['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '1', '--data', '30000']
epoch: 0 training_loss 0.2816834409534931 test_loss: 0.21510372161865235
epoch: 1 training_loss 0.20362293407320975 test_loss: 0.18475656509399413
epoch: 2 training_loss 0.19408834278583526 test_loss: 0.1901428818702698
epoch: 3 training_loss 0.20097172893583776 test_loss: 0.18012179136276246
epoch: 4 training_loss 0.1931944940239191 test_loss: 0.16404825448989868
epoch: 5 training_loss 0.1880903148651123 test_loss: 0.1909806728363037
epoch: 6 training_loss 0.2012173816561699 test_loss: 0.19161179065704345
epoch: 7 training_loss 0.1990804998576641 test_loss: 0.18668510913848876
epoch: 8 training_loss 0.18563909582793714 test_loss: 0.19726991653442383
epoch: 9 training_loss 0.1838534640520811 test_loss: 0.18027175664901735
epoch: 10 training_loss 0.19310912750661374 test_loss: 0.18038949966430665
epoch: 11 training_loss 0.18906304195523263 test_loss: 0.1900203824043274
epoch: 12 training_loss 0.18725596770644187 test_loss: 0.16653496026992798
epoch: 13 training_loss 0.18642071440815924 test_loss: 0.19685332775115966
epoch: 14 training_loss 0.1929891436547041 test_loss: 0.1816534399986267
epoch: 15 training_loss 0.1749561884254217 test_loss: 0.18536592721939088
epoch: 16 training_loss 0.18841109834611416 test_loss: 0.1751886487007141
epoch: 17 training_loss 0.1918514361977577 test_loss: 0.17941733598709106
epoch: 18 training_loss 0.18368487536907196 test_loss: 0.17278233766555787
epoch: 19 training_loss 0.1896407537907362 test_loss: 0.17848403453826905
epoch: 20 training_loss 0.18118989773094654 test_loss: 0.1751032829284668
epoch: 21 training_loss 0.18603187933564186 test_loss: 0.18585096597671508
epoch: 22 training_loss 0.18090804055333137 test_loss: 0.20024068355560304
epoch: 23 training_loss 0.19104467391967772 test_loss: 0.19067015647888183
epoch: 24 training_loss 0.18136489249765872 test_loss: 0.15562353134155274
epoch: 25 training_loss 0.17947891809046268 test_loss: 0.18412011861801147
epoch: 26 training_loss 0.18799518108367919 test_loss: 0.17754127979278564
epoch: 27 training_loss 0.1822847843915224 test_loss: 0.17502723932266234
epoch: 28 training_loss 0.1894474608451128 test_loss: 0.185744571685791
epoch: 29 training_loss 0.19090467296540736 test_loss: 0.1849857449531555
epoch: 30 training_loss 0.18724010087549686 test_loss: 0.1785157084465027
epoch: 31 training_loss 0.18403243742883205 test_loss: 0.17649444341659545
epoch: 32 training_loss 0.1816284606605768 test_loss: 0.16802061796188356
epoch: 33 training_loss 0.18862591430544853 test_loss: 0.18716763257980346
epoch: 34 training_loss 0.18546024955809115 test_loss: 0.17711340188980101
epoch: 35 training_loss 0.18386935822665693 test_loss: 0.17593169212341309
epoch: 36 training_loss 0.1783747286349535 test_loss: 0.19092109203338622
epoch: 37 training_loss 0.18679328970611095 test_loss: 0.18459708690643312
epoch: 38 training_loss 0.17505379520356656 test_loss: 0.16599186658859252
epoch: 39 training_loss 0.17465723387897014 test_loss: 0.17432564496994019
epoch: 40 training_loss 0.17583617903292179 test_loss: 0.16124702692031861
epoch: 41 training_loss 0.17754942268133164 test_loss: 0.17413628101348877
epoch: 42 training_loss 0.1840531299263239 test_loss: 0.17504556179046632
epoch: 43 training_loss 0.17649436347186565 test_loss: 0.18072001934051513
epoch: 44 training_loss 0.17623411037027836 test_loss: 0.1688772439956665
epoch: 45 training_loss 0.18132992453873156 test_loss: 0.18185664415359498
epoch: 46 training_loss 0.18175140276551247 test_loss: 0.1759824275970459
epoch: 47 training_loss 0.18321163088083267 test_loss: 0.17033811807632446
epoch: 48 training_loss 0.18928824476897715 test_loss: 0.18181982040405273
epoch: 49 training_loss 0.17958663009107112 test_loss: 0.19908126592636108
epoch: 50 training_loss 0.17979721151292324 test_loss: 0.1760133385658264
epoch: 51 training_loss 0.18121652737259863 test_loss: 0.17435624599456787
epoch: 52 training_loss 0.18294478178024293 test_loss: 0.19231753349304198
epoch: 53 training_loss 0.18135745897889138 test_loss: 0.17814079523086548
epoch: 54 training_loss 0.1829515154659748 test_loss: 0.16799782514572142
epoch: 55 training_loss 0.18277983486652374 test_loss: 0.18372728824615478
epoch: 56 training_loss 0.1805841501057148 test_loss: 0.16036430597305298
epoch: 57 training_loss 0.1788790649175644 test_loss: 0.1754133701324463
epoch: 58 training_loss 0.17373273834586145 test_loss: 0.1792243242263794
epoch: 59 training_loss 0.17709530457854272 test_loss: 0.18336894512176513
epoch: 60 training_loss 0.17362644381821155 test_loss: 0.17314161062240602
epoch: 61 training_loss 0.17811642423272134 test_loss: 0.17826906442642212
epoch: 62 training_loss 0.16988130055367948 test_loss: 0.16821457147598268
epoch: 63 training_loss 0.1836215642094612 test_loss: 0.1675809621810913
epoch: 64 training_loss 0.18066717833280563 test_loss: 0.18135117292404174
epoch: 65 training_loss 0.17573414273560048 test_loss: 0.17159550189971923
epoch: 66 training_loss 0.17692314364016057 test_loss: 0.17046692371368408
epoch: 67 training_loss 0.17257293961942197 test_loss: 0.18168745040893555
epoch: 68 training_loss 0.1867913721501827 test_loss: 0.174096417427063
epoch: 69 training_loss 0.18065025709569454 test_loss: 0.16449522972106934
epoch: 70 training_loss 0.1779134726524353 test_loss: 0.1793235421180725
epoch: 71 training_loss 0.17397504590451718 test_loss: 0.16240437030792237
epoch: 72 training_loss 0.18308599531650543 test_loss: 0.17814143896102905
epoch: 73 training_loss 0.1730108819156885 test_loss: 0.16956789493560792
epoch: 74 training_loss 0.1785805717855692 test_loss: 0.17416986227035522
epoch: 75 training_loss 0.17581967264413834 test_loss: 0.18065414428710938
epoch: 76 training_loss 0.175909695699811 test_loss: 0.1633324384689331
epoch: 77 training_loss 0.1701243521273136 test_loss: 0.18289828300476074
epoch: 78 training_loss 0.17830833487212658 test_loss: 0.16326050758361815
epoch: 79 training_loss 0.18427882745862006 test_loss: 0.17247042655944825
epoch: 80 training_loss 0.18434727676212787 test_loss: 0.17915432453155516
epoch: 81 training_loss 0.1720946364104748 test_loss: 0.1712595820426941
epoch: 82 training_loss 0.17621326431632042 test_loss: 0.16772148609161378
epoch: 83 training_loss 0.17181064665317536 test_loss: 0.18568044900894165
epoch: 84 training_loss 0.17715650595724583 test_loss: 0.18848392963409424
epoch: 85 training_loss 0.18564663633704184 test_loss: 0.17522553205490113
epoch: 86 training_loss 0.1744104991108179 test_loss: 0.17138664722442626
epoch: 87 training_loss 0.18616537839174271 test_loss: 0.1728031277656555
epoch: 88 training_loss 0.17793003216385841 test_loss: 0.17769016027450563
epoch: 89 training_loss 0.18521774426102638 test_loss: 0.17771681547164916
epoch: 90 training_loss 0.17649310387670994 test_loss: 0.17239664793014525
epoch: 91 training_loss 0.17215240068733692 test_loss: 0.16280936002731322
epoch: 92 training_loss 0.1743928576260805 test_loss: 0.18235830068588257
epoch: 93 training_loss 0.17668875232338904 test_loss: 0.1641393780708313
epoch: 94 training_loss 0.17377645432949065 test_loss: 0.17188631296157836
epoch: 95 training_loss 0.17309881754219533 test_loss: 0.17167530059814454
epoch: 96 training_loss 0.1797231312841177 test_loss: 0.1642999529838562
epoch: 97 training_loss 0.176398196965456 test_loss: 0.1646339178085327
epoch: 98 training_loss 0.16571569822728635 test_loss: 0.16612184047698975
epoch: 99 training_loss 0.18346557669341565 test_loss: 0.1812480092048645
epoch: 100 training_loss 0.176369102075696 test_loss: 0.1670607566833496
epoch: 101 training_loss 0.18035393096506597 test_loss: 0.15763100385665893
epoch: 102 training_loss 0.1696740060299635 test_loss: 0.18019654750823974
epoch: 103 training_loss 0.18015161782503128 test_loss: 0.16458396911621093
epoch: 104 training_loss 0.1825833147764206 test_loss: 0.17189381122589112
epoch: 105 training_loss 0.17690654393285513 test_loss: 0.16478776931762695
epoch: 106 training_loss 0.18670156717300415 test_loss: 0.15803251266479493
epoch: 107 training_loss 0.17870488755404948 test_loss: 0.1875375032424927
epoch: 108 training_loss 0.17389204122126103 test_loss: 0.17532315254211425
epoch: 109 training_loss 0.17673123367130755 test_loss: 0.17403841018676758
epoch: 110 training_loss 0.17597121484577655 test_loss: 0.17924392223358154
epoch: 111 training_loss 0.1819253998249769 test_loss: 0.17198857069015502
epoch: 112 training_loss 0.17606427490711213 test_loss: 0.1776521921157837
epoch: 113 training_loss 0.17904055200517177 test_loss: 0.17703937292098998
epoch: 114 training_loss 0.18035543896257877 test_loss: 0.17167497873306276
epoch: 115 training_loss 0.16903003558516502 test_loss: 0.1626410722732544
epoch: 116 training_loss 0.17913553856313227 test_loss: 0.17147672176361084
epoch: 117 training_loss 0.1835590448230505 test_loss: 0.17352648973464965
epoch: 118 training_loss 0.178945666924119 test_loss: 0.1659129023551941
epoch: 119 training_loss 0.16771640211343766 test_loss: 0.17652297019958496
epoch: 120 training_loss 0.1676553924381733 test_loss: 0.1623189091682434
epoch: 121 training_loss 0.18008107841014862 test_loss: 0.1672012209892273
epoch: 122 training_loss 0.18084669321775437 test_loss: 0.17002397775650024
epoch: 123 training_loss 0.18733448781073092 test_loss: 0.15381370782852172
epoch: 124 training_loss 0.1780470786988735 test_loss: 0.17215577363967896
epoch: 125 training_loss 0.17789504803717138 test_loss: 0.17644824981689453
epoch: 126 training_loss 0.1811847172677517 test_loss: 0.1725324034690857
epoch: 127 training_loss 0.17639553874731065 test_loss: 0.17889469861984253
epoch: 128 training_loss 0.17458230324089527 test_loss: 0.17055838108062743
epoch: 129 training_loss 0.18136733938008548 test_loss: 0.168102490901947
epoch: 130 training_loss 0.18467883341014385 test_loss: 0.17878491878509523
epoch: 131 training_loss 0.18065325684845449 test_loss: 0.16070563793182374
epoch: 132 training_loss 0.17468896050006152 test_loss: 0.1564507246017456
epoch: 133 training_loss 0.18295565366744995 test_loss: 0.17617050409317017
epoch: 134 training_loss 0.16736658558249473 test_loss: 0.174233877658844
epoch: 135 training_loss 0.1757780349999666 test_loss: 0.18445489406585694
epoch: 136 training_loss 0.18253402523696421 test_loss: 0.16878716945648192
epoch: 137 training_loss 0.1779603049904108 test_loss: 0.16704070568084717
epoch: 138 training_loss 0.17899866901338102 test_loss: 0.1506056308746338
epoch: 139 training_loss 0.17258222110569477 test_loss: 0.17642252445220946
epoch: 140 training_loss 0.17903708964586257 test_loss: 0.18115774393081666
epoch: 141 training_loss 0.1835221207141876 test_loss: 0.185632586479187
epoch: 142 training_loss 0.18091128148138524 test_loss: 0.16602871417999268
epoch: 143 training_loss 0.17173946842551233 test_loss: 0.16733522415161134
epoch: 144 training_loss 0.17390030764043332 test_loss: 0.17369704246520995
epoch: 145 training_loss 0.171362778916955 test_loss: 0.1636504888534546
epoch: 146 training_loss 0.17863295681774616 test_loss: 0.16744346618652345
epoch: 147 training_loss 0.17227912940084933 test_loss: 0.17444816827774048
epoch: 148 training_loss 0.17636171981692314 test_loss: 0.1657860040664673
epoch: 149 training_loss 0.17931556597352027 test_loss: 0.17185388803482055
epoch: 0 training_loss 8.06055016040802 test_loss: 4.781442642211914
epoch: 1 training_loss 3.6665977215766907 test_loss: 2.9787506103515624
epoch: 2 training_loss 2.5513262128829957 test_loss: 2.3431488037109376
epoch: 3 training_loss 2.108308572769165 test_loss: 1.9614412307739257
epoch: 4 training_loss 1.8142107260227203 test_loss: 1.6947607040405273
epoch: 5 training_loss 1.6411211478710175 test_loss: 1.5454739570617675
epoch: 6 training_loss 1.5187847316265106 test_loss: 1.458812427520752
epoch: 7 training_loss 1.3981758618354798 test_loss: 1.3566312789916992
epoch: 8 training_loss 1.331166843175888 test_loss: 1.3205703735351562
epoch: 9 training_loss 1.2662750613689422 test_loss: 1.2697016716003418
epoch: 10 training_loss 1.1970230275392533 test_loss: 1.1786331176757812
epoch: 11 training_loss 1.1773389655351638 test_loss: 1.1539591789245605
epoch: 12 training_loss 1.1021308547258377 test_loss: 1.0897375106811524
epoch: 13 training_loss 1.0926067042350769 test_loss: 1.0866567611694335
epoch: 14 training_loss 1.0469293427467345 test_loss: 1.055552101135254
epoch: 15 training_loss 1.0277725172042846 test_loss: 1.0253537178039551
epoch: 16 training_loss 1.0063986825942992 test_loss: 0.9505800247192383
epoch: 17 training_loss 0.9599891799688339 test_loss: 0.9717202186584473
epoch: 18 training_loss 0.9563435983657836 test_loss: 0.9430261611938476
epoch: 19 training_loss 0.9349683773517609 test_loss: 0.9826729774475098
epoch: 20 training_loss 0.9236047399044037 test_loss: 0.8910371780395507
epoch: 21 training_loss 0.8946043479442597 test_loss: 0.9117591857910157
epoch: 22 training_loss 0.8765744757652283 test_loss: 0.87513427734375
epoch: 23 training_loss 0.8617288970947266 test_loss: 0.8812165260314941
epoch: 24 training_loss 0.8464858913421631 test_loss: 0.8095416069030762
epoch: 25 training_loss 0.834859025478363 test_loss: 0.8160638809204102
epoch: 26 training_loss 0.8132599437236786 test_loss: 0.7995230674743652
epoch: 27 training_loss 0.7946921932697296 test_loss: 0.7904139995574951
epoch: 28 training_loss 0.7870950496196747 test_loss: 0.7613579750061035
epoch: 29 training_loss 0.7935303568840026 test_loss: 0.764115285873413
epoch: 30 training_loss 0.7739013242721557 test_loss: 0.774534273147583
epoch: 31 training_loss 0.7757746583223343 test_loss: 0.779917573928833
epoch: 32 training_loss 0.7587499594688416 test_loss: 0.7261317729949951
epoch: 33 training_loss 0.7488265818357468 test_loss: 0.7408056259155273
epoch: 34 training_loss 0.7209179604053497 test_loss: 0.706117582321167
epoch: 35 training_loss 0.7305467891693115 test_loss: 0.7125470638275146
epoch: 36 training_loss 0.7281927132606506 test_loss: 0.7108118057250976
epoch: 37 training_loss 0.7243158572912216 test_loss: 0.6926293849945069
epoch: 38 training_loss 0.701542004942894 test_loss: 0.7209159851074218
epoch: 39 training_loss 0.7130686020851136 test_loss: 0.7101301193237305
epoch: 40 training_loss 0.6963026034832 test_loss: 0.6633926391601562
epoch: 41 training_loss 0.6892551296949386 test_loss: 0.68978271484375
epoch: 42 training_loss 0.681138442158699 test_loss: 0.6998380661010742
epoch: 43 training_loss 0.6777572393417358 test_loss: 0.6826250553131104
epoch: 44 training_loss 0.6810181766748429 test_loss: 0.6825916767120361
epoch: 45 training_loss 0.6706938910484314 test_loss: 0.6525706291198731
epoch: 46 training_loss 0.6594459646940232 test_loss: 0.6915537357330322
epoch: 47 training_loss 0.6652965128421784 test_loss: 0.6613251686096191
epoch: 48 training_loss 0.6598515766859054 test_loss: 0.6607507228851318
epoch: 49 training_loss 0.6551221132278442 test_loss: 0.6635181903839111
epoch: 50 training_loss 0.6383003515005111 test_loss: 0.6221212387084961
epoch: 51 training_loss 0.6494274497032165 test_loss: 0.6524733066558838
epoch: 52 training_loss 0.6441296780109406 test_loss: 0.6227803707122803
epoch: 53 training_loss 0.648192133307457 test_loss: 0.6206179618835449
epoch: 54 training_loss 0.6268890780210495 test_loss: 0.6126342296600342
epoch: 55 training_loss 0.6301865977048874 test_loss: 0.6182597637176513
epoch: 56 training_loss 0.6288500040769577 test_loss: 0.6114999771118164
epoch: 57 training_loss 0.6370053344964981 test_loss: 0.6175886154174804
epoch: 58 training_loss 0.6209761732816697 test_loss: 0.6773199558258056
epoch: 59 training_loss 0.6275350332260132 test_loss: 0.6162788391113281
epoch: 60 training_loss 0.6172230619192124 test_loss: 0.6096558094024658
epoch: 61 training_loss 0.6136981457471847 test_loss: 0.6021904468536377
epoch: 62 training_loss 0.6033128833770752 test_loss: 0.5853006839752197
epoch: 63 training_loss 0.6122361439466476 test_loss: 0.6174108982086182
epoch: 64 training_loss 0.6078942358493805 test_loss: 0.5977135181427002
epoch: 65 training_loss 0.6007968604564666 test_loss: 0.6370932102203369
epoch: 66 training_loss 0.6098626536130906 test_loss: 0.583643102645874
epoch: 67 training_loss 0.6039064973592758 test_loss: 0.5958744525909424
epoch: 68 training_loss 0.5932517790794373 test_loss: 0.60713791847229
epoch: 69 training_loss 0.5941244179010391 test_loss: 0.5953712463378906
epoch: 70 training_loss 0.5911395436525345 test_loss: 0.585435152053833
epoch: 71 training_loss 0.5995470005273819 test_loss: 0.5875946044921875
epoch: 72 training_loss 0.5960285747051239 test_loss: 0.5953854560852051
epoch: 73 training_loss 0.5910641330480576 test_loss: 0.578611946105957
epoch: 74 training_loss 0.5817681390047074 test_loss: 0.5893185615539551
epoch: 75 training_loss 0.5732804948091507 test_loss: 0.5765386581420898
epoch: 76 training_loss 0.5752249979972839 test_loss: 0.5782749652862549
epoch: 77 training_loss 0.5851478356122971 test_loss: 0.5681727886199951
epoch: 78 training_loss 0.5704717034101486 test_loss: 0.6003658294677734
epoch: 79 training_loss 0.5739040368795395 test_loss: 0.575399112701416
epoch: 80 training_loss 0.5728008073568344 test_loss: 0.5683755874633789
epoch: 81 training_loss 0.5746685093641282 test_loss: 0.5571657180786133
epoch: 82 training_loss 0.5702365374565125 test_loss: 0.5643192291259765
epoch: 83 training_loss 0.5658599883317947 test_loss: 0.5666506290435791
epoch: 84 training_loss 0.5701993930339814 test_loss: 0.5675891399383545
epoch: 85 training_loss 0.5584216034412384 test_loss: 0.5649108409881591
epoch: 86 training_loss 0.5593159580230713 test_loss: 0.5555029392242432
epoch: 87 training_loss 0.5696479541063308 test_loss: 0.5498082637786865
epoch: 88 training_loss 0.5601463213562965 test_loss: 0.5487274169921875
epoch: 89 training_loss 0.5637589201331139 test_loss: 0.5669917583465576
epoch: 90 training_loss 0.5673763877153397 test_loss: 0.5805756092071533
epoch: 91 training_loss 0.550456962287426 test_loss: 0.5539857387542725
epoch: 92 training_loss 0.5627787703275681 test_loss: 0.5612904548645019
epoch: 93 training_loss 0.5522285962104797 test_loss: 0.5835338115692139
epoch: 94 training_loss 0.5541730779409408 test_loss: 0.5485887050628662
epoch: 95 training_loss 0.5614390647411347 test_loss: 0.539418363571167
epoch: 96 training_loss 0.5567880159616471 test_loss: 0.5570608139038086
epoch: 97 training_loss 0.5469261959195137 test_loss: 0.5411766052246094
epoch: 98 training_loss 0.5466726282238961 test_loss: 0.5415922641754151
epoch: 99 training_loss 0.541737819314003 test_loss: 0.5710353851318359
epoch: 100 training_loss 0.5467531442642212 test_loss: 0.545517110824585
epoch: 101 training_loss 0.5476642400026321 test_loss: 0.5615801811218262
epoch: 102 training_loss 0.5423407018184662 test_loss: 0.5415384769439697
epoch: 103 training_loss 0.542727116048336 test_loss: 0.5232919692993164
epoch: 104 training_loss 0.5497416827082634 test_loss: 0.5350069046020508
epoch: 105 training_loss 0.5343399304151535 test_loss: 0.528581953048706
epoch: 106 training_loss 0.5322016939520836 test_loss: 0.5399769306182861
epoch: 107 training_loss 0.529420602619648 test_loss: 0.5820343017578125
epoch: 108 training_loss 0.5369883090257644 test_loss: 0.5544257640838623
epoch: 109 training_loss 0.5339665660262107 test_loss: 0.5453493118286132
epoch: 110 training_loss 0.5375880482792854 test_loss: 0.5206228733062744
epoch: 111 training_loss 0.530494529902935 test_loss: 0.5393608093261719
epoch: 112 training_loss 0.5363160121440887 test_loss: 0.5375558376312256
epoch: 113 training_loss 0.5177265521883965 test_loss: 0.531054162979126
epoch: 114 training_loss 0.5269489231705665 test_loss: 0.5359148502349853
epoch: 115 training_loss 0.5316064155101776 test_loss: 0.5311832904815674
epoch: 116 training_loss 0.5359875372052193 test_loss: 0.574880838394165
epoch: 117 training_loss 0.5283297884464264 test_loss: 0.5387639045715332
epoch: 118 training_loss 0.5186358353495598 test_loss: 0.5370246410369873
epoch: 119 training_loss 0.5172340136766433 test_loss: 0.5279307842254639
epoch: 120 training_loss 0.5293449467420578 test_loss: 0.5137856483459473
epoch: 121 training_loss 0.5250586953759193 test_loss: 0.5491806507110596
epoch: 122 training_loss 0.5264020934700966 test_loss: 0.5188404560089112
epoch: 123 training_loss 0.5179780778288842 test_loss: 0.517598295211792
epoch: 124 training_loss 0.5208575594425201 test_loss: 0.5041018009185791
epoch: 125 training_loss 0.516308379471302 test_loss: 0.5128556251525879
epoch: 126 training_loss 0.5370820835232735 test_loss: 0.516496992111206
epoch: 127 training_loss 0.5128015699982643 test_loss: 0.5255951881408691
epoch: 128 training_loss 0.5150688070058823 test_loss: 0.5187710762023926
epoch: 129 training_loss 0.5168081170320511 test_loss: 0.5619750022888184
epoch: 130 training_loss 0.5086168730258942 test_loss: 0.5109497547149658
epoch: 131 training_loss 0.5108511346578598 test_loss: 0.5130151748657227
epoch: 132 training_loss 0.5186952602863312 test_loss: 0.5067066192626953
epoch: 133 training_loss 0.5055367144942283 test_loss: 0.49639301300048827
epoch: 134 training_loss 0.518568810224533 test_loss: 0.5103015422821044
epoch: 135 training_loss 0.5062950932979584 test_loss: 0.49456372261047366
epoch: 136 training_loss 0.5073894712328911 test_loss: 0.5063979625701904
epoch: 137 training_loss 0.514800233244896 test_loss: 0.5295411109924316
epoch: 138 training_loss 0.5013212919235229 test_loss: 0.5018505096435547
epoch: 139 training_loss 0.5111761039495468 test_loss: 0.5352038860321044
epoch: 140 training_loss 0.5104856824874878 test_loss: 0.5104807853698731
epoch: 141 training_loss 0.50883785456419 test_loss: 0.5091986656188965
epoch: 142 training_loss 0.5068462660908699 test_loss: 0.5097911834716797
epoch: 143 training_loss 0.5082932576537132 test_loss: 0.4974630355834961
epoch: 144 training_loss 0.5125369396805763 test_loss: 0.5280605316162109
epoch: 145 training_loss 0.5041353300213813 test_loss: 0.5072269916534424
epoch: 146 training_loss 0.5135532295703888 test_loss: 0.506358003616333
epoch: 147 training_loss 0.49892750710248945 test_loss: 0.4888289928436279
epoch: 148 training_loss 0.5005214142799378 test_loss: 0.48685431480407715
epoch: 149 training_loss 0.49565669625997544 test_loss: 0.4889965534210205
2883.9243080191004
episode: 0 training return: tensor(-300.3820, device='cuda:0')
episode: 1 training return: tensor(-258.5983, device='cuda:0')
episode: 2 training return: tensor(-339.6577, device='cuda:0')
episode: 3 training return: tensor(-207.1843, device='cuda:0')
epoch: 1 test_true_pfm: 2111.411868982292 sim_pfm: -136.5298176452828
episode: 4 training return: tensor(-336.8825, device='cuda:0')
episode: 5 training return: tensor(-344.3939, device='cuda:0')
episode: 6 training return: tensor(-348.6490, device='cuda:0')
episode: 7 training return: tensor(-329.7680, device='cuda:0')
epoch: 2 test_true_pfm: 1277.0583958520529 sim_pfm: -329.97474118921673
episode: 8 training return: tensor(-337.7205, device='cuda:0')
episode: 9 training return: tensor(-308.0755, device='cuda:0')
episode: 10 training return: tensor(-299.1709, device='cuda:0')
episode: 11 training return: tensor(379.4700, device='cuda:0')
epoch: 3 test_true_pfm: 1496.3013028424193 sim_pfm: -58.0013556368649
episode: 12 training return: tensor(-340.1138, device='cuda:0')
episode: 13 training return: tensor(-152.9527, device='cuda:0')
episode: 14 training return: tensor(-341.8825, device='cuda:0')
episode: 15 training return: tensor(-216.1346, device='cuda:0')
epoch: 4 test_true_pfm: 1799.277713806134 sim_pfm: 161.41155488135215
episode: 16 training return: tensor(11.2470, device='cuda:0')
episode: 17 training return: tensor(-351.8626, device='cuda:0')
episode: 18 training return: tensor(-342.6592, device='cuda:0')
episode: 19 training return: tensor(-328.4834, device='cuda:0')
epoch: 5 test_true_pfm: 1736.654742549507 sim_pfm: 31.419464151957072
episode: 20 training return: tensor(-306.9595, device='cuda:0')
episode: 21 training return: tensor(65.4477, device='cuda:0')
episode: 22 training return: tensor(120.1157, device='cuda:0')
episode: 23 training return: tensor(49.1563, device='cuda:0')
epoch: 6 test_true_pfm: 2965.5368218624812 sim_pfm: -28.121241976041347
episode: 24 training return: tensor(-58.5266, device='cuda:0')
episode: 25 training return: tensor(-301.3931, device='cuda:0')
episode: 26 training return: tensor(-345.9682, device='cuda:0')
episode: 27 training return: tensor(-355.3824, device='cuda:0')
epoch: 7 test_true_pfm: 2445.3216172675097 sim_pfm: 25.334413747448707
episode: 28 training return: tensor(243.3839, device='cuda:0')
episode: 29 training return: tensor(-334.5959, device='cuda:0')
episode: 30 training return: tensor(-346.9967, device='cuda:0')
episode: 31 training return: tensor(-300.3910, device='cuda:0')
epoch: 8 test_true_pfm: 2994.893878535497 sim_pfm: -171.48215902814022
episode: 32 training return: tensor(-253.6806, device='cuda:0')
episode: 33 training return: tensor(18.5347, device='cuda:0')
episode: 34 training return: tensor(-355.8187, device='cuda:0')
episode: 35 training return: tensor(-283.2673, device='cuda:0')
epoch: 9 test_true_pfm: 2639.2194488436257 sim_pfm: 153.7633242252438
episode: 36 training return: tensor(396.5299, device='cuda:0')
episode: 37 training return: tensor(-294.0080, device='cuda:0')
episode: 38 training return: tensor(-350.8236, device='cuda:0')
episode: 39 training return: tensor(-359.0173, device='cuda:0')
epoch: 10 test_true_pfm: 2817.7277676048107 sim_pfm: 303.5384499983241
episode: 40 training return: tensor(-300.1970, device='cuda:0')
episode: 41 training return: tensor(281.7813, device='cuda:0')
episode: 42 training return: tensor(-294.3668, device='cuda:0')
episode: 43 training return: tensor(-169.7190, device='cuda:0')
epoch: 11 test_true_pfm: 2181.6975000619664 sim_pfm: -80.63178463031848
episode: 44 training return: tensor(-300.5226, device='cuda:0')
episode: 45 training return: tensor(380.7056, device='cuda:0')
episode: 46 training return: tensor(-167.2904, device='cuda:0')
episode: 47 training return: tensor(-249.7054, device='cuda:0')
epoch: 12 test_true_pfm: 2625.786610664424 sim_pfm: -35.58414667961188
episode: 48 training return: tensor(-337.1270, device='cuda:0')
episode: 49 training return: tensor(-159.7316, device='cuda:0')
episode: 50 training return: tensor(-341.2452, device='cuda:0')
episode: 51 training return: tensor(-249.9332, device='cuda:0')
epoch: 13 test_true_pfm: 2179.1344532132734 sim_pfm: 346.88627706619445
episode: 52 training return: tensor(-168.5858, device='cuda:0')
episode: 53 training return: tensor(-358.1461, device='cuda:0')
episode: 54 training return: tensor(-338.0823, device='cuda:0')
episode: 55 training return: tensor(-89.9093, device='cuda:0')
epoch: 14 test_true_pfm: 1857.7766450002598 sim_pfm: -17.650069182321506
episode: 56 training return: tensor(-282.8130, device='cuda:0')
episode: 57 training return: tensor(54.1821, device='cuda:0')
episode: 58 training return: tensor(-346.8685, device='cuda:0')
episode: 59 training return: tensor(-60.1968, device='cuda:0')
epoch: 15 test_true_pfm: 1928.7473722980055 sim_pfm: 152.68334551577573
episode: 60 training return: tensor(-338.8685, device='cuda:0')
episode: 61 training return: tensor(338.7972, device='cuda:0')
episode: 62 training return: tensor(-309.7715, device='cuda:0')
episode: 63 training return: tensor(352.7721, device='cuda:0')
epoch: 16 test_true_pfm: 2510.26671663379 sim_pfm: -23.850517618702725
episode: 64 training return: tensor(71.9279, device='cuda:0')
episode: 65 training return: tensor(-347.2057, device='cuda:0')
episode: 66 training return: tensor(-284.6942, device='cuda:0')
episode: 67 training return: tensor(358.2803, device='cuda:0')
epoch: 17 test_true_pfm: 2441.892529624487 sim_pfm: 95.48837894375902
episode: 68 training return: tensor(-320.8802, device='cuda:0')
episode: 69 training return: tensor(-289.3368, device='cuda:0')
episode: 70 training return: tensor(-298.5724, device='cuda:0')
episode: 71 training return: tensor(298.7809, device='cuda:0')
epoch: 18 test_true_pfm: 2542.3774876217585 sim_pfm: -40.80187895517641
episode: 72 training return: tensor(-348.5259, device='cuda:0')
episode: 73 training return: tensor(-348.7246, device='cuda:0')
episode: 74 training return: tensor(-238.6468, device='cuda:0')
episode: 75 training return: tensor(380.5851, device='cuda:0')
epoch: 19 test_true_pfm: 2153.8336820556565 sim_pfm: -188.05703075876227
episode: 76 training return: tensor(-253.0900, device='cuda:0')
episode: 77 training return: tensor(-356.4338, device='cuda:0')
episode: 78 training return: tensor(-193.2131, device='cuda:0')
episode: 79 training return: tensor(72.9517, device='cuda:0')
epoch: 20 test_true_pfm: 2979.89528090987 sim_pfm: 61.498271476943046
episode: 80 training return: tensor(-345.7495, device='cuda:0')
episode: 81 training return: tensor(-217.1446, device='cuda:0')
episode: 82 training return: tensor(126.7646, device='cuda:0')
episode: 83 training return: tensor(-338.8434, device='cuda:0')
epoch: 21 test_true_pfm: 2828.249739309597 sim_pfm: 128.38516071780273
episode: 84 training return: tensor(-339.8980, device='cuda:0')
episode: 85 training return: tensor(342.8890, device='cuda:0')
episode: 86 training return: tensor(314.8360, device='cuda:0')
episode: 87 training return: tensor(-367.8139, device='cuda:0')
epoch: 22 test_true_pfm: 2585.517035692161 sim_pfm: 295.84221957977087
episode: 88 training return: tensor(-216.2132, device='cuda:0')
episode: 89 training return: tensor(326.0596, device='cuda:0')
episode: 90 training return: tensor(-261.2971, device='cuda:0')
episode: 91 training return: tensor(347.3772, device='cuda:0')
epoch: 23 test_true_pfm: 1599.550124763303 sim_pfm: -25.579650058100622
episode: 92 training return: tensor(346.2517, device='cuda:0')
episode: 93 training return: tensor(-229.8129, device='cuda:0')
episode: 94 training return: tensor(-254.7259, device='cuda:0')
episode: 95 training return: tensor(324.6588, device='cuda:0')
epoch: 24 test_true_pfm: 1867.9538482071177 sim_pfm: -102.8264626848977
episode: 96 training return: tensor(280.7816, device='cuda:0')
episode: 97 training return: tensor(-196.3296, device='cuda:0')
episode: 98 training return: tensor(-346.2707, device='cuda:0')
episode: 99 training return: tensor(-297.2455, device='cuda:0')
epoch: 25 test_true_pfm: 2022.9008987243008 sim_pfm: 167.17883793264627
episode: 100 training return: tensor(230.8029, device='cuda:0')
episode: 101 training return: tensor(-283.2470, device='cuda:0')
episode: 102 training return: tensor(-18.0888, device='cuda:0')
episode: 103 training return: tensor(-337.1515, device='cuda:0')
epoch: 26 test_true_pfm: 2514.989402860267 sim_pfm: -112.18832597136497
episode: 104 training return: tensor(326.8919, device='cuda:0')
episode: 105 training return: tensor(91.2454, device='cuda:0')
episode: 106 training return: tensor(-51.9220, device='cuda:0')
episode: 107 training return: tensor(339.6971, device='cuda:0')
epoch: 27 test_true_pfm: 2357.0319163150575 sim_pfm: 241.10492074508997
episode: 108 training return: tensor(-341.0803, device='cuda:0')
episode: 109 training return: tensor(-315.5502, device='cuda:0')
episode: 110 training return: tensor(-284.5604, device='cuda:0')
episode: 111 training return: tensor(-344.5830, device='cuda:0')
epoch: 28 test_true_pfm: 1798.2160216112025 sim_pfm: -38.64446735486854
episode: 112 training return: tensor(-368.4709, device='cuda:0')
episode: 113 training return: tensor(-182.9252, device='cuda:0')
episode: 114 training return: tensor(-260.5605, device='cuda:0')
episode: 115 training return: tensor(-265.5943, device='cuda:0')
epoch: 29 test_true_pfm: 2100.8269307533133 sim_pfm: 138.8218337483704
episode: 116 training return: tensor(-343.9439, device='cuda:0')
episode: 117 training return: tensor(-257.3772, device='cuda:0')
episode: 118 training return: tensor(398.5601, device='cuda:0')
episode: 119 training return: tensor(-247.9885, device='cuda:0')
epoch: 30 test_true_pfm: 2718.143747998755 sim_pfm: -28.348554070456885
episode: 120 training return: tensor(-272.2921, device='cuda:0')
episode: 121 training return: tensor(-188.6053, device='cuda:0')
episode: 122 training return: tensor(351.9729, device='cuda:0')
episode: 123 training return: tensor(379.6647, device='cuda:0')
epoch: 31 test_true_pfm: 2688.539572586597 sim_pfm: -36.56959933199687
episode: 124 training return: tensor(-173.9827, device='cuda:0')
episode: 125 training return: tensor(334.0279, device='cuda:0')
episode: 126 training return: tensor(-185.5836, device='cuda:0')
episode: 127 training return: tensor(356.3700, device='cuda:0')
epoch: 32 test_true_pfm: 2177.4041396090565 sim_pfm: 148.86254549767668
episode: 128 training return: tensor(143.8468, device='cuda:0')
episode: 129 training return: tensor(-337.5992, device='cuda:0')
episode: 130 training return: tensor(-212.3355, device='cuda:0')
episode: 131 training return: tensor(36.1590, device='cuda:0')
epoch: 33 test_true_pfm: 2236.7894963088015 sim_pfm: -147.50044219618817
episode: 132 training return: tensor(-314.6153, device='cuda:0')
episode: 133 training return: tensor(363.3873, device='cuda:0')
episode: 134 training return: tensor(-190.8055, device='cuda:0')
episode: 135 training return: tensor(337.0089, device='cuda:0')
epoch: 34 test_true_pfm: 2642.209261206231 sim_pfm: 201.21947185796066
episode: 136 training return: tensor(123.4150, device='cuda:0')
episode: 137 training return: tensor(-54.9958, device='cuda:0')
episode: 138 training return: tensor(-243.3865, device='cuda:0')
episode: 139 training return: tensor(-357.9491, device='cuda:0')
epoch: 35 test_true_pfm: 1574.5293208731052 sim_pfm: 180.51111535986033
episode: 140 training return: tensor(407.9537, device='cuda:0')
episode: 141 training return: tensor(-289.6046, device='cuda:0')
episode: 142 training return: tensor(-254.3585, device='cuda:0')
episode: 143 training return: tensor(-46.7345, device='cuda:0')
epoch: 36 test_true_pfm: 2091.9873066610007 sim_pfm: -113.88837112043984
episode: 144 training return: tensor(341.1436, device='cuda:0')
episode: 145 training return: tensor(-344.3190, device='cuda:0')
episode: 146 training return: tensor(-284.0243, device='cuda:0')
episode: 147 training return: tensor(109.7884, device='cuda:0')
epoch: 37 test_true_pfm: 2020.0076524663182 sim_pfm: 164.43812029075343
episode: 148 training return: tensor(133.9998, device='cuda:0')
episode: 149 training return: tensor(392.4878, device='cuda:0')
episode: 150 training return: tensor(-167.5032, device='cuda:0')
episode: 151 training return: tensor(-163.0318, device='cuda:0')
epoch: 38 test_true_pfm: 2019.7954187825935 sim_pfm: 87.2116250525384
episode: 152 training return: tensor(-168.4118, device='cuda:0')
episode: 153 training return: tensor(-328.4905, device='cuda:0')
episode: 154 training return: tensor(176.5298, device='cuda:0')
episode: 155 training return: tensor(-209.7573, device='cuda:0')
epoch: 39 test_true_pfm: 2079.5248797843083 sim_pfm: -231.96631949336734
episode: 156 training return: tensor(-222.1083, device='cuda:0')
episode: 157 training return: tensor(-252.0469, device='cuda:0')
episode: 158 training return: tensor(-343.4572, device='cuda:0')
episode: 159 training return: tensor(349.2038, device='cuda:0')
epoch: 40 test_true_pfm: 2575.4523212436457 sim_pfm: -80.08516270585824
episode: 160 training return: tensor(347.0720, device='cuda:0')
episode: 161 training return: tensor(-158.4242, device='cuda:0')
episode: 162 training return: tensor(-341.3420, device='cuda:0')
episode: 163 training return: tensor(-243.3314, device='cuda:0')
epoch: 41 test_true_pfm: 2332.5258864931816 sim_pfm: 216.95770286515472
episode: 164 training return: tensor(-203.4407, device='cuda:0')
episode: 165 training return: tensor(-336.6548, device='cuda:0')
episode: 166 training return: tensor(354.6377, device='cuda:0')
episode: 167 training return: tensor(-296.5059, device='cuda:0')
epoch: 42 test_true_pfm: 2902.8775899192424 sim_pfm: 62.65313698564811
episode: 168 training return: tensor(-66.4487, device='cuda:0')
episode: 169 training return: tensor(-329.3180, device='cuda:0')
episode: 170 training return: tensor(-294.1320, device='cuda:0')
episode: 171 training return: tensor(-296.4055, device='cuda:0')
epoch: 43 test_true_pfm: 2830.3280570719235 sim_pfm: 117.58332442453441
episode: 172 training return: tensor(58.4239, device='cuda:0')
episode: 173 training return: tensor(326.5933, device='cuda:0')
episode: 174 training return: tensor(-344.7274, device='cuda:0')
episode: 175 training return: tensor(-303.8621, device='cuda:0')
epoch: 44 test_true_pfm: 1592.6875276108785 sim_pfm: -204.55432221417627
episode: 176 training return: tensor(352.6295, device='cuda:0')
episode: 177 training return: tensor(-39.1128, device='cuda:0')
episode: 178 training return: tensor(-37.5831, device='cuda:0')
episode: 179 training return: tensor(-351.2242, device='cuda:0')
epoch: 45 test_true_pfm: 2212.7706783703065 sim_pfm: -38.59437822313824
episode: 180 training return: tensor(132.4436, device='cuda:0')
episode: 181 training return: tensor(351.6640, device='cuda:0')
episode: 182 training return: tensor(-352.9798, device='cuda:0')
episode: 183 training return: tensor(-263.2259, device='cuda:0')
epoch: 46 test_true_pfm: 1728.0502350574573 sim_pfm: -191.06490447061756
episode: 184 training return: tensor(193.4080, device='cuda:0')
episode: 185 training return: tensor(225.7191, device='cuda:0')
episode: 186 training return: tensor(-169.1914, device='cuda:0')
episode: 187 training return: tensor(-246.4480, device='cuda:0')
epoch: 47 test_true_pfm: 2546.3610901127468 sim_pfm: -78.87933065004957
episode: 188 training return: tensor(-333.2596, device='cuda:0')
episode: 189 training return: tensor(-341.6591, device='cuda:0')
episode: 190 training return: tensor(276.3617, device='cuda:0')
episode: 191 training return: tensor(-352.9455, device='cuda:0')
epoch: 48 test_true_pfm: 2715.6501156715763 sim_pfm: 15.2706885918354
episode: 192 training return: tensor(342.4968, device='cuda:0')
episode: 193 training return: tensor(-335.8032, device='cuda:0')
episode: 194 training return: tensor(322.9274, device='cuda:0')
episode: 195 training return: tensor(90.4955, device='cuda:0')
epoch: 49 test_true_pfm: 1882.0539109468075 sim_pfm: -230.80231592982696
episode: 196 training return: tensor(-339.3100, device='cuda:0')
episode: 197 training return: tensor(195.4689, device='cuda:0')
episode: 198 training return: tensor(-184.1832, device='cuda:0')
episode: 199 training return: tensor(177.8661, device='cuda:0')
epoch: 50 test_true_pfm: 1772.4584484833838 sim_pfm: -213.98322462420523
episode: 200 training return: tensor(-334.3819, device='cuda:0')
episode: 201 training return: tensor(-285.4884, device='cuda:0')
episode: 202 training return: tensor(421.8104, device='cuda:0')
episode: 203 training return: tensor(37.8345, device='cuda:0')
epoch: 51 test_true_pfm: 3134.588855734444 sim_pfm: 19.908017290678497
episode: 204 training return: tensor(-308.8094, device='cuda:0')
episode: 205 training return: tensor(90.8691, device='cuda:0')
episode: 206 training return: tensor(-349.2806, device='cuda:0')
episode: 207 training return: tensor(-192.4905, device='cuda:0')
epoch: 52 test_true_pfm: 2292.197310635671 sim_pfm: -126.2960978942768
episode: 208 training return: tensor(-307.5407, device='cuda:0')
episode: 209 training return: tensor(-219.6977, device='cuda:0')
episode: 210 training return: tensor(392.2250, device='cuda:0')
episode: 211 training return: tensor(-46.2588, device='cuda:0')
epoch: 53 test_true_pfm: 2586.5527804844337 sim_pfm: -0.007040021164963643
episode: 212 training return: tensor(-278.5605, device='cuda:0')
episode: 213 training return: tensor(-335.1227, device='cuda:0')
episode: 214 training return: tensor(-214.4934, device='cuda:0')
episode: 215 training return: tensor(-308.7224, device='cuda:0')
epoch: 54 test_true_pfm: 2507.0783541314663 sim_pfm: -34.930757456924766
episode: 216 training return: tensor(345.3002, device='cuda:0')
episode: 217 training return: tensor(-314.8181, device='cuda:0')
episode: 218 training return: tensor(-306.9851, device='cuda:0')
episode: 219 training return: tensor(-347.2788, device='cuda:0')
epoch: 55 test_true_pfm: 1962.3873092831827 sim_pfm: 168.496930023015
episode: 220 training return: tensor(-159.0969, device='cuda:0')
episode: 221 training return: tensor(-340.8866, device='cuda:0')
episode: 222 training return: tensor(-347.5891, device='cuda:0')
episode: 223 training return: tensor(-349.6103, device='cuda:0')
epoch: 56 test_true_pfm: 2839.7705999720515 sim_pfm: 73.72870152893786
episode: 224 training return: tensor(89.5647, device='cuda:0')
episode: 225 training return: tensor(-259.7395, device='cuda:0')
episode: 226 training return: tensor(-327.2907, device='cuda:0')
episode: 227 training return: tensor(-305.9694, device='cuda:0')
epoch: 57 test_true_pfm: 2243.7633563784584 sim_pfm: 209.73761719558388
episode: 228 training return: tensor(-362.3261, device='cuda:0')
episode: 229 training return: tensor(-297.3568, device='cuda:0')
episode: 230 training return: tensor(-336.9233, device='cuda:0')
episode: 231 training return: tensor(-273.2599, device='cuda:0')
epoch: 58 test_true_pfm: 1655.940236594378 sim_pfm: 114.6047180496001
episode: 232 training return: tensor(-341.0847, device='cuda:0')
episode: 233 training return: tensor(374.4544, device='cuda:0')
episode: 234 training return: tensor(-48.0931, device='cuda:0')
episode: 235 training return: tensor(70.6385, device='cuda:0')
epoch: 59 test_true_pfm: 2366.3877245888166 sim_pfm: -107.37273501273982
episode: 236 training return: tensor(359.2571, device='cuda:0')
episode: 237 training return: tensor(-190.9208, device='cuda:0')
episode: 238 training return: tensor(268.3175, device='cuda:0')
episode: 239 training return: tensor(126.2793, device='cuda:0')
epoch: 60 test_true_pfm: 1739.1978924492712 sim_pfm: -12.367595296935178
episode: 240 training return: tensor(-218.8465, device='cuda:0')
episode: 241 training return: tensor(-274.1307, device='cuda:0')
episode: 242 training return: tensor(-360.7346, device='cuda:0')
episode: 243 training return: tensor(-297.5993, device='cuda:0')
epoch: 61 test_true_pfm: 2910.229976251774 sim_pfm: 287.365540529058
episode: 244 training return: tensor(-196.6532, device='cuda:0')
episode: 245 training return: tensor(212.8089, device='cuda:0')
episode: 246 training return: tensor(-308.5060, device='cuda:0')
episode: 247 training return: tensor(-297.0711, device='cuda:0')
epoch: 62 test_true_pfm: 2595.953227209636 sim_pfm: 29.877846155121613
episode: 248 training return: tensor(-344.2540, device='cuda:0')
episode: 249 training return: tensor(-259.1010, device='cuda:0')
episode: 250 training return: tensor(-74.8174, device='cuda:0')
episode: 251 training return: tensor(126.6195, device='cuda:0')
epoch: 63 test_true_pfm: 2592.4285749492196 sim_pfm: 275.9812561996126
episode: 252 training return: tensor(332.5629, device='cuda:0')
episode: 253 training return: tensor(-295.1787, device='cuda:0')
episode: 254 training return: tensor(-339.7649, device='cuda:0')
episode: 255 training return: tensor(-336.0985, device='cuda:0')
epoch: 64 test_true_pfm: 2433.20812692302 sim_pfm: 6.588114340712006
episode: 256 training return: tensor(105.7752, device='cuda:0')
episode: 257 training return: tensor(-162.3512, device='cuda:0')
episode: 258 training return: tensor(52.4507, device='cuda:0')
episode: 259 training return: tensor(-215.0545, device='cuda:0')
epoch: 65 test_true_pfm: 2436.90243263622 sim_pfm: 54.78672750542561
episode: 260 training return: tensor(10.0443, device='cuda:0')
episode: 261 training return: tensor(-328.8452, device='cuda:0')
episode: 262 training return: tensor(-284.8422, device='cuda:0')
episode: 263 training return: tensor(104.2501, device='cuda:0')
epoch: 66 test_true_pfm: 2674.059690279216 sim_pfm: 221.85321536791162
episode: 264 training return: tensor(-316.6526, device='cuda:0')
episode: 265 training return: tensor(354.5658, device='cuda:0')
episode: 266 training return: tensor(-208.3535, device='cuda:0')
episode: 267 training return: tensor(-108.7470, device='cuda:0')
epoch: 67 test_true_pfm: 2754.17963350763 sim_pfm: -38.675658258609474
episode: 268 training return: tensor(334.8488, device='cuda:0')
episode: 269 training return: tensor(-305.2002, device='cuda:0')
episode: 270 training return: tensor(-345.2570, device='cuda:0')
episode: 271 training return: tensor(-156.7702, device='cuda:0')
epoch: 68 test_true_pfm: 2386.5917208121464 sim_pfm: 120.5137146729976
episode: 272 training return: tensor(-52.4295, device='cuda:0')
episode: 273 training return: tensor(362.6044, device='cuda:0')
episode: 274 training return: tensor(-346.2799, device='cuda:0')
episode: 275 training return: tensor(-190.1045, device='cuda:0')
epoch: 69 test_true_pfm: 2868.4998497930665 sim_pfm: -9.236736280668993
episode: 276 training return: tensor(337.9599, device='cuda:0')
episode: 277 training return: tensor(-313.0005, device='cuda:0')
episode: 278 training return: tensor(-340.5891, device='cuda:0')
episode: 279 training return: tensor(-74.5755, device='cuda:0')
epoch: 70 test_true_pfm: 2752.013597263946 sim_pfm: 230.06834432148995
episode: 280 training return: tensor(-102.3828, device='cuda:0')
episode: 281 training return: tensor(-22.7094, device='cuda:0')
episode: 282 training return: tensor(-95.7006, device='cuda:0')
episode: 283 training return: tensor(-283.0302, device='cuda:0')
epoch: 71 test_true_pfm: 2647.7180570295636 sim_pfm: 238.23631771979854
episode: 284 training return: tensor(110.1648, device='cuda:0')
episode: 285 training return: tensor(-290.1258, device='cuda:0')
episode: 286 training return: tensor(0.6879, device='cuda:0')
episode: 287 training return: tensor(257.0788, device='cuda:0')
epoch: 72 test_true_pfm: 2787.630446716273 sim_pfm: 85.06566112721339
episode: 288 training return: tensor(-295.6401, device='cuda:0')
episode: 289 training return: tensor(389.9300, device='cuda:0')
episode: 290 training return: tensor(-333.6901, device='cuda:0')
episode: 291 training return: tensor(-272.5902, device='cuda:0')
epoch: 73 test_true_pfm: 2020.4658921912135 sim_pfm: -29.55855118405695
episode: 292 training return: tensor(-335.4316, device='cuda:0')
episode: 293 training return: tensor(-317.2336, device='cuda:0')
episode: 294 training return: tensor(-211.2393, device='cuda:0')
episode: 295 training return: tensor(-345.5979, device='cuda:0')
epoch: 74 test_true_pfm: 2909.622118829711 sim_pfm: 241.30921076238155
episode: 296 training return: tensor(13.2062, device='cuda:0')
episode: 297 training return: tensor(-351.2781, device='cuda:0')
episode: 298 training return: tensor(189.6220, device='cuda:0')
episode: 299 training return: tensor(318.8247, device='cuda:0')
epoch: 75 test_true_pfm: 1613.6732987577898 sim_pfm: 244.4568294356577
episode: 300 training return: tensor(-262.7725, device='cuda:0')
episode: 301 training return: tensor(-238.8388, device='cuda:0')
episode: 302 training return: tensor(-347.4048, device='cuda:0')
episode: 303 training return: tensor(-211.7363, device='cuda:0')
epoch: 76 test_true_pfm: 2468.403892144033 sim_pfm: 180.12070353433955
episode: 304 training return: tensor(105.2904, device='cuda:0')
episode: 305 training return: tensor(-289.8564, device='cuda:0')
episode: 306 training return: tensor(-328.5475, device='cuda:0')
episode: 307 training return: tensor(-342.0001, device='cuda:0')
epoch: 77 test_true_pfm: 1957.6982431586277 sim_pfm: 89.03957068240076
episode: 308 training return: tensor(-266.0707, device='cuda:0')
episode: 309 training return: tensor(-353.5194, device='cuda:0')
episode: 310 training return: tensor(-194.0705, device='cuda:0')
episode: 311 training return: tensor(161.9756, device='cuda:0')
epoch: 78 test_true_pfm: 2998.3857525231183 sim_pfm: 153.61451584725486
episode: 312 training return: tensor(312.6136, device='cuda:0')
episode: 313 training return: tensor(-246.0011, device='cuda:0')
episode: 314 training return: tensor(274.5807, device='cuda:0')
episode: 315 training return: tensor(-272.9685, device='cuda:0')
epoch: 79 test_true_pfm: 3055.1402465495707 sim_pfm: 88.31270504478987
episode: 316 training return: tensor(-21.5154, device='cuda:0')
episode: 317 training return: tensor(-244.9215, device='cuda:0')
episode: 318 training return: tensor(-338.3456, device='cuda:0')
episode: 319 training return: tensor(-339.4097, device='cuda:0')
epoch: 80 test_true_pfm: 2584.1917947634556 sim_pfm: 257.50908253508777
episode: 320 training return: tensor(-302.4486, device='cuda:0')
episode: 321 training return: tensor(-363.2180, device='cuda:0')
episode: 322 training return: tensor(60.9492, device='cuda:0')
episode: 323 training return: tensor(280.4202, device='cuda:0')
epoch: 81 test_true_pfm: 2201.8882436174213 sim_pfm: 340.1508118729883
episode: 324 training return: tensor(-192.6861, device='cuda:0')
episode: 325 training return: tensor(170.3098, device='cuda:0')
episode: 326 training return: tensor(-344.2533, device='cuda:0')
episode: 327 training return: tensor(-272.4557, device='cuda:0')
epoch: 82 test_true_pfm: 2184.536634486412 sim_pfm: 122.22007225339378
episode: 328 training return: tensor(-267.4626, device='cuda:0')
episode: 329 training return: tensor(360.6247, device='cuda:0')
episode: 330 training return: tensor(387.8134, device='cuda:0')
episode: 331 training return: tensor(-357.1242, device='cuda:0')
epoch: 83 test_true_pfm: 1940.6976897362745 sim_pfm: 154.34460306284018
episode: 332 training return: tensor(152.9821, device='cuda:0')
episode: 333 training return: tensor(164.2918, device='cuda:0')
episode: 334 training return: tensor(94.5230, device='cuda:0')
episode: 335 training return: tensor(-348.7741, device='cuda:0')
epoch: 84 test_true_pfm: 1993.0344218346763 sim_pfm: 156.46076385347018
episode: 336 training return: tensor(-342.2921, device='cuda:0')
episode: 337 training return: tensor(-25.4057, device='cuda:0')
episode: 338 training return: tensor(-160.4323, device='cuda:0')
episode: 339 training return: tensor(-339.8604, device='cuda:0')
epoch: 85 test_true_pfm: 3000.434091775844 sim_pfm: 128.44214154907968
episode: 340 training return: tensor(-124.1224, device='cuda:0')
episode: 341 training return: tensor(-203.2811, device='cuda:0')
episode: 342 training return: tensor(-291.5546, device='cuda:0')
episode: 343 training return: tensor(-229.2804, device='cuda:0')
epoch: 86 test_true_pfm: 2688.586607962014 sim_pfm: 122.86761873083499
episode: 344 training return: tensor(-205.7685, device='cuda:0')
episode: 345 training return: tensor(-261.0193, device='cuda:0')
episode: 346 training return: tensor(-211.3219, device='cuda:0')
episode: 347 training return: tensor(-200.9704, device='cuda:0')
epoch: 87 test_true_pfm: 2548.2653153586857 sim_pfm: 261.27472384180874
episode: 348 training return: tensor(327.0930, device='cuda:0')
episode: 349 training return: tensor(-200.8198, device='cuda:0')
episode: 350 training return: tensor(24.1689, device='cuda:0')
episode: 351 training return: tensor(-324.3042, device='cuda:0')
epoch: 88 test_true_pfm: 2239.324044243346 sim_pfm: 269.92067176662385
episode: 352 training return: tensor(-286.6391, device='cuda:0')
episode: 353 training return: tensor(351.8216, device='cuda:0')
episode: 354 training return: tensor(-337.7466, device='cuda:0')
episode: 355 training return: tensor(-277.3895, device='cuda:0')
epoch: 89 test_true_pfm: 1955.7601072967052 sim_pfm: -33.16649754261986
episode: 356 training return: tensor(-209.8717, device='cuda:0')
episode: 357 training return: tensor(98.0425, device='cuda:0')
episode: 358 training return: tensor(-337.6542, device='cuda:0')
episode: 359 training return: tensor(-50.2885, device='cuda:0')
epoch: 90 test_true_pfm: 2839.7132030451435 sim_pfm: 217.90246330896238
episode: 360 training return: tensor(-2.0658, device='cuda:0')
episode: 361 training return: tensor(-299.4036, device='cuda:0')
episode: 362 training return: tensor(-343.0826, device='cuda:0')
episode: 363 training return: tensor(347.9975, device='cuda:0')
epoch: 91 test_true_pfm: 2458.2687780631295 sim_pfm: 241.18696047210446
episode: 364 training return: tensor(-267.4378, device='cuda:0')
episode: 365 training return: tensor(-243.9428, device='cuda:0')
episode: 366 training return: tensor(-27.7313, device='cuda:0')
episode: 367 training return: tensor(-333.0808, device='cuda:0')
epoch: 92 test_true_pfm: 3286.2454502729656 sim_pfm: 141.2684624956552
episode: 368 training return: tensor(-205.6346, device='cuda:0')
episode: 369 training return: tensor(329.7959, device='cuda:0')
episode: 370 training return: tensor(-334.0097, device='cuda:0')
episode: 371 training return: tensor(403.9285, device='cuda:0')
epoch: 93 test_true_pfm: 2885.6444768684214 sim_pfm: 311.1765249988918
episode: 372 training return: tensor(-200.3458, device='cuda:0')
episode: 373 training return: tensor(-209.7744, device='cuda:0')
episode: 374 training return: tensor(-96.8243, device='cuda:0')
episode: 375 training return: tensor(-334.5775, device='cuda:0')
epoch: 94 test_true_pfm: 3093.096462708931 sim_pfm: 283.0856587797559
episode: 376 training return: tensor(-73.6420, device='cuda:0')
episode: 377 training return: tensor(-260.8561, device='cuda:0')
episode: 378 training return: tensor(-341.9554, device='cuda:0')
episode: 379 training return: tensor(-307.8440, device='cuda:0')
epoch: 95 test_true_pfm: 2999.744194746457 sim_pfm: 295.972545427115
episode: 380 training return: tensor(241.4625, device='cuda:0')
episode: 381 training return: tensor(-253.1201, device='cuda:0')
episode: 382 training return: tensor(-277.2501, device='cuda:0')
episode: 383 training return: tensor(358.8770, device='cuda:0')
epoch: 96 test_true_pfm: 2264.633537575451 sim_pfm: 381.544222224106
episode: 384 training return: tensor(335.0668, device='cuda:0')
episode: 385 training return: tensor(-71.2998, device='cuda:0')
episode: 386 training return: tensor(-344.0801, device='cuda:0')
episode: 387 training return: tensor(282.0666, device='cuda:0')
epoch: 97 test_true_pfm: 2719.4843052082447 sim_pfm: 161.06890658514263
episode: 388 training return: tensor(-283.7195, device='cuda:0')
episode: 389 training return: tensor(-219.0523, device='cuda:0')
episode: 390 training return: tensor(-338.8212, device='cuda:0')
episode: 391 training return: tensor(373.5273, device='cuda:0')
epoch: 98 test_true_pfm: 2168.613165322798 sim_pfm: -34.85313341044821
episode: 392 training return: tensor(-233.0361, device='cuda:0')
episode: 393 training return: tensor(-355.8528, device='cuda:0')
episode: 394 training return: tensor(-343.8220, device='cuda:0')
episode: 395 training return: tensor(270.3828, device='cuda:0')
epoch: 99 test_true_pfm: 2544.282352250357 sim_pfm: 230.80299183514822
episode: 396 training return: tensor(-289.9178, device='cuda:0')
episode: 397 training return: tensor(-330.1419, device='cuda:0')
episode: 398 training return: tensor(-300.6909, device='cuda:0')
episode: 399 training return: tensor(-71.1676, device='cuda:0')
epoch: 100 test_true_pfm: 2920.709967298198 sim_pfm: 326.0926164740619
episode: 400 training return: tensor(-292.1141, device='cuda:0')
episode: 401 training return: tensor(273.9635, device='cuda:0')
episode: 402 training return: tensor(-341.2080, device='cuda:0')
episode: 403 training return: tensor(-311.4803, device='cuda:0')
epoch: 101 test_true_pfm: 2184.7539043945762 sim_pfm: 26.120758002391085
episode: 404 training return: tensor(360.4738, device='cuda:0')
episode: 405 training return: tensor(-224.2927, device='cuda:0')
episode: 406 training return: tensor(-202.6304, device='cuda:0')
episode: 407 training return: tensor(-314.3425, device='cuda:0')
epoch: 102 test_true_pfm: 2600.286590023155 sim_pfm: 278.4858545846073
episode: 408 training return: tensor(-220.9641, device='cuda:0')
episode: 409 training return: tensor(-195.5340, device='cuda:0')
episode: 410 training return: tensor(-248.1131, device='cuda:0')
episode: 411 training return: tensor(-344.0852, device='cuda:0')
epoch: 103 test_true_pfm: 2525.0570543260037 sim_pfm: 2.45170719694579
episode: 412 training return: tensor(166.1626, device='cuda:0')
episode: 413 training return: tensor(340.3681, device='cuda:0')
episode: 414 training return: tensor(351.6781, device='cuda:0')
episode: 415 training return: tensor(-285.4231, device='cuda:0')
epoch: 104 test_true_pfm: 1879.4403428741282 sim_pfm: 37.407915002744026
episode: 416 training return: tensor(358.5521, device='cuda:0')
episode: 417 training return: tensor(-343.6967, device='cuda:0')
episode: 418 training return: tensor(-246.7718, device='cuda:0')
episode: 419 training return: tensor(210.8598, device='cuda:0')
epoch: 105 test_true_pfm: 2746.6490991057 sim_pfm: 225.51042578183115
episode: 420 training return: tensor(-350.3855, device='cuda:0')
episode: 421 training return: tensor(320.6296, device='cuda:0')
episode: 422 training return: tensor(-335.5168, device='cuda:0')
episode: 423 training return: tensor(-271.9522, device='cuda:0')
epoch: 106 test_true_pfm: 2903.4727142650568 sim_pfm: 242.8668889022665
episode: 424 training return: tensor(-327.0081, device='cuda:0')
episode: 425 training return: tensor(-25.5903, device='cuda:0')
episode: 426 training return: tensor(-310.2807, device='cuda:0')
episode: 427 training return: tensor(-358.8839, device='cuda:0')
epoch: 107 test_true_pfm: 2015.1302109525084 sim_pfm: 145.54310123310037
episode: 428 training return: tensor(-207.4634, device='cuda:0')
episode: 429 training return: tensor(-225.0049, device='cuda:0')
episode: 430 training return: tensor(239.8053, device='cuda:0')
episode: 431 training return: tensor(125.9046, device='cuda:0')
epoch: 108 test_true_pfm: 2722.710998270973 sim_pfm: 355.47639813058777
episode: 432 training return: tensor(-343.0822, device='cuda:0')
episode: 433 training return: tensor(117.9151, device='cuda:0')
episode: 434 training return: tensor(-175.5200, device='cuda:0')
episode: 435 training return: tensor(-277.0844, device='cuda:0')
epoch: 109 test_true_pfm: 2708.5966981593847 sim_pfm: 372.790537177003
episode: 436 training return: tensor(-206.2989, device='cuda:0')
episode: 437 training return: tensor(-205.8376, device='cuda:0')
episode: 438 training return: tensor(298.2426, device='cuda:0')
episode: 439 training return: tensor(-17.3405, device='cuda:0')
epoch: 110 test_true_pfm: 3020.4059440202473 sim_pfm: 78.724467569642
episode: 440 training return: tensor(-210.5890, device='cuda:0')
episode: 441 training return: tensor(-295.5061, device='cuda:0')
episode: 442 training return: tensor(-338.1555, device='cuda:0')
episode: 443 training return: tensor(-245.4520, device='cuda:0')
epoch: 111 test_true_pfm: 2673.6807272660103 sim_pfm: -72.03014961835773
episode: 444 training return: tensor(-338.1569, device='cuda:0')
episode: 445 training return: tensor(-314.5828, device='cuda:0')
episode: 446 training return: tensor(398.5160, device='cuda:0')
episode: 447 training return: tensor(-313.6687, device='cuda:0')
epoch: 112 test_true_pfm: 3117.029403318758 sim_pfm: 154.83771307296897
episode: 448 training return: tensor(-214.4191, device='cuda:0')
episode: 449 training return: tensor(-320.8660, device='cuda:0')
episode: 450 training return: tensor(-291.5080, device='cuda:0')
episode: 451 training return: tensor(-265.4828, device='cuda:0')
epoch: 113 test_true_pfm: 2935.7980733513327 sim_pfm: 342.42490204582765
episode: 452 training return: tensor(304.4951, device='cuda:0')
episode: 453 training return: tensor(-175.2642, device='cuda:0')
episode: 454 training return: tensor(-296.7187, device='cuda:0')
episode: 455 training return: tensor(-340.8701, device='cuda:0')
epoch: 114 test_true_pfm: 2650.1562261028016 sim_pfm: 127.89278068738834
episode: 456 training return: tensor(24.6047, device='cuda:0')
episode: 457 training return: tensor(-176.3089, device='cuda:0')
episode: 458 training return: tensor(-246.4245, device='cuda:0')
episode: 459 training return: tensor(-338.1847, device='cuda:0')
epoch: 115 test_true_pfm: 2971.288138124273 sim_pfm: 188.4368193562453
episode: 460 training return: tensor(239.0619, device='cuda:0')
episode: 461 training return: tensor(-199.1388, device='cuda:0')
episode: 462 training return: tensor(-206.5191, device='cuda:0')
episode: 463 training return: tensor(-271.4774, device='cuda:0')
epoch: 116 test_true_pfm: 2412.197063268092 sim_pfm: 277.16856725281104
episode: 464 training return: tensor(-333.6673, device='cuda:0')
episode: 465 training return: tensor(367.3818, device='cuda:0')
episode: 466 training return: tensor(206.8886, device='cuda:0')
episode: 467 training return: tensor(-350.8288, device='cuda:0')
epoch: 117 test_true_pfm: 2199.119644186496 sim_pfm: 154.54670769783357
episode: 468 training return: tensor(341.0150, device='cuda:0')
episode: 469 training return: tensor(-189.4069, device='cuda:0')
episode: 470 training return: tensor(334.1683, device='cuda:0')
episode: 471 training return: tensor(-216.0645, device='cuda:0')
epoch: 118 test_true_pfm: 2984.0894982493214 sim_pfm: -179.20335957789212
episode: 472 training return: tensor(117.3815, device='cuda:0')
episode: 473 training return: tensor(-334.4183, device='cuda:0')
episode: 474 training return: tensor(347.4330, device='cuda:0')
episode: 475 training return: tensor(-292.0866, device='cuda:0')
epoch: 119 test_true_pfm: 1982.9986846755708 sim_pfm: 139.44359569922867
episode: 476 training return: tensor(148.8111, device='cuda:0')
episode: 477 training return: tensor(-277.3780, device='cuda:0')
episode: 478 training return: tensor(-41.1186, device='cuda:0')
episode: 479 training return: tensor(156.6332, device='cuda:0')
epoch: 120 test_true_pfm: 3134.256340023256 sim_pfm: 135.49536118541923
episode: 480 training return: tensor(-203.0209, device='cuda:0')
episode: 481 training return: tensor(352.7003, device='cuda:0')
episode: 482 training return: tensor(-206.6725, device='cuda:0')
episode: 483 training return: tensor(-336.1093, device='cuda:0')
epoch: 121 test_true_pfm: 2728.387151040359 sim_pfm: -115.83126318225793
episode: 484 training return: tensor(334.8333, device='cuda:0')
episode: 485 training return: tensor(-340.2255, device='cuda:0')
episode: 486 training return: tensor(-334.7710, device='cuda:0')
episode: 487 training return: tensor(-192.2946, device='cuda:0')
epoch: 122 test_true_pfm: 3012.406783996344 sim_pfm: 362.1720442244162
episode: 488 training return: tensor(-330.0763, device='cuda:0')
episode: 489 training return: tensor(-283.6616, device='cuda:0')
episode: 490 training return: tensor(-303.0353, device='cuda:0')
episode: 491 training return: tensor(-335.7529, device='cuda:0')
epoch: 123 test_true_pfm: 3045.8254911166673 sim_pfm: 265.71416331032134
episode: 492 training return: tensor(391.1979, device='cuda:0')
episode: 493 training return: tensor(2.6533, device='cuda:0')
episode: 494 training return: tensor(-285.5009, device='cuda:0')
episode: 495 training return: tensor(-38.9225, device='cuda:0')
epoch: 124 test_true_pfm: 2979.839537132868 sim_pfm: 150.2179232228858
episode: 496 training return: tensor(25.5813, device='cuda:0')
episode: 497 training return: tensor(-332.4107, device='cuda:0')
episode: 498 training return: tensor(284.5435, device='cuda:0')
episode: 499 training return: tensor(-196.8453, device='cuda:0')
epoch: 125 test_true_pfm: 2198.972128008475 sim_pfm: -9.723845609774193
episode: 500 training return: tensor(-272.6656, device='cuda:0')
episode: 501 training return: tensor(-82.0885, device='cuda:0')
episode: 502 training return: tensor(-316.9151, device='cuda:0')
episode: 503 training return: tensor(-88.1349, device='cuda:0')
epoch: 126 test_true_pfm: 1844.9484142786296 sim_pfm: 232.74990332794064
episode: 504 training return: tensor(-345.7314, device='cuda:0')
episode: 505 training return: tensor(324.6344, device='cuda:0')
episode: 506 training return: tensor(-319.1979, device='cuda:0')
episode: 507 training return: tensor(-290.1326, device='cuda:0')
epoch: 127 test_true_pfm: 2702.4054305959357 sim_pfm: 107.88294871292116
episode: 508 training return: tensor(380.8380, device='cuda:0')
episode: 509 training return: tensor(11.9688, device='cuda:0')
episode: 510 training return: tensor(348.6481, device='cuda:0')
episode: 511 training return: tensor(-198.7139, device='cuda:0')
epoch: 128 test_true_pfm: 1832.7620288640453 sim_pfm: 15.809562740847468
episode: 512 training return: tensor(344.7764, device='cuda:0')
episode: 513 training return: tensor(-347.6044, device='cuda:0')
episode: 514 training return: tensor(-318.9092, device='cuda:0')
episode: 515 training return: tensor(-102.6993, device='cuda:0')
epoch: 129 test_true_pfm: 3152.649718818049 sim_pfm: 60.47564263207217
episode: 516 training return: tensor(-249.8162, device='cuda:0')
episode: 517 training return: tensor(-241.4285, device='cuda:0')
episode: 518 training return: tensor(-338.2590, device='cuda:0')
episode: 519 training return: tensor(-210.5405, device='cuda:0')
epoch: 130 test_true_pfm: 2825.148867150074 sim_pfm: 160.26665466249688
episode: 520 training return: tensor(336.2814, device='cuda:0')
episode: 521 training return: tensor(-170.0022, device='cuda:0')
episode: 522 training return: tensor(-170.9519, device='cuda:0')
episode: 523 training return: tensor(-257.9030, device='cuda:0')
epoch: 131 test_true_pfm: 2642.755880937013 sim_pfm: 160.82343814031142
episode: 524 training return: tensor(-358.4640, device='cuda:0')
episode: 525 training return: tensor(-333.7246, device='cuda:0')
episode: 526 training return: tensor(-243.2665, device='cuda:0')
episode: 527 training return: tensor(334.0080, device='cuda:0')
epoch: 132 test_true_pfm: 3248.282573864908 sim_pfm: 152.26048508177823
episode: 528 training return: tensor(-308.7012, device='cuda:0')
episode: 529 training return: tensor(-247.4690, device='cuda:0')
episode: 530 training return: tensor(-278.4677, device='cuda:0')
episode: 531 training return: tensor(-188.6230, device='cuda:0')
epoch: 133 test_true_pfm: 2915.4233083516615 sim_pfm: 51.75404134078417
episode: 532 training return: tensor(390.0305, device='cuda:0')
episode: 533 training return: tensor(319.9214, device='cuda:0')
episode: 534 training return: tensor(-354.9381, device='cuda:0')
episode: 535 training return: tensor(353.0340, device='cuda:0')
epoch: 134 test_true_pfm: 3063.2730936819607 sim_pfm: 374.9193055887202
episode: 536 training return: tensor(-22.9692, device='cuda:0')
episode: 537 training return: tensor(106.0752, device='cuda:0')
episode: 538 training return: tensor(331.9605, device='cuda:0')
episode: 539 training return: tensor(-307.5074, device='cuda:0')
epoch: 135 test_true_pfm: 3010.939588337999 sim_pfm: 248.01995368144708
episode: 540 training return: tensor(-298.5935, device='cuda:0')
episode: 541 training return: tensor(329.9272, device='cuda:0')
episode: 542 training return: tensor(-294.8705, device='cuda:0')
episode: 543 training return: tensor(341.0283, device='cuda:0')
epoch: 136 test_true_pfm: 1831.9570830279633 sim_pfm: -223.78946343249604
episode: 544 training return: tensor(-281.4538, device='cuda:0')
episode: 545 training return: tensor(312.2002, device='cuda:0')
episode: 546 training return: tensor(359.4503, device='cuda:0')
episode: 547 training return: tensor(20.6688, device='cuda:0')
epoch: 137 test_true_pfm: 2736.5530217917385 sim_pfm: 141.58996767777717
episode: 548 training return: tensor(-274.4197, device='cuda:0')
episode: 549 training return: tensor(259.5497, device='cuda:0')
episode: 550 training return: tensor(-215.8494, device='cuda:0')
episode: 551 training return: tensor(-52.6838, device='cuda:0')
epoch: 138 test_true_pfm: 3218.5127039946833 sim_pfm: 59.68728976580314
episode: 552 training return: tensor(-89.2876, device='cuda:0')
episode: 553 training return: tensor(-204.5822, device='cuda:0')
episode: 554 training return: tensor(-260.6249, device='cuda:0')
episode: 555 training return: tensor(-325.3081, device='cuda:0')
epoch: 139 test_true_pfm: 2686.800457865223 sim_pfm: 189.30325131859476
episode: 556 training return: tensor(339.7620, device='cuda:0')
episode: 557 training return: tensor(-351.9428, device='cuda:0')
episode: 558 training return: tensor(-342.3327, device='cuda:0')
episode: 559 training return: tensor(-257.6177, device='cuda:0')
epoch: 140 test_true_pfm: 1621.05267927096 sim_pfm: 245.67996395930336
episode: 560 training return: tensor(-315.4597, device='cuda:0')
episode: 561 training return: tensor(-230.9791, device='cuda:0')
episode: 562 training return: tensor(-315.9008, device='cuda:0')
episode: 563 training return: tensor(31.7828, device='cuda:0')
epoch: 141 test_true_pfm: 2832.0198312788525 sim_pfm: 15.755556444327036
episode: 564 training return: tensor(-326.9858, device='cuda:0')
episode: 565 training return: tensor(-25.8118, device='cuda:0')
episode: 566 training return: tensor(-177.9982, device='cuda:0')
episode: 567 training return: tensor(-109.5491, device='cuda:0')
epoch: 142 test_true_pfm: 3044.7827084009455 sim_pfm: 69.23518581475946
episode: 568 training return: tensor(-215.0168, device='cuda:0')
episode: 569 training return: tensor(111.5935, device='cuda:0')
episode: 570 training return: tensor(83.1763, device='cuda:0')
episode: 571 training return: tensor(210.0070, device='cuda:0')
epoch: 143 test_true_pfm: 2214.844506440446 sim_pfm: 155.53615462209564
episode: 572 training return: tensor(172.1466, device='cuda:0')
episode: 573 training return: tensor(-318.6612, device='cuda:0')
episode: 574 training return: tensor(-339.8453, device='cuda:0')
episode: 575 training return: tensor(-281.6995, device='cuda:0')
epoch: 144 test_true_pfm: 2226.617006281554 sim_pfm: -39.89546312750705
episode: 576 training return: tensor(-321.5643, device='cuda:0')
episode: 577 training return: tensor(-292.6245, device='cuda:0')
episode: 578 training return: tensor(-352.3507, device='cuda:0')
episode: 579 training return: tensor(-212.4957, device='cuda:0')
epoch: 145 test_true_pfm: 2654.6764452235857 sim_pfm: 156.56592086956758
episode: 580 training return: tensor(-323.9776, device='cuda:0')
episode: 581 training return: tensor(-187.6563, device='cuda:0')
episode: 582 training return: tensor(-161.7065, device='cuda:0')
episode: 583 training return: tensor(-214.5478, device='cuda:0')
epoch: 146 test_true_pfm: 2732.5263823151968 sim_pfm: 17.16452538028049
episode: 584 training return: tensor(349.2924, device='cuda:0')
episode: 585 training return: tensor(74.4746, device='cuda:0')
episode: 586 training return: tensor(361.2874, device='cuda:0')
episode: 587 training return: tensor(337.2423, device='cuda:0')
epoch: 147 test_true_pfm: 2834.902089539644 sim_pfm: -21.090830111488078
episode: 588 training return: tensor(-339.3388, device='cuda:0')
episode: 589 training return: tensor(364.8445, device='cuda:0')
episode: 590 training return: tensor(336.2868, device='cuda:0')
episode: 591 training return: tensor(408.9770, device='cuda:0')
epoch: 148 test_true_pfm: 2644.628197672881 sim_pfm: 284.57199866718537
episode: 592 training return: tensor(-197.4413, device='cuda:0')
episode: 593 training return: tensor(-256.8460, device='cuda:0')
episode: 594 training return: tensor(-154.9094, device='cuda:0')
episode: 595 training return: tensor(-346.5993, device='cuda:0')
epoch: 149 test_true_pfm: 2344.3817909224686 sim_pfm: 193.9203190979509
episode: 596 training return: tensor(-275.3828, device='cuda:0')
episode: 597 training return: tensor(-306.1034, device='cuda:0')
episode: 598 training return: tensor(-346.6344, device='cuda:0')
episode: 599 training return: tensor(-83.4744, device='cuda:0')
epoch: 150 test_true_pfm: 2381.3470728183643 sim_pfm: 44.933010059447646
