['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '4']
epoch: 0 training_loss 0.26098950415849687 test_loss: 0.20802133083343505
epoch: 1 training_loss 0.1998514986783266 test_loss: 0.19940295219421386
epoch: 2 training_loss 0.19525740101933478 test_loss: 0.22557222843170166
epoch: 3 training_loss 0.20197795569896698 test_loss: 0.20375144481658936
epoch: 4 training_loss 0.20174987606704234 test_loss: 0.2192927837371826
epoch: 5 training_loss 0.1894788830727339 test_loss: 0.18074003458023072
epoch: 6 training_loss 0.20254215367138387 test_loss: 0.18233420848846435
epoch: 7 training_loss 0.18435646928846836 test_loss: 0.20381300449371337
epoch: 8 training_loss 0.18744196876883507 test_loss: 0.20033903121948243
epoch: 9 training_loss 0.1960308451205492 test_loss: 0.1821555733680725
epoch: 10 training_loss 0.18401872128248214 test_loss: 0.1916072130203247
epoch: 11 training_loss 0.18513385340571403 test_loss: 0.1896260380744934
epoch: 12 training_loss 0.19436278603971005 test_loss: 0.19132280349731445
epoch: 13 training_loss 0.18423614777624608 test_loss: 0.1822616457939148
epoch: 14 training_loss 0.18316727086901666 test_loss: 0.1687362790107727
epoch: 15 training_loss 0.1914067891985178 test_loss: 0.19471540451049804
epoch: 16 training_loss 0.1827822034060955 test_loss: 0.19195624589920043
epoch: 17 training_loss 0.18773551888763904 test_loss: 0.17950509786605834
epoch: 18 training_loss 0.1830550429970026 test_loss: 0.1882636785507202
epoch: 19 training_loss 0.1861706491559744 test_loss: 0.18596930503845216
epoch: 20 training_loss 0.1841608276963234 test_loss: 0.19536080360412597
epoch: 21 training_loss 0.1820533987879753 test_loss: 0.18208662271499634
epoch: 22 training_loss 0.1802462273836136 test_loss: 0.17086020708084107
epoch: 23 training_loss 0.18401546094566584 test_loss: 0.19563308954238892
epoch: 24 training_loss 0.1852674863487482 test_loss: 0.19828850030899048
epoch: 25 training_loss 0.1841698030382395 test_loss: 0.17467466592788697
epoch: 26 training_loss 0.18784834019839763 test_loss: 0.16763535737991334
epoch: 27 training_loss 0.1703267838060856 test_loss: 0.17255395650863647
epoch: 28 training_loss 0.1831037549674511 test_loss: 0.185547935962677
epoch: 29 training_loss 0.18563391786068678 test_loss: 0.1786130428314209
epoch: 30 training_loss 0.1790496665984392 test_loss: 0.17135870456695557
epoch: 31 training_loss 0.18466640815138816 test_loss: 0.19332245588302613
epoch: 32 training_loss 0.17425902530550957 test_loss: 0.19533361196517945
epoch: 33 training_loss 0.1852057957649231 test_loss: 0.19073911905288696
epoch: 34 training_loss 0.18557523429393769 test_loss: 0.18594213724136352
epoch: 35 training_loss 0.18087359361350536 test_loss: 0.1938934087753296
epoch: 36 training_loss 0.1868595603853464 test_loss: 0.1887202501296997
epoch: 37 training_loss 0.1812662547826767 test_loss: 0.1696377396583557
epoch: 38 training_loss 0.17993649035692216 test_loss: 0.1676006317138672
epoch: 39 training_loss 0.1869931974261999 test_loss: 0.1858653426170349
epoch: 40 training_loss 0.18376161120831966 test_loss: 0.18231502771377564
epoch: 41 training_loss 0.18136379979550837 test_loss: 0.18698993921279908
epoch: 42 training_loss 0.18366918712854385 test_loss: 0.17288217544555665
epoch: 43 training_loss 0.17935220681130887 test_loss: 0.1832895040512085
epoch: 44 training_loss 0.18520363964140416 test_loss: 0.19034054279327392
epoch: 45 training_loss 0.18408073775470257 test_loss: 0.18776382207870485
epoch: 46 training_loss 0.17893622890114785 test_loss: 0.17542015314102172
epoch: 47 training_loss 0.17942894220352174 test_loss: 0.18519777059555054
epoch: 48 training_loss 0.183923296071589 test_loss: 0.18151124715805053
epoch: 49 training_loss 0.1875089520215988 test_loss: 0.1710050106048584
epoch: 50 training_loss 0.17700691342353822 test_loss: 0.1925256848335266
epoch: 51 training_loss 0.1801419622451067 test_loss: 0.17563639879226683
epoch: 52 training_loss 0.18207241579890251 test_loss: 0.1779141306877136
epoch: 53 training_loss 0.17219581451267005 test_loss: 0.1988453149795532
epoch: 54 training_loss 0.1805737466365099 test_loss: 0.18004729747772216
epoch: 55 training_loss 0.18517450876533986 test_loss: 0.17737420797348022
epoch: 56 training_loss 0.17942229755222797 test_loss: 0.1831192135810852
epoch: 57 training_loss 0.18046453945338725 test_loss: 0.20062434673309326
epoch: 58 training_loss 0.18137104801833628 test_loss: 0.18507121801376342
epoch: 59 training_loss 0.17942999236285687 test_loss: 0.17342395782470704
epoch: 60 training_loss 0.1652520003914833 test_loss: 0.1807076334953308
epoch: 61 training_loss 0.17744807668030263 test_loss: 0.18159630298614501
epoch: 62 training_loss 0.18702015563845634 test_loss: 0.17419047355651857
epoch: 63 training_loss 0.17882095381617547 test_loss: 0.1844380736351013
epoch: 64 training_loss 0.1782369464635849 test_loss: 0.18165700435638427
epoch: 65 training_loss 0.17959224089980125 test_loss: 0.17624472379684447
epoch: 66 training_loss 0.1795560819655657 test_loss: 0.1832476019859314
epoch: 67 training_loss 0.17726481705904007 test_loss: 0.18133534193038942
epoch: 68 training_loss 0.17938021719455718 test_loss: 0.18969080448150635
epoch: 69 training_loss 0.18314008556306363 test_loss: 0.17491369247436522
epoch: 70 training_loss 0.1798402637243271 test_loss: 0.18265398740768432
epoch: 71 training_loss 0.17671395055949687 test_loss: 0.1812601327896118
epoch: 72 training_loss 0.17190502382814885 test_loss: 0.16391526460647582
epoch: 73 training_loss 0.1787275068461895 test_loss: 0.18278071880340577
epoch: 74 training_loss 0.17974829904735087 test_loss: 0.1964455008506775
epoch: 75 training_loss 0.18872287206351757 test_loss: 0.1797610878944397
epoch: 76 training_loss 0.18246361933648586 test_loss: 0.19522485733032227
epoch: 77 training_loss 0.17631762459874153 test_loss: 0.1804442048072815
epoch: 78 training_loss 0.17545945279300212 test_loss: 0.1837286591529846
epoch: 79 training_loss 0.17702102087438107 test_loss: 0.18243961334228515
epoch: 80 training_loss 0.18061350755393504 test_loss: 0.18493237495422363
epoch: 81 training_loss 0.1753969981521368 test_loss: 0.1726193904876709
epoch: 82 training_loss 0.18025762885808944 test_loss: 0.17671624422073365
epoch: 83 training_loss 0.17246954552829266 test_loss: 0.17514538764953613
epoch: 84 training_loss 0.18312475584447385 test_loss: 0.17286664247512817
epoch: 85 training_loss 0.17310024857521056 test_loss: 0.18087501525878907
epoch: 86 training_loss 0.18436060704290866 test_loss: 0.1871053695678711
epoch: 87 training_loss 0.18031560473144054 test_loss: 0.1745997905731201
epoch: 88 training_loss 0.1634250891953707 test_loss: 0.17659224271774293
epoch: 89 training_loss 0.18317710556089878 test_loss: 0.18800607919692994
epoch: 90 training_loss 0.18220034874975682 test_loss: 0.1766802430152893
epoch: 91 training_loss 0.17515145644545554 test_loss: 0.16528210639953614
epoch: 92 training_loss 0.17663268826901912 test_loss: 0.17116861343383788
epoch: 93 training_loss 0.18427566327154637 test_loss: 0.17391003370285035
epoch: 94 training_loss 0.18084444776177405 test_loss: 0.17028852701187133
epoch: 95 training_loss 0.18341889627277852 test_loss: 0.19067193269729615
epoch: 96 training_loss 0.1861086268723011 test_loss: 0.18449804782867432
epoch: 97 training_loss 0.17676249012351036 test_loss: 0.18590477705001832
epoch: 98 training_loss 0.18333733946084976 test_loss: 0.18118284940719603
epoch: 99 training_loss 0.18227022081613542 test_loss: 0.1820010781288147
epoch: 100 training_loss 0.17754124999046325 test_loss: 0.16705034971237182
epoch: 101 training_loss 0.17710691697895528 test_loss: 0.1820901393890381
epoch: 102 training_loss 0.1747171475738287 test_loss: 0.17500590085983275
epoch: 103 training_loss 0.18361398123204709 test_loss: 0.1724295973777771
epoch: 104 training_loss 0.173041849732399 test_loss: 0.19022074937820435
epoch: 105 training_loss 0.16967643231153487 test_loss: 0.16862598657608033
epoch: 106 training_loss 0.17812130264937878 test_loss: 0.18367120027542114
epoch: 107 training_loss 0.1749314919859171 test_loss: 0.16852163076400756
epoch: 108 training_loss 0.17492686927318574 test_loss: 0.17973828315734863
epoch: 109 training_loss 0.1873565375059843 test_loss: 0.18428887128829957
epoch: 110 training_loss 0.1778895591199398 test_loss: 0.17683777809143067
epoch: 111 training_loss 0.17412304285913704 test_loss: 0.1853783369064331
epoch: 112 training_loss 0.18292853668332099 test_loss: 0.1756618618965149
epoch: 113 training_loss 0.1828492520749569 test_loss: 0.17456244230270385
epoch: 114 training_loss 0.17480474941432475 test_loss: 0.1607535481452942
epoch: 115 training_loss 0.17310078449547292 test_loss: 0.17695999145507812
epoch: 116 training_loss 0.17329661183059217 test_loss: 0.18291715383529664
epoch: 117 training_loss 0.18366153381764888 test_loss: 0.1778899073600769
epoch: 118 training_loss 0.17164554588496686 test_loss: 0.19697662591934204
epoch: 119 training_loss 0.1780094985663891 test_loss: 0.17258474826812745
epoch: 120 training_loss 0.1815790206938982 test_loss: 0.1811307907104492
epoch: 121 training_loss 0.17472765229642392 test_loss: 0.16757683753967284
epoch: 122 training_loss 0.17204821735620499 test_loss: 0.18073312044143677
epoch: 123 training_loss 0.1779782198369503 test_loss: 0.17136718034744264
epoch: 124 training_loss 0.17947597973048687 test_loss: 0.18027573823928833
epoch: 125 training_loss 0.17966934643685817 test_loss: 0.1851418733596802
epoch: 126 training_loss 0.1831515422463417 test_loss: 0.17442314624786376
epoch: 127 training_loss 0.18377284951508044 test_loss: 0.16899830102920532
epoch: 128 training_loss 0.17554213937371968 test_loss: 0.1772870182991028
epoch: 129 training_loss 0.17153861731290818 test_loss: 0.1847371816635132
epoch: 130 training_loss 0.1762193350493908 test_loss: 0.17111366987228394
epoch: 131 training_loss 0.17248802684247494 test_loss: 0.17239545583724974
epoch: 132 training_loss 0.176398409307003 test_loss: 0.17939989566802977
epoch: 133 training_loss 0.1893823567032814 test_loss: 0.16541459560394287
epoch: 134 training_loss 0.1837708945199847 test_loss: 0.187605881690979
epoch: 135 training_loss 0.17722032479941846 test_loss: 0.18973817825317382
epoch: 136 training_loss 0.1747472008317709 test_loss: 0.16736663579940797
epoch: 137 training_loss 0.17940923161804676 test_loss: 0.18023625612258912
epoch: 138 training_loss 0.18174324244260787 test_loss: 0.17692729234695434
epoch: 139 training_loss 0.17337063141167164 test_loss: 0.1783847451210022
epoch: 140 training_loss 0.17738432601094245 test_loss: 0.17093679904937745
epoch: 141 training_loss 0.1781317039579153 test_loss: 0.17187854051589965
epoch: 142 training_loss 0.1812636437267065 test_loss: 0.17851760387420654
epoch: 143 training_loss 0.1730171585455537 test_loss: 0.15701180696487427
epoch: 144 training_loss 0.17741027481853963 test_loss: 0.17310749292373656
epoch: 145 training_loss 0.17533926494419574 test_loss: 0.16683287620544435
epoch: 146 training_loss 0.17468440897762774 test_loss: 0.17510855197906494
epoch: 147 training_loss 0.17435135036706925 test_loss: 0.17881581783294678
epoch: 148 training_loss 0.18324000157415868 test_loss: 0.1765006184577942
epoch: 149 training_loss 0.17345755197107793 test_loss: 0.16478462219238282
epoch: 0 training_loss 8.592187304496765 test_loss: 5.076716613769531
epoch: 1 training_loss 3.831961054801941 test_loss: 2.9345209121704103
epoch: 2 training_loss 2.5646701192855836 test_loss: 2.188538360595703
epoch: 3 training_loss 2.013550418615341 test_loss: 1.8904905319213867
epoch: 4 training_loss 1.7130957794189454 test_loss: 1.5678724288940429
epoch: 5 training_loss 1.5581906938552856 test_loss: 1.4765249252319337
epoch: 6 training_loss 1.4385903751850129 test_loss: 1.35633544921875
epoch: 7 training_loss 1.313119568824768 test_loss: 1.3134628295898438
epoch: 8 training_loss 1.268496094942093 test_loss: 1.223017120361328
epoch: 9 training_loss 1.1599001312255859 test_loss: 1.1321917533874513
epoch: 10 training_loss 1.1189388209581375 test_loss: 1.0916531562805176
epoch: 11 training_loss 1.0657139140367509 test_loss: 1.0378506660461426
epoch: 12 training_loss 1.0340815955400466 test_loss: 1.0280290603637696
epoch: 13 training_loss 0.9899596589803695 test_loss: 0.9674333572387696
epoch: 14 training_loss 0.9761596709489823 test_loss: 0.9627724647521972
epoch: 15 training_loss 0.9412033206224442 test_loss: 0.9168618202209473
epoch: 16 training_loss 0.8962009292840958 test_loss: 0.9159221649169922
epoch: 17 training_loss 0.8882290357351303 test_loss: 0.8573521614074707
epoch: 18 training_loss 0.8676350367069244 test_loss: 0.8811121940612793
epoch: 19 training_loss 0.8599060690402984 test_loss: 0.8446328163146972
epoch: 20 training_loss 0.853255198597908 test_loss: 0.8624615669250488
epoch: 21 training_loss 0.8391439360380173 test_loss: 0.8112650871276855
epoch: 22 training_loss 0.8063851165771484 test_loss: 0.8313796997070313
epoch: 23 training_loss 0.8000070428848267 test_loss: 0.7947999477386475
epoch: 24 training_loss 0.7946090000867844 test_loss: 0.7787519931793213
epoch: 25 training_loss 0.7945099103450776 test_loss: 0.7779889583587647
epoch: 26 training_loss 0.7595403969287873 test_loss: 0.7739476203918457
epoch: 27 training_loss 0.7728781569004058 test_loss: 0.7483794689178467
epoch: 28 training_loss 0.7537659239768982 test_loss: 0.7382976531982421
epoch: 29 training_loss 0.738030936717987 test_loss: 0.7250121593475342
epoch: 30 training_loss 0.7270230638980866 test_loss: 0.7211917400360107
epoch: 31 training_loss 0.7204523140192032 test_loss: 0.7338024616241455
epoch: 32 training_loss 0.7199646466970444 test_loss: 0.7052656650543213
epoch: 33 training_loss 0.7016870874166489 test_loss: 0.702286958694458
epoch: 34 training_loss 0.701805071234703 test_loss: 0.7011594295501709
epoch: 35 training_loss 0.6958442974090576 test_loss: 0.7520276069641113
epoch: 36 training_loss 0.6925179392099381 test_loss: 0.6905605792999268
epoch: 37 training_loss 0.6831999754905701 test_loss: 0.7172718048095703
epoch: 38 training_loss 0.6821798855066299 test_loss: 0.6654672622680664
epoch: 39 training_loss 0.6767982894182205 test_loss: 0.6613316059112548
epoch: 40 training_loss 0.6635986328125 test_loss: 0.6493353366851806
epoch: 41 training_loss 0.6638273531198502 test_loss: 0.6546507358551026
epoch: 42 training_loss 0.649264065027237 test_loss: 0.6482338905334473
epoch: 43 training_loss 0.6617406630516052 test_loss: 0.6855846881866455
epoch: 44 training_loss 0.6511783224344253 test_loss: 0.6183093547821045
epoch: 45 training_loss 0.6379136192798615 test_loss: 0.6353908538818359
epoch: 46 training_loss 0.6435930269956589 test_loss: 0.6437551498413085
epoch: 47 training_loss 0.6423259687423706 test_loss: 0.6308570384979248
epoch: 48 training_loss 0.6335216307640076 test_loss: 0.6214435577392579
epoch: 49 training_loss 0.6232384532690048 test_loss: 0.6174436092376709
epoch: 50 training_loss 0.63410560131073 test_loss: 0.6072579383850097
epoch: 51 training_loss 0.6231625801324845 test_loss: 0.616513729095459
epoch: 52 training_loss 0.6363193202018738 test_loss: 0.6313232898712158
epoch: 53 training_loss 0.626084310412407 test_loss: 0.6294424057006835
epoch: 54 training_loss 0.6170344060659408 test_loss: 0.6018828868865966
epoch: 55 training_loss 0.6056562358140946 test_loss: 0.6094707012176513
epoch: 56 training_loss 0.6115846425294876 test_loss: 0.6055008411407471
epoch: 57 training_loss 0.6038497066497803 test_loss: 0.598483657836914
epoch: 58 training_loss 0.5978562235832214 test_loss: 0.6218760967254638
epoch: 59 training_loss 0.5957311236858368 test_loss: 0.5789176464080811
epoch: 60 training_loss 0.5977542120218277 test_loss: 0.6115562438964843
epoch: 61 training_loss 0.5939887678623199 test_loss: 0.5978906154632568
epoch: 62 training_loss 0.5833045083284378 test_loss: 0.5709170818328857
epoch: 63 training_loss 0.5868691313266754 test_loss: 0.5782436847686767
epoch: 64 training_loss 0.5936251014471055 test_loss: 0.5912649631500244
epoch: 65 training_loss 0.5766718155145645 test_loss: 0.5698092460632325
epoch: 66 training_loss 0.5847862750291825 test_loss: 0.5799797534942627
epoch: 67 training_loss 0.5832723510265351 test_loss: 0.6013394355773926
epoch: 68 training_loss 0.5748018527030945 test_loss: 0.5632992744445801
epoch: 69 training_loss 0.5648959571123123 test_loss: 0.5599853515625
epoch: 70 training_loss 0.576414247751236 test_loss: 0.5953780174255371
epoch: 71 training_loss 0.5713477814197541 test_loss: 0.5797142505645752
epoch: 72 training_loss 0.5681625121831894 test_loss: 0.582679033279419
epoch: 73 training_loss 0.564136125445366 test_loss: 0.5792512416839599
epoch: 74 training_loss 0.5665593069791793 test_loss: 0.5418965816497803
epoch: 75 training_loss 0.5710914361476899 test_loss: 0.5867623805999755
epoch: 76 training_loss 0.5634852802753448 test_loss: 0.5669357299804687
epoch: 77 training_loss 0.562404159605503 test_loss: 0.5431296348571777
epoch: 78 training_loss 0.5551502802968025 test_loss: 0.5770610332489013
epoch: 79 training_loss 0.5650143936276436 test_loss: 0.6090947151184082
epoch: 80 training_loss 0.5621360385417938 test_loss: 0.5686368465423584
epoch: 81 training_loss 0.5556655597686767 test_loss: 0.5590685367584228
epoch: 82 training_loss 0.5428077858686448 test_loss: 0.546047592163086
epoch: 83 training_loss 0.5400535503029823 test_loss: 0.5403514862060547
epoch: 84 training_loss 0.5635763686895371 test_loss: 0.5363155841827393
epoch: 85 training_loss 0.5525471067428589 test_loss: 0.5256734848022461
epoch: 86 training_loss 0.5371915724873543 test_loss: 0.5417829990386963
epoch: 87 training_loss 0.5499739533662796 test_loss: 0.5414260864257813
epoch: 88 training_loss 0.5494017952680588 test_loss: 0.5416923522949219
epoch: 89 training_loss 0.5436275851726532 test_loss: 0.5347232818603516
epoch: 90 training_loss 0.5371468842029572 test_loss: 0.542112922668457
epoch: 91 training_loss 0.538582994043827 test_loss: 0.5299972534179688
epoch: 92 training_loss 0.525780645608902 test_loss: 0.5306636810302734
epoch: 93 training_loss 0.5407860514521599 test_loss: 0.5265211582183837
epoch: 94 training_loss 0.5382973676919938 test_loss: 0.5291024208068847
epoch: 95 training_loss 0.5288214093446731 test_loss: 0.536130952835083
epoch: 96 training_loss 0.5291201767325401 test_loss: 0.5229684829711914
epoch: 97 training_loss 0.5419391474127769 test_loss: 0.5194239139556884
epoch: 98 training_loss 0.5263748970627785 test_loss: 0.5283244132995606
epoch: 99 training_loss 0.5275272533297539 test_loss: 0.5302725791931152
epoch: 100 training_loss 0.5225675868988037 test_loss: 0.5158702850341796
epoch: 101 training_loss 0.5226699030399322 test_loss: 0.5164238929748535
epoch: 102 training_loss 0.5238253965973854 test_loss: 0.5158414363861084
epoch: 103 training_loss 0.5277534860372544 test_loss: 0.5159470081329346
epoch: 104 training_loss 0.5212192675471305 test_loss: 0.5130172729492187
epoch: 105 training_loss 0.5258183526992798 test_loss: 0.5133046627044677
epoch: 106 training_loss 0.5176014277338982 test_loss: 0.5219585418701171
epoch: 107 training_loss 0.5274299198389053 test_loss: 0.5355668544769288
epoch: 108 training_loss 0.515718629360199 test_loss: 0.5163123130798339
epoch: 109 training_loss 0.5097967949509621 test_loss: 0.5046939373016357
epoch: 110 training_loss 0.5146277877688408 test_loss: 0.5177556991577148
epoch: 111 training_loss 0.5043881490826607 test_loss: 0.5073529243469238
epoch: 112 training_loss 0.5117332640290261 test_loss: 0.5301187992095947
epoch: 113 training_loss 0.5134703627228737 test_loss: 0.5157251834869385
epoch: 114 training_loss 0.5115443816781045 test_loss: 0.510753059387207
epoch: 115 training_loss 0.5122871646285057 test_loss: 0.5112967491149902
epoch: 116 training_loss 0.5036439713835716 test_loss: 0.4918802738189697
epoch: 117 training_loss 0.5044498631358146 test_loss: 0.49526205062866213
epoch: 118 training_loss 0.5096454676985741 test_loss: 0.5093252182006835
epoch: 119 training_loss 0.5117124542593956 test_loss: 0.49559588432312013
epoch: 120 training_loss 0.5043070486187935 test_loss: 0.5160509586334229
epoch: 121 training_loss 0.5019127395749092 test_loss: 0.5202634334564209
epoch: 122 training_loss 0.5067617756128311 test_loss: 0.49204206466674805
epoch: 123 training_loss 0.5049555277824402 test_loss: 0.49122419357299807
epoch: 124 training_loss 0.5082734921574592 test_loss: 0.508158540725708
epoch: 125 training_loss 0.5017602968215943 test_loss: 0.5165768623352051
epoch: 126 training_loss 0.5072980278730392 test_loss: 0.5024559497833252
epoch: 127 training_loss 0.4990459856390953 test_loss: 0.5133871555328369
epoch: 128 training_loss 0.5164151158928871 test_loss: 0.5120598793029785
epoch: 129 training_loss 0.49725775778293607 test_loss: 0.4969342231750488
epoch: 130 training_loss 0.49376414597034457 test_loss: 0.4974022388458252
epoch: 131 training_loss 0.4974181601405144 test_loss: 0.49732022285461425
epoch: 132 training_loss 0.49095051616430285 test_loss: 0.48809123039245605
epoch: 133 training_loss 0.5036843964457511 test_loss: 0.48107089996337893
epoch: 134 training_loss 0.49560547322034837 test_loss: 0.4967524528503418
epoch: 135 training_loss 0.49474334478378296 test_loss: 0.49324593544006345
epoch: 136 training_loss 0.4844249603152275 test_loss: 0.5060638427734375
epoch: 137 training_loss 0.4909837195277214 test_loss: 0.49899706840515134
epoch: 138 training_loss 0.4866666588187218 test_loss: 0.48576908111572265
epoch: 139 training_loss 0.49274568766355514 test_loss: 0.48372578620910645
epoch: 140 training_loss 0.4836041885614395 test_loss: 0.49029016494750977
epoch: 141 training_loss 0.493040032684803 test_loss: 0.5156026840209961
epoch: 142 training_loss 0.49823556214570996 test_loss: 0.48098039627075195
epoch: 143 training_loss 0.48560006558895114 test_loss: 0.5003944873809815
epoch: 144 training_loss 0.48144025474786756 test_loss: 0.4755910873413086
epoch: 145 training_loss 0.48528059750795366 test_loss: 0.47893261909484863
epoch: 146 training_loss 0.48071747422218325 test_loss: 0.48211822509765623
epoch: 147 training_loss 0.4904695552587509 test_loss: 0.4750950813293457
epoch: 148 training_loss 0.4797385808825493 test_loss: 0.5056300640106202
epoch: 149 training_loss 0.4793061912059784 test_loss: 0.4894861221313477
2593.377657120961
episode: 0 training return: tensor(163.6044, device='cuda:0')
episode: 1 training return: tensor(264.2770, device='cuda:0')
episode: 2 training return: tensor(-305.3953, device='cuda:0')
episode: 3 training return: tensor(-358.3237, device='cuda:0')
epoch: 1 test_true_pfm: 1823.5231346359085 sim_pfm: 148.8228607980806
episode: 4 training return: tensor(-364.1818, device='cuda:0')
episode: 5 training return: tensor(-311.8688, device='cuda:0')
episode: 6 training return: tensor(243.8552, device='cuda:0')
episode: 7 training return: tensor(-397.3045, device='cuda:0')
epoch: 2 test_true_pfm: 2304.5937754823813 sim_pfm: -159.56557370939603
episode: 8 training return: tensor(-400.7170, device='cuda:0')
episode: 9 training return: tensor(-358.3548, device='cuda:0')
episode: 10 training return: tensor(-416.7552, device='cuda:0')
episode: 11 training return: tensor(-313.7611, device='cuda:0')
epoch: 3 test_true_pfm: 2021.684740509843 sim_pfm: -51.100753555161646
episode: 12 training return: tensor(-390.9616, device='cuda:0')
episode: 13 training return: tensor(-306.6473, device='cuda:0')
episode: 14 training return: tensor(-383.9153, device='cuda:0')
episode: 15 training return: tensor(-292.9582, device='cuda:0')
epoch: 4 test_true_pfm: 1512.280732264804 sim_pfm: -327.51652097783517
episode: 16 training return: tensor(144.3631, device='cuda:0')
episode: 17 training return: tensor(-145.9296, device='cuda:0')
episode: 18 training return: tensor(-358.8029, device='cuda:0')
episode: 19 training return: tensor(-402.6846, device='cuda:0')
epoch: 5 test_true_pfm: 1742.637858546915 sim_pfm: -313.19536285098485
episode: 20 training return: tensor(274.1551, device='cuda:0')
episode: 21 training return: tensor(-140.7018, device='cuda:0')
episode: 22 training return: tensor(303.3322, device='cuda:0')
episode: 23 training return: tensor(-322.2445, device='cuda:0')
epoch: 6 test_true_pfm: 2660.305758908233 sim_pfm: -159.39827004517429
episode: 24 training return: tensor(-136.7026, device='cuda:0')
episode: 25 training return: tensor(-307.3989, device='cuda:0')
episode: 26 training return: tensor(-399.0003, device='cuda:0')
episode: 27 training return: tensor(201.4690, device='cuda:0')
epoch: 7 test_true_pfm: 2143.8564059157784 sim_pfm: -331.9517589082437
episode: 28 training return: tensor(-223.4419, device='cuda:0')
episode: 29 training return: tensor(-310.3214, device='cuda:0')
episode: 30 training return: tensor(-401.7188, device='cuda:0')
episode: 31 training return: tensor(-212.5461, device='cuda:0')
epoch: 8 test_true_pfm: 2608.771840876053 sim_pfm: 144.88043617958706
episode: 32 training return: tensor(72.7910, device='cuda:0')
episode: 33 training return: tensor(-394.9802, device='cuda:0')
episode: 34 training return: tensor(-88.1213, device='cuda:0')
episode: 35 training return: tensor(-81.1776, device='cuda:0')
epoch: 9 test_true_pfm: 2337.277309430363 sim_pfm: -18.404053405703355
episode: 36 training return: tensor(-279.3421, device='cuda:0')
episode: 37 training return: tensor(-316.2507, device='cuda:0')
episode: 38 training return: tensor(86.5500, device='cuda:0')
episode: 39 training return: tensor(-298.9167, device='cuda:0')
epoch: 10 test_true_pfm: 2043.2358675800845 sim_pfm: -137.97820753037618
episode: 40 training return: tensor(-391.7661, device='cuda:0')
episode: 41 training return: tensor(-45.7505, device='cuda:0')
episode: 42 training return: tensor(-272.4245, device='cuda:0')
episode: 43 training return: tensor(-370.5167, device='cuda:0')
epoch: 11 test_true_pfm: 1450.674875955152 sim_pfm: -261.57957012124825
episode: 44 training return: tensor(-25.2051, device='cuda:0')
episode: 45 training return: tensor(257.8190, device='cuda:0')
episode: 46 training return: tensor(137.2940, device='cuda:0')
episode: 47 training return: tensor(118.8034, device='cuda:0')
epoch: 12 test_true_pfm: 2046.2205004133066 sim_pfm: -298.73276266162674
episode: 48 training return: tensor(-364.5689, device='cuda:0')
episode: 49 training return: tensor(240.4676, device='cuda:0')
episode: 50 training return: tensor(38.2863, device='cuda:0')
episode: 51 training return: tensor(-407.0459, device='cuda:0')
epoch: 13 test_true_pfm: 2234.3078847343436 sim_pfm: -339.7241876739038
episode: 52 training return: tensor(-300.5854, device='cuda:0')
episode: 53 training return: tensor(277.4718, device='cuda:0')
episode: 54 training return: tensor(-123.6226, device='cuda:0')
episode: 55 training return: tensor(254.0576, device='cuda:0')
epoch: 14 test_true_pfm: 2942.3485000216156 sim_pfm: -304.1591068528166
episode: 56 training return: tensor(-364.7753, device='cuda:0')
episode: 57 training return: tensor(216.0924, device='cuda:0')
episode: 58 training return: tensor(-393.4677, device='cuda:0')
episode: 59 training return: tensor(6.7013, device='cuda:0')
epoch: 15 test_true_pfm: 2731.829164526935 sim_pfm: -7.7786430632210495
episode: 60 training return: tensor(-195.2955, device='cuda:0')
episode: 61 training return: tensor(267.2238, device='cuda:0')
episode: 62 training return: tensor(-2.6019, device='cuda:0')
episode: 63 training return: tensor(-391.7610, device='cuda:0')
epoch: 16 test_true_pfm: 1928.4098643401092 sim_pfm: 266.8626949960599
episode: 64 training return: tensor(-322.3178, device='cuda:0')
episode: 65 training return: tensor(-385.6611, device='cuda:0')
episode: 66 training return: tensor(-139.6187, device='cuda:0')
episode: 67 training return: tensor(-359.0475, device='cuda:0')
epoch: 17 test_true_pfm: 2390.7589795891886 sim_pfm: 158.06904165440938
episode: 68 training return: tensor(-108.9776, device='cuda:0')
episode: 69 training return: tensor(-355.5041, device='cuda:0')
episode: 70 training return: tensor(-309.0668, device='cuda:0')
episode: 71 training return: tensor(-397.3701, device='cuda:0')
epoch: 18 test_true_pfm: 1925.825627743962 sim_pfm: 123.66681420610014
episode: 72 training return: tensor(247.7391, device='cuda:0')
episode: 73 training return: tensor(-218.2718, device='cuda:0')
episode: 74 training return: tensor(-115.9691, device='cuda:0')
episode: 75 training return: tensor(-366.9727, device='cuda:0')
epoch: 19 test_true_pfm: 2737.433626992575 sim_pfm: -63.3737832159483
episode: 76 training return: tensor(-224.1660, device='cuda:0')
episode: 77 training return: tensor(-336.9525, device='cuda:0')
episode: 78 training return: tensor(220.0604, device='cuda:0')
episode: 79 training return: tensor(-229.8643, device='cuda:0')
epoch: 20 test_true_pfm: 3012.49338605975 sim_pfm: -16.36871659362805
episode: 80 training return: tensor(-83.5609, device='cuda:0')
episode: 81 training return: tensor(128.6120, device='cuda:0')
episode: 82 training return: tensor(-228.9071, device='cuda:0')
episode: 83 training return: tensor(-355.2784, device='cuda:0')
epoch: 21 test_true_pfm: 2855.2526360863844 sim_pfm: 47.43363909830805
episode: 84 training return: tensor(254.1766, device='cuda:0')
episode: 85 training return: tensor(-301.1780, device='cuda:0')
episode: 86 training return: tensor(45.8138, device='cuda:0')
episode: 87 training return: tensor(-324.8011, device='cuda:0')
epoch: 22 test_true_pfm: 2059.7964569809683 sim_pfm: -31.409114619678196
episode: 88 training return: tensor(328.8243, device='cuda:0')
episode: 89 training return: tensor(-319.3565, device='cuda:0')
episode: 90 training return: tensor(297.8699, device='cuda:0')
episode: 91 training return: tensor(298.4010, device='cuda:0')
epoch: 23 test_true_pfm: 2122.6888399433815 sim_pfm: -36.90034983625325
episode: 92 training return: tensor(75.5857, device='cuda:0')
episode: 93 training return: tensor(229.3207, device='cuda:0')
episode: 94 training return: tensor(-397.1139, device='cuda:0')
episode: 95 training return: tensor(-117.0796, device='cuda:0')
epoch: 24 test_true_pfm: 2399.3769224892117 sim_pfm: -12.903162353866113
episode: 96 training return: tensor(268.9802, device='cuda:0')
episode: 97 training return: tensor(155.5720, device='cuda:0')
episode: 98 training return: tensor(-400.3908, device='cuda:0')
episode: 99 training return: tensor(-154.5689, device='cuda:0')
epoch: 25 test_true_pfm: 2724.714067911294 sim_pfm: -84.95095089125486
episode: 100 training return: tensor(248.4742, device='cuda:0')
episode: 101 training return: tensor(-354.4315, device='cuda:0')
episode: 102 training return: tensor(237.1275, device='cuda:0')
episode: 103 training return: tensor(-346.9848, device='cuda:0')
epoch: 26 test_true_pfm: 1964.1745832804438 sim_pfm: 284.23109346959
episode: 104 training return: tensor(-356.3292, device='cuda:0')
episode: 105 training return: tensor(-134.6691, device='cuda:0')
episode: 106 training return: tensor(-303.4969, device='cuda:0')
episode: 107 training return: tensor(-292.9021, device='cuda:0')
epoch: 27 test_true_pfm: 2009.5547118622344 sim_pfm: -10.601603714283556
episode: 108 training return: tensor(-396.2980, device='cuda:0')
episode: 109 training return: tensor(-111.0456, device='cuda:0')
episode: 110 training return: tensor(258.3352, device='cuda:0')
episode: 111 training return: tensor(-124.9916, device='cuda:0')
epoch: 28 test_true_pfm: 2130.1660603617547 sim_pfm: -222.3729296073046
episode: 112 training return: tensor(-310.0979, device='cuda:0')
episode: 113 training return: tensor(174.1734, device='cuda:0')
episode: 114 training return: tensor(-305.6801, device='cuda:0')
episode: 115 training return: tensor(257.9937, device='cuda:0')
epoch: 29 test_true_pfm: 2564.0837975806426 sim_pfm: -49.775912382775765
episode: 116 training return: tensor(-40.2504, device='cuda:0')
episode: 117 training return: tensor(9.3313, device='cuda:0')
episode: 118 training return: tensor(-271.3040, device='cuda:0')
episode: 119 training return: tensor(178.6927, device='cuda:0')
epoch: 30 test_true_pfm: 1896.9569341594154 sim_pfm: 54.84175559718278
episode: 120 training return: tensor(72.7749, device='cuda:0')
episode: 121 training return: tensor(250.6980, device='cuda:0')
episode: 122 training return: tensor(-95.1978, device='cuda:0')
episode: 123 training return: tensor(-298.4201, device='cuda:0')
epoch: 31 test_true_pfm: 3027.1248790831687 sim_pfm: 63.925412103291215
episode: 124 training return: tensor(245.0508, device='cuda:0')
episode: 125 training return: tensor(255.1814, device='cuda:0')
episode: 126 training return: tensor(-289.1208, device='cuda:0')
episode: 127 training return: tensor(-359.7689, device='cuda:0')
epoch: 32 test_true_pfm: 2716.152751971951 sim_pfm: 12.144785919381926
episode: 128 training return: tensor(-5.3364, device='cuda:0')
episode: 129 training return: tensor(243.7592, device='cuda:0')
episode: 130 training return: tensor(-392.2940, device='cuda:0')
episode: 131 training return: tensor(183.8872, device='cuda:0')
epoch: 33 test_true_pfm: 2288.9963955361222 sim_pfm: -141.31889076162284
episode: 132 training return: tensor(-387.8652, device='cuda:0')
episode: 133 training return: tensor(-195.4344, device='cuda:0')
episode: 134 training return: tensor(-314.8332, device='cuda:0')
episode: 135 training return: tensor(-136.3905, device='cuda:0')
epoch: 34 test_true_pfm: 2892.809720651228 sim_pfm: -129.54387057043883
episode: 136 training return: tensor(-132.8420, device='cuda:0')
episode: 137 training return: tensor(-302.6240, device='cuda:0')
episode: 138 training return: tensor(-391.2592, device='cuda:0')
episode: 139 training return: tensor(-283.3380, device='cuda:0')
epoch: 35 test_true_pfm: 2759.391834338026 sim_pfm: 11.062440589642696
episode: 140 training return: tensor(241.5728, device='cuda:0')
episode: 141 training return: tensor(149.5685, device='cuda:0')
episode: 142 training return: tensor(-279.7067, device='cuda:0')
episode: 143 training return: tensor(-242.3481, device='cuda:0')
epoch: 36 test_true_pfm: 2449.2830887684763 sim_pfm: 135.60388434192282
episode: 144 training return: tensor(124.3177, device='cuda:0')
episode: 145 training return: tensor(-37.3339, device='cuda:0')
episode: 146 training return: tensor(248.2549, device='cuda:0')
episode: 147 training return: tensor(-284.8792, device='cuda:0')
epoch: 37 test_true_pfm: 2896.3634538548486 sim_pfm: -134.1659391578966
episode: 148 training return: tensor(-368.6322, device='cuda:0')
episode: 149 training return: tensor(-384.7292, device='cuda:0')
episode: 150 training return: tensor(-331.2138, device='cuda:0')
episode: 151 training return: tensor(-151.2775, device='cuda:0')
epoch: 38 test_true_pfm: 2907.521864628059 sim_pfm: -220.7687028403161
episode: 152 training return: tensor(-86.9156, device='cuda:0')
episode: 153 training return: tensor(-277.9435, device='cuda:0')
episode: 154 training return: tensor(-353.3755, device='cuda:0')
episode: 155 training return: tensor(-323.1145, device='cuda:0')
epoch: 39 test_true_pfm: 1907.9306231933276 sim_pfm: 130.14048122478803
episode: 156 training return: tensor(4.8295, device='cuda:0')
episode: 157 training return: tensor(247.4465, device='cuda:0')
episode: 158 training return: tensor(-267.9568, device='cuda:0')
episode: 159 training return: tensor(-302.2998, device='cuda:0')
epoch: 40 test_true_pfm: 3060.5500484370555 sim_pfm: -95.7805662001095
episode: 160 training return: tensor(60.5079, device='cuda:0')
episode: 161 training return: tensor(-326.6226, device='cuda:0')
episode: 162 training return: tensor(-180.8752, device='cuda:0')
episode: 163 training return: tensor(-40.3764, device='cuda:0')
epoch: 41 test_true_pfm: 2703.4792210245796 sim_pfm: -234.5298746896054
episode: 164 training return: tensor(-340.5702, device='cuda:0')
episode: 165 training return: tensor(-352.5150, device='cuda:0')
episode: 166 training return: tensor(-347.1453, device='cuda:0')
episode: 167 training return: tensor(-125.3554, device='cuda:0')
epoch: 42 test_true_pfm: 1627.6301488275114 sim_pfm: -55.08384911726656
episode: 168 training return: tensor(-101.0243, device='cuda:0')
episode: 169 training return: tensor(-145.3647, device='cuda:0')
episode: 170 training return: tensor(-309.1267, device='cuda:0')
episode: 171 training return: tensor(20.3549, device='cuda:0')
epoch: 43 test_true_pfm: 3253.4816256729014 sim_pfm: 174.79814930838378
episode: 172 training return: tensor(-132.2486, device='cuda:0')
episode: 173 training return: tensor(12.0678, device='cuda:0')
episode: 174 training return: tensor(-68.6535, device='cuda:0')
episode: 175 training return: tensor(-236.5682, device='cuda:0')
epoch: 44 test_true_pfm: 2347.9498412504176 sim_pfm: -309.2894133649922
episode: 176 training return: tensor(84.2744, device='cuda:0')
episode: 177 training return: tensor(3.1325, device='cuda:0')
episode: 178 training return: tensor(-315.7633, device='cuda:0')
episode: 179 training return: tensor(-341.2548, device='cuda:0')
epoch: 45 test_true_pfm: 3264.697909928662 sim_pfm: 134.3821346538995
episode: 180 training return: tensor(11.3251, device='cuda:0')
episode: 181 training return: tensor(-249.0223, device='cuda:0')
episode: 182 training return: tensor(-27.8567, device='cuda:0')
episode: 183 training return: tensor(-276.4914, device='cuda:0')
epoch: 46 test_true_pfm: 3015.6918695864188 sim_pfm: 67.42419160780264
episode: 184 training return: tensor(-107.0949, device='cuda:0')
episode: 185 training return: tensor(40.7978, device='cuda:0')
episode: 186 training return: tensor(-67.8030, device='cuda:0')
episode: 187 training return: tensor(-97.4405, device='cuda:0')
epoch: 47 test_true_pfm: 2969.9868787432138 sim_pfm: -102.38047117225749
episode: 188 training return: tensor(260.3474, device='cuda:0')
episode: 189 training return: tensor(246.6866, device='cuda:0')
episode: 190 training return: tensor(53.1651, device='cuda:0')
episode: 191 training return: tensor(-23.4634, device='cuda:0')
epoch: 48 test_true_pfm: 2145.523391607508 sim_pfm: -54.22697554453043
episode: 192 training return: tensor(48.7800, device='cuda:0')
episode: 193 training return: tensor(-338.5351, device='cuda:0')
episode: 194 training return: tensor(42.1888, device='cuda:0')
episode: 195 training return: tensor(-119.6876, device='cuda:0')
epoch: 49 test_true_pfm: 1683.5093219513149 sim_pfm: -128.02001655109538
episode: 196 training return: tensor(-257.7906, device='cuda:0')
episode: 197 training return: tensor(-110.4903, device='cuda:0')
episode: 198 training return: tensor(-352.9709, device='cuda:0')
episode: 199 training return: tensor(-348.8058, device='cuda:0')
epoch: 50 test_true_pfm: 3057.1126025105636 sim_pfm: 181.10493090360737
episode: 200 training return: tensor(-350.7452, device='cuda:0')
episode: 201 training return: tensor(-392.6366, device='cuda:0')
episode: 202 training return: tensor(-383.9069, device='cuda:0')
episode: 203 training return: tensor(-299.4886, device='cuda:0')
epoch: 51 test_true_pfm: 1964.5625191736024 sim_pfm: 126.1515804239704
episode: 204 training return: tensor(-252.6716, device='cuda:0')
episode: 205 training return: tensor(-223.3136, device='cuda:0')
episode: 206 training return: tensor(-346.0009, device='cuda:0')
episode: 207 training return: tensor(41.0063, device='cuda:0')
epoch: 52 test_true_pfm: 2521.285777964407 sim_pfm: -52.95835222682217
episode: 208 training return: tensor(-346.4498, device='cuda:0')
episode: 209 training return: tensor(-364.5930, device='cuda:0')
episode: 210 training return: tensor(-35.1471, device='cuda:0')
episode: 211 training return: tensor(215.9471, device='cuda:0')
epoch: 53 test_true_pfm: 2825.224576334274 sim_pfm: 166.53879139417162
episode: 212 training return: tensor(263.3538, device='cuda:0')
episode: 213 training return: tensor(9.1873, device='cuda:0')
episode: 214 training return: tensor(-220.5896, device='cuda:0')
episode: 215 training return: tensor(73.4594, device='cuda:0')
epoch: 54 test_true_pfm: 2877.65394416373 sim_pfm: 63.71843667453504
episode: 216 training return: tensor(-306.7596, device='cuda:0')
episode: 217 training return: tensor(2.3794, device='cuda:0')
episode: 218 training return: tensor(-157.2131, device='cuda:0')
episode: 219 training return: tensor(-347.2289, device='cuda:0')
epoch: 55 test_true_pfm: 2441.9962584238297 sim_pfm: -110.13874050047404
episode: 220 training return: tensor(-334.4320, device='cuda:0')
episode: 221 training return: tensor(-320.7170, device='cuda:0')
episode: 222 training return: tensor(-299.0438, device='cuda:0')
episode: 223 training return: tensor(-128.8423, device='cuda:0')
epoch: 56 test_true_pfm: 2167.1073087554523 sim_pfm: -203.009657347342
episode: 224 training return: tensor(248.0032, device='cuda:0')
episode: 225 training return: tensor(239.1669, device='cuda:0')
episode: 226 training return: tensor(-230.4309, device='cuda:0')
episode: 227 training return: tensor(246.4726, device='cuda:0')
epoch: 57 test_true_pfm: 1902.1999367326614 sim_pfm: -6.652504625351867
episode: 228 training return: tensor(-379.5075, device='cuda:0')
episode: 229 training return: tensor(-352.5015, device='cuda:0')
episode: 230 training return: tensor(-376.8656, device='cuda:0')
episode: 231 training return: tensor(-74.8373, device='cuda:0')
epoch: 58 test_true_pfm: 2080.04668724088 sim_pfm: -12.409358701979121
episode: 232 training return: tensor(33.7108, device='cuda:0')
episode: 233 training return: tensor(-134.3960, device='cuda:0')
episode: 234 training return: tensor(247.9537, device='cuda:0')
episode: 235 training return: tensor(-394.8629, device='cuda:0')
epoch: 59 test_true_pfm: 2981.915730860978 sim_pfm: -123.30786730184143
episode: 236 training return: tensor(-306.7522, device='cuda:0')
episode: 237 training return: tensor(-386.6411, device='cuda:0')
episode: 238 training return: tensor(-91.3089, device='cuda:0')
episode: 239 training return: tensor(-287.2505, device='cuda:0')
epoch: 60 test_true_pfm: 2176.4700926480996 sim_pfm: 14.62461395689752
episode: 240 training return: tensor(-393.6278, device='cuda:0')
episode: 241 training return: tensor(254.8707, device='cuda:0')
episode: 242 training return: tensor(-335.1509, device='cuda:0')
episode: 243 training return: tensor(-135.7952, device='cuda:0')
epoch: 61 test_true_pfm: 2121.4149871009217 sim_pfm: 18.825476589185808
episode: 244 training return: tensor(251.4714, device='cuda:0')
episode: 245 training return: tensor(-240.4780, device='cuda:0')
episode: 246 training return: tensor(-380.3655, device='cuda:0')
episode: 247 training return: tensor(252.2190, device='cuda:0')
epoch: 62 test_true_pfm: 2628.3456591594218 sim_pfm: -173.9855547157737
episode: 248 training return: tensor(-303.0049, device='cuda:0')
episode: 249 training return: tensor(-423.5686, device='cuda:0')
episode: 250 training return: tensor(300.5801, device='cuda:0')
episode: 251 training return: tensor(146.8563, device='cuda:0')
epoch: 63 test_true_pfm: 2499.0338017936606 sim_pfm: -267.18905797438737
episode: 252 training return: tensor(265.3778, device='cuda:0')
episode: 253 training return: tensor(-313.4705, device='cuda:0')
episode: 254 training return: tensor(260.1320, device='cuda:0')
episode: 255 training return: tensor(-305.8969, device='cuda:0')
epoch: 64 test_true_pfm: 1481.7355942225006 sim_pfm: -91.6285563284764
episode: 256 training return: tensor(256.8499, device='cuda:0')
episode: 257 training return: tensor(239.2015, device='cuda:0')
episode: 258 training return: tensor(-73.0648, device='cuda:0')
episode: 259 training return: tensor(-48.1628, device='cuda:0')
epoch: 65 test_true_pfm: 2409.510021759461 sim_pfm: -196.5943626765317
episode: 260 training return: tensor(-399.2198, device='cuda:0')
episode: 261 training return: tensor(298.0153, device='cuda:0')
episode: 262 training return: tensor(-66.7163, device='cuda:0')
episode: 263 training return: tensor(18.4926, device='cuda:0')
epoch: 66 test_true_pfm: 1547.1924687536582 sim_pfm: 145.19933299120748
episode: 264 training return: tensor(-301.0301, device='cuda:0')
episode: 265 training return: tensor(-213.7549, device='cuda:0')
episode: 266 training return: tensor(-206.3583, device='cuda:0')
episode: 267 training return: tensor(160.6837, device='cuda:0')
epoch: 67 test_true_pfm: 2072.4204469126084 sim_pfm: -148.2300675274649
episode: 268 training return: tensor(-257.6362, device='cuda:0')
episode: 269 training return: tensor(-354.8083, device='cuda:0')
episode: 270 training return: tensor(-289.4179, device='cuda:0')
episode: 271 training return: tensor(122.0937, device='cuda:0')
epoch: 68 test_true_pfm: 2780.1084358976454 sim_pfm: -171.45227185447584
episode: 272 training return: tensor(256.9125, device='cuda:0')
episode: 273 training return: tensor(-396.5947, device='cuda:0')
episode: 274 training return: tensor(-317.9379, device='cuda:0')
episode: 275 training return: tensor(-279.4728, device='cuda:0')
epoch: 69 test_true_pfm: 2144.896361796427 sim_pfm: -111.34560483099388
episode: 276 training return: tensor(149.5503, device='cuda:0')
episode: 277 training return: tensor(249.8275, device='cuda:0')
episode: 278 training return: tensor(-272.9877, device='cuda:0')
episode: 279 training return: tensor(212.2302, device='cuda:0')
epoch: 70 test_true_pfm: 2860.163626980724 sim_pfm: 66.03926020529859
episode: 280 training return: tensor(-280.9852, device='cuda:0')
episode: 281 training return: tensor(67.2842, device='cuda:0')
episode: 282 training return: tensor(110.0049, device='cuda:0')
episode: 283 training return: tensor(296.4926, device='cuda:0')
epoch: 71 test_true_pfm: 2090.7559718646007 sim_pfm: 250.25964144363147
episode: 284 training return: tensor(152.7000, device='cuda:0')
episode: 285 training return: tensor(295.6425, device='cuda:0')
episode: 286 training return: tensor(35.1338, device='cuda:0')
episode: 287 training return: tensor(-29.3395, device='cuda:0')
epoch: 72 test_true_pfm: 3065.6425761432797 sim_pfm: -130.9334680631291
episode: 288 training return: tensor(-116.1349, device='cuda:0')
episode: 289 training return: tensor(187.6129, device='cuda:0')
episode: 290 training return: tensor(-90.1410, device='cuda:0')
episode: 291 training return: tensor(-111.7865, device='cuda:0')
epoch: 73 test_true_pfm: 2173.676437566815 sim_pfm: 17.018418842887815
episode: 292 training return: tensor(-283.2708, device='cuda:0')
episode: 293 training return: tensor(259.1199, device='cuda:0')
episode: 294 training return: tensor(-393.8696, device='cuda:0')
episode: 295 training return: tensor(231.2005, device='cuda:0')
epoch: 74 test_true_pfm: 1608.4765359902974 sim_pfm: -95.87412875448354
episode: 296 training return: tensor(-331.9936, device='cuda:0')
episode: 297 training return: tensor(-224.4228, device='cuda:0')
episode: 298 training return: tensor(-383.6275, device='cuda:0')
episode: 299 training return: tensor(294.9173, device='cuda:0')
epoch: 75 test_true_pfm: 2705.472754398213 sim_pfm: 144.78017089295705
episode: 300 training return: tensor(-3.1124, device='cuda:0')
episode: 301 training return: tensor(-384.2644, device='cuda:0')
episode: 302 training return: tensor(-379.5793, device='cuda:0')
episode: 303 training return: tensor(157.2316, device='cuda:0')
epoch: 76 test_true_pfm: 2448.5919908449055 sim_pfm: -314.3227561535411
episode: 304 training return: tensor(252.3933, device='cuda:0')
episode: 305 training return: tensor(280.5051, device='cuda:0')
episode: 306 training return: tensor(-393.0537, device='cuda:0')
episode: 307 training return: tensor(-80.2833, device='cuda:0')
epoch: 77 test_true_pfm: 2244.798019953285 sim_pfm: -211.9692723323436
episode: 308 training return: tensor(-310.7090, device='cuda:0')
episode: 309 training return: tensor(-391.8047, device='cuda:0')
episode: 310 training return: tensor(-289.7718, device='cuda:0')
episode: 311 training return: tensor(-357.2676, device='cuda:0')
epoch: 78 test_true_pfm: 1537.9439806755538 sim_pfm: -125.95995399311262
episode: 312 training return: tensor(-303.4377, device='cuda:0')
episode: 313 training return: tensor(245.5843, device='cuda:0')
episode: 314 training return: tensor(-398.8316, device='cuda:0')
episode: 315 training return: tensor(174.5749, device='cuda:0')
epoch: 79 test_true_pfm: 1948.378892447582 sim_pfm: -288.8255685230154
episode: 316 training return: tensor(-279.9161, device='cuda:0')
episode: 317 training return: tensor(-366.6369, device='cuda:0')
episode: 318 training return: tensor(-307.1560, device='cuda:0')
episode: 319 training return: tensor(-116.9865, device='cuda:0')
epoch: 80 test_true_pfm: 1970.8123303028121 sim_pfm: -99.5331942414341
episode: 320 training return: tensor(-154.2037, device='cuda:0')
episode: 321 training return: tensor(-273.7235, device='cuda:0')
episode: 322 training return: tensor(263.9683, device='cuda:0')
episode: 323 training return: tensor(-34.0395, device='cuda:0')
epoch: 81 test_true_pfm: 2159.0594548681934 sim_pfm: -169.7045904979265
episode: 324 training return: tensor(-292.3120, device='cuda:0')
episode: 325 training return: tensor(-236.4692, device='cuda:0')
episode: 326 training return: tensor(-347.2247, device='cuda:0')
episode: 327 training return: tensor(-306.7905, device='cuda:0')
epoch: 82 test_true_pfm: 2534.3374964814057 sim_pfm: 67.99144149309723
episode: 328 training return: tensor(-51.9536, device='cuda:0')
episode: 329 training return: tensor(-308.5190, device='cuda:0')
episode: 330 training return: tensor(-397.8481, device='cuda:0')
episode: 331 training return: tensor(-200.0766, device='cuda:0')
epoch: 83 test_true_pfm: 2149.7035704121413 sim_pfm: -82.11623076799636
episode: 332 training return: tensor(157.9187, device='cuda:0')
episode: 333 training return: tensor(-216.8465, device='cuda:0')
episode: 334 training return: tensor(-392.6256, device='cuda:0')
episode: 335 training return: tensor(259.3242, device='cuda:0')
epoch: 84 test_true_pfm: 2599.29465718428 sim_pfm: -162.30797573497208
episode: 336 training return: tensor(-50.1993, device='cuda:0')
episode: 337 training return: tensor(-304.0806, device='cuda:0')
episode: 338 training return: tensor(114.5430, device='cuda:0')
episode: 339 training return: tensor(-231.1928, device='cuda:0')
epoch: 85 test_true_pfm: 2703.8534825103857 sim_pfm: -93.54486295054085
episode: 340 training return: tensor(249.2089, device='cuda:0')
episode: 341 training return: tensor(-344.5943, device='cuda:0')
episode: 342 training return: tensor(-279.5927, device='cuda:0')
episode: 343 training return: tensor(34.6679, device='cuda:0')
epoch: 86 test_true_pfm: 1658.2074511721241 sim_pfm: -118.57005400862545
episode: 344 training return: tensor(-395.1656, device='cuda:0')
episode: 345 training return: tensor(-298.8792, device='cuda:0')
episode: 346 training return: tensor(294.6338, device='cuda:0')
episode: 347 training return: tensor(-341.7542, device='cuda:0')
epoch: 87 test_true_pfm: 2575.0144263567 sim_pfm: -146.85002551150197
episode: 348 training return: tensor(212.2928, device='cuda:0')
episode: 349 training return: tensor(-394.7832, device='cuda:0')
episode: 350 training return: tensor(-42.1808, device='cuda:0')
episode: 351 training return: tensor(-100.2841, device='cuda:0')
epoch: 88 test_true_pfm: 2090.143153513308 sim_pfm: 58.06163113139337
episode: 352 training return: tensor(-396.7703, device='cuda:0')
episode: 353 training return: tensor(-397.5199, device='cuda:0')
episode: 354 training return: tensor(-351.1480, device='cuda:0')
episode: 355 training return: tensor(-143.7703, device='cuda:0')
epoch: 89 test_true_pfm: 1675.5270500939089 sim_pfm: 44.445275600339905
episode: 356 training return: tensor(-227.9126, device='cuda:0')
episode: 357 training return: tensor(295.1104, device='cuda:0')
episode: 358 training return: tensor(-34.3694, device='cuda:0')
episode: 359 training return: tensor(-108.4712, device='cuda:0')
epoch: 90 test_true_pfm: 1595.5568501732578 sim_pfm: 25.964568020698305
episode: 360 training return: tensor(-392.5291, device='cuda:0')
episode: 361 training return: tensor(-381.2241, device='cuda:0')
episode: 362 training return: tensor(-133.9568, device='cuda:0')
episode: 363 training return: tensor(-253.3738, device='cuda:0')
epoch: 91 test_true_pfm: 2081.49154787947 sim_pfm: -263.7817733453315
episode: 364 training return: tensor(-340.4139, device='cuda:0')
episode: 365 training return: tensor(70.6138, device='cuda:0')
episode: 366 training return: tensor(-305.9877, device='cuda:0')
episode: 367 training return: tensor(110.7776, device='cuda:0')
epoch: 92 test_true_pfm: 2482.7235052335054 sim_pfm: 275.28319635797135
episode: 368 training return: tensor(263.6698, device='cuda:0')
episode: 369 training return: tensor(-229.2577, device='cuda:0')
episode: 370 training return: tensor(-395.1296, device='cuda:0')
episode: 371 training return: tensor(-370.4814, device='cuda:0')
epoch: 93 test_true_pfm: 3210.144704850319 sim_pfm: -101.81662889601041
episode: 372 training return: tensor(268.1303, device='cuda:0')
episode: 373 training return: tensor(-372.5027, device='cuda:0')
episode: 374 training return: tensor(-59.3525, device='cuda:0')
episode: 375 training return: tensor(242.6297, device='cuda:0')
epoch: 94 test_true_pfm: 2713.359058091191 sim_pfm: -114.18112471267038
episode: 376 training return: tensor(-246.7487, device='cuda:0')
episode: 377 training return: tensor(-382.1436, device='cuda:0')
episode: 378 training return: tensor(278.3372, device='cuda:0')
episode: 379 training return: tensor(-388.8174, device='cuda:0')
epoch: 95 test_true_pfm: 2140.151977809398 sim_pfm: -16.12263564701425
episode: 380 training return: tensor(239.1957, device='cuda:0')
episode: 381 training return: tensor(-266.5127, device='cuda:0')
episode: 382 training return: tensor(-302.1675, device='cuda:0')
episode: 383 training return: tensor(-309.5617, device='cuda:0')
epoch: 96 test_true_pfm: 2469.749499694591 sim_pfm: 75.13482464918827
episode: 384 training return: tensor(250.8687, device='cuda:0')
episode: 385 training return: tensor(164.4502, device='cuda:0')
episode: 386 training return: tensor(224.6910, device='cuda:0')
episode: 387 training return: tensor(-225.5027, device='cuda:0')
epoch: 97 test_true_pfm: 1610.3232318585833 sim_pfm: 159.995791872779
episode: 388 training return: tensor(-112.7873, device='cuda:0')
episode: 389 training return: tensor(-394.1032, device='cuda:0')
episode: 390 training return: tensor(-266.0390, device='cuda:0')
episode: 391 training return: tensor(263.5031, device='cuda:0')
epoch: 98 test_true_pfm: 3263.0829244163633 sim_pfm: 167.74867761162264
episode: 392 training return: tensor(12.3736, device='cuda:0')
episode: 393 training return: tensor(-134.8037, device='cuda:0')
episode: 394 training return: tensor(-360.2127, device='cuda:0')
episode: 395 training return: tensor(208.2892, device='cuda:0')
epoch: 99 test_true_pfm: 2688.865831620804 sim_pfm: 8.583728448012456
episode: 396 training return: tensor(-384.8739, device='cuda:0')
episode: 397 training return: tensor(248.6967, device='cuda:0')
episode: 398 training return: tensor(146.0096, device='cuda:0')
episode: 399 training return: tensor(-317.6353, device='cuda:0')
epoch: 100 test_true_pfm: 2237.9851113812283 sim_pfm: -82.73235490071238
episode: 400 training return: tensor(-306.1004, device='cuda:0')
episode: 401 training return: tensor(-377.5513, device='cuda:0')
episode: 402 training return: tensor(15.6404, device='cuda:0')
episode: 403 training return: tensor(-55.5009, device='cuda:0')
epoch: 101 test_true_pfm: 2151.8755622611643 sim_pfm: 36.43925048913419
episode: 404 training return: tensor(228.9942, device='cuda:0')
episode: 405 training return: tensor(-325.2201, device='cuda:0')
episode: 406 training return: tensor(-284.0706, device='cuda:0')
episode: 407 training return: tensor(-393.8694, device='cuda:0')
epoch: 102 test_true_pfm: 2145.3607978073355 sim_pfm: -287.673868102623
episode: 408 training return: tensor(-301.1067, device='cuda:0')
episode: 409 training return: tensor(-278.9109, device='cuda:0')
episode: 410 training return: tensor(248.9464, device='cuda:0')
episode: 411 training return: tensor(271.1770, device='cuda:0')
epoch: 103 test_true_pfm: 2488.210697089966 sim_pfm: -106.26727039850084
episode: 412 training return: tensor(-399.8936, device='cuda:0')
episode: 413 training return: tensor(263.8795, device='cuda:0')
episode: 414 training return: tensor(-394.8254, device='cuda:0')
episode: 415 training return: tensor(-246.9846, device='cuda:0')
epoch: 104 test_true_pfm: 1930.0935115654963 sim_pfm: -98.9767348759924
episode: 416 training return: tensor(249.5414, device='cuda:0')
episode: 417 training return: tensor(250.7680, device='cuda:0')
episode: 418 training return: tensor(-397.3416, device='cuda:0')
episode: 419 training return: tensor(-233.2447, device='cuda:0')
epoch: 105 test_true_pfm: 1842.6037222960265 sim_pfm: 221.7020600621278
episode: 420 training return: tensor(-299.9727, device='cuda:0')
episode: 421 training return: tensor(-120.3524, device='cuda:0')
episode: 422 training return: tensor(66.7771, device='cuda:0')
episode: 423 training return: tensor(-348.9506, device='cuda:0')
epoch: 106 test_true_pfm: 2027.776692514248 sim_pfm: 260.16691167046275
episode: 424 training return: tensor(78.3006, device='cuda:0')
episode: 425 training return: tensor(289.6898, device='cuda:0')
episode: 426 training return: tensor(230.1414, device='cuda:0')
episode: 427 training return: tensor(112.0040, device='cuda:0')
epoch: 107 test_true_pfm: 2657.343827109891 sim_pfm: -46.39049517607782
episode: 428 training return: tensor(-16.4114, device='cuda:0')
episode: 429 training return: tensor(-19.6973, device='cuda:0')
episode: 430 training return: tensor(-294.6382, device='cuda:0')
episode: 431 training return: tensor(-46.7477, device='cuda:0')
epoch: 108 test_true_pfm: 2951.866831405166 sim_pfm: -220.11250375478994
episode: 432 training return: tensor(-54.1891, device='cuda:0')
episode: 433 training return: tensor(-92.3202, device='cuda:0')
episode: 434 training return: tensor(-101.1155, device='cuda:0')
episode: 435 training return: tensor(-291.0793, device='cuda:0')
epoch: 109 test_true_pfm: 2432.4848565626985 sim_pfm: -289.5163649235037
episode: 436 training return: tensor(93.3893, device='cuda:0')
episode: 437 training return: tensor(255.5809, device='cuda:0')
episode: 438 training return: tensor(-296.4548, device='cuda:0')
episode: 439 training return: tensor(-226.1481, device='cuda:0')
epoch: 110 test_true_pfm: 2176.2320185325348 sim_pfm: -119.2444477613705
episode: 440 training return: tensor(-369.8057, device='cuda:0')
episode: 441 training return: tensor(-309.2947, device='cuda:0')
episode: 442 training return: tensor(-197.4134, device='cuda:0')
episode: 443 training return: tensor(-6.3583, device='cuda:0')
epoch: 111 test_true_pfm: 1596.7167002327872 sim_pfm: -168.15974083942515
episode: 444 training return: tensor(29.7876, device='cuda:0')
episode: 445 training return: tensor(-173.2458, device='cuda:0')
episode: 446 training return: tensor(-308.6166, device='cuda:0')
episode: 447 training return: tensor(-53.7823, device='cuda:0')
epoch: 112 test_true_pfm: 1819.490586752293 sim_pfm: -9.286588304540297
episode: 448 training return: tensor(265.1656, device='cuda:0')
episode: 449 training return: tensor(133.7996, device='cuda:0')
episode: 450 training return: tensor(-219.5540, device='cuda:0')
episode: 451 training return: tensor(152.1555, device='cuda:0')
epoch: 113 test_true_pfm: 3262.162296467263 sim_pfm: 68.08576711220667
episode: 452 training return: tensor(-394.2950, device='cuda:0')
episode: 453 training return: tensor(-364.6801, device='cuda:0')
episode: 454 training return: tensor(-363.4109, device='cuda:0')
episode: 455 training return: tensor(194.9210, device='cuda:0')
epoch: 114 test_true_pfm: 2713.3986732079466 sim_pfm: -288.2504973258862
episode: 456 training return: tensor(-331.7054, device='cuda:0')
episode: 457 training return: tensor(252.4310, device='cuda:0')
episode: 458 training return: tensor(-316.6926, device='cuda:0')
episode: 459 training return: tensor(-315.1965, device='cuda:0')
epoch: 115 test_true_pfm: 2174.2050881749296 sim_pfm: -223.78506908220393
episode: 460 training return: tensor(-103.5680, device='cuda:0')
episode: 461 training return: tensor(54.8305, device='cuda:0')
episode: 462 training return: tensor(236.0364, device='cuda:0')
episode: 463 training return: tensor(-355.2186, device='cuda:0')
epoch: 116 test_true_pfm: 2169.4625460198345 sim_pfm: 39.0341104370018
episode: 464 training return: tensor(187.2129, device='cuda:0')
episode: 465 training return: tensor(-235.8943, device='cuda:0')
episode: 466 training return: tensor(252.6784, device='cuda:0')
episode: 467 training return: tensor(302.9604, device='cuda:0')
epoch: 117 test_true_pfm: 2947.0731423315324 sim_pfm: 76.7146294779377
episode: 468 training return: tensor(-351.5934, device='cuda:0')
episode: 469 training return: tensor(-109.2006, device='cuda:0')
episode: 470 training return: tensor(-50.5344, device='cuda:0')
episode: 471 training return: tensor(-259.5220, device='cuda:0')
epoch: 118 test_true_pfm: 1601.4002956241154 sim_pfm: 268.39437033810344
episode: 472 training return: tensor(-346.9859, device='cuda:0')
episode: 473 training return: tensor(-342.4348, device='cuda:0')
episode: 474 training return: tensor(-308.5913, device='cuda:0')
episode: 475 training return: tensor(-374.5997, device='cuda:0')
epoch: 119 test_true_pfm: 2437.9227476352676 sim_pfm: -86.36685304924806
episode: 476 training return: tensor(-358.8752, device='cuda:0')
episode: 477 training return: tensor(251.0522, device='cuda:0')
episode: 478 training return: tensor(235.8284, device='cuda:0')
episode: 479 training return: tensor(224.7253, device='cuda:0')
epoch: 120 test_true_pfm: 2561.9387608137713 sim_pfm: 189.63375026701638
episode: 480 training return: tensor(81.9053, device='cuda:0')
episode: 481 training return: tensor(-396.1435, device='cuda:0')
episode: 482 training return: tensor(-50.1966, device='cuda:0')
episode: 483 training return: tensor(-397.2529, device='cuda:0')
epoch: 121 test_true_pfm: 2154.892314568195 sim_pfm: 86.69275836562156
episode: 484 training return: tensor(-339.1431, device='cuda:0')
episode: 485 training return: tensor(-131.9332, device='cuda:0')
episode: 486 training return: tensor(152.4417, device='cuda:0')
episode: 487 training return: tensor(-303.0702, device='cuda:0')
epoch: 122 test_true_pfm: 1955.7352138094 sim_pfm: 77.06112439400749
episode: 488 training return: tensor(-343.9835, device='cuda:0')
episode: 489 training return: tensor(-280.8926, device='cuda:0')
episode: 490 training return: tensor(-267.0756, device='cuda:0')
episode: 491 training return: tensor(-352.7259, device='cuda:0')
epoch: 123 test_true_pfm: 2195.3975609317495 sim_pfm: -9.073979622015031
episode: 492 training return: tensor(-282.3485, device='cuda:0')
episode: 493 training return: tensor(-340.7884, device='cuda:0')
episode: 494 training return: tensor(26.6961, device='cuda:0')
episode: 495 training return: tensor(-137.3289, device='cuda:0')
epoch: 124 test_true_pfm: 2019.3033237779598 sim_pfm: -288.47094824172865
episode: 496 training return: tensor(-104.5526, device='cuda:0')
episode: 497 training return: tensor(-308.4981, device='cuda:0')
episode: 498 training return: tensor(262.1402, device='cuda:0')
episode: 499 training return: tensor(-383.0329, device='cuda:0')
epoch: 125 test_true_pfm: 1921.317002026246 sim_pfm: 22.098080917533178
episode: 500 training return: tensor(-108.9668, device='cuda:0')
episode: 501 training return: tensor(10.0232, device='cuda:0')
episode: 502 training return: tensor(-74.9618, device='cuda:0')
episode: 503 training return: tensor(-301.0152, device='cuda:0')
epoch: 126 test_true_pfm: 1813.6592758655381 sim_pfm: -77.19946369817869
episode: 504 training return: tensor(-360.0591, device='cuda:0')
episode: 505 training return: tensor(-155.4326, device='cuda:0')
episode: 506 training return: tensor(249.9251, device='cuda:0')
episode: 507 training return: tensor(-326.7836, device='cuda:0')
epoch: 127 test_true_pfm: 3297.732272272187 sim_pfm: 33.71480903296227
episode: 508 training return: tensor(-41.5194, device='cuda:0')
episode: 509 training return: tensor(-43.5028, device='cuda:0')
episode: 510 training return: tensor(-102.7226, device='cuda:0')
episode: 511 training return: tensor(46.2601, device='cuda:0')
epoch: 128 test_true_pfm: 3256.893895674282 sim_pfm: -256.0856022830315
episode: 512 training return: tensor(-166.8840, device='cuda:0')
episode: 513 training return: tensor(-396.2186, device='cuda:0')
episode: 514 training return: tensor(-312.2629, device='cuda:0')
episode: 515 training return: tensor(-56.8389, device='cuda:0')
epoch: 129 test_true_pfm: 2478.0927308896694 sim_pfm: -98.69487297630015
episode: 516 training return: tensor(108.5741, device='cuda:0')
episode: 517 training return: tensor(-209.6374, device='cuda:0')
episode: 518 training return: tensor(-105.3720, device='cuda:0')
episode: 519 training return: tensor(115.2485, device='cuda:0')
epoch: 130 test_true_pfm: 1613.6653658029256 sim_pfm: -290.30373601673637
episode: 520 training return: tensor(-390.6029, device='cuda:0')
episode: 521 training return: tensor(269.0409, device='cuda:0')
episode: 522 training return: tensor(-340.3138, device='cuda:0')
episode: 523 training return: tensor(260.1429, device='cuda:0')
epoch: 131 test_true_pfm: 2365.5703749719046 sim_pfm: -92.46065709936859
episode: 524 training return: tensor(-388.0511, device='cuda:0')
episode: 525 training return: tensor(-342.9916, device='cuda:0')
episode: 526 training return: tensor(-393.2878, device='cuda:0')
episode: 527 training return: tensor(-76.8219, device='cuda:0')
epoch: 132 test_true_pfm: 2437.2188823849824 sim_pfm: -84.3460842051524
episode: 528 training return: tensor(38.8572, device='cuda:0')
episode: 529 training return: tensor(-318.1661, device='cuda:0')
episode: 530 training return: tensor(-300.5435, device='cuda:0')
episode: 531 training return: tensor(161.0801, device='cuda:0')
epoch: 133 test_true_pfm: 1597.5774529190621 sim_pfm: -207.0042439487103
episode: 532 training return: tensor(-339.3097, device='cuda:0')
episode: 533 training return: tensor(-345.7961, device='cuda:0')
episode: 534 training return: tensor(-94.1832, device='cuda:0')
episode: 535 training return: tensor(-348.0659, device='cuda:0')
epoch: 134 test_true_pfm: 2933.3444962759154 sim_pfm: 40.75316650313713
episode: 536 training return: tensor(-277.0450, device='cuda:0')
episode: 537 training return: tensor(-334.9299, device='cuda:0')
episode: 538 training return: tensor(-4.7157, device='cuda:0')
episode: 539 training return: tensor(-301.6948, device='cuda:0')
epoch: 135 test_true_pfm: 2889.972219403921 sim_pfm: 102.98920083101257
episode: 540 training return: tensor(-377.0270, device='cuda:0')
episode: 541 training return: tensor(40.1855, device='cuda:0')
episode: 542 training return: tensor(32.6595, device='cuda:0')
episode: 543 training return: tensor(-125.6375, device='cuda:0')
epoch: 136 test_true_pfm: 3012.1728549790496 sim_pfm: -108.44665165712165
episode: 544 training return: tensor(-295.8246, device='cuda:0')
episode: 545 training return: tensor(-287.7944, device='cuda:0')
episode: 546 training return: tensor(-398.0113, device='cuda:0')
episode: 547 training return: tensor(-190.8443, device='cuda:0')
epoch: 137 test_true_pfm: 2139.7274996913343 sim_pfm: 56.50407590146642
episode: 548 training return: tensor(-312.3772, device='cuda:0')
episode: 549 training return: tensor(-268.7445, device='cuda:0')
episode: 550 training return: tensor(-390.1980, device='cuda:0')
episode: 551 training return: tensor(-350.0730, device='cuda:0')
epoch: 138 test_true_pfm: 3080.9194028482216 sim_pfm: -14.89331207141125
episode: 552 training return: tensor(-318.3627, device='cuda:0')
episode: 553 training return: tensor(239.2872, device='cuda:0')
episode: 554 training return: tensor(-299.7512, device='cuda:0')
episode: 555 training return: tensor(-394.8522, device='cuda:0')
epoch: 139 test_true_pfm: 2041.0849920481778 sim_pfm: 129.5021769031106
episode: 556 training return: tensor(-113.5890, device='cuda:0')
episode: 557 training return: tensor(-213.0271, device='cuda:0')
episode: 558 training return: tensor(-301.3839, device='cuda:0')
episode: 559 training return: tensor(-47.3891, device='cuda:0')
epoch: 140 test_true_pfm: 2156.393508273651 sim_pfm: -21.998222541044623
episode: 560 training return: tensor(127.4058, device='cuda:0')
episode: 561 training return: tensor(-132.8734, device='cuda:0')
episode: 562 training return: tensor(303.9795, device='cuda:0')
episode: 563 training return: tensor(-360.9794, device='cuda:0')
epoch: 141 test_true_pfm: 2158.1887333829486 sim_pfm: -159.29114165300658
episode: 564 training return: tensor(-305.1269, device='cuda:0')
episode: 565 training return: tensor(-246.8361, device='cuda:0')
episode: 566 training return: tensor(-29.8313, device='cuda:0')
episode: 567 training return: tensor(291.4540, device='cuda:0')
epoch: 142 test_true_pfm: 1599.7453486077884 sim_pfm: -193.35358107883562
episode: 568 training return: tensor(-160.6094, device='cuda:0')
episode: 569 training return: tensor(-307.1201, device='cuda:0')
episode: 570 training return: tensor(-299.5472, device='cuda:0')
episode: 571 training return: tensor(277.3911, device='cuda:0')
epoch: 143 test_true_pfm: 1645.4931112775957 sim_pfm: -295.2730632663976
episode: 572 training return: tensor(-396.5478, device='cuda:0')
episode: 573 training return: tensor(-266.1833, device='cuda:0')
episode: 574 training return: tensor(-228.0264, device='cuda:0')
episode: 575 training return: tensor(-396.7315, device='cuda:0')
epoch: 144 test_true_pfm: 2148.31011866964 sim_pfm: -275.3256347933784
episode: 576 training return: tensor(-73.4138, device='cuda:0')
episode: 577 training return: tensor(-341.2554, device='cuda:0')
episode: 578 training return: tensor(259.0245, device='cuda:0')
episode: 579 training return: tensor(309.3240, device='cuda:0')
epoch: 145 test_true_pfm: 2585.792202608453 sim_pfm: -290.4044163507254
episode: 580 training return: tensor(-384.4403, device='cuda:0')
episode: 581 training return: tensor(-368.6339, device='cuda:0')
episode: 582 training return: tensor(-226.6624, device='cuda:0')
episode: 583 training return: tensor(-97.7984, device='cuda:0')
epoch: 146 test_true_pfm: 2432.52802583484 sim_pfm: -168.97921536230328
episode: 584 training return: tensor(262.6762, device='cuda:0')
episode: 585 training return: tensor(-325.1628, device='cuda:0')
episode: 586 training return: tensor(-342.9348, device='cuda:0')
episode: 587 training return: tensor(269.6404, device='cuda:0')
epoch: 147 test_true_pfm: 1804.7978897834503 sim_pfm: -218.64896451179325
episode: 588 training return: tensor(-362.7798, device='cuda:0')
episode: 589 training return: tensor(-132.1976, device='cuda:0')
episode: 590 training return: tensor(-285.7570, device='cuda:0')
episode: 591 training return: tensor(-57.0266, device='cuda:0')
epoch: 148 test_true_pfm: 2253.977012604399 sim_pfm: 18.108758983473916
episode: 592 training return: tensor(-72.1551, device='cuda:0')
episode: 593 training return: tensor(198.3653, device='cuda:0')
episode: 594 training return: tensor(-229.5176, device='cuda:0')
episode: 595 training return: tensor(-343.5393, device='cuda:0')
epoch: 149 test_true_pfm: 2699.7877646216302 sim_pfm: -190.4734011636077
episode: 596 training return: tensor(272.5652, device='cuda:0')
episode: 597 training return: tensor(254.8972, device='cuda:0')
episode: 598 training return: tensor(-5.7098, device='cuda:0')
episode: 599 training return: tensor(-131.4565, device='cuda:0')
epoch: 150 test_true_pfm: 1736.2827410744924 sim_pfm: -114.85619705077261
