['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '4', '--data', '10000']
epoch: 0 training_loss 0.25570222437381745 test_loss: 0.213175630569458
epoch: 1 training_loss 0.1972207422554493 test_loss: 0.2137747049331665
epoch: 2 training_loss 0.1997505669295788 test_loss: 0.18216127157211304
epoch: 3 training_loss 0.19367796048521996 test_loss: 0.18922777175903321
epoch: 4 training_loss 0.1997973769903183 test_loss: 0.19045250415802
epoch: 5 training_loss 0.2037420367449522 test_loss: 0.1689214825630188
epoch: 6 training_loss 0.18858328312635422 test_loss: 0.1852760910987854
epoch: 7 training_loss 0.1974092973768711 test_loss: 0.17441856861114502
epoch: 8 training_loss 0.19221409246325494 test_loss: 0.18012725114822387
epoch: 9 training_loss 0.18386444717645645 test_loss: 0.18304625749588013
epoch: 10 training_loss 0.1879518824070692 test_loss: 0.19801222085952758
epoch: 11 training_loss 0.1884835535287857 test_loss: 0.17908846139907836
epoch: 12 training_loss 0.18467666074633599 test_loss: 0.1825828433036804
epoch: 13 training_loss 0.18358903996646403 test_loss: 0.1815989851951599
epoch: 14 training_loss 0.18270458355546 test_loss: 0.17841296195983886
epoch: 15 training_loss 0.17925655283033848 test_loss: 0.19421124458312988
epoch: 16 training_loss 0.18393330104649067 test_loss: 0.17589362859725952
epoch: 17 training_loss 0.18053488835692405 test_loss: 0.179207181930542
epoch: 18 training_loss 0.17777501225471495 test_loss: 0.18159620761871337
epoch: 19 training_loss 0.18291859604418279 test_loss: 0.1820939302444458
epoch: 20 training_loss 0.17711394630372523 test_loss: 0.17889761924743652
epoch: 21 training_loss 0.1761857583373785 test_loss: 0.17313754558563232
epoch: 22 training_loss 0.18629496343433857 test_loss: 0.17092084884643555
epoch: 23 training_loss 0.16739582262933253 test_loss: 0.18792790174484253
epoch: 24 training_loss 0.17450938813388348 test_loss: 0.20437848567962646
epoch: 25 training_loss 0.17419592551887036 test_loss: 0.17771002054214477
epoch: 26 training_loss 0.17436197809875012 test_loss: 0.1799567699432373
epoch: 27 training_loss 0.17778130449354648 test_loss: 0.18094202280044555
epoch: 28 training_loss 0.17803438305854796 test_loss: 0.18719059228897095
epoch: 29 training_loss 0.17109262220561505 test_loss: 0.1851420521736145
epoch: 30 training_loss 0.18258204698562622 test_loss: 0.17866795063018798
epoch: 31 training_loss 0.17939322866499424 test_loss: 0.1663341760635376
epoch: 32 training_loss 0.17870570614933967 test_loss: 0.18559978008270264
epoch: 33 training_loss 0.17934916876256465 test_loss: 0.17718621492385864
epoch: 34 training_loss 0.17982085399329661 test_loss: 0.1799583315849304
epoch: 35 training_loss 0.17991371549665927 test_loss: 0.17734605073928833
epoch: 36 training_loss 0.18024978078901768 test_loss: 0.18280496597290039
epoch: 37 training_loss 0.17650482833385467 test_loss: 0.18044191598892212
epoch: 38 training_loss 0.179971288330853 test_loss: 0.1791629195213318
epoch: 39 training_loss 0.1766149753332138 test_loss: 0.180788254737854
epoch: 40 training_loss 0.18054637886583805 test_loss: 0.17396819591522217
epoch: 41 training_loss 0.17843987435102462 test_loss: 0.17805758714675904
epoch: 42 training_loss 0.17278386607766152 test_loss: 0.17863694429397584
epoch: 43 training_loss 0.17856294907629489 test_loss: 0.1681045413017273
epoch: 44 training_loss 0.17791962556540966 test_loss: 0.18181319236755372
epoch: 45 training_loss 0.17539876855909825 test_loss: 0.18143573999404908
epoch: 46 training_loss 0.17606603316962718 test_loss: 0.1739375352859497
epoch: 47 training_loss 0.17604690447449683 test_loss: 0.2041853427886963
epoch: 48 training_loss 0.16811833269894122 test_loss: 0.17310140132904053
epoch: 49 training_loss 0.17825860626995563 test_loss: 0.17872658967971802
epoch: 50 training_loss 0.17633172288537025 test_loss: 0.18704694509506226
epoch: 51 training_loss 0.1777876254916191 test_loss: 0.17374969720840455
epoch: 52 training_loss 0.17042732320725917 test_loss: 0.17651861906051636
epoch: 53 training_loss 0.1758926422894001 test_loss: 0.17503682374954224
epoch: 54 training_loss 0.1773568019270897 test_loss: 0.18026418685913087
epoch: 55 training_loss 0.17742489606142045 test_loss: 0.18724186420440675
epoch: 56 training_loss 0.16863492514938117 test_loss: 0.1757521152496338
epoch: 57 training_loss 0.166923254057765 test_loss: 0.16746500730514527
epoch: 58 training_loss 0.16991479523479938 test_loss: 0.18720394372940063
epoch: 59 training_loss 0.17575454384088515 test_loss: 0.1766645312309265
epoch: 60 training_loss 0.1750585262477398 test_loss: 0.1737865090370178
epoch: 61 training_loss 0.1788552240282297 test_loss: 0.17058174610137938
epoch: 62 training_loss 0.1666714362055063 test_loss: 0.18317651748657227
epoch: 63 training_loss 0.1818773127347231 test_loss: 0.18130843639373778
epoch: 64 training_loss 0.1718185043334961 test_loss: 0.1785990834236145
epoch: 65 training_loss 0.17093438051640988 test_loss: 0.18566681146621705
epoch: 66 training_loss 0.17837056778371335 test_loss: 0.17951403856277465
epoch: 67 training_loss 0.17662910118699074 test_loss: 0.1839860796928406
epoch: 68 training_loss 0.17211118917912244 test_loss: 0.18890485763549805
epoch: 69 training_loss 0.17843790642917157 test_loss: 0.18735700845718384
epoch: 70 training_loss 0.16935608685016632 test_loss: 0.17302676439285278
epoch: 71 training_loss 0.17494895808398725 test_loss: 0.19003945589065552
epoch: 72 training_loss 0.1726568763703108 test_loss: 0.19725908041000367
epoch: 73 training_loss 0.17782620303332805 test_loss: 0.1819538950920105
epoch: 74 training_loss 0.17010414615273475 test_loss: 0.18013056516647338
epoch: 75 training_loss 0.18319855764508247 test_loss: 0.1690598964691162
epoch: 76 training_loss 0.16730787396430968 test_loss: 0.19306524991989135
epoch: 77 training_loss 0.1731412935256958 test_loss: 0.17901726961135864
epoch: 78 training_loss 0.16844559270888568 test_loss: 0.18677980899810792
epoch: 79 training_loss 0.17435409285128117 test_loss: 0.18002188205718994
epoch: 80 training_loss 0.17328522704541682 test_loss: 0.1804349422454834
epoch: 81 training_loss 0.16725790660828352 test_loss: 0.18668891191482545
epoch: 82 training_loss 0.16635910779237748 test_loss: 0.17421475648880005
epoch: 83 training_loss 0.17104998555034398 test_loss: 0.18978698253631593
epoch: 84 training_loss 0.17550935931503772 test_loss: 0.1773427963256836
epoch: 85 training_loss 0.17199979953467845 test_loss: 0.19545440673828124
epoch: 86 training_loss 0.16896454721689225 test_loss: 0.19003084897994996
epoch: 87 training_loss 0.17188587978482248 test_loss: 0.1923107385635376
epoch: 88 training_loss 0.181723687723279 test_loss: 0.17648012638092042
epoch: 89 training_loss 0.16954616598784925 test_loss: 0.1822375774383545
epoch: 90 training_loss 0.16803730741143227 test_loss: 0.17907651662826538
epoch: 91 training_loss 0.1674810730665922 test_loss: 0.20944137573242189
epoch: 92 training_loss 0.16735284648835658 test_loss: 0.17827768325805665
epoch: 93 training_loss 0.17030060708522796 test_loss: 0.1844268560409546
epoch: 94 training_loss 0.1704045707732439 test_loss: 0.19130513668060303
epoch: 95 training_loss 0.16827398858964443 test_loss: 0.18691667318344116
epoch: 96 training_loss 0.1720239096134901 test_loss: 0.18437994718551637
epoch: 97 training_loss 0.1650567577406764 test_loss: 0.17920101881027223
epoch: 98 training_loss 0.17339512571692467 test_loss: 0.16985771656036378
epoch: 99 training_loss 0.16794846668839455 test_loss: 0.1752668499946594
epoch: 100 training_loss 0.1646544972807169 test_loss: 0.1890282392501831
epoch: 101 training_loss 0.16070229589939117 test_loss: 0.1932360291481018
epoch: 102 training_loss 0.17639760069549085 test_loss: 0.17310105562210082
epoch: 103 training_loss 0.1676291836798191 test_loss: 0.18122800588607788
epoch: 104 training_loss 0.1678555652499199 test_loss: 0.1720718502998352
epoch: 105 training_loss 0.16345689997076987 test_loss: 0.16548875570297242
epoch: 106 training_loss 0.17238608844578265 test_loss: 0.18423082828521728
epoch: 107 training_loss 0.17159974731504918 test_loss: 0.17206772565841674
epoch: 108 training_loss 0.1680108791589737 test_loss: 0.1856189489364624
epoch: 109 training_loss 0.16706619292497635 test_loss: 0.1841598391532898
epoch: 110 training_loss 0.16866803869605065 test_loss: 0.17987666130065919
epoch: 111 training_loss 0.1699689366668463 test_loss: 0.1870356559753418
epoch: 112 training_loss 0.16943879991769792 test_loss: 0.19122681617736817
epoch: 113 training_loss 0.1733614547550678 test_loss: 0.18494006395339965
epoch: 114 training_loss 0.16802725665271281 test_loss: 0.17585723400115966
epoch: 115 training_loss 0.171209417283535 test_loss: 0.1840693712234497
epoch: 116 training_loss 0.17626177050173283 test_loss: 0.18306562900543213
epoch: 117 training_loss 0.1676742697507143 test_loss: 0.1836242914199829
epoch: 118 training_loss 0.16964346185326576 test_loss: 0.1779571533203125
epoch: 119 training_loss 0.16459753058850765 test_loss: 0.18619694709777831
epoch: 120 training_loss 0.171164890229702 test_loss: 0.17574763298034668
epoch: 121 training_loss 0.17129546023905276 test_loss: 0.17502952814102174
epoch: 122 training_loss 0.17000758983194827 test_loss: 0.17534042596817018
epoch: 123 training_loss 0.1589953426644206 test_loss: 0.17788567543029785
epoch: 124 training_loss 0.16457649156451226 test_loss: 0.183635413646698
epoch: 125 training_loss 0.16869852147996425 test_loss: 0.18072032928466797
epoch: 126 training_loss 0.16320025637745858 test_loss: 0.18558214902877807
epoch: 127 training_loss 0.16302568197250367 test_loss: 0.1934923529624939
epoch: 128 training_loss 0.16480476684868337 test_loss: 0.1709902048110962
epoch: 129 training_loss 0.1675431677699089 test_loss: 0.1750045657157898
epoch: 130 training_loss 0.16471140675246715 test_loss: 0.17818615436553956
epoch: 131 training_loss 0.16372290447354318 test_loss: 0.17802057266235352
epoch: 132 training_loss 0.16976496756076812 test_loss: 0.18430712223052978
epoch: 133 training_loss 0.17268933862447738 test_loss: 0.1768062472343445
epoch: 134 training_loss 0.16584615424275398 test_loss: 0.1865478515625
epoch: 135 training_loss 0.17920336611568927 test_loss: 0.18293945789337157
epoch: 136 training_loss 0.1698237070441246 test_loss: 0.18222352266311645
epoch: 137 training_loss 0.16465495087206364 test_loss: 0.18018784523010253
epoch: 138 training_loss 0.16464656606316566 test_loss: 0.185606849193573
epoch: 139 training_loss 0.1681811536848545 test_loss: 0.18433700799942015
epoch: 140 training_loss 0.16460161782801153 test_loss: 0.1889349102973938
epoch: 141 training_loss 0.15872804686427117 test_loss: 0.18466804027557374
epoch: 142 training_loss 0.17765316061675548 test_loss: 0.19692201614379884
epoch: 143 training_loss 0.16500369291752576 test_loss: 0.17385537624359132
epoch: 144 training_loss 0.16465935207903384 test_loss: 0.1777329444885254
epoch: 145 training_loss 0.1698290641605854 test_loss: 0.19853107929229735
epoch: 146 training_loss 0.1707548725605011 test_loss: 0.18743457794189453
epoch: 147 training_loss 0.15980503685772418 test_loss: 0.19256794452667236
epoch: 148 training_loss 0.16480157785117627 test_loss: 0.17635996341705323
epoch: 149 training_loss 0.16512626942247152 test_loss: 0.19988151788711547
epoch: 0 training_loss 10.13486478805542 test_loss: 5.357573318481445
epoch: 1 training_loss 4.3500453162193295 test_loss: 3.4433357238769533
epoch: 2 training_loss 3.0261270093917845 test_loss: 2.643560218811035
epoch: 3 training_loss 2.4247888815402985 test_loss: 2.054269027709961
epoch: 4 training_loss 1.912148767709732 test_loss: 1.7132255554199218
epoch: 5 training_loss 1.6895576751232146 test_loss: 1.5109149932861328
epoch: 6 training_loss 1.501491802930832 test_loss: 1.4106931686401367
epoch: 7 training_loss 1.3797976326942445 test_loss: 1.3201529502868652
epoch: 8 training_loss 1.2864503633975983 test_loss: 1.2003084182739259
epoch: 9 training_loss 1.222227761745453 test_loss: 1.1932572364807128
epoch: 10 training_loss 1.1612832748889923 test_loss: 1.1255515098571778
epoch: 11 training_loss 1.1317407381534577 test_loss: 1.0996845245361329
epoch: 12 training_loss 1.083375739455223 test_loss: 1.0596379280090331
epoch: 13 training_loss 1.0668015551567078 test_loss: 1.0782966613769531
epoch: 14 training_loss 1.0262603145837783 test_loss: 1.0194901466369628
epoch: 15 training_loss 1.0054011368751525 test_loss: 1.011416244506836
epoch: 16 training_loss 0.9806296974420547 test_loss: 1.0049375534057616
epoch: 17 training_loss 0.9681021201610566 test_loss: 0.9648177146911621
epoch: 18 training_loss 0.9440173423290252 test_loss: 0.9326362609863281
epoch: 19 training_loss 0.9285921680927277 test_loss: 0.8999663352966308
epoch: 20 training_loss 0.910630658864975 test_loss: 0.8863831520080566
epoch: 21 training_loss 0.899863309264183 test_loss: 0.8692667007446289
epoch: 22 training_loss 0.8833823198080063 test_loss: 0.8618593215942383
epoch: 23 training_loss 0.8654022067785263 test_loss: 0.865358543395996
epoch: 24 training_loss 0.8489110845327378 test_loss: 0.840504264831543
epoch: 25 training_loss 0.8406797027587891 test_loss: 0.8306084632873535
epoch: 26 training_loss 0.8279203194379806 test_loss: 0.8126157760620117
epoch: 27 training_loss 0.8212025368213653 test_loss: 0.8017610549926758
epoch: 28 training_loss 0.7994587028026581 test_loss: 0.7813149929046631
epoch: 29 training_loss 0.8052574694156647 test_loss: 0.765618371963501
epoch: 30 training_loss 0.7709045058488846 test_loss: 0.7923182964324951
epoch: 31 training_loss 0.7839684438705444 test_loss: 0.7720753192901612
epoch: 32 training_loss 0.7650427591800689 test_loss: 0.7557708263397217
epoch: 33 training_loss 0.7566937750577927 test_loss: 0.7548954963684082
epoch: 34 training_loss 0.7415331321954727 test_loss: 0.7398425102233886
epoch: 35 training_loss 0.7382041949033737 test_loss: 0.7301471710205079
epoch: 36 training_loss 0.7320941811800004 test_loss: 0.7164129734039306
epoch: 37 training_loss 0.7337218183279037 test_loss: 0.7434697151184082
epoch: 38 training_loss 0.7187320441007614 test_loss: 0.7118932247161865
epoch: 39 training_loss 0.7187218230962753 test_loss: 0.7258353233337402
epoch: 40 training_loss 0.707301806807518 test_loss: 0.7121358871459961
epoch: 41 training_loss 0.7073263818025589 test_loss: 0.7007896900177002
epoch: 42 training_loss 0.6918276250362396 test_loss: 0.6862001419067383
epoch: 43 training_loss 0.7025932389497757 test_loss: 0.6836806297302246
epoch: 44 training_loss 0.6807100987434387 test_loss: 0.6676368236541748
epoch: 45 training_loss 0.6851130044460296 test_loss: 0.674350643157959
epoch: 46 training_loss 0.6838280200958252 test_loss: 0.7328876495361328
epoch: 47 training_loss 0.6747720712423324 test_loss: 0.6645244121551513
epoch: 48 training_loss 0.6541741740703583 test_loss: 0.6535892486572266
epoch: 49 training_loss 0.6589843779802322 test_loss: 0.6560544490814209
epoch: 50 training_loss 0.6554460948705674 test_loss: 0.650762939453125
epoch: 51 training_loss 0.6568571263551712 test_loss: 0.6615294933319091
epoch: 52 training_loss 0.6499539232254028 test_loss: 0.6708811759948731
epoch: 53 training_loss 0.6580518424510956 test_loss: 0.6997062683105468
epoch: 54 training_loss 0.6609824818372726 test_loss: 0.6267798900604248
epoch: 55 training_loss 0.6355206090211868 test_loss: 0.6390375614166259
epoch: 56 training_loss 0.6368642210960388 test_loss: 0.6344157695770264
epoch: 57 training_loss 0.6401868999004364 test_loss: 0.6387977123260498
epoch: 58 training_loss 0.6234121417999268 test_loss: 0.6272031307220459
epoch: 59 training_loss 0.6375861221551895 test_loss: 0.6184032917022705
epoch: 60 training_loss 0.6296948570013047 test_loss: 0.6733656883239746
epoch: 61 training_loss 0.6367048609256745 test_loss: 0.6315235614776611
epoch: 62 training_loss 0.6122230386734009 test_loss: 0.6102725982666015
epoch: 63 training_loss 0.6108064842224121 test_loss: 0.6153180599212646
epoch: 64 training_loss 0.6089874398708344 test_loss: 0.6507213115692139
epoch: 65 training_loss 0.6120038682222366 test_loss: 0.6281654834747314
epoch: 66 training_loss 0.5953375214338302 test_loss: 0.6081909656524658
epoch: 67 training_loss 0.6088444918394089 test_loss: 0.624681043624878
epoch: 68 training_loss 0.6117517346143723 test_loss: 0.6086484909057617
epoch: 69 training_loss 0.5983893001079559 test_loss: 0.6045503139495849
epoch: 70 training_loss 0.5986997598409652 test_loss: 0.5950186729431153
epoch: 71 training_loss 0.5975321573019028 test_loss: 0.5778533935546875
epoch: 72 training_loss 0.5908014976978302 test_loss: 0.6188748359680176
epoch: 73 training_loss 0.606940204501152 test_loss: 0.6034910678863525
epoch: 74 training_loss 0.5873951417207718 test_loss: 0.5868170738220215
epoch: 75 training_loss 0.5767986351251602 test_loss: 0.5749540328979492
epoch: 76 training_loss 0.5829771101474762 test_loss: 0.5761133670806885
epoch: 77 training_loss 0.5744146421551705 test_loss: 0.5968530178070068
epoch: 78 training_loss 0.5909821498394012 test_loss: 0.5766395092010498
epoch: 79 training_loss 0.5792678153514862 test_loss: 0.5931037425994873
epoch: 80 training_loss 0.5738356775045395 test_loss: 0.5658007144927979
epoch: 81 training_loss 0.5652520281076431 test_loss: 0.5585852146148682
epoch: 82 training_loss 0.5687429904937744 test_loss: 0.5896215438842773
epoch: 83 training_loss 0.566075193285942 test_loss: 0.5636726379394531
epoch: 84 training_loss 0.5645008641481399 test_loss: 0.5894381046295166
epoch: 85 training_loss 0.5731308269500732 test_loss: 0.5648946762084961
epoch: 86 training_loss 0.5721133086085319 test_loss: 0.5763527393341065
epoch: 87 training_loss 0.5688059002161026 test_loss: 0.5654068470001221
epoch: 88 training_loss 0.5598037442564965 test_loss: 0.6225046634674072
epoch: 89 training_loss 0.5736287567019462 test_loss: 0.5847474098205566
epoch: 90 training_loss 0.5552357724308967 test_loss: 0.5534132957458496
epoch: 91 training_loss 0.5569219860434532 test_loss: 0.5686938762664795
epoch: 92 training_loss 0.5562617921829224 test_loss: 0.5528318405151367
epoch: 93 training_loss 0.5504969769716263 test_loss: 0.556538438796997
epoch: 94 training_loss 0.567647602558136 test_loss: 0.5567398548126221
epoch: 95 training_loss 0.5500885540246964 test_loss: 0.5723907470703125
epoch: 96 training_loss 0.5487662148475647 test_loss: 0.5620999813079834
epoch: 97 training_loss 0.5507877427339554 test_loss: 0.5332841873168945
epoch: 98 training_loss 0.5505556392669678 test_loss: 0.5970734596252442
epoch: 99 training_loss 0.5496387773752213 test_loss: 0.5226922035217285
epoch: 100 training_loss 0.5456185010075569 test_loss: 0.5450579166412354
epoch: 101 training_loss 0.5529192522168159 test_loss: 0.5748311519622803
epoch: 102 training_loss 0.5440161386132241 test_loss: 0.5452211856842041
epoch: 103 training_loss 0.5506061977148056 test_loss: 0.5508333206176758
epoch: 104 training_loss 0.5409608060121536 test_loss: 0.5328845977783203
epoch: 105 training_loss 0.5403217056393623 test_loss: 0.558293342590332
epoch: 106 training_loss 0.5329811260104179 test_loss: 0.5294832706451416
epoch: 107 training_loss 0.526963512301445 test_loss: 0.5407503128051758
epoch: 108 training_loss 0.5427084636688232 test_loss: 0.5306380748748779
epoch: 109 training_loss 0.5291178157925606 test_loss: 0.5615715026855469
epoch: 110 training_loss 0.5439601597189904 test_loss: 0.5537727355957032
epoch: 111 training_loss 0.5394188010692597 test_loss: 0.5332142353057862
epoch: 112 training_loss 0.5423786580562592 test_loss: 0.5620695590972901
epoch: 113 training_loss 0.5291774168610572 test_loss: 0.5308670997619629
epoch: 114 training_loss 0.5220372202992439 test_loss: 0.5417400360107422
epoch: 115 training_loss 0.5238361403346061 test_loss: 0.5261305332183838
epoch: 116 training_loss 0.5238772732019424 test_loss: 0.5437952518463135
epoch: 117 training_loss 0.5312778455018997 test_loss: 0.5323301315307617
epoch: 118 training_loss 0.5257689982652665 test_loss: 0.5268398284912109
epoch: 119 training_loss 0.5224679607152939 test_loss: 0.5277305603027344
epoch: 120 training_loss 0.5216147491335869 test_loss: 0.5404555320739746
epoch: 121 training_loss 0.5210734635591507 test_loss: 0.5181103229522706
epoch: 122 training_loss 0.5259980183839797 test_loss: 0.5299952507019043
epoch: 123 training_loss 0.5215042212605476 test_loss: 0.5315042972564697
epoch: 124 training_loss 0.5243040537834167 test_loss: 0.5206880092620849
epoch: 125 training_loss 0.5171068540215492 test_loss: 0.5178305625915527
epoch: 126 training_loss 0.5214227673411369 test_loss: 0.5506336688995361
epoch: 127 training_loss 0.5124343809485435 test_loss: 0.5295456886291504
epoch: 128 training_loss 0.5188324639201164 test_loss: 0.5187277793884277
epoch: 129 training_loss 0.5165491384267807 test_loss: 0.5673104286193847
epoch: 130 training_loss 0.5247316908836365 test_loss: 0.5711613655090332
epoch: 131 training_loss 0.5149833366274834 test_loss: 0.5393679141998291
epoch: 132 training_loss 0.5242828974127769 test_loss: 0.5358162879943847
epoch: 133 training_loss 0.512930510044098 test_loss: 0.5015143871307373
epoch: 134 training_loss 0.5037094366550445 test_loss: 0.5275176525115967
epoch: 135 training_loss 0.5089027202129364 test_loss: 0.5108726501464844
epoch: 136 training_loss 0.5193234011530876 test_loss: 0.5205049037933349
epoch: 137 training_loss 0.5137459436058998 test_loss: 0.5550978183746338
epoch: 138 training_loss 0.5049425929784774 test_loss: 0.5022314071655274
epoch: 139 training_loss 0.5035473680496216 test_loss: 0.5071298122406006
epoch: 140 training_loss 0.508205437362194 test_loss: 0.5081760883331299
epoch: 141 training_loss 0.5171911054849625 test_loss: 0.48926639556884766
epoch: 142 training_loss 0.5076679843664169 test_loss: 0.5067119121551513
epoch: 143 training_loss 0.5038760095834732 test_loss: 0.5280964851379395
epoch: 144 training_loss 0.5069361564517021 test_loss: 0.5259939193725586
epoch: 145 training_loss 0.5119804108142852 test_loss: 0.5151255607604981
epoch: 146 training_loss 0.505524733364582 test_loss: 0.5049127101898193
epoch: 147 training_loss 0.4988265958428383 test_loss: 0.49413418769836426
epoch: 148 training_loss 0.5010932111740112 test_loss: 0.5100260257720948
epoch: 149 training_loss 0.4998077690601349 test_loss: 0.500312089920044
2848.915990250755
episode: 0 training return: tensor(-306.9487, device='cuda:0')
episode: 1 training return: tensor(-332.7791, device='cuda:0')
episode: 2 training return: tensor(-220.7161, device='cuda:0')
episode: 3 training return: tensor(-289.9549, device='cuda:0')
epoch: 1 test_true_pfm: 2284.2393019152173 sim_pfm: 15.999835453820802
episode: 4 training return: tensor(-347.2838, device='cuda:0')
episode: 5 training return: tensor(-266.3158, device='cuda:0')
episode: 6 training return: tensor(-264.7524, device='cuda:0')
episode: 7 training return: tensor(-195.1787, device='cuda:0')
epoch: 2 test_true_pfm: 2915.4800190473106 sim_pfm: 67.0716799532917
episode: 8 training return: tensor(-74.7920, device='cuda:0')
episode: 9 training return: tensor(-87.8071, device='cuda:0')
episode: 10 training return: tensor(-353.3072, device='cuda:0')
episode: 11 training return: tensor(-354.4113, device='cuda:0')
epoch: 3 test_true_pfm: 1271.3641251727302 sim_pfm: -356.8950111576608
episode: 12 training return: tensor(-247.8796, device='cuda:0')
episode: 13 training return: tensor(96.3294, device='cuda:0')
episode: 14 training return: tensor(-350.9274, device='cuda:0')
episode: 15 training return: tensor(-345.7061, device='cuda:0')
epoch: 4 test_true_pfm: 1378.9592352477657 sim_pfm: -308.0477747972279
episode: 16 training return: tensor(-275.0973, device='cuda:0')
episode: 17 training return: tensor(-162.1183, device='cuda:0')
episode: 18 training return: tensor(-115.1657, device='cuda:0')
episode: 19 training return: tensor(-300.0153, device='cuda:0')
epoch: 5 test_true_pfm: 1538.8817397575974 sim_pfm: -256.3108738170704
episode: 20 training return: tensor(86.7228, device='cuda:0')
episode: 21 training return: tensor(-213.1558, device='cuda:0')
episode: 22 training return: tensor(219.5995, device='cuda:0')
episode: 23 training return: tensor(-354.8539, device='cuda:0')
epoch: 6 test_true_pfm: 1401.2522778404716 sim_pfm: -265.0827415928167
episode: 24 training return: tensor(-332.0356, device='cuda:0')
episode: 25 training return: tensor(-175.6240, device='cuda:0')
episode: 26 training return: tensor(-334.6520, device='cuda:0')
episode: 27 training return: tensor(-49.9783, device='cuda:0')
epoch: 7 test_true_pfm: 1306.7839711530821 sim_pfm: -358.9388815757896
episode: 28 training return: tensor(-289.1268, device='cuda:0')
episode: 29 training return: tensor(177.2485, device='cuda:0')
episode: 30 training return: tensor(-237.6081, device='cuda:0')
episode: 31 training return: tensor(-326.6808, device='cuda:0')
epoch: 8 test_true_pfm: 1262.9068671352186 sim_pfm: -353.7047121215049
episode: 32 training return: tensor(-360.2139, device='cuda:0')
episode: 33 training return: tensor(149.5055, device='cuda:0')
episode: 34 training return: tensor(-316.1855, device='cuda:0')
episode: 35 training return: tensor(-259.2477, device='cuda:0')
epoch: 9 test_true_pfm: 1286.8754637533186 sim_pfm: -370.9066513214493
episode: 36 training return: tensor(-337.8124, device='cuda:0')
episode: 37 training return: tensor(-260.0993, device='cuda:0')
episode: 38 training return: tensor(-94.6381, device='cuda:0')
episode: 39 training return: tensor(-371.9397, device='cuda:0')
epoch: 10 test_true_pfm: 1826.0998843209754 sim_pfm: -143.23720145665962
episode: 40 training return: tensor(-305.6182, device='cuda:0')
episode: 41 training return: tensor(-292.8630, device='cuda:0')
episode: 42 training return: tensor(-286.3269, device='cuda:0')
episode: 43 training return: tensor(-331.5670, device='cuda:0')
epoch: 11 test_true_pfm: 1601.8812288643157 sim_pfm: -114.33143382577691
episode: 44 training return: tensor(-144.8660, device='cuda:0')
episode: 45 training return: tensor(-314.8618, device='cuda:0')
episode: 46 training return: tensor(-248.4539, device='cuda:0')
episode: 47 training return: tensor(-357.5800, device='cuda:0')
epoch: 12 test_true_pfm: 2632.2991069775053 sim_pfm: 52.0709236736487
episode: 48 training return: tensor(-337.1737, device='cuda:0')
episode: 49 training return: tensor(319.1349, device='cuda:0')
episode: 50 training return: tensor(-359.2692, device='cuda:0')
episode: 51 training return: tensor(-93.7899, device='cuda:0')
epoch: 13 test_true_pfm: 1841.4155776833104 sim_pfm: 97.57704059319803
episode: 52 training return: tensor(164.3073, device='cuda:0')
episode: 53 training return: tensor(-350.5941, device='cuda:0')
episode: 54 training return: tensor(206.0649, device='cuda:0')
episode: 55 training return: tensor(-318.5683, device='cuda:0')
epoch: 14 test_true_pfm: 1947.5797669104286 sim_pfm: 21.981159057972643
episode: 56 training return: tensor(-327.4633, device='cuda:0')
episode: 57 training return: tensor(326.0503, device='cuda:0')
episode: 58 training return: tensor(324.5826, device='cuda:0')
episode: 59 training return: tensor(-280.7955, device='cuda:0')
epoch: 15 test_true_pfm: 2350.2371375880743 sim_pfm: 39.15522693775711
episode: 60 training return: tensor(25.6355, device='cuda:0')
episode: 61 training return: tensor(-59.1547, device='cuda:0')
episode: 62 training return: tensor(-331.1581, device='cuda:0')
episode: 63 training return: tensor(-0.3220, device='cuda:0')
epoch: 16 test_true_pfm: 3164.495177699893 sim_pfm: 123.1659526353081
episode: 64 training return: tensor(-314.6052, device='cuda:0')
episode: 65 training return: tensor(-342.3156, device='cuda:0')
episode: 66 training return: tensor(-261.4595, device='cuda:0')
episode: 67 training return: tensor(-311.9890, device='cuda:0')
epoch: 17 test_true_pfm: 2818.7077314955372 sim_pfm: 184.86498634532714
episode: 68 training return: tensor(131.5900, device='cuda:0')
episode: 69 training return: tensor(222.5753, device='cuda:0')
episode: 70 training return: tensor(-274.6647, device='cuda:0')
episode: 71 training return: tensor(-80.3055, device='cuda:0')
epoch: 18 test_true_pfm: 2743.783425588927 sim_pfm: 129.6610989237282
episode: 72 training return: tensor(251.0709, device='cuda:0')
episode: 73 training return: tensor(-341.5450, device='cuda:0')
episode: 74 training return: tensor(-191.9114, device='cuda:0')
episode: 75 training return: tensor(-30.7632, device='cuda:0')
epoch: 19 test_true_pfm: 2908.5975587507887 sim_pfm: 170.55619230262042
episode: 76 training return: tensor(-343.9949, device='cuda:0')
episode: 77 training return: tensor(260.7368, device='cuda:0')
episode: 78 training return: tensor(-263.0825, device='cuda:0')
episode: 79 training return: tensor(-216.6552, device='cuda:0')
epoch: 20 test_true_pfm: 2783.4964518419997 sim_pfm: 60.190477972190514
episode: 80 training return: tensor(178.7330, device='cuda:0')
episode: 81 training return: tensor(-359.7702, device='cuda:0')
episode: 82 training return: tensor(-215.5151, device='cuda:0')
episode: 83 training return: tensor(-334.0282, device='cuda:0')
epoch: 21 test_true_pfm: 3087.094661053272 sim_pfm: 261.6624982027958
episode: 84 training return: tensor(-352.6034, device='cuda:0')
episode: 85 training return: tensor(-256.7817, device='cuda:0')
episode: 86 training return: tensor(318.6649, device='cuda:0')
episode: 87 training return: tensor(-72.7102, device='cuda:0')
epoch: 22 test_true_pfm: 2527.6951275250703 sim_pfm: 31.15343312380719
episode: 88 training return: tensor(-179.4808, device='cuda:0')
episode: 89 training return: tensor(-288.5881, device='cuda:0')
episode: 90 training return: tensor(-259.7262, device='cuda:0')
episode: 91 training return: tensor(-316.0146, device='cuda:0')
epoch: 23 test_true_pfm: 2763.3061151581533 sim_pfm: 155.57964041597248
episode: 92 training return: tensor(-352.1690, device='cuda:0')
episode: 93 training return: tensor(191.5700, device='cuda:0')
episode: 94 training return: tensor(-336.1388, device='cuda:0')
episode: 95 training return: tensor(-300.4215, device='cuda:0')
epoch: 24 test_true_pfm: 3230.314078083102 sim_pfm: 243.42051195458043
episode: 96 training return: tensor(-354.0009, device='cuda:0')
episode: 97 training return: tensor(-303.1237, device='cuda:0')
episode: 98 training return: tensor(-346.7328, device='cuda:0')
episode: 99 training return: tensor(-280.8389, device='cuda:0')
epoch: 25 test_true_pfm: 1929.590902916558 sim_pfm: -215.39488357390897
episode: 100 training return: tensor(-355.4372, device='cuda:0')
episode: 101 training return: tensor(-174.7863, device='cuda:0')
episode: 102 training return: tensor(-198.6159, device='cuda:0')
episode: 103 training return: tensor(0.3462, device='cuda:0')
epoch: 26 test_true_pfm: 2829.3595145066806 sim_pfm: 24.656093045816913
episode: 104 training return: tensor(-321.0070, device='cuda:0')
episode: 105 training return: tensor(-354.9175, device='cuda:0')
episode: 106 training return: tensor(-81.4314, device='cuda:0')
episode: 107 training return: tensor(-258.8369, device='cuda:0')
epoch: 27 test_true_pfm: 1531.996717446833 sim_pfm: -3.3717339085997082
episode: 108 training return: tensor(-88.5091, device='cuda:0')
episode: 109 training return: tensor(-38.9018, device='cuda:0')
episode: 110 training return: tensor(-296.4908, device='cuda:0')
episode: 111 training return: tensor(-322.3577, device='cuda:0')
epoch: 28 test_true_pfm: 1940.8498231339702 sim_pfm: -4.722849052108359
episode: 112 training return: tensor(-309.0155, device='cuda:0')
episode: 113 training return: tensor(-35.1407, device='cuda:0')
episode: 114 training return: tensor(243.2593, device='cuda:0')
episode: 115 training return: tensor(-337.4317, device='cuda:0')
epoch: 29 test_true_pfm: 3256.9899183956163 sim_pfm: 46.7501188965883
episode: 116 training return: tensor(-197.8984, device='cuda:0')
episode: 117 training return: tensor(-296.5978, device='cuda:0')
episode: 118 training return: tensor(-58.6297, device='cuda:0')
episode: 119 training return: tensor(-214.1273, device='cuda:0')
epoch: 30 test_true_pfm: 2821.117164919866 sim_pfm: 91.39330818046194
episode: 120 training return: tensor(-263.9749, device='cuda:0')
episode: 121 training return: tensor(-344.5035, device='cuda:0')
episode: 122 training return: tensor(-228.6561, device='cuda:0')
episode: 123 training return: tensor(-253.4920, device='cuda:0')
epoch: 31 test_true_pfm: 3146.2956084527336 sim_pfm: 133.48495597208967
episode: 124 training return: tensor(-324.0807, device='cuda:0')
episode: 125 training return: tensor(-276.1755, device='cuda:0')
episode: 126 training return: tensor(-348.5757, device='cuda:0')
episode: 127 training return: tensor(-352.6510, device='cuda:0')
epoch: 32 test_true_pfm: 2907.3014537131385 sim_pfm: 248.1106359187203
episode: 128 training return: tensor(64.9615, device='cuda:0')
episode: 129 training return: tensor(227.6480, device='cuda:0')
episode: 130 training return: tensor(-360.6172, device='cuda:0')
episode: 131 training return: tensor(248.4772, device='cuda:0')
epoch: 33 test_true_pfm: 3047.0676162746045 sim_pfm: 132.52782950105998
episode: 132 training return: tensor(-334.1953, device='cuda:0')
episode: 133 training return: tensor(-333.8237, device='cuda:0')
episode: 134 training return: tensor(166.1150, device='cuda:0')
episode: 135 training return: tensor(-342.0214, device='cuda:0')
epoch: 34 test_true_pfm: 2762.538187924262 sim_pfm: 138.06837592048882
episode: 136 training return: tensor(4.3740, device='cuda:0')
episode: 137 training return: tensor(113.4564, device='cuda:0')
episode: 138 training return: tensor(-9.8333, device='cuda:0')
episode: 139 training return: tensor(48.6294, device='cuda:0')
epoch: 35 test_true_pfm: 3231.952684454985 sim_pfm: 206.42477110264977
episode: 140 training return: tensor(-272.1816, device='cuda:0')
episode: 141 training return: tensor(-357.9953, device='cuda:0')
episode: 142 training return: tensor(-338.7849, device='cuda:0')
episode: 143 training return: tensor(-102.9341, device='cuda:0')
epoch: 36 test_true_pfm: 2996.180257439922 sim_pfm: 284.68886584060965
episode: 144 training return: tensor(-332.3749, device='cuda:0')
episode: 145 training return: tensor(-340.3592, device='cuda:0')
episode: 146 training return: tensor(-311.3842, device='cuda:0')
episode: 147 training return: tensor(-337.6487, device='cuda:0')
epoch: 37 test_true_pfm: 2692.5029999797193 sim_pfm: 191.41391686095935
episode: 148 training return: tensor(-336.4605, device='cuda:0')
episode: 149 training return: tensor(-283.8023, device='cuda:0')
episode: 150 training return: tensor(-172.9647, device='cuda:0')
episode: 151 training return: tensor(-358.1399, device='cuda:0')
epoch: 38 test_true_pfm: 3044.4748618549606 sim_pfm: 207.06569938288885
episode: 152 training return: tensor(-345.4906, device='cuda:0')
episode: 153 training return: tensor(-353.4499, device='cuda:0')
episode: 154 training return: tensor(-137.4158, device='cuda:0')
episode: 155 training return: tensor(-310.5271, device='cuda:0')
epoch: 39 test_true_pfm: 3087.2079017340297 sim_pfm: 189.3542188576345
episode: 156 training return: tensor(-108.4795, device='cuda:0')
episode: 157 training return: tensor(-118.0560, device='cuda:0')
episode: 158 training return: tensor(-284.6666, device='cuda:0')
episode: 159 training return: tensor(353.1921, device='cuda:0')
epoch: 40 test_true_pfm: 2280.912844775565 sim_pfm: -9.125599253146598
episode: 160 training return: tensor(269.2849, device='cuda:0')
episode: 161 training return: tensor(-262.3838, device='cuda:0')
episode: 162 training return: tensor(-355.1778, device='cuda:0')
episode: 163 training return: tensor(-269.2888, device='cuda:0')
epoch: 41 test_true_pfm: 2647.8180109388077 sim_pfm: 59.57832834375828
episode: 164 training return: tensor(-314.0409, device='cuda:0')
episode: 165 training return: tensor(-306.0421, device='cuda:0')
episode: 166 training return: tensor(-339.3094, device='cuda:0')
episode: 167 training return: tensor(-292.8608, device='cuda:0')
epoch: 42 test_true_pfm: 2126.007393881947 sim_pfm: 28.017423622649705
episode: 168 training return: tensor(-49.2705, device='cuda:0')
episode: 169 training return: tensor(-291.4001, device='cuda:0')
episode: 170 training return: tensor(156.8448, device='cuda:0')
episode: 171 training return: tensor(130.2940, device='cuda:0')
epoch: 43 test_true_pfm: 2847.951896081427 sim_pfm: 250.6017190962642
episode: 172 training return: tensor(-296.5785, device='cuda:0')
episode: 173 training return: tensor(-266.4004, device='cuda:0')
episode: 174 training return: tensor(-292.8235, device='cuda:0')
episode: 175 training return: tensor(-232.5123, device='cuda:0')
epoch: 44 test_true_pfm: 2368.3472149527115 sim_pfm: 254.73022430413403
episode: 176 training return: tensor(-61.2086, device='cuda:0')
episode: 177 training return: tensor(-341.2097, device='cuda:0')
episode: 178 training return: tensor(264.0952, device='cuda:0')
episode: 179 training return: tensor(-310.1870, device='cuda:0')
epoch: 45 test_true_pfm: 1628.1520776093419 sim_pfm: -241.8300095127585
episode: 180 training return: tensor(-297.0199, device='cuda:0')
episode: 181 training return: tensor(-288.7317, device='cuda:0')
episode: 182 training return: tensor(-302.0177, device='cuda:0')
episode: 183 training return: tensor(4.7211, device='cuda:0')
epoch: 46 test_true_pfm: 3122.2112755618637 sim_pfm: -36.259710186326025
episode: 184 training return: tensor(-187.3028, device='cuda:0')
episode: 185 training return: tensor(-327.4681, device='cuda:0')
episode: 186 training return: tensor(-221.9553, device='cuda:0')
episode: 187 training return: tensor(-297.9901, device='cuda:0')
epoch: 47 test_true_pfm: 3214.299861743661 sim_pfm: 251.5913941936645
episode: 188 training return: tensor(-313.8940, device='cuda:0')
episode: 189 training return: tensor(-290.9018, device='cuda:0')
episode: 190 training return: tensor(-269.6315, device='cuda:0')
episode: 191 training return: tensor(-283.6734, device='cuda:0')
epoch: 48 test_true_pfm: 3049.530177629216 sim_pfm: -75.89088237831795
episode: 192 training return: tensor(-213.2736, device='cuda:0')
episode: 193 training return: tensor(-269.0354, device='cuda:0')
episode: 194 training return: tensor(-346.1884, device='cuda:0')
episode: 195 training return: tensor(56.2788, device='cuda:0')
epoch: 49 test_true_pfm: 2764.4371410906756 sim_pfm: 190.9813541166465
episode: 196 training return: tensor(-345.5343, device='cuda:0')
episode: 197 training return: tensor(-353.9468, device='cuda:0')
episode: 198 training return: tensor(-339.8119, device='cuda:0')
episode: 199 training return: tensor(-265.2337, device='cuda:0')
epoch: 50 test_true_pfm: 2429.473047276264 sim_pfm: 144.7739112584386
episode: 200 training return: tensor(-189.9258, device='cuda:0')
episode: 201 training return: tensor(-264.8370, device='cuda:0')
episode: 202 training return: tensor(-354.8046, device='cuda:0')
episode: 203 training return: tensor(-325.6404, device='cuda:0')
epoch: 51 test_true_pfm: 2347.921283773722 sim_pfm: 131.94171765405918
episode: 204 training return: tensor(293.4584, device='cuda:0')
episode: 205 training return: tensor(-332.9022, device='cuda:0')
episode: 206 training return: tensor(-288.6386, device='cuda:0')
episode: 207 training return: tensor(-209.1286, device='cuda:0')
epoch: 52 test_true_pfm: 2380.8755453171384 sim_pfm: 38.3762847489755
episode: 208 training return: tensor(-340.8638, device='cuda:0')
episode: 209 training return: tensor(283.4494, device='cuda:0')
episode: 210 training return: tensor(-195.7956, device='cuda:0')
episode: 211 training return: tensor(-336.5008, device='cuda:0')
epoch: 53 test_true_pfm: 2597.870998094996 sim_pfm: 190.39973036006754
episode: 212 training return: tensor(-155.2878, device='cuda:0')
episode: 213 training return: tensor(-87.5115, device='cuda:0')
episode: 214 training return: tensor(251.8972, device='cuda:0')
episode: 215 training return: tensor(85.1506, device='cuda:0')
epoch: 54 test_true_pfm: 3078.2130793066885 sim_pfm: 28.527253277386382
episode: 216 training return: tensor(-343.3066, device='cuda:0')
episode: 217 training return: tensor(-299.2848, device='cuda:0')
episode: 218 training return: tensor(-303.4006, device='cuda:0')
episode: 219 training return: tensor(-283.1302, device='cuda:0')
epoch: 55 test_true_pfm: 3037.8297980639904 sim_pfm: 180.4831011312102
episode: 220 training return: tensor(-338.3889, device='cuda:0')
episode: 221 training return: tensor(-14.7929, device='cuda:0')
episode: 222 training return: tensor(-307.6882, device='cuda:0')
episode: 223 training return: tensor(-319.7484, device='cuda:0')
epoch: 56 test_true_pfm: 2479.2396029693623 sim_pfm: 141.4676162963345
episode: 224 training return: tensor(-345.7382, device='cuda:0')
episode: 225 training return: tensor(-316.3552, device='cuda:0')
episode: 226 training return: tensor(5.2536, device='cuda:0')
episode: 227 training return: tensor(-291.2502, device='cuda:0')
epoch: 57 test_true_pfm: 3281.267688999122 sim_pfm: 205.86424877630392
episode: 228 training return: tensor(-298.9111, device='cuda:0')
episode: 229 training return: tensor(-319.9773, device='cuda:0')
episode: 230 training return: tensor(-294.8131, device='cuda:0')
episode: 231 training return: tensor(-327.1111, device='cuda:0')
epoch: 58 test_true_pfm: 2820.1008190803564 sim_pfm: 239.39543207431174
episode: 232 training return: tensor(-356.9933, device='cuda:0')
episode: 233 training return: tensor(-304.4708, device='cuda:0')
episode: 234 training return: tensor(-210.7536, device='cuda:0')
episode: 235 training return: tensor(-287.4753, device='cuda:0')
epoch: 59 test_true_pfm: 2758.1631433731745 sim_pfm: 279.96754964531283
episode: 236 training return: tensor(-277.2882, device='cuda:0')
episode: 237 training return: tensor(-298.3578, device='cuda:0')
episode: 238 training return: tensor(-70.7822, device='cuda:0')
episode: 239 training return: tensor(-228.5400, device='cuda:0')
epoch: 60 test_true_pfm: 2129.9459442639327 sim_pfm: -37.8693843773508
episode: 240 training return: tensor(-349.7404, device='cuda:0')
episode: 241 training return: tensor(-326.8275, device='cuda:0')
episode: 242 training return: tensor(-100.2790, device='cuda:0')
episode: 243 training return: tensor(70.1442, device='cuda:0')
epoch: 61 test_true_pfm: 2132.48481588455 sim_pfm: -15.443066872830968
episode: 244 training return: tensor(-209.6504, device='cuda:0')
episode: 245 training return: tensor(-302.6141, device='cuda:0')
episode: 246 training return: tensor(-361.1117, device='cuda:0')
episode: 247 training return: tensor(-279.0222, device='cuda:0')
epoch: 62 test_true_pfm: 2639.849331417425 sim_pfm: 97.02175090434805
episode: 248 training return: tensor(-280.3688, device='cuda:0')
episode: 249 training return: tensor(-314.7365, device='cuda:0')
episode: 250 training return: tensor(-307.7612, device='cuda:0')
episode: 251 training return: tensor(-149.7860, device='cuda:0')
epoch: 63 test_true_pfm: 2577.738509469502 sim_pfm: 150.33640030321354
episode: 252 training return: tensor(-298.7480, device='cuda:0')
episode: 253 training return: tensor(-341.7515, device='cuda:0')
episode: 254 training return: tensor(-265.7065, device='cuda:0')
episode: 255 training return: tensor(-294.6156, device='cuda:0')
epoch: 64 test_true_pfm: 1411.7783939324506 sim_pfm: -48.1020277972954
episode: 256 training return: tensor(-298.3668, device='cuda:0')
episode: 257 training return: tensor(166.7651, device='cuda:0')
episode: 258 training return: tensor(-179.5339, device='cuda:0')
episode: 259 training return: tensor(-362.4889, device='cuda:0')
epoch: 65 test_true_pfm: 2605.725752495646 sim_pfm: 72.76045005277653
episode: 260 training return: tensor(344.1070, device='cuda:0')
episode: 261 training return: tensor(-261.6427, device='cuda:0')
episode: 262 training return: tensor(-184.0891, device='cuda:0')
episode: 263 training return: tensor(-284.4621, device='cuda:0')
epoch: 66 test_true_pfm: 1933.9902601154947 sim_pfm: -29.889692022659194
episode: 264 training return: tensor(-316.9813, device='cuda:0')
episode: 265 training return: tensor(-283.9209, device='cuda:0')
episode: 266 training return: tensor(-290.6822, device='cuda:0')
episode: 267 training return: tensor(-200.7812, device='cuda:0')
epoch: 67 test_true_pfm: 2402.6489762048227 sim_pfm: -80.24075861224749
episode: 268 training return: tensor(121.0357, device='cuda:0')
episode: 269 training return: tensor(0.5847, device='cuda:0')
episode: 270 training return: tensor(-313.5755, device='cuda:0')
episode: 271 training return: tensor(-314.3343, device='cuda:0')
epoch: 68 test_true_pfm: 2092.3352819379743 sim_pfm: 236.76650629058713
episode: 272 training return: tensor(-254.9870, device='cuda:0')
episode: 273 training return: tensor(-348.9819, device='cuda:0')
episode: 274 training return: tensor(-231.1066, device='cuda:0')
episode: 275 training return: tensor(-15.1173, device='cuda:0')
epoch: 69 test_true_pfm: 2246.263795301084 sim_pfm: 115.840230273403
episode: 276 training return: tensor(-335.5047, device='cuda:0')
episode: 277 training return: tensor(-203.5215, device='cuda:0')
episode: 278 training return: tensor(-93.3176, device='cuda:0')
episode: 279 training return: tensor(-354.8344, device='cuda:0')
epoch: 70 test_true_pfm: 3090.3331455192492 sim_pfm: 87.88911236021279
episode: 280 training return: tensor(-335.4777, device='cuda:0')
episode: 281 training return: tensor(-12.1612, device='cuda:0')
episode: 282 training return: tensor(-315.4550, device='cuda:0')
episode: 283 training return: tensor(-350.5841, device='cuda:0')
epoch: 71 test_true_pfm: 2591.8795725023106 sim_pfm: -11.119701879797503
episode: 284 training return: tensor(-345.0606, device='cuda:0')
episode: 285 training return: tensor(-351.4341, device='cuda:0')
episode: 286 training return: tensor(-278.9235, device='cuda:0')
episode: 287 training return: tensor(-360.3777, device='cuda:0')
epoch: 72 test_true_pfm: 2515.822588706901 sim_pfm: 183.05380197492195
episode: 288 training return: tensor(-348.6037, device='cuda:0')
episode: 289 training return: tensor(-305.3221, device='cuda:0')
episode: 290 training return: tensor(-320.1200, device='cuda:0')
episode: 291 training return: tensor(-359.0049, device='cuda:0')
epoch: 73 test_true_pfm: 2769.8146898859504 sim_pfm: -17.49269387545064
episode: 292 training return: tensor(-303.7925, device='cuda:0')
episode: 293 training return: tensor(-334.9200, device='cuda:0')
episode: 294 training return: tensor(-288.4958, device='cuda:0')
episode: 295 training return: tensor(-282.4360, device='cuda:0')
epoch: 74 test_true_pfm: 1505.8314802759778 sim_pfm: -106.31505635404028
episode: 296 training return: tensor(-344.5867, device='cuda:0')
episode: 297 training return: tensor(-101.0334, device='cuda:0')
episode: 298 training return: tensor(-124.6671, device='cuda:0')
episode: 299 training return: tensor(-363.5548, device='cuda:0')
epoch: 75 test_true_pfm: 3253.075512529694 sim_pfm: 265.8227796459396
episode: 300 training return: tensor(-310.8912, device='cuda:0')
episode: 301 training return: tensor(-310.6286, device='cuda:0')
episode: 302 training return: tensor(-355.1693, device='cuda:0')
episode: 303 training return: tensor(-343.1873, device='cuda:0')
epoch: 76 test_true_pfm: 2123.0830591977715 sim_pfm: 26.3062923521987
episode: 304 training return: tensor(-328.3010, device='cuda:0')
episode: 305 training return: tensor(-346.2238, device='cuda:0')
episode: 306 training return: tensor(-304.4453, device='cuda:0')
episode: 307 training return: tensor(172.0629, device='cuda:0')
epoch: 77 test_true_pfm: 2548.579952781456 sim_pfm: -9.084609379739655
episode: 308 training return: tensor(-298.0180, device='cuda:0')
episode: 309 training return: tensor(-38.7382, device='cuda:0')
episode: 310 training return: tensor(-356.5594, device='cuda:0')
episode: 311 training return: tensor(-353.2500, device='cuda:0')
epoch: 78 test_true_pfm: 2631.5545610424037 sim_pfm: 256.4052758044175
episode: 312 training return: tensor(-33.3367, device='cuda:0')
episode: 313 training return: tensor(270.2259, device='cuda:0')
episode: 314 training return: tensor(-348.1581, device='cuda:0')
episode: 315 training return: tensor(-360.7675, device='cuda:0')
epoch: 79 test_true_pfm: 2069.727909467953 sim_pfm: -93.9279646143453
episode: 316 training return: tensor(-312.3521, device='cuda:0')
episode: 317 training return: tensor(-297.1320, device='cuda:0')
episode: 318 training return: tensor(-176.2113, device='cuda:0')
episode: 319 training return: tensor(-307.2238, device='cuda:0')
epoch: 80 test_true_pfm: 1695.1760478794524 sim_pfm: -43.518180600047344
episode: 320 training return: tensor(-331.4373, device='cuda:0')
episode: 321 training return: tensor(-169.1846, device='cuda:0')
episode: 322 training return: tensor(-42.0682, device='cuda:0')
episode: 323 training return: tensor(-311.6590, device='cuda:0')
epoch: 81 test_true_pfm: 2364.2028200774425 sim_pfm: 155.14641765578804
episode: 324 training return: tensor(-352.4099, device='cuda:0')
episode: 325 training return: tensor(-258.2038, device='cuda:0')
episode: 326 training return: tensor(301.5811, device='cuda:0')
episode: 327 training return: tensor(-355.1765, device='cuda:0')
epoch: 82 test_true_pfm: 1570.925628055046 sim_pfm: -213.90801909868605
episode: 328 training return: tensor(-327.9383, device='cuda:0')
episode: 329 training return: tensor(-352.3167, device='cuda:0')
episode: 330 training return: tensor(-311.5125, device='cuda:0')
episode: 331 training return: tensor(-287.6195, device='cuda:0')
epoch: 83 test_true_pfm: 2408.3167867524044 sim_pfm: 62.313131476267394
episode: 332 training return: tensor(199.8559, device='cuda:0')
episode: 333 training return: tensor(-184.4530, device='cuda:0')
episode: 334 training return: tensor(-290.1151, device='cuda:0')
episode: 335 training return: tensor(-354.2239, device='cuda:0')
epoch: 84 test_true_pfm: 1976.684399880113 sim_pfm: -100.31055749271763
episode: 336 training return: tensor(-299.8977, device='cuda:0')
episode: 337 training return: tensor(313.1248, device='cuda:0')
episode: 338 training return: tensor(-278.6388, device='cuda:0')
episode: 339 training return: tensor(-285.8546, device='cuda:0')
epoch: 85 test_true_pfm: 2185.8597772833896 sim_pfm: -244.51174591605863
episode: 340 training return: tensor(-288.6566, device='cuda:0')
episode: 341 training return: tensor(-312.2728, device='cuda:0')
episode: 342 training return: tensor(-349.7725, device='cuda:0')
episode: 343 training return: tensor(-367.3167, device='cuda:0')
epoch: 86 test_true_pfm: 2199.388246520124 sim_pfm: 102.3773547624781
episode: 344 training return: tensor(-269.3963, device='cuda:0')
episode: 345 training return: tensor(-303.7653, device='cuda:0')
episode: 346 training return: tensor(-249.4147, device='cuda:0')
episode: 347 training return: tensor(-286.5197, device='cuda:0')
epoch: 87 test_true_pfm: 2074.7977962764057 sim_pfm: -162.13319879329842
episode: 348 training return: tensor(34.8305, device='cuda:0')
episode: 349 training return: tensor(-354.0283, device='cuda:0')
episode: 350 training return: tensor(-318.0724, device='cuda:0')
episode: 351 training return: tensor(-211.3012, device='cuda:0')
epoch: 88 test_true_pfm: 2565.9576899881795 sim_pfm: -71.31407114382212
episode: 352 training return: tensor(-295.8101, device='cuda:0')
episode: 353 training return: tensor(-234.5116, device='cuda:0')
episode: 354 training return: tensor(-41.7272, device='cuda:0')
episode: 355 training return: tensor(-329.3519, device='cuda:0')
epoch: 89 test_true_pfm: 2047.8267325279196 sim_pfm: 84.12387939348507
episode: 356 training return: tensor(-244.4903, device='cuda:0')
episode: 357 training return: tensor(-8.5387, device='cuda:0')
episode: 358 training return: tensor(-355.3683, device='cuda:0')
episode: 359 training return: tensor(20.0793, device='cuda:0')
epoch: 90 test_true_pfm: 2347.306755485457 sim_pfm: -66.21074219082948
episode: 360 training return: tensor(-330.6476, device='cuda:0')
episode: 361 training return: tensor(-106.6934, device='cuda:0')
episode: 362 training return: tensor(-346.9138, device='cuda:0')
episode: 363 training return: tensor(-293.9864, device='cuda:0')
epoch: 91 test_true_pfm: 2141.8632608295716 sim_pfm: -142.63949825882446
episode: 364 training return: tensor(-30.0723, device='cuda:0')
episode: 365 training return: tensor(-286.5336, device='cuda:0')
episode: 366 training return: tensor(-303.7135, device='cuda:0')
episode: 367 training return: tensor(-297.1131, device='cuda:0')
epoch: 92 test_true_pfm: 2763.1218343209234 sim_pfm: 49.664200948706515
episode: 368 training return: tensor(-247.5839, device='cuda:0')
episode: 369 training return: tensor(272.3353, device='cuda:0')
episode: 370 training return: tensor(-357.4521, device='cuda:0')
episode: 371 training return: tensor(-234.5816, device='cuda:0')
epoch: 93 test_true_pfm: 2117.0499937066943 sim_pfm: -94.44769030660002
episode: 372 training return: tensor(-298.4923, device='cuda:0')
episode: 373 training return: tensor(-166.3905, device='cuda:0')
episode: 374 training return: tensor(173.8825, device='cuda:0')
episode: 375 training return: tensor(-301.1657, device='cuda:0')
epoch: 94 test_true_pfm: 2170.253776456651 sim_pfm: -110.40072528186526
episode: 376 training return: tensor(-341.7527, device='cuda:0')
episode: 377 training return: tensor(-271.7731, device='cuda:0')
episode: 378 training return: tensor(119.8483, device='cuda:0')
episode: 379 training return: tensor(-283.0047, device='cuda:0')
epoch: 95 test_true_pfm: 2904.266454470416 sim_pfm: -134.96821552295782
episode: 380 training return: tensor(-304.6546, device='cuda:0')
episode: 381 training return: tensor(-274.7291, device='cuda:0')
episode: 382 training return: tensor(-307.5806, device='cuda:0')
episode: 383 training return: tensor(-321.2994, device='cuda:0')
epoch: 96 test_true_pfm: 2789.0648525417346 sim_pfm: 115.33166256835102
episode: 384 training return: tensor(-318.5989, device='cuda:0')
episode: 385 training return: tensor(-337.8192, device='cuda:0')
episode: 386 training return: tensor(-298.1458, device='cuda:0')
episode: 387 training return: tensor(-265.1857, device='cuda:0')
epoch: 97 test_true_pfm: 2809.3537270120396 sim_pfm: -105.94680763179592
episode: 388 training return: tensor(-296.7002, device='cuda:0')
episode: 389 training return: tensor(-329.9323, device='cuda:0')
episode: 390 training return: tensor(-295.2297, device='cuda:0')
episode: 391 training return: tensor(-340.7793, device='cuda:0')
epoch: 98 test_true_pfm: 1770.9242489302994 sim_pfm: -120.54881851912553
episode: 392 training return: tensor(-299.6702, device='cuda:0')
episode: 393 training return: tensor(-271.5521, device='cuda:0')
episode: 394 training return: tensor(-321.1011, device='cuda:0')
episode: 395 training return: tensor(-292.0469, device='cuda:0')
epoch: 99 test_true_pfm: 2274.852547799603 sim_pfm: 2.8329545812060437
episode: 396 training return: tensor(-286.9724, device='cuda:0')
episode: 397 training return: tensor(-36.2962, device='cuda:0')
episode: 398 training return: tensor(-337.8768, device='cuda:0')
episode: 399 training return: tensor(-300.7841, device='cuda:0')
epoch: 100 test_true_pfm: 2259.350470504502 sim_pfm: -84.35825924121309
episode: 400 training return: tensor(-316.1824, device='cuda:0')
episode: 401 training return: tensor(-283.7887, device='cuda:0')
episode: 402 training return: tensor(-354.5035, device='cuda:0')
episode: 403 training return: tensor(-279.7955, device='cuda:0')
epoch: 101 test_true_pfm: 2034.4090125548762 sim_pfm: 40.72207955736667
episode: 404 training return: tensor(-302.5175, device='cuda:0')
episode: 405 training return: tensor(-364.0928, device='cuda:0')
episode: 406 training return: tensor(-351.3975, device='cuda:0')
episode: 407 training return: tensor(-110.3593, device='cuda:0')
epoch: 102 test_true_pfm: 2439.5373488291057 sim_pfm: 109.77460217724244
episode: 408 training return: tensor(-345.1053, device='cuda:0')
episode: 409 training return: tensor(-287.9495, device='cuda:0')
episode: 410 training return: tensor(-340.1537, device='cuda:0')
episode: 411 training return: tensor(-342.7040, device='cuda:0')
epoch: 103 test_true_pfm: 2372.026173473633 sim_pfm: 38.053519557317486
episode: 412 training return: tensor(-357.1975, device='cuda:0')
episode: 413 training return: tensor(-87.3731, device='cuda:0')
episode: 414 training return: tensor(138.3678, device='cuda:0')
episode: 415 training return: tensor(-302.3030, device='cuda:0')
epoch: 104 test_true_pfm: 2662.9330177899787 sim_pfm: 0.4447233408379058
episode: 416 training return: tensor(-311.9044, device='cuda:0')
episode: 417 training return: tensor(265.8499, device='cuda:0')
episode: 418 training return: tensor(-221.0499, device='cuda:0')
episode: 419 training return: tensor(-302.6188, device='cuda:0')
epoch: 105 test_true_pfm: 2898.4355490451403 sim_pfm: 276.93623449638835
episode: 420 training return: tensor(-360.3558, device='cuda:0')
episode: 421 training return: tensor(-99.0365, device='cuda:0')
episode: 422 training return: tensor(-334.7626, device='cuda:0')
episode: 423 training return: tensor(-309.9980, device='cuda:0')
epoch: 106 test_true_pfm: 2429.932507939289 sim_pfm: -136.97520145294644
episode: 424 training return: tensor(-298.1829, device='cuda:0')
episode: 425 training return: tensor(-257.6916, device='cuda:0')
episode: 426 training return: tensor(-343.2383, device='cuda:0')
episode: 427 training return: tensor(-212.6503, device='cuda:0')
epoch: 107 test_true_pfm: 2085.151929945172 sim_pfm: 22.90083827553705
episode: 428 training return: tensor(167.0878, device='cuda:0')
episode: 429 training return: tensor(-320.1386, device='cuda:0')
episode: 430 training return: tensor(-296.1613, device='cuda:0')
episode: 431 training return: tensor(-92.5414, device='cuda:0')
epoch: 108 test_true_pfm: 2001.5291952282541 sim_pfm: -90.78153975515549
episode: 432 training return: tensor(-356.6964, device='cuda:0')
episode: 433 training return: tensor(-349.1574, device='cuda:0')
episode: 434 training return: tensor(-185.2507, device='cuda:0')
episode: 435 training return: tensor(-273.1949, device='cuda:0')
epoch: 109 test_true_pfm: 1900.0946790000605 sim_pfm: -56.90676672013554
episode: 436 training return: tensor(-284.3877, device='cuda:0')
episode: 437 training return: tensor(-301.6699, device='cuda:0')
episode: 438 training return: tensor(-261.6215, device='cuda:0')
episode: 439 training return: tensor(-332.0497, device='cuda:0')
epoch: 110 test_true_pfm: 2821.05961363454 sim_pfm: 159.24446214939235
episode: 440 training return: tensor(-4.3833, device='cuda:0')
episode: 441 training return: tensor(-324.7689, device='cuda:0')
episode: 442 training return: tensor(-267.8192, device='cuda:0')
episode: 443 training return: tensor(-314.6408, device='cuda:0')
epoch: 111 test_true_pfm: 2268.8681385060177 sim_pfm: -85.64738523211174
episode: 444 training return: tensor(-28.8213, device='cuda:0')
episode: 445 training return: tensor(-347.9781, device='cuda:0')
episode: 446 training return: tensor(-198.4976, device='cuda:0')
episode: 447 training return: tensor(-293.2146, device='cuda:0')
epoch: 112 test_true_pfm: 2723.978732743399 sim_pfm: 3.380361620336771
episode: 448 training return: tensor(-184.7298, device='cuda:0')
episode: 449 training return: tensor(-61.3296, device='cuda:0')
episode: 450 training return: tensor(-360.6853, device='cuda:0')
episode: 451 training return: tensor(-234.4444, device='cuda:0')
epoch: 113 test_true_pfm: 2024.3795340251697 sim_pfm: -140.63816344126826
episode: 452 training return: tensor(-302.4062, device='cuda:0')
episode: 453 training return: tensor(-326.7525, device='cuda:0')
episode: 454 training return: tensor(-197.7388, device='cuda:0')
episode: 455 training return: tensor(-289.8876, device='cuda:0')
epoch: 114 test_true_pfm: 1576.0966006115268 sim_pfm: -229.5786572629586
episode: 456 training return: tensor(-352.0300, device='cuda:0')
episode: 457 training return: tensor(-337.0424, device='cuda:0')
episode: 458 training return: tensor(77.0797, device='cuda:0')
episode: 459 training return: tensor(-71.2825, device='cuda:0')
epoch: 115 test_true_pfm: 2927.759107112452 sim_pfm: -35.0909699012797
episode: 460 training return: tensor(-47.5389, device='cuda:0')
episode: 461 training return: tensor(-260.2253, device='cuda:0')
episode: 462 training return: tensor(-72.2572, device='cuda:0')
episode: 463 training return: tensor(-347.3720, device='cuda:0')
epoch: 116 test_true_pfm: 2747.8530991697517 sim_pfm: 141.27206343398817
episode: 464 training return: tensor(-358.9212, device='cuda:0')
episode: 465 training return: tensor(-329.2286, device='cuda:0')
episode: 466 training return: tensor(-287.2181, device='cuda:0')
episode: 467 training return: tensor(-358.1993, device='cuda:0')
epoch: 117 test_true_pfm: 1979.8087459067974 sim_pfm: 97.33530172732814
episode: 468 training return: tensor(-336.1014, device='cuda:0')
episode: 469 training return: tensor(78.8110, device='cuda:0')
episode: 470 training return: tensor(-63.8663, device='cuda:0')
episode: 471 training return: tensor(-293.8630, device='cuda:0')
epoch: 118 test_true_pfm: 1862.3454566522407 sim_pfm: -110.13116534669341
episode: 472 training return: tensor(-289.6629, device='cuda:0')
episode: 473 training return: tensor(-334.4469, device='cuda:0')
episode: 474 training return: tensor(-294.2796, device='cuda:0')
episode: 475 training return: tensor(-313.0642, device='cuda:0')
epoch: 119 test_true_pfm: 2604.5969825615375 sim_pfm: 265.781981820066
episode: 476 training return: tensor(-242.6889, device='cuda:0')
episode: 477 training return: tensor(-347.5542, device='cuda:0')
episode: 478 training return: tensor(-313.5211, device='cuda:0')
episode: 479 training return: tensor(93.8636, device='cuda:0')
epoch: 120 test_true_pfm: 2564.338511924625 sim_pfm: 163.4657540419333
episode: 480 training return: tensor(-288.9314, device='cuda:0')
episode: 481 training return: tensor(-337.7637, device='cuda:0')
episode: 482 training return: tensor(-356.8950, device='cuda:0')
episode: 483 training return: tensor(-211.5819, device='cuda:0')
epoch: 121 test_true_pfm: 1559.8900757996055 sim_pfm: -185.92015197100895
episode: 484 training return: tensor(-297.7557, device='cuda:0')
episode: 485 training return: tensor(-9.6586, device='cuda:0')
episode: 486 training return: tensor(-286.8509, device='cuda:0')
episode: 487 training return: tensor(-351.5852, device='cuda:0')
epoch: 122 test_true_pfm: 2521.806649676128 sim_pfm: 22.76835089859863
episode: 488 training return: tensor(-300.7078, device='cuda:0')
episode: 489 training return: tensor(-305.0699, device='cuda:0')
episode: 490 training return: tensor(-342.1855, device='cuda:0')
episode: 491 training return: tensor(-318.5544, device='cuda:0')
epoch: 123 test_true_pfm: 1742.5137447155212 sim_pfm: -79.81951539129174
episode: 492 training return: tensor(-351.8682, device='cuda:0')
episode: 493 training return: tensor(-319.1768, device='cuda:0')
episode: 494 training return: tensor(-176.9461, device='cuda:0')
episode: 495 training return: tensor(-314.5301, device='cuda:0')
epoch: 124 test_true_pfm: 2908.1589459006823 sim_pfm: -108.45058165956289
episode: 496 training return: tensor(215.1002, device='cuda:0')
episode: 497 training return: tensor(-357.7037, device='cuda:0')
episode: 498 training return: tensor(-350.7997, device='cuda:0')
episode: 499 training return: tensor(-177.9409, device='cuda:0')
epoch: 125 test_true_pfm: 2829.335109973387 sim_pfm: 181.97244401332378
episode: 500 training return: tensor(-357.9055, device='cuda:0')
episode: 501 training return: tensor(-282.6138, device='cuda:0')
episode: 502 training return: tensor(-282.7412, device='cuda:0')
episode: 503 training return: tensor(-300.1946, device='cuda:0')
epoch: 126 test_true_pfm: 1451.5336876346016 sim_pfm: -191.2206573965765
episode: 504 training return: tensor(-340.4389, device='cuda:0')
episode: 505 training return: tensor(-341.4996, device='cuda:0')
episode: 506 training return: tensor(-247.6195, device='cuda:0')
episode: 507 training return: tensor(-305.3214, device='cuda:0')
epoch: 127 test_true_pfm: 1584.1008713216422 sim_pfm: 101.68236917838415
episode: 508 training return: tensor(-175.5764, device='cuda:0')
episode: 509 training return: tensor(-334.3767, device='cuda:0')
episode: 510 training return: tensor(-323.2182, device='cuda:0')
episode: 511 training return: tensor(-267.5940, device='cuda:0')
epoch: 128 test_true_pfm: 2463.745672917455 sim_pfm: -95.21511326258769
episode: 512 training return: tensor(-337.8925, device='cuda:0')
episode: 513 training return: tensor(-352.5498, device='cuda:0')
episode: 514 training return: tensor(-262.4012, device='cuda:0')
episode: 515 training return: tensor(-281.3699, device='cuda:0')
epoch: 129 test_true_pfm: 1926.6641552876524 sim_pfm: -97.74707018646102
episode: 516 training return: tensor(-364.2116, device='cuda:0')
episode: 517 training return: tensor(-226.0122, device='cuda:0')
episode: 518 training return: tensor(-120.3344, device='cuda:0')
episode: 519 training return: tensor(-285.9614, device='cuda:0')
epoch: 130 test_true_pfm: 2354.643858887756 sim_pfm: 114.00893939410646
episode: 520 training return: tensor(-360.0352, device='cuda:0')
episode: 521 training return: tensor(-353.2228, device='cuda:0')
episode: 522 training return: tensor(-292.5506, device='cuda:0')
episode: 523 training return: tensor(-345.5226, device='cuda:0')
epoch: 131 test_true_pfm: 1670.8779366904007 sim_pfm: -221.82611196932461
episode: 524 training return: tensor(-214.8349, device='cuda:0')
episode: 525 training return: tensor(-186.7878, device='cuda:0')
episode: 526 training return: tensor(-93.6074, device='cuda:0')
episode: 527 training return: tensor(-293.8160, device='cuda:0')
epoch: 132 test_true_pfm: 1563.4503515698536 sim_pfm: -119.72800398635445
episode: 528 training return: tensor(-275.3105, device='cuda:0')
episode: 529 training return: tensor(-119.9177, device='cuda:0')
episode: 530 training return: tensor(314.1985, device='cuda:0')
episode: 531 training return: tensor(-193.2608, device='cuda:0')
epoch: 133 test_true_pfm: 2497.9896946954664 sim_pfm: 13.313572602889812
episode: 532 training return: tensor(-214.1514, device='cuda:0')
episode: 533 training return: tensor(-16.1706, device='cuda:0')
episode: 534 training return: tensor(-356.3051, device='cuda:0')
episode: 535 training return: tensor(-115.9312, device='cuda:0')
epoch: 134 test_true_pfm: 1983.5790843929342 sim_pfm: -52.02449888875708
episode: 536 training return: tensor(-294.3527, device='cuda:0')
episode: 537 training return: tensor(-283.9698, device='cuda:0')
episode: 538 training return: tensor(-266.3462, device='cuda:0')
episode: 539 training return: tensor(-349.8282, device='cuda:0')
epoch: 135 test_true_pfm: 1913.1527710094663 sim_pfm: -24.625652074736234
episode: 540 training return: tensor(-272.1374, device='cuda:0')
episode: 541 training return: tensor(-358.8103, device='cuda:0')
episode: 542 training return: tensor(-347.0413, device='cuda:0')
episode: 543 training return: tensor(-357.1370, device='cuda:0')
epoch: 136 test_true_pfm: 1757.5451402241786 sim_pfm: -202.73108258888047
episode: 544 training return: tensor(-290.6982, device='cuda:0')
episode: 545 training return: tensor(-357.0764, device='cuda:0')
episode: 546 training return: tensor(67.0018, device='cuda:0')
episode: 547 training return: tensor(-354.0947, device='cuda:0')
epoch: 137 test_true_pfm: 2083.533366019905 sim_pfm: 7.9109510748336715
episode: 548 training return: tensor(275.5067, device='cuda:0')
episode: 549 training return: tensor(-284.8772, device='cuda:0')
episode: 550 training return: tensor(-308.4315, device='cuda:0')
episode: 551 training return: tensor(-296.9740, device='cuda:0')
epoch: 138 test_true_pfm: 3027.0845933767637 sim_pfm: 208.97243665307178
episode: 552 training return: tensor(-196.0088, device='cuda:0')
episode: 553 training return: tensor(339.0898, device='cuda:0')
episode: 554 training return: tensor(-243.4454, device='cuda:0')
episode: 555 training return: tensor(-369.1530, device='cuda:0')
epoch: 139 test_true_pfm: 2201.9154160827966 sim_pfm: 172.16841210155204
episode: 556 training return: tensor(-358.2931, device='cuda:0')
episode: 557 training return: tensor(-287.1410, device='cuda:0')
episode: 558 training return: tensor(-44.9697, device='cuda:0')
episode: 559 training return: tensor(-307.7999, device='cuda:0')
epoch: 140 test_true_pfm: 2514.6074260079668 sim_pfm: -143.29952644267664
episode: 560 training return: tensor(-352.7921, device='cuda:0')
episode: 561 training return: tensor(-260.7628, device='cuda:0')
episode: 562 training return: tensor(-309.8487, device='cuda:0')
episode: 563 training return: tensor(-305.6524, device='cuda:0')
epoch: 141 test_true_pfm: 2064.052781234507 sim_pfm: -38.588447970493384
episode: 564 training return: tensor(58.8348, device='cuda:0')
episode: 565 training return: tensor(19.5972, device='cuda:0')
episode: 566 training return: tensor(-247.7396, device='cuda:0')
episode: 567 training return: tensor(-261.7076, device='cuda:0')
epoch: 142 test_true_pfm: 2675.6275676748646 sim_pfm: -52.12344529305119
episode: 568 training return: tensor(-311.6126, device='cuda:0')
episode: 569 training return: tensor(-354.4976, device='cuda:0')
episode: 570 training return: tensor(285.5115, device='cuda:0')
episode: 571 training return: tensor(-327.6945, device='cuda:0')
epoch: 143 test_true_pfm: 2020.64883836032 sim_pfm: 39.512351632448066
episode: 572 training return: tensor(-345.1297, device='cuda:0')
episode: 573 training return: tensor(-284.4219, device='cuda:0')
episode: 574 training return: tensor(-214.3434, device='cuda:0')
episode: 575 training return: tensor(-215.2036, device='cuda:0')
epoch: 144 test_true_pfm: 1899.0038045862614 sim_pfm: -23.822409126568044
episode: 576 training return: tensor(-359.7855, device='cuda:0')
episode: 577 training return: tensor(-269.6288, device='cuda:0')
episode: 578 training return: tensor(-261.7769, device='cuda:0')
episode: 579 training return: tensor(-339.1568, device='cuda:0')
epoch: 145 test_true_pfm: 2560.846793745106 sim_pfm: 15.491020088394484
episode: 580 training return: tensor(-348.9877, device='cuda:0')
episode: 581 training return: tensor(-336.6980, device='cuda:0')
episode: 582 training return: tensor(-321.7430, device='cuda:0')
episode: 583 training return: tensor(-334.3792, device='cuda:0')
epoch: 146 test_true_pfm: 2445.2526421107173 sim_pfm: 130.4677560462927
episode: 584 training return: tensor(-268.6885, device='cuda:0')
episode: 585 training return: tensor(-212.2853, device='cuda:0')
episode: 586 training return: tensor(263.3877, device='cuda:0')
episode: 587 training return: tensor(-355.2361, device='cuda:0')
epoch: 147 test_true_pfm: 2838.5048320065034 sim_pfm: -11.453918856413415
episode: 588 training return: tensor(-364.2165, device='cuda:0')
episode: 589 training return: tensor(-286.1509, device='cuda:0')
episode: 590 training return: tensor(-308.6140, device='cuda:0')
episode: 591 training return: tensor(-272.6104, device='cuda:0')
epoch: 148 test_true_pfm: 2575.1037132114593 sim_pfm: 140.44958342165532
episode: 592 training return: tensor(-342.1805, device='cuda:0')
episode: 593 training return: tensor(-345.6807, device='cuda:0')
episode: 594 training return: tensor(-340.3703, device='cuda:0')
episode: 595 training return: tensor(-334.0545, device='cuda:0')
epoch: 149 test_true_pfm: 2007.9980645642925 sim_pfm: -143.70223460082585
episode: 596 training return: tensor(-325.3263, device='cuda:0')
episode: 597 training return: tensor(-44.9641, device='cuda:0')
episode: 598 training return: tensor(-200.1085, device='cuda:0')
episode: 599 training return: tensor(-290.6252, device='cuda:0')
epoch: 150 test_true_pfm: 1976.2322435969957 sim_pfm: -108.28772388235666
