251280572
episode: 96 training return: tensor(342.3180, device='cuda:0')
episode: 97 training return: tensor(215.0173, device='cuda:0')
episode: 98 training return: tensor(122.7662, device='cuda:0')
episode: 99 training return: tensor(167.0985, device='cuda:0')
epoch: 25 test_true_pfm: 2820.0399230385033 sim_pfm: 316.5503867152535
episode: 100 training return: tensor(211.9131, device='cuda:0')
episode: 101 training return: tensor(196.7225, device='cuda:0')
episode: 102 training return: tensor(333.2274, device='cuda:0')
episode: 103 training return: tensor(347.0691, device='cuda:0')
epoch: 26 test_true_pfm: 3978.4084541279894 sim_pfm: 280.36002813781187
episode: 104 training return: tensor(347.1306, device='cuda:0')
episode: 105 training return: tensor(236.9839, device='cuda:0')
episode: 106 training return: tensor(387.9642, device='cuda:0')
episode: 107 training return: tensor(142.4557, device='cuda:0')
epoch: 27 test_true_pfm: 3878.5257192067947 sim_pfm: 322.512910591516
episode: 108 training return: tensor(-650.2116, device='cuda:0')
episode: 109 training return: tensor(284.5761, device='cuda:0')
episode: 110 training return: tensor(158.8678, device='cuda:0')
episode: 111 training return: tensor(378.1295, device='cuda:0')
epoch: 28 test_true_pfm: 3880.8923225466883 sim_pfm: 227.75394381413935
episode: 112 training return: tensor(373.9227, device='cuda:0')
episode: 113 training return: tensor(215.4573, device='cuda:0')
episode: 114 training return: tensor(307.6852, device='cuda:0')
episode: 115 training return: tensor(246.5675, device='cuda:0')
epoch: 29 test_true_pfm: 3902.1224980973016 sim_pfm: 376.83457155172556
episode: 116 training return: tensor(164.0884, device='cuda:0')
episode: 117 training return: tensor(200.7657, device='cuda:0')
episode: 118 training return: tensor(300.4805, device='cuda:0')
episode: 119 training return: tensor(-821.8978, device='cuda:0')
epoch: 30 test_true_pfm: 3781.8001212892377 sim_pfm: 246.72920969843594
episode: 120 training return: tensor(175.6058, device='cuda:0')
episode: 121 training return: tensor(385.9909, device='cuda:0')
episode: 122 training return: tensor(373.2723, device='cuda:0')
episode: 123 training return: tensor(167.6345, device='cuda:0')
epoch: 31 test_true_pfm: 3994.5930865099413 sim_pfm: 313.6000816638698
episode: 124 training return: tensor(145.5208, device='cuda:0')
episode: 125 training return: tensor(272.6115, device='cuda:0')
episode: 126 training return: tensor(159.9771, device='cuda:0')
episode: 127 training return: tensor(168.2214, device='cuda:0')
epoch: 32 test_true_pfm: 3933.8053590935738 sim_pfm: 371.26319771118386
episode: 128 training return: tensor(337.8765, device='cuda:0')
episode: 129 training return: tensor(201.1134, device='cuda:0')
episode: 130 training return: tensor(228.8460, device='cuda:0')
episode: 131 training return: tensor(304.8858, device='cuda:0')
epoch: 33 test_true_pfm: 4013.119870708231 sim_pfm: 382.21795039977104
episode: 132 training return: tensor(154.4632, device='cuda:0')
episode: 133 training return: tensor(371.2729, device='cuda:0')
episode: 134 training return: tensor(209.6942, device='cuda:0')
episode: 135 training return: tensor(294.9037, device='cuda:0')
epoch: 34 test_true_pfm: 3860.4621738942897 sim_pfm: 327.90204268030357
episode: 136 training return: tensor(193.3152, device='cuda:0')
episode: 137 training return: tensor(172.9757, device='cuda:0')
episode: 138 training return: tensor(407.2336, device='cuda:0')
episode: 139 training return: tensor(348.5578, device='cuda:0')
epoch: 35 test_true_pfm: 3999.1659080538025 sim_pfm: 342.1653537269837
episode: 140 training return: tensor(323.2601, device='cuda:0')
episode: 141 training return: tensor(225.9451, device='cuda:0')
episode: 142 training return: tensor(322.7746, device='cuda:0')
episode: 143 training return: tensor(210.3571, device='cuda:0')
epoch: 36 test_true_pfm: 3965.4271297638847 sim_pfm: 363.8780693383208
episode: 144 training return: tensor(217.7863, device='cuda:0')
episode: 145 training return: tensor(235.8033, device='cuda:0')
episode: 146 training return: tensor(302.5100, device='cuda:0')
episode: 147 training return: tensor(251.0758, device='cuda:0')
epoch: 37 test_true_pfm: 3953.7985545381307 sim_pfm: 340.92693017042865
episode: 148 training return: tensor(230.6526, device='cuda:0')
episode: 149 training return: tensor(391.1725, device='cuda:0')
episode: 150 training return: tensor(189.9901, device='cuda:0')
episode: 151 training return: tensor(372.3156, device='cuda:0')
epoch: 38 test_true_pfm: 3987.1114076916197 sim_pfm: 400.9894790278049
episode: 152 training return: tensor(192.6838, device='cuda:0')
episode: 153 training return: tensor(374.0265, device='cuda:0')
episode: 154 training return: tensor(269.1461, device='cuda:0')
episode: 155 training return: tensor(356.7992, device='cuda:0')
epoch: 39 test_true_pfm: 3960.124990204371 sim_pfm: 354.1475995056001
episode: 156 training return: tensor(235.2516, device='cuda:0')
episode: 157 training return: tensor(352.1296, device='cuda:0')
episode: 158 training return: tensor(434.1573, device='cuda:0')
episode: 159 training return: tensor(261.8753, device='cuda:0')
epoch: 40 test_true_pfm: 4036.909207059636 sim_pfm: 372.9433746601183
episode: 160 training return: tensor(354.1680, device='cuda:0')
episode: 161 training return: tensor(347.0524, device='cuda:0')
episode: 162 training return: tensor(246.3639, device='cuda:0')
episode: 163 training return: tensor(391.9818, device='cuda:0')
epoch: 41 test_true_pfm: 3959.0152853419518 sim_pfm: 316.3752655063872
episode: 164 training return: tensor(332.7295, device='cuda:0')
episode: 165 training return: tensor(366.4872, device='cuda:0')
episode: 166 training return: tensor(369.4818, device='cuda:0')
episode: 167 training return: tensor(361.7409, device='cuda:0')
epoch: 42 test_true_pfm: 3983.422481246936 sim_pfm: 344.5883743572631
episode: 168 training return: tensor(344.0579, device='cuda:0')
episode: 169 training return: tensor(307.3597, device='cuda:0')
episode: 170 training return: tensor(320.5514, device='cuda:0')
episode: 171 training return: tensor(306.2983, device='cuda:0')
epoch: 43 test_true_pfm: 3998.9264267428157 sim_pfm: 329.9759827745923
episode: 172 training return: tensor(336.1734, device='cuda:0')
episode: 173 training return: tensor(174.6279, device='cuda:0')
episode: 174 training return: tensor(328.6618, device='cuda:0')
episode: 175 training return: tensor(389.0776, device='cuda:0')
epoch: 44 test_true_pfm: 4108.4695229614945 sim_pfm: 409.79993372026365
episode: 176 training return: tensor(187.1112, device='cuda:0')
episode: 177 training return: tensor(218.0592, device='cuda:0')
episode: 178 training return: tensor(380.4221, device='cuda:0')
episode: 179 training return: tensor(404.4601, device='cuda:0')
epoch: 45 test_true_pfm: 4014.265799909291 sim_pfm: 308.45912830690696
episode: 180 training return: tensor(322.1732, device='cuda:0')
episode: 181 training return: tensor(345.7087, device='cuda:0')
episode: 182 training return: tensor(360.6813, device='cuda:0')
episode: 183 training return: tensor(267.4275, device='cuda:0')
epoch: 46 test_true_pfm: 4016.1713402186265 sim_pfm: 318.2238451493516
episode: 184 training return: tensor(276.8184, device='cuda:0')
episode: 185 training return: tensor(341.8474, device='cuda:0')
episode: 186 training return: tensor(192.9710, device='cuda:0')
episode: 187 training return: tensor(356.4862, device='cuda:0')
epoch: 47 test_true_pfm: 4016.1151636759896 sim_pfm: 394.85633684167016
episode: 188 training return: tensor(244.5667, device='cuda:0')
episode: 189 training return: tensor(399.9300, device='cuda:0')
episode: 190 training return: tensor(217.8922, device='cuda:0')
episode: 191 training return: tensor(387.1523, device='cuda:0')
epoch: 48 test_true_pfm: 3941.1118987862515 sim_pfm: 319.433300544372
episode: 192 training return: tensor(363.5365, device='cuda:0')
episode: 193 training return: tensor(166.1164, device='cuda:0')
episode: 194 training return: tensor(295.5164, device='cuda:0')
episode: 195 training return: tensor(125.1827, device='cuda:0')
epoch: 49 test_true_pfm: 3951.815204159697 sim_pfm: 358.5407269941643
episode: 196 training return: tensor(320.7203, device='cuda:0')
episode: 197 training return: tensor(-729.9245, device='cuda:0')
episode: 198 training return: tensor(406.2577, device='cuda:0')
episode: 199 training return: tensor(393.1165, device='cuda:0')
epoch: 50 test_true_pfm: 4030.1383948661482 sim_pfm: 348.6779161619682
episode: 200 training return: tensor(308.1452, device='cuda:0')
episode: 201 training return: tensor(317.1236, device='cuda:0')
episode: 202 training return: tensor(342.2607, device='cuda:0')
episode: 203 training return: tensor(236.2108, device='cuda:0')
epoch: 51 test_true_pfm: 3975.6402392595155 sim_pfm: 370.32527602117625
episode: 204 training return: tensor(184.7502, device='cuda:0')
episode: 205 training return: tensor(362.3693, device='cuda:0')
episode: 206 training return: tensor(339.4112, device='cuda:0')
episode: 207 training return: tensor(267.1738, device='cuda:0')
epoch: 52 test_true_pfm: 3999.5826430039233 sim_pfm: 397.01749743393157
episode: 208 training return: tensor(359.0559, device='cuda:0')
episode: 209 training return: tensor(305.6641, device='cuda:0')
episode: 210 training return: tensor(372.3970, device='cuda:0')
episode: 211 training return: tensor(424.4684, device='cuda:0')
epoch: 53 test_true_pfm: 4072.150360878524 sim_pfm: 415.909645552388
episode: 212 training return: tensor(307.3092, device='cuda:0')
episode: 213 training return: tensor(141.0120, device='cuda:0')
episode: 214 training return: tensor(191.7685, device='cuda:0')
episode: 215 training return: tensor(387.7572, device='cuda:0')
epoch: 54 test_true_pfm: 4019.7723585495137 sim_pfm: 383.0282481382213
episode: 216 training return: tensor(322.5827, device='cuda:0')
episode: 217 training return: tensor(336.3897, device='cuda:0')
episode: 218 training return: tensor(316.9889, device='cuda:0')
episode: 219 training return: tensor(338.4767, device='cuda:0')
epoch: 55 test_true_pfm: 3938.7853186402103 sim_pfm: 346.5934805592212
episode: 220 training return: tensor(393.2048, device='cuda:0')
episode: 221 training return: tensor(319.0299, device='cuda:0')
episode: 222 training return: tensor(314.4807, device='cuda:0')
episode: 223 training return: tensor(249.9829, device='cuda:0')
epoch: 56 test_true_pfm: 4093.3886666417216 sim_pfm: 360.29646500116604
episode: 224 training return: tensor(273.6737, device='cuda:0')
episode: 225 training return: tensor(279.0518, device='cuda:0')
episode: 226 training return: tensor(35.8060, device='cuda:0')
episode: 227 training return: tensor(425.2997, device='cuda:0')
epoch: 57 test_true_pfm: 4068.7861137871337 sim_pfm: 425.3576530752859
episode: 228 training return: tensor(239.1290, device='cuda:0')
episode: 229 training return: tensor(165.2690, device='cuda:0')
episode: 230 training return: tensor(352.5977, device='cuda:0')
episode: 231 training return: tensor(319.4668, device='cuda:0')
epoch: 58 test_true_pfm: 4026.5882373595327 sim_pfm: 345.36267459053005
episode: 232 training return: tensor(326.3626, device='cuda:0')
episode: 233 training return: tensor(269.0417, device='cuda:0')
episode: 234 training return: tensor(346.2861, device='cuda:0')
episode: 235 training return: tensor(378.8419, device='cuda:0')
epoch: 59 test_true_pfm: 3919.026384206711 sim_pfm: 368.1655495633798
episode: 236 training return: tensor(320.1367, device='cuda:0')
episode: 237 training return: tensor(402.4045, device='cuda:0')
episode: 238 training return: tensor(318.1247, device='cuda:0')
episode: 239 training return: tensor(287.3015, device='cuda:0')
epoch: 60 test_true_pfm: 4074.251541434556 sim_pfm: 394.0895539609871
episode: 240 training return: tensor(271.5558, device='cuda:0')
episode: 241 training return: tensor(193.9538, device='cuda:0')
episode: 242 training return: tensor(204.4633, device='cuda:0')
episode: 243 training return: tensor(343.9313, device='cuda:0')
epoch: 61 test_true_pfm: 3966.9018180037615 sim_pfm: 414.3285852275537
episode: 244 training return: tensor(351.5984, device='cuda:0')
episode: 245 training return: tensor(314.1399, device='cuda:0')
episode: 246 training return: tensor(343.5186, device='cuda:0')
episode: 247 training return: tensor(386.1726, device='cuda:0')
epoch: 62 test_true_pfm: 3944.29896513021 sim_pfm: 329.16414616353967
episode: 248 training return: tensor(381.4481, device='cuda:0')
episode: 249 training return: tensor(397.7633, device='cuda:0')
episode: 250 training return: tensor(264.2469, device='cuda:0')
episode: 251 training return: tensor(326.2303, device='cuda:0')
epoch: 63 test_true_pfm: 3992.8508156313933 sim_pfm: 325.9036380481557
episode: 252 training return: tensor(363.4703, device='cuda:0')
episode: 253 training return: tensor(328.3036, device='cuda:0')
episode: 254 training return: tensor(388.1744, device='cuda:0')
episode: 255 training return: tensor(72.8264, device='cuda:0')
epoch: 64 test_true_pfm: 3999.85341011204 sim_pfm: 341.0129756874521
episode: 256 training return: tensor(275.9299, device='cuda:0')
episode: 257 training return: tensor(264.8924, device='cuda:0')
episode: 258 training return: tensor(233.9884, device='cuda:0')
episode: 259 training return: tensor(246.7222, device='cuda:0')
epoch: 65 test_true_pfm: 3993.6917053061748 sim_pfm: 334.8527952138781
episode: 260 training return: tensor(360.6510, device='cuda:0')
episode: 261 training return: tensor(281.5343, device='cuda:0')
episode: 262 training return: tensor(189.0652, device='cuda:0')
episode: 263 training return: tensor(298.9909, device='cuda:0')
epoch: 66 test_true_pfm: 3964.936369082711 sim_pfm: 354.78080319900374
episode: 264 training return: tensor(397.5780, device='cuda:0')
episode: 265 training return: tensor(291.2272, device='cuda:0')
episode: 266 training return: tensor(360.2068, device='cuda:0')
episode: 267 training return: tensor(395.7165, device='cuda:0')
epoch: 67 test_true_pfm: 4099.772590085523 sim_pfm: 404.62067098340293
episode: 268 training return: tensor(192.0596, device='cuda:0')
episode: 269 training return: tensor(296.0016, device='cuda:0')
episode: 270 training return: tensor(431.9448, device='cuda:0')
episode: 271 training return: tensor(181.4547, device='cuda:0')
epoch: 68 test_true_pfm: 3960.9998467687706 sim_pfm: 412.63438673171913
episode: 272 training return: tensor(392.5787, device='cuda:0')
episode: 273 training return: tensor(259.2496, device='cuda:0')
episode: 274 training return: tensor(432.6249, device='cuda:0')
episode: 275 training return: tensor(402.3069, device='cuda:0')
epoch: 69 test_true_pfm: 4002.715303530944 sim_pfm: 336.45687226060545
episode: 276 training return: tensor(252.6986, device='cuda:0')
episode: 277 training return: tensor(265.5085, device='cuda:0')
episode: 278 training return: tensor(415.2983, device='cuda:0')
episode: 279 training return: tensor(385.6085, device='cuda:0')
epoch: 70 test_true_pfm: 4033.071854914493 sim_pfm: 323.2367230601085
episode: 280 training return: tensor(295.5717, device='cuda:0')
episode: 281 training return: tensor(237.9650, device='cuda:0')
episode: 282 training return: tensor(396.1442, device='cuda:0')
episode: 283 training return: tensor(365.2206, device='cuda:0')
epoch: 71 test_true_pfm: 4040.662408672233 sim_pfm: 398.598601331653
episode: 284 training return: tensor(402.7773, device='cuda:0')
episode: 285 training return: tensor(365.5165, device='cuda:0')
episode: 286 training return: tensor(366.6612, device='cuda:0')
episode: 287 training return: tensor(321.1921, device='cuda:0')
epoch: 72 test_true_pfm: 4000.315668155896 sim_pfm: 342.9427285827308
episode: 288 training return: tensor(346.1423, device='cuda:0')
episode: 289 training return: tensor(248.7643, device='cuda:0')
episode: 290 training return: tensor(386.3491, device='cuda:0')
episode: 291 training return: tensor(172.9421, device='cuda:0')
epoch: 73 test_true_pfm: 3991.2056478129048 sim_pfm: 354.81750616179005
episode: 292 training return: tensor(407.6348, device='cuda:0')
episode: 293 training return: tensor(259.1234, device='cuda:0')
episode: 294 training return: tensor(369.6292, device='cuda:0')
episode: 295 training return: tensor(200.1328, device='cuda:0')
epoch: 74 test_true_pfm: 4020.6190856596877 sim_pfm: 402.00463410880184
episode: 296 training return: tensor(393.7199, device='cuda:0')
episode: 297 training return: tensor(289.3456, device='cuda:0')
episode: 298 training return: tensor(376.3067, device='cuda:0')
episode: 299 training return: tensor(279.2293, device='cuda:0')
epoch: 75 test_true_pfm: 4001.2922365655036 sim_pfm: 312.34863758584834
episode: 300 training return: tensor(264.4243, device='cuda:0')
episode: 301 training return: tensor(382.1916, device='cuda:0')
episode: 302 training return: tensor(326.3543, device='cuda:0')
episode: 303 training return: tensor(352.2877, device='cuda:0')
epoch: 76 test_true_pfm: 4011.677363339842 sim_pfm: 397.2589871759022
episode: 304 training return: tensor(384.4570, device='cuda:0')
episode: 305 training return: tensor(218.6668, device='cuda:0')
episode: 306 training return: tensor(281.2802, device='cuda:0')
episode: 307 training return: tensor(39.7236, device='cuda:0')
epoch: 77 test_true_pfm: 4086.741460472718 sim_pfm: 440.9682420187746
episode: 308 training return: tensor(261.6194, device='cuda:0')
episode: 309 training return: tensor(415.2840, device='cuda:0')
episode: 310 training return: tensor(92.0145, device='cuda:0')
episode: 311 training return: tensor(279.0272, device='cuda:0')
epoch: 78 test_true_pfm: 4010.8826437990265 sim_pfm: 351.929096331005
episode: 312 training return: tensor(246.6729, device='cuda:0')
episode: 313 training return: tensor(374.3395, device='cuda:0')
episode: 314 training return: tensor(301.8313, device='cuda:0')
episode: 315 training return: tensor(363.5773, device='cuda:0')
epoch: 79 test_true_pfm: 3991.9698681488385 sim_pfm: 344.11190295520163
episode: 316 training return: tensor(251.7481, device='cuda:0')
episode: 317 training return: tensor(292.7050, device='cuda:0')
episode: 318 training return: tensor(244.2392, device='cuda:0')
episode: 319 training return: tensor(255.9052, device='cuda:0')
epoch: 80 test_true_pfm: 4038.9053354853154 sim_pfm: 400.30864345736336
episode: 320 training return: tensor(280.3514, device='cuda:0')
episode: 321 training return: tensor(196.2278, device='cuda:0')
episode: 322 training return: tensor(357.3443, device='cuda:0')
episode: 323 training return: tensor(401.8665, device='cuda:0')
epoch: 81 test_true_pfm: 3970.417443300818 sim_pfm: 393.0151873990253
episode: 324 training return: tensor(303.0321, device='cuda:0')
episode: 325 training return: tensor(302.7775, device='cuda:0')
episode: 326 training return: tensor(367.9838, device='cuda:0')
episode: 327 training return: tensor(243.1102, device='cuda:0')
epoch: 82 test_true_pfm: 4079.8651912122536 sim_pfm: 374.663508184293
episode: 328 training return: tensor(329.4660, device='cuda:0')
episode: 329 training return: tensor(430.2807, device='cuda:0')
episode: 330 training return: tensor(168.3087, device='cuda:0')
episode: 331 training return: tensor(259.8703, device='cuda:0')
epoch: 83 test_true_pfm: 4074.32676329302 sim_pfm: 426.516108249091
episode: 332 training return: tensor(369.1559, device='cuda:0')
episode: 333 training return: tensor(396.2874, device='cuda:0')
episode: 334 training return: tensor(366.8677, device='cuda:0')
episode: 335 training return: tensor(264.3962, device='cuda:0')
epoch: 84 test_true_pfm: 4029.92118940095 sim_pfm: 438.83075243209413
episode: 336 training return: tensor(360.4905, device='cuda:0')
episode: 337 training return: tensor(353.6544, device='cuda:0')
episode: 338 training return: tensor(407.0690, device='cuda:0')
episode: 339 training return: tensor(291.4648, device='cuda:0')
epoch: 85 test_true_pfm: 4051.3969244092045 sim_pfm: 389.6479577567079
episode: 340 training return: tensor(188.5413, device='cuda:0')
episode: 341 training return: tensor(339.9197, device='cuda:0')
episode: 342 training return: tensor(363.5765, device='cuda:0')
episode: 343 training return: tensor(258.2296, device='cuda:0')
epoch: 86 test_true_pfm: 3859.4362408246657 sim_pfm: 402.68226248477004
episode: 344 training return: tensor(312.3728, device='cuda:0')
episode: 345 training return: tensor(283.7624, device='cuda:0')
episode: 346 training return: tensor(270.2558, device='cuda:0')
episode: 347 training return: tensor(422.4462, device='cuda:0')
epoch: 87 test_true_pfm: 4008.5908202973274 sim_pfm: 291.4783107654075
episode: 348 training return: tensor(392.4654, device='cuda:0')
episode: 349 training return: tensor(345.4708, device='cuda:0')
episode: 350 training return: tensor(313.6253, device='cuda:0')
episode: 351 training return: tensor(338.1465, device='cuda:0')
epoch: 88 test_true_pfm: 3985.6387808086542 sim_pfm: 343.185407034917
episode: 352 training return: tensor(362.4796, device='cuda:0')
episode: 353 training return: tensor(391.9344, device='cuda:0')
episode: 354 training return: tensor(266.9908, device='cuda:0')
episode: 355 training return: tensor(422.4089, device='cuda:0')
epoch: 89 test_true_pfm: 3992.1346038373395 sim_pfm: 327.3755778856964
episode: 356 training return: tensor(366.5450, device='cuda:0')
episode: 357 training return: tensor(384.1105, device='cuda:0')
episode: 358 training return: tensor(366.8506, device='cuda:0')
episode: 359 training return: tensor(311.1635, device='cuda:0')
epoch: 90 test_true_pfm: 4034.2070224026006 sim_pfm: 417.91581011071685
episode: 360 training return: tensor(133.0844, device='cuda:0')
episode: 361 training return: tensor(294.8425, device='cuda:0')
episode: 362 training return: tensor(235.1274, device='cuda:0')
episode: 363 training return: tensor(230.3864, device='cuda:0')
epoch: 91 test_true_pfm: 3922.0847588911856 sim_pfm: 391.9043432182225
episode: 364 training return: tensor(237.1834, device='cuda:0')
episode: 365 training return: tensor(113.9311, device='cuda:0')
episode: 366 training return: tensor(266.3407, device='cuda:0')
episode: 367 training return: tensor(278.9312, device='cuda:0')
epoch: 92 test_true_pfm: 3968.752518784939 sim_pfm: 410.343636484904
episode: 368 training return: tensor(316.5545, device='cuda:0')
episode: 369 training return: tensor(247.8604, device='cuda:0')
episode: 370 training return: tensor(303.9803, device='cuda:0')
episode: 371 training return: tensor(217.8158, device='cuda:0')
epoch: 93 test_true_pfm: 4073.240048680036 sim_pfm: 399.3126402856239
episode: 372 training return: tensor(395.4880, device='cuda:0')
episode: 373 training return: tensor(418.7952, device='cuda:0')
episode: 374 training return: tensor(280.0509, device='cuda:0')
episode: 375 training return: tensor(308.7919, device='cuda:0')
epoch: 94 test_true_pfm: 4070.902375784126 sim_pfm: 325.30824529378634
episode: 376 training return: tensor(384.9693, device='cuda:0')
episode: 377 training return: tensor(324.2951, device='cuda:0')
episode: 378 training return: tensor(398.5288, device='cuda:0')
episode: 379 training return: tensor(256.5108, device='cuda:0')
epoch: 95 test_true_pfm: 3993.9999370583523 sim_pfm: 441.25794216881815
episode: 380 training return: tensor(297.7935, device='cuda:0')
episode: 381 training return: tensor(357.7283, device='cuda:0')
episode: 382 training return: tensor(273.1987, device='cuda:0')
episode: 383 training return: tensor(400.1230, device='cuda:0')
epoch: 96 test_true_pfm: 3971.3525018614278 sim_pfm: 328.11309403083095
episode: 384 training return: tensor(241.6953, device='cuda:0')
episode: 385 training return: tensor(297.7485, device='cuda:0')
episode: 386 training return: tensor(410.8941, device='cuda:0')
episode: 387 training return: tensor(378.1385, device='cuda:0')
epoch: 97 test_true_pfm: 3932.196390461268 sim_pfm: 360.4600733107266
episode: 388 training return: tensor(394.2166, device='cuda:0')
episode: 389 training return: tensor(261.1803, device='cuda:0')
episode: 390 training return: tensor(302.3698, device='cuda:0')
episode: 391 training return: tensor(259.7406, device='cuda:0')
epoch: 98 test_true_pfm: 3977.7748109289423 sim_pfm: 387.50907120865304
episode: 392 training return: tensor(277.7227, device='cuda:0')
episode: 393 training return: tensor(224.6057, device='cuda:0')
episode: 394 training return: tensor(234.2116, device='cuda:0')
episode: 395 training return: tensor(369.0272, device='cuda:0')
epoch: 99 test_true_pfm: 4022.321794143825 sim_pfm: 404.57311476842733
episode: 396 training return: tensor(357.9322, device='cuda:0')
episode: 397 training return: tensor(357.8306, device='cuda:0')
episode: 398 training return: tensor(201.0298, device='cuda:0')
episode: 399 training return: tensor(263.5925, device='cuda:0')
epoch: 100 test_true_pfm: 4000.0995852194296 sim_pfm: 443.0465896843525
episode: 400 training return: tensor(314.1777, device='cuda:0')
episode: 401 training return: tensor(435.0469, device='cuda:0')
episode: 402 training return: tensor(354.2468, device='cuda:0')
episode: 403 training return: tensor(382.2072, device='cuda:0')
epoch: 101 test_true_pfm: 4038.6226133100804 sim_pfm: 288.1543143937306
episode: 404 training return: tensor(300.3748, device='cuda:0')
episode: 405 training return: tensor(312.8414, device='cuda:0')
episode: 406 training return: tensor(391.9626, device='cuda:0')
episode: 407 training return: tensor(397.1819, device='cuda:0')
epoch: 102 test_true_pfm: 4001.2740507764865 sim_pfm: 387.73315230439766
episode: 408 training return: tensor(388.1584, device='cuda:0')
episode: 409 training return: tensor(269.4573, device='cuda:0')
episode: 410 training return: tensor(355.8497, device='cuda:0')
episode: 411 training return: tensor(388.7383, device='cuda:0')
epoch: 103 test_true_pfm: 3995.009984835065 sim_pfm: 357.23510268367437
episode: 412 training return: tensor(383.5365, device='cuda:0')
episode: 413 training return: tensor(329.0411, device='cuda:0')
episode: 414 training return: tensor(363.1548, device='cuda:0')
episode: 415 training return: tensor(317.1372, device='cuda:0')
epoch: 104 test_true_pfm: 4035.012625153986 sim_pfm: 368.12852000937954
episode: 416 training return: tensor(396.8459, device='cuda:0')
episode: 417 training return: tensor(309.0419, device='cuda:0')
episode: 418 training return: tensor(331.5356, device='cuda:0')
episode: 419 training return: tensor(380.1679, device='cuda:0')
epoch: 105 test_true_pfm: 4020.7934563190065 sim_pfm: 386.65419463890913
episode: 420 training return: tensor(278.9851, device='cuda:0')
episode: 421 training return: tensor(420.6167, device='cuda:0')
episode: 422 training return: tensor(378.5072, device='cuda:0')
episode: 423 training return: tensor(343.1696, device='cuda:0')
epoch: 106 test_true_pfm: 4042.088368781902 sim_pfm: 376.6638867148043
episode: 424 training return: tensor(375.9885, device='cuda:0')
episode: 425 training return: tensor(317.0623, device='cuda:0')
episode: 426 training return: tensor(375.2428, device='cuda:0')
episode: 427 training return: tensor(329.8367, device='cuda:0')
epoch: 107 test_true_pfm: 3929.149868373341 sim_pfm: 405.46499703383114
episode: 428 training return: tensor(342.6974, device='cuda:0')
episode: 429 training return: tensor(142.7141, device='cuda:0')
episode: 430 training return: tensor(319.0210, device='cuda:0')
episode: 431 training return: tensor(314.8624, device='cuda:0')
epoch: 108 test_true_pfm: 4020.6384545299093 sim_pfm: 316.382476483559
episode: 432 training return: tensor(331.4949, device='cuda:0')
episode: 433 training return: tensor(66.7720, device='cuda:0')
episode: 434 training return: tensor(332.2581, device='cuda:0')
episode: 435 training return: tensor(233.6321, device='cuda:0')
epoch: 109 test_true_pfm: 3964.067290197587 sim_pfm: 374.24128885291674
episode: 436 training return: tensor(245.7384, device='cuda:0')
episode: 437 training return: tensor(401.1210, device='cuda:0')
episode: 438 training return: tensor(434.4892, device='cuda:0')
episode: 439 training return: tensor(246.0067, device='cuda:0')
epoch: 110 test_true_pfm: 4023.8039837278234 sim_pfm: 421.40810285691015
episode: 440 training return: tensor(337.0127, device='cuda:0')
episode: 441 training return: tensor(294.4089, device='cuda:0')
episode: 442 training return: tensor(348.8686, device='cuda:0')
episode: 443 training return: tensor(261.1081, device='cuda:0')
epoch: 111 test_true_pfm: 4048.473735175465 sim_pfm: 397.28956524973427
episode: 444 training return: tensor(363.2230, device='cuda:0')
episode: 445 training return: tensor(279.6671, device='cuda:0')
episode: 446 training return: tensor(374.6763, device='cuda:0')
episode: 447 training return: tensor(412.1477, device='cuda:0')
epoch: 112 test_true_pfm: 3970.193812307715 sim_pfm: 330.3504809795413
episode: 448 training return: tensor(380.9119, device='cuda:0')
episode: 449 training return: tensor(373.1528, device='cuda:0')
episode: 450 training return: tensor(414.9135, device='cuda:0')
episode: 451 training return: tensor(357.7106, device='cuda:0')
epoch: 113 test_true_pfm: 4009.3745484714145 sim_pfm: 385.19917580863694
episode: 452 training return: tensor(362.9142, device='cuda:0')
episode: 453 training return: tensor(214.8097, device='cuda:0')
episode: 454 training return: tensor(373.7541, device='cuda:0')
episode: 455 training return: tensor(398.8881, device='cuda:0')
epoch: 114 test_true_pfm: 4057.0347430959446 sim_pfm: 342.9499267055944
episode: 456 training return: tensor(404.8882, device='cuda:0')
episode: 457 training return: tensor(388.7445, device='cuda:0')
episode: 458 training return: tensor(393.5674, device='cuda:0')
episode: 459 training return: tensor(346.3583, device='cuda:0')
epoch: 115 test_true_pfm: 4002.183815450455 sim_pfm: 342.82238429938053
episode: 460 training return: tensor(385.9134, device='cuda:0')
episode: 461 training return: tensor(178.7457, device='cuda:0')
episode: 462 training return: tensor(340.1252, device='cuda:0')
episode: 463 training return: tensor(276.4394, device='cuda:0')
epoch: 116 test_true_pfm: 3943.407583702204 sim_pfm: 304.89347516708466
episode: 464 training return: tensor(348.4737, device='cuda:0')
episode: 465 training return: tensor(376.2077, device='cuda:0')
episode: 466 training return: tensor(310.1180, device='cuda:0')
episode: 467 training return: tensor(303.2605, device='cuda:0')
epoch: 117 test_true_pfm: 4077.575997634772 sim_pfm: 400.98761199519504
episode: 468 training return: tensor(409.9340, device='cuda:0')
episode: 469 training return: tensor(380.0030, device='cuda:0')
episode: 470 training return: tensor(383.9146, device='cuda:0')
episode: 471 training return: tensor(376.9337, device='cuda:0')
epoch: 118 test_true_pfm: 4064.8894603842123 sim_pfm: 434.7498011864761
episode: 472 training return: tensor(394.3577, device='cuda:0')
episode: 473 training return: tensor(375.8795, device='cuda:0')
episode: 474 training return: tensor(336.8677, device='cuda:0')
episode: 475 training return: tensor(413.8586, device='cuda:0')
epoch: 119 test_true_pfm: 3963.905404369422 sim_pfm: 371.09231850043096
episode: 476 training return: tensor(311.3280, device='cuda:0')
episode: 477 training return: tensor(347.4581, device='cuda:0')
episode: 478 training return: tensor(316.8607, device='cuda:0')
episode: 479 training return: tensor(306.3571, device='cuda:0')
epoch: 120 test_true_pfm: 4011.935961091465 sim_pfm: 347.89516413758975
episode: 480 training return: tensor(224.4945, device='cuda:0')
episode: 481 training return: tensor(374.4973, device='cuda:0')
episode: 482 training return: tensor(346.2192, device='cuda:0')
episode: 483 training return: tensor(262.8920, device='cuda:0')
epoch: 121 test_true_pfm: 3987.837377048129 sim_pfm: 415.65001521399245
episode: 484 training return: tensor(372.8696, device='cuda:0')
episode: 485 training return: tensor(390.7498, device='cuda:0')
episode: 486 training return: tensor(352.5204, device='cuda:0')
episode: 487 training return: tensor(387.8832, device='cuda:0')
epoch: 122 test_true_pfm: 4097.385839007187 sim_pfm: 303.203700763348
episode: 488 training return: tensor(281.1119, device='cuda:0')
episode: 489 training return: tensor(323.1507, device='cuda:0')
episode: 490 training return: tensor(335.7930, device='cuda:0')
episode: 491 training return: tensor(374.4515, device='cuda:0')
epoch: 123 test_true_pfm: 3981.8203760596057 sim_pfm: 357.68126806429547
episode: 492 training return: tensor(318.6346, device='cuda:0')
episode: 493 training return: tensor(388.9104, device='cuda:0')
episode: 494 training return: tensor(248.6150, device='cuda:0')
episode: 495 training return: tensor(312.5567, device='cuda:0')
epoch: 124 test_true_pfm: 3971.713220349755 sim_pfm: 386.6589675353607
episode: 496 training return: tensor(267.4664, device='cuda:0')
episode: 497 training return: tensor(351.9598, device='cuda:0')
episode: 498 training return: tensor(271.8497, device='cuda:0')
episode: 499 training return: tensor(266.5042, device='cuda:0')
epoch: 125 test_true_pfm: 4072.160906656826 sim_pfm: 391.76585760203307
episode: 500 training return: tensor(410.3816, device='cuda:0')
episode: 501 training return: tensor(320.6102, device='cuda:0')
episode: 502 training return: tensor(420.5814, device='cuda:0')
episode: 503 training return: tensor(224.9970, device='cuda:0')
epoch: 126 test_true_pfm: 3929.3976313136736 sim_pfm: 371.87169387575705
episode: 504 training return: tensor(145.1029, device='cuda:0')
episode: 505 training return: tensor(366.9535, device='cuda:0')
episode: 506 training return: tensor(378.5444, device='cuda:0')
episode: 507 training return: tensor(412.3108, device='cuda:0')
epoch: 127 test_true_pfm: 4068.0314773264577 sim_pfm: 391.804845444926
episode: 508 training return: tensor(234.1795, device='cuda:0')
episode: 509 training return: tensor(342.7929, device='cuda:0')
episode: 510 training return: tensor(361.8189, device='cuda:0')
episode: 511 training return: tensor(335.0638, device='cuda:0')
epoch: 128 test_true_pfm: 3851.8926049059105 sim_pfm: 371.4415857957113
episode: 512 training return: tensor(397.5475, device='cuda:0')
episode: 513 training return: tensor(290.4817, device='cuda:0')
episode: 514 training return: tensor(205.0300, device='cuda:0')
episode: 515 training return: tensor(409.5357, device='cuda:0')
epoch: 129 test_true_pfm: 3974.207127414816 sim_pfm: 384.8529811481324
episode: 516 training return: tensor(264.9305, device='cuda:0')
episode: 517 training return: tensor(412.0062, device='cuda:0')
episode: 518 training return: tensor(226.6459, device='cuda:0')
episode: 519 training return: tensor(391.2578, device='cuda:0')
epoch: 130 test_true_pfm: 3999.2771488754674 sim_pfm: 414.5375868138702
episode: 520 training return: tensor(386.9862, device='cuda:0')
episode: 521 training return: tensor(381.9229, device='cuda:0')
episode: 522 training return: tensor(401.5891, device='cuda:0')
episode: 523 training return: tensor(352.5030, device='cuda:0')
epoch: 131 test_true_pfm: 3951.624290502268 sim_pfm: 367.5540614601341
episode: 524 training return: tensor(281.6708, device='cuda:0')
episode: 525 training return: tensor(326.0320, device='cuda:0')
episode: 526 training return: tensor(303.0058, device='cuda:0')
episode: 527 training return: tensor(401.5356, device='cuda:0')
epoch: 132 test_true_pfm: 4025.7944925548177 sim_pfm: 354.2668669934889
episode: 528 training return: tensor(370.7202, device='cuda:0')
episode: 529 training return: tensor(380.9066, device='cuda:0')
episode: 530 training return: tensor(385.7734, device='cuda:0')
episode: 531 training return: tensor(392.5626, device='cuda:0')
epoch: 133 test_true_pfm: 4064.971319660252 sim_pfm: 379.6065826900497
episode: 532 training return: tensor(389.3617, device='cuda:0')
episode: 533 training return: tensor(94.3608, device='cuda:0')
episode: 534 training return: tensor(379.2025, device='cuda:0')
episode: 535 training return: tensor(278.3589, device='cuda:0')
epoch: 134 test_true_pfm: 4036.935052940488 sim_pfm: 324.13157328394783
episode: 536 training return: tensor(226.7074, device='cuda:0')
episode: 537 training return: tensor(313.9417, device='cuda:0')
episode: 538 training return: tensor(404.0305, device='cuda:0')
episode: 539 training return: tensor(422.7717, device='cuda:0')
epoch: 135 test_true_pfm: 3967.148187213434 sim_pfm: 380.1900780957658
episode: 540 training return: tensor(429.1824, device='cuda:0')
episode: 541 training return: tensor(360.8826, device='cuda:0')
episode: 542 training return: tensor(367.1745, device='cuda:0')
episode: 543 training return: tensor(246.0743, device='cuda:0')
epoch: 136 test_true_pfm: 4001.449810963661 sim_pfm: 388.4119853790423
episode: 544 training return: tensor(47.4200, device='cuda:0')
episode: 545 training return: tensor(322.7047, device='cuda:0')
episode: 546 training return: tensor(380.7551, device='cuda:0')
episode: 547 training return: tensor(312.0630, device='cuda:0')
epoch: 137 test_true_pfm: 3994.9640124905986 sim_pfm: 352.21566382846987
episode: 548 training return: tensor(399.7065, device='cuda:0')
episode: 549 training return: tensor(376.1017, device='cuda:0')
episode: 550 training return: tensor(335.2467, device='cuda:0')
episode: 551 training return: tensor(379.1020, device='cuda:0')
epoch: 138 test_true_pfm: 4020.698058547297 sim_pfm: 384.9378472072228
episode: 552 training return: tensor(396.0933, device='cuda:0')
episode: 553 training return: tensor(368.8164, device='cuda:0')
episode: 554 training return: tensor(154.1500, device='cuda:0')
episode: 555 training return: tensor(379.5910, device='cuda:0')
epoch: 139 test_true_pfm: 3992.857091471593 sim_pfm: 383.0185866495788
episode: 556 training return: tensor(176.0832, device='cuda:0')
episode: 557 training return: tensor(386.6373, device='cuda:0')
episode: 558 training return: tensor(236.4256, device='cuda:0')
episode: 559 training return: tensor(354.7379, device='cuda:0')
epoch: 140 test_true_pfm: 4074.164849216964 sim_pfm: 402.97603447547107
episode: 560 training return: tensor(413.3229, device='cuda:0')
episode: 561 training return: tensor(340.4993, device='cuda:0')
episode: 562 training return: tensor(412.4881, device='cuda:0')
episode: 563 training return: tensor(277.8021, device='cuda:0')
epoch: 141 test_true_pfm: 3972.0445702411016 sim_pfm: 344.96354240493383
episode: 564 training return: tensor(399.3189, device='cuda:0')
episode: 565 training return: tensor(338.8962, device='cuda:0')
episode: 566 training return: tensor(323.7861, device='cuda:0')
episode: 567 training return: tensor(442.9329, device='cuda:0')
epoch: 142 test_true_pfm: 3956.215504877508 sim_pfm: 360.860274051578
episode: 568 training return: tensor(423.6737, device='cuda:0')
episode: 569 training return: tensor(375.4128, device='cuda:0')
episode: 570 training return: tensor(415.9377, device='cuda:0')
episode: 571 training return: tensor(324.4897, device='cuda:0')
epoch: 143 test_true_pfm: 4000.6784621628935 sim_pfm: 376.6592711760507
episode: 572 training return: tensor(343.0278, device='cuda:0')
episode: 573 training return: tensor(267.3689, device='cuda:0')
episode: 574 training return: tensor(356.4254, device='cuda:0')
episode: 575 training return: tensor(376.4521, device='cuda:0')
epoch: 144 test_true_pfm: 3965.6763565576543 sim_pfm: 369.54355642325635
episode: 576 training return: tensor(316.4356, device='cuda:0')
episode: 577 training return: tensor(325.3974, device='cuda:0')
episode: 578 training return: tensor(263.7968, device='cuda:0')
episode: 579 training return: tensor(380.2099, device='cuda:0')
epoch: 145 test_true_pfm: 4016.3667945063426 sim_pfm: 381.52645120420493
episode: 580 training return: tensor(272.8124, device='cuda:0')
episode: 581 training return: tensor(298.3052, device='cuda:0')
episode: 582 training return: tensor(368.5952, device='cuda:0')
episode: 583 training return: tensor(350.6978, device='cuda:0')
epoch: 146 test_true_pfm: 4057.0971492187145 sim_pfm: 377.4369884498204
episode: 584 training return: tensor(346.1181, device='cuda:0')
episode: 585 training return: tensor(286.2090, device='cuda:0')
episode: 586 training return: tensor(401.1151, device='cuda:0')
episode: 587 training return: tensor(387.2978, device='cuda:0')
epoch: 147 test_true_pfm: 4033.8840893919373 sim_pfm: 388.7033457367118
episode: 588 training return: tensor(331.7429, device='cuda:0')
episode: 589 training return: tensor(348.0240, device='cuda:0')
episode: 590 training return: tensor(223.5760, device='cuda:0')
episode: 591 training return: tensor(264.8154, device='cuda:0')
epoch: 148 test_true_pfm: 3981.083400309298 sim_pfm: 393.39774850538623
episode: 592 training return: tensor(380.0696, device='cuda:0')
episode: 593 training return: tensor(356.1557, device='cuda:0')
episode: 594 training return: tensor(388.1999, device='cuda:0')
episode: 595 training return: tensor(402.4324, device='cuda:0')
epoch: 149 test_true_pfm: 4092.9652896753246 sim_pfm: 397.28307839248254
episode: 596 training return: tensor(382.1364, device='cuda:0')
episode: 597 training return: tensor(399.5275, device='cuda:0')
episode: 598 training return: tensor(110.0668, device='cuda:0')
episode: 599 training return: tensor(330.2034, device='cuda:0')
epoch: 150 test_true_pfm: 4006.481088707654 sim_pfm: 393.83177680980106
