['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '8', '--data', '100000', '--regu', '0.2']
epoch: 0 training_loss 0.24851017832756042 test_loss: 0.21519434452056885
epoch: 1 training_loss 0.20013690672814846 test_loss: 0.21112060546875
epoch: 2 training_loss 0.19915460266172885 test_loss: 0.20789475440979005
epoch: 3 training_loss 0.19240055695176125 test_loss: 0.20014989376068115
epoch: 4 training_loss 0.1891445755958557 test_loss: 0.19854495525360108
epoch: 5 training_loss 0.19096479654312135 test_loss: 0.19694315195083617
epoch: 6 training_loss 0.19546897523105145 test_loss: 0.19808152914047242
epoch: 7 training_loss 0.1889565385133028 test_loss: 0.1828900694847107
epoch: 8 training_loss 0.19100396171212197 test_loss: 0.19146891832351684
epoch: 9 training_loss 0.18564427718520166 test_loss: 0.20184581279754638
epoch: 10 training_loss 0.17739300355315207 test_loss: 0.17990039587020873
epoch: 11 training_loss 0.1881396961212158 test_loss: 0.19435389041900636
epoch: 12 training_loss 0.18533387072384358 test_loss: 0.1757627844810486
epoch: 13 training_loss 0.19494222819805146 test_loss: 0.1921006441116333
epoch: 14 training_loss 0.1728759827464819 test_loss: 0.16789650917053223
epoch: 15 training_loss 0.18022237688302994 test_loss: 0.18006933927536012
epoch: 16 training_loss 0.178095573335886 test_loss: 0.19879372119903566
epoch: 17 training_loss 0.19065392144024373 test_loss: 0.1968948006629944
epoch: 18 training_loss 0.18091234743595122 test_loss: 0.1998944640159607
epoch: 19 training_loss 0.17576160609722138 test_loss: 0.20686590671539307
epoch: 20 training_loss 0.1839788257330656 test_loss: 0.18353514671325682
epoch: 21 training_loss 0.1836201110482216 test_loss: 0.18909890651702882
epoch: 22 training_loss 0.17485469840466977 test_loss: 0.1764937162399292
epoch: 23 training_loss 0.17792569383978843 test_loss: 0.17611637115478515
epoch: 24 training_loss 0.17789156384766103 test_loss: 0.1950790047645569
epoch: 25 training_loss 0.17511416502296925 test_loss: 0.17871594429016113
epoch: 26 training_loss 0.17881132423877716 test_loss: 0.1739114761352539
epoch: 27 training_loss 0.18146153181791305 test_loss: 0.1814664125442505
epoch: 28 training_loss 0.17870387353003025 test_loss: 0.18348408937454225
epoch: 29 training_loss 0.1789253557473421 test_loss: 0.17515114545822144
epoch: 30 training_loss 0.17691595911979674 test_loss: 0.19421062469482422
epoch: 31 training_loss 0.17850796125829219 test_loss: 0.18083029985427856
epoch: 32 training_loss 0.18383156642317772 test_loss: 0.16981287002563478
epoch: 33 training_loss 0.18006667673587798 test_loss: 0.18803409337997437
epoch: 34 training_loss 0.18824792154133319 test_loss: 0.1905131459236145
epoch: 35 training_loss 0.17526863470673562 test_loss: 0.19869757890701295
epoch: 36 training_loss 0.17617070451378822 test_loss: 0.17565879821777344
epoch: 37 training_loss 0.1817293430864811 test_loss: 0.19926689863204955
epoch: 38 training_loss 0.1899239833652973 test_loss: 0.1830574631690979
epoch: 39 training_loss 0.18878578305244445 test_loss: 0.16732406616210938
epoch: 40 training_loss 0.18324802957475186 test_loss: 0.16433931589126588
epoch: 41 training_loss 0.18735351234674455 test_loss: 0.1780996322631836
epoch: 42 training_loss 0.17767279006540776 test_loss: 0.17815110683441163
epoch: 43 training_loss 0.18619428485631942 test_loss: 0.16579756736755372
epoch: 44 training_loss 0.1787556864321232 test_loss: 0.17301079034805297
epoch: 45 training_loss 0.1742842607945204 test_loss: 0.18590523004531861
epoch: 46 training_loss 0.18127244465053083 test_loss: 0.16672348976135254
epoch: 47 training_loss 0.18064862288534642 test_loss: 0.1853295683860779
epoch: 48 training_loss 0.1756230366230011 test_loss: 0.17913800477981567
epoch: 49 training_loss 0.18174408741295336 test_loss: 0.18061596155166626
epoch: 50 training_loss 0.1820853616297245 test_loss: 0.19378857612609862
epoch: 51 training_loss 0.18090301513671875 test_loss: 0.19348880052566528
epoch: 52 training_loss 0.17994328945875168 test_loss: 0.18443841934204103
epoch: 53 training_loss 0.17883858166635036 test_loss: 0.16526389122009277
epoch: 54 training_loss 0.1814067240804434 test_loss: 0.19240604639053344
epoch: 55 training_loss 0.1820831759274006 test_loss: 0.1743033528327942
epoch: 56 training_loss 0.18801152072846888 test_loss: 0.19659923315048217
epoch: 57 training_loss 0.17831634029746055 test_loss: 0.1813291311264038
epoch: 58 training_loss 0.18342150755226613 test_loss: 0.18288910388946533
epoch: 59 training_loss 0.17715565949678422 test_loss: 0.18687554597854614
epoch: 60 training_loss 0.182325743958354 test_loss: 0.1746188521385193
epoch: 61 training_loss 0.17677759900689125 test_loss: 0.18322685956954957
epoch: 62 training_loss 0.18200568057596683 test_loss: 0.1870424270629883
epoch: 63 training_loss 0.17923417896032334 test_loss: 0.17157325744628907
epoch: 64 training_loss 0.1776202792674303 test_loss: 0.19502989053726197
epoch: 65 training_loss 0.17895890675485135 test_loss: 0.18754018545150758
epoch: 66 training_loss 0.17288712546229362 test_loss: 0.16199735403060914
epoch: 67 training_loss 0.19185949876904487 test_loss: 0.17905014753341675
epoch: 68 training_loss 0.18277327053248882 test_loss: 0.1828887343406677
epoch: 69 training_loss 0.17891047529876233 test_loss: 0.18975391387939453
epoch: 70 training_loss 0.18418742835521698 test_loss: 0.18122764825820922
epoch: 71 training_loss 0.17547207079827787 test_loss: 0.2078749418258667
epoch: 72 training_loss 0.18196504831314086 test_loss: 0.1721868634223938
epoch: 73 training_loss 0.1896740908175707 test_loss: 0.18334106206893921
epoch: 74 training_loss 0.1762440837174654 test_loss: 0.1955502986907959
epoch: 75 training_loss 0.18427821569144726 test_loss: 0.183533775806427
epoch: 76 training_loss 0.18084834955632687 test_loss: 0.16809045076370238
epoch: 77 training_loss 0.1754569347202778 test_loss: 0.1689846158027649
epoch: 78 training_loss 0.172345539778471 test_loss: 0.177851665019989
epoch: 79 training_loss 0.17636396758258344 test_loss: 0.19432929754257203
epoch: 80 training_loss 0.17498966783285141 test_loss: 0.18324800729751586
epoch: 81 training_loss 0.1729477398097515 test_loss: 0.18626400232315063
epoch: 82 training_loss 0.1796111511439085 test_loss: 0.17024081945419312
epoch: 83 training_loss 0.17894033670425416 test_loss: 0.18060874938964844
epoch: 84 training_loss 0.1822506571561098 test_loss: 0.17929999828338622
epoch: 85 training_loss 0.17671665791422128 test_loss: 0.18334622383117677
epoch: 86 training_loss 0.17201153494417667 test_loss: 0.20595765113830566
epoch: 87 training_loss 0.17703272216022015 test_loss: 0.19704933166503907
epoch: 88 training_loss 0.17455548159778117 test_loss: 0.1727656602859497
epoch: 89 training_loss 0.18214442670345307 test_loss: 0.19021191596984863
epoch: 90 training_loss 0.186236257776618 test_loss: 0.17158451080322265
epoch: 91 training_loss 0.17704623498022556 test_loss: 0.17572754621505737
epoch: 92 training_loss 0.18183162897825242 test_loss: 0.18366771936416626
epoch: 93 training_loss 0.18163813211023808 test_loss: 0.18775402307510375
epoch: 94 training_loss 0.17692682564258574 test_loss: 0.17725099325180055
epoch: 95 training_loss 0.17530382074415685 test_loss: 0.18143439292907715
epoch: 96 training_loss 0.18150007605552673 test_loss: 0.1599869728088379
epoch: 97 training_loss 0.17581651836633683 test_loss: 0.18117958307266235
epoch: 98 training_loss 0.17827274143695832 test_loss: 0.18123148679733275
epoch: 99 training_loss 0.1789041681587696 test_loss: 0.18955103158950806
epoch: 100 training_loss 0.17600963324308394 test_loss: 0.1689310908317566
epoch: 101 training_loss 0.17314263116568326 test_loss: 0.17129764556884766
epoch: 102 training_loss 0.1759080895781517 test_loss: 0.18901869058609008
epoch: 103 training_loss 0.17286205492913723 test_loss: 0.1827610731124878
epoch: 104 training_loss 0.17482219688594342 test_loss: 0.1972772240638733
epoch: 105 training_loss 0.1835211680829525 test_loss: 0.17764281034469603
epoch: 106 training_loss 0.18097359120845793 test_loss: 0.18499698638916015
epoch: 107 training_loss 0.17487014420330524 test_loss: 0.18064961433410645
epoch: 108 training_loss 0.1883751105517149 test_loss: 0.18712540864944457
epoch: 109 training_loss 0.1857349405437708 test_loss: 0.17277594804763793
epoch: 110 training_loss 0.17978275410830974 test_loss: 0.18434641361236573
epoch: 111 training_loss 0.18228151105344295 test_loss: 0.18535280227661133
epoch: 112 training_loss 0.1770967872440815 test_loss: 0.17124054431915284
epoch: 113 training_loss 0.1746069896221161 test_loss: 0.19595439434051515
epoch: 114 training_loss 0.18767684929072856 test_loss: 0.1711543917655945
epoch: 115 training_loss 0.17968019120395184 test_loss: 0.18509976863861083
epoch: 116 training_loss 0.18714090749621393 test_loss: 0.17304061651229857
epoch: 117 training_loss 0.18225635439157487 test_loss: 0.17625480890274048
epoch: 118 training_loss 0.18105948224663734 test_loss: 0.17252800464630128
epoch: 119 training_loss 0.1808687348663807 test_loss: 0.1790871262550354
epoch: 120 training_loss 0.18093920893967153 test_loss: 0.18226226568222045
epoch: 121 training_loss 0.18085122480988503 test_loss: 0.1760849952697754
epoch: 122 training_loss 0.18183877825737 test_loss: 0.1913408160209656
epoch: 123 training_loss 0.17928828202188016 test_loss: 0.17346365451812745
epoch: 124 training_loss 0.17813609026372432 test_loss: 0.17678747177124024
epoch: 125 training_loss 0.18038567390292884 test_loss: 0.1715493083000183
epoch: 126 training_loss 0.18361653856933116 test_loss: 0.1899314522743225
epoch: 127 training_loss 0.1759055535495281 test_loss: 0.19540839195251464
epoch: 128 training_loss 0.17305072039365768 test_loss: 0.17886096239089966
epoch: 129 training_loss 0.17865614883601666 test_loss: 0.18803853988647462
epoch: 130 training_loss 0.17903076425194742 test_loss: 0.18125966787338257
epoch: 131 training_loss 0.18258790753781795 test_loss: 0.1862926959991455
epoch: 132 training_loss 0.17369690299034118 test_loss: 0.17281848192214966
epoch: 133 training_loss 0.17492253743112088 test_loss: 0.19069461822509765
epoch: 134 training_loss 0.1752217711508274 test_loss: 0.17199238538742065
epoch: 135 training_loss 0.171234747543931 test_loss: 0.15901403427124022
epoch: 136 training_loss 0.17812966011464595 test_loss: 0.1795318603515625
epoch: 137 training_loss 0.17582216687500477 test_loss: 0.1819758176803589
epoch: 138 training_loss 0.1804033877700567 test_loss: 0.17873402833938598
epoch: 139 training_loss 0.1735933341830969 test_loss: 0.17914907932281493
epoch: 140 training_loss 0.17661945559084416 test_loss: 0.17954423427581787
epoch: 141 training_loss 0.18274262756109239 test_loss: 0.1747828245162964
epoch: 142 training_loss 0.1791179696470499 test_loss: 0.1914171576499939
epoch: 143 training_loss 0.18088172182440757 test_loss: 0.1924234986305237
epoch: 144 training_loss 0.17866764642298222 test_loss: 0.17818691730499267
epoch: 145 training_loss 0.1731168707460165 test_loss: 0.16489570140838622
epoch: 146 training_loss 0.17767813354730605 test_loss: 0.19603147506713867
epoch: 147 training_loss 0.17278014719486237 test_loss: 0.2012732744216919
epoch: 148 training_loss 0.17319633498787879 test_loss: 0.17141653299331666
epoch: 149 training_loss 0.1792177826166153 test_loss: 0.17746845483779908
epoch: 0 training_loss 8.455631098747254 test_loss: 4.874840927124024
epoch: 1 training_loss 3.980350661277771 test_loss: 3.262343978881836
epoch: 2 training_loss 2.807254590988159 test_loss: 2.4403371810913086
epoch: 3 training_loss 2.21902889251709 test_loss: 2.03299503326416
epoch: 4 training_loss 1.8890213692188262 test_loss: 1.7821754455566405
epoch: 5 training_loss 1.6873731982707978 test_loss: 1.5580315589904785
epoch: 6 training_loss 1.4956488740444183 test_loss: 1.439680576324463
epoch: 7 training_loss 1.3823819768428802 test_loss: 1.2995254516601562
epoch: 8 training_loss 1.2865978074073792 test_loss: 1.2651881217956542
epoch: 9 training_loss 1.206110279560089 test_loss: 1.1767148971557617
epoch: 10 training_loss 1.17010271191597 test_loss: 1.1697086334228515
epoch: 11 training_loss 1.1079410737752915 test_loss: 1.0704676628112793
epoch: 12 training_loss 1.0574748200178146 test_loss: 1.0694168090820313
epoch: 13 training_loss 1.0320990204811096 test_loss: 0.9915635108947753
epoch: 14 training_loss 0.9916883033514022 test_loss: 0.9951230049133301
epoch: 15 training_loss 0.9721267795562745 test_loss: 0.9971456527709961
epoch: 16 training_loss 0.9562592488527298 test_loss: 0.9188754081726074
epoch: 17 training_loss 0.918233626484871 test_loss: 0.911561107635498
epoch: 18 training_loss 0.9089507448673249 test_loss: 0.8771992683410644
epoch: 19 training_loss 0.8740478509664535 test_loss: 0.9036388397216797
epoch: 20 training_loss 0.8753651046752929 test_loss: 0.8507102966308594
epoch: 21 training_loss 0.8670431452989579 test_loss: 0.8549290657043457
epoch: 22 training_loss 0.8482623493671417 test_loss: 0.8160715103149414
epoch: 23 training_loss 0.8218281155824662 test_loss: 0.8438438415527344
epoch: 24 training_loss 0.8107279747724533 test_loss: 0.8276498794555665
epoch: 25 training_loss 0.817173997759819 test_loss: 0.8294285774230957
epoch: 26 training_loss 0.8007082253694534 test_loss: 0.7996747016906738
epoch: 27 training_loss 0.7702753436565399 test_loss: 0.7706540107727051
epoch: 28 training_loss 0.7807806777954102 test_loss: 0.7811206817626953
epoch: 29 training_loss 0.7736529636383057 test_loss: 0.759101676940918
epoch: 30 training_loss 0.7643219411373139 test_loss: 0.7690239429473877
epoch: 31 training_loss 0.7432204931974411 test_loss: 0.7799849033355712
epoch: 32 training_loss 0.7340252333879471 test_loss: 0.7545377731323242
epoch: 33 training_loss 0.7432934409379959 test_loss: 0.7277895927429199
epoch: 34 training_loss 0.7351522308588028 test_loss: 0.717139720916748
epoch: 35 training_loss 0.7234722065925598 test_loss: 0.7190459728240967
epoch: 36 training_loss 0.7083807164430618 test_loss: 0.7015434741973877
epoch: 37 training_loss 0.7079499727487564 test_loss: 0.7076235294342041
epoch: 38 training_loss 0.6967619293928147 test_loss: 0.700911569595337
epoch: 39 training_loss 0.7012729924917221 test_loss: 0.7072965145111084
epoch: 40 training_loss 0.689866019487381 test_loss: 0.6833374500274658
epoch: 41 training_loss 0.6877919149398803 test_loss: 0.6781499862670899
epoch: 42 training_loss 0.6860608649253845 test_loss: 0.672447919845581
epoch: 43 training_loss 0.676186049580574 test_loss: 0.6846327781677246
epoch: 44 training_loss 0.6779000967741012 test_loss: 0.6918675899505615
epoch: 45 training_loss 0.6742876416444779 test_loss: 0.6855663299560547
epoch: 46 training_loss 0.6716094356775284 test_loss: 0.6517754077911377
epoch: 47 training_loss 0.6593248480558396 test_loss: 0.6816854000091552
epoch: 48 training_loss 0.6700307524204254 test_loss: 0.6510532855987549
epoch: 49 training_loss 0.6600621527433396 test_loss: 0.6481260299682617
epoch: 50 training_loss 0.6453728604316712 test_loss: 0.6571078777313233
epoch: 51 training_loss 0.6360410732030869 test_loss: 0.6511127948760986
epoch: 52 training_loss 0.6417792373895645 test_loss: 0.6415196418762207
epoch: 53 training_loss 0.6420526909828186 test_loss: 0.6504530906677246
epoch: 54 training_loss 0.6357854962348938 test_loss: 0.6457548618316651
epoch: 55 training_loss 0.6384108078479767 test_loss: 0.6315855979919434
epoch: 56 training_loss 0.6221099704504013 test_loss: 0.6298859119415283
epoch: 57 training_loss 0.6260524821281434 test_loss: 0.6197275638580322
epoch: 58 training_loss 0.6250703692436218 test_loss: 0.6227630138397217
epoch: 59 training_loss 0.6181373000144958 test_loss: 0.6097221374511719
epoch: 60 training_loss 0.6164611303806304 test_loss: 0.6049537181854248
epoch: 61 training_loss 0.6070383429527283 test_loss: 0.6084271430969238
epoch: 62 training_loss 0.6219899505376816 test_loss: 0.6077181339263916
epoch: 63 training_loss 0.6105371743440628 test_loss: 0.6021414756774902
epoch: 64 training_loss 0.6027158862352371 test_loss: 0.5919923782348633
epoch: 65 training_loss 0.6012266737222671 test_loss: 0.5966594219207764
epoch: 66 training_loss 0.5933283817768097 test_loss: 0.6107742309570312
epoch: 67 training_loss 0.5936806172132492 test_loss: 0.5969294548034668
epoch: 68 training_loss 0.5897098851203918 test_loss: 0.5927653789520264
epoch: 69 training_loss 0.5951081192493439 test_loss: 0.6186005115509033
epoch: 70 training_loss 0.5928949695825577 test_loss: 0.579622459411621
epoch: 71 training_loss 0.5845723468065261 test_loss: 0.5807106018066406
epoch: 72 training_loss 0.5822089266777039 test_loss: 0.5784276485443115
epoch: 73 training_loss 0.5717308461666107 test_loss: 0.5711761474609375
epoch: 74 training_loss 0.5785921913385391 test_loss: 0.5727970600128174
epoch: 75 training_loss 0.5726956808567047 test_loss: 0.5783040523529053
epoch: 76 training_loss 0.5671898245811462 test_loss: 0.5566776275634766
epoch: 77 training_loss 0.5778618821501732 test_loss: 0.5650486469268798
epoch: 78 training_loss 0.5843928036093712 test_loss: 0.5868534088134766
epoch: 79 training_loss 0.5663550019264221 test_loss: 0.5627758979797364
epoch: 80 training_loss 0.5547645714879036 test_loss: 0.5571025848388672
epoch: 81 training_loss 0.5648875805735588 test_loss: 0.5416267395019532
epoch: 82 training_loss 0.5597930634021759 test_loss: 0.5658199787139893
epoch: 83 training_loss 0.560393685400486 test_loss: 0.5736475944519043
epoch: 84 training_loss 0.5654184213280677 test_loss: 0.5566821575164795
epoch: 85 training_loss 0.5557221835851669 test_loss: 0.5503764629364014
epoch: 86 training_loss 0.5576385855674744 test_loss: 0.5501503944396973
epoch: 87 training_loss 0.5546851414442062 test_loss: 0.5400971412658692
epoch: 88 training_loss 0.5430439203977585 test_loss: 0.5535492897033691
epoch: 89 training_loss 0.5489831802248955 test_loss: 0.546396017074585
epoch: 90 training_loss 0.5525594526529312 test_loss: 0.5562356472015381
epoch: 91 training_loss 0.5521018025279045 test_loss: 0.5384581089019775
epoch: 92 training_loss 0.5464907622337342 test_loss: 0.5358936309814453
epoch: 93 training_loss 0.5508544203639031 test_loss: 0.5324770927429199
epoch: 94 training_loss 0.5476646456122398 test_loss: 0.528942060470581
epoch: 95 training_loss 0.5464314872026443 test_loss: 0.5299147605895996
epoch: 96 training_loss 0.5376394808292388 test_loss: 0.5274588108062744
epoch: 97 training_loss 0.5339926210045814 test_loss: 0.539856243133545
epoch: 98 training_loss 0.5379748031497001 test_loss: 0.5448385715484619
epoch: 99 training_loss 0.5406453654170036 test_loss: 0.5320689678192139
epoch: 100 training_loss 0.5340276634693146 test_loss: 0.5350244522094727
epoch: 101 training_loss 0.545971155166626 test_loss: 0.5138480186462402
epoch: 102 training_loss 0.5338306856155396 test_loss: 0.5357932090759278
epoch: 103 training_loss 0.5351324224472046 test_loss: 0.5524104595184326
epoch: 104 training_loss 0.5400123941898346 test_loss: 0.5317421436309815
epoch: 105 training_loss 0.5275990656018257 test_loss: 0.542564582824707
epoch: 106 training_loss 0.5227995911240577 test_loss: 0.5163575172424316
epoch: 107 training_loss 0.5389769607782364 test_loss: 0.5371107578277587
epoch: 108 training_loss 0.5243929064273835 test_loss: 0.5182351112365723
epoch: 109 training_loss 0.5197322022914886 test_loss: 0.5128312110900879
epoch: 110 training_loss 0.5267595899105072 test_loss: 0.5240979194641113
epoch: 111 training_loss 0.5285060769319534 test_loss: 0.5109014511108398
epoch: 112 training_loss 0.5273750364780426 test_loss: 0.5249574184417725
epoch: 113 training_loss 0.5135258436203003 test_loss: 0.5203430652618408
epoch: 114 training_loss 0.5202417680621148 test_loss: 0.5214693546295166
epoch: 115 training_loss 0.5155173793435097 test_loss: 0.5065935611724853
epoch: 116 training_loss 0.5112528970837593 test_loss: 0.522100830078125
epoch: 117 training_loss 0.520849485695362 test_loss: 0.5011869430541992
epoch: 118 training_loss 0.5157065966725349 test_loss: 0.5314475059509277
epoch: 119 training_loss 0.5176545798778533 test_loss: 0.5126045703887939
epoch: 120 training_loss 0.5233160358667374 test_loss: 0.5063830375671386
epoch: 121 training_loss 0.5051581025123596 test_loss: 0.5013707637786865
epoch: 122 training_loss 0.5051003560423851 test_loss: 0.5037714004516601
epoch: 123 training_loss 0.5098245310783386 test_loss: 0.5025711059570312
epoch: 124 training_loss 0.5071230134367943 test_loss: 0.5212574005126953
epoch: 125 training_loss 0.518044250011444 test_loss: 0.531232500076294
epoch: 126 training_loss 0.5119419604539871 test_loss: 0.5211390018463135
epoch: 127 training_loss 0.5093372136354446 test_loss: 0.5117077827453613
epoch: 128 training_loss 0.5069016236066818 test_loss: 0.5276989936828613
epoch: 129 training_loss 0.504485302567482 test_loss: 0.5091427326202392
epoch: 130 training_loss 0.5008845391869545 test_loss: 0.5189262866973877
epoch: 131 training_loss 0.5000675404071808 test_loss: 0.495023250579834
epoch: 132 training_loss 0.5015609276294708 test_loss: 0.5006596565246582
epoch: 133 training_loss 0.5025202402472496 test_loss: 0.5017219066619873
epoch: 134 training_loss 0.5026366549730301 test_loss: 0.4978030204772949
epoch: 135 training_loss 0.5039052620530129 test_loss: 0.5054725646972656
epoch: 136 training_loss 0.4982076054811478 test_loss: 0.5039443492889404
epoch: 137 training_loss 0.49776716709136964 test_loss: 0.5044313907623291
epoch: 138 training_loss 0.49028740674257276 test_loss: 0.49421491622924807
epoch: 139 training_loss 0.4965811306238174 test_loss: 0.5036145210266113
epoch: 140 training_loss 0.4934667468070984 test_loss: 0.48832526206970217
epoch: 141 training_loss 0.5030863255262374 test_loss: 0.5000674247741699
epoch: 142 training_loss 0.4972861012816429 test_loss: 0.48731317520141604
epoch: 143 training_loss 0.5022327581048012 test_loss: 0.4767801284790039
epoch: 144 training_loss 0.5037685042619705 test_loss: 0.504144811630249
epoch: 145 training_loss 0.490904980301857 test_loss: 0.48979172706604
epoch: 146 training_loss 0.496113124191761 test_loss: 0.47230329513549807
epoch: 147 training_loss 0.4934482556581497 test_loss: 0.4754815101623535
epoch: 148 training_loss 0.489494736790657 test_loss: 0.4814916610717773
epoch: 149 training_loss 0.4900140997767448 test_loss: 0.48120918273925783
2207.5275872311186
episode: 0 training return: tensor(-346.5738, device='cuda:0')
episode: 1 training return: tensor(-364.8105, device='cuda:0')
episode: 2 training return: tensor(250.3103, device='cuda:0')
episode: 3 training return: tensor(58.6936, device='cuda:0')
epoch: 1 test_true_pfm: 1334.9669435920216 sim_pfm: -136.65076240159883
episode: 4 training return: tensor(-331.5024, device='cuda:0')
episode: 5 training return: tensor(-253.4171, device='cuda:0')
episode: 6 training return: tensor(-292.2253, device='cuda:0')
episode: 7 training return: tensor(267.0608, device='cuda:0')
epoch: 2 test_true_pfm: 2541.9628321002856 sim_pfm: -233.16324655824187
episode: 8 training return: tensor(-351.4234, device='cuda:0')
episode: 9 training return: tensor(4.7788, device='cuda:0')
episode: 10 training return: tensor(-450.1280, device='cuda:0')
episode: 11 training return: tensor(-269.7982, device='cuda:0')
epoch: 3 test_true_pfm: 1234.8561106859354 sim_pfm: -382.78828505417914
episode: 12 training return: tensor(295.9078, device='cuda:0')
episode: 13 training return: tensor(-326.0122, device='cuda:0')
episode: 14 training return: tensor(-427.5166, device='cuda:0')
episode: 15 training return: tensor(-83.0406, device='cuda:0')
epoch: 4 test_true_pfm: 2229.4626235847954 sim_pfm: -120.85667229367148
episode: 16 training return: tensor(-146.6169, device='cuda:0')
episode: 17 training return: tensor(-217.7293, device='cuda:0')
episode: 18 training return: tensor(-195.6572, device='cuda:0')
episode: 19 training return: tensor(-314.5823, device='cuda:0')
epoch: 5 test_true_pfm: 1423.3006567918237 sim_pfm: -100.24679467308063
episode: 20 training return: tensor(-426.1367, device='cuda:0')
episode: 21 training return: tensor(-157.6208, device='cuda:0')
episode: 22 training return: tensor(-477.6339, device='cuda:0')
episode: 23 training return: tensor(-321.2043, device='cuda:0')
epoch: 6 test_true_pfm: 2145.3860157630747 sim_pfm: -46.77062384594077
episode: 24 training return: tensor(-347.2536, device='cuda:0')
episode: 25 training return: tensor(-109.7739, device='cuda:0')
episode: 26 training return: tensor(261.0493, device='cuda:0')
episode: 27 training return: tensor(-127.8121, device='cuda:0')
epoch: 7 test_true_pfm: 1303.7291314322092 sim_pfm: -412.70337960199686
episode: 28 training return: tensor(-220.4263, device='cuda:0')
episode: 29 training return: tensor(-405.5499, device='cuda:0')
episode: 30 training return: tensor(-315.9300, device='cuda:0')
episode: 31 training return: tensor(-264.1172, device='cuda:0')
epoch: 8 test_true_pfm: 1776.4734666170214 sim_pfm: -65.69826082172222
episode: 32 training return: tensor(45.7270, device='cuda:0')
episode: 33 training return: tensor(99.0180, device='cuda:0')
episode: 34 training return: tensor(-97.7402, device='cuda:0')
episode: 35 training return: tensor(-402.0051, device='cuda:0')
epoch: 9 test_true_pfm: 1286.4243450408221 sim_pfm: -385.282895750046
episode: 36 training return: tensor(-416.2893, device='cuda:0')
episode: 37 training return: tensor(-402.7103, device='cuda:0')
episode: 38 training return: tensor(-418.1748, device='cuda:0')
episode: 39 training return: tensor(-271.5199, device='cuda:0')
epoch: 10 test_true_pfm: 1274.101439584414 sim_pfm: -355.250583684848
episode: 40 training return: tensor(244.6857, device='cuda:0')
episode: 41 training return: tensor(-367.8052, device='cuda:0')
episode: 42 training return: tensor(-390.9592, device='cuda:0')
episode: 43 training return: tensor(-302.8125, device='cuda:0')
epoch: 11 test_true_pfm: 2092.207797612748 sim_pfm: -262.7127428913179
episode: 44 training return: tensor(-430.7821, device='cuda:0')
episode: 45 training return: tensor(-330.2101, device='cuda:0')
episode: 46 training return: tensor(-382.2076, device='cuda:0')
episode: 47 training return: tensor(-397.0382, device='cuda:0')
epoch: 12 test_true_pfm: 1347.0537496497725 sim_pfm: -327.3427371464204
episode: 48 training return: tensor(-389.8927, device='cuda:0')
episode: 49 training return: tensor(206.5205, device='cuda:0')
episode: 50 training return: tensor(-407.4479, device='cuda:0')
episode: 51 training return: tensor(-357.9343, device='cuda:0')
epoch: 13 test_true_pfm: 2283.7562482730386 sim_pfm: -231.10233266993114
episode: 52 training return: tensor(-360.1744, device='cuda:0')
episode: 53 training return: tensor(-48.8646, device='cuda:0')
episode: 54 training return: tensor(-183.3609, device='cuda:0')
episode: 55 training return: tensor(-253.6908, device='cuda:0')
epoch: 14 test_true_pfm: 2297.5243330331746 sim_pfm: 74.96952018665615
episode: 56 training return: tensor(-435.0612, device='cuda:0')
episode: 57 training return: tensor(-171.4349, device='cuda:0')
episode: 58 training return: tensor(-387.9931, device='cuda:0')
episode: 59 training return: tensor(-271.2273, device='cuda:0')
epoch: 15 test_true_pfm: 1968.229753114174 sim_pfm: -127.38853210649297
episode: 60 training return: tensor(-388.9911, device='cuda:0')
episode: 61 training return: tensor(-166.3099, device='cuda:0')
episode: 62 training return: tensor(-273.5710, device='cuda:0')
episode: 63 training return: tensor(-353.3974, device='cuda:0')
epoch: 16 test_true_pfm: 2181.9905388501793 sim_pfm: -80.28594997878342
episode: 64 training return: tensor(-112.3160, device='cuda:0')
episode: 65 training return: tensor(-358.8196, device='cuda:0')
episode: 66 training return: tensor(-288.8578, device='cuda:0')
episode: 67 training return: tensor(16.5433, device='cuda:0')
epoch: 17 test_true_pfm: 2477.0472032279417 sim_pfm: -202.40697977453237
episode: 68 training return: tensor(-357.2571, device='cuda:0')
episode: 69 training return: tensor(-258.7638, device='cuda:0')
episode: 70 training return: tensor(-343.4354, device='cuda:0')
episode: 71 training return: tensor(-349.4490, device='cuda:0')
epoch: 18 test_true_pfm: 1819.8839815663123 sim_pfm: -210.41701803728938
episode: 72 training return: tensor(-200.9641, device='cuda:0')
episode: 73 training return: tensor(-315.8601, device='cuda:0')
episode: 74 training return: tensor(-288.9044, device='cuda:0')
episode: 75 training return: tensor(-405.5344, device='cuda:0')
epoch: 19 test_true_pfm: 1755.5770422765709 sim_pfm: -263.9456492250708
episode: 76 training return: tensor(-262.0158, device='cuda:0')
episode: 77 training return: tensor(239.2197, device='cuda:0')
episode: 78 training return: tensor(-261.9543, device='cuda:0')
episode: 79 training return: tensor(91.4492, device='cuda:0')
epoch: 20 test_true_pfm: 1702.5743993938468 sim_pfm: -157.1925014757629
episode: 80 training return: tensor(-398.3387, device='cuda:0')
episode: 81 training return: tensor(-241.0865, device='cuda:0')
episode: 82 training return: tensor(-64.3698, device='cuda:0')
episode: 83 training return: tensor(-389.7336, device='cuda:0')
epoch: 21 test_true_pfm: 1909.8411609779312 sim_pfm: -187.63771573857716
episode: 84 training return: tensor(-247.3283, device='cuda:0')
episode: 85 training return: tensor(-341.2383, device='cuda:0')
episode: 86 training return: tensor(-214.1614, device='cuda:0')
episode: 87 training return: tensor(233.7489, device='cuda:0')
epoch: 22 test_true_pfm: 2691.7853136599438 sim_pfm: -33.78536725352751
episode: 88 training return: tensor(318.5547, device='cuda:0')
episode: 89 training return: tensor(-390.3512, device='cuda:0')
episode: 90 training return: tensor(162.6046, device='cuda:0')
episode: 91 training return: tensor(-270.6563, device='cuda:0')
epoch: 23 test_true_pfm: 1871.6883177883903 sim_pfm: -151.71135975072198
episode: 92 training return: tensor(-138.2667, device='cuda:0')
episode: 93 training return: tensor(-28.0908, device='cuda:0')
episode: 94 training return: tensor(-391.4064, device='cuda:0')
episode: 95 training return: tensor(-250.2236, device='cuda:0')
epoch: 24 test_true_pfm: 2178.2972459929993 sim_pfm: -153.64925546773398
episode: 96 training return: tensor(-230.6297, device='cuda:0')
episode: 97 training return: tensor(256.6497, device='cuda:0')
episode: 98 training return: tensor(-327.4569, device='cuda:0')
episode: 99 training return: tensor(-118.4360, device='cuda:0')
epoch: 25 test_true_pfm: 1615.2403514886598 sim_pfm: -66.8807687954007
episode: 100 training return: tensor(-413.3060, device='cuda:0')
episode: 101 training return: tensor(-309.1268, device='cuda:0')
episode: 102 training return: tensor(-343.6870, device='cuda:0')
episode: 103 training return: tensor(-300.2698, device='cuda:0')
epoch: 26 test_true_pfm: 2401.439110502718 sim_pfm: -223.9661196419038
episode: 104 training return: tensor(-251.1352, device='cuda:0')
episode: 105 training return: tensor(-266.2992, device='cuda:0')
episode: 106 training return: tensor(-347.9679, device='cuda:0')
episode: 107 training return: tensor(-261.5486, device='cuda:0')
epoch: 27 test_true_pfm: 2632.999887905207 sim_pfm: -48.28840037087988
episode: 108 training return: tensor(-343.3538, device='cuda:0')
episode: 109 training return: tensor(-393.0700, device='cuda:0')
episode: 110 training return: tensor(-39.8390, device='cuda:0')
episode: 111 training return: tensor(-177.8037, device='cuda:0')
epoch: 28 test_true_pfm: 1909.8694429898153 sim_pfm: 87.21021488766807
episode: 112 training return: tensor(72.1011, device='cuda:0')
episode: 113 training return: tensor(-189.5661, device='cuda:0')
episode: 114 training return: tensor(-369.8285, device='cuda:0')
episode: 115 training return: tensor(249.7076, device='cuda:0')
epoch: 29 test_true_pfm: 2102.3308662552968 sim_pfm: 8.71046472939391
episode: 116 training return: tensor(-398.9268, device='cuda:0')
episode: 117 training return: tensor(-222.5244, device='cuda:0')
episode: 118 training return: tensor(-361.1375, device='cuda:0')
episode: 119 training return: tensor(269.2903, device='cuda:0')
epoch: 30 test_true_pfm: 2440.296448287989 sim_pfm: 174.9800426629954
episode: 120 training return: tensor(-282.0182, device='cuda:0')
episode: 121 training return: tensor(-280.8198, device='cuda:0')
episode: 122 training return: tensor(-2.5193, device='cuda:0')
episode: 123 training return: tensor(93.3965, device='cuda:0')
epoch: 31 test_true_pfm: 2752.9662130615493 sim_pfm: -98.41595959263698
episode: 124 training return: tensor(-395.8347, device='cuda:0')
episode: 125 training return: tensor(-250.9673, device='cuda:0')
episode: 126 training return: tensor(-354.6332, device='cuda:0')
episode: 127 training return: tensor(-397.4273, device='cuda:0')
epoch: 32 test_true_pfm: 1619.21722933659 sim_pfm: -152.1807173974424
episode: 128 training return: tensor(-245.6626, device='cuda:0')
episode: 129 training return: tensor(-179.2529, device='cuda:0')
episode: 130 training return: tensor(-192.9327, device='cuda:0')
episode: 131 training return: tensor(-268.6830, device='cuda:0')
epoch: 33 test_true_pfm: 2731.5226860577045 sim_pfm: -21.295446163547847
episode: 132 training return: tensor(-265.2972, device='cuda:0')
episode: 133 training return: tensor(-170.9824, device='cuda:0')
episode: 134 training return: tensor(-228.3351, device='cuda:0')
episode: 135 training return: tensor(-165.2164, device='cuda:0')
epoch: 34 test_true_pfm: 2156.4688777470446 sim_pfm: -273.6138714835203
episode: 136 training return: tensor(-104.5708, device='cuda:0')
episode: 137 training return: tensor(-297.4259, device='cuda:0')
episode: 138 training return: tensor(-306.4982, device='cuda:0')
episode: 139 training return: tensor(-49.4400, device='cuda:0')
epoch: 35 test_true_pfm: 1611.5771912121954 sim_pfm: -159.7739548505051
episode: 140 training return: tensor(-17.3191, device='cuda:0')
episode: 141 training return: tensor(-20.7693, device='cuda:0')
episode: 142 training return: tensor(-58.2101, device='cuda:0')
episode: 143 training return: tensor(-394.0151, device='cuda:0')
epoch: 36 test_true_pfm: 3195.835788968868 sim_pfm: 160.40150685790772
episode: 144 training return: tensor(266.1631, device='cuda:0')
episode: 145 training return: tensor(-252.7561, device='cuda:0')
episode: 146 training return: tensor(-118.8645, device='cuda:0')
episode: 147 training return: tensor(-283.1627, device='cuda:0')
epoch: 37 test_true_pfm: 1730.4736049613255 sim_pfm: -233.71215595204072
episode: 148 training return: tensor(-87.5733, device='cuda:0')
episode: 149 training return: tensor(-252.5581, device='cuda:0')
episode: 150 training return: tensor(-23.3139, device='cuda:0')
episode: 151 training return: tensor(290.3709, device='cuda:0')
epoch: 38 test_true_pfm: 1685.940071619807 sim_pfm: -191.63989222581344
episode: 152 training return: tensor(25.6006, device='cuda:0')
episode: 153 training return: tensor(-396.9558, device='cuda:0')
episode: 154 training return: tensor(-409.7262, device='cuda:0')
episode: 155 training return: tensor(-342.4698, device='cuda:0')
epoch: 39 test_true_pfm: 1792.3253156765722 sim_pfm: -177.83120725560002
episode: 156 training return: tensor(184.1653, device='cuda:0')
episode: 157 training return: tensor(312.2267, device='cuda:0')
episode: 158 training return: tensor(28.0661, device='cuda:0')
episode: 159 training return: tensor(-22.2119, device='cuda:0')
epoch: 40 test_true_pfm: 3155.0194268793316 sim_pfm: 97.80220318213105
episode: 160 training return: tensor(-254.6761, device='cuda:0')
episode: 161 training return: tensor(-39.6753, device='cuda:0')
episode: 162 training return: tensor(-239.3158, device='cuda:0')
episode: 163 training return: tensor(-283.9003, device='cuda:0')
epoch: 41 test_true_pfm: 1615.4173971404962 sim_pfm: -93.23000395065174
episode: 164 training return: tensor(-213.3891, device='cuda:0')
episode: 165 training return: tensor(-139.6523, device='cuda:0')
episode: 166 training return: tensor(277.1857, device='cuda:0')
episode: 167 training return: tensor(-7.7916, device='cuda:0')
epoch: 42 test_true_pfm: 1665.7046934725759 sim_pfm: -172.26567890285514
episode: 168 training return: tensor(-24.1139, device='cuda:0')
episode: 169 training return: tensor(-390.4791, device='cuda:0')
episode: 170 training return: tensor(88.0770, device='cuda:0')
episode: 171 training return: tensor(-281.3596, device='cuda:0')
epoch: 43 test_true_pfm: 1692.5197920428202 sim_pfm: -66.5088564864709
episode: 172 training return: tensor(-396.2604, device='cuda:0')
episode: 173 training return: tensor(-96.2173, device='cuda:0')
episode: 174 training return: tensor(-266.8181, device='cuda:0')
episode: 175 training return: tensor(-94.6676, device='cuda:0')
epoch: 44 test_true_pfm: 2071.9577076816836 sim_pfm: -66.48073108081978
episode: 176 training return: tensor(-291.4309, device='cuda:0')
episode: 177 training return: tensor(-34.1154, device='cuda:0')
episode: 178 training return: tensor(-352.3215, device='cuda:0')
episode: 179 training return: tensor(-397.8647, device='cuda:0')
epoch: 45 test_true_pfm: 1872.3936709684538 sim_pfm: 25.910613501114614
episode: 180 training return: tensor(-416.1487, device='cuda:0')
episode: 181 training return: tensor(-362.6052, device='cuda:0')
episode: 182 training return: tensor(-68.7915, device='cuda:0')
episode: 183 training return: tensor(-267.5622, device='cuda:0')
epoch: 46 test_true_pfm: 2078.8374294805926 sim_pfm: -156.73400253601721
episode: 184 training return: tensor(-269.0771, device='cuda:0')
episode: 185 training return: tensor(-275.8308, device='cuda:0')
episode: 186 training return: tensor(-399.0425, device='cuda:0')
episode: 187 training return: tensor(204.1909, device='cuda:0')
epoch: 47 test_true_pfm: 1917.9354786175873 sim_pfm: 16.707304032868706
episode: 188 training return: tensor(305.3204, device='cuda:0')
episode: 189 training return: tensor(292.5020, device='cuda:0')
episode: 190 training return: tensor(-27.3909, device='cuda:0')
episode: 191 training return: tensor(-205.4847, device='cuda:0')
epoch: 48 test_true_pfm: 1609.6778379074158 sim_pfm: -236.51011330409287
episode: 192 training return: tensor(-331.2285, device='cuda:0')
episode: 193 training return: tensor(-242.4825, device='cuda:0')
episode: 194 training return: tensor(-315.5201, device='cuda:0')
episode: 195 training return: tensor(45.9625, device='cuda:0')
epoch: 49 test_true_pfm: 2324.610675186752 sim_pfm: -180.410491743678
episode: 196 training return: tensor(-380.2640, device='cuda:0')
episode: 197 training return: tensor(-397.4041, device='cuda:0')
episode: 198 training return: tensor(-146.8626, device='cuda:0')
episode: 199 training return: tensor(39.5587, device='cuda:0')
epoch: 50 test_true_pfm: 2853.396097173383 sim_pfm: -153.77848853135947
episode: 200 training return: tensor(-337.3857, device='cuda:0')
episode: 201 training return: tensor(-313.7456, device='cuda:0')
episode: 202 training return: tensor(-218.2556, device='cuda:0')
episode: 203 training return: tensor(-20.0298, device='cuda:0')
epoch: 51 test_true_pfm: 1606.0931887048216 sim_pfm: -181.1705651358934
episode: 204 training return: tensor(223.3357, device='cuda:0')
episode: 205 training return: tensor(-257.0707, device='cuda:0')
episode: 206 training return: tensor(-201.8177, device='cuda:0')
episode: 207 training return: tensor(-390.4334, device='cuda:0')
epoch: 52 test_true_pfm: 1906.253907039444 sim_pfm: 164.69129821890965
episode: 208 training return: tensor(-165.8465, device='cuda:0')
episode: 209 training return: tensor(-116.8939, device='cuda:0')
episode: 210 training return: tensor(-359.5925, device='cuda:0')
episode: 211 training return: tensor(32.2582, device='cuda:0')
epoch: 53 test_true_pfm: 2093.3825097658882 sim_pfm: -106.00045840630385
episode: 212 training return: tensor(-38.9525, device='cuda:0')
episode: 213 training return: tensor(-63.8330, device='cuda:0')
episode: 214 training return: tensor(278.2044, device='cuda:0')
episode: 215 training return: tensor(-389.2259, device='cuda:0')
epoch: 54 test_true_pfm: 1928.9215057806975 sim_pfm: -105.88071081079154
episode: 216 training return: tensor(-150.5356, device='cuda:0')
episode: 217 training return: tensor(-392.1115, device='cuda:0')
episode: 218 training return: tensor(-280.9990, device='cuda:0')
episode: 219 training return: tensor(238.7422, device='cuda:0')
epoch: 55 test_true_pfm: 2335.5492878856185 sim_pfm: 16.66090242176627
episode: 220 training return: tensor(-17.6206, device='cuda:0')
episode: 221 training return: tensor(-247.3342, device='cuda:0')
episode: 222 training return: tensor(-82.7471, device='cuda:0')
episode: 223 training return: tensor(-304.9253, device='cuda:0')
epoch: 56 test_true_pfm: 2226.131614472903 sim_pfm: -258.68029862456024
episode: 224 training return: tensor(-198.1269, device='cuda:0')
episode: 225 training return: tensor(-283.7333, device='cuda:0')
episode: 226 training return: tensor(30.8360, device='cuda:0')
episode: 227 training return: tensor(-328.1089, device='cuda:0')
epoch: 57 test_true_pfm: 2924.947195940779 sim_pfm: -102.23883792860822
episode: 228 training return: tensor(-283.7677, device='cuda:0')
episode: 229 training return: tensor(180.7380, device='cuda:0')
episode: 230 training return: tensor(-327.0477, device='cuda:0')
episode: 231 training return: tensor(-95.3348, device='cuda:0')
epoch: 58 test_true_pfm: 2477.171772487163 sim_pfm: -64.20115556246795
episode: 232 training return: tensor(-288.9448, device='cuda:0')
episode: 233 training return: tensor(238.8234, device='cuda:0')
episode: 234 training return: tensor(-259.3922, device='cuda:0')
episode: 235 training return: tensor(-170.2689, device='cuda:0')
epoch: 59 test_true_pfm: 2199.3201656137426 sim_pfm: 87.6567644692065
episode: 236 training return: tensor(-3.7944, device='cuda:0')
episode: 237 training return: tensor(-288.4398, device='cuda:0')
episode: 238 training return: tensor(-338.1731, device='cuda:0')
episode: 239 training return: tensor(-391.8300, device='cuda:0')
epoch: 60 test_true_pfm: 1816.4098255545166 sim_pfm: 154.53432012080643
episode: 240 training return: tensor(-317.8603, device='cuda:0')
episode: 241 training return: tensor(-6.5500, device='cuda:0')
episode: 242 training return: tensor(-331.1198, device='cuda:0')
episode: 243 training return: tensor(-342.5902, device='cuda:0')
epoch: 61 test_true_pfm: 1615.277132124691 sim_pfm: -233.33718410039242
episode: 244 training return: tensor(-253.1983, device='cuda:0')
episode: 245 training return: tensor(-201.6853, device='cuda:0')
episode: 246 training return: tensor(-351.5932, device='cuda:0')
episode: 247 training return: tensor(-396.4797, device='cuda:0')
epoch: 62 test_true_pfm: 2961.1068364708804 sim_pfm: 76.63712752488209
episode: 248 training return: tensor(-118.8871, device='cuda:0')
episode: 249 training return: tensor(129.5715, device='cuda:0')
episode: 250 training return: tensor(-401.1886, device='cuda:0')
episode: 251 training return: tensor(-31.7219, device='cuda:0')
epoch: 63 test_true_pfm: 2004.2077436018255 sim_pfm: 86.69140580713672
episode: 252 training return: tensor(-141.4467, device='cuda:0')
episode: 253 training return: tensor(-393.0499, device='cuda:0')
episode: 254 training return: tensor(-82.1260, device='cuda:0')
episode: 255 training return: tensor(-402.7321, device='cuda:0')
epoch: 64 test_true_pfm: 2572.6886528014443 sim_pfm: 70.7472016926816
episode: 256 training return: tensor(-335.6192, device='cuda:0')
episode: 257 training return: tensor(-71.2312, device='cuda:0')
episode: 258 training return: tensor(45.4285, device='cuda:0')
episode: 259 training return: tensor(-28.7693, device='cuda:0')
epoch: 65 test_true_pfm: 2207.4993208479036 sim_pfm: -148.04797069510096
episode: 260 training return: tensor(-370.1985, device='cuda:0')
episode: 261 training return: tensor(-348.3232, device='cuda:0')
episode: 262 training return: tensor(-78.1446, device='cuda:0')
episode: 263 training return: tensor(163.3459, device='cuda:0')
epoch: 66 test_true_pfm: 2884.6628959119275 sim_pfm: -15.020087868169261
episode: 264 training return: tensor(-271.8980, device='cuda:0')
episode: 265 training return: tensor(-81.8499, device='cuda:0')
episode: 266 training return: tensor(-266.9692, device='cuda:0')
episode: 267 training return: tensor(-342.6859, device='cuda:0')
epoch: 67 test_true_pfm: 1617.71687611153 sim_pfm: -85.99754558282439
episode: 268 training return: tensor(-164.8035, device='cuda:0')
episode: 269 training return: tensor(-260.4808, device='cuda:0')
episode: 270 training return: tensor(-252.8855, device='cuda:0')
episode: 271 training return: tensor(-374.2208, device='cuda:0')
epoch: 68 test_true_pfm: 2234.874575523941 sim_pfm: 91.86259151249153
episode: 272 training return: tensor(294.2106, device='cuda:0')
episode: 273 training return: tensor(-210.7501, device='cuda:0')
episode: 274 training return: tensor(258.4717, device='cuda:0')
episode: 275 training return: tensor(245.2361, device='cuda:0')
epoch: 69 test_true_pfm: 2360.110301369987 sim_pfm: -4.092467467339399
episode: 276 training return: tensor(-168.5202, device='cuda:0')
episode: 277 training return: tensor(-387.3474, device='cuda:0')
episode: 278 training return: tensor(-320.5718, device='cuda:0')
episode: 279 training return: tensor(271.2090, device='cuda:0')
epoch: 70 test_true_pfm: 3237.307260555179 sim_pfm: 157.27820240182336
episode: 280 training return: tensor(-72.6789, device='cuda:0')
episode: 281 training return: tensor(-132.1627, device='cuda:0')
episode: 282 training return: tensor(-14.9425, device='cuda:0')
episode: 283 training return: tensor(-397.5246, device='cuda:0')
epoch: 71 test_true_pfm: 2634.363210600785 sim_pfm: -151.4339464609317
episode: 284 training return: tensor(-329.8317, device='cuda:0')
episode: 285 training return: tensor(-157.3238, device='cuda:0')
episode: 286 training return: tensor(-317.0398, device='cuda:0')
episode: 287 training return: tensor(38.6686, device='cuda:0')
epoch: 72 test_true_pfm: 1746.085790261721 sim_pfm: 22.371551718485232
episode: 288 training return: tensor(-346.4590, device='cuda:0')
episode: 289 training return: tensor(-34.1945, device='cuda:0')
episode: 290 training return: tensor(-395.0346, device='cuda:0')
episode: 291 training return: tensor(231.0170, device='cuda:0')
epoch: 73 test_true_pfm: 1920.4711496673706 sim_pfm: -137.33334360385197
episode: 292 training return: tensor(-241.6529, device='cuda:0')
episode: 293 training return: tensor(-350.0083, device='cuda:0')
episode: 294 training return: tensor(-41.0813, device='cuda:0')
episode: 295 training return: tensor(-263.8799, device='cuda:0')
epoch: 74 test_true_pfm: 2250.253441592828 sim_pfm: -176.76823308865036
episode: 296 training return: tensor(-94.9412, device='cuda:0')
episode: 297 training return: tensor(-263.9912, device='cuda:0')
episode: 298 training return: tensor(-38.4536, device='cuda:0')
episode: 299 training return: tensor(-275.1243, device='cuda:0')
epoch: 75 test_true_pfm: 1525.022266525364 sim_pfm: -295.0713074480591
episode: 300 training return: tensor(-287.0338, device='cuda:0')
episode: 301 training return: tensor(-269.1513, device='cuda:0')
episode: 302 training return: tensor(-195.0910, device='cuda:0')
episode: 303 training return: tensor(-292.0413, device='cuda:0')
epoch: 76 test_true_pfm: 2541.7855174932542 sim_pfm: -36.538220978264384
episode: 304 training return: tensor(-127.5380, device='cuda:0')
episode: 305 training return: tensor(-253.6807, device='cuda:0')
episode: 306 training return: tensor(138.6921, device='cuda:0')
episode: 307 training return: tensor(-263.2330, device='cuda:0')
epoch: 77 test_true_pfm: 1715.7946282630492 sim_pfm: -205.36369676627996
episode: 308 training return: tensor(-153.9978, device='cuda:0')
episode: 309 training return: tensor(-216.3222, device='cuda:0')
episode: 310 training return: tensor(87.4567, device='cuda:0')
episode: 311 training return: tensor(74.2875, device='cuda:0')
epoch: 78 test_true_pfm: 2300.6817334286784 sim_pfm: -216.90710247897854
episode: 312 training return: tensor(-238.6980, device='cuda:0')
episode: 313 training return: tensor(-169.8348, device='cuda:0')
episode: 314 training return: tensor(-266.3629, device='cuda:0')
episode: 315 training return: tensor(-236.2192, device='cuda:0')
epoch: 79 test_true_pfm: 1948.8392377413693 sim_pfm: -51.36709622927204
episode: 316 training return: tensor(-400.4870, device='cuda:0')
episode: 317 training return: tensor(-65.7086, device='cuda:0')
episode: 318 training return: tensor(-339.1523, device='cuda:0')
episode: 319 training return: tensor(-336.3457, device='cuda:0')
epoch: 80 test_true_pfm: 2747.5231280784096 sim_pfm: 38.593966181118354
episode: 320 training return: tensor(-80.1686, device='cuda:0')
episode: 321 training return: tensor(-253.3257, device='cuda:0')
episode: 322 training return: tensor(-13.8191, device='cuda:0')
episode: 323 training return: tensor(289.9268, device='cuda:0')
epoch: 81 test_true_pfm: 1862.7807474275894 sim_pfm: -333.8377397484631
episode: 324 training return: tensor(167.9517, device='cuda:0')
episode: 325 training return: tensor(-158.6145, device='cuda:0')
episode: 326 training return: tensor(273.9719, device='cuda:0')
episode: 327 training return: tensor(39.4866, device='cuda:0')
epoch: 82 test_true_pfm: 2797.932285800915 sim_pfm: -213.6256656423211
episode: 328 training return: tensor(-429.0497, device='cuda:0')
episode: 329 training return: tensor(-374.0152, device='cuda:0')
episode: 330 training return: tensor(247.9543, device='cuda:0')
episode: 331 training return: tensor(-216.6949, device='cuda:0')
epoch: 83 test_true_pfm: 2678.4684535772853 sim_pfm: -68.97344967947963
episode: 332 training return: tensor(-350.2164, device='cuda:0')
episode: 333 training return: tensor(-116.1390, device='cuda:0')
episode: 334 training return: tensor(-369.9732, device='cuda:0')
episode: 335 training return: tensor(244.2984, device='cuda:0')
epoch: 84 test_true_pfm: 1812.3333417559418 sim_pfm: -207.38122574131316
episode: 336 training return: tensor(-231.5043, device='cuda:0')
episode: 337 training return: tensor(-271.1659, device='cuda:0')
episode: 338 training return: tensor(315.7936, device='cuda:0')
episode: 339 training return: tensor(-155.9459, device='cuda:0')
epoch: 85 test_true_pfm: 1562.0216293225085 sim_pfm: -301.00240699746064
episode: 340 training return: tensor(256.2313, device='cuda:0')
episode: 341 training return: tensor(-191.4838, device='cuda:0')
episode: 342 training return: tensor(76.7587, device='cuda:0')
episode: 343 training return: tensor(97.6041, device='cuda:0')
epoch: 86 test_true_pfm: 3191.2713696907117 sim_pfm: -92.81700999710786
episode: 344 training return: tensor(57.2966, device='cuda:0')
episode: 345 training return: tensor(-368.5546, device='cuda:0')
episode: 346 training return: tensor(-252.3821, device='cuda:0')
episode: 347 training return: tensor(-257.1841, device='cuda:0')
epoch: 87 test_true_pfm: 1860.1154137762653 sim_pfm: -180.17316336984126
episode: 348 training return: tensor(-9.9961, device='cuda:0')
episode: 349 training return: tensor(-91.2005, device='cuda:0')
episode: 350 training return: tensor(-54.7245, device='cuda:0')
episode: 351 training return: tensor(-313.9025, device='cuda:0')
epoch: 88 test_true_pfm: 3118.117284189733 sim_pfm: 28.298798877823476
episode: 352 training return: tensor(-375.8435, device='cuda:0')
episode: 353 training return: tensor(299.7840, device='cuda:0')
episode: 354 training return: tensor(-387.5661, device='cuda:0')
episode: 355 training return: tensor(262.2605, device='cuda:0')
epoch: 89 test_true_pfm: 2712.269924453388 sim_pfm: 278.19415659589384
episode: 356 training return: tensor(-372.5752, device='cuda:0')
episode: 357 training return: tensor(-307.3417, device='cuda:0')
episode: 358 training return: tensor(-350.9910, device='cuda:0')
episode: 359 training return: tensor(294.8050, device='cuda:0')
epoch: 90 test_true_pfm: 1948.3020118081486 sim_pfm: -313.65483421869186
episode: 360 training return: tensor(-422.8259, device='cuda:0')
episode: 361 training return: tensor(28.6226, device='cuda:0')
episode: 362 training return: tensor(-114.6446, device='cuda:0')
episode: 363 training return: tensor(19.3381, device='cuda:0')
epoch: 91 test_true_pfm: 2124.8368003373434 sim_pfm: 101.23698710516328
episode: 364 training return: tensor(-357.4923, device='cuda:0')
episode: 365 training return: tensor(-13.1102, device='cuda:0')
episode: 366 training return: tensor(-258.3621, device='cuda:0')
episode: 367 training return: tensor(265.4637, device='cuda:0')
epoch: 92 test_true_pfm: 1875.8713634653843 sim_pfm: -284.51958010611514
episode: 368 training return: tensor(-245.6667, device='cuda:0')
episode: 369 training return: tensor(275.7027, device='cuda:0')
episode: 370 training return: tensor(-323.3087, device='cuda:0')
episode: 371 training return: tensor(-330.1485, device='cuda:0')
epoch: 93 test_true_pfm: 1949.4379301790466 sim_pfm: -304.3508321343882
episode: 372 training return: tensor(-331.8924, device='cuda:0')
episode: 373 training return: tensor(261.7879, device='cuda:0')
episode: 374 training return: tensor(-330.0711, device='cuda:0')
episode: 375 training return: tensor(-227.7826, device='cuda:0')
epoch: 94 test_true_pfm: 2096.61791592516 sim_pfm: -290.16429540514946
episode: 376 training return: tensor(-353.5058, device='cuda:0')
episode: 377 training return: tensor(264.3461, device='cuda:0')
episode: 378 training return: tensor(243.4348, device='cuda:0')
episode: 379 training return: tensor(-321.2961, device='cuda:0')
epoch: 95 test_true_pfm: 2398.637612332821 sim_pfm: -58.24027681610702
episode: 380 training return: tensor(-148.8823, device='cuda:0')
episode: 381 training return: tensor(-36.6154, device='cuda:0')
episode: 382 training return: tensor(-57.0880, device='cuda:0')
episode: 383 training return: tensor(302.3043, device='cuda:0')
epoch: 96 test_true_pfm: 2272.683882579348 sim_pfm: -16.549240448046476
episode: 384 training return: tensor(-246.5769, device='cuda:0')
episode: 385 training return: tensor(312.9701, device='cuda:0')
episode: 386 training return: tensor(-279.9327, device='cuda:0')
episode: 387 training return: tensor(293.8889, device='cuda:0')
epoch: 97 test_true_pfm: 1994.4060589315366 sim_pfm: -238.48292109753433
episode: 388 training return: tensor(314.7988, device='cuda:0')
episode: 389 training return: tensor(-154.8855, device='cuda:0')
episode: 390 training return: tensor(-118.9016, device='cuda:0')
episode: 391 training return: tensor(-72.6599, device='cuda:0')
epoch: 98 test_true_pfm: 1992.587330512781 sim_pfm: 309.9242339619668
episode: 392 training return: tensor(-154.9397, device='cuda:0')
episode: 393 training return: tensor(-151.1281, device='cuda:0')
episode: 394 training return: tensor(82.6228, device='cuda:0')
episode: 395 training return: tensor(179.5124, device='cuda:0')
epoch: 99 test_true_pfm: 3159.2135238814503 sim_pfm: 157.3241945038511
episode: 396 training return: tensor(-157.8915, device='cuda:0')
episode: 397 training return: tensor(225.5834, device='cuda:0')
episode: 398 training return: tensor(-143.4818, device='cuda:0')
episode: 399 training return: tensor(-95.8535, device='cuda:0')
epoch: 100 test_true_pfm: 2111.676008238075 sim_pfm: -152.16996335695148
episode: 400 training return: tensor(253.8764, device='cuda:0')
episode: 401 training return: tensor(-109.9557, device='cuda:0')
episode: 402 training return: tensor(-10.6438, device='cuda:0')
episode: 403 training return: tensor(251.8457, device='cuda:0')
epoch: 101 test_true_pfm: 2742.871621336135 sim_pfm: -76.60958289659659
episode: 404 training return: tensor(-105.0652, device='cuda:0')
episode: 405 training return: tensor(48.1216, device='cuda:0')
episode: 406 training return: tensor(-259.1980, device='cuda:0')
episode: 407 training return: tensor(-49.5408, device='cuda:0')
epoch: 102 test_true_pfm: 2566.9933526375753 sim_pfm: 196.20967094627363
episode: 408 training return: tensor(286.3538, device='cuda:0')
episode: 409 training return: tensor(-60.2699, device='cuda:0')
episode: 410 training return: tensor(-29.1022, device='cuda:0')
episode: 411 training return: tensor(-207.1353, device='cuda:0')
epoch: 103 test_true_pfm: 2475.4791601851466 sim_pfm: 165.3461145197895
episode: 412 training return: tensor(-276.5414, device='cuda:0')
episode: 413 training return: tensor(-330.1755, device='cuda:0')
episode: 414 training return: tensor(234.4634, device='cuda:0')
episode: 415 training return: tensor(57.4942, device='cuda:0')
epoch: 104 test_true_pfm: 1502.701801289405 sim_pfm: -236.25647031988288
episode: 416 training return: tensor(303.9492, device='cuda:0')
episode: 417 training return: tensor(-354.1661, device='cuda:0')
episode: 418 training return: tensor(-316.0005, device='cuda:0')
episode: 419 training return: tensor(-328.0081, device='cuda:0')
epoch: 105 test_true_pfm: 1553.6798942365251 sim_pfm: -317.13941315275343
episode: 420 training return: tensor(12.8127, device='cuda:0')
episode: 421 training return: tensor(305.8855, device='cuda:0')
episode: 422 training return: tensor(-260.4367, device='cuda:0')
episode: 423 training return: tensor(-175.7532, device='cuda:0')
epoch: 106 test_true_pfm: 3082.9331642443576 sim_pfm: 310.17625605582725
episode: 424 training return: tensor(-206.6535, device='cuda:0')
episode: 425 training return: tensor(-221.0158, device='cuda:0')
episode: 426 training return: tensor(259.2304, device='cuda:0')
episode: 427 training return: tensor(258.7802, device='cuda:0')
epoch: 107 test_true_pfm: 2000.1799920666354 sim_pfm: -115.0753229172745
episode: 428 training return: tensor(182.9004, device='cuda:0')
episode: 429 training return: tensor(-361.4202, device='cuda:0')
episode: 430 training return: tensor(-100.4133, device='cuda:0')
episode: 431 training return: tensor(-319.2515, device='cuda:0')
epoch: 108 test_true_pfm: 2407.20412248634 sim_pfm: -139.6393512437353
episode: 432 training return: tensor(4.4162, device='cuda:0')
episode: 433 training return: tensor(-289.0894, device='cuda:0')
episode: 434 training return: tensor(-181.3238, device='cuda:0')
episode: 435 training return: tensor(-113.0889, device='cuda:0')
epoch: 109 test_true_pfm: 3312.429988546825 sim_pfm: -57.50397721043555
episode: 436 training return: tensor(208.2544, device='cuda:0')
episode: 437 training return: tensor(-229.5243, device='cuda:0')
episode: 438 training return: tensor(70.5263, device='cuda:0')
episode: 439 training return: tensor(-324.4177, device='cuda:0')
epoch: 110 test_true_pfm: 2780.0007580161546 sim_pfm: -222.65617802572282
episode: 440 training return: tensor(-307.8486, device='cuda:0')
episode: 441 training return: tensor(-10.5557, device='cuda:0')
episode: 442 training return: tensor(3.9159, device='cuda:0')
episode: 443 training return: tensor(18.8558, device='cuda:0')
epoch: 111 test_true_pfm: 3289.1680998215884 sim_pfm: -63.01494205230847
episode: 444 training return: tensor(-65.3016, device='cuda:0')
episode: 445 training return: tensor(56.1509, device='cuda:0')
episode: 446 training return: tensor(290.1381, device='cuda:0')
episode: 447 training return: tensor(-372.6424, device='cuda:0')
epoch: 112 test_true_pfm: 1769.6762300909788 sim_pfm: -251.9498468032883
episode: 448 training return: tensor(-341.3461, device='cuda:0')
episode: 449 training return: tensor(-139.8106, device='cuda:0')
episode: 450 training return: tensor(-332.4740, device='cuda:0')
episode: 451 training return: tensor(17.5731, device='cuda:0')
epoch: 113 test_true_pfm: 1429.2626801199388 sim_pfm: 12.789174834731966
episode: 452 training return: tensor(278.7448, device='cuda:0')
episode: 453 training return: tensor(-329.2113, device='cuda:0')
episode: 454 training return: tensor(-303.8694, device='cuda:0')
episode: 455 training return: tensor(30.0191, device='cuda:0')
epoch: 114 test_true_pfm: 2405.006836164389 sim_pfm: -194.74170212373915
episode: 456 training return: tensor(-30.3029, device='cuda:0')
episode: 457 training return: tensor(120.4084, device='cuda:0')
episode: 458 training return: tensor(-339.9969, device='cuda:0')
episode: 459 training return: tensor(-138.9891, device='cuda:0')
epoch: 115 test_true_pfm: 1574.098523808432 sim_pfm: -284.2996682348118
episode: 460 training return: tensor(252.1774, device='cuda:0')
episode: 461 training return: tensor(34.5272, device='cuda:0')
episode: 462 training return: tensor(-329.4134, device='cuda:0')
episode: 463 training return: tensor(-318.8047, device='cuda:0')
epoch: 116 test_true_pfm: 2312.785844106184 sim_pfm: 114.49462142350967
episode: 464 training return: tensor(-45.7271, device='cuda:0')
episode: 465 training return: tensor(249.6277, device='cuda:0')
episode: 466 training return: tensor(-340.8700, device='cuda:0')
episode: 467 training return: tensor(29.9598, device='cuda:0')
epoch: 117 test_true_pfm: 2290.1881157122284 sim_pfm: -150.73661789576485
episode: 468 training return: tensor(111.7215, device='cuda:0')
episode: 469 training return: tensor(-157.7006, device='cuda:0')
episode: 470 training return: tensor(309.2842, device='cuda:0')
episode: 471 training return: tensor(285.1017, device='cuda:0')
epoch: 118 test_true_pfm: 2342.7970546335096 sim_pfm: 17.80930197169073
episode: 472 training return: tensor(215.1022, device='cuda:0')
episode: 473 training return: tensor(266.9296, device='cuda:0')
episode: 474 training return: tensor(-264.3439, device='cuda:0')
episode: 475 training return: tensor(244.4290, device='cuda:0')
epoch: 119 test_true_pfm: 2335.0370308098923 sim_pfm: 261.5566812933442
episode: 476 training return: tensor(-195.4426, device='cuda:0')
episode: 477 training return: tensor(-352.3328, device='cuda:0')
episode: 478 training return: tensor(-388.0412, device='cuda:0')
episode: 479 training return: tensor(277.9949, device='cuda:0')
epoch: 120 test_true_pfm: 2166.432603021486 sim_pfm: -93.58445922969258
episode: 480 training return: tensor(-273.2128, device='cuda:0')
episode: 481 training return: tensor(-62.1931, device='cuda:0')
episode: 482 training return: tensor(-414.7651, device='cuda:0')
episode: 483 training return: tensor(-169.8711, device='cuda:0')
epoch: 121 test_true_pfm: 2028.0078118397462 sim_pfm: -102.09068851095314
episode: 484 training return: tensor(169.2025, device='cuda:0')
episode: 485 training return: tensor(267.7220, device='cuda:0')
episode: 486 training return: tensor(248.7899, device='cuda:0')
episode: 487 training return: tensor(-394.8228, device='cuda:0')
epoch: 122 test_true_pfm: 1749.3012530276974 sim_pfm: -317.17928793219227
episode: 488 training return: tensor(290.6732, device='cuda:0')
episode: 489 training return: tensor(250.0512, device='cuda:0')
episode: 490 training return: tensor(251.4654, device='cuda:0')
episode: 491 training return: tensor(289.1577, device='cuda:0')
epoch: 123 test_true_pfm: 1953.1228681053271 sim_pfm: -51.619503223279025
episode: 492 training return: tensor(-334.6037, device='cuda:0')
episode: 493 training return: tensor(-235.2402, device='cuda:0')
episode: 494 training return: tensor(-274.1429, device='cuda:0')
episode: 495 training return: tensor(-246.5854, device='cuda:0')
epoch: 124 test_true_pfm: 2099.497145275727 sim_pfm: -311.1559704320098
episode: 496 training return: tensor(-338.4903, device='cuda:0')
episode: 497 training return: tensor(-171.5612, device='cuda:0')
episode: 498 training return: tensor(-268.2671, device='cuda:0')
episode: 499 training return: tensor(281.7885, device='cuda:0')
epoch: 125 test_true_pfm: 2120.409598138904 sim_pfm: 77.03912179230247
episode: 500 training return: tensor(-201.7321, device='cuda:0')
episode: 501 training return: tensor(-142.4710, device='cuda:0')
episode: 502 training return: tensor(281.5854, device='cuda:0')
episode: 503 training return: tensor(250.9591, device='cuda:0')
epoch: 126 test_true_pfm: 1732.2014732019052 sim_pfm: -328.7599338727111
episode: 504 training return: tensor(-298.7729, device='cuda:0')
episode: 505 training return: tensor(-241.3746, device='cuda:0')
episode: 506 training return: tensor(-444.9882, device='cuda:0')
episode: 507 training return: tensor(-147.1302, device='cuda:0')
epoch: 127 test_true_pfm: 3314.3655439527097 sim_pfm: 82.76206498178847
episode: 508 training return: tensor(-17.8117, device='cuda:0')
episode: 509 training return: tensor(-140.4531, device='cuda:0')
episode: 510 training return: tensor(289.6364, device='cuda:0')
episode: 511 training return: tensor(-339.2390, device='cuda:0')
epoch: 128 test_true_pfm: 1511.6647273823792 sim_pfm: -313.2569190626576
episode: 512 training return: tensor(-353.0750, device='cuda:0')
episode: 513 training return: tensor(321.8693, device='cuda:0')
episode: 514 training return: tensor(87.4325, device='cuda:0')
episode: 515 training return: tensor(88.1247, device='cuda:0')
epoch: 129 test_true_pfm: 1610.097584570216 sim_pfm: -330.5383831603297
episode: 516 training return: tensor(-253.4070, device='cuda:0')
episode: 517 training return: tensor(158.2161, device='cuda:0')
episode: 518 training return: tensor(242.3875, device='cuda:0')
episode: 519 training return: tensor(116.9202, device='cuda:0')
epoch: 130 test_true_pfm: 1591.989547259767 sim_pfm: -292.6996141439886
episode: 520 training return: tensor(-138.8574, device='cuda:0')
episode: 521 training return: tensor(25.0568, device='cuda:0')
episode: 522 training return: tensor(-287.9991, device='cuda:0')
episode: 523 training return: tensor(-181.2852, device='cuda:0')
epoch: 131 test_true_pfm: 3282.812772876898 sim_pfm: -135.98954305332154
episode: 524 training return: tensor(0.9409, device='cuda:0')
episode: 525 training return: tensor(-224.3319, device='cuda:0')
episode: 526 training return: tensor(258.2078, device='cuda:0')
episode: 527 training return: tensor(-215.9367, device='cuda:0')
epoch: 132 test_true_pfm: 1782.7486602119025 sim_pfm: 101.57650697720237
episode: 528 training return: tensor(-51.3665, device='cuda:0')
episode: 529 training return: tensor(-311.6074, device='cuda:0')
episode: 530 training return: tensor(-162.8100, device='cuda:0')
episode: 531 training return: tensor(41.1904, device='cuda:0')
epoch: 133 test_true_pfm: 2889.4484760556575 sim_pfm: -25.879480568362244
episode: 532 training return: tensor(230.5973, device='cuda:0')
episode: 533 training return: tensor(-352.2622, device='cuda:0')
episode: 534 training return: tensor(-59.3874, device='cuda:0')
episode: 535 training return: tensor(-277.7876, device='cuda:0')
epoch: 134 test_true_pfm: 1749.4031282459603 sim_pfm: -304.9584497415344
episode: 536 training return: tensor(75.2809, device='cuda:0')
episode: 537 training return: tensor(186.4055, device='cuda:0')
episode: 538 training return: tensor(-236.8332, device='cuda:0')
episode: 539 training return: tensor(-394.4256, device='cuda:0')
epoch: 135 test_true_pfm: 1665.7015865775754 sim_pfm: -184.16010834424137
episode: 540 training return: tensor(-234.1290, device='cuda:0')
episode: 541 training return: tensor(-331.4280, device='cuda:0')
episode: 542 training return: tensor(250.7203, device='cuda:0')
episode: 543 training return: tensor(-281.0919, device='cuda:0')
epoch: 136 test_true_pfm: 1471.5698681725014 sim_pfm: -314.5084017958725
episode: 544 training return: tensor(-6.7007, device='cuda:0')
episode: 545 training return: tensor(-283.8983, device='cuda:0')
episode: 546 training return: tensor(178.5278, device='cuda:0')
episode: 547 training return: tensor(28.5371, device='cuda:0')
epoch: 137 test_true_pfm: 1684.3368506299046 sim_pfm: -80.01249323560235
episode: 548 training return: tensor(161.3649, device='cuda:0')
episode: 549 training return: tensor(289.0733, device='cuda:0')
episode: 550 training return: tensor(-277.8855, device='cuda:0')
episode: 551 training return: tensor(-233.2490, device='cuda:0')
epoch: 138 test_true_pfm: 1755.4909969607224 sim_pfm: -301.0797315471961
episode: 552 training return: tensor(92.7671, device='cuda:0')
episode: 553 training return: tensor(-267.3991, device='cuda:0')
episode: 554 training return: tensor(-63.5267, device='cuda:0')
episode: 555 training return: tensor(-195.7415, device='cuda:0')
epoch: 139 test_true_pfm: 1533.040698807408 sim_pfm: -15.321024055903157
episode: 556 training return: tensor(-324.2764, device='cuda:0')
episode: 557 training return: tensor(74.1838, device='cuda:0')
episode: 558 training return: tensor(-231.3706, device='cuda:0')
episode: 559 training return: tensor(-344.3393, device='cuda:0')
epoch: 140 test_true_pfm: 1618.5818977749102 sim_pfm: -107.59974930531462
episode: 560 training return: tensor(-298.3619, device='cuda:0')
episode: 561 training return: tensor(-392.6068, device='cuda:0')
episode: 562 training return: tensor(270.3532, device='cuda:0')
episode: 563 training return: tensor(278.3995, device='cuda:0')
epoch: 141 test_true_pfm: 3167.0079653278494 sim_pfm: 166.09860079408585
episode: 564 training return: tensor(315.1629, device='cuda:0')
episode: 565 training return: tensor(-195.9374, device='cuda:0')
episode: 566 training return: tensor(-291.0902, device='cuda:0')
episode: 567 training return: tensor(-35.7391, device='cuda:0')
epoch: 142 test_true_pfm: 2852.43049393716 sim_pfm: -111.89133401649694
episode: 568 training return: tensor(-14.4440, device='cuda:0')
episode: 569 training return: tensor(-109.6435, device='cuda:0')
episode: 570 training return: tensor(-76.3232, device='cuda:0')
episode: 571 training return: tensor(-171.3956, device='cuda:0')
epoch: 143 test_true_pfm: 3086.4491106267906 sim_pfm: 77.57399340278546
episode: 572 training return: tensor(-136.8619, device='cuda:0')
episode: 573 training return: tensor(223.0860, device='cuda:0')
episode: 574 training return: tensor(209.6683, device='cuda:0')
episode: 575 training return: tensor(-283.2319, device='cuda:0')
epoch: 144 test_true_pfm: 2213.2408902012453 sim_pfm: -182.99453486110238
episode: 576 training return: tensor(-61.7355, device='cuda:0')
episode: 577 training return: tensor(-334.5183, device='cuda:0')
episode: 578 training return: tensor(-193.5189, device='cuda:0')
episode: 579 training return: tensor(276.4274, device='cuda:0')
epoch: 145 test_true_pfm: 1537.9771228694683 sim_pfm: -103.94728906303256
episode: 580 training return: tensor(90.1044, device='cuda:0')
episode: 581 training return: tensor(-389.5966, device='cuda:0')
episode: 582 training return: tensor(-193.2129, device='cuda:0')
episode: 583 training return: tensor(-88.3892, device='cuda:0')
epoch: 146 test_true_pfm: 2674.356425305609 sim_pfm: 12.945416021325704
episode: 584 training return: tensor(19.6218, device='cuda:0')
episode: 585 training return: tensor(-180.3338, device='cuda:0')
episode: 586 training return: tensor(-35.1184, device='cuda:0')
episode: 587 training return: tensor(142.8501, device='cuda:0')
epoch: 147 test_true_pfm: 3123.3550958965684 sim_pfm: 213.96392718227193
episode: 588 training return: tensor(271.5832, device='cuda:0')
episode: 589 training return: tensor(-296.7147, device='cuda:0')
episode: 590 training return: tensor(266.7712, device='cuda:0')
episode: 591 training return: tensor(247.1257, device='cuda:0')
epoch: 148 test_true_pfm: 2220.914427892048 sim_pfm: 6.440363075312537
episode: 592 training return: tensor(-375.3504, device='cuda:0')
episode: 593 training return: tensor(132.7539, device='cuda:0')
episode: 594 training return: tensor(332.1094, device='cuda:0')
episode: 595 training return: tensor(316.7075, device='cuda:0')
epoch: 149 test_true_pfm: 2168.2789809203223 sim_pfm: 85.3835932741058
episode: 596 training return: tensor(-161.2211, device='cuda:0')
episode: 597 training return: tensor(-379.9474, device='cuda:0')
episode: 598 training return: tensor(-351.5377, device='cuda:0')
episode: 599 training return: tensor(-365.1294, device='cuda:0')
epoch: 150 test_true_pfm: 1573.722208198508 sim_pfm: -241.09804324514698
