['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'uncertainty', '--traj', 'medium', '--seed', '2', '--data', '100000']
epoch: 0 training_loss 0.27495862014591693 test_loss: 0.22905657291412354
epoch: 1 training_loss 0.15517772547900677 test_loss: 0.14696478843688965
epoch: 2 training_loss 0.13705991622060537 test_loss: 0.13461158275604249
epoch: 3 training_loss 0.12370308335870504 test_loss: 0.12219291925430298
epoch: 4 training_loss 0.1127428781054914 test_loss: 0.10881093740463257
epoch: 5 training_loss 0.12095376662909985 test_loss: 0.11029465198516845
epoch: 6 training_loss 0.11183139123022556 test_loss: 0.10768976211547851
epoch: 7 training_loss 0.11738290207460522 test_loss: 0.11763837337493896
epoch: 8 training_loss 0.11063272459432483 test_loss: 0.11096328496932983
epoch: 9 training_loss 0.10825410529971123 test_loss: 0.09723513126373291
epoch: 10 training_loss 0.10472970236092806 test_loss: 0.11016136407852173
epoch: 11 training_loss 0.11146594259887933 test_loss: 0.10920612812042237
epoch: 12 training_loss 0.10888714667409659 test_loss: 0.10952315330505372
epoch: 13 training_loss 0.09622098853811621 test_loss: 0.09839763641357421
epoch: 14 training_loss 0.10484496057033539 test_loss: 0.09372795820236206
epoch: 15 training_loss 0.10446356914937496 test_loss: 0.11327042579650878
epoch: 16 training_loss 0.09772546593099833 test_loss: 0.11899985074996948
epoch: 17 training_loss 0.09921771232038737 test_loss: 0.11292959451675415
epoch: 18 training_loss 0.0966998778283596 test_loss: 0.1021151065826416
epoch: 19 training_loss 0.09627049438655376 test_loss: 0.11647942066192626
epoch: 20 training_loss 0.09870895989239216 test_loss: 0.10531237125396728
epoch: 21 training_loss 0.09845497770234943 test_loss: 0.10426265001296997
epoch: 22 training_loss 0.09214719474315643 test_loss: 0.10781599283218384
epoch: 23 training_loss 0.09451976407319307 test_loss: 0.10703792572021484
epoch: 24 training_loss 0.10514023011550307 test_loss: 0.11249592304229736
epoch: 25 training_loss 0.09717180728912353 test_loss: 0.08921545147895812
epoch: 26 training_loss 0.09778313405811787 test_loss: 0.09023502469062805
epoch: 27 training_loss 0.10315060529857874 test_loss: 0.10687812566757202
epoch: 28 training_loss 0.08967419436201453 test_loss: 0.12067848443984985
epoch: 29 training_loss 0.09414625803939998 test_loss: 0.11196883916854858
epoch: 30 training_loss 0.09454145541414619 test_loss: 0.09211806654930114
epoch: 31 training_loss 0.09160585520789027 test_loss: 0.10025361776351929
epoch: 32 training_loss 0.09483985818922519 test_loss: 0.08771944642066956
epoch: 33 training_loss 0.10111954469233751 test_loss: 0.10470612049102783
epoch: 34 training_loss 0.09916052348911762 test_loss: 0.09375147223472595
epoch: 35 training_loss 0.0931452901288867 test_loss: 0.09320957064628602
epoch: 36 training_loss 0.08889748394489289 test_loss: 0.10296573638916015
epoch: 37 training_loss 0.08635165821760893 test_loss: 0.10130037069320678
epoch: 38 training_loss 0.09761400949209928 test_loss: 0.11749838590621949
epoch: 39 training_loss 0.08986674735322595 test_loss: 0.10491024255752564
epoch: 40 training_loss 0.08920209005475044 test_loss: 0.1063498854637146
epoch: 41 training_loss 0.09117729203775525 test_loss: 0.08765077590942383
epoch: 42 training_loss 0.09806675879284739 test_loss: 0.10196930170059204
epoch: 43 training_loss 0.08652389001101256 test_loss: 0.10991860628128051
epoch: 44 training_loss 0.09160435874015092 test_loss: 0.10222543478012085
epoch: 45 training_loss 0.09373314324766398 test_loss: 0.0850545346736908
epoch: 46 training_loss 0.09485838543623686 test_loss: 0.09102216362953186
epoch: 47 training_loss 0.08828661158680916 test_loss: 0.09586921334266663
epoch: 48 training_loss 0.09113855261355638 test_loss: 0.10271644592285156
epoch: 49 training_loss 0.08949848154559731 test_loss: 0.11455579996109008
epoch: 50 training_loss 0.0911704620346427 test_loss: 0.10112620592117309
epoch: 51 training_loss 0.08944007132202386 test_loss: 0.10882416963577271
epoch: 52 training_loss 0.09054571140557527 test_loss: 0.11096818447113037
epoch: 53 training_loss 0.09025903221219778 test_loss: 0.1179168701171875
epoch: 54 training_loss 0.08486128215678036 test_loss: 0.11295676231384277
epoch: 55 training_loss 0.08768188118003309 test_loss: 0.1079143762588501
epoch: 56 training_loss 0.083856867775321 test_loss: 0.09335082173347473
epoch: 57 training_loss 0.09321047388017177 test_loss: 0.09831593036651612
epoch: 58 training_loss 0.0880478566326201 test_loss: 0.08380087614059448
epoch: 59 training_loss 0.09058297354727983 test_loss: 0.10492852926254273
epoch: 60 training_loss 0.08985063917934895 test_loss: 0.10794309377670289
epoch: 61 training_loss 0.08687360344454646 test_loss: 0.10709069967269898
epoch: 62 training_loss 0.08711365949362516 test_loss: 0.09827446341514587
epoch: 63 training_loss 0.08613476661965251 test_loss: 0.10250543355941773
epoch: 64 training_loss 0.09325916297733784 test_loss: 0.09715011715888977
epoch: 65 training_loss 0.08427229488268495 test_loss: 0.11177990436553956
epoch: 66 training_loss 0.08986922565847635 test_loss: 0.098954576253891
epoch: 67 training_loss 0.0867062122002244 test_loss: 0.09601349830627441
epoch: 68 training_loss 0.08847666151821613 test_loss: 0.10810314416885376
epoch: 69 training_loss 0.08919356328435242 test_loss: 0.1124607801437378
epoch: 70 training_loss 0.08980656638741494 test_loss: 0.091185063123703
epoch: 71 training_loss 0.08207755524665117 test_loss: 0.10022032260894775
epoch: 72 training_loss 0.09380641873925924 test_loss: 0.10576494932174682
epoch: 73 training_loss 0.08817819595336913 test_loss: 0.10559028387069702
epoch: 74 training_loss 0.08726579943671822 test_loss: 0.09661654233932496
epoch: 75 training_loss 0.08660801254212856 test_loss: 0.09980396628379821
epoch: 76 training_loss 0.09112016260623931 test_loss: 0.09193202257156372
epoch: 77 training_loss 0.08136813065037131 test_loss: 0.10498300790786744
epoch: 78 training_loss 0.09045686209574341 test_loss: 0.09121103286743164
epoch: 79 training_loss 0.08875837499275803 test_loss: 0.10699613094329834
epoch: 80 training_loss 0.084508938472718 test_loss: 0.09612853527069092
epoch: 81 training_loss 0.0894159446284175 test_loss: 0.09863963723182678
epoch: 82 training_loss 0.09218047395348548 test_loss: 0.08380732536315919
epoch: 83 training_loss 0.08585604541003704 test_loss: 0.11874040365219116
epoch: 84 training_loss 0.08078924661502242 test_loss: 0.09851921796798706
epoch: 85 training_loss 0.09068091673776507 test_loss: 0.09877662062644958
epoch: 86 training_loss 0.08608811868354678 test_loss: 0.1013867735862732
epoch: 87 training_loss 0.0806480409298092 test_loss: 0.09832425117492676
epoch: 88 training_loss 0.0816779793985188 test_loss: 0.10208652019500733
epoch: 89 training_loss 0.07741344342939556 test_loss: 0.11453738212585449
epoch: 90 training_loss 0.08471353225409985 test_loss: 0.09812620878219605
epoch: 91 training_loss 0.08377331966534257 test_loss: 0.09772393703460694
epoch: 92 training_loss 0.08555815843865275 test_loss: 0.09032572507858276
epoch: 93 training_loss 0.08303450407460332 test_loss: 0.09855719208717346
epoch: 94 training_loss 0.08805699955672025 test_loss: 0.11047358512878418
epoch: 95 training_loss 0.08405146988108754 test_loss: 0.10510573387145997
epoch: 96 training_loss 0.0864622613787651 test_loss: 0.10001318454742432
epoch: 97 training_loss 0.08283037161454558 test_loss: 0.09598292708396912
epoch: 98 training_loss 0.08221457118168474 test_loss: 0.09461562037467956
epoch: 99 training_loss 0.07951844887807966 test_loss: 0.10765022039413452
epoch: 100 training_loss 0.08673533304594457 test_loss: 0.11904085874557495
epoch: 101 training_loss 0.08124945424497128 test_loss: 0.10694499015808105
epoch: 102 training_loss 0.07874301183968782 test_loss: 0.09200863242149353
epoch: 103 training_loss 0.08003131777048111 test_loss: 0.10014790296554565
epoch: 104 training_loss 0.08787598146125675 test_loss: 0.10012863874435425
epoch: 105 training_loss 0.08117587007582187 test_loss: 0.08971737027168274
epoch: 106 training_loss 0.08392307074740529 test_loss: 0.10451874732971192
epoch: 107 training_loss 0.08198999404907227 test_loss: 0.08585896492004394
epoch: 108 training_loss 0.08949639251455664 test_loss: 0.09884633421897888
epoch: 109 training_loss 0.08484404502436518 test_loss: 0.10701333284378052
epoch: 110 training_loss 0.0793035501986742 test_loss: 0.09906166791915894
epoch: 111 training_loss 0.07961775057017803 test_loss: 0.1097385048866272
epoch: 112 training_loss 0.08147367507219315 test_loss: 0.10110920667648315
epoch: 113 training_loss 0.08394062880426645 test_loss: 0.09735353589057923
epoch: 114 training_loss 0.08562718565575779 test_loss: 0.09069907069206237
epoch: 115 training_loss 0.08519650423899293 test_loss: 0.0958358883857727
epoch: 116 training_loss 0.08464324075728655 test_loss: 0.08234645128250122
epoch: 117 training_loss 0.08066382942721248 test_loss: 0.0944471538066864
epoch: 118 training_loss 0.0805540780350566 test_loss: 0.10150284767150879
epoch: 119 training_loss 0.08099901184439659 test_loss: 0.09738126397132874
epoch: 120 training_loss 0.07844280192628503 test_loss: 0.11117514371871948
epoch: 121 training_loss 0.08348920042626559 test_loss: 0.09657887220382691
epoch: 122 training_loss 0.08297798622399569 test_loss: 0.08612411618232726
epoch: 123 training_loss 0.085416567530483 test_loss: 0.1036842942237854
epoch: 124 training_loss 0.08380683554336428 test_loss: 0.10117220878601074
epoch: 125 training_loss 0.0795951624121517 test_loss: 0.08833073377609253
epoch: 126 training_loss 0.0732768901064992 test_loss: 0.0997765839099884
epoch: 127 training_loss 0.0771647590631619 test_loss: 0.10550198554992676
epoch: 128 training_loss 0.08075096167623996 test_loss: 0.10634001493453979
epoch: 129 training_loss 0.08770903198048473 test_loss: 0.08711401224136353
epoch: 130 training_loss 0.08168754708021879 test_loss: 0.10808556079864502
epoch: 131 training_loss 0.07761986143887042 test_loss: 0.10046414136886597
epoch: 132 training_loss 0.08469982903450728 test_loss: 0.09013363718986511
epoch: 133 training_loss 0.07916316717863082 test_loss: 0.09321040511131287
epoch: 134 training_loss 0.07909221431240439 test_loss: 0.09002100825309753
epoch: 135 training_loss 0.07918338778428734 test_loss: 0.08697688579559326
epoch: 136 training_loss 0.08116790330037475 test_loss: 0.09815312623977661
epoch: 137 training_loss 0.08086539095267653 test_loss: 0.11186414957046509
epoch: 138 training_loss 0.07534589942544699 test_loss: 0.09660292863845825
epoch: 139 training_loss 0.0785994947142899 test_loss: 0.10824964046478272
epoch: 140 training_loss 0.07912947626784445 test_loss: 0.0944023847579956
epoch: 141 training_loss 0.0809267370775342 test_loss: 0.09607477188110351
epoch: 142 training_loss 0.07632877685129642 test_loss: 0.10621062517166138
epoch: 143 training_loss 0.0833980518952012 test_loss: 0.09708492755889893
epoch: 144 training_loss 0.08612196271307766 test_loss: 0.0979608416557312
epoch: 145 training_loss 0.08069169851019979 test_loss: 0.09019057154655456
epoch: 146 training_loss 0.07909334894269705 test_loss: 0.09152946472167969
epoch: 147 training_loss 0.08114036338403821 test_loss: 0.10619144439697266
epoch: 148 training_loss 0.07953653438016772 test_loss: 0.10624691247940063
epoch: 149 training_loss 0.0830047883093357 test_loss: 0.09528729915618897
epoch: 0 training_loss 0.28528204694390297 test_loss: 0.18780057430267333
epoch: 1 training_loss 0.16135432049632073 test_loss: 0.17465612888336182
epoch: 2 training_loss 0.13458664055913686 test_loss: 0.14623160362243653
epoch: 3 training_loss 0.11748592510819435 test_loss: 0.14054806232452394
epoch: 4 training_loss 0.11798870451748371 test_loss: 0.11328136920928955
epoch: 5 training_loss 0.12055008575320243 test_loss: 0.11778182983398437
epoch: 6 training_loss 0.11041539788246155 test_loss: 0.15318310260772705
epoch: 7 training_loss 0.1162497130781412 test_loss: 0.13462079763412477
epoch: 8 training_loss 0.1080785021558404 test_loss: 0.09786513447761536
epoch: 9 training_loss 0.1055287129059434 test_loss: 0.12141720056533814
epoch: 10 training_loss 0.11392207853496075 test_loss: 0.1043163776397705
epoch: 11 training_loss 0.0951460368745029 test_loss: 0.10940729379653931
epoch: 12 training_loss 0.09893917990848422 test_loss: 0.1080449104309082
epoch: 13 training_loss 0.10026442693546414 test_loss: 0.11571667194366456
epoch: 14 training_loss 0.10231499060988426 test_loss: 0.11972993612289429
epoch: 15 training_loss 0.0940363859757781 test_loss: 0.10064129829406739
epoch: 16 training_loss 0.09835606765002013 test_loss: 0.11651912927627564
epoch: 17 training_loss 0.09063623633235693 test_loss: 0.11968275308609008
epoch: 18 training_loss 0.09966981098987163 test_loss: 0.13241477012634278
epoch: 19 training_loss 0.09807433068752289 test_loss: 0.09258924126625061
epoch: 20 training_loss 0.09358238035812974 test_loss: 0.0952578604221344
epoch: 21 training_loss 0.09533429849892855 test_loss: 0.10351834297180176
epoch: 22 training_loss 0.08720188740640879 test_loss: 0.09512563943862914
epoch: 23 training_loss 0.10219674395397306 test_loss: 0.1096613049507141
epoch: 24 training_loss 0.09466688130050897 test_loss: 0.09405315518379212
epoch: 25 training_loss 0.09726537711918354 test_loss: 0.09438731074333191
epoch: 26 training_loss 0.09161836637184023 test_loss: 0.09868589043617249
epoch: 27 training_loss 0.08986783565953374 test_loss: 0.09322922825813293
epoch: 28 training_loss 0.09258952816948295 test_loss: 0.09211939573287964
epoch: 29 training_loss 0.0858149003982544 test_loss: 0.1013745903968811
epoch: 30 training_loss 0.09164409218356014 test_loss: 0.10690065622329711
epoch: 31 training_loss 0.09595064230263234 test_loss: 0.10909714698791503
epoch: 32 training_loss 0.0888521745800972 test_loss: 0.09092205166816711
epoch: 33 training_loss 0.08283911032602191 test_loss: 0.10827566385269165
epoch: 34 training_loss 0.08963690942153335 test_loss: 0.10198630094528198
epoch: 35 training_loss 0.0890082641877234 test_loss: 0.08482440710067748
epoch: 36 training_loss 0.08855779800564051 test_loss: 0.09848805665969848
epoch: 37 training_loss 0.09343254838138819 test_loss: 0.08244614601135254
epoch: 38 training_loss 0.08521144581958652 test_loss: 0.09720379114151001
epoch: 39 training_loss 0.08447532523423433 test_loss: 0.09694932103157043
epoch: 40 training_loss 0.08351478394120931 test_loss: 0.09296585321426391
epoch: 41 training_loss 0.09208029011264443 test_loss: 0.09942094087600709
epoch: 42 training_loss 0.08677785269916058 test_loss: 0.10375312566757203
epoch: 43 training_loss 0.0860719058662653 test_loss: 0.0912928819656372
epoch: 44 training_loss 0.08304417358711362 test_loss: 0.1086580514907837
epoch: 45 training_loss 0.09353955389931798 test_loss: 0.08762716650962829
epoch: 46 training_loss 0.09023606203496456 test_loss: 0.09769182801246643
epoch: 47 training_loss 0.0893228561617434 test_loss: 0.10103099346160889
epoch: 48 training_loss 0.0816411204263568 test_loss: 0.10771178007125855
epoch: 49 training_loss 0.08195909791626037 test_loss: 0.10347597599029541
epoch: 50 training_loss 0.08997427653521299 test_loss: 0.08145438432693482
epoch: 51 training_loss 0.0859169453009963 test_loss: 0.09704257249832153
epoch: 52 training_loss 0.08366730848327279 test_loss: 0.09761889576911927
epoch: 53 training_loss 0.08425031412392854 test_loss: 0.09177805185317993
epoch: 54 training_loss 0.08221702780574561 test_loss: 0.08923370838165283
epoch: 55 training_loss 0.08283841965720057 test_loss: 0.09624540209770202
epoch: 56 training_loss 0.08549242664128542 test_loss: 0.08742823600769042
epoch: 57 training_loss 0.08372853405773639 test_loss: 0.08458229303359985
epoch: 58 training_loss 0.08618735181167722 test_loss: 0.09577269554138183
epoch: 59 training_loss 0.08125840382650494 test_loss: 0.09701722264289855
epoch: 60 training_loss 0.08343723371624946 test_loss: 0.0924163281917572
epoch: 61 training_loss 0.08927877962589265 test_loss: 0.09566107988357545
epoch: 62 training_loss 0.08560993819497525 test_loss: 0.08909671306610108
epoch: 63 training_loss 0.08128309002146125 test_loss: 0.10941387414932251
epoch: 64 training_loss 0.09104212660342455 test_loss: 0.1045425534248352
epoch: 65 training_loss 0.08599032800644636 test_loss: 0.09277739524841308
epoch: 66 training_loss 0.08736842138692737 test_loss: 0.09343112707138061
epoch: 67 training_loss 0.08273210239596665 test_loss: 0.09430896639823913
epoch: 68 training_loss 0.08588827533647418 test_loss: 0.10278459787368774
epoch: 69 training_loss 0.0808907325565815 test_loss: 0.09435994029045106
epoch: 70 training_loss 0.07629142170771956 test_loss: 0.08939388394355774
epoch: 71 training_loss 0.08148386164335535 test_loss: 0.09155938625335694
epoch: 72 training_loss 0.0869820843078196 test_loss: 0.09301047921180725
epoch: 73 training_loss 0.0784839579463005 test_loss: 0.10815649032592774
epoch: 74 training_loss 0.08950929241254926 test_loss: 0.09924663305282592
epoch: 75 training_loss 0.08070773931220174 test_loss: 0.09961104393005371
epoch: 76 training_loss 0.08766180658712983 test_loss: 0.09627814292907715
epoch: 77 training_loss 0.07630748944357038 test_loss: 0.09649010896682739
epoch: 78 training_loss 0.07235341221094131 test_loss: 0.10030698776245117
epoch: 79 training_loss 0.08053087649866938 test_loss: 0.100583016872406
epoch: 80 training_loss 0.08630570564419031 test_loss: 0.09192832708358764
epoch: 81 training_loss 0.07664128840900958 test_loss: 0.09401481747627258
epoch: 82 training_loss 0.08987022822722793 test_loss: 0.10278304815292358
epoch: 83 training_loss 0.08178768245503307 test_loss: 0.09764993786811829
epoch: 84 training_loss 0.07810676721855998 test_loss: 0.10010493993759155
epoch: 85 training_loss 0.08209346651099622 test_loss: 0.08951347470283508
epoch: 86 training_loss 0.08365030441433191 test_loss: 0.07931504249572754
epoch: 87 training_loss 0.08033089906908572 test_loss: 0.09363105297088622
epoch: 88 training_loss 0.08094167748466134 test_loss: 0.0842165470123291
epoch: 89 training_loss 0.08083352788351476 test_loss: 0.10592920780181884
epoch: 90 training_loss 0.08335600746795535 test_loss: 0.09837990999221802
epoch: 91 training_loss 0.08326372290961444 test_loss: 0.10269299745559693
epoch: 92 training_loss 0.08006770987063647 test_loss: 0.09857207536697388
epoch: 93 training_loss 0.08096225822344422 test_loss: 0.10212607383728027
epoch: 94 training_loss 0.08663251891732215 test_loss: 0.09603956937789918
epoch: 95 training_loss 0.07871744778007268 test_loss: 0.10149897336959839
epoch: 96 training_loss 0.07708417718298734 test_loss: 0.09811518788337707
epoch: 97 training_loss 0.0769233219884336 test_loss: 0.1130369782447815
epoch: 98 training_loss 0.07552907271310687 test_loss: 0.08760285377502441
epoch: 99 training_loss 0.09086643058806658 test_loss: 0.09111678600311279
epoch: 100 training_loss 0.079163418430835 test_loss: 0.08678553104400635
epoch: 101 training_loss 0.08408433206379413 test_loss: 0.09060272574424744
epoch: 102 training_loss 0.08145804842934012 test_loss: 0.07929359674453736
epoch: 103 training_loss 0.08245763039216399 test_loss: 0.097779780626297
epoch: 104 training_loss 0.07971063388511539 test_loss: 0.09070761799812317
epoch: 105 training_loss 0.08363585826009512 test_loss: 0.0966089427471161
epoch: 106 training_loss 0.08316110728308558 test_loss: 0.09737280011177063
epoch: 107 training_loss 0.08109595207497478 test_loss: 0.09457153081893921
epoch: 108 training_loss 0.07760621279478074 test_loss: 0.09591915011405945
epoch: 109 training_loss 0.0781774640083313 test_loss: 0.09099244475364685
epoch: 110 training_loss 0.07145106758922339 test_loss: 0.12079280614852905
epoch: 111 training_loss 0.08171533763408662 test_loss: 0.09121913909912109
epoch: 112 training_loss 0.07553944643586874 test_loss: 0.09515478610992431
epoch: 113 training_loss 0.08917744748294354 test_loss: 0.09909281134605408
epoch: 114 training_loss 0.0701688345707953 test_loss: 0.0910751461982727
epoch: 115 training_loss 0.0808258281648159 test_loss: 0.10194187164306641
epoch: 116 training_loss 0.07843444928526878 test_loss: 0.09486048221588135
epoch: 117 training_loss 0.0758938835375011 test_loss: 0.0973073422908783
epoch: 118 training_loss 0.07818178245797754 test_loss: 0.09733268618583679
epoch: 119 training_loss 0.07986251471564174 test_loss: 0.10130888223648071
epoch: 120 training_loss 0.07793400522321463 test_loss: 0.0884777545928955
epoch: 121 training_loss 0.076975874081254 test_loss: 0.08198784589767456
epoch: 122 training_loss 0.08137816395610571 test_loss: 0.09238711595535279
epoch: 123 training_loss 0.08018208649009466 test_loss: 0.09753392934799195
epoch: 124 training_loss 0.07331755925901234 test_loss: 0.09833265542984009
epoch: 125 training_loss 0.08006198493763804 test_loss: 0.09930163621902466
epoch: 126 training_loss 0.08202271746471525 test_loss: 0.09354841113090515
epoch: 127 training_loss 0.0850626451522112 test_loss: 0.09683046340942383
epoch: 128 training_loss 0.07587920174002648 test_loss: 0.08654015064239502
epoch: 129 training_loss 0.07932898979634047 test_loss: 0.10698590278625489
epoch: 130 training_loss 0.0779079894721508 test_loss: 0.10194242000579834
epoch: 131 training_loss 0.07258870206773281 test_loss: 0.08837834596633912
epoch: 132 training_loss 0.0686392311938107 test_loss: 0.1001010537147522
epoch: 133 training_loss 0.07661824421957135 test_loss: 0.10421994924545289
epoch: 134 training_loss 0.07178087380714715 test_loss: 0.10928915739059449
epoch: 135 training_loss 0.0761590350419283 test_loss: 0.0916864037513733
epoch: 136 training_loss 0.07000059893354774 test_loss: 0.09804068803787232
epoch: 137 training_loss 0.08556736835278571 test_loss: 0.10232524871826172
epoch: 138 training_loss 0.07913702497258783 test_loss: 0.09167832732200623
epoch: 139 training_loss 0.0777995912078768 test_loss: 0.08570836186408996
epoch: 140 training_loss 0.08285389406606555 test_loss: 0.09917330741882324
epoch: 141 training_loss 0.0728375212289393 test_loss: 0.11760165691375732
epoch: 142 training_loss 0.07535924803465605 test_loss: 0.09430885314941406
epoch: 143 training_loss 0.08093490464612842 test_loss: 0.09445908665657043
epoch: 144 training_loss 0.07841975055634975 test_loss: 0.09956946372985839
epoch: 145 training_loss 0.07284760996699333 test_loss: 0.09084664583206177
epoch: 146 training_loss 0.07282097712159157 test_loss: 0.11324133872985839
epoch: 147 training_loss 0.07316899064928294 test_loss: 0.09416223764419555
epoch: 148 training_loss 0.07356011578813196 test_loss: 0.09869365096092224
epoch: 149 training_loss 0.07183728508651256 test_loss: 0.09562572836875916
epoch: 0 training_loss 0.2508323333412409 test_loss: 0.17234246730804442
epoch: 1 training_loss 0.1474829113483429 test_loss: 0.14244551658630372
epoch: 2 training_loss 0.12761507105082273 test_loss: 0.1330391526222229
epoch: 3 training_loss 0.12571178290992976 test_loss: 0.11689034700393677
epoch: 4 training_loss 0.12590631756931545 test_loss: 0.1530277967453003
epoch: 5 training_loss 0.11215937230736017 test_loss: 0.11038144826889038
epoch: 6 training_loss 0.1188985825330019 test_loss: 0.12245843410491944
epoch: 7 training_loss 0.10962357610464096 test_loss: 0.10932480096817017
epoch: 8 training_loss 0.10415104834362865 test_loss: 0.11188784837722779
epoch: 9 training_loss 0.10347312364727258 test_loss: 0.10275182723999024
epoch: 10 training_loss 0.10150719255208969 test_loss: 0.12434329986572265
epoch: 11 training_loss 0.0999123172275722 test_loss: 0.11439145803451538
epoch: 12 training_loss 0.09690304329618811 test_loss: 0.12551379203796387
epoch: 13 training_loss 0.09814567048102617 test_loss: 0.09911524057388306
epoch: 14 training_loss 0.10197459531947971 test_loss: 0.10690504312515259
epoch: 15 training_loss 0.09256084745749832 test_loss: 0.10061872005462646
epoch: 16 training_loss 0.08669491862878204 test_loss: 0.09225666522979736
epoch: 17 training_loss 0.09888916088268161 test_loss: 0.10108896493911743
epoch: 18 training_loss 0.09837256852537393 test_loss: 0.09462119936943054
epoch: 19 training_loss 0.09259155314415693 test_loss: 0.10856680870056153
epoch: 20 training_loss 0.09217383224517108 test_loss: 0.10521849393844604
epoch: 21 training_loss 0.08903121246956289 test_loss: 0.1064110517501831
epoch: 22 training_loss 0.1010755574144423 test_loss: 0.09524591565132141
epoch: 23 training_loss 0.09850454857572913 test_loss: 0.09838313460350037
epoch: 24 training_loss 0.0923750981874764 test_loss: 0.11105746030807495
epoch: 25 training_loss 0.09249433301389218 test_loss: 0.10715653896331787
epoch: 26 training_loss 0.09708236576989293 test_loss: 0.11050848960876465
epoch: 27 training_loss 0.09282280227169394 test_loss: 0.09834399223327636
epoch: 28 training_loss 0.08795392420142889 test_loss: 0.10927020311355591
epoch: 29 training_loss 0.10175169469788671 test_loss: 0.10880599021911622
epoch: 30 training_loss 0.09259579058736563 test_loss: 0.09391134977340698
epoch: 31 training_loss 0.08741141559556126 test_loss: 0.11126130819320679
epoch: 32 training_loss 0.09228049743920565 test_loss: 0.09189786314964295
epoch: 33 training_loss 0.09065910007804633 test_loss: 0.10717781782150268
epoch: 34 training_loss 0.09268523093312979 test_loss: 0.10682750940322876
epoch: 35 training_loss 0.09488737851381301 test_loss: 0.09646127820014953
epoch: 36 training_loss 0.0913211821205914 test_loss: 0.09336212873458863
epoch: 37 training_loss 0.08960144978016615 test_loss: 0.10410077571868896
epoch: 38 training_loss 0.09345523357391357 test_loss: 0.09925076961517335
epoch: 39 training_loss 0.07843737373128533 test_loss: 0.10194618701934814
epoch: 40 training_loss 0.09056053325533867 test_loss: 0.10667572021484376
epoch: 41 training_loss 0.09061778653413058 test_loss: 0.10760198831558228
epoch: 42 training_loss 0.08484951065853238 test_loss: 0.10592617988586425
epoch: 43 training_loss 0.09004861490800976 test_loss: 0.09356485605239868
epoch: 44 training_loss 0.08919011252000927 test_loss: 0.11034440994262695
epoch: 45 training_loss 0.08523297373205424 test_loss: 0.095257967710495
epoch: 46 training_loss 0.08862508911639452 test_loss: 0.09416459798812866
epoch: 47 training_loss 0.08837719473987818 test_loss: 0.08156130909919738
epoch: 48 training_loss 0.09209824459627271 test_loss: 0.1029646635055542
epoch: 49 training_loss 0.08380326138809323 test_loss: 0.0897203505039215
epoch: 50 training_loss 0.09028056677430868 test_loss: 0.11192629337310792
epoch: 51 training_loss 0.08936041807755828 test_loss: 0.08956320285797119
epoch: 52 training_loss 0.09358720760792494 test_loss: 0.12346309423446655
epoch: 53 training_loss 0.08753055110573768 test_loss: 0.1005907654762268
epoch: 54 training_loss 0.08662551589310169 test_loss: 0.0879239022731781
epoch: 55 training_loss 0.09186924366280437 test_loss: 0.08091693520545959
epoch: 56 training_loss 0.08850612079724669 test_loss: 0.10015918016433716
epoch: 57 training_loss 0.08860211730003358 test_loss: 0.10788516998291016
epoch: 58 training_loss 0.08470316734164954 test_loss: 0.08324621915817261
epoch: 59 training_loss 0.08900916282087565 test_loss: 0.09849320650100708
epoch: 60 training_loss 0.08001757828518748 test_loss: 0.09116716384887695
epoch: 61 training_loss 0.08570520555600523 test_loss: 0.09715969562530517
epoch: 62 training_loss 0.08667427029460668 test_loss: 0.10452715158462525
epoch: 63 training_loss 0.08711413971148431 test_loss: 0.11205786466598511
epoch: 64 training_loss 0.09099708428606391 test_loss: 0.08790533542633057
epoch: 65 training_loss 0.08741911016404628 test_loss: 0.09004539847373963
epoch: 66 training_loss 0.08780790994875133 test_loss: 0.09710567593574523
epoch: 67 training_loss 0.08171945823356509 test_loss: 0.09152205586433411
epoch: 68 training_loss 0.08748679561540484 test_loss: 0.0978234052658081
epoch: 69 training_loss 0.0945920554921031 test_loss: 0.10813755989074707
epoch: 70 training_loss 0.0922915262915194 test_loss: 0.10472131967544555
epoch: 71 training_loss 0.0827304265461862 test_loss: 0.09448728561401368
epoch: 72 training_loss 0.08863561516627669 test_loss: 0.09369778633117676
epoch: 73 training_loss 0.08305251989513636 test_loss: 0.09776488542556763
epoch: 74 training_loss 0.08251553255133331 test_loss: 0.10555193424224854
epoch: 75 training_loss 0.08132419059053063 test_loss: 0.07859897017478942
epoch: 76 training_loss 0.08745737688615918 test_loss: 0.10145806074142456
epoch: 77 training_loss 0.08089535331353545 test_loss: 0.08911056518554687
epoch: 78 training_loss 0.08007469890639186 test_loss: 0.0955570638179779
epoch: 79 training_loss 0.08321839166805148 test_loss: 0.09624319672584533
epoch: 80 training_loss 0.0858429972268641 test_loss: 0.09277710914611817
epoch: 81 training_loss 0.08262732587754726 test_loss: 0.09584105610847474
epoch: 82 training_loss 0.08478726157918573 test_loss: 0.09543567895889282
epoch: 83 training_loss 0.07714095192030072 test_loss: 0.10936769247055053
epoch: 84 training_loss 0.07944721030071378 test_loss: 0.08138748407363891
epoch: 85 training_loss 0.08527394648641348 test_loss: 0.10397036075592041
epoch: 86 training_loss 0.08632984601892531 test_loss: 0.09508928060531616
epoch: 87 training_loss 0.08399916458874941 test_loss: 0.10042351484298706
epoch: 88 training_loss 0.0861091995984316 test_loss: 0.11372815370559693
epoch: 89 training_loss 0.08179701576009393 test_loss: 0.09150208234786987
epoch: 90 training_loss 0.0810909005254507 test_loss: 0.0873927891254425
epoch: 91 training_loss 0.0787503531575203 test_loss: 0.09827996492385864
epoch: 92 training_loss 0.08051434900611638 test_loss: 0.09565430879592896
epoch: 93 training_loss 0.07809846550226211 test_loss: 0.09606141448020936
epoch: 94 training_loss 0.08162841711193324 test_loss: 0.07974476218223572
epoch: 95 training_loss 0.08275483753532172 test_loss: 0.10631011724472046
epoch: 96 training_loss 0.0833452613465488 test_loss: 0.11463947296142578
epoch: 97 training_loss 0.0857384260557592 test_loss: 0.1095091700553894
epoch: 98 training_loss 0.078740667803213 test_loss: 0.10132483243942261
epoch: 99 training_loss 0.07856378061696886 test_loss: 0.08700124025344849
epoch: 100 training_loss 0.08060219693928956 test_loss: 0.09817608594894409
epoch: 101 training_loss 0.08816619233228266 test_loss: 0.10906262397766113
epoch: 102 training_loss 0.0822699567489326 test_loss: 0.09458028078079224
epoch: 103 training_loss 0.0887376968190074 test_loss: 0.10262948274612427
epoch: 104 training_loss 0.08381257822737098 test_loss: 0.09785454869270324
epoch: 105 training_loss 0.08343173876404762 test_loss: 0.10807909965515136
epoch: 106 training_loss 0.09243558414280414 test_loss: 0.10117174386978149
epoch: 107 training_loss 0.08494567330926657 test_loss: 0.08107938766479492
epoch: 108 training_loss 0.0818142899312079 test_loss: 0.08117360472679139
epoch: 109 training_loss 0.07962669609114528 test_loss: 0.10558918714523316
epoch: 110 training_loss 0.07902029033750296 test_loss: 0.08777833580970765
epoch: 111 training_loss 0.08107404202222825 test_loss: 0.09866326451301574
epoch: 112 training_loss 0.0757852259837091 test_loss: 0.09091511368751526
epoch: 113 training_loss 0.07706181927584112 test_loss: 0.08404170870780944
epoch: 114 training_loss 0.08617827279493212 test_loss: 0.08240257501602173
epoch: 115 training_loss 0.07884368782863022 test_loss: 0.10040867328643799
epoch: 116 training_loss 0.0775547386519611 test_loss: 0.10062814950942993
epoch: 117 training_loss 0.07646798545494676 test_loss: 0.09212543368339539
epoch: 118 training_loss 0.07470323855057359 test_loss: 0.11031780242919922
epoch: 119 training_loss 0.07669467038474977 test_loss: 0.1081350564956665
epoch: 120 training_loss 0.08448886793106794 test_loss: 0.11089081764221191
epoch: 121 training_loss 0.08116377761587501 test_loss: 0.10134553909301758
epoch: 122 training_loss 0.07416443174704909 test_loss: 0.09559666514396667
epoch: 123 training_loss 0.07866386267822235 test_loss: 0.08442531824111939
epoch: 124 training_loss 0.07635730117559433 test_loss: 0.0826074719429016
epoch: 125 training_loss 0.07844767305999994 test_loss: 0.10795410871505737
epoch: 126 training_loss 0.08366822961717844 test_loss: 0.09522963762283325
epoch: 127 training_loss 0.08341149000450969 test_loss: 0.09242883920669556
epoch: 128 training_loss 0.0744231148250401 test_loss: 0.09214785695075989
epoch: 129 training_loss 0.07458650350570678 test_loss: 0.1025154709815979
epoch: 130 training_loss 0.07358169160783291 test_loss: 0.10303454399108887
epoch: 131 training_loss 0.0814890094473958 test_loss: 0.09293718934059143
epoch: 132 training_loss 0.078243627846241 test_loss: 0.1059649109840393
epoch: 133 training_loss 0.08020926577970386 test_loss: 0.11609710454940796
epoch: 134 training_loss 0.08403664009645581 test_loss: 0.1059494137763977
epoch: 135 training_loss 0.07453713160008192 test_loss: 0.0952243983745575
epoch: 136 training_loss 0.07722372642718256 test_loss: 0.10878334045410157
epoch: 137 training_loss 0.07310656305402517 test_loss: 0.0888028085231781
epoch: 138 training_loss 0.07995250659063459 test_loss: 0.09035453796386719
epoch: 139 training_loss 0.07671557074412703 test_loss: 0.1050671935081482
epoch: 140 training_loss 0.07617311120964587 test_loss: 0.10768518447875977
epoch: 141 training_loss 0.07512726787477732 test_loss: 0.09042938351631165
epoch: 142 training_loss 0.0753043355140835 test_loss: 0.10381031036376953
epoch: 143 training_loss 0.07611079152673483 test_loss: 0.10241442918777466
epoch: 144 training_loss 0.07408215168863536 test_loss: 0.10143334865570068
epoch: 145 training_loss 0.07254648705944419 test_loss: 0.10169998407363892
epoch: 146 training_loss 0.07376037107780575 test_loss: 0.10969526767730713
epoch: 147 training_loss 0.08004877403378487 test_loss: 0.09625204801559448
epoch: 148 training_loss 0.0744099808577448 test_loss: 0.10683156251907348
epoch: 149 training_loss 0.0770396626740694 test_loss: 0.10202986001968384
epoch: 0 training_loss 0.2642986561357975 test_loss: 0.17367841005325318
epoch: 1 training_loss 0.16163124036043883 test_loss: 0.14543733596801758
epoch: 2 training_loss 0.1422320155799389 test_loss: 0.13254928588867188
epoch: 3 training_loss 0.12754419077187776 test_loss: 0.1048420786857605
epoch: 4 training_loss 0.1167418410629034 test_loss: 0.11763966083526611
epoch: 5 training_loss 0.11437995355576276 test_loss: 0.11605205535888671
epoch: 6 training_loss 0.11084928372874855 test_loss: 0.12220549583435059
epoch: 7 training_loss 0.11057533536106348 test_loss: 0.10092881917953492
epoch: 8 training_loss 0.11174584422260522 test_loss: 0.10180985927581787
epoch: 9 training_loss 0.1080673304386437 test_loss: 0.11557366847991943
epoch: 10 training_loss 0.10803175326436758 test_loss: 0.09831150770187377
epoch: 11 training_loss 0.11464892469346523 test_loss: 0.11942089796066284
epoch: 12 training_loss 0.1075630121305585 test_loss: 0.11861696243286132
epoch: 13 training_loss 0.10302776344120503 test_loss: 0.09041103720664978
epoch: 14 training_loss 0.10321928663179278 test_loss: 0.10557413101196289
epoch: 15 training_loss 0.09673725401982665 test_loss: 0.10565451383590699
epoch: 16 training_loss 0.09130752574652433 test_loss: 0.09673188924789429
epoch: 17 training_loss 0.10606864005327225 test_loss: 0.10213522911071778
epoch: 18 training_loss 0.0924943158403039 test_loss: 0.08539385795593261
epoch: 19 training_loss 0.09240110889077187 test_loss: 0.09833781123161316
epoch: 20 training_loss 0.09688889598473907 test_loss: 0.10984222888946533
epoch: 21 training_loss 0.09149400042369962 test_loss: 0.10640586614608764
epoch: 22 training_loss 0.10315107859671116 test_loss: 0.11345839500427246
epoch: 23 training_loss 0.09096531260758639 test_loss: 0.10235332250595093
epoch: 24 training_loss 0.10079828280955554 test_loss: 0.102017080783844
epoch: 25 training_loss 0.08457165377214551 test_loss: 0.10001946687698364
epoch: 26 training_loss 0.09103809366002678 test_loss: 0.0867088258266449
epoch: 27 training_loss 0.09182204643264413 test_loss: 0.09835930466651917
epoch: 28 training_loss 0.09675033124163747 test_loss: 0.09003108143806457
epoch: 29 training_loss 0.09405807519331574 test_loss: 0.09669869542121887
epoch: 30 training_loss 0.08412999929860235 test_loss: 0.09760413765907287
epoch: 31 training_loss 0.09139933850616216 test_loss: 0.08817211389541627
epoch: 32 training_loss 0.09516084015369415 test_loss: 0.09991306066513062
epoch: 33 training_loss 0.0958954824693501 test_loss: 0.11360402107238769
epoch: 34 training_loss 0.09048241747543216 test_loss: 0.091547292470932
epoch: 35 training_loss 0.09465852921828627 test_loss: 0.09277957677841187
epoch: 36 training_loss 0.09161360088735819 test_loss: 0.08415533304214477
epoch: 37 training_loss 0.08746419943869115 test_loss: 0.10960543155670166
epoch: 38 training_loss 0.09830468207597733 test_loss: 0.10929957628250123
epoch: 39 training_loss 0.09106487175449729 test_loss: 0.10829203128814698
epoch: 40 training_loss 0.09776893632486462 test_loss: 0.09852926135063171
epoch: 41 training_loss 0.08670301357284188 test_loss: 0.10066864490509034
epoch: 42 training_loss 0.09426816483028233 test_loss: 0.08306401371955871
epoch: 43 training_loss 0.08549172267317771 test_loss: 0.09419543147087098
epoch: 44 training_loss 0.08545489836484194 test_loss: 0.09558514952659607
epoch: 45 training_loss 0.09387923393398523 test_loss: 0.10214040279388428
epoch: 46 training_loss 0.08761385709047317 test_loss: 0.08547528982162475
epoch: 47 training_loss 0.08779532991349698 test_loss: 0.09636887907981873
epoch: 48 training_loss 0.08645890075713396 test_loss: 0.09763289093971253
epoch: 49 training_loss 0.08957076653838157 test_loss: 0.09005640149116516
epoch: 50 training_loss 0.08384223315864801 test_loss: 0.08570913076400757
epoch: 51 training_loss 0.09117754306644202 test_loss: 0.09908294677734375
epoch: 52 training_loss 0.09121885478496551 test_loss: 0.09655312299728394
epoch: 53 training_loss 0.0930505033582449 test_loss: 0.08551942110061646
epoch: 54 training_loss 0.09007592521607875 test_loss: 0.09826781153678894
epoch: 55 training_loss 0.08999449882656335 test_loss: 0.09883183240890503
epoch: 56 training_loss 0.09771412758156657 test_loss: 0.0846049964427948
epoch: 57 training_loss 0.08537020618095995 test_loss: 0.09711260795593261
epoch: 58 training_loss 0.09143342349678278 test_loss: 0.09442154765129089
epoch: 59 training_loss 0.08660491237416863 test_loss: 0.09773095846176147
epoch: 60 training_loss 0.09161324799060822 test_loss: 0.09385444521903992
epoch: 61 training_loss 0.08959765383973718 test_loss: 0.10247740745544434
epoch: 62 training_loss 0.09177508534863592 test_loss: 0.0952885627746582
epoch: 63 training_loss 0.08637359630316496 test_loss: 0.10399645566940308
epoch: 64 training_loss 0.08781731383875012 test_loss: 0.08501327633857728
epoch: 65 training_loss 0.0938007102906704 test_loss: 0.09106807708740235
epoch: 66 training_loss 0.08754268219694496 test_loss: 0.10283174514770507
epoch: 67 training_loss 0.08377927020192147 test_loss: 0.09107986688613892
epoch: 68 training_loss 0.0874784410558641 test_loss: 0.09049972891807556
epoch: 69 training_loss 0.08890979081392288 test_loss: 0.08912582397460937
epoch: 70 training_loss 0.08360564591363072 test_loss: 0.09148810505867004
epoch: 71 training_loss 0.08658501993864774 test_loss: 0.08379426598548889
epoch: 72 training_loss 0.0961112997867167 test_loss: 0.10748629570007324
epoch: 73 training_loss 0.08331866815686226 test_loss: 0.09431191086769104
epoch: 74 training_loss 0.0832701875269413 test_loss: 0.08789907097816467
epoch: 75 training_loss 0.09038589499890805 test_loss: 0.09675974249839783
epoch: 76 training_loss 0.0868604015558958 test_loss: 0.0829075276851654
epoch: 77 training_loss 0.08072361649945378 test_loss: 0.09359717965126038
epoch: 78 training_loss 0.08754436010494829 test_loss: 0.0914143443107605
epoch: 79 training_loss 0.08479858284816146 test_loss: 0.09324661493301392
epoch: 80 training_loss 0.08847268536686897 test_loss: 0.08973479866981507
epoch: 81 training_loss 0.08707282263785601 test_loss: 0.09343417882919311
epoch: 82 training_loss 0.08356676930561661 test_loss: 0.101459801197052
epoch: 83 training_loss 0.08690088711678982 test_loss: 0.09531890749931335
epoch: 84 training_loss 0.08473478073254227 test_loss: 0.09652673602104186
epoch: 85 training_loss 0.08329997904598713 test_loss: 0.09928417205810547
epoch: 86 training_loss 0.08198417825624346 test_loss: 0.09623646140098571
epoch: 87 training_loss 0.086680001411587 test_loss: 0.09378472566604615
epoch: 88 training_loss 0.08640699911862612 test_loss: 0.10664663314819336
epoch: 89 training_loss 0.0776017170958221 test_loss: 0.08913658857345581
epoch: 90 training_loss 0.07854032995179296 test_loss: 0.09308536052703857
epoch: 91 training_loss 0.08020365374162793 test_loss: 0.0984818160533905
epoch: 92 training_loss 0.08686337472870946 test_loss: 0.09061534404754638
epoch: 93 training_loss 0.08483021836727858 test_loss: 0.08953108191490174
epoch: 94 training_loss 0.085365967489779 test_loss: 0.09514068961143493
epoch: 95 training_loss 0.0802095527946949 test_loss: 0.0972071647644043
epoch: 96 training_loss 0.08400894720107317 test_loss: 0.08489194512367249
epoch: 97 training_loss 0.08381348934024573 test_loss: 0.07989431619644165
epoch: 98 training_loss 0.0883022771589458 test_loss: 0.10655062198638916
epoch: 99 training_loss 0.08246208669617772 test_loss: 0.0911199152469635
epoch: 100 training_loss 0.08014601577073335 test_loss: 0.1055492639541626
epoch: 101 training_loss 0.08618280433118343 test_loss: 0.09033058881759644
epoch: 102 training_loss 0.08995410064235329 test_loss: 0.10810900926589966
epoch: 103 training_loss 0.08233251951634885 test_loss: 0.09061388373374939
epoch: 104 training_loss 0.08511304309591651 test_loss: 0.09378934502601624
epoch: 105 training_loss 0.08060302012600004 test_loss: 0.09369678497314453
epoch: 106 training_loss 0.0792809179238975 test_loss: 0.10289558172225952
epoch: 107 training_loss 0.0798180266469717 test_loss: 0.09889946579933166
epoch: 108 training_loss 0.07643853539600969 test_loss: 0.08863692879676818
epoch: 109 training_loss 0.0853047651052475 test_loss: 0.0981182336807251
epoch: 110 training_loss 0.08119765117764473 test_loss: 0.08873259425163268
epoch: 111 training_loss 0.08745362957939505 test_loss: 0.10411319732666016
epoch: 112 training_loss 0.08644422085955739 test_loss: 0.08349443674087524
epoch: 113 training_loss 0.0797576617822051 test_loss: 0.08425024747848511
epoch: 114 training_loss 0.08528636738657952 test_loss: 0.09755088090896606
epoch: 115 training_loss 0.08085192022845149 test_loss: 0.10874667167663574
epoch: 116 training_loss 0.0829344497434795 test_loss: 0.0942186713218689
epoch: 117 training_loss 0.07744735917076469 test_loss: 0.10944368839263915
epoch: 118 training_loss 0.08348282070830465 test_loss: 0.09845072627067566
epoch: 119 training_loss 0.07992831761948764 test_loss: 0.09866306185722351
epoch: 120 training_loss 0.07920837309211493 test_loss: 0.09121387004852295
epoch: 121 training_loss 0.08130102775990963 test_loss: 0.09220218062400817
epoch: 122 training_loss 0.07631762991659344 test_loss: 0.09373968839645386
epoch: 123 training_loss 0.08107653413899243 test_loss: 0.10688556432723999
epoch: 124 training_loss 0.0833390592597425 test_loss: 0.08445240259170532
epoch: 125 training_loss 0.08100872803479434 test_loss: 0.09051732420921325
epoch: 126 training_loss 0.08415398884564639 test_loss: 0.0856659471988678
epoch: 127 training_loss 0.0876515083387494 test_loss: 0.1049310326576233
epoch: 128 training_loss 0.07985321052372456 test_loss: 0.09895258545875549
epoch: 129 training_loss 0.07702816648408771 test_loss: 0.0949082612991333
epoch: 130 training_loss 0.08480631807819008 test_loss: 0.09303117990493774
epoch: 131 training_loss 0.08460759313777089 test_loss: 0.1049695372581482
epoch: 132 training_loss 0.08369192643091082 test_loss: 0.10312536954879761
epoch: 133 training_loss 0.08521260255947709 test_loss: 0.08958900570869446
epoch: 134 training_loss 0.08277483658865094 test_loss: 0.0878736436367035
epoch: 135 training_loss 0.07935632667504251 test_loss: 0.08257445693016052
epoch: 136 training_loss 0.08038296606391668 test_loss: 0.10034326314926148
epoch: 137 training_loss 0.08075716728344559 test_loss: 0.07893331050872802
epoch: 138 training_loss 0.07771056842058897 test_loss: 0.09816229343414307
epoch: 139 training_loss 0.07647133926860988 test_loss: 0.1048875093460083
epoch: 140 training_loss 0.08332810723222792 test_loss: 0.0888775646686554
epoch: 141 training_loss 0.08399940185248851 test_loss: 0.10518046617507934
epoch: 142 training_loss 0.08035467174835503 test_loss: 0.09208023548126221
epoch: 143 training_loss 0.08751930065453052 test_loss: 0.09630439281463624
epoch: 144 training_loss 0.07771696062758565 test_loss: 0.09372530579566955
epoch: 145 training_loss 0.0901513610780239 test_loss: 0.08456780314445496
epoch: 146 training_loss 0.0785517003852874 test_loss: 0.09230740070343017
epoch: 147 training_loss 0.0752339300327003 test_loss: 0.09964606761932374
epoch: 148 training_loss 0.07499343995004892 test_loss: 0.083660888671875
epoch: 149 training_loss 0.07955703095532954 test_loss: 0.09275926947593689
episode: 0 training return: -820.3282818017451
episode: 1 training return: -839.8696316268118
episode: 2 training return: -861.8468295397663
episode: 3 training return: -827.4620370258139
epoch: 1 test_true_pfm: -10.841999362854345 sim_pfm: -630.2385286006312
episode: 4 training return: -849.5961246575098
episode: 5 training return: -847.2906357065676
episode: 6 training return: -797.6006793454042
episode: 7 training return: -861.7887745507192
epoch: 2 test_true_pfm: -102.39605498291553 sim_pfm: -874.4112937652432
episode: 8 training return: -816.3934899319418
episode: 9 training return: -831.2748272125659
episode: 10 training return: -891.1224548850989
episode: 11 training return: -842.2307961206751
epoch: 3 test_true_pfm: 150.4892925378959 sim_pfm: -678.6432248563666
episode: 12 training return: -778.8569180528366
episode: 13 training return: -849.9686660851087
episode: 14 training return: -785.3113509001473
episode: 15 training return: -724.2577188550601
epoch: 4 test_true_pfm: -173.68464873871918 sim_pfm: -680.9258404910569
episode: 16 training return: -852.5197534413245
episode: 17 training return: -799.9112920144212
episode: 18 training return: -782.5837658771644
episode: 19 training return: -772.8939157376003
epoch: 5 test_true_pfm: -68.83904888733315 sim_pfm: -775.5077411534653
episode: 20 training return: -760.1768221844809
episode: 21 training return: -701.4621279299195
episode: 22 training return: -763.0841471260263
episode: 23 training return: -788.8241350146365
epoch: 6 test_true_pfm: -324.66957110524135 sim_pfm: -872.2229366507477
episode: 24 training return: -779.4989861521144
episode: 25 training return: -829.3674870452663
episode: 26 training return: -819.6324064700856
episode: 27 training return: -831.0847418844166
epoch: 7 test_true_pfm: 356.33798215649125 sim_pfm: -701.1349839387043
episode: 28 training return: -824.0017856197984
episode: 29 training return: -795.54641045265
episode: 30 training return: -679.8817011848465
episode: 31 training return: -773.48766928747
epoch: 8 test_true_pfm: 437.136242597321 sim_pfm: -692.8932146200223
episode: 32 training return: -790.6733940708963
episode: 33 training return: -668.8373545555406
episode: 34 training return: -660.930825896341
episode: 35 training return: -702.3097524021609
epoch: 9 test_true_pfm: 93.88441272938314 sim_pfm: -614.9084873285657
episode: 36 training return: -760.0362054173684
episode: 37 training return: -677.7796565250502
episode: 38 training return: -632.0994418155252
episode: 39 training return: -702.3895317760873
epoch: 10 test_true_pfm: 462.40931707150054 sim_pfm: -599.1125488686022
episode: 40 training return: -614.8400431486665
episode: 41 training return: -678.4676221892242
episode: 42 training return: -708.9914672823555
episode: 43 training return: -634.6444877506283
epoch: 11 test_true_pfm: 345.188449528979 sim_pfm: -634.4424842339004
episode: 44 training return: -710.8649311671799
episode: 45 training return: -672.6940089230425
episode: 46 training return: -647.9731694488512
episode: 47 training return: -675.478254327203
epoch: 12 test_true_pfm: 197.07314258542044 sim_pfm: -619.9763687414884
episode: 48 training return: -648.7555881362543
episode: 49 training return: -674.6056642339895
episode: 50 training return: -673.9278405954639
episode: 51 training return: -734.9151483320901
epoch: 13 test_true_pfm: 260.90548907253566 sim_pfm: -535.7372100629385
episode: 52 training return: -587.8914891528957
episode: 53 training return: -639.6734426822441
episode: 54 training return: -686.6031538933402
episode: 55 training return: -607.9680458778666
epoch: 14 test_true_pfm: 163.42162830897462 sim_pfm: -625.7501375990004
episode: 56 training return: -630.9701232743695
episode: 57 training return: -645.6196942961201
episode: 58 training return: -606.7769599306856
episode: 59 training return: -587.5382363229741
epoch: 15 test_true_pfm: 32.09671996155035 sim_pfm: -517.8165594149126
episode: 60 training return: -573.320850694814
episode: 61 training return: -628.021659460148
episode: 62 training return: -612.1945192130892
episode: 63 training return: -664.1549316029806
epoch: 16 test_true_pfm: 214.97427890537492 sim_pfm: -585.8631519369725
episode: 64 training return: -597.3387603857434
episode: 65 training return: -563.499080297795
episode: 66 training return: -598.6419428701589
episode: 67 training return: -582.6738887560174
epoch: 17 test_true_pfm: 1.9614860419144844 sim_pfm: -609.3766487367819
episode: 68 training return: -612.0418812673
episode: 69 training return: -590.691417385811
episode: 70 training return: -582.9834194281794
episode: 71 training return: -601.6363302259863
epoch: 18 test_true_pfm: 114.30251048671596 sim_pfm: -516.3810368774454
episode: 72 training return: -631.6869038943013
episode: 73 training return: -586.4726087139987
episode: 74 training return: -586.4505500648514
episode: 75 training return: -656.8582721579941
epoch: 19 test_true_pfm: 147.00661033082486 sim_pfm: -464.9404435941395
episode: 76 training return: -633.8104476459395
episode: 77 training return: -588.0169914090689
episode: 78 training return: -598.3292766183356
episode: 79 training return: -667.0247471581879
epoch: 20 test_true_pfm: 262.0840632507416 sim_pfm: -543.1634624088207
episode: 80 training return: -594.2399867840741
episode: 81 training return: -560.2011828591759
episode: 82 training return: -703.0483047750583
episode: 83 training return: -603.1176248349143
epoch: 21 test_true_pfm: 45.84328683583882 sim_pfm: -528.1599678015033
episode: 84 training return: -619.1817332989856
episode: 85 training return: -562.2211736481086
episode: 86 training return: -603.2850512519747
episode: 87 training return: -916.8860950914217
epoch: 22 test_true_pfm: 113.69049922252516 sim_pfm: -627.3730864701962
episode: 88 training return: -580.2648503018839
episode: 89 training return: -578.2782574955046
episode: 90 training return: -588.9013286830241
episode: 91 training return: -585.1275794996917
epoch: 23 test_true_pfm: 344.4864577665274 sim_pfm: -503.0881670614401
episode: 92 training return: -555.8273119696914
episode: 93 training return: -591.8797173068966
episode: 94 training return: -637.7440070062116
episode: 95 training return: -525.0843698676018
epoch: 24 test_true_pfm: 207.93444300294672 sim_pfm: -543.6419998855214
episode: 96 training return: -603.9968758630088
episode: 97 training return: -651.3438264369917
episode: 98 training return: -581.7130617175353
episode: 99 training return: -627.979424538559
epoch: 25 test_true_pfm: 216.5401074014941 sim_pfm: -486.8412007223181
episode: 100 training return: -606.9476877756777
episode: 101 training return: -634.5233086921819
episode: 102 training return: -592.6351670606401
episode: 103 training return: -569.6862260700482
epoch: 26 test_true_pfm: 385.77961153967254 sim_pfm: -488.03767906489696
episode: 104 training return: -513.2788137811685
episode: 105 training return: -568.8474825366807
episode: 106 training return: -538.6231978094721
episode: 107 training return: -580.5216000428912
epoch: 27 test_true_pfm: 192.5089582993476 sim_pfm: -555.8161077852438
episode: 108 training return: -583.8980383721125
episode: 109 training return: -556.127266887929
episode: 110 training return: -628.2184205875344
episode: 111 training return: -577.3373464978423
epoch: 28 test_true_pfm: 271.19608851214974 sim_pfm: -520.2724147751933
episode: 112 training return: -550.834085321459
episode: 113 training return: -554.1362978752827
episode: 114 training return: -563.3893543233835
episode: 115 training return: -537.5633342958531
epoch: 29 test_true_pfm: 226.49013149691052 sim_pfm: -638.5180123389431
episode: 116 training return: -598.1533057078049
episode: 117 training return: -566.3851300468932
episode: 118 training return: -561.4086502957061
episode: 119 training return: -562.676070677713
epoch: 30 test_true_pfm: 182.20338930899084 sim_pfm: -587.0442614316811
episode: 120 training return: -590.1589878067931
episode: 121 training return: -758.6429529223077
episode: 122 training return: -574.8595679789061
episode: 123 training return: -582.7392491861373
epoch: 31 test_true_pfm: 274.7795791217062 sim_pfm: -516.1715768535224
episode: 124 training return: -535.7416700084035
episode: 125 training return: -541.1791641714354
episode: 126 training return: -569.429155994185
episode: 127 training return: -598.5594167864364
epoch: 32 test_true_pfm: 221.2214572389503 sim_pfm: -492.96834154850245
episode: 128 training return: -580.2786438237969
episode: 129 training return: -582.1319107618681
episode: 130 training return: -628.3943855868107
episode: 131 training return: -555.9994958367603
epoch: 33 test_true_pfm: 154.91514533793523 sim_pfm: -526.3245386567052
episode: 132 training return: -698.7813759648636
episode: 133 training return: -564.0432832426195
episode: 134 training return: -565.7337072874893
episode: 135 training return: -537.7282590850115
epoch: 34 test_true_pfm: 225.29883274999216 sim_pfm: -504.98871929866533
episode: 136 training return: -588.9180471092178
episode: 137 training return: -557.662247444036
episode: 138 training return: -571.8016633673079
episode: 139 training return: -560.2510724709507
epoch: 35 test_true_pfm: 101.48056740129901 sim_pfm: -566.9533967617843
episode: 140 training return: -598.8670489274258
episode: 141 training return: -575.8205737958328
episode: 142 training return: -566.8440367469408
episode: 143 training return: -574.6924980818404
epoch: 36 test_true_pfm: 159.43318612550163 sim_pfm: -548.1424830201785
episode: 144 training return: -555.6117567470421
episode: 145 training return: -585.9560238583576
episode: 146 training return: -539.7016974856552
episode: 147 training return: -560.9335780442768
epoch: 37 test_true_pfm: 294.55960845654073 sim_pfm: -499.327494699185
episode: 148 training return: -549.0179291009279
episode: 149 training return: -590.9553441175568
episode: 150 training return: -575.5398900405058
episode: 151 training return: -610.1956196465552
epoch: 38 test_true_pfm: 397.2196848289263 sim_pfm: -471.5713932945586
episode: 152 training return: -549.9251091699695
episode: 153 training return: -596.1714545178475
episode: 154 training return: -601.9778139405038
episode: 155 training return: -547.2074990336458
epoch: 39 test_true_pfm: 246.4586213091652 sim_pfm: -494.54177408845317
episode: 156 training return: -570.2888830811141
episode: 157 training return: -559.6492818462787
episode: 158 training return: -578.5320240178467
episode: 159 training return: -538.2775533880729
epoch: 40 test_true_pfm: 375.4202770259337 sim_pfm: -455.3531588086899
episode: 160 training return: -562.0342708747623
episode: 161 training return: -539.5331101412361
episode: 162 training return: -537.2864130357787
episode: 163 training return: -606.4136561425711
epoch: 41 test_true_pfm: 239.3429562213987 sim_pfm: -535.2713175655464
episode: 164 training return: -571.6916747367022
episode: 165 training return: -558.385765913226
episode: 166 training return: -604.3584520006591
episode: 167 training return: -535.2164515313265
epoch: 42 test_true_pfm: 372.39837952526403 sim_pfm: -547.0552931817939
episode: 168 training return: -559.0052073322872
episode: 169 training return: -557.2671983305684
episode: 170 training return: -558.6027221566394
episode: 171 training return: -578.7973190160357
epoch: 43 test_true_pfm: 177.15688262025648 sim_pfm: -646.5775448600785
episode: 172 training return: -559.2314766771224
episode: 173 training return: -550.9074839418038
episode: 174 training return: -578.4330472386529
episode: 175 training return: -553.1243950457216
epoch: 44 test_true_pfm: 408.1024032268474 sim_pfm: -458.5464804712606
episode: 176 training return: -573.4881467193782
episode: 177 training return: -741.9982459304423
episode: 178 training return: -576.385507490001
episode: 179 training return: -574.2487947752988
epoch: 45 test_true_pfm: 538.1523658943513 sim_pfm: -442.80413090926123
episode: 180 training return: -508.81251016251787
episode: 181 training return: -524.8242416566932
episode: 182 training return: -568.3290844322809
episode: 183 training return: -546.187096709418
epoch: 46 test_true_pfm: 384.86554553270526 sim_pfm: -610.5861436401668
episode: 184 training return: -548.10201987158
episode: 185 training return: -560.4067739699368
episode: 186 training return: -561.290154845865
episode: 187 training return: -583.4074889342651
epoch: 47 test_true_pfm: 435.2486254500109 sim_pfm: -450.4427419780596
episode: 188 training return: -547.1376449281018
episode: 189 training return: -590.8256129109491
episode: 190 training return: -513.9513487933074
episode: 191 training return: -656.0493352557967
epoch: 48 test_true_pfm: 325.58709680440785 sim_pfm: -569.0221966972117
episode: 192 training return: -558.8223237960273
episode: 193 training return: -572.2537651377418
episode: 194 training return: -509.6551351873685
episode: 195 training return: -571.2502346515497
epoch: 49 test_true_pfm: 505.46810845124537 sim_pfm: -439.3063300094759
episode: 196 training return: -540.5994647385544
episode: 197 training return: -515.8698338126848
episode: 198 training return: -561.0254558346797
episode: 199 training return: -553.6904709990225
epoch: 50 test_true_pfm: 182.60415245287524 sim_pfm: -592.0599257445359
episode: 200 training return: -557.0294611958074
episode: 201 training return: -527.0237835172973
episode: 202 training return: -611.3403043587174
episode: 203 training return: -533.4148022949886
epoch: 51 test_true_pfm: 446.14624421393137 sim_pfm: -426.93795385295954
episode: 204 training return: -573.4176964700072
episode: 205 training return: -518.0272647440895
episode: 206 training return: -554.372158092213
episode: 207 training return: -543.0634529273697
epoch: 52 test_true_pfm: 349.7652215054665 sim_pfm: -499.12920620585766
episode: 208 training return: -554.8034506163556
episode: 209 training return: -541.4016504573124
episode: 210 training return: -534.9301500669341
episode: 211 training return: -549.1145311952195
epoch: 53 test_true_pfm: 509.87348677759445 sim_pfm: -410.23287915926363
episode: 212 training return: -627.5154228716789
episode: 213 training return: -574.4496673570576
episode: 214 training return: -570.1472426193775
episode: 215 training return: -568.2211597583389
epoch: 54 test_true_pfm: 395.44274122041355 sim_pfm: -447.51006181997394
episode: 216 training return: -552.4878202971705
episode: 217 training return: -526.1332875108396
episode: 218 training return: -525.4941268845301
episode: 219 training return: -508.99603878546645
epoch: 55 test_true_pfm: 536.4852258702367 sim_pfm: -438.1928340275413
episode: 220 training return: -526.9231835474997
episode: 221 training return: -553.2670150723003
episode: 222 training return: -536.5416724084934
episode: 223 training return: -571.0101413563588
epoch: 56 test_true_pfm: 380.82351764911664 sim_pfm: -436.8147787648515
episode: 224 training return: -569.9655862328322
episode: 225 training return: -534.47604256604
episode: 226 training return: -565.0913450425039
episode: 227 training return: -540.1675931307944
epoch: 57 test_true_pfm: 459.33888008723665 sim_pfm: -410.7240797056679
episode: 228 training return: -513.146146306044
episode: 229 training return: -495.5757109159895
episode: 230 training return: -526.9539336723253
episode: 231 training return: -536.3121031029453
epoch: 58 test_true_pfm: 464.4908485171829 sim_pfm: -431.02664351103687
episode: 232 training return: -512.908803634551
episode: 233 training return: -579.608703704253
episode: 234 training return: -547.8129979604732
episode: 235 training return: -535.8851949180225
epoch: 59 test_true_pfm: 570.091160730342 sim_pfm: -425.7292292329676
episode: 236 training return: -559.6439500103698
episode: 237 training return: -580.2634820835096
episode: 238 training return: -552.0139928889432
episode: 239 training return: -557.9901037840242
epoch: 60 test_true_pfm: 240.9758815643852 sim_pfm: -498.52182673462784
episode: 240 training return: -522.4932061491669
episode: 241 training return: -522.2991027677595
episode: 242 training return: -571.3728953075226
episode: 243 training return: -548.0232894376462
epoch: 61 test_true_pfm: 533.2708961836786 sim_pfm: -534.8245788881476
episode: 244 training return: -526.181352489253
episode: 245 training return: -578.470152212086
episode: 246 training return: -548.8556318817967
episode: 247 training return: -525.6550123069975
epoch: 62 test_true_pfm: 550.8556687268004 sim_pfm: -412.82229712268185
episode: 248 training return: -556.0707456096023
episode: 249 training return: -548.0158179363922
episode: 250 training return: -544.4239277910241
episode: 251 training return: -495.16218553748604
epoch: 63 test_true_pfm: 612.3561703951932 sim_pfm: -411.34832106502887
episode: 252 training return: -469.0487960903556
episode: 253 training return: -515.3779161089875
episode: 254 training return: -550.5929816796676
episode: 255 training return: -517.9234365736853
epoch: 64 test_true_pfm: 635.5192745778712 sim_pfm: -424.4465873821398
episode: 256 training return: -520.6376852140178
episode: 257 training return: -522.379295391589
episode: 258 training return: -564.6215623512348
episode: 259 training return: -537.9056165985021
epoch: 65 test_true_pfm: 435.89539059415625 sim_pfm: -442.90716536308014
episode: 260 training return: -568.2811779949975
episode: 261 training return: -561.0525107730831
episode: 262 training return: -570.9364740538954
episode: 263 training return: -504.4847089940868
epoch: 66 test_true_pfm: 543.1901190036875 sim_pfm: -411.92090170928196
episode: 264 training return: -542.0672077723365
episode: 265 training return: -538.3807846149994
episode: 266 training return: -539.3899343930582
episode: 267 training return: -501.02572351472116
epoch: 67 test_true_pfm: 487.262339620707 sim_pfm: -528.1366766202458
episode: 268 training return: -519.2934355104494
episode: 269 training return: -549.4404160031229
episode: 270 training return: -569.8166368067439
episode: 271 training return: -549.6739546184184
epoch: 68 test_true_pfm: 493.7079762717896 sim_pfm: -445.2232316906054
episode: 272 training return: -536.5035892067668
episode: 273 training return: -569.0968958814877
episode: 274 training return: -526.4607708751236
episode: 275 training return: -549.4434346165507
epoch: 69 test_true_pfm: 551.0833994711309 sim_pfm: -420.040102091267
episode: 276 training return: -536.9824768645616
episode: 277 training return: -529.4395800734496
episode: 278 training return: -528.0138545160634
episode: 279 training return: -526.5655051846306
epoch: 70 test_true_pfm: 399.57138205352436 sim_pfm: -540.2759836345764
episode: 280 training return: -524.0911746998869
episode: 281 training return: -497.80074817393677
episode: 282 training return: -510.0408437599215
episode: 283 training return: -506.72973830718416
epoch: 71 test_true_pfm: 531.2806517220879 sim_pfm: -418.08293157436265
episode: 284 training return: -494.8281259956331
episode: 285 training return: -503.520668011089
episode: 286 training return: -539.8920278644623
episode: 287 training return: -505.75282918666653
epoch: 72 test_true_pfm: 457.2310579357592 sim_pfm: -432.86655957665033
episode: 288 training return: -536.6052398686958
episode: 289 training return: -498.813662273275
episode: 290 training return: -543.1563352679626
episode: 291 training return: -517.601271709435
epoch: 73 test_true_pfm: 484.9169889765173 sim_pfm: -431.5826061949435
episode: 292 training return: -509.6293528030957
episode: 293 training return: -546.365868333847
episode: 294 training return: -544.350591973738
episode: 295 training return: -541.7907593964326
epoch: 74 test_true_pfm: 539.2403733207398 sim_pfm: -418.5161186228111
episode: 296 training return: -516.8832795417327
episode: 297 training return: -479.1937716878466
episode: 298 training return: -509.5786573403295
episode: 299 training return: -551.0845053483297
epoch: 75 test_true_pfm: 455.52635232570515 sim_pfm: -440.4158520657888
episode: 300 training return: -503.14194241287373
episode: 301 training return: -541.8949672212938
episode: 302 training return: -532.4805936807177
episode: 303 training return: -534.3694773750359
epoch: 76 test_true_pfm: 533.1483050716612 sim_pfm: -405.64451135795906
episode: 304 training return: -539.631125644774
episode: 305 training return: -550.4762040248936
episode: 306 training return: -535.3433901104137
episode: 307 training return: -537.4360479716481
epoch: 77 test_true_pfm: 538.3819986399895 sim_pfm: -403.75588151719245
episode: 308 training return: -550.0568584563946
episode: 309 training return: -515.7180379094556
episode: 310 training return: -518.2859266404258
episode: 311 training return: -535.4010965423151
epoch: 78 test_true_pfm: 555.6032633264876 sim_pfm: -413.0081429514897
episode: 312 training return: -524.3489373852807
episode: 313 training return: -519.1334101841013
episode: 314 training return: -509.0186468302891
episode: 315 training return: -509.2492732218918
epoch: 79 test_true_pfm: 503.558095275541 sim_pfm: -423.6335675005585
episode: 316 training return: -563.9731960405694
episode: 317 training return: -526.2344718080296
episode: 318 training return: -554.4023919059822
episode: 319 training return: -524.205319965289
epoch: 80 test_true_pfm: 366.9763042350123 sim_pfm: -433.83973049543846
episode: 320 training return: -504.90199737973734
episode: 321 training return: -517.1928966072862
episode: 322 training return: -579.4092728563184
episode: 323 training return: -539.7264206748325
epoch: 81 test_true_pfm: 495.91095234254243 sim_pfm: -416.8024145024736
episode: 324 training return: -529.9553088240807
episode: 325 training return: -485.22056766924703
episode: 326 training return: -502.6742766904372
episode: 327 training return: -556.9128749591953
epoch: 82 test_true_pfm: 479.67784175520137 sim_pfm: -429.3892275559965
episode: 328 training return: -548.9291564816828
episode: 329 training return: -528.6926597046526
episode: 330 training return: -543.7900744442418
episode: 331 training return: -499.79272849901145
epoch: 83 test_true_pfm: 599.7260306949187 sim_pfm: -409.65220185915103
episode: 332 training return: -567.9103228185538
episode: 333 training return: -546.0631741744841
episode: 334 training return: -528.1137629470388
episode: 335 training return: -566.1676476748763
epoch: 84 test_true_pfm: 471.73190453645606 sim_pfm: -414.438095323665
episode: 336 training return: -482.9472182775758
episode: 337 training return: -758.4064835431551
episode: 338 training return: -540.3130340136365
episode: 339 training return: -521.9486007768015
epoch: 85 test_true_pfm: 412.2639172423912 sim_pfm: -451.66983870588183
episode: 340 training return: -485.19939575074136
episode: 341 training return: -525.681551729758
episode: 342 training return: -531.2552277995162
episode: 343 training return: -538.7791253847495
epoch: 86 test_true_pfm: 477.04159503611294 sim_pfm: -428.66450975838046
episode: 344 training return: -480.1762075930261
episode: 345 training return: -516.1282506896778
episode: 346 training return: -541.7659858761011
episode: 347 training return: -518.9032406443032
epoch: 87 test_true_pfm: 576.4045416075799 sim_pfm: -424.6824451096152
episode: 348 training return: -547.5912663160965
episode: 349 training return: -528.3249954596348
episode: 350 training return: -542.047005427638
episode: 351 training return: -506.5202204723566
epoch: 88 test_true_pfm: 515.1686764100128 sim_pfm: -448.4789295285879
episode: 352 training return: -533.4829023211718
episode: 353 training return: -537.0181419997213
episode: 354 training return: -527.3440598715484
episode: 355 training return: -533.9293546193594
epoch: 89 test_true_pfm: 483.70441017710965 sim_pfm: -441.84451867337907
episode: 356 training return: -509.4325699703738
episode: 357 training return: -566.5048342815076
episode: 358 training return: -545.1472636015671
episode: 359 training return: -498.3011467967479
epoch: 90 test_true_pfm: 450.4362135435206 sim_pfm: -425.15138385917567
episode: 360 training return: -497.54582021719534
episode: 361 training return: -526.2771013139788
episode: 362 training return: -523.0285617223913
episode: 363 training return: -553.6286269788936
epoch: 91 test_true_pfm: 486.3745147574832 sim_pfm: -427.2112120099866
episode: 364 training return: -533.980867411586
episode: 365 training return: -546.2341627099497
episode: 366 training return: -540.5407137312749
episode: 367 training return: -528.5391880204312
epoch: 92 test_true_pfm: 521.0591054045112 sim_pfm: -459.7907786722739
episode: 368 training return: -500.87684214084925
episode: 369 training return: -538.5944646402436
episode: 370 training return: -533.3422857821896
episode: 371 training return: -518.1032729510313
epoch: 93 test_true_pfm: 429.33005791407294 sim_pfm: -459.2065911032082
episode: 372 training return: -527.0845204720301
episode: 373 training return: -531.009469089286
episode: 374 training return: -536.5879921190025
episode: 375 training return: -511.6842846134384
epoch: 94 test_true_pfm: 602.1707361406643 sim_pfm: -431.85129584995934
episode: 376 training return: -531.6166723131922
episode: 377 training return: -480.6812707108382
episode: 378 training return: -521.3920195068529
episode: 379 training return: -539.4887061960146
epoch: 95 test_true_pfm: 548.928571276667 sim_pfm: -423.2618109665043
episode: 380 training return: -542.3102443250643
episode: 381 training return: -491.28832230893016
episode: 382 training return: -545.5572569862852
episode: 383 training return: -547.1472326424151
epoch: 96 test_true_pfm: 442.0187928128411 sim_pfm: -439.9731707030566
episode: 384 training return: -540.1940367860334
episode: 385 training return: -505.45117010933797
episode: 386 training return: -542.3097153059053
episode: 387 training return: -492.247433055236
epoch: 97 test_true_pfm: 527.591552929849 sim_pfm: -415.6551411897448
episode: 388 training return: -503.96784992622497
episode: 389 training return: -552.1246780275023
episode: 390 training return: -525.1868241284029
episode: 391 training return: -533.0084521287979
epoch: 98 test_true_pfm: 508.210398065293 sim_pfm: -413.4995573446269
episode: 392 training return: -525.6070825459486
episode: 393 training return: -523.9863934295682
episode: 394 training return: -516.4508012979662
episode: 395 training return: -518.7346088323037
epoch: 99 test_true_pfm: 589.0537858326363 sim_pfm: -441.63714008533094
episode: 396 training return: -499.7533712658806
episode: 397 training return: -531.9584513707096
episode: 398 training return: -523.193717130567
episode: 399 training return: -527.3417287335797
epoch: 100 test_true_pfm: 429.5370100187005 sim_pfm: -424.8758446631673
episode: 400 training return: -517.804561153906
episode: 401 training return: -548.1961689694008
episode: 402 training return: -504.3933036975775
episode: 403 training return: -553.2111927100041
epoch: 101 test_true_pfm: 485.82618887106673 sim_pfm: -445.47128469674345
episode: 404 training return: -559.1421857782185
episode: 405 training return: -532.5165883224872
episode: 406 training return: -541.6417923154548
episode: 407 training return: -563.8566742141088
epoch: 102 test_true_pfm: 551.7754444920065 sim_pfm: -420.3442799018848
episode: 408 training return: -511.98954196168097
episode: 409 training return: -490.833599228295
episode: 410 training return: -520.7050166218232
episode: 411 training return: -559.4978361087743
epoch: 103 test_true_pfm: 709.645298706448 sim_pfm: -400.0966785037728
episode: 412 training return: -547.6412314971872
episode: 413 training return: -537.7696526485458
episode: 414 training return: -547.6677601183843
episode: 415 training return: -506.53475707491003
epoch: 104 test_true_pfm: 588.9419262002585 sim_pfm: -397.592318347663
episode: 416 training return: -528.3674310802835
episode: 417 training return: -553.2338733230642
episode: 418 training return: -541.7469765817625
episode: 419 training return: -546.6178903223976
epoch: 105 test_true_pfm: 490.53978811587876 sim_pfm: -433.93501643306314
episode: 420 training return: -511.6874567489535
episode: 421 training return: -590.918366234091
episode: 422 training return: -509.17944202128007
episode: 423 training return: -478.38782278075973
epoch: 106 test_true_pfm: 554.2579528330189 sim_pfm: -409.3344156274173
episode: 424 training return: -530.5156463415145
episode: 425 training return: -514.4599522368509
episode: 426 training return: -531.7052688023074
episode: 427 training return: -487.59740034816485
epoch: 107 test_true_pfm: 513.1020183418192 sim_pfm: -411.5838676383136
episode: 428 training return: -472.8471271069456
episode: 429 training return: -517.7865445580616
episode: 430 training return: -525.4041811179226
episode: 431 training return: -484.9251358202527
epoch: 108 test_true_pfm: 441.96501285481713 sim_pfm: -460.65236094342
episode: 432 training return: -537.6778632279975
episode: 433 training return: -480.7873283173803
episode: 434 training return: -525.9914113601027
episode: 435 training return: -495.2858084193283
epoch: 109 test_true_pfm: 432.8125698121271 sim_pfm: -427.42961571320274
episode: 436 training return: -493.5998535783559
episode: 437 training return: -490.9675425029108
episode: 438 training return: -518.1965778671139
episode: 439 training return: -522.7804199779986
epoch: 110 test_true_pfm: 449.7430919151812 sim_pfm: -439.11521212344746
episode: 440 training return: -547.2564158297989
episode: 441 training return: -518.5309786599304
episode: 442 training return: -568.5122637494463
episode: 443 training return: -518.6712324709343
epoch: 111 test_true_pfm: 519.5091346443252 sim_pfm: -436.38823109111553
episode: 444 training return: -531.6634641750613
episode: 445 training return: -537.6448971161732
episode: 446 training return: -521.6010262860107
episode: 447 training return: -517.5062381453921
epoch: 112 test_true_pfm: 512.2052138536326 sim_pfm: -427.22347774744503
episode: 448 training return: -495.3934351328707
episode: 449 training return: -536.3011595152893
episode: 450 training return: -525.5928209193822
episode: 451 training return: -494.7161023759828
epoch: 113 test_true_pfm: 447.2204133983018 sim_pfm: -413.4836883476467
episode: 452 training return: -494.4173810469152
episode: 453 training return: -508.9482028377012
episode: 454 training return: -489.4671420625578
episode: 455 training return: -519.446675725685
epoch: 114 test_true_pfm: 568.5251830340358 sim_pfm: -424.8276580606171
episode: 456 training return: -509.87521588439347
episode: 457 training return: -530.4681784089414
episode: 458 training return: -518.030216928885
episode: 459 training return: -540.7597586373058
epoch: 115 test_true_pfm: 510.1204648944932 sim_pfm: -409.12637950760046
episode: 460 training return: -499.58757926790787
episode: 461 training return: -529.2038942181956
episode: 462 training return: -517.6338100052396
episode: 463 training return: -523.7537783378395
epoch: 116 test_true_pfm: 446.0068360515082 sim_pfm: -458.71883658720753
episode: 464 training return: -533.1213254266886
episode: 465 training return: -533.8452552597678
episode: 466 training return: -516.5288080998828
episode: 467 training return: -533.6282533201253
epoch: 117 test_true_pfm: 415.4400662636925 sim_pfm: -431.78121489637357
episode: 468 training return: -555.5547619384348
episode: 469 training return: -513.2901254854494
episode: 470 training return: -472.6649135142966
episode: 471 training return: -548.8982413398422
epoch: 118 test_true_pfm: 572.4994615107472 sim_pfm: -425.0667363306114
episode: 472 training return: -494.52683564087386
episode: 473 training return: -528.3569606656127
episode: 474 training return: -523.5535725490397
episode: 475 training return: -524.043752368935
epoch: 119 test_true_pfm: 527.6822728587985 sim_pfm: -428.486460532561
episode: 476 training return: -522.0696844586776
episode: 477 training return: -489.10041353738006
episode: 478 training return: -535.92921389397
episode: 479 training return: -522.406507733687
epoch: 120 test_true_pfm: 437.1424616945454 sim_pfm: -415.38591117937193
episode: 480 training return: -523.572920035326
episode: 481 training return: -507.2507537618706
episode: 482 training return: -543.8121126997785
episode: 483 training return: -507.4172481224069
epoch: 121 test_true_pfm: 463.11606793351945 sim_pfm: -453.4152925961703
episode: 484 training return: -529.0295770745898
episode: 485 training return: -537.175474685525
episode: 486 training return: -522.7511394420543
episode: 487 training return: -548.7586154706341
epoch: 122 test_true_pfm: 536.8618485505573 sim_pfm: -410.805872744073
episode: 488 training return: -495.222524475946
episode: 489 training return: -546.6889593289959
episode: 490 training return: -501.68895488748467
episode: 491 training return: -523.6594265581758
epoch: 123 test_true_pfm: 486.2671785771516 sim_pfm: -429.90111421088585
episode: 492 training return: -534.9121448467347
episode: 493 training return: -542.1163364706866
episode: 494 training return: -541.1001402339907
episode: 495 training return: -501.1991358356737
epoch: 124 test_true_pfm: 488.0994622590347 sim_pfm: -424.99687714121757
episode: 496 training return: -532.6904132865175
episode: 497 training return: -484.18509692693647
episode: 498 training return: -523.6050002557295
episode: 499 training return: -477.18413381863377
epoch: 125 test_true_pfm: 498.75727812642054 sim_pfm: -403.3551597644812
episode: 500 training return: -534.8037163103909
episode: 501 training return: -508.8719542836246
episode: 502 training return: -554.938803587138
episode: 503 training return: -504.2654037172411
epoch: 126 test_true_pfm: 465.97530494822155 sim_pfm: -449.61211071567595
episode: 504 training return: -531.2018493052514
episode: 505 training return: -520.4555086468806
episode: 506 training return: -524.7153007727848
episode: 507 training return: -536.518541225986
epoch: 127 test_true_pfm: 465.014778828561 sim_pfm: -405.95735697199626
episode: 508 training return: -498.1908406990112
episode: 509 training return: -509.09407483816307
episode: 510 training return: -500.8415685770007
episode: 511 training return: -540.4074268360401
epoch: 128 test_true_pfm: 533.778115916933 sim_pfm: -426.72826618091216
episode: 512 training return: -536.1092345233197
episode: 513 training return: -523.0355008481166
episode: 514 training return: -516.2426571659793
episode: 515 training return: -521.3663582865911
epoch: 129 test_true_pfm: 504.09010651659537 sim_pfm: -419.56719640876935
episode: 516 training return: -502.8583145828035
episode: 517 training return: -513.7956176943059
episode: 518 training return: -503.0919627620608
episode: 519 training return: -488.6536232250231
epoch: 130 test_true_pfm: 466.6279494082928 sim_pfm: -442.06238035788647
episode: 520 training return: -520.5895611504255
episode: 521 training return: -495.6702649251645
episode: 522 training return: -506.6180201961827
episode: 523 training return: -521.2753513542559
epoch: 131 test_true_pfm: 442.065699447535 sim_pfm: -447.385105334741
episode: 524 training return: -513.224822883707
episode: 525 training return: -580.7994141474007
episode: 526 training return: -481.51429785836586
episode: 527 training return: -506.0448071395545
epoch: 132 test_true_pfm: 489.77433369144586 sim_pfm: -405.78294574696224
episode: 528 training return: -533.1430051332248
episode: 529 training return: -544.0349551424868
episode: 530 training return: -499.75353147553807
episode: 531 training return: -509.3052856692663
epoch: 133 test_true_pfm: 476.3361754016914 sim_pfm: -418.6669396517121
episode: 532 training return: -511.41688815183653
episode: 533 training return: -491.27669837187807
episode: 534 training return: -517.069479778028
episode: 535 training return: -509.98554492601556
epoch: 134 test_true_pfm: 459.0979871465816 sim_pfm: -402.136245824721
episode: 536 training return: -534.2793421292872
episode: 537 training return: -551.4301644492155
episode: 538 training return: -478.54529632597223
episode: 539 training return: -514.8751720997982
epoch: 135 test_true_pfm: 511.24224219640263 sim_pfm: -422.4050835996427
episode: 540 training return: -524.4711929046615
episode: 541 training return: -502.97572411152004
episode: 542 training return: -571.9735324148163
episode: 543 training return: -551.054456100936
epoch: 136 test_true_pfm: 542.3478952707688 sim_pfm: -409.26363789466114
episode: 544 training return: -495.76546182737025
episode: 545 training return: -521.6928105497688
episode: 546 training return: -500.5670518667399
episode: 547 training return: -510.3164187356417
epoch: 137 test_true_pfm: 467.4703904331125 sim_pfm: -431.06012682554274
episode: 548 training return: -500.13529671180015
episode: 549 training return: -511.9631178572071
episode: 550 training return: -468.7678066815827
episode: 551 training return: -541.3629363847404
epoch: 138 test_true_pfm: 600.7460365825688 sim_pfm: -408.538216605904
episode: 552 training return: -527.733407476454
episode: 553 training return: -548.836865877458
episode: 554 training return: -504.8246485904937
episode: 555 training return: -499.18706200904677
epoch: 139 test_true_pfm: 494.6362117513375 sim_pfm: -410.8032591994432
episode: 556 training return: -518.6275822387973
episode: 557 training return: -497.0413447069993
episode: 558 training return: -522.4841429640262
episode: 559 training return: -510.9545084467986
epoch: 140 test_true_pfm: 406.20277247080816 sim_pfm: -428.0683697532222
episode: 560 training return: -482.29854486931487
episode: 561 training return: -533.0834335222454
episode: 562 training return: -554.5238231048421
episode: 563 training return: -507.5322608329466
epoch: 141 test_true_pfm: 489.51496548940764 sim_pfm: -418.3998797958582
episode: 564 training return: -513.4451037849836
episode: 565 training return: -544.7770654071821
episode: 566 training return: -486.1943006984828
episode: 567 training return: -514.7178964813969
epoch: 142 test_true_pfm: 491.93226269145083 sim_pfm: -425.04645245004457
episode: 568 training return: -510.1942649617732
episode: 569 training return: -481.58976749232755
episode: 570 training return: -533.1140743764851
episode: 571 training return: -565.5995686690258
epoch: 143 test_true_pfm: 469.0786102201564 sim_pfm: -423.9215584369395
episode: 572 training return: -519.746967833069
episode: 573 training return: -513.7807911998335
episode: 574 training return: -554.5231574188862
episode: 575 training return: -498.84955671323695
epoch: 144 test_true_pfm: 390.19431264120095 sim_pfm: -416.2112836515359
episode: 576 training return: -518.2629500535337
episode: 577 training return: -515.0312032442442
episode: 578 training return: -540.5289533281903
episode: 579 training return: -532.4094159171028
epoch: 145 test_true_pfm: 471.71941233181127 sim_pfm: -406.2859585180383
episode: 580 training return: -522.0723494123656
episode: 581 training return: -491.1304205936178
episode: 582 training return: -481.30729644990873
episode: 583 training return: -535.4596824962994
epoch: 146 test_true_pfm: 348.18838399347555 sim_pfm: -414.106237960451
episode: 584 training return: -473.42557207315724
episode: 585 training return: -546.9192149526122
episode: 586 training return: -502.6036555251979
episode: 587 training return: -509.08527168720445
epoch: 147 test_true_pfm: 419.7791081206483 sim_pfm: -422.1380333806715
episode: 588 training return: -506.5500433881412
episode: 589 training return: -525.0016521050363
episode: 590 training return: -488.6519162291965
episode: 591 training return: -559.752343334863
epoch: 148 test_true_pfm: 461.11060163166394 sim_pfm: -403.32438463453644
episode: 592 training return: -534.9072371345338
episode: 593 training return: -493.1913544724441
episode: 594 training return: -511.2823488091307
episode: 595 training return: -523.0471394872602
epoch: 149 test_true_pfm: 500.53143096351715 sim_pfm: -412.6703346188671
episode: 596 training return: -515.2495669651067
episode: 597 training return: -514.4236567668426
episode: 598 training return: -488.7520841655588
episode: 599 training return: -502.2838040246855
epoch: 150 test_true_pfm: 532.7022587203273 sim_pfm: -403.8095166698338
