['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'behavior', '--traj', 'medium', '--seed', '1']
epoch: 0 training_loss 0.3367242787778377 test_loss: 0.22566256523132325
epoch: 1 training_loss 0.18769134201109408 test_loss: 0.145656955242157
epoch: 2 training_loss 0.1485973445698619 test_loss: 0.12953585386276245
epoch: 3 training_loss 0.1339460064470768 test_loss: 0.13868122100830077
epoch: 4 training_loss 0.1210758213698864 test_loss: 0.13555877208709716
epoch: 5 training_loss 0.12701871156692504 test_loss: 0.1266351819038391
epoch: 6 training_loss 0.11314464379101992 test_loss: 0.13776427507400513
epoch: 7 training_loss 0.1186635209992528 test_loss: 0.1468616843223572
epoch: 8 training_loss 0.11942229501903057 test_loss: 0.11884140968322754
epoch: 9 training_loss 0.10519335983321071 test_loss: 0.1246860146522522
epoch: 10 training_loss 0.11892547195777298 test_loss: 0.12086341381072999
epoch: 11 training_loss 0.10773477155715228 test_loss: 0.11003108024597168
epoch: 12 training_loss 0.11481805175542831 test_loss: 0.12121309041976928
epoch: 13 training_loss 0.11286733692511916 test_loss: 0.11685774326324463
epoch: 14 training_loss 0.10774207677692176 test_loss: 0.11313831806182861
epoch: 15 training_loss 0.10806437749415636 test_loss: 0.1258350133895874
epoch: 16 training_loss 0.10876698795706034 test_loss: 0.10179295539855956
epoch: 17 training_loss 0.11531437277793884 test_loss: 0.11167892217636108
epoch: 18 training_loss 0.102981579862535 test_loss: 0.11697605848312378
epoch: 19 training_loss 0.11486857766285538 test_loss: 0.11738278865814208
epoch: 20 training_loss 0.11043847478926182 test_loss: 0.11651217937469482
epoch: 21 training_loss 0.11298558309674263 test_loss: 0.1034575343132019
epoch: 22 training_loss 0.10767320618033409 test_loss: 0.10063283443450928
epoch: 23 training_loss 0.10528019262477756 test_loss: 0.12018328905105591
epoch: 24 training_loss 0.1164942704513669 test_loss: 0.11525402069091797
epoch: 25 training_loss 0.1099578750692308 test_loss: 0.10405057668685913
epoch: 26 training_loss 0.11409260036423802 test_loss: 0.09711869359016419
epoch: 27 training_loss 0.10883094862103462 test_loss: 0.1040846586227417
epoch: 28 training_loss 0.10530186641961337 test_loss: 0.12744466066360474
epoch: 29 training_loss 0.11787627816200257 test_loss: 0.11932640075683594
epoch: 30 training_loss 0.10980679556727409 test_loss: 0.12137362957000733
epoch: 31 training_loss 0.11089620288461446 test_loss: 0.1048957109451294
epoch: 32 training_loss 0.10254725961014628 test_loss: 0.13156189918518066
epoch: 33 training_loss 0.10877137668430806 test_loss: 0.11461255550384522
epoch: 34 training_loss 0.10187485724687577 test_loss: 0.13101168870925903
epoch: 35 training_loss 0.104808589220047 test_loss: 0.11809920072555542
epoch: 36 training_loss 0.1123425724543631 test_loss: 0.1329314589500427
epoch: 37 training_loss 0.10476222723722457 test_loss: 0.11688488721847534
epoch: 38 training_loss 0.10485484441742302 test_loss: 0.09797880649566651
epoch: 39 training_loss 0.10271295430138708 test_loss: 0.12054263353347779
epoch: 40 training_loss 0.10904479846358299 test_loss: 0.12587581872940062
epoch: 41 training_loss 0.11172049574553966 test_loss: 0.13003628253936766
epoch: 42 training_loss 0.11162651170045138 test_loss: 0.10832178592681885
epoch: 43 training_loss 0.1071273049339652 test_loss: 0.10928956270217896
epoch: 44 training_loss 0.10317385707050562 test_loss: 0.12209150791168213
epoch: 45 training_loss 0.10581650083884597 test_loss: 0.1290485978126526
epoch: 46 training_loss 0.11031214624643326 test_loss: 0.11685007810592651
epoch: 47 training_loss 0.11099825326353312 test_loss: 0.11044312715530395
epoch: 48 training_loss 0.1018679017573595 test_loss: 0.11488809585571289
epoch: 49 training_loss 0.102399838604033 test_loss: 0.13358557224273682
epoch: 50 training_loss 0.1116157508455217 test_loss: 0.12932698726654052
epoch: 51 training_loss 0.09711764460429549 test_loss: 0.11066533327102661
epoch: 52 training_loss 0.10395668063312768 test_loss: 0.10358831882476807
epoch: 53 training_loss 0.1076478748396039 test_loss: 0.11384040117263794
epoch: 54 training_loss 0.11008164219558239 test_loss: 0.12102867364883423
epoch: 55 training_loss 0.1054243041574955 test_loss: 0.09641412496566773
epoch: 56 training_loss 0.10523452492430806 test_loss: 0.10251063108444214
epoch: 57 training_loss 0.10588680937886238 test_loss: 0.10810182094573975
epoch: 58 training_loss 0.1004041322786361 test_loss: 0.12137277126312256
epoch: 59 training_loss 0.10639999203383922 test_loss: 0.10203777551651001
epoch: 60 training_loss 0.10644799945876002 test_loss: 0.10576260089874268
epoch: 61 training_loss 0.09345273388549685 test_loss: 0.10418133735656739
epoch: 62 training_loss 0.09151799546554684 test_loss: 0.10132546424865722
epoch: 63 training_loss 0.10482866786420346 test_loss: 0.10548478364944458
epoch: 64 training_loss 0.10803309487178922 test_loss: 0.10352625846862792
epoch: 65 training_loss 0.10415199372917414 test_loss: 0.10743751525878906
epoch: 66 training_loss 0.10736492302268744 test_loss: 0.11976484060287476
epoch: 67 training_loss 0.10813217002898455 test_loss: 0.11238166093826293
epoch: 68 training_loss 0.1017322206683457 test_loss: 0.1077282190322876
epoch: 69 training_loss 0.11134551089257001 test_loss: 0.12851229906082154
epoch: 70 training_loss 0.11096251398324966 test_loss: 0.115951669216156
epoch: 71 training_loss 0.10051313985139132 test_loss: 0.11008607149124146
epoch: 72 training_loss 0.10519273245707154 test_loss: 0.08993680477142334
epoch: 73 training_loss 0.10923847001045943 test_loss: 0.11421091556549072
epoch: 74 training_loss 0.10617789039388299 test_loss: 0.10931806564331055
epoch: 75 training_loss 0.10748911734670401 test_loss: 0.1065556526184082
epoch: 76 training_loss 0.10424839492887258 test_loss: 0.09086658358573914
epoch: 77 training_loss 0.10001114033162593 test_loss: 0.11619681119918823
epoch: 78 training_loss 0.10956968266516924 test_loss: 0.1133270263671875
epoch: 79 training_loss 0.10034970130771398 test_loss: 0.09755256175994872
epoch: 80 training_loss 0.10089215265586972 test_loss: 0.10528365373611451
epoch: 81 training_loss 0.10631742484867573 test_loss: 0.1171692967414856
epoch: 82 training_loss 0.1101157284155488 test_loss: 0.11231397390365601
epoch: 83 training_loss 0.10594055410474539 test_loss: 0.11480547189712524
epoch: 84 training_loss 0.10654666721820831 test_loss: 0.1225389838218689
epoch: 85 training_loss 0.10684367239475251 test_loss: 0.1032234787940979
epoch: 86 training_loss 0.10595065385103225 test_loss: 0.11634668111801147
epoch: 87 training_loss 0.10054831624031067 test_loss: 0.11414786577224731
epoch: 88 training_loss 0.1000420442968607 test_loss: 0.10875203609466552
epoch: 89 training_loss 0.10890053860843181 test_loss: 0.11361644268035889
epoch: 90 training_loss 0.10095199810341 test_loss: 0.1111185908317566
epoch: 91 training_loss 0.10600350165739655 test_loss: 0.11428052186965942
epoch: 92 training_loss 0.11552854970097542 test_loss: 0.11029043197631835
epoch: 93 training_loss 0.09963738514110446 test_loss: 0.10880272388458252
epoch: 94 training_loss 0.10333759976550937 test_loss: 0.11683857440948486
epoch: 95 training_loss 0.10144655102863907 test_loss: 0.11404823064804077
epoch: 96 training_loss 0.09795155350118875 test_loss: 0.12405297756195069
epoch: 97 training_loss 0.09904266642406583 test_loss: 0.10607765913009644
epoch: 98 training_loss 0.0979647177271545 test_loss: 0.11028716564178467
epoch: 99 training_loss 0.09475562490522861 test_loss: 0.09010238647460937
epoch: 100 training_loss 0.11239204429090023 test_loss: 0.10358082056045533
epoch: 101 training_loss 0.10952185124158859 test_loss: 0.12425144910812377
epoch: 102 training_loss 0.09896623883396387 test_loss: 0.12156519889831544
epoch: 103 training_loss 0.10494299065321684 test_loss: 0.1212857723236084
epoch: 104 training_loss 0.09786084460094571 test_loss: 0.10897021293640137
epoch: 105 training_loss 0.10284835096448659 test_loss: 0.10389240980148315
epoch: 106 training_loss 0.09991570301353932 test_loss: 0.10283609628677368
epoch: 107 training_loss 0.1038644720800221 test_loss: 0.10440316200256347
epoch: 108 training_loss 0.10050168514251709 test_loss: 0.11383990049362183
epoch: 109 training_loss 0.11053591459989548 test_loss: 0.11953210830688477
epoch: 110 training_loss 0.09482294384390116 test_loss: 0.10831201076507568
epoch: 111 training_loss 0.10617092890664935 test_loss: 0.13397244215011597
epoch: 112 training_loss 0.10695363637059926 test_loss: 0.10664805173873901
epoch: 113 training_loss 0.10552494183182716 test_loss: 0.1193386197090149
epoch: 114 training_loss 0.09482874518260359 test_loss: 0.10778011083602905
epoch: 115 training_loss 0.10433830004185438 test_loss: 0.10457139015197754
epoch: 116 training_loss 0.10934355273842812 test_loss: 0.10725853443145753
epoch: 117 training_loss 0.09997226364910602 test_loss: 0.09296318888664246
epoch: 118 training_loss 0.10100308518856764 test_loss: 0.11772075891494752
epoch: 119 training_loss 0.10962688252329826 test_loss: 0.11415449380874634
epoch: 120 training_loss 0.10256865311414004 test_loss: 0.11546331644058228
epoch: 121 training_loss 0.1055541799031198 test_loss: 0.09836764335632324
epoch: 122 training_loss 0.09959835167974233 test_loss: 0.12417804002761841
epoch: 123 training_loss 0.10260108228772878 test_loss: 0.12464964389801025
epoch: 124 training_loss 0.10484914407134056 test_loss: 0.10025354623794555
epoch: 125 training_loss 0.1044124860689044 test_loss: 0.10456048250198365
epoch: 126 training_loss 0.10687014248222113 test_loss: 0.09062466621398926
epoch: 127 training_loss 0.1052637830004096 test_loss: 0.10584403276443481
epoch: 128 training_loss 0.10279974866658449 test_loss: 0.11023424863815308
epoch: 129 training_loss 0.1123351139947772 test_loss: 0.11511451005935669
epoch: 130 training_loss 0.10219132153317333 test_loss: 0.09970554113388061
epoch: 131 training_loss 0.10110977835953236 test_loss: 0.10580122470855713
epoch: 132 training_loss 0.10379954196512699 test_loss: 0.10325026512145996
epoch: 133 training_loss 0.10085660541430115 test_loss: 0.11255731582641601
epoch: 134 training_loss 0.10675561964511872 test_loss: 0.1116781234741211
epoch: 135 training_loss 0.09863511804491282 test_loss: 0.09905433654785156
epoch: 136 training_loss 0.09608146168291569 test_loss: 0.10602477788925171
epoch: 137 training_loss 0.1010844380222261 test_loss: 0.0955138385295868
epoch: 138 training_loss 0.10653169371187687 test_loss: 0.11143049001693725
epoch: 139 training_loss 0.10782481459900736 test_loss: 0.0964114487171173
epoch: 140 training_loss 0.10348292013630271 test_loss: 0.12139965295791626
epoch: 141 training_loss 0.10315395263954998 test_loss: 0.12458525896072388
epoch: 142 training_loss 0.10800403464585542 test_loss: 0.11314330101013184
epoch: 143 training_loss 0.10779093869030476 test_loss: 0.10588769912719727
epoch: 144 training_loss 0.10132965121418237 test_loss: 0.1123877763748169
epoch: 145 training_loss 0.09687530739232898 test_loss: 0.12148411273956299
epoch: 146 training_loss 0.09747018534690141 test_loss: 0.09255265593528747
epoch: 147 training_loss 0.104820999186486 test_loss: 0.12270232439041137
epoch: 148 training_loss 0.09450108217075467 test_loss: 0.11522489786148071
epoch: 149 training_loss 0.09996690042316914 test_loss: 0.1143985390663147
epoch: 0 training_loss 49.462422428131106 test_loss: 23.969204711914063
epoch: 1 training_loss 17.9213192653656 test_loss: 14.453288269042968
epoch: 2 training_loss 12.635671863555908 test_loss: 11.398911285400391
epoch: 3 training_loss 10.038336906433106 test_loss: 9.180382537841798
epoch: 4 training_loss 8.479770355224609 test_loss: 8.074321746826172
epoch: 5 training_loss 7.35941333770752 test_loss: 6.869712066650391
epoch: 6 training_loss 6.425046396255493 test_loss: 6.1227680206298825
epoch: 7 training_loss 5.817634358406067 test_loss: 5.438772583007813
epoch: 8 training_loss 5.351050524711609 test_loss: 5.4483386993408205
epoch: 9 training_loss 4.852876591682434 test_loss: 4.683091735839843
epoch: 10 training_loss 4.5143804621696475 test_loss: 4.336931228637695
epoch: 11 training_loss 4.258502018451691 test_loss: 4.158733749389649
epoch: 12 training_loss 4.024155261516571 test_loss: 3.955948257446289
epoch: 13 training_loss 3.8206158232688905 test_loss: 3.8394115447998045
epoch: 14 training_loss 3.6950383043289183 test_loss: 3.617047882080078
epoch: 15 training_loss 3.555590455532074 test_loss: 3.515528106689453
epoch: 16 training_loss 3.3578004336357115 test_loss: 3.3229774475097655
epoch: 17 training_loss 3.307389397621155 test_loss: 3.349063491821289
epoch: 18 training_loss 3.142108178138733 test_loss: 3.049406051635742
epoch: 19 training_loss 3.1175798106193544 test_loss: 2.9221271514892577
epoch: 20 training_loss 3.052013397216797 test_loss: 2.871004104614258
epoch: 21 training_loss 2.9921961426734924 test_loss: 3.0346851348876953
epoch: 22 training_loss 2.8798789191246033 test_loss: 3.0101179122924804
epoch: 23 training_loss 2.8145056843757628 test_loss: 2.835769271850586
epoch: 24 training_loss 2.735152013301849 test_loss: 2.731964874267578
epoch: 25 training_loss 2.714118275642395 test_loss: 2.7055219650268554
epoch: 26 training_loss 2.6452916073799133 test_loss: 2.5684507369995115
epoch: 27 training_loss 2.52596675157547 test_loss: 2.5722164154052733
epoch: 28 training_loss 2.530740692615509 test_loss: 2.6301769256591796
epoch: 29 training_loss 2.502196924686432 test_loss: 2.494197463989258
epoch: 30 training_loss 2.4785170412063597 test_loss: 2.332358169555664
epoch: 31 training_loss 2.3985759377479554 test_loss: 2.412174415588379
epoch: 32 training_loss 2.393357963562012 test_loss: 2.429448127746582
epoch: 33 training_loss 2.313898446559906 test_loss: 2.2595510482788086
epoch: 34 training_loss 2.3020506072044373 test_loss: 2.2420597076416016
epoch: 35 training_loss 2.3544184362888334 test_loss: 2.2967933654785155
epoch: 36 training_loss 2.2331950342655182 test_loss: 2.3942676544189454
epoch: 37 training_loss 2.1886284160614013 test_loss: 2.3272613525390624
epoch: 38 training_loss 2.2006361854076384 test_loss: 2.249029350280762
epoch: 39 training_loss 2.223965995311737 test_loss: 2.1286102294921876
epoch: 40 training_loss 2.1420373022556305 test_loss: 2.1484060287475586
epoch: 41 training_loss 2.112720794677734 test_loss: 2.0966726303100587
epoch: 42 training_loss 2.066412148475647 test_loss: 2.088410758972168
epoch: 43 training_loss 2.066520553827286 test_loss: 2.0511381149291994
epoch: 44 training_loss 2.064080888032913 test_loss: 2.0486984252929688
epoch: 45 training_loss 2.023815596103668 test_loss: 2.069356918334961
epoch: 46 training_loss 2.0428100383281707 test_loss: 2.0349943161010744
epoch: 47 training_loss 2.0391811573505403 test_loss: 2.003998947143555
epoch: 48 training_loss 1.9909882986545562 test_loss: 1.9945188522338868
epoch: 49 training_loss 2.0113513648509977 test_loss: 2.0010612487792967
epoch: 50 training_loss 1.9659981667995452 test_loss: 2.0566892623901367
epoch: 51 training_loss 1.9552241659164429 test_loss: 1.9610260009765625
epoch: 52 training_loss 1.946657165288925 test_loss: 1.9206899642944335
epoch: 53 training_loss 1.907090892791748 test_loss: 1.9950521469116211
epoch: 54 training_loss 1.8763048994541167 test_loss: 1.9204336166381837
epoch: 55 training_loss 1.914345419406891 test_loss: 1.852817916870117
epoch: 56 training_loss 1.8715932142734528 test_loss: 1.8720769882202148
epoch: 57 training_loss 1.876882528066635 test_loss: 1.8478296279907227
epoch: 58 training_loss 1.8705869925022125 test_loss: 1.8676017761230468
epoch: 59 training_loss 1.8302358019351959 test_loss: 1.8493741989135741
epoch: 60 training_loss 1.8195664298534393 test_loss: 1.8713874816894531
epoch: 61 training_loss 1.8253062224388124 test_loss: 1.8848316192626953
epoch: 62 training_loss 1.8206183576583863 test_loss: 1.8009273529052734
epoch: 63 training_loss 1.8158835923671723 test_loss: 1.7732172012329102
epoch: 64 training_loss 1.801567384004593 test_loss: 1.8526342391967774
epoch: 65 training_loss 1.806592833995819 test_loss: 1.8752328872680664
epoch: 66 training_loss 1.8089331376552582 test_loss: 1.7304920196533202
epoch: 67 training_loss 1.7598803508281708 test_loss: 1.8079553604125977
epoch: 68 training_loss 1.7652818763256073 test_loss: 1.7998516082763671
epoch: 69 training_loss 1.7284363424777984 test_loss: 1.7769920349121093
epoch: 70 training_loss 1.7452167320251464 test_loss: 1.7620357513427733
epoch: 71 training_loss 1.7201360845565796 test_loss: 1.7631763458251952
epoch: 72 training_loss 1.754082326889038 test_loss: 1.7211219787597656
epoch: 73 training_loss 1.6933643627166748 test_loss: 1.6957063674926758
epoch: 74 training_loss 1.717554737329483 test_loss: 1.723887825012207
epoch: 75 training_loss 1.7003668975830077 test_loss: 1.7638105392456054
epoch: 76 training_loss 1.720994122028351 test_loss: 1.7358589172363281
epoch: 77 training_loss 1.7136037099361419 test_loss: 1.702263069152832
epoch: 78 training_loss 1.6801854825019837 test_loss: 1.710338020324707
epoch: 79 training_loss 1.671138302087784 test_loss: 1.6751371383666993
epoch: 80 training_loss 1.6555458629131317 test_loss: 1.6863595962524414
epoch: 81 training_loss 1.6742059624195098 test_loss: 1.6475921630859376
epoch: 82 training_loss 1.6559731137752534 test_loss: 1.6598520278930664
epoch: 83 training_loss 1.6512290263175964 test_loss: 1.6147478103637696
epoch: 84 training_loss 1.6657299780845642 test_loss: 1.668766975402832
epoch: 85 training_loss 1.6388678741455078 test_loss: 1.6657623291015624
epoch: 86 training_loss 1.6427213287353515 test_loss: 1.6254079818725586
epoch: 87 training_loss 1.6315103077888489 test_loss: 1.6570547103881836
epoch: 88 training_loss 1.6433084225654602 test_loss: 1.6897546768188476
epoch: 89 training_loss 1.6369661366939545 test_loss: 1.664788055419922
epoch: 90 training_loss 1.620428112745285 test_loss: 1.6150751113891602
epoch: 91 training_loss 1.5882350325584411 test_loss: 1.583311176300049
epoch: 92 training_loss 1.6066411209106446 test_loss: 1.5556134223937987
epoch: 93 training_loss 1.6137136113643646 test_loss: 1.688123893737793
epoch: 94 training_loss 1.6084722042083741 test_loss: 1.5876786231994628
epoch: 95 training_loss 1.6070172691345215 test_loss: 1.5941938400268554
epoch: 96 training_loss 1.5718117833137513 test_loss: 1.5747276306152345
epoch: 97 training_loss 1.5929991757869721 test_loss: 1.6020517349243164
epoch: 98 training_loss 1.5812361061573028 test_loss: 1.537026596069336
epoch: 99 training_loss 1.592607445716858 test_loss: 1.614997673034668
epoch: 100 training_loss 1.5793805372714997 test_loss: 1.5556139945983887
epoch: 101 training_loss 1.5736838495731353 test_loss: 1.5585689544677734
epoch: 102 training_loss 1.5597985672950745 test_loss: 1.633797836303711
epoch: 103 training_loss 1.5463408041000366 test_loss: 1.584686851501465
epoch: 104 training_loss 1.5785047423839569 test_loss: 1.5381525993347167
epoch: 105 training_loss 1.5400422155857085 test_loss: 1.5735583305358887
epoch: 106 training_loss 1.5518519568443299 test_loss: 1.5410567283630372
epoch: 107 training_loss 1.570656361579895 test_loss: 1.5164201736450196
epoch: 108 training_loss 1.5631243360042573 test_loss: 1.5115973472595214
epoch: 109 training_loss 1.5532422804832458 test_loss: 1.5820879936218262
epoch: 110 training_loss 1.5138408637046814 test_loss: 1.527241039276123
epoch: 111 training_loss 1.5449540436267852 test_loss: 1.578031349182129
epoch: 112 training_loss 1.5255714237689972 test_loss: 1.526323413848877
epoch: 113 training_loss 1.5276802241802216 test_loss: 1.512826156616211
epoch: 114 training_loss 1.5204561758041382 test_loss: 1.5089465141296388
epoch: 115 training_loss 1.4949695229530335 test_loss: 1.5000075340270995
epoch: 116 training_loss 1.5394725918769836 test_loss: 1.5275056838989258
epoch: 117 training_loss 1.5252729892730712 test_loss: 1.5316296577453614
epoch: 118 training_loss 1.504293565750122 test_loss: 1.5138652801513672
epoch: 119 training_loss 1.5332454323768616 test_loss: 1.4694050788879394
epoch: 120 training_loss 1.5016942846775054 test_loss: 1.4912353515625
epoch: 121 training_loss 1.4901971518993378 test_loss: 1.471419906616211
epoch: 122 training_loss 1.5100854218006134 test_loss: 1.511159324645996
epoch: 123 training_loss 1.4866402554512024 test_loss: 1.5292902946472169
epoch: 124 training_loss 1.4870282888412476 test_loss: 1.4840663909912108
epoch: 125 training_loss 1.4927261197566986 test_loss: 1.511131763458252
epoch: 126 training_loss 1.4841449534893036 test_loss: 1.4996673583984375
epoch: 127 training_loss 1.4841184759140014 test_loss: 1.487581729888916
epoch: 128 training_loss 1.4996715652942658 test_loss: 1.475202751159668
epoch: 129 training_loss 1.477577178478241 test_loss: 1.5259875297546386
epoch: 130 training_loss 1.497672324180603 test_loss: 1.4801787376403808
epoch: 131 training_loss 1.4702619302272797 test_loss: 1.4811788558959962
epoch: 132 training_loss 1.4873399341106415 test_loss: 1.4479990005493164
epoch: 133 training_loss 1.4684290146827699 test_loss: 1.4939543724060058
epoch: 134 training_loss 1.4798526859283447 test_loss: 1.490338134765625
epoch: 135 training_loss 1.4818580961227417 test_loss: 1.479915237426758
epoch: 136 training_loss 1.4798168182373046 test_loss: 1.4443381309509278
epoch: 137 training_loss 1.485910336971283 test_loss: 1.4703824996948243
epoch: 138 training_loss 1.4308471989631653 test_loss: 1.4564111709594727
epoch: 139 training_loss 1.4481263315677644 test_loss: 1.4828139305114747
epoch: 140 training_loss 1.4425492334365844 test_loss: 1.4586627006530761
epoch: 141 training_loss 1.4653568816184999 test_loss: 1.4227045059204102
epoch: 142 training_loss 1.4336824023723602 test_loss: 1.496830368041992
epoch: 143 training_loss 1.4562845981121064 test_loss: 1.4831835746765136
epoch: 144 training_loss 1.4874568474292755 test_loss: 1.4528785705566407
epoch: 145 training_loss 1.4328506624698638 test_loss: 1.437009048461914
epoch: 146 training_loss 1.4369125711917876 test_loss: 1.4757803916931151
epoch: 147 training_loss 1.4499969255924225 test_loss: 1.5237796783447266
epoch: 148 training_loss 1.4219220447540284 test_loss: 1.4446128845214843
epoch: 149 training_loss 1.4259765100479127 test_loss: 1.4514233589172363
5073.857374889093
episode: 0 training return: tensor(35.9751, device='cuda:0')
episode: 1 training return: tensor(53.8153, device='cuda:0')
episode: 2 training return: tensor(9.1949, device='cuda:0')
episode: 3 training return: tensor(-45.6408, device='cuda:0')
epoch: 1 test_true_pfm: 5020.11423388694 sim_pfm: 48.13485678446401
episode: 4 training return: tensor(-42.6967, device='cuda:0')
episode: 5 training return: tensor(-59.9072, device='cuda:0')
episode: 6 training return: tensor(-22.3690, device='cuda:0')
episode: 7 training return: tensor(16.6103, device='cuda:0')
epoch: 2 test_true_pfm: 4960.108135053087 sim_pfm: 22.875647223282915
episode: 8 training return: tensor(1.5270, device='cuda:0')
episode: 9 training return: tensor(29.0731, device='cuda:0')
episode: 10 training return: tensor(-27.5956, device='cuda:0')
episode: 11 training return: tensor(-9.9749, device='cuda:0')
epoch: 3 test_true_pfm: 5099.442267382753 sim_pfm: 50.68830560784166
episode: 12 training return: tensor(-253.1766, device='cuda:0')
episode: 13 training return: tensor(-51.7185, device='cuda:0')
episode: 14 training return: tensor(50.0327, device='cuda:0')
episode: 15 training return: tensor(-83.0627, device='cuda:0')
epoch: 4 test_true_pfm: 4956.152372333451 sim_pfm: 44.81885658375298
episode: 16 training return: tensor(-26.6776, device='cuda:0')
episode: 17 training return: tensor(-0.1774, device='cuda:0')
episode: 18 training return: tensor(19.1842, device='cuda:0')
episode: 19 training return: tensor(116.2059, device='cuda:0')
epoch: 5 test_true_pfm: 5166.049519154431 sim_pfm: 105.87275989485595
episode: 20 training return: tensor(-54.9378, device='cuda:0')
episode: 21 training return: tensor(-88.3341, device='cuda:0')
episode: 22 training return: tensor(21.0916, device='cuda:0')
episode: 23 training return: tensor(-5.2670, device='cuda:0')
epoch: 6 test_true_pfm: 5135.657698846276 sim_pfm: 87.35865221502415
episode: 24 training return: tensor(-10.7265, device='cuda:0')
episode: 25 training return: tensor(8.1648, device='cuda:0')
episode: 26 training return: tensor(17.2730, device='cuda:0')
episode: 27 training return: tensor(112.2715, device='cuda:0')
epoch: 7 test_true_pfm: 5122.169968656769 sim_pfm: 104.09266447206998
episode: 28 training return: tensor(16.6644, device='cuda:0')
episode: 29 training return: tensor(97.6374, device='cuda:0')
episode: 30 training return: tensor(64.7691, device='cuda:0')
episode: 31 training return: tensor(-451.3974, device='cuda:0')
epoch: 8 test_true_pfm: 5177.765755664262 sim_pfm: 91.49142667197157
episode: 32 training return: tensor(3.2633, device='cuda:0')
episode: 33 training return: tensor(53.3268, device='cuda:0')
episode: 34 training return: tensor(30.3450, device='cuda:0')
episode: 35 training return: tensor(146.7196, device='cuda:0')
epoch: 9 test_true_pfm: 5158.997414239249 sim_pfm: 124.66723719296472
episode: 36 training return: tensor(-14.1800, device='cuda:0')
episode: 37 training return: tensor(14.8132, device='cuda:0')
episode: 38 training return: tensor(130.1102, device='cuda:0')
episode: 39 training return: tensor(56.7882, device='cuda:0')
epoch: 10 test_true_pfm: 5186.16387759554 sim_pfm: 146.39107331751924
episode: 40 training return: tensor(85.1763, device='cuda:0')
episode: 41 training return: tensor(34.0607, device='cuda:0')
episode: 42 training return: tensor(70.3742, device='cuda:0')
episode: 43 training return: tensor(197.0265, device='cuda:0')
epoch: 11 test_true_pfm: 5291.683473656251 sim_pfm: 141.14138911288077
episode: 44 training return: tensor(72.5064, device='cuda:0')
episode: 45 training return: tensor(-8.3567, device='cuda:0')
episode: 46 training return: tensor(127.4184, device='cuda:0')
episode: 47 training return: tensor(133.0217, device='cuda:0')
epoch: 12 test_true_pfm: 5243.824749664236 sim_pfm: 164.50776951496178
episode: 48 training return: tensor(92.6130, device='cuda:0')
episode: 49 training return: tensor(-26.1083, device='cuda:0')
episode: 50 training return: tensor(116.0426, device='cuda:0')
episode: 51 training return: tensor(38.2383, device='cuda:0')
epoch: 13 test_true_pfm: 5358.3296840444145 sim_pfm: 107.77120351489673
episode: 52 training return: tensor(18.2056, device='cuda:0')
episode: 53 training return: tensor(-21.7028, device='cuda:0')
episode: 54 training return: tensor(80.1105, device='cuda:0')
episode: 55 training return: tensor(200.5035, device='cuda:0')
epoch: 14 test_true_pfm: 5306.43322949062 sim_pfm: 168.23860882711597
episode: 56 training return: tensor(83.0757, device='cuda:0')
episode: 57 training return: tensor(143.8313, device='cuda:0')
episode: 58 training return: tensor(67.4509, device='cuda:0')
episode: 59 training return: tensor(209.7998, device='cuda:0')
epoch: 15 test_true_pfm: 5163.923751928688 sim_pfm: 225.6302593195578
episode: 60 training return: tensor(-26.5593, device='cuda:0')
episode: 61 training return: tensor(-13.7075, device='cuda:0')
episode: 62 training return: tensor(126.4236, device='cuda:0')
episode: 63 training return: tensor(103.9217, device='cuda:0')
epoch: 16 test_true_pfm: 5171.301882440363 sim_pfm: 184.76754321857393
episode: 64 training return: tensor(124.9231, device='cuda:0')
episode: 65 training return: tensor(96.0193, device='cuda:0')
episode: 66 training return: tensor(44.1934, device='cuda:0')
episode: 67 training return: tensor(110.7263, device='cuda:0')
epoch: 17 test_true_pfm: 5220.475829007089 sim_pfm: 192.98976035714927
episode: 68 training return: tensor(164.3384, device='cuda:0')
episode: 69 training return: tensor(34.8722, device='cuda:0')
episode: 70 training return: tensor(34.6920, device='cuda:0')
episode: 71 training return: tensor(179.5424, device='cuda:0')
epoch: 18 test_true_pfm: 5309.945734575766 sim_pfm: 210.21930583942836
episode: 72 training return: tensor(76.0831, device='cuda:0')
episode: 73 training return: tensor(190.2402, device='cuda:0')
episode: 74 training return: tensor(103.2163, device='cuda:0')
episode: 75 training return: tensor(48.1314, device='cuda:0')
epoch: 19 test_true_pfm: 5404.950830825502 sim_pfm: 163.49147542380766
episode: 76 training return: tensor(100.9482, device='cuda:0')
episode: 77 training return: tensor(49.4679, device='cuda:0')
episode: 78 training return: tensor(165.8890, device='cuda:0')
episode: 79 training return: tensor(97.6339, device='cuda:0')
epoch: 20 test_true_pfm: 5255.342666405409 sim_pfm: 273.7296902157347
episode: 80 training return: tensor(173.3846, device='cuda:0')
episode: 81 training return: tensor(41.5674, device='cuda:0')
episode: 82 training return: tensor(198.8703, device='cuda:0')
episode: 83 training return: tensor(21.4370, device='cuda:0')
epoch: 21 test_true_pfm: 5339.319781080893 sim_pfm: -154.83682207751554
episode: 84 training return: tensor(76.5593, device='cuda:0')
episode: 85 training return: tensor(164.0178, device='cuda:0')
episode: 86 training return: tensor(172.8677, device='cuda:0')
episode: 87 training return: tensor(107.6614, device='cuda:0')
epoch: 22 test_true_pfm: 5193.133111131617 sim_pfm: 242.49891214629557
episode: 88 training return: tensor(151.2847, device='cuda:0')
episode: 89 training return: tensor(136.6311, device='cuda:0')
episode: 90 training return: tensor(149.4208, device='cuda:0')
episode: 91 training return: tensor(85.1757, device='cuda:0')
epoch: 23 test_true_pfm: 5351.30006993076 sim_pfm: 224.64494388046054
episode: 92 training return: tensor(93.5307, device='cuda:0')
episode: 93 training return: tensor(109.4021, device='cuda:0')
episode: 94 training return: tensor(25.5564, device='cuda:0')
episode: 95 training return: tensor(124.5465, device='cuda:0')
epoch: 24 test_true_pfm: 5262.882217652722 sim_pfm: 207.47286191082094
episode: 96 training return: tensor(146.6057, device='cuda:0')
episode: 97 training return: tensor(111.0571, device='cuda:0')
episode: 98 training return: tensor(272.9010, device='cuda:0')
episode: 99 training return: tensor(61.3238, device='cuda:0')
epoch: 25 test_true_pfm: 5306.194071443891 sim_pfm: -132.9272558967738
episode: 100 training return: tensor(209.4911, device='cuda:0')
episode: 101 training return: tensor(74.6143, device='cuda:0')
episode: 102 training return: tensor(69.5941, device='cuda:0')
episode: 103 training return: tensor(115.6965, device='cuda:0')
epoch: 26 test_true_pfm: 5418.303080610406 sim_pfm: 234.42554639865799
episode: 104 training return: tensor(178.3539, device='cuda:0')
episode: 105 training return: tensor(139.2958, device='cuda:0')
episode: 106 training return: tensor(-9.9008, device='cuda:0')
episode: 107 training return: tensor(159.9956, device='cuda:0')
epoch: 27 test_true_pfm: 5347.532376653208 sim_pfm: 262.7141153768559
episode: 108 training return: tensor(165.3231, device='cuda:0')
episode: 109 training return: tensor(244.7559, device='cuda:0')
episode: 110 training return: tensor(102.4624, device='cuda:0')
episode: 111 training return: tensor(66.2858, device='cuda:0')
epoch: 28 test_true_pfm: 5324.890303697449 sim_pfm: 193.68622639753934
episode: 112 training return: tensor(199.1587, device='cuda:0')
episode: 113 training return: tensor(39.5257, device='cuda:0')
episode: 114 training return: tensor(168.5331, device='cuda:0')
episode: 115 training return: tensor(145.7168, device='cuda:0')
epoch: 29 test_true_pfm: 5323.050830345209 sim_pfm: 259.03242875412496
episode: 116 training return: tensor(54.0639, device='cuda:0')
episode: 117 training return: tensor(94.3499, device='cuda:0')
episode: 118 training return: tensor(40.1525, device='cuda:0')
episode: 119 training return: tensor(92.1961, device='cuda:0')
epoch: 30 test_true_pfm: 5370.15201608352 sim_pfm: 265.9031835276789
episode: 120 training return: tensor(102.0363, device='cuda:0')
episode: 121 training return: tensor(217.7702, device='cuda:0')
episode: 122 training return: tensor(152.5874, device='cuda:0')
episode: 123 training return: tensor(150.2897, device='cuda:0')
epoch: 31 test_true_pfm: 5354.819265981104 sim_pfm: 247.5835109926993
episode: 124 training return: tensor(215.7936, device='cuda:0')
episode: 125 training return: tensor(186.6026, device='cuda:0')
episode: 126 training return: tensor(38.2257, device='cuda:0')
episode: 127 training return: tensor(128.9313, device='cuda:0')
epoch: 32 test_true_pfm: 5463.75240085769 sim_pfm: 250.86744290514616
episode: 128 training return: tensor(119.7915, device='cuda:0')
episode: 129 training return: tensor(196.3691, device='cuda:0')
episode: 130 training return: tensor(189.5681, device='cuda:0')
episode: 131 training return: tensor(76.8253, device='cuda:0')
epoch: 33 test_true_pfm: 3819.492873404259 sim_pfm: 276.610256797896
episode: 132 training return: tensor(183.6678, device='cuda:0')
episode: 133 training return: tensor(215.3413, device='cuda:0')
episode: 134 training return: tensor(251.6459, device='cuda:0')
episode: 135 training return: tensor(69.3091, device='cuda:0')
epoch: 34 test_true_pfm: 5383.50848906768 sim_pfm: -54.23695141876427
episode: 136 training return: tensor(178.7981, device='cuda:0')
episode: 137 training return: tensor(116.5239, device='cuda:0')
episode: 138 training return: tensor(-48.7689, device='cuda:0')
episode: 139 training return: tensor(181.9741, device='cuda:0')
epoch: 35 test_true_pfm: 5397.362334314952 sim_pfm: 247.2489825436205
episode: 140 training return: tensor(220.8398, device='cuda:0')
episode: 141 training return: tensor(178.0970, device='cuda:0')
episode: 142 training return: tensor(257.4578, device='cuda:0')
episode: 143 training return: tensor(166.9959, device='cuda:0')
epoch: 36 test_true_pfm: 5399.161534329908 sim_pfm: 243.7768246172151
episode: 144 training return: tensor(158.0104, device='cuda:0')
episode: 145 training return: tensor(164.9936, device='cuda:0')
episode: 146 training return: tensor(223.9888, device='cuda:0')
episode: 147 training return: tensor(222.3648, device='cuda:0')
epoch: 37 test_true_pfm: 5412.5895544698715 sim_pfm: 230.4454320210692
episode: 148 training return: tensor(111.3964, device='cuda:0')
episode: 149 training return: tensor(162.2660, device='cuda:0')
episode: 150 training return: tensor(-25.3638, device='cuda:0')
episode: 151 training return: tensor(257.0083, device='cuda:0')
epoch: 38 test_true_pfm: 5475.531128193441 sim_pfm: 325.7856356102663
episode: 152 training return: tensor(266.9311, device='cuda:0')
episode: 153 training return: tensor(241.6399, device='cuda:0')
episode: 154 training return: tensor(238.4640, device='cuda:0')
episode: 155 training return: tensor(208.5186, device='cuda:0')
epoch: 39 test_true_pfm: 5419.975944841048 sim_pfm: 294.003706833435
episode: 156 training return: tensor(97.2890, device='cuda:0')
episode: 157 training return: tensor(258.2089, device='cuda:0')
episode: 158 training return: tensor(125.5359, device='cuda:0')
episode: 159 training return: tensor(186.4654, device='cuda:0')
epoch: 40 test_true_pfm: 5474.631024938266 sim_pfm: 311.29872215477127
episode: 160 training return: tensor(134.7983, device='cuda:0')
episode: 161 training return: tensor(155.1006, device='cuda:0')
episode: 162 training return: tensor(261.7006, device='cuda:0')
episode: 163 training return: tensor(231.5583, device='cuda:0')
epoch: 41 test_true_pfm: 5316.489071848038 sim_pfm: 282.5048603694886
episode: 164 training return: tensor(256.8955, device='cuda:0')
episode: 165 training return: tensor(165.0350, device='cuda:0')
episode: 166 training return: tensor(239.2734, device='cuda:0')
episode: 167 training return: tensor(218.6105, device='cuda:0')
epoch: 42 test_true_pfm: 5382.917119388599 sim_pfm: 329.5386231914551
episode: 168 training return: tensor(261.7581, device='cuda:0')
episode: 169 training return: tensor(391.5500, device='cuda:0')
episode: 170 training return: tensor(53.2932, device='cuda:0')
episode: 171 training return: tensor(61.3322, device='cuda:0')
epoch: 43 test_true_pfm: 5346.335629829008 sim_pfm: 218.48225317933247
episode: 172 training return: tensor(157.3221, device='cuda:0')
episode: 173 training return: tensor(278.6267, device='cuda:0')
episode: 174 training return: tensor(217.2551, device='cuda:0')
episode: 175 training return: tensor(227.3308, device='cuda:0')
epoch: 44 test_true_pfm: 5502.745368338418 sim_pfm: 239.38649963544836
episode: 176 training return: tensor(82.7978, device='cuda:0')
episode: 177 training return: tensor(86.9625, device='cuda:0')
episode: 178 training return: tensor(122.6530, device='cuda:0')
episode: 179 training return: tensor(237.8253, device='cuda:0')
epoch: 45 test_true_pfm: 5428.558973405047 sim_pfm: 283.934935572887
episode: 180 training return: tensor(187.5439, device='cuda:0')
episode: 181 training return: tensor(291.9427, device='cuda:0')
episode: 182 training return: tensor(248.4808, device='cuda:0')
episode: 183 training return: tensor(252.0149, device='cuda:0')
epoch: 46 test_true_pfm: 5457.406579065933 sim_pfm: 18.245042595333263
episode: 184 training return: tensor(246.9254, device='cuda:0')
episode: 185 training return: tensor(202.1003, device='cuda:0')
episode: 186 training return: tensor(278.5856, device='cuda:0')
episode: 187 training return: tensor(317.0737, device='cuda:0')
epoch: 47 test_true_pfm: 5424.8280517133835 sim_pfm: 276.5148295655187
episode: 188 training return: tensor(302.1080, device='cuda:0')
episode: 189 training return: tensor(119.2267, device='cuda:0')
episode: 190 training return: tensor(223.7452, device='cuda:0')
episode: 191 training return: tensor(190.9902, device='cuda:0')
epoch: 48 test_true_pfm: 5517.257338160248 sim_pfm: 290.11566204670817
episode: 192 training return: tensor(259.4882, device='cuda:0')
episode: 193 training return: tensor(144.1412, device='cuda:0')
episode: 194 training return: tensor(272.2136, device='cuda:0')
episode: 195 training return: tensor(188.5396, device='cuda:0')
epoch: 49 test_true_pfm: 5524.486660172556 sim_pfm: 369.03157654619037
episode: 196 training return: tensor(284.3123, device='cuda:0')
episode: 197 training return: tensor(283.6829, device='cuda:0')
episode: 198 training return: tensor(215.9115, device='cuda:0')
episode: 199 training return: tensor(161.0165, device='cuda:0')
epoch: 50 test_true_pfm: 5497.51219163613 sim_pfm: 397.6794684845566
episode: 200 training return: tensor(275.5008, device='cuda:0')
episode: 201 training return: tensor(224.7210, device='cuda:0')
episode: 202 training return: tensor(121.3971, device='cuda:0')
episode: 203 training return: tensor(190.9877, device='cuda:0')
epoch: 51 test_true_pfm: 5515.898550522895 sim_pfm: 307.3461914961129
episode: 204 training return: tensor(131.2663, device='cuda:0')
episode: 205 training return: tensor(208.3995, device='cuda:0')
episode: 206 training return: tensor(301.1267, device='cuda:0')
episode: 207 training return: tensor(207.4650, device='cuda:0')
epoch: 52 test_true_pfm: 5535.729756006492 sim_pfm: 312.40312986962573
episode: 208 training return: tensor(234.0376, device='cuda:0')
episode: 209 training return: tensor(203.6958, device='cuda:0')
episode: 210 training return: tensor(148.5380, device='cuda:0')
episode: 211 training return: tensor(345.3023, device='cuda:0')
epoch: 53 test_true_pfm: 5488.06070025194 sim_pfm: 352.2951819720911
episode: 212 training return: tensor(290.0934, device='cuda:0')
episode: 213 training return: tensor(296.2562, device='cuda:0')
episode: 214 training return: tensor(250.5618, device='cuda:0')
episode: 215 training return: tensor(134.6523, device='cuda:0')
epoch: 54 test_true_pfm: 5528.920753206472 sim_pfm: 327.2923478144609
episode: 216 training return: tensor(329.2516, device='cuda:0')
episode: 217 training return: tensor(263.9009, device='cuda:0')
episode: 218 training return: tensor(221.4683, device='cuda:0')
episode: 219 training return: tensor(169.2211, device='cuda:0')
epoch: 55 test_true_pfm: 5440.641164138025 sim_pfm: 313.4535091419045
episode: 220 training return: tensor(275.1572, device='cuda:0')
episode: 221 training return: tensor(253.5316, device='cuda:0')
episode: 222 training return: tensor(208.5253, device='cuda:0')
episode: 223 training return: tensor(204.5644, device='cuda:0')
epoch: 56 test_true_pfm: 5510.984589973821 sim_pfm: 316.8820762555115
episode: 224 training return: tensor(381.3026, device='cuda:0')
episode: 225 training return: tensor(265.8536, device='cuda:0')
episode: 226 training return: tensor(164.3595, device='cuda:0')
episode: 227 training return: tensor(-156.8963, device='cuda:0')
epoch: 57 test_true_pfm: 5438.507663060097 sim_pfm: 355.995742526177
episode: 228 training return: tensor(199.7688, device='cuda:0')
episode: 229 training return: tensor(276.0424, device='cuda:0')
episode: 230 training return: tensor(268.7212, device='cuda:0')
episode: 231 training return: tensor(210.1792, device='cuda:0')
epoch: 58 test_true_pfm: 5503.159542731536 sim_pfm: 276.31251601938857
episode: 232 training return: tensor(201.1102, device='cuda:0')
episode: 233 training return: tensor(203.7751, device='cuda:0')
episode: 234 training return: tensor(165.7753, device='cuda:0')
episode: 235 training return: tensor(102.0022, device='cuda:0')
epoch: 59 test_true_pfm: 5520.29485717032 sim_pfm: 289.31823876226554
episode: 236 training return: tensor(125.8301, device='cuda:0')
episode: 237 training return: tensor(211.8004, device='cuda:0')
episode: 238 training return: tensor(142.5012, device='cuda:0')
episode: 239 training return: tensor(255.2835, device='cuda:0')
epoch: 60 test_true_pfm: 5528.958458235301 sim_pfm: 327.46781781259534
episode: 240 training return: tensor(210.2790, device='cuda:0')
episode: 241 training return: tensor(249.6770, device='cuda:0')
episode: 242 training return: tensor(274.9425, device='cuda:0')
episode: 243 training return: tensor(268.2875, device='cuda:0')
epoch: 61 test_true_pfm: 5554.278994627811 sim_pfm: 366.74343439384637
episode: 244 training return: tensor(212.6360, device='cuda:0')
episode: 245 training return: tensor(307.2724, device='cuda:0')
episode: 246 training return: tensor(225.2262, device='cuda:0')
episode: 247 training return: tensor(227.8347, device='cuda:0')
epoch: 62 test_true_pfm: 5513.532620860856 sim_pfm: 306.71490267289727
episode: 248 training return: tensor(270.1313, device='cuda:0')
episode: 249 training return: tensor(251.6935, device='cuda:0')
episode: 250 training return: tensor(259.4420, device='cuda:0')
episode: 251 training return: tensor(89.5859, device='cuda:0')
epoch: 63 test_true_pfm: 5568.267487093929 sim_pfm: 332.2315551507442
episode: 252 training return: tensor(243.4621, device='cuda:0')
episode: 253 training return: tensor(306.0146, device='cuda:0')
episode: 254 training return: tensor(221.3361, device='cuda:0')
episode: 255 training return: tensor(358.4031, device='cuda:0')
epoch: 64 test_true_pfm: 5438.988577200487 sim_pfm: 311.2602793679592
episode: 256 training return: tensor(293.6198, device='cuda:0')
episode: 257 training return: tensor(194.1409, device='cuda:0')
episode: 258 training return: tensor(188.8381, device='cuda:0')
episode: 259 training return: tensor(169.6562, device='cuda:0')
epoch: 65 test_true_pfm: 5439.93838704043 sim_pfm: 314.7507047056958
episode: 260 training return: tensor(43.0207, device='cuda:0')
episode: 261 training return: tensor(228.2328, device='cuda:0')
episode: 262 training return: tensor(205.7836, device='cuda:0')
episode: 263 training return: tensor(63.6669, device='cuda:0')
epoch: 66 test_true_pfm: 5480.007067882197 sim_pfm: 393.28471031816053
episode: 264 training return: tensor(228.7407, device='cuda:0')
episode: 265 training return: tensor(285.4521, device='cuda:0')
episode: 266 training return: tensor(302.9254, device='cuda:0')
episode: 267 training return: tensor(213.1148, device='cuda:0')
epoch: 67 test_true_pfm: 5515.071853734294 sim_pfm: 333.38085780422745
episode: 268 training return: tensor(230.9804, device='cuda:0')
episode: 269 training return: tensor(201.7728, device='cuda:0')
episode: 270 training return: tensor(207.5400, device='cuda:0')
episode: 271 training return: tensor(171.3660, device='cuda:0')
epoch: 68 test_true_pfm: 5523.619556976161 sim_pfm: 342.2580054828334
episode: 272 training return: tensor(237.1047, device='cuda:0')
episode: 273 training return: tensor(102.5832, device='cuda:0')
episode: 274 training return: tensor(205.9963, device='cuda:0')
episode: 275 training return: tensor(186.0650, device='cuda:0')
epoch: 69 test_true_pfm: 5473.531830105155 sim_pfm: 354.8486941262284
episode: 276 training return: tensor(187.5956, device='cuda:0')
episode: 277 training return: tensor(305.7141, device='cuda:0')
episode: 278 training return: tensor(193.7822, device='cuda:0')
episode: 279 training return: tensor(202.0930, device='cuda:0')
epoch: 70 test_true_pfm: 5503.696995297924 sim_pfm: 295.7594791880304
episode: 280 training return: tensor(270.9217, device='cuda:0')
episode: 281 training return: tensor(202.3265, device='cuda:0')
episode: 282 training return: tensor(342.3180, device='cuda:0')
episode: 283 training return: tensor(315.3386, device='cuda:0')
epoch: 71 test_true_pfm: 5488.67160109934 sim_pfm: 353.22484073304804
episode: 284 training return: tensor(108.3318, device='cuda:0')
episode: 285 training return: tensor(224.7543, device='cuda:0')
episode: 286 training return: tensor(187.1050, device='cuda:0')
episode: 287 training return: tensor(198.6761, device='cuda:0')
epoch: 72 test_true_pfm: 5515.439512087614 sim_pfm: 373.3989567611231
episode: 288 training return: tensor(303.3423, device='cuda:0')
episode: 289 training return: tensor(228.9762, device='cuda:0')
episode: 290 training return: tensor(199.8340, device='cuda:0')
episode: 291 training return: tensor(250.0733, device='cuda:0')
epoch: 73 test_true_pfm: 5563.622206471239 sim_pfm: 345.5691647368173
episode: 292 training return: tensor(352.2925, device='cuda:0')
episode: 293 training return: tensor(232.6307, device='cuda:0')
episode: 294 training return: tensor(170.1333, device='cuda:0')
episode: 295 training return: tensor(226.1587, device='cuda:0')
epoch: 74 test_true_pfm: 5437.489444638678 sim_pfm: 354.84066021849867
episode: 296 training return: tensor(350.3242, device='cuda:0')
episode: 297 training return: tensor(299.6646, device='cuda:0')
episode: 298 training return: tensor(182.6113, device='cuda:0')
episode: 299 training return: tensor(266.0398, device='cuda:0')
epoch: 75 test_true_pfm: 5470.774277743476 sim_pfm: 425.55605822692934
episode: 300 training return: tensor(203.9466, device='cuda:0')
episode: 301 training return: tensor(284.6083, device='cuda:0')
episode: 302 training return: tensor(297.6270, device='cuda:0')
episode: 303 training return: tensor(264.3670, device='cuda:0')
epoch: 76 test_true_pfm: 5512.8051416361195 sim_pfm: 345.34495249402244
episode: 304 training return: tensor(272.9278, device='cuda:0')
episode: 305 training return: tensor(133.4930, device='cuda:0')
episode: 306 training return: tensor(337.7294, device='cuda:0')
episode: 307 training return: tensor(204.9465, device='cuda:0')
epoch: 77 test_true_pfm: 5544.618535253972 sim_pfm: 350.6644993900166
episode: 308 training return: tensor(218.9752, device='cuda:0')
episode: 309 training return: tensor(278.0645, device='cuda:0')
episode: 310 training return: tensor(224.4838, device='cuda:0')
episode: 311 training return: tensor(305.2729, device='cuda:0')
epoch: 78 test_true_pfm: 5516.444611773778 sim_pfm: 383.708171542113
episode: 312 training return: tensor(264.2426, device='cuda:0')
episode: 313 training return: tensor(297.0804, device='cuda:0')
episode: 314 training return: tensor(314.2319, device='cuda:0')
episode: 315 training return: tensor(138.5058, device='cuda:0')
epoch: 79 test_true_pfm: 5572.790617338465 sim_pfm: 332.23552967971773
episode: 316 training return: tensor(253.3772, device='cuda:0')
episode: 317 training return: tensor(299.5504, device='cuda:0')
episode: 318 training return: tensor(207.3666, device='cuda:0')
episode: 319 training return: tensor(372.1243, device='cuda:0')
epoch: 80 test_true_pfm: 5478.070289431659 sim_pfm: 337.33774470338057
episode: 320 training return: tensor(295.0493, device='cuda:0')
episode: 321 training return: tensor(333.7202, device='cuda:0')
episode: 322 training return: tensor(319.7382, device='cuda:0')
episode: 323 training return: tensor(301.1194, device='cuda:0')
epoch: 81 test_true_pfm: 5549.6075587767145 sim_pfm: 357.3365950748266
episode: 324 training return: tensor(244.2561, device='cuda:0')
episode: 325 training return: tensor(212.4040, device='cuda:0')
episode: 326 training return: tensor(226.5233, device='cuda:0')
episode: 327 training return: tensor(226.1833, device='cuda:0')
epoch: 82 test_true_pfm: 5539.063200151792 sim_pfm: 288.6787718401368
episode: 328 training return: tensor(186.2584, device='cuda:0')
episode: 329 training return: tensor(148.6864, device='cuda:0')
episode: 330 training return: tensor(313.3090, device='cuda:0')
episode: 331 training return: tensor(374.9086, device='cuda:0')
epoch: 83 test_true_pfm: 5539.554673486247 sim_pfm: 399.7374794646942
episode: 332 training return: tensor(90.6298, device='cuda:0')
episode: 333 training return: tensor(223.9868, device='cuda:0')
episode: 334 training return: tensor(225.7711, device='cuda:0')
episode: 335 training return: tensor(309.3329, device='cuda:0')
epoch: 84 test_true_pfm: 5584.091373540861 sim_pfm: 404.9244924396141
episode: 336 training return: tensor(341.1001, device='cuda:0')
episode: 337 training return: tensor(185.5206, device='cuda:0')
episode: 338 training return: tensor(245.8742, device='cuda:0')
episode: 339 training return: tensor(391.2814, device='cuda:0')
epoch: 85 test_true_pfm: 5539.281664501021 sim_pfm: 339.3960561962643
episode: 340 training return: tensor(222.2358, device='cuda:0')
episode: 341 training return: tensor(206.0234, device='cuda:0')
episode: 342 training return: tensor(329.7795, device='cuda:0')
episode: 343 training return: tensor(282.3460, device='cuda:0')
epoch: 86 test_true_pfm: 5631.589521370935 sim_pfm: 378.0244700772455
episode: 344 training return: tensor(255.4231, device='cuda:0')
episode: 345 training return: tensor(355.6932, device='cuda:0')
episode: 346 training return: tensor(262.9991, device='cuda:0')
episode: 347 training return: tensor(-886.5270, device='cuda:0')
epoch: 87 test_true_pfm: 5509.21954996074 sim_pfm: 311.54487746513524
episode: 348 training return: tensor(244.8556, device='cuda:0')
episode: 349 training return: tensor(354.2033, device='cuda:0')
episode: 350 training return: tensor(302.9524, device='cuda:0')
episode: 351 training return: tensor(235.4199, device='cuda:0')
epoch: 88 test_true_pfm: 5527.618472980066 sim_pfm: 383.57650176706375
episode: 352 training return: tensor(347.0739, device='cuda:0')
episode: 353 training return: tensor(165.8645, device='cuda:0')
episode: 354 training return: tensor(272.8530, device='cuda:0')
episode: 355 training return: tensor(159.5561, device='cuda:0')
epoch: 89 test_true_pfm: 5556.759001520865 sim_pfm: 335.9630161708531
episode: 356 training return: tensor(262.0541, device='cuda:0')
episode: 357 training return: tensor(301.3710, device='cuda:0')
episode: 358 training return: tensor(181.9773, device='cuda:0')
episode: 359 training return: tensor(319.8052, device='cuda:0')
epoch: 90 test_true_pfm: 5557.981082517094 sim_pfm: 378.45634043207974
episode: 360 training return: tensor(263.5403, device='cuda:0')
episode: 361 training return: tensor(222.8599, device='cuda:0')
episode: 362 training return: tensor(357.1649, device='cuda:0')
episode: 363 training return: tensor(295.2678, device='cuda:0')
epoch: 91 test_true_pfm: 5602.8902129751505 sim_pfm: 360.669748733247
episode: 364 training return: tensor(284.5569, device='cuda:0')
episode: 365 training return: tensor(214.0318, device='cuda:0')
episode: 366 training return: tensor(304.0720, device='cuda:0')
episode: 367 training return: tensor(330.0649, device='cuda:0')
epoch: 92 test_true_pfm: 5569.116646633088 sim_pfm: 354.13281004014425
episode: 368 training return: tensor(155.1153, device='cuda:0')
episode: 369 training return: tensor(231.5802, device='cuda:0')
episode: 370 training return: tensor(308.0086, device='cuda:0')
episode: 371 training return: tensor(400.9385, device='cuda:0')
epoch: 93 test_true_pfm: 5520.204390324171 sim_pfm: 408.72234677542775
episode: 372 training return: tensor(370.3250, device='cuda:0')
episode: 373 training return: tensor(288.6009, device='cuda:0')
episode: 374 training return: tensor(303.5718, device='cuda:0')
episode: 375 training return: tensor(176.3375, device='cuda:0')
epoch: 94 test_true_pfm: 5574.913398058223 sim_pfm: 307.63773070234066
episode: 376 training return: tensor(271.4874, device='cuda:0')
episode: 377 training return: tensor(330.3694, device='cuda:0')
episode: 378 training return: tensor(178.6119, device='cuda:0')
episode: 379 training return: tensor(303.1244, device='cuda:0')
epoch: 95 test_true_pfm: 5553.588648197384 sim_pfm: 362.35786465363344
episode: 380 training return: tensor(240.3481, device='cuda:0')
episode: 381 training return: tensor(270.5316, device='cuda:0')
episode: 382 training return: tensor(298.2769, device='cuda:0')
episode: 383 training return: tensor(343.5808, device='cuda:0')
epoch: 96 test_true_pfm: 5586.245300992021 sim_pfm: 369.4642549163934
episode: 384 training return: tensor(176.4733, device='cuda:0')
episode: 385 training return: tensor(305.9683, device='cuda:0')
episode: 386 training return: tensor(273.8970, device='cuda:0')
episode: 387 training return: tensor(169.3510, device='cuda:0')
epoch: 97 test_true_pfm: 5577.376974010777 sim_pfm: 396.8700144879501
episode: 388 training return: tensor(299.7609, device='cuda:0')
episode: 389 training return: tensor(213.9770, device='cuda:0')
episode: 390 training return: tensor(311.6598, device='cuda:0')
episode: 391 training return: tensor(292.3372, device='cuda:0')
epoch: 98 test_true_pfm: 5552.132859661557 sim_pfm: 378.5049255488072
episode: 392 training return: tensor(312.0009, device='cuda:0')
episode: 393 training return: tensor(257.7608, device='cuda:0')
episode: 394 training return: tensor(275.7381, device='cuda:0')
episode: 395 training return: tensor(261.1360, device='cuda:0')
epoch: 99 test_true_pfm: 5595.4462281883725 sim_pfm: 402.6993299959965
episode: 396 training return: tensor(295.2348, device='cuda:0')
episode: 397 training return: tensor(249.7963, device='cuda:0')
episode: 398 training return: tensor(281.8760, device='cuda:0')
episode: 399 training return: tensor(313.2451, device='cuda:0')
epoch: 100 test_true_pfm: 5570.661351467636 sim_pfm: 346.3031366994255
episode: 400 training return: tensor(261.4185, device='cuda:0')
episode: 401 training return: tensor(149.2018, device='cuda:0')
episode: 402 training return: tensor(240.8279, device='cuda:0')
episode: 403 training return: tensor(317.5702, device='cuda:0')
epoch: 101 test_true_pfm: 5592.981629019397 sim_pfm: 378.8079392823468
episode: 404 training return: tensor(300.1219, device='cuda:0')
episode: 405 training return: tensor(272.3626, device='cuda:0')
episode: 406 training return: tensor(267.0579, device='cuda:0')
episode: 407 training return: tensor(316.6335, device='cuda:0')
epoch: 102 test_true_pfm: 5492.565509862897 sim_pfm: 384.84953635300434
episode: 408 training return: tensor(338.6072, device='cuda:0')
episode: 409 training return: tensor(310.6080, device='cuda:0')
episode: 410 training return: tensor(356.2367, device='cuda:0')
episode: 411 training return: tensor(357.8288, device='cuda:0')
epoch: 103 test_true_pfm: 5673.616588155623 sim_pfm: 353.959681317249
episode: 412 training return: tensor(256.7881, device='cuda:0')
episode: 413 training return: tensor(365.4137, device='cuda:0')
episode: 414 training return: tensor(277.9258, device='cuda:0')
episode: 415 training return: tensor(330.7326, device='cuda:0')
epoch: 104 test_true_pfm: 5521.465568486706 sim_pfm: 382.2314467621812
episode: 416 training return: tensor(214.3466, device='cuda:0')
episode: 417 training return: tensor(301.1684, device='cuda:0')
episode: 418 training return: tensor(370.5504, device='cuda:0')
episode: 419 training return: tensor(282.5147, device='cuda:0')
epoch: 105 test_true_pfm: 5570.391742313924 sim_pfm: 375.98677276899497
episode: 420 training return: tensor(288.3147, device='cuda:0')
episode: 421 training return: tensor(71.8426, device='cuda:0')
episode: 422 training return: tensor(324.8049, device='cuda:0')
episode: 423 training return: tensor(254.1067, device='cuda:0')
epoch: 106 test_true_pfm: 5622.98630789114 sim_pfm: 398.51393808458425
episode: 424 training return: tensor(353.0661, device='cuda:0')
episode: 425 training return: tensor(222.1680, device='cuda:0')
episode: 426 training return: tensor(247.2643, device='cuda:0')
episode: 427 training return: tensor(215.9337, device='cuda:0')
epoch: 107 test_true_pfm: 5584.5578467906225 sim_pfm: 439.2157506648218
episode: 428 training return: tensor(398.8820, device='cuda:0')
episode: 429 training return: tensor(271.9710, device='cuda:0')
episode: 430 training return: tensor(321.3566, device='cuda:0')
episode: 431 training return: tensor(226.9862, device='cuda:0')
epoch: 108 test_true_pfm: 5547.771987451208 sim_pfm: 397.3016526600113
episode: 432 training return: tensor(223.0224, device='cuda:0')
episode: 433 training return: tensor(351.5835, device='cuda:0')
episode: 434 training return: tensor(295.4411, device='cuda:0')
episode: 435 training return: tensor(314.3229, device='cuda:0')
epoch: 109 test_true_pfm: 5146.107848207829 sim_pfm: 403.094821921249
episode: 436 training return: tensor(139.7897, device='cuda:0')
episode: 437 training return: tensor(327.3860, device='cuda:0')
episode: 438 training return: tensor(278.8452, device='cuda:0')
episode: 439 training return: tensor(391.3263, device='cuda:0')
epoch: 110 test_true_pfm: 5598.097170952645 sim_pfm: 435.9610217634278
episode: 440 training return: tensor(293.6219, device='cuda:0')
episode: 441 training return: tensor(338.0953, device='cuda:0')
episode: 442 training return: tensor(299.4171, device='cuda:0')
episode: 443 training return: tensor(337.0972, device='cuda:0')
epoch: 111 test_true_pfm: 5524.329595801132 sim_pfm: 378.8538189304333
episode: 444 training return: tensor(192.4645, device='cuda:0')
episode: 445 training return: tensor(396.1173, device='cuda:0')
episode: 446 training return: tensor(263.5800, device='cuda:0')
episode: 447 training return: tensor(272.4217, device='cuda:0')
epoch: 112 test_true_pfm: 5603.508928894189 sim_pfm: 409.4775567261192
episode: 448 training return: tensor(297.9749, device='cuda:0')
episode: 449 training return: tensor(279.0723, device='cuda:0')
episode: 450 training return: tensor(269.7960, device='cuda:0')
episode: 451 training return: tensor(199.9373, device='cuda:0')
epoch: 113 test_true_pfm: 5598.94181732995 sim_pfm: 366.5858700981674
episode: 452 training return: tensor(202.9631, device='cuda:0')
episode: 453 training return: tensor(352.3159, device='cuda:0')
episode: 454 training return: tensor(259.2117, device='cuda:0')
episode: 455 training return: tensor(360.4756, device='cuda:0')
epoch: 114 test_true_pfm: 5474.649694281274 sim_pfm: 421.25286388469004
episode: 456 training return: tensor(270.0415, device='cuda:0')
episode: 457 training return: tensor(300.6591, device='cuda:0')
episode: 458 training return: tensor(208.4052, device='cuda:0')
episode: 459 training return: tensor(344.0736, device='cuda:0')
epoch: 115 test_true_pfm: 5615.763438670991 sim_pfm: 342.33112686915166
episode: 460 training return: tensor(273.3087, device='cuda:0')
episode: 461 training return: tensor(368.6384, device='cuda:0')
episode: 462 training return: tensor(288.8972, device='cuda:0')
episode: 463 training return: tensor(349.2710, device='cuda:0')
epoch: 116 test_true_pfm: 5649.919908733963 sim_pfm: 397.34774220039253
episode: 464 training return: tensor(274.6697, device='cuda:0')
episode: 465 training return: tensor(-132.8201, device='cuda:0')
episode: 466 training return: tensor(278.9073, device='cuda:0')
episode: 467 training return: tensor(316.4978, device='cuda:0')
epoch: 117 test_true_pfm: 5568.923177614728 sim_pfm: 419.7030970237295
episode: 468 training return: tensor(253.7366, device='cuda:0')
episode: 469 training return: tensor(244.5634, device='cuda:0')
episode: 470 training return: tensor(198.9584, device='cuda:0')
episode: 471 training return: tensor(254.3370, device='cuda:0')
epoch: 118 test_true_pfm: 5543.931413967119 sim_pfm: 400.1719805554603
episode: 472 training return: tensor(355.5173, device='cuda:0')
episode: 473 training return: tensor(286.8030, device='cuda:0')
episode: 474 training return: tensor(264.1543, device='cuda:0')
episode: 475 training return: tensor(340.8311, device='cuda:0')
epoch: 119 test_true_pfm: 5687.94079114491 sim_pfm: 454.1034120104353
episode: 476 training return: tensor(293.0963, device='cuda:0')
episode: 477 training return: tensor(376.4106, device='cuda:0')
episode: 478 training return: tensor(257.8620, device='cuda:0')
episode: 479 training return: tensor(261.5260, device='cuda:0')
epoch: 120 test_true_pfm: 5594.575440329885 sim_pfm: 405.78237224703963
episode: 480 training return: tensor(316.8263, device='cuda:0')
episode: 481 training return: tensor(312.9676, device='cuda:0')
episode: 482 training return: tensor(284.5724, device='cuda:0')
episode: 483 training return: tensor(213.6027, device='cuda:0')
epoch: 121 test_true_pfm: 5618.264823369008 sim_pfm: 391.0641248737229
episode: 484 training return: tensor(287.9584, device='cuda:0')
episode: 485 training return: tensor(258.8852, device='cuda:0')
episode: 486 training return: tensor(358.2462, device='cuda:0')
episode: 487 training return: tensor(343.9732, device='cuda:0')
epoch: 122 test_true_pfm: 5642.957134772427 sim_pfm: 410.16172976836486
episode: 488 training return: tensor(293.3878, device='cuda:0')
episode: 489 training return: tensor(235.2130, device='cuda:0')
episode: 490 training return: tensor(244.2271, device='cuda:0')
episode: 491 training return: tensor(317.3167, device='cuda:0')
epoch: 123 test_true_pfm: 5558.6809668417345 sim_pfm: 380.45525785849895
episode: 492 training return: tensor(346.4848, device='cuda:0')
episode: 493 training return: tensor(349.6274, device='cuda:0')
episode: 494 training return: tensor(380.7086, device='cuda:0')
episode: 495 training return: tensor(336.5836, device='cuda:0')
epoch: 124 test_true_pfm: 5643.541113662312 sim_pfm: 401.9752331657219
episode: 496 training return: tensor(303.2336, device='cuda:0')
episode: 497 training return: tensor(356.3658, device='cuda:0')
episode: 498 training return: tensor(270.7351, device='cuda:0')
episode: 499 training return: tensor(325.4164, device='cuda:0')
epoch: 125 test_true_pfm: 5514.050855038368 sim_pfm: 418.25312606373336
episode: 500 training return: tensor(351.4796, device='cuda:0')
episode: 501 training return: tensor(407.5182, device='cuda:0')
episode: 502 training return: tensor(360.1069, device='cuda:0')
episode: 503 training return: tensor(445.4022, device='cuda:0')
epoch: 126 test_true_pfm: 5658.833000830021 sim_pfm: 402.8025389467172
episode: 504 training return: tensor(348.4898, device='cuda:0')
episode: 505 training return: tensor(354.0475, device='cuda:0')
episode: 506 training return: tensor(291.7863, device='cuda:0')
episode: 507 training return: tensor(144.0337, device='cuda:0')
epoch: 127 test_true_pfm: 5632.44091737354 sim_pfm: 443.5960622187995
episode: 508 training return: tensor(169.2431, device='cuda:0')
episode: 509 training return: tensor(243.5965, device='cuda:0')
episode: 510 training return: tensor(314.8738, device='cuda:0')
episode: 511 training return: tensor(323.0762, device='cuda:0')
epoch: 128 test_true_pfm: 5602.236912936884 sim_pfm: 345.09878802113235
episode: 512 training return: tensor(261.1830, device='cuda:0')
episode: 513 training return: tensor(235.6162, device='cuda:0')
episode: 514 training return: tensor(363.9182, device='cuda:0')
episode: 515 training return: tensor(233.6978, device='cuda:0')
epoch: 129 test_true_pfm: 5581.914118255691 sim_pfm: 334.6170027944415
episode: 516 training return: tensor(276.9315, device='cuda:0')
episode: 517 training return: tensor(213.7566, device='cuda:0')
episode: 518 training return: tensor(365.6783, device='cuda:0')
episode: 519 training return: tensor(248.4709, device='cuda:0')
epoch: 130 test_true_pfm: 5620.271437526062 sim_pfm: 387.631496849431
episode: 520 training return: tensor(260.6910, device='cuda:0')
episode: 521 training return: tensor(111.5902, device='cuda:0')
episode: 522 training return: tensor(225.3266, device='cuda:0')
episode: 523 training return: tensor(260.9617, device='cuda:0')
epoch: 131 test_true_pfm: 5567.501145606123 sim_pfm: 354.7115238921251
episode: 524 training return: tensor(374.9312, device='cuda:0')
episode: 525 training return: tensor(304.3332, device='cuda:0')
episode: 526 training return: tensor(309.4457, device='cuda:0')
episode: 527 training return: tensor(220.5429, device='cuda:0')
epoch: 132 test_true_pfm: 5644.257733494514 sim_pfm: 407.10274436352
episode: 528 training return: tensor(283.8148, device='cuda:0')
episode: 529 training return: tensor(320.1698, device='cuda:0')
episode: 530 training return: tensor(352.3112, device='cuda:0')
episode: 531 training return: tensor(333.9207, device='cuda:0')
epoch: 133 test_true_pfm: 5634.429052465109 sim_pfm: 454.14232904460124
episode: 532 training return: tensor(229.5797, device='cuda:0')
episode: 533 training return: tensor(289.8969, device='cuda:0')
episode: 534 training return: tensor(244.0902, device='cuda:0')
episode: 535 training return: tensor(339.7894, device='cuda:0')
epoch: 134 test_true_pfm: 5647.629002008175 sim_pfm: 397.96116954490816
episode: 536 training return: tensor(289.4809, device='cuda:0')
episode: 537 training return: tensor(229.1408, device='cuda:0')
episode: 538 training return: tensor(349.5014, device='cuda:0')
episode: 539 training return: tensor(257.5921, device='cuda:0')
epoch: 135 test_true_pfm: 5676.018629782167 sim_pfm: 389.66074568007997
episode: 540 training return: tensor(292.5591, device='cuda:0')
episode: 541 training return: tensor(308.2525, device='cuda:0')
episode: 542 training return: tensor(350.7081, device='cuda:0')
episode: 543 training return: tensor(277.0673, device='cuda:0')
epoch: 136 test_true_pfm: 5564.7447179555675 sim_pfm: 385.76226793792256
episode: 544 training return: tensor(309.6091, device='cuda:0')
episode: 545 training return: tensor(267.4289, device='cuda:0')
episode: 546 training return: tensor(224.2377, device='cuda:0')
episode: 547 training return: tensor(349.4007, device='cuda:0')
epoch: 137 test_true_pfm: 5625.3599360091985 sim_pfm: 469.51306543553557
episode: 548 training return: tensor(444.2035, device='cuda:0')
episode: 549 training return: tensor(261.3619, device='cuda:0')
episode: 550 training return: tensor(308.3993, device='cuda:0')
episode: 551 training return: tensor(299.9985, device='cuda:0')
epoch: 138 test_true_pfm: 5593.618270578718 sim_pfm: 419.7305909105635
episode: 552 training return: tensor(385.1385, device='cuda:0')
episode: 553 training return: tensor(290.3368, device='cuda:0')
episode: 554 training return: tensor(352.4277, device='cuda:0')
episode: 555 training return: tensor(301.1428, device='cuda:0')
epoch: 139 test_true_pfm: 5585.474493570821 sim_pfm: 429.3312674574942
episode: 556 training return: tensor(390.3126, device='cuda:0')
episode: 557 training return: tensor(312.6342, device='cuda:0')
episode: 558 training return: tensor(345.0796, device='cuda:0')
episode: 559 training return: tensor(261.8642, device='cuda:0')
epoch: 140 test_true_pfm: 5582.3124121470655 sim_pfm: 452.29922052906477
episode: 560 training return: tensor(320.5531, device='cuda:0')
episode: 561 training return: tensor(294.4655, device='cuda:0')
episode: 562 training return: tensor(339.7419, device='cuda:0')
episode: 563 training return: tensor(363.7346, device='cuda:0')
epoch: 141 test_true_pfm: 5614.221147036388 sim_pfm: 423.433254450482
episode: 564 training return: tensor(351.5290, device='cuda:0')
episode: 565 training return: tensor(310.4972, device='cuda:0')
episode: 566 training return: tensor(257.0171, device='cuda:0')
episode: 567 training return: tensor(306.3738, device='cuda:0')
epoch: 142 test_true_pfm: 5586.8070319143035 sim_pfm: 460.8862689897651
episode: 568 training return: tensor(370.6532, device='cuda:0')
episode: 569 training return: tensor(268.8461, device='cuda:0')
episode: 570 training return: tensor(261.0176, device='cuda:0')
episode: 571 training return: tensor(262.6096, device='cuda:0')
epoch: 143 test_true_pfm: 5662.379786692214 sim_pfm: 431.92075591996155
episode: 572 training return: tensor(338.5971, device='cuda:0')
episode: 573 training return: tensor(361.3129, device='cuda:0')
episode: 574 training return: tensor(379.9369, device='cuda:0')
episode: 575 training return: tensor(346.1704, device='cuda:0')
epoch: 144 test_true_pfm: 5581.262434521133 sim_pfm: 406.70729062256095
episode: 576 training return: tensor(355.3128, device='cuda:0')
episode: 577 training return: tensor(264.4207, device='cuda:0')
episode: 578 training return: tensor(286.7727, device='cuda:0')
episode: 579 training return: tensor(306.4256, device='cuda:0')
epoch: 145 test_true_pfm: 5544.445627057573 sim_pfm: 437.58342013550765
episode: 580 training return: tensor(358.8759, device='cuda:0')
episode: 581 training return: tensor(311.1452, device='cuda:0')
episode: 582 training return: tensor(363.7099, device='cuda:0')
episode: 583 training return: tensor(347.8253, device='cuda:0')
epoch: 146 test_true_pfm: 5728.085130384476 sim_pfm: 420.30273908231175
episode: 584 training return: tensor(357.6214, device='cuda:0')
episode: 585 training return: tensor(322.7150, device='cuda:0')
episode: 586 training return: tensor(360.1999, device='cuda:0')
episode: 587 training return: tensor(254.1943, device='cuda:0')
epoch: 147 test_true_pfm: 5669.3143067622905 sim_pfm: 414.25329369846924
episode: 588 training return: tensor(270.4602, device='cuda:0')
episode: 589 training return: tensor(342.9633, device='cuda:0')
episode: 590 training return: tensor(261.9370, device='cuda:0')
episode: 591 training return: tensor(366.8013, device='cuda:0')
epoch: 148 test_true_pfm: 5645.604258852 sim_pfm: 442.42254323205754
episode: 592 training return: tensor(250.1318, device='cuda:0')
episode: 593 training return: tensor(292.8145, device='cuda:0')
episode: 594 training return: tensor(342.8926, device='cuda:0')
episode: 595 training return: tensor(250.0962, device='cuda:0')
epoch: 149 test_true_pfm: 5569.355627767264 sim_pfm: 370.8790076460379
episode: 596 training return: tensor(240.7189, device='cuda:0')
episode: 597 training return: tensor(330.6511, device='cuda:0')
episode: 598 training return: tensor(281.7336, device='cuda:0')
episode: 599 training return: tensor(375.5733, device='cuda:0')
epoch: 150 test_true_pfm: 5623.326350487702 sim_pfm: 408.0328538016377
