['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'expert', '--seed', '1']
epoch: 0 training_loss 0.2481057007610798 test_loss: 0.17941383123397828
epoch: 1 training_loss 0.1789682600647211 test_loss: 0.16350157260894777
epoch: 2 training_loss 0.16423924550414085 test_loss: 0.14622453451156617
epoch: 3 training_loss 0.16381739988923072 test_loss: 0.16836705207824706
epoch: 4 training_loss 0.16934665389358997 test_loss: 0.16083276271820068
epoch: 5 training_loss 0.15619068693369628 test_loss: 0.15028011798858643
epoch: 6 training_loss 0.1498888450860977 test_loss: 0.1415291428565979
epoch: 7 training_loss 0.15617048099637032 test_loss: 0.12920769453048705
epoch: 8 training_loss 0.15484758369624615 test_loss: 0.1379644513130188
epoch: 9 training_loss 0.15276695732027293 test_loss: 0.14384629726409912
epoch: 10 training_loss 0.15142020631581546 test_loss: 0.1517349123954773
epoch: 11 training_loss 0.1551262888684869 test_loss: 0.14277302026748656
epoch: 12 training_loss 0.14939632639288902 test_loss: 0.13431886434555054
epoch: 13 training_loss 0.14661107487976552 test_loss: 0.1355236291885376
epoch: 14 training_loss 0.1421656246110797 test_loss: 0.12158455848693847
epoch: 15 training_loss 0.15220527932047845 test_loss: 0.1431310772895813
epoch: 16 training_loss 0.14304535739123822 test_loss: 0.14197124242782594
epoch: 17 training_loss 0.14429355405271052 test_loss: 0.14066494703292848
epoch: 18 training_loss 0.13864276833832265 test_loss: 0.1251120686531067
epoch: 19 training_loss 0.14426366429775953 test_loss: 0.1437086582183838
epoch: 20 training_loss 0.14450723581016064 test_loss: 0.12486411333084106
epoch: 21 training_loss 0.13553905829787255 test_loss: 0.16417876482009888
epoch: 22 training_loss 0.14008832387626172 test_loss: 0.14122960567474366
epoch: 23 training_loss 0.1438028497248888 test_loss: 0.13372987508773804
epoch: 24 training_loss 0.1451334086805582 test_loss: 0.16075767278671266
epoch: 25 training_loss 0.14371890790760516 test_loss: 0.13118547201156616
epoch: 26 training_loss 0.14138165835291147 test_loss: 0.12795096635818481
epoch: 27 training_loss 0.13923635374754667 test_loss: 0.12527655363082885
epoch: 28 training_loss 0.1423578502982855 test_loss: 0.13375637531280518
epoch: 29 training_loss 0.14094061721116305 test_loss: 0.14494313001632692
epoch: 30 training_loss 0.14149243630468844 test_loss: 0.16405504941940308
epoch: 31 training_loss 0.13071275845170022 test_loss: 0.14909145832061768
epoch: 32 training_loss 0.14247099045664072 test_loss: 0.1426721215248108
epoch: 33 training_loss 0.14731300130486488 test_loss: 0.14025684595108032
epoch: 34 training_loss 0.1347424155473709 test_loss: 0.1227272629737854
epoch: 35 training_loss 0.1361794950067997 test_loss: 0.14788663387298584
epoch: 36 training_loss 0.1427804410085082 test_loss: 0.1420813798904419
epoch: 37 training_loss 0.1285662869736552 test_loss: 0.132115375995636
epoch: 38 training_loss 0.1375885296985507 test_loss: 0.1297925591468811
epoch: 39 training_loss 0.13215784054249524 test_loss: 0.13781609535217285
epoch: 40 training_loss 0.14710547011345626 test_loss: 0.13432990312576293
epoch: 41 training_loss 0.13465382009744645 test_loss: 0.14652161598205565
epoch: 42 training_loss 0.13606743566691876 test_loss: 0.1354600191116333
epoch: 43 training_loss 0.13570751693099736 test_loss: 0.12126864194869995
epoch: 44 training_loss 0.13671615581959487 test_loss: 0.13962031602859498
epoch: 45 training_loss 0.13597625464200974 test_loss: 0.12650009393692016
epoch: 46 training_loss 0.13191088750958443 test_loss: 0.139745032787323
epoch: 47 training_loss 0.143341667316854 test_loss: 0.12994384765625
epoch: 48 training_loss 0.12930981371551753 test_loss: 0.13727011680603027
epoch: 49 training_loss 0.13932466816157102 test_loss: 0.15459396839141845
epoch: 50 training_loss 0.14152703650295734 test_loss: 0.12910287380218505
epoch: 51 training_loss 0.13905976414680482 test_loss: 0.13994603157043456
epoch: 52 training_loss 0.14548174154013396 test_loss: 0.1434424877166748
epoch: 53 training_loss 0.14099874138832091 test_loss: 0.15251072645187377
epoch: 54 training_loss 0.13926547426730396 test_loss: 0.12692168951034546
epoch: 55 training_loss 0.13853338982909918 test_loss: 0.11828548908233642
epoch: 56 training_loss 0.1319961591809988 test_loss: 0.14011038541793824
epoch: 57 training_loss 0.13643103905022144 test_loss: 0.15013209581375123
epoch: 58 training_loss 0.1362109585851431 test_loss: 0.14267410039901735
epoch: 59 training_loss 0.13681659162044524 test_loss: 0.1351765751838684
epoch: 60 training_loss 0.12411209627985954 test_loss: 0.11868672370910645
epoch: 61 training_loss 0.13063651956617833 test_loss: 0.1435503125190735
epoch: 62 training_loss 0.13891784712672234 test_loss: 0.14147084951400757
epoch: 63 training_loss 0.13766813587397336 test_loss: 0.14373000860214233
epoch: 64 training_loss 0.14616632219403983 test_loss: 0.12548696994781494
epoch: 65 training_loss 0.12372810401022434 test_loss: 0.13609715700149536
epoch: 66 training_loss 0.13063712056726218 test_loss: 0.14023976325988768
epoch: 67 training_loss 0.13380985841155052 test_loss: 0.14925533533096313
epoch: 68 training_loss 0.13643835306167604 test_loss: 0.11411471366882324
epoch: 69 training_loss 0.14078320637345315 test_loss: 0.1275347113609314
epoch: 70 training_loss 0.13652459517121315 test_loss: 0.13643248081207277
epoch: 71 training_loss 0.14315165370702743 test_loss: 0.1385461688041687
epoch: 72 training_loss 0.13152563277631998 test_loss: 0.11464383602142333
epoch: 73 training_loss 0.13592703089118005 test_loss: 0.13094738721847535
epoch: 74 training_loss 0.13382087145000696 test_loss: 0.12562851905822753
epoch: 75 training_loss 0.13782640125602483 test_loss: 0.13223479986190795
epoch: 76 training_loss 0.13471905123442413 test_loss: 0.15162783861160278
epoch: 77 training_loss 0.13193857602775097 test_loss: 0.13162131309509278
epoch: 78 training_loss 0.13314957346767187 test_loss: 0.13646790981292725
epoch: 79 training_loss 0.13829192623496056 test_loss: 0.14173699617385865
epoch: 80 training_loss 0.12916451398283244 test_loss: 0.1395272731781006
epoch: 81 training_loss 0.1409585713595152 test_loss: 0.12373884916305541
epoch: 82 training_loss 0.1394546890258789 test_loss: 0.1447329640388489
epoch: 83 training_loss 0.14212110210210085 test_loss: 0.11972395181655884
epoch: 84 training_loss 0.13975596852600575 test_loss: 0.11540403366088867
epoch: 85 training_loss 0.123329017162323 test_loss: 0.13042120933532714
epoch: 86 training_loss 0.12786374028772116 test_loss: 0.1199565052986145
epoch: 87 training_loss 0.13055803157389165 test_loss: 0.12173714637756347
epoch: 88 training_loss 0.13700691118836403 test_loss: 0.13847506046295166
epoch: 89 training_loss 0.1406625084206462 test_loss: 0.1520483136177063
epoch: 90 training_loss 0.1403278323635459 test_loss: 0.13768477439880372
epoch: 91 training_loss 0.1366125373914838 test_loss: 0.1293887972831726
epoch: 92 training_loss 0.1410225884988904 test_loss: 0.12590070962905883
epoch: 93 training_loss 0.13274648547172546 test_loss: 0.14905298948287965
epoch: 94 training_loss 0.14451852444559335 test_loss: 0.1294475317001343
epoch: 95 training_loss 0.13755953408777713 test_loss: 0.13195040225982665
epoch: 96 training_loss 0.13434083644300698 test_loss: 0.10432188510894776
epoch: 97 training_loss 0.1373519254848361 test_loss: 0.1365002155303955
epoch: 98 training_loss 0.13344088681042193 test_loss: 0.14544984102249145
epoch: 99 training_loss 0.130702133923769 test_loss: 0.13678909540176393
epoch: 100 training_loss 0.1459439294412732 test_loss: 0.1270824193954468
epoch: 101 training_loss 0.13489312410354615 test_loss: 0.1291830062866211
epoch: 102 training_loss 0.13766903039067985 test_loss: 0.14046250581741332
epoch: 103 training_loss 0.1337046530097723 test_loss: 0.1491425156593323
epoch: 104 training_loss 0.13186626754701136 test_loss: 0.13932870626449584
epoch: 105 training_loss 0.14057000465691089 test_loss: 0.14530746936798095
epoch: 106 training_loss 0.13500508148223161 test_loss: 0.11818650960922242
epoch: 107 training_loss 0.1259733309969306 test_loss: 0.1303501844406128
epoch: 108 training_loss 0.13143190424889326 test_loss: 0.12310140132904053
epoch: 109 training_loss 0.14550990127027036 test_loss: 0.13277722597122193
epoch: 110 training_loss 0.13030508767813445 test_loss: 0.13260012865066528
epoch: 111 training_loss 0.13063442368060352 test_loss: 0.13719187974929808
epoch: 112 training_loss 0.13283814035356045 test_loss: 0.13263720273971558
epoch: 113 training_loss 0.13811748959124087 test_loss: 0.13338030576705934
epoch: 114 training_loss 0.13874430570751428 test_loss: 0.13577628135681152
epoch: 115 training_loss 0.13666007027029992 test_loss: 0.1273168921470642
epoch: 116 training_loss 0.12932616107165815 test_loss: 0.13497209548950195
epoch: 117 training_loss 0.12700651921331882 test_loss: 0.10996437072753906
epoch: 118 training_loss 0.13515147246420384 test_loss: 0.1235434889793396
epoch: 119 training_loss 0.13735222861170768 test_loss: 0.11491405963897705
epoch: 120 training_loss 0.13357564963400365 test_loss: 0.13752952814102173
epoch: 121 training_loss 0.1362763861939311 test_loss: 0.1305161952972412
epoch: 122 training_loss 0.13086539976298808 test_loss: 0.1317822217941284
epoch: 123 training_loss 0.1356797121465206 test_loss: 0.1337694764137268
epoch: 124 training_loss 0.1382103367894888 test_loss: 0.13735228776931763
epoch: 125 training_loss 0.14193488892167808 test_loss: 0.13145310878753663
epoch: 126 training_loss 0.14018464513123036 test_loss: 0.13961215019226075
epoch: 127 training_loss 0.1250484996289015 test_loss: 0.14873675107955933
epoch: 128 training_loss 0.13262972336262466 test_loss: 0.13787444829940795
epoch: 129 training_loss 0.1324209701269865 test_loss: 0.11868337392807007
epoch: 130 training_loss 0.14054865848273038 test_loss: 0.134892737865448
epoch: 131 training_loss 0.13713401474058629 test_loss: 0.13640899658203126
epoch: 132 training_loss 0.1386236907169223 test_loss: 0.1416133999824524
epoch: 133 training_loss 0.13798159297555684 test_loss: 0.13843027353286744
epoch: 134 training_loss 0.13808799078688025 test_loss: 0.132272469997406
epoch: 135 training_loss 0.1374697581678629 test_loss: 0.14070849418640136
epoch: 136 training_loss 0.13718307174742222 test_loss: 0.130830979347229
epoch: 137 training_loss 0.13486729580909013 test_loss: 0.11415891647338867
epoch: 138 training_loss 0.13735069561749697 test_loss: 0.1288846969604492
epoch: 139 training_loss 0.1325192329660058 test_loss: 0.13364096879959106
epoch: 140 training_loss 0.13566073048859834 test_loss: 0.13345309495925903
epoch: 141 training_loss 0.12988644424825907 test_loss: 0.1319209098815918
epoch: 142 training_loss 0.1395051595941186 test_loss: 0.14024513959884644
epoch: 143 training_loss 0.13078635232523084 test_loss: 0.1470641851425171
epoch: 144 training_loss 0.13138253644108772 test_loss: 0.12552146911621093
epoch: 145 training_loss 0.13205455001443625 test_loss: 0.11967146396636963
epoch: 146 training_loss 0.13079013889655472 test_loss: 0.14330947399139404
epoch: 147 training_loss 0.135403077788651 test_loss: 0.12078007459640502
epoch: 148 training_loss 0.13998994894325734 test_loss: 0.11549556255340576
epoch: 149 training_loss 0.13852667715400457 test_loss: 0.12790721654891968
epoch: 0 training_loss 7.852896614074707 test_loss: 4.732240295410156
epoch: 1 training_loss 3.665716676712036 test_loss: 2.801395606994629
epoch: 2 training_loss 2.387487196922302 test_loss: 2.0150447845458985
epoch: 3 training_loss 1.8039749228954316 test_loss: 1.6471391677856446
epoch: 4 training_loss 1.5140585684776307 test_loss: 1.3940150260925293
epoch: 5 training_loss 1.2805431723594665 test_loss: 1.2359610557556153
epoch: 6 training_loss 1.2032178616523743 test_loss: 1.189132022857666
epoch: 7 training_loss 1.0830302131175995 test_loss: 1.0681743621826172
epoch: 8 training_loss 1.0190838342905044 test_loss: 1.0360329627990723
epoch: 9 training_loss 0.9585788154602051 test_loss: 0.9684663772583008
epoch: 10 training_loss 0.9515328103303909 test_loss: 0.8858595848083496
epoch: 11 training_loss 0.919150293469429 test_loss: 0.902281379699707
epoch: 12 training_loss 0.8856325286626816 test_loss: 0.85574369430542
epoch: 13 training_loss 0.8438633698225021 test_loss: 0.9095062255859375
epoch: 14 training_loss 0.8535996913909912 test_loss: 0.8162461280822754
epoch: 15 training_loss 0.8257460325956345 test_loss: 0.7872140407562256
epoch: 16 training_loss 0.8055351060628891 test_loss: 0.8270894050598144
epoch: 17 training_loss 0.7775170266628265 test_loss: 0.853947639465332
epoch: 18 training_loss 0.7737197041511535 test_loss: 0.7509898662567138
epoch: 19 training_loss 0.7541924393177033 test_loss: 0.7594911098480225
epoch: 20 training_loss 0.749819608926773 test_loss: 0.7676164627075195
epoch: 21 training_loss 0.7389471411705018 test_loss: 0.752128267288208
epoch: 22 training_loss 0.7296850454807281 test_loss: 0.7262178897857666
epoch: 23 training_loss 0.7249612826108932 test_loss: 0.735958480834961
epoch: 24 training_loss 0.7047276639938355 test_loss: 0.7242546558380127
epoch: 25 training_loss 0.7044665378332138 test_loss: 0.6876718997955322
epoch: 26 training_loss 0.7023949939012527 test_loss: 0.7297495365142822
epoch: 27 training_loss 0.692211617231369 test_loss: 0.664029884338379
epoch: 28 training_loss 0.6727756106853485 test_loss: 0.709768009185791
epoch: 29 training_loss 0.6428494650125504 test_loss: 0.6937455177307129
epoch: 30 training_loss 0.6681943297386169 test_loss: 0.6699969291687011
epoch: 31 training_loss 0.664767193198204 test_loss: 0.6783636093139649
epoch: 32 training_loss 0.660039774775505 test_loss: 0.6399418354034424
epoch: 33 training_loss 0.6540382581949234 test_loss: 0.6489686489105224
epoch: 34 training_loss 0.6386795550584793 test_loss: 0.6460012435913086
epoch: 35 training_loss 0.6659930145740509 test_loss: 0.621079397201538
epoch: 36 training_loss 0.6361315840482712 test_loss: 0.599676513671875
epoch: 37 training_loss 0.6415665990114212 test_loss: 0.6142609596252442
epoch: 38 training_loss 0.633756376504898 test_loss: 0.6242716789245606
epoch: 39 training_loss 0.6226357460021973 test_loss: 0.5903199195861817
epoch: 40 training_loss 0.6060664373636245 test_loss: 0.6172448635101319
epoch: 41 training_loss 0.6034042906761169 test_loss: 0.6213752746582031
epoch: 42 training_loss 0.6135654616355896 test_loss: 0.5879905223846436
epoch: 43 training_loss 0.6049417889118195 test_loss: 0.6021581649780273
epoch: 44 training_loss 0.6121396601200104 test_loss: 0.6215144157409668
epoch: 45 training_loss 0.5974773502349854 test_loss: 0.6371254444122314
epoch: 46 training_loss 0.5992563277482986 test_loss: 0.5958944320678711
epoch: 47 training_loss 0.5791311624646187 test_loss: 0.6000555515289306
epoch: 48 training_loss 0.5881757974624634 test_loss: 0.588084363937378
epoch: 49 training_loss 0.5870288199186325 test_loss: 0.5771712779998779
epoch: 50 training_loss 0.5814272940158844 test_loss: 0.5952281951904297
epoch: 51 training_loss 0.5696215981245041 test_loss: 0.5732128143310546
epoch: 52 training_loss 0.5796629184484482 test_loss: 0.5798748016357422
epoch: 53 training_loss 0.5682112473249435 test_loss: 0.570751428604126
epoch: 54 training_loss 0.5657830837368966 test_loss: 0.5739305496215821
epoch: 55 training_loss 0.5581992816925049 test_loss: 0.5563704967498779
epoch: 56 training_loss 0.573104996085167 test_loss: 0.6031442642211914
epoch: 57 training_loss 0.567501783668995 test_loss: 0.5682923316955566
epoch: 58 training_loss 0.5616210401058197 test_loss: 0.5732561588287354
epoch: 59 training_loss 0.5581779345870018 test_loss: 0.5603314876556397
epoch: 60 training_loss 0.575946890115738 test_loss: 0.579922866821289
epoch: 61 training_loss 0.5642326799035072 test_loss: 0.5484856128692627
epoch: 62 training_loss 0.5540464761853218 test_loss: 0.5698785305023193
epoch: 63 training_loss 0.5592495769262313 test_loss: 0.5711339950561524
epoch: 64 training_loss 0.549776366353035 test_loss: 0.5458867073059082
epoch: 65 training_loss 0.5600079107284546 test_loss: 0.5474146366119385
epoch: 66 training_loss 0.5504673901200294 test_loss: 0.5553403377532959
epoch: 67 training_loss 0.5460028779506684 test_loss: 0.5518336296081543
epoch: 68 training_loss 0.555392185151577 test_loss: 0.5461031436920166
epoch: 69 training_loss 0.5354768764972687 test_loss: 0.6544341564178466
epoch: 70 training_loss 0.5528392603993416 test_loss: 0.5721729278564454
epoch: 71 training_loss 0.5411873200535774 test_loss: 0.5552272319793701
epoch: 72 training_loss 0.5381700509786606 test_loss: 0.5416617393493652
epoch: 73 training_loss 0.5369030129909516 test_loss: 0.5445284366607666
epoch: 74 training_loss 0.5416631883382798 test_loss: 0.550875473022461
epoch: 75 training_loss 0.5373192617297172 test_loss: 0.52206449508667
epoch: 76 training_loss 0.5411418461799622 test_loss: 0.5588223457336425
epoch: 77 training_loss 0.5372873848676681 test_loss: 0.5182477951049804
epoch: 78 training_loss 0.5395621001720429 test_loss: 0.5381203174591065
epoch: 79 training_loss 0.5349781167507172 test_loss: 0.5422452926635742
epoch: 80 training_loss 0.5417514571547508 test_loss: 0.5446170330047607
epoch: 81 training_loss 0.5365881851315498 test_loss: 0.5429525375366211
epoch: 82 training_loss 0.5394960588216782 test_loss: 0.5240192413330078
epoch: 83 training_loss 0.5329758164286613 test_loss: 0.5321672916412353
epoch: 84 training_loss 0.5190093401074409 test_loss: 0.5174620628356934
epoch: 85 training_loss 0.5277933871746063 test_loss: 0.550093126296997
epoch: 86 training_loss 0.5196858063340187 test_loss: 0.5437934398651123
epoch: 87 training_loss 0.5197977143526077 test_loss: 0.5197280883789063
epoch: 88 training_loss 0.525174745619297 test_loss: 0.530417537689209
epoch: 89 training_loss 0.5205811476707458 test_loss: 0.5414827346801758
epoch: 90 training_loss 0.516958376467228 test_loss: 0.5123018741607666
epoch: 91 training_loss 0.5098367160558701 test_loss: 0.5140419483184815
epoch: 92 training_loss 0.5145044505596161 test_loss: 0.5126251220703125
epoch: 93 training_loss 0.5205209675431252 test_loss: 0.5392926692962646
epoch: 94 training_loss 0.5068903014063835 test_loss: 0.5215607643127441
epoch: 95 training_loss 0.5060080510377883 test_loss: 0.5111421108245849
epoch: 96 training_loss 0.5030302214622497 test_loss: 0.5308628559112549
epoch: 97 training_loss 0.5051513978838921 test_loss: 0.5100766658782959
epoch: 98 training_loss 0.5078662216663361 test_loss: 0.5259750843048095
epoch: 99 training_loss 0.5043209767341614 test_loss: 0.5512948036193848
epoch: 100 training_loss 0.511265626847744 test_loss: 0.5237227439880371
epoch: 101 training_loss 0.5143644997477531 test_loss: 0.5059577465057373
epoch: 102 training_loss 0.5072383585572243 test_loss: 0.4987340450286865
epoch: 103 training_loss 0.5034894698858261 test_loss: 0.510080623626709
epoch: 104 training_loss 0.5030404397845268 test_loss: 0.5105955600738525
epoch: 105 training_loss 0.5092678907513618 test_loss: 0.5324816703796387
epoch: 106 training_loss 0.4953430700302124 test_loss: 0.49538440704345704
epoch: 107 training_loss 0.5051120972633362 test_loss: 0.5121057987213135
epoch: 108 training_loss 0.5061664327979087 test_loss: 0.5072836399078369
epoch: 109 training_loss 0.5080351209640503 test_loss: 0.5082445621490479
epoch: 110 training_loss 0.5057672515511513 test_loss: 0.5202169418334961
epoch: 111 training_loss 0.5050898492336273 test_loss: 0.5544561386108399
epoch: 112 training_loss 0.5041384756565094 test_loss: 0.49045648574829104
epoch: 113 training_loss 0.5003222221136093 test_loss: 0.5009501457214356
epoch: 114 training_loss 0.4915412387251854 test_loss: 0.477923059463501
epoch: 115 training_loss 0.5057788637280464 test_loss: 0.5124327182769776
epoch: 116 training_loss 0.4948550382256508 test_loss: 0.49421353340148927
epoch: 117 training_loss 0.49592188239097595 test_loss: 0.5015915870666504
epoch: 118 training_loss 0.5165685582160949 test_loss: 0.4845149040222168
epoch: 119 training_loss 0.49415844440460205 test_loss: 0.5103447437286377
epoch: 120 training_loss 0.4968955433368683 test_loss: 0.5164483547210693
epoch: 121 training_loss 0.48873392164707186 test_loss: 0.4929854393005371
epoch: 122 training_loss 0.49920088320970535 test_loss: 0.5260085105895996
epoch: 123 training_loss 0.4936577618122101 test_loss: 0.5435022354125977
epoch: 124 training_loss 0.49476546138525007 test_loss: 0.4920642375946045
epoch: 125 training_loss 0.4865397474169731 test_loss: 0.48282060623168943
epoch: 126 training_loss 0.4853687408566475 test_loss: 0.4918616771697998
epoch: 127 training_loss 0.48789905309677123 test_loss: 0.49995436668396
epoch: 128 training_loss 0.4862352368235588 test_loss: 0.49602136611938474
epoch: 129 training_loss 0.480107561647892 test_loss: 0.4918454647064209
epoch: 130 training_loss 0.49280205577611924 test_loss: 0.48594255447387696
epoch: 131 training_loss 0.49192891508340836 test_loss: 0.49218926429748533
epoch: 132 training_loss 0.47804074972867966 test_loss: 0.49857378005981445
epoch: 133 training_loss 0.49514173686504365 test_loss: 0.48389511108398436
epoch: 134 training_loss 0.4846362516283989 test_loss: 0.49565720558166504
epoch: 135 training_loss 0.49046991050243377 test_loss: 0.4920313358306885
epoch: 136 training_loss 0.49101871758699417 test_loss: 0.5047290802001954
epoch: 137 training_loss 0.4902040559053421 test_loss: 0.4891106605529785
epoch: 138 training_loss 0.4848279720544815 test_loss: 0.487263822555542
epoch: 139 training_loss 0.4771081352233887 test_loss: 0.4761963367462158
epoch: 140 training_loss 0.4786923712491989 test_loss: 0.48560490608215334
epoch: 141 training_loss 0.47324606239795686 test_loss: 0.47417631149291994
epoch: 142 training_loss 0.4838191491365433 test_loss: 0.4757777214050293
epoch: 143 training_loss 0.4879131641983986 test_loss: 0.4737538814544678
epoch: 144 training_loss 0.48656606674194336 test_loss: 0.48422741889953613
epoch: 145 training_loss 0.48435699582099917 test_loss: 0.46998138427734376
epoch: 146 training_loss 0.47641644805669786 test_loss: 0.47342491149902344
epoch: 147 training_loss 0.48136629432439804 test_loss: 0.4805785655975342
epoch: 148 training_loss 0.4715947467088699 test_loss: 0.483411979675293
epoch: 149 training_loss 0.4689901632070541 test_loss: 0.47441606521606444
3154.194037548099
episode: 0 training return: tensor(-74.7201, device='cuda:0')
episode: 1 training return: tensor(-67.1628, device='cuda:0')
episode: 2 training return: tensor(-329.0459, device='cuda:0')
episode: 3 training return: tensor(-77.6641, device='cuda:0')
epoch: 1 test_true_pfm: 3157.452111526319 sim_pfm: -99.67684362187477
episode: 4 training return: tensor(-101.2479, device='cuda:0')
episode: 5 training return: tensor(-84.4967, device='cuda:0')
episode: 6 training return: tensor(-53.8933, device='cuda:0')
episode: 7 training return: tensor(-73.8407, device='cuda:0')
epoch: 2 test_true_pfm: 3165.474771947818 sim_pfm: -90.12667118932586
episode: 8 training return: tensor(-698.0616, device='cuda:0')
episode: 9 training return: tensor(-55.5630, device='cuda:0')
episode: 10 training return: tensor(-81.7846, device='cuda:0')
episode: 11 training return: tensor(-73.1075, device='cuda:0')
epoch: 3 test_true_pfm: 3002.5252216980984 sim_pfm: -200.18865357871013
episode: 12 training return: tensor(-69.2618, device='cuda:0')
episode: 13 training return: tensor(-75.4360, device='cuda:0')
episode: 14 training return: tensor(-113.1773, device='cuda:0')
episode: 15 training return: tensor(-359.0945, device='cuda:0')
epoch: 4 test_true_pfm: 2153.5608834074987 sim_pfm: -349.6007869270882
episode: 16 training return: tensor(-58.7673, device='cuda:0')
episode: 17 training return: tensor(-129.1892, device='cuda:0')
episode: 18 training return: tensor(-94.8604, device='cuda:0')
episode: 19 training return: tensor(-704.9185, device='cuda:0')
epoch: 5 test_true_pfm: 2902.118816365061 sim_pfm: -96.62635636568302
episode: 20 training return: tensor(-115.5908, device='cuda:0')
episode: 21 training return: tensor(-82.9391, device='cuda:0')
episode: 22 training return: tensor(-688.7798, device='cuda:0')
episode: 23 training return: tensor(-96.9767, device='cuda:0')
epoch: 6 test_true_pfm: 3125.437690390776 sim_pfm: -221.41887374206757
episode: 24 training return: tensor(-633.7022, device='cuda:0')
episode: 25 training return: tensor(-707.6487, device='cuda:0')
episode: 26 training return: tensor(-709.9396, device='cuda:0')
episode: 27 training return: tensor(-108.8422, device='cuda:0')
epoch: 7 test_true_pfm: 981.7490447455472 sim_pfm: -512.750499999267
episode: 28 training return: tensor(-107.6102, device='cuda:0')
episode: 29 training return: tensor(-97.8493, device='cuda:0')
episode: 30 training return: tensor(-86.8150, device='cuda:0')
episode: 31 training return: tensor(-97.1117, device='cuda:0')
epoch: 8 test_true_pfm: 3180.187102528476 sim_pfm: -140.99030263523068
episode: 32 training return: tensor(-133.7373, device='cuda:0')
episode: 33 training return: tensor(-111.3631, device='cuda:0')
episode: 34 training return: tensor(-100.1058, device='cuda:0')
episode: 35 training return: tensor(-96.0936, device='cuda:0')
epoch: 9 test_true_pfm: 2269.5442361569494 sim_pfm: -97.17495105634832
episode: 36 training return: tensor(-91.9741, device='cuda:0')
episode: 37 training return: tensor(-66.7636, device='cuda:0')
episode: 38 training return: tensor(-72.5110, device='cuda:0')
episode: 39 training return: tensor(-74.0376, device='cuda:0')
epoch: 10 test_true_pfm: 2814.7988131045145 sim_pfm: -78.62027419605874
episode: 40 training return: tensor(-46.2464, device='cuda:0')
episode: 41 training return: tensor(-108.0051, device='cuda:0')
episode: 42 training return: tensor(-91.6035, device='cuda:0')
episode: 43 training return: tensor(-50.2584, device='cuda:0')
epoch: 11 test_true_pfm: 3215.279576507824 sim_pfm: -62.36818683998232
episode: 44 training return: tensor(-114.7161, device='cuda:0')
episode: 45 training return: tensor(-44.6849, device='cuda:0')
episode: 46 training return: tensor(-314.1038, device='cuda:0')
episode: 47 training return: tensor(-63.8704, device='cuda:0')
epoch: 12 test_true_pfm: 3192.4650702422655 sim_pfm: -66.64166947469737
episode: 48 training return: tensor(-658.1306, device='cuda:0')
episode: 49 training return: tensor(-81.5961, device='cuda:0')
episode: 50 training return: tensor(-50.3126, device='cuda:0')
episode: 51 training return: tensor(-74.4064, device='cuda:0')
epoch: 13 test_true_pfm: 3104.5609665765805 sim_pfm: -61.94874294301068
episode: 52 training return: tensor(-58.2242, device='cuda:0')
episode: 53 training return: tensor(-60.1402, device='cuda:0')
episode: 54 training return: tensor(-83.6184, device='cuda:0')
episode: 55 training return: tensor(-324.5036, device='cuda:0')
epoch: 14 test_true_pfm: 3186.1233716602633 sim_pfm: -71.43542589258868
episode: 56 training return: tensor(-361.2016, device='cuda:0')
episode: 57 training return: tensor(-633.8894, device='cuda:0')
episode: 58 training return: tensor(-65.1708, device='cuda:0')
episode: 59 training return: tensor(-407.6486, device='cuda:0')
epoch: 15 test_true_pfm: 3170.4121728016144 sim_pfm: -83.95801083915285
episode: 60 training return: tensor(-80.8107, device='cuda:0')
episode: 61 training return: tensor(-68.1422, device='cuda:0')
episode: 62 training return: tensor(-221.4718, device='cuda:0')
episode: 63 training return: tensor(-48.6659, device='cuda:0')
epoch: 16 test_true_pfm: 3202.000304225699 sim_pfm: -70.23033666420572
episode: 64 training return: tensor(-67.8373, device='cuda:0')
episode: 65 training return: tensor(-35.0735, device='cuda:0')
episode: 66 training return: tensor(-680.7237, device='cuda:0')
episode: 67 training return: tensor(-204.2845, device='cuda:0')
epoch: 17 test_true_pfm: 2835.7835814470236 sim_pfm: -64.5435177256586
episode: 68 training return: tensor(-80.1987, device='cuda:0')
episode: 69 training return: tensor(-73.2883, device='cuda:0')
episode: 70 training return: tensor(-109.7035, device='cuda:0')
episode: 71 training return: tensor(-82.1826, device='cuda:0')
epoch: 18 test_true_pfm: 3187.443177246807 sim_pfm: -73.96955844119657
episode: 72 training return: tensor(-701.0555, device='cuda:0')
episode: 73 training return: tensor(-50.3335, device='cuda:0')
episode: 74 training return: tensor(-69.5730, device='cuda:0')
episode: 75 training return: tensor(-46.3525, device='cuda:0')
epoch: 19 test_true_pfm: 3202.4483451133565 sim_pfm: -64.90934920720368
episode: 76 training return: tensor(-458.6314, device='cuda:0')
episode: 77 training return: tensor(-64.5191, device='cuda:0')
episode: 78 training return: tensor(-60.0415, device='cuda:0')
episode: 79 training return: tensor(-77.4000, device='cuda:0')
epoch: 20 test_true_pfm: 3188.824177423768 sim_pfm: -60.113077839526035
episode: 80 training return: tensor(-85.7419, device='cuda:0')
episode: 81 training return: tensor(-63.0569, device='cuda:0')
episode: 82 training return: tensor(-66.1172, device='cuda:0')
episode: 83 training return: tensor(-73.7923, device='cuda:0')
epoch: 21 test_true_pfm: 2863.3454585483014 sim_pfm: -73.18568269787163
episode: 84 training return: tensor(-48.2559, device='cuda:0')
episode: 85 training return: tensor(-80.8374, device='cuda:0')
episode: 86 training return: tensor(-75.3897, device='cuda:0')
episode: 87 training return: tensor(-439.0912, device='cuda:0')
epoch: 22 test_true_pfm: 3182.831850892495 sim_pfm: -83.56482881609311
episode: 88 training return: tensor(-63.7052, device='cuda:0')
episode: 89 training return: tensor(-70.6508, device='cuda:0')
episode: 90 training return: tensor(-65.0377, device='cuda:0')
episode: 91 training return: tensor(-86.2843, device='cuda:0')
epoch: 23 test_true_pfm: 3186.663764627288 sim_pfm: -68.25105085289881
episode: 92 training return: tensor(-23.2522, device='cuda:0')
episode: 93 training return: tensor(-42.9397, device='cuda:0')
episode: 94 training return: tensor(-44.2109, device='cuda:0')
episode: 95 training return: tensor(-28.6766, device='cuda:0')
epoch: 24 test_true_pfm: 3161.9232869463776 sim_pfm: -154.07433357285723
episode: 96 training return: tensor(-55.3144, device='cuda:0')
episode: 97 training return: tensor(-39.7620, device='cuda:0')
episode: 98 training return: tensor(-67.4233, device='cuda:0')
episode: 99 training return: tensor(-93.3486, device='cuda:0')
epoch: 25 test_true_pfm: 3203.663168854489 sim_pfm: -65.36642787723879
episode: 100 training return: tensor(-32.9287, device='cuda:0')
episode: 101 training return: tensor(-658.4918, device='cuda:0')
episode: 102 training return: tensor(-78.5385, device='cuda:0')
episode: 103 training return: tensor(-38.6656, device='cuda:0')
epoch: 26 test_true_pfm: 2854.245728408199 sim_pfm: -53.30057320697233
episode: 104 training return: tensor(-61.6919, device='cuda:0')
episode: 105 training return: tensor(-75.4241, device='cuda:0')
episode: 106 training return: tensor(-52.9808, device='cuda:0')
episode: 107 training return: tensor(-52.3498, device='cuda:0')
epoch: 27 test_true_pfm: 3168.582933990909 sim_pfm: -69.60422653501155
episode: 108 training return: tensor(-77.3465, device='cuda:0')
episode: 109 training return: tensor(-51.1445, device='cuda:0')
episode: 110 training return: tensor(-62.8427, device='cuda:0')
episode: 111 training return: tensor(-70.4341, device='cuda:0')
epoch: 28 test_true_pfm: 3163.994173660103 sim_pfm: -84.45712369622197
episode: 112 training return: tensor(-47.1808, device='cuda:0')
episode: 113 training return: tensor(-74.3732, device='cuda:0')
episode: 114 training return: tensor(-48.4602, device='cuda:0')
episode: 115 training return: tensor(-111.4516, device='cuda:0')
epoch: 29 test_true_pfm: 3202.014162577357 sim_pfm: -66.60316929001904
episode: 116 training return: tensor(-59.2292, device='cuda:0')
episode: 117 training return: tensor(-76.4220, device='cuda:0')
episode: 118 training return: tensor(-36.7404, device='cuda:0')
episode: 119 training return: tensor(-48.7602, device='cuda:0')
epoch: 30 test_true_pfm: 3186.802591843243 sim_pfm: -94.19983974820934
episode: 120 training return: tensor(-75.6172, device='cuda:0')
episode: 121 training return: tensor(-73.4707, device='cuda:0')
episode: 122 training return: tensor(-87.8692, device='cuda:0')
episode: 123 training return: tensor(-106.8085, device='cuda:0')
epoch: 31 test_true_pfm: 3181.5262104986664 sim_pfm: -74.42426119195686
episode: 124 training return: tensor(-247.2106, device='cuda:0')
episode: 125 training return: tensor(-94.4748, device='cuda:0')
episode: 126 training return: tensor(-87.1865, device='cuda:0')
episode: 127 training return: tensor(-70.6174, device='cuda:0')
epoch: 32 test_true_pfm: 3188.125718976464 sim_pfm: -62.137066881133556
episode: 128 training return: tensor(-40.8129, device='cuda:0')
episode: 129 training return: tensor(-102.0499, device='cuda:0')
episode: 130 training return: tensor(-84.7255, device='cuda:0')
episode: 131 training return: tensor(-50.4947, device='cuda:0')
epoch: 33 test_true_pfm: 3173.219487802349 sim_pfm: -63.623922781659836
episode: 132 training return: tensor(-54.7680, device='cuda:0')
episode: 133 training return: tensor(-87.1887, device='cuda:0')
episode: 134 training return: tensor(-82.3554, device='cuda:0')
episode: 135 training return: tensor(-25.6947, device='cuda:0')
epoch: 34 test_true_pfm: 3199.2860876438904 sim_pfm: -64.44079314298385
episode: 136 training return: tensor(-479.1120, device='cuda:0')
episode: 137 training return: tensor(-87.2242, device='cuda:0')
episode: 138 training return: tensor(-63.0802, device='cuda:0')
episode: 139 training return: tensor(-81.0349, device='cuda:0')
epoch: 35 test_true_pfm: 3181.747039614766 sim_pfm: -59.180007061659126
episode: 140 training return: tensor(-69.9014, device='cuda:0')
episode: 141 training return: tensor(-75.4009, device='cuda:0')
episode: 142 training return: tensor(-102.8225, device='cuda:0')
episode: 143 training return: tensor(79.1825, device='cuda:0')
epoch: 36 test_true_pfm: 3205.583815033036 sim_pfm: -63.846071557452284
episode: 144 training return: tensor(-53.2316, device='cuda:0')
episode: 145 training return: tensor(-36.1362, device='cuda:0')
episode: 146 training return: tensor(-73.5022, device='cuda:0')
episode: 147 training return: tensor(-12.9040, device='cuda:0')
epoch: 37 test_true_pfm: 3200.919978177439 sim_pfm: -63.15961945110272
episode: 148 training return: tensor(-51.1180, device='cuda:0')
episode: 149 training return: tensor(-55.3792, device='cuda:0')
episode: 150 training return: tensor(-67.4599, device='cuda:0')
episode: 151 training return: tensor(-58.3511, device='cuda:0')
epoch: 38 test_true_pfm: 3200.7941710274868 sim_pfm: -68.02305837379147
episode: 152 training return: tensor(-68.5094, device='cuda:0')
episode: 153 training return: tensor(-61.7400, device='cuda:0')
episode: 154 training return: tensor(-66.9065, device='cuda:0')
episode: 155 training return: tensor(-60.9992, device='cuda:0')
epoch: 39 test_true_pfm: 3199.9657362517755 sim_pfm: -64.5642718221158
episode: 156 training return: tensor(-70.2064, device='cuda:0')
episode: 157 training return: tensor(-529.3838, device='cuda:0')
episode: 158 training return: tensor(-619.4623, device='cuda:0')
episode: 159 training return: tensor(-340.9388, device='cuda:0')
epoch: 40 test_true_pfm: 3175.8304876822845 sim_pfm: -61.01131141621348
episode: 160 training return: tensor(-56.5820, device='cuda:0')
episode: 161 training return: tensor(-2.8062, device='cuda:0')
episode: 162 training return: tensor(-94.7391, device='cuda:0')
episode: 163 training return: tensor(-79.8798, device='cuda:0')
epoch: 41 test_true_pfm: 3172.3182094599833 sim_pfm: -225.0694381495317
episode: 164 training return: tensor(-59.6888, device='cuda:0')
episode: 165 training return: tensor(-72.0673, device='cuda:0')
episode: 166 training return: tensor(1.9277, device='cuda:0')
episode: 167 training return: tensor(-50.4439, device='cuda:0')
epoch: 42 test_true_pfm: 3183.9344169135434 sim_pfm: -75.2370388994653
episode: 168 training return: tensor(-59.3061, device='cuda:0')
episode: 169 training return: tensor(-48.3871, device='cuda:0')
episode: 170 training return: tensor(-46.8497, device='cuda:0')
episode: 171 training return: tensor(-208.7063, device='cuda:0')
epoch: 43 test_true_pfm: 3188.1285684825757 sim_pfm: -72.13764181610895
episode: 172 training return: tensor(-76.7019, device='cuda:0')
episode: 173 training return: tensor(-46.8740, device='cuda:0')
episode: 174 training return: tensor(-94.3194, device='cuda:0')
episode: 175 training return: tensor(-66.4168, device='cuda:0')
epoch: 44 test_true_pfm: 3192.8797723617777 sim_pfm: -81.39195137090671
episode: 176 training return: tensor(-610.4523, device='cuda:0')
episode: 177 training return: tensor(-97.1085, device='cuda:0')
episode: 178 training return: tensor(-68.1167, device='cuda:0')
episode: 179 training return: tensor(-37.2859, device='cuda:0')
epoch: 45 test_true_pfm: 3203.0187375859946 sim_pfm: -50.33122278621886
episode: 180 training return: tensor(-44.3244, device='cuda:0')
episode: 181 training return: tensor(-74.1852, device='cuda:0')
episode: 182 training return: tensor(-66.1981, device='cuda:0')
episode: 183 training return: tensor(-70.9022, device='cuda:0')
epoch: 46 test_true_pfm: 3191.2707894372784 sim_pfm: -78.90726957948452
episode: 184 training return: tensor(-612.6688, device='cuda:0')
episode: 185 training return: tensor(-50.7751, device='cuda:0')
episode: 186 training return: tensor(-68.7423, device='cuda:0')
episode: 187 training return: tensor(-48.8985, device='cuda:0')
epoch: 47 test_true_pfm: 3199.8345871323363 sim_pfm: -46.54577709035948
episode: 188 training return: tensor(-71.6192, device='cuda:0')
episode: 189 training return: tensor(-187.5182, device='cuda:0')
episode: 190 training return: tensor(-54.6582, device='cuda:0')
episode: 191 training return: tensor(-45.7354, device='cuda:0')
epoch: 48 test_true_pfm: 3170.5184186638035 sim_pfm: -79.18237028779306
episode: 192 training return: tensor(-48.8943, device='cuda:0')
episode: 193 training return: tensor(-49.5878, device='cuda:0')
episode: 194 training return: tensor(-63.0315, device='cuda:0')
episode: 195 training return: tensor(-61.3069, device='cuda:0')
epoch: 49 test_true_pfm: 3211.95012836626 sim_pfm: -59.30651548547515
episode: 196 training return: tensor(-49.6746, device='cuda:0')
episode: 197 training return: tensor(-28.8634, device='cuda:0')
episode: 198 training return: tensor(-63.4073, device='cuda:0')
episode: 199 training return: tensor(-51.4587, device='cuda:0')
epoch: 50 test_true_pfm: 3211.5444549877443 sim_pfm: -58.94018857743746
episode: 200 training return: tensor(-245.9933, device='cuda:0')
episode: 201 training return: tensor(-79.9910, device='cuda:0')
episode: 202 training return: tensor(-60.7883, device='cuda:0')
episode: 203 training return: tensor(-55.5952, device='cuda:0')
epoch: 51 test_true_pfm: 3218.783253076445 sim_pfm: -41.02853185586476
episode: 204 training return: tensor(-281.0246, device='cuda:0')
episode: 205 training return: tensor(-42.4624, device='cuda:0')
episode: 206 training return: tensor(-47.2495, device='cuda:0')
episode: 207 training return: tensor(-292.9025, device='cuda:0')
epoch: 52 test_true_pfm: 3203.161648940153 sim_pfm: -47.1735249516399
episode: 208 training return: tensor(-241.1162, device='cuda:0')
episode: 209 training return: tensor(-78.1321, device='cuda:0')
episode: 210 training return: tensor(-40.9430, device='cuda:0')
episode: 211 training return: tensor(-70.0360, device='cuda:0')
epoch: 53 test_true_pfm: 3228.0885037019484 sim_pfm: -30.72657259218977
episode: 212 training return: tensor(-62.0138, device='cuda:0')
episode: 213 training return: tensor(-74.2775, device='cuda:0')
episode: 214 training return: tensor(-54.5080, device='cuda:0')
episode: 215 training return: tensor(-211.4282, device='cuda:0')
epoch: 54 test_true_pfm: 3206.0951338253267 sim_pfm: -57.35756368233706
episode: 216 training return: tensor(-151.4399, device='cuda:0')
episode: 217 training return: tensor(-45.0025, device='cuda:0')
episode: 218 training return: tensor(-64.9714, device='cuda:0')
episode: 219 training return: tensor(-60.2936, device='cuda:0')
epoch: 55 test_true_pfm: 3191.4726525800525 sim_pfm: -77.53624927433945
episode: 220 training return: tensor(-48.0255, device='cuda:0')
episode: 221 training return: tensor(-659.4921, device='cuda:0')
episode: 222 training return: tensor(-706.6603, device='cuda:0')
episode: 223 training return: tensor(-76.1922, device='cuda:0')
epoch: 56 test_true_pfm: 3189.3091656197244 sim_pfm: -64.93942346405431
episode: 224 training return: tensor(-60.0350, device='cuda:0')
episode: 225 training return: tensor(-60.6786, device='cuda:0')
episode: 226 training return: tensor(-57.3598, device='cuda:0')
episode: 227 training return: tensor(-56.6513, device='cuda:0')
epoch: 57 test_true_pfm: 3198.7065261068524 sim_pfm: -63.269034754902044
episode: 228 training return: tensor(-75.1770, device='cuda:0')
episode: 229 training return: tensor(-358.6205, device='cuda:0')
episode: 230 training return: tensor(-34.1233, device='cuda:0')
episode: 231 training return: tensor(-51.9135, device='cuda:0')
epoch: 58 test_true_pfm: 3195.3480615331337 sim_pfm: -63.88177468639333
episode: 232 training return: tensor(-61.4968, device='cuda:0')
episode: 233 training return: tensor(-69.1081, device='cuda:0')
episode: 234 training return: tensor(-397.2822, device='cuda:0')
episode: 235 training return: tensor(-203.2421, device='cuda:0')
epoch: 59 test_true_pfm: 3196.854461174055 sim_pfm: -68.26781433380286
episode: 236 training return: tensor(-78.5930, device='cuda:0')
episode: 237 training return: tensor(-85.4281, device='cuda:0')
episode: 238 training return: tensor(-74.0771, device='cuda:0')
episode: 239 training return: tensor(-73.1085, device='cuda:0')
epoch: 60 test_true_pfm: 3222.2711188403714 sim_pfm: -50.260293703118805
episode: 240 training return: tensor(-75.8733, device='cuda:0')
episode: 241 training return: tensor(-75.1452, device='cuda:0')
episode: 242 training return: tensor(-438.3699, device='cuda:0')
episode: 243 training return: tensor(-46.9322, device='cuda:0')
epoch: 61 test_true_pfm: 3203.9407777073466 sim_pfm: -53.775461814676724
episode: 244 training return: tensor(-1.7702, device='cuda:0')
episode: 245 training return: tensor(-78.4104, device='cuda:0')
episode: 246 training return: tensor(-282.0053, device='cuda:0')
episode: 247 training return: tensor(-59.9525, device='cuda:0')
epoch: 62 test_true_pfm: 3210.2234505392703 sim_pfm: -57.98485142918071
episode: 248 training return: tensor(-690.4138, device='cuda:0')
episode: 249 training return: tensor(-62.5997, device='cuda:0')
episode: 250 training return: tensor(-66.0156, device='cuda:0')
episode: 251 training return: tensor(-73.1395, device='cuda:0')
epoch: 63 test_true_pfm: 3199.5119603602648 sim_pfm: -55.40459389637302
episode: 252 training return: tensor(-77.9636, device='cuda:0')
episode: 253 training return: tensor(11.6483, device='cuda:0')
episode: 254 training return: tensor(-35.3528, device='cuda:0')
episode: 255 training return: tensor(-70.5146, device='cuda:0')
epoch: 64 test_true_pfm: 3185.6999916517784 sim_pfm: -56.17844798732161
episode: 256 training return: tensor(-52.3705, device='cuda:0')
episode: 257 training return: tensor(-83.8967, device='cuda:0')
episode: 258 training return: tensor(-39.1473, device='cuda:0')
episode: 259 training return: tensor(-49.0168, device='cuda:0')
epoch: 65 test_true_pfm: 3180.297393766507 sim_pfm: -80.55387652713883
episode: 260 training return: tensor(-75.2520, device='cuda:0')
episode: 261 training return: tensor(-56.2198, device='cuda:0')
episode: 262 training return: tensor(-45.0438, device='cuda:0')
episode: 263 training return: tensor(-57.9492, device='cuda:0')
epoch: 66 test_true_pfm: 3223.022594131026 sim_pfm: -50.38489590371804
episode: 264 training return: tensor(-85.7504, device='cuda:0')
episode: 265 training return: tensor(-59.0739, device='cuda:0')
episode: 266 training return: tensor(-48.1646, device='cuda:0')
episode: 267 training return: tensor(-42.0924, device='cuda:0')
epoch: 67 test_true_pfm: 3193.8080285450073 sim_pfm: -73.66587003280681
episode: 268 training return: tensor(-25.3018, device='cuda:0')
episode: 269 training return: tensor(-55.7380, device='cuda:0')
episode: 270 training return: tensor(-38.0014, device='cuda:0')
episode: 271 training return: tensor(-84.4842, device='cuda:0')
epoch: 68 test_true_pfm: 3205.259577066971 sim_pfm: -65.35620102680211
episode: 272 training return: tensor(-70.2930, device='cuda:0')
episode: 273 training return: tensor(-695.8826, device='cuda:0')
episode: 274 training return: tensor(-47.9459, device='cuda:0')
episode: 275 training return: tensor(-68.0341, device='cuda:0')
epoch: 69 test_true_pfm: 3205.1273633555306 sim_pfm: -53.64620028063655
episode: 276 training return: tensor(-163.0205, device='cuda:0')
episode: 277 training return: tensor(-37.9041, device='cuda:0')
episode: 278 training return: tensor(-20.2653, device='cuda:0')
episode: 279 training return: tensor(-66.9412, device='cuda:0')
epoch: 70 test_true_pfm: 3218.9352804162086 sim_pfm: -48.76555107499007
episode: 280 training return: tensor(-54.1154, device='cuda:0')
episode: 281 training return: tensor(-71.5453, device='cuda:0')
episode: 282 training return: tensor(-64.0880, device='cuda:0')
episode: 283 training return: tensor(-33.9295, device='cuda:0')
epoch: 71 test_true_pfm: 3213.0287731811845 sim_pfm: -39.294826993524715
episode: 284 training return: tensor(-212.4574, device='cuda:0')
episode: 285 training return: tensor(-50.0672, device='cuda:0')
episode: 286 training return: tensor(-64.6243, device='cuda:0')
episode: 287 training return: tensor(-44.3091, device='cuda:0')
epoch: 72 test_true_pfm: 3250.8244128744136 sim_pfm: -51.26936516238493
episode: 288 training return: tensor(-691.4008, device='cuda:0')
episode: 289 training return: tensor(-43.2199, device='cuda:0')
episode: 290 training return: tensor(-27.3407, device='cuda:0')
episode: 291 training return: tensor(-70.9082, device='cuda:0')
epoch: 73 test_true_pfm: 3217.358344356233 sim_pfm: -43.716320179917
episode: 292 training return: tensor(-82.3128, device='cuda:0')
episode: 293 training return: tensor(-72.4563, device='cuda:0')
episode: 294 training return: tensor(-0.8675, device='cuda:0')
episode: 295 training return: tensor(-89.2777, device='cuda:0')
epoch: 74 test_true_pfm: 3207.8864550557287 sim_pfm: -55.86486966532539
episode: 296 training return: tensor(-77.6392, device='cuda:0')
episode: 297 training return: tensor(-19.5307, device='cuda:0')
episode: 298 training return: tensor(-176.3505, device='cuda:0')
episode: 299 training return: tensor(-62.4455, device='cuda:0')
epoch: 75 test_true_pfm: 3217.361003626942 sim_pfm: -62.35714252056399
episode: 300 training return: tensor(-640.8690, device='cuda:0')
episode: 301 training return: tensor(-45.4627, device='cuda:0')
episode: 302 training return: tensor(-41.0360, device='cuda:0')
episode: 303 training return: tensor(-72.6093, device='cuda:0')
epoch: 76 test_true_pfm: 3209.1036289249764 sim_pfm: -53.818923388491385
episode: 304 training return: tensor(-125.2868, device='cuda:0')
episode: 305 training return: tensor(-689.7120, device='cuda:0')
episode: 306 training return: tensor(-66.4506, device='cuda:0')
episode: 307 training return: tensor(-87.8400, device='cuda:0')
epoch: 77 test_true_pfm: 3210.3492206160595 sim_pfm: -50.62332512027933
episode: 308 training return: tensor(-48.3889, device='cuda:0')
episode: 309 training return: tensor(-52.7340, device='cuda:0')
episode: 310 training return: tensor(-87.2850, device='cuda:0')
episode: 311 training return: tensor(-611.9507, device='cuda:0')
epoch: 78 test_true_pfm: 3217.315116721871 sim_pfm: -43.41856576067706
episode: 312 training return: tensor(-32.7050, device='cuda:0')
episode: 313 training return: tensor(-30.5805, device='cuda:0')
episode: 314 training return: tensor(-65.5774, device='cuda:0')
episode: 315 training return: tensor(-74.2242, device='cuda:0')
epoch: 79 test_true_pfm: 3206.421903629883 sim_pfm: -50.36739312754556
episode: 316 training return: tensor(-54.7003, device='cuda:0')
episode: 317 training return: tensor(31.2662, device='cuda:0')
episode: 318 training return: tensor(-50.4878, device='cuda:0')
episode: 319 training return: tensor(-27.5111, device='cuda:0')
epoch: 80 test_true_pfm: 3204.459694816766 sim_pfm: -35.67667619444546
episode: 320 training return: tensor(-16.5459, device='cuda:0')
episode: 321 training return: tensor(-52.1878, device='cuda:0')
episode: 322 training return: tensor(-41.2689, device='cuda:0')
episode: 323 training return: tensor(-54.1232, device='cuda:0')
epoch: 81 test_true_pfm: 3210.927713513149 sim_pfm: -57.189320953136
episode: 324 training return: tensor(-38.2503, device='cuda:0')
episode: 325 training return: tensor(-38.1750, device='cuda:0')
episode: 326 training return: tensor(-70.0270, device='cuda:0')
episode: 327 training return: tensor(-48.6830, device='cuda:0')
epoch: 82 test_true_pfm: 3197.3970064166388 sim_pfm: -51.01366720162332
episode: 328 training return: tensor(-62.0975, device='cuda:0')
episode: 329 training return: tensor(5.9523, device='cuda:0')
episode: 330 training return: tensor(-74.1018, device='cuda:0')
episode: 331 training return: tensor(-91.5030, device='cuda:0')
epoch: 83 test_true_pfm: 3203.8687355114494 sim_pfm: -53.17480704933405
episode: 332 training return: tensor(-76.5651, device='cuda:0')
episode: 333 training return: tensor(-76.4767, device='cuda:0')
episode: 334 training return: tensor(-65.9609, device='cuda:0')
episode: 335 training return: tensor(-675.8727, device='cuda:0')
epoch: 84 test_true_pfm: 3199.3366443153977 sim_pfm: -58.3762120991208
episode: 336 training return: tensor(-73.4721, device='cuda:0')
episode: 337 training return: tensor(-74.8569, device='cuda:0')
episode: 338 training return: tensor(-41.4176, device='cuda:0')
episode: 339 training return: tensor(-27.1484, device='cuda:0')
epoch: 85 test_true_pfm: 3216.7266046619316 sim_pfm: -51.34604889457114
episode: 340 training return: tensor(-63.7622, device='cuda:0')
episode: 341 training return: tensor(-36.7512, device='cuda:0')
episode: 342 training return: tensor(-49.1129, device='cuda:0')
episode: 343 training return: tensor(6.5588, device='cuda:0')
epoch: 86 test_true_pfm: 3208.301303290736 sim_pfm: -51.525288360503815
episode: 344 training return: tensor(-618.3272, device='cuda:0')
episode: 345 training return: tensor(-89.2755, device='cuda:0')
episode: 346 training return: tensor(-44.2240, device='cuda:0')
episode: 347 training return: tensor(-57.7855, device='cuda:0')
epoch: 87 test_true_pfm: 3211.4393511154944 sim_pfm: -49.110964678645054
episode: 348 training return: tensor(-65.8655, device='cuda:0')
episode: 349 training return: tensor(-46.2150, device='cuda:0')
episode: 350 training return: tensor(-63.2737, device='cuda:0')
episode: 351 training return: tensor(-63.4456, device='cuda:0')
epoch: 88 test_true_pfm: 3203.4058251078072 sim_pfm: -55.990091132863505
episode: 352 training return: tensor(-698.0623, device='cuda:0')
episode: 353 training return: tensor(-66.0381, device='cuda:0')
episode: 354 training return: tensor(-45.4115, device='cuda:0')
episode: 355 training return: tensor(-57.3791, device='cuda:0')
epoch: 89 test_true_pfm: 3215.8259991990817 sim_pfm: -57.23575366366034
episode: 356 training return: tensor(-62.5106, device='cuda:0')
episode: 357 training return: tensor(-455.4214, device='cuda:0')
episode: 358 training return: tensor(-55.8080, device='cuda:0')
episode: 359 training return: tensor(-43.2952, device='cuda:0')
epoch: 90 test_true_pfm: 3201.040376097195 sim_pfm: -72.88411445539289
episode: 360 training return: tensor(-71.7221, device='cuda:0')
episode: 361 training return: tensor(-694.3720, device='cuda:0')
episode: 362 training return: tensor(-19.4368, device='cuda:0')
episode: 363 training return: tensor(-78.9581, device='cuda:0')
epoch: 91 test_true_pfm: 3203.806039884698 sim_pfm: -54.16210455288334
episode: 364 training return: tensor(-77.0129, device='cuda:0')
episode: 365 training return: tensor(-53.9389, device='cuda:0')
episode: 366 training return: tensor(-73.2850, device='cuda:0')
episode: 367 training return: tensor(-21.8136, device='cuda:0')
epoch: 92 test_true_pfm: 3201.035800851529 sim_pfm: -66.03772110782059
episode: 368 training return: tensor(-440.9918, device='cuda:0')
episode: 369 training return: tensor(-52.0503, device='cuda:0')
episode: 370 training return: tensor(-284.6800, device='cuda:0')
episode: 371 training return: tensor(-47.2455, device='cuda:0')
epoch: 93 test_true_pfm: 3199.449115948001 sim_pfm: -67.54996071447385
episode: 372 training return: tensor(-610.0297, device='cuda:0')
episode: 373 training return: tensor(-65.9924, device='cuda:0')
episode: 374 training return: tensor(-28.4794, device='cuda:0')
episode: 375 training return: tensor(-59.2809, device='cuda:0')
epoch: 94 test_true_pfm: 3209.603205699186 sim_pfm: -52.8627078407056
episode: 376 training return: tensor(-61.3754, device='cuda:0')
episode: 377 training return: tensor(-80.0905, device='cuda:0')
episode: 378 training return: tensor(-277.7217, device='cuda:0')
episode: 379 training return: tensor(-59.8223, device='cuda:0')
epoch: 95 test_true_pfm: 3205.1144457485793 sim_pfm: -53.84764011024769
episode: 380 training return: tensor(-31.1994, device='cuda:0')
episode: 381 training return: tensor(-2.9407, device='cuda:0')
episode: 382 training return: tensor(-84.0295, device='cuda:0')
episode: 383 training return: tensor(-63.6578, device='cuda:0')
epoch: 96 test_true_pfm: 3187.1583751386374 sim_pfm: -69.92431741359178
episode: 384 training return: tensor(-53.9900, device='cuda:0')
episode: 385 training return: tensor(-56.7528, device='cuda:0')
episode: 386 training return: tensor(-49.2451, device='cuda:0')
episode: 387 training return: tensor(-36.4769, device='cuda:0')
epoch: 97 test_true_pfm: 3228.085518449252 sim_pfm: -42.77485182878445
episode: 388 training return: tensor(-62.9352, device='cuda:0')
episode: 389 training return: tensor(-66.1816, device='cuda:0')
episode: 390 training return: tensor(-66.7802, device='cuda:0')
episode: 391 training return: tensor(-248.8531, device='cuda:0')
epoch: 98 test_true_pfm: 3207.6225016684743 sim_pfm: -51.238432856693784
episode: 392 training return: tensor(-61.2506, device='cuda:0')
episode: 393 training return: tensor(-88.5430, device='cuda:0')
episode: 394 training return: tensor(-70.8228, device='cuda:0')
episode: 395 training return: tensor(-46.4155, device='cuda:0')
epoch: 99 test_true_pfm: 3229.134832164758 sim_pfm: -45.13275113279815
episode: 396 training return: tensor(-51.8822, device='cuda:0')
episode: 397 training return: tensor(-71.5018, device='cuda:0')
episode: 398 training return: tensor(-54.9353, device='cuda:0')
episode: 399 training return: tensor(-86.7731, device='cuda:0')
epoch: 100 test_true_pfm: 3207.5364033341107 sim_pfm: -53.14263034937903
episode: 400 training return: tensor(-225.3453, device='cuda:0')
episode: 401 training return: tensor(-12.4777, device='cuda:0')
episode: 402 training return: tensor(-69.0518, device='cuda:0')
episode: 403 training return: tensor(-85.1173, device='cuda:0')
epoch: 101 test_true_pfm: 3230.2917731884595 sim_pfm: -40.60954122295758
episode: 404 training return: tensor(14.9191, device='cuda:0')
episode: 405 training return: tensor(-71.5633, device='cuda:0')
episode: 406 training return: tensor(-64.7829, device='cuda:0')
episode: 407 training return: tensor(-54.2927, device='cuda:0')
epoch: 102 test_true_pfm: 3201.2605776156656 sim_pfm: -48.03279492534542
episode: 408 training return: tensor(-40.1890, device='cuda:0')
episode: 409 training return: tensor(-66.7506, device='cuda:0')
episode: 410 training return: tensor(-87.7213, device='cuda:0')
episode: 411 training return: tensor(-129.7865, device='cuda:0')
epoch: 103 test_true_pfm: 3210.2518948979164 sim_pfm: -64.63674177299254
episode: 412 training return: tensor(-0.6727, device='cuda:0')
episode: 413 training return: tensor(-52.7753, device='cuda:0')
episode: 414 training return: tensor(-75.0929, device='cuda:0')
episode: 415 training return: tensor(-446.7809, device='cuda:0')
epoch: 104 test_true_pfm: 3228.454732395275 sim_pfm: -48.08850429814387
episode: 416 training return: tensor(-68.1668, device='cuda:0')
episode: 417 training return: tensor(-48.2533, device='cuda:0')
episode: 418 training return: tensor(-61.9131, device='cuda:0')
episode: 419 training return: tensor(-74.4308, device='cuda:0')
epoch: 105 test_true_pfm: 3218.3263524985796 sim_pfm: -44.85276331126806
episode: 420 training return: tensor(-58.2208, device='cuda:0')
episode: 421 training return: tensor(-62.0418, device='cuda:0')
episode: 422 training return: tensor(-67.9117, device='cuda:0')
episode: 423 training return: tensor(-701.3256, device='cuda:0')
epoch: 106 test_true_pfm: 3203.06286331834 sim_pfm: -52.313997670979006
episode: 424 training return: tensor(-51.3712, device='cuda:0')
episode: 425 training return: tensor(-47.1504, device='cuda:0')
episode: 426 training return: tensor(-68.4734, device='cuda:0')
episode: 427 training return: tensor(-65.5796, device='cuda:0')
epoch: 107 test_true_pfm: 3215.741941763077 sim_pfm: -47.79085591658562
episode: 428 training return: tensor(11.4363, device='cuda:0')
episode: 429 training return: tensor(-59.8614, device='cuda:0')
episode: 430 training return: tensor(43.2800, device='cuda:0')
episode: 431 training return: tensor(-62.4759, device='cuda:0')
epoch: 108 test_true_pfm: 3210.5695528760966 sim_pfm: -54.68755262385821
episode: 432 training return: tensor(-86.2378, device='cuda:0')
episode: 433 training return: tensor(-53.2155, device='cuda:0')
episode: 434 training return: tensor(41.5915, device='cuda:0')
episode: 435 training return: tensor(-57.1733, device='cuda:0')
epoch: 109 test_true_pfm: 3207.9362244954586 sim_pfm: -45.45584846528558
episode: 436 training return: tensor(-43.9064, device='cuda:0')
episode: 437 training return: tensor(-53.1861, device='cuda:0')
episode: 438 training return: tensor(-72.3583, device='cuda:0')
episode: 439 training return: tensor(-73.2788, device='cuda:0')
epoch: 110 test_true_pfm: 3196.920737380043 sim_pfm: -69.17515630363293
episode: 440 training return: tensor(-35.8082, device='cuda:0')
episode: 441 training return: tensor(-20.7467, device='cuda:0')
episode: 442 training return: tensor(-68.0540, device='cuda:0')
episode: 443 training return: tensor(-192.5839, device='cuda:0')
epoch: 111 test_true_pfm: 3198.355580184929 sim_pfm: -53.122091206993595
episode: 444 training return: tensor(-81.7901, device='cuda:0')
episode: 445 training return: tensor(-60.5914, device='cuda:0')
episode: 446 training return: tensor(-38.5106, device='cuda:0')
episode: 447 training return: tensor(-58.7483, device='cuda:0')
epoch: 112 test_true_pfm: 3213.5823376989006 sim_pfm: -48.35567994370164
episode: 448 training return: tensor(-51.7772, device='cuda:0')
episode: 449 training return: tensor(-74.6558, device='cuda:0')
episode: 450 training return: tensor(-35.0510, device='cuda:0')
episode: 451 training return: tensor(-66.4207, device='cuda:0')
epoch: 113 test_true_pfm: 3208.64159212393 sim_pfm: -55.042636772210244
episode: 452 training return: tensor(-45.1247, device='cuda:0')
episode: 453 training return: tensor(-58.6647, device='cuda:0')
episode: 454 training return: tensor(-516.0792, device='cuda:0')
episode: 455 training return: tensor(-78.2558, device='cuda:0')
epoch: 114 test_true_pfm: 3193.223888751876 sim_pfm: -63.08905640325975
episode: 456 training return: tensor(-341.4985, device='cuda:0')
episode: 457 training return: tensor(-86.5600, device='cuda:0')
episode: 458 training return: tensor(-271.8116, device='cuda:0')
episode: 459 training return: tensor(-50.4992, device='cuda:0')
epoch: 115 test_true_pfm: 3204.3714442378637 sim_pfm: -48.94820528572503
episode: 460 training return: tensor(-65.7644, device='cuda:0')
episode: 461 training return: tensor(66.2012, device='cuda:0')
episode: 462 training return: tensor(-42.2633, device='cuda:0')
episode: 463 training return: tensor(-74.9820, device='cuda:0')
epoch: 116 test_true_pfm: 3218.054327957397 sim_pfm: -35.11458046747915
episode: 464 training return: tensor(-62.0251, device='cuda:0')
episode: 465 training return: tensor(-74.1724, device='cuda:0')
episode: 466 training return: tensor(-39.5389, device='cuda:0')
episode: 467 training return: tensor(-43.4081, device='cuda:0')
epoch: 117 test_true_pfm: 3218.516655786518 sim_pfm: -55.38349129321674
episode: 468 training return: tensor(-72.0013, device='cuda:0')
episode: 469 training return: tensor(-37.5456, device='cuda:0')
episode: 470 training return: tensor(-25.3112, device='cuda:0')
episode: 471 training return: tensor(-52.0412, device='cuda:0')
epoch: 118 test_true_pfm: 3205.7253942957173 sim_pfm: -62.67066925719458
episode: 472 training return: tensor(-58.0265, device='cuda:0')
episode: 473 training return: tensor(-68.8683, device='cuda:0')
episode: 474 training return: tensor(-68.1494, device='cuda:0')
episode: 475 training return: tensor(-45.1166, device='cuda:0')
epoch: 119 test_true_pfm: 3214.417563847404 sim_pfm: -53.069565476092976
episode: 476 training return: tensor(-53.3650, device='cuda:0')
episode: 477 training return: tensor(-57.8057, device='cuda:0')
episode: 478 training return: tensor(-10.6033, device='cuda:0')
episode: 479 training return: tensor(-278.5173, device='cuda:0')
epoch: 120 test_true_pfm: 3211.0228644518593 sim_pfm: -46.31846548533455
episode: 480 training return: tensor(-70.0052, device='cuda:0')
episode: 481 training return: tensor(-19.6309, device='cuda:0')
episode: 482 training return: tensor(-48.7303, device='cuda:0')
episode: 483 training return: tensor(-274.1274, device='cuda:0')
epoch: 121 test_true_pfm: 3206.786617537846 sim_pfm: -61.53937896185865
episode: 484 training return: tensor(-69.1976, device='cuda:0')
episode: 485 training return: tensor(-58.3830, device='cuda:0')
episode: 486 training return: tensor(-50.6532, device='cuda:0')
episode: 487 training return: tensor(-56.7407, device='cuda:0')
epoch: 122 test_true_pfm: 3197.0385773118674 sim_pfm: -67.41780738486948
episode: 488 training return: tensor(-56.3919, device='cuda:0')
episode: 489 training return: tensor(-47.3395, device='cuda:0')
episode: 490 training return: tensor(-201.1933, device='cuda:0')
episode: 491 training return: tensor(-71.0594, device='cuda:0')
epoch: 123 test_true_pfm: 3224.1531746368946 sim_pfm: -49.630398922871485
episode: 492 training return: tensor(-42.8767, device='cuda:0')
episode: 493 training return: tensor(-430.4738, device='cuda:0')
episode: 494 training return: tensor(-78.1658, device='cuda:0')
episode: 495 training return: tensor(-69.4758, device='cuda:0')
epoch: 124 test_true_pfm: 3215.8924547164484 sim_pfm: -44.12289472457875
episode: 496 training return: tensor(-88.9888, device='cuda:0')
episode: 497 training return: tensor(-70.1213, device='cuda:0')
episode: 498 training return: tensor(-61.2316, device='cuda:0')
episode: 499 training return: tensor(-69.3736, device='cuda:0')
epoch: 125 test_true_pfm: 3204.7001367920125 sim_pfm: -50.29195270920172
episode: 500 training return: tensor(-55.7613, device='cuda:0')
episode: 501 training return: tensor(-61.1509, device='cuda:0')
episode: 502 training return: tensor(-659.0036, device='cuda:0')
episode: 503 training return: tensor(-91.2051, device='cuda:0')
epoch: 126 test_true_pfm: 3202.9203492481106 sim_pfm: -59.169668858104465
episode: 504 training return: tensor(-61.1859, device='cuda:0')
episode: 505 training return: tensor(-65.8459, device='cuda:0')
episode: 506 training return: tensor(-41.1933, device='cuda:0')
episode: 507 training return: tensor(-67.0619, device='cuda:0')
epoch: 127 test_true_pfm: 3212.157092894721 sim_pfm: -53.84380799229257
episode: 508 training return: tensor(-127.8409, device='cuda:0')
episode: 509 training return: tensor(8.0132, device='cuda:0')
episode: 510 training return: tensor(-65.2261, device='cuda:0')
episode: 511 training return: tensor(-53.4260, device='cuda:0')
epoch: 128 test_true_pfm: 3207.705883043274 sim_pfm: -10.472540744609432
episode: 512 training return: tensor(-75.9768, device='cuda:0')
episode: 513 training return: tensor(-196.0599, device='cuda:0')
episode: 514 training return: tensor(-46.1817, device='cuda:0')
episode: 515 training return: tensor(-18.4834, device='cuda:0')
epoch: 129 test_true_pfm: 3202.8730391974964 sim_pfm: -48.4480999323229
episode: 516 training return: tensor(-498.3582, device='cuda:0')
episode: 517 training return: tensor(-64.0871, device='cuda:0')
episode: 518 training return: tensor(-80.7931, device='cuda:0')
episode: 519 training return: tensor(-276.2582, device='cuda:0')
epoch: 130 test_true_pfm: 3196.3830099868087 sim_pfm: -58.19986565353853
episode: 520 training return: tensor(-163.3997, device='cuda:0')
episode: 521 training return: tensor(-43.2325, device='cuda:0')
episode: 522 training return: tensor(-75.6939, device='cuda:0')
episode: 523 training return: tensor(-520.1409, device='cuda:0')
epoch: 131 test_true_pfm: 3205.2027416121723 sim_pfm: -55.48144829176211
episode: 524 training return: tensor(-50.6832, device='cuda:0')
episode: 525 training return: tensor(-22.8631, device='cuda:0')
episode: 526 training return: tensor(-42.6815, device='cuda:0')
episode: 527 training return: tensor(-47.7500, device='cuda:0')
epoch: 132 test_true_pfm: 3208.149490945734 sim_pfm: -61.19524616969284
episode: 528 training return: tensor(-56.5663, device='cuda:0')
episode: 529 training return: tensor(-635.1623, device='cuda:0')
episode: 530 training return: tensor(-46.6822, device='cuda:0')
episode: 531 training return: tensor(-60.1899, device='cuda:0')
epoch: 133 test_true_pfm: 3215.1247504572543 sim_pfm: -59.249200020276476
episode: 532 training return: tensor(-75.2804, device='cuda:0')
episode: 533 training return: tensor(39.1694, device='cuda:0')
episode: 534 training return: tensor(-46.4018, device='cuda:0')
episode: 535 training return: tensor(57.8687, device='cuda:0')
epoch: 134 test_true_pfm: 3210.0852887819206 sim_pfm: -45.41599238842415
episode: 536 training return: tensor(-51.1579, device='cuda:0')
episode: 537 training return: tensor(-74.9706, device='cuda:0')
episode: 538 training return: tensor(-50.9967, device='cuda:0')
episode: 539 training return: tensor(-61.1388, device='cuda:0')
epoch: 135 test_true_pfm: 3209.952879980907 sim_pfm: -65.37816625656949
episode: 540 training return: tensor(-370.7775, device='cuda:0')
episode: 541 training return: tensor(-43.0317, device='cuda:0')
episode: 542 training return: tensor(-50.9194, device='cuda:0')
episode: 543 training return: tensor(-68.7725, device='cuda:0')
epoch: 136 test_true_pfm: 3194.012626300528 sim_pfm: -61.71459603292169
episode: 544 training return: tensor(-69.7477, device='cuda:0')
episode: 545 training return: tensor(-57.9691, device='cuda:0')
episode: 546 training return: tensor(-74.4672, device='cuda:0')
episode: 547 training return: tensor(-101.7451, device='cuda:0')
epoch: 137 test_true_pfm: 3216.5990126260763 sim_pfm: -46.93020036874805
episode: 548 training return: tensor(-66.6025, device='cuda:0')
episode: 549 training return: tensor(-54.1604, device='cuda:0')
episode: 550 training return: tensor(-23.7983, device='cuda:0')
episode: 551 training return: tensor(-44.2126, device='cuda:0')
epoch: 138 test_true_pfm: 3217.589724486807 sim_pfm: -52.01697015521737
episode: 552 training return: tensor(-99.5317, device='cuda:0')
episode: 553 training return: tensor(-77.9136, device='cuda:0')
episode: 554 training return: tensor(-32.1719, device='cuda:0')
episode: 555 training return: tensor(-399.2122, device='cuda:0')
epoch: 139 test_true_pfm: 3212.3496595291494 sim_pfm: -52.76427508197958
episode: 556 training return: tensor(-35.3194, device='cuda:0')
episode: 557 training return: tensor(-211.5369, device='cuda:0')
episode: 558 training return: tensor(-65.8011, device='cuda:0')
episode: 559 training return: tensor(-5.4823, device='cuda:0')
epoch: 140 test_true_pfm: 3221.272033498861 sim_pfm: -49.355475755272586
episode: 560 training return: tensor(-7.8390, device='cuda:0')
episode: 561 training return: tensor(-58.1919, device='cuda:0')
episode: 562 training return: tensor(-47.6769, device='cuda:0')
episode: 563 training return: tensor(-88.0498, device='cuda:0')
epoch: 141 test_true_pfm: 3204.4414179294067 sim_pfm: -53.84072923364389
episode: 564 training return: tensor(-44.5066, device='cuda:0')
episode: 565 training return: tensor(-43.8500, device='cuda:0')
episode: 566 training return: tensor(-50.9997, device='cuda:0')
episode: 567 training return: tensor(-64.1424, device='cuda:0')
epoch: 142 test_true_pfm: 3203.3568305449967 sim_pfm: -62.948382949155835
episode: 568 training return: tensor(-60.8184, device='cuda:0')
episode: 569 training return: tensor(-54.2197, device='cuda:0')
episode: 570 training return: tensor(-72.7506, device='cuda:0')
episode: 571 training return: tensor(-393.2047, device='cuda:0')
epoch: 143 test_true_pfm: 3199.4520022949855 sim_pfm: -56.07516730829957
episode: 572 training return: tensor(74.3635, device='cuda:0')
episode: 573 training return: tensor(-59.6858, device='cuda:0')
episode: 574 training return: tensor(-598.8228, device='cuda:0')
episode: 575 training return: tensor(-66.9372, device='cuda:0')
epoch: 144 test_true_pfm: 3267.027883883564 sim_pfm: -50.782323343698714
episode: 576 training return: tensor(-67.4523, device='cuda:0')
episode: 577 training return: tensor(-543.2195, device='cuda:0')
episode: 578 training return: tensor(-211.7702, device='cuda:0')
episode: 579 training return: tensor(-47.4625, device='cuda:0')
epoch: 145 test_true_pfm: 3223.5872160443832 sim_pfm: -43.515757187483054
episode: 580 training return: tensor(-64.9409, device='cuda:0')
episode: 581 training return: tensor(-50.3780, device='cuda:0')
episode: 582 training return: tensor(-50.6924, device='cuda:0')
episode: 583 training return: tensor(-78.0390, device='cuda:0')
epoch: 146 test_true_pfm: 3208.073601566362 sim_pfm: -62.600442023472475
episode: 584 training return: tensor(-213.2736, device='cuda:0')
episode: 585 training return: tensor(-656.5219, device='cuda:0')
episode: 586 training return: tensor(-15.8213, device='cuda:0')
episode: 587 training return: tensor(-609.5795, device='cuda:0')
epoch: 147 test_true_pfm: 3219.35935044439 sim_pfm: -54.21347956267224
episode: 588 training return: tensor(-67.0650, device='cuda:0')
episode: 589 training return: tensor(-264.8596, device='cuda:0')
episode: 590 training return: tensor(-37.2094, device='cuda:0')
episode: 591 training return: tensor(-65.8413, device='cuda:0')
epoch: 148 test_true_pfm: 3224.7745562763043 sim_pfm: -50.015193707775325
episode: 592 training return: tensor(-51.8038, device='cuda:0')
episode: 593 training return: tensor(-364.9414, device='cuda:0')
episode: 594 training return: tensor(-80.6383, device='cuda:0')
episode: 595 training return: tensor(-80.3728, device='cuda:0')
epoch: 149 test_true_pfm: 3217.003098347825 sim_pfm: -47.76006928298739
episode: 596 training return: tensor(-46.0814, device='cuda:0')
episode: 597 training return: tensor(-33.0247, device='cuda:0')
episode: 598 training return: tensor(-41.4506, device='cuda:0')
episode: 599 training return: tensor(-64.2033, device='cuda:0')
epoch: 150 test_true_pfm: 3220.8767119477507 sim_pfm: -47.817673969305666
