['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'behavior', '--traj', 'expert', '--seed', '2']
epoch: 0 training_loss 0.20595006063580512 test_loss: 0.14285485744476317
epoch: 1 training_loss 0.14101413197815418 test_loss: 0.11950496435165406
epoch: 2 training_loss 0.1319097139313817 test_loss: 0.1437838315963745
epoch: 3 training_loss 0.1323172388970852 test_loss: 0.1417343020439148
epoch: 4 training_loss 0.12040281865745783 test_loss: 0.16083722114562987
epoch: 5 training_loss 0.12046792708337307 test_loss: 0.12340683937072754
epoch: 6 training_loss 0.1239776125922799 test_loss: 0.1142583966255188
epoch: 7 training_loss 0.1230099507421255 test_loss: 0.10246747732162476
epoch: 8 training_loss 0.12754485193639994 test_loss: 0.12767764329910278
epoch: 9 training_loss 0.12200079925358295 test_loss: 0.11007767915725708
epoch: 10 training_loss 0.1268433240428567 test_loss: 0.10314438343048096
epoch: 11 training_loss 0.12660527490079404 test_loss: 0.12292355298995972
epoch: 12 training_loss 0.11946727767586708 test_loss: 0.11429532766342163
epoch: 13 training_loss 0.12052983902394772 test_loss: 0.11274621486663819
epoch: 14 training_loss 0.12442878559231758 test_loss: 0.1190229058265686
epoch: 15 training_loss 0.11386148899793624 test_loss: 0.11252697706222534
epoch: 16 training_loss 0.12145593829452991 test_loss: 0.11941297054290771
epoch: 17 training_loss 0.11751639906316996 test_loss: 0.10612125396728515
epoch: 18 training_loss 0.12426471419632434 test_loss: 0.11592632532119751
epoch: 19 training_loss 0.11760231260210276 test_loss: 0.10877714157104493
epoch: 20 training_loss 0.12256170123815537 test_loss: 0.1165615439414978
epoch: 21 training_loss 0.120892683416605 test_loss: 0.1126389741897583
epoch: 22 training_loss 0.12220303915441036 test_loss: 0.10772136449813843
epoch: 23 training_loss 0.11356087021529675 test_loss: 0.13178831338882446
epoch: 24 training_loss 0.11898520659655333 test_loss: 0.14726338386535645
epoch: 25 training_loss 0.118603135086596 test_loss: 0.11537455320358277
epoch: 26 training_loss 0.1228538129106164 test_loss: 0.1160646915435791
epoch: 27 training_loss 0.12177507493644953 test_loss: 0.09530571699142457
epoch: 28 training_loss 0.11657056171447039 test_loss: 0.10993020534515381
epoch: 29 training_loss 0.11526678938418627 test_loss: 0.10378233194351197
epoch: 30 training_loss 0.11309346940368414 test_loss: 0.11254335641860962
epoch: 31 training_loss 0.12138230588287115 test_loss: 0.11039490699768066
epoch: 32 training_loss 0.10862431485205888 test_loss: 0.12117736339569092
epoch: 33 training_loss 0.11919782698154449 test_loss: 0.0981357216835022
epoch: 34 training_loss 0.111069947630167 test_loss: 0.10622490644454956
epoch: 35 training_loss 0.11722592830657959 test_loss: 0.11090154647827148
epoch: 36 training_loss 0.11544384755194187 test_loss: 0.1121636986732483
epoch: 37 training_loss 0.12463109515607357 test_loss: 0.12124869823455811
epoch: 38 training_loss 0.11258706085383892 test_loss: 0.10055570602416992
epoch: 39 training_loss 0.11123509269207715 test_loss: 0.10222852230072021
epoch: 40 training_loss 0.12363373637199401 test_loss: 0.11233177185058593
epoch: 41 training_loss 0.11528953403234482 test_loss: 0.10814262628555298
epoch: 42 training_loss 0.11611734714359045 test_loss: 0.12708029747009278
epoch: 43 training_loss 0.11702150084078312 test_loss: 0.11023174524307251
epoch: 44 training_loss 0.11396320976316929 test_loss: 0.1224056601524353
epoch: 45 training_loss 0.10870519150048494 test_loss: 0.10575741529464722
epoch: 46 training_loss 0.11517205066978932 test_loss: 0.10568749904632568
epoch: 47 training_loss 0.12210298284888267 test_loss: 0.10917080640792846
epoch: 48 training_loss 0.11539277978241444 test_loss: 0.10753334760665893
epoch: 49 training_loss 0.1129280361905694 test_loss: 0.10907700061798095
epoch: 50 training_loss 0.11806071527302266 test_loss: 0.11364796161651611
epoch: 51 training_loss 0.11668398551642895 test_loss: 0.0988690972328186
epoch: 52 training_loss 0.11236222758889199 test_loss: 0.10638762712478637
epoch: 53 training_loss 0.11485523570328951 test_loss: 0.12367476224899292
epoch: 54 training_loss 0.11492333300411701 test_loss: 0.12496837377548217
epoch: 55 training_loss 0.11274655807763338 test_loss: 0.12119773626327515
epoch: 56 training_loss 0.1117446694895625 test_loss: 0.11221824884414673
epoch: 57 training_loss 0.11832758862525225 test_loss: 0.10734348297119141
epoch: 58 training_loss 0.10983314260840416 test_loss: 0.11606074571609497
epoch: 59 training_loss 0.11739828027784824 test_loss: 0.10623830556869507
epoch: 60 training_loss 0.11424829110503197 test_loss: 0.10587511062622071
epoch: 61 training_loss 0.11408205408602953 test_loss: 0.10830380916595458
epoch: 62 training_loss 0.11719625417143106 test_loss: 0.1080282211303711
epoch: 63 training_loss 0.10993787541985511 test_loss: 0.10048290491104125
epoch: 64 training_loss 0.11420854456722736 test_loss: 0.10460679531097412
epoch: 65 training_loss 0.11484110035002232 test_loss: 0.11203447580337525
epoch: 66 training_loss 0.11738516855984926 test_loss: 0.11302968263626098
epoch: 67 training_loss 0.11571503154933453 test_loss: 0.11178287267684936
epoch: 68 training_loss 0.111285630017519 test_loss: 0.10588072538375855
epoch: 69 training_loss 0.10926433950662613 test_loss: 0.11651521921157837
epoch: 70 training_loss 0.1201114746183157 test_loss: 0.10187143087387085
epoch: 71 training_loss 0.11652929004281759 test_loss: 0.10826003551483154
epoch: 72 training_loss 0.11601481385529042 test_loss: 0.10342082977294922
epoch: 73 training_loss 0.11360865652561188 test_loss: 0.11316962242126465
epoch: 74 training_loss 0.11550213094800711 test_loss: 0.11369320154190063
epoch: 75 training_loss 0.12122144930064678 test_loss: 0.1128306269645691
epoch: 76 training_loss 0.1094172065332532 test_loss: 0.11142867803573608
epoch: 77 training_loss 0.11237359378486872 test_loss: 0.10576170682907104
epoch: 78 training_loss 0.11629347227513791 test_loss: 0.1140408992767334
epoch: 79 training_loss 0.11578271761536599 test_loss: 0.11337852478027344
epoch: 80 training_loss 0.11679707057774066 test_loss: 0.09815223813056946
epoch: 81 training_loss 0.12009279746562243 test_loss: 0.11254719495773316
epoch: 82 training_loss 0.10898692663758994 test_loss: 0.10614373683929443
epoch: 83 training_loss 0.11498318083584308 test_loss: 0.10714540481567383
epoch: 84 training_loss 0.11240965213626623 test_loss: 0.1107375144958496
epoch: 85 training_loss 0.11263071618974209 test_loss: 0.10532493591308593
epoch: 86 training_loss 0.11285715848207474 test_loss: 0.09913317561149597
epoch: 87 training_loss 0.11642151217907667 test_loss: 0.10858473777770997
epoch: 88 training_loss 0.11145481497049331 test_loss: 0.11162729263305664
epoch: 89 training_loss 0.11137016974389553 test_loss: 0.11198951005935669
epoch: 90 training_loss 0.117924445271492 test_loss: 0.09933879971504211
epoch: 91 training_loss 0.11317477967590094 test_loss: 0.09861755967140198
epoch: 92 training_loss 0.11423619728535414 test_loss: 0.11033823490142822
epoch: 93 training_loss 0.11499338414520026 test_loss: 0.1135934591293335
epoch: 94 training_loss 0.11404989335685968 test_loss: 0.10531817674636841
epoch: 95 training_loss 0.11142281763255596 test_loss: 0.11625199317932129
epoch: 96 training_loss 0.11482536464929581 test_loss: 0.11599353551864625
epoch: 97 training_loss 0.11508119583129883 test_loss: 0.10742298364639283
epoch: 98 training_loss 0.11816357083618641 test_loss: 0.11401317119598389
epoch: 99 training_loss 0.11270419541746378 test_loss: 0.10540207624435424
epoch: 100 training_loss 0.11922086261212826 test_loss: 0.1060471773147583
epoch: 101 training_loss 0.11879789181053639 test_loss: 0.10549595355987548
epoch: 102 training_loss 0.11244058862328529 test_loss: 0.11058220863342286
epoch: 103 training_loss 0.11450917836278678 test_loss: 0.10327813625335694
epoch: 104 training_loss 0.11612618900835514 test_loss: 0.11398242712020874
epoch: 105 training_loss 0.11761308006942273 test_loss: 0.10378284454345703
epoch: 106 training_loss 0.11252126768231392 test_loss: 0.1210910439491272
epoch: 107 training_loss 0.10690692197531462 test_loss: 0.1240163803100586
epoch: 108 training_loss 0.11159320812672377 test_loss: 0.10666693449020385
epoch: 109 training_loss 0.1111733028665185 test_loss: 0.1007996916770935
epoch: 110 training_loss 0.11274307448416948 test_loss: 0.10026249885559083
epoch: 111 training_loss 0.11108171705156565 test_loss: 0.11932566165924072
epoch: 112 training_loss 0.1125280487537384 test_loss: 0.11931092739105224
epoch: 113 training_loss 0.11490050468593836 test_loss: 0.10918288230895996
epoch: 114 training_loss 0.11337544031441212 test_loss: 0.09367662072181701
epoch: 115 training_loss 0.11157586373388767 test_loss: 0.10986483097076416
epoch: 116 training_loss 0.1085954624414444 test_loss: 0.10220860242843628
epoch: 117 training_loss 0.1090169071406126 test_loss: 0.09852694869041442
epoch: 118 training_loss 0.1161317552626133 test_loss: 0.10589003562927246
epoch: 119 training_loss 0.11155505549162627 test_loss: 0.1113898515701294
epoch: 120 training_loss 0.12175946351140737 test_loss: 0.1081493616104126
epoch: 121 training_loss 0.11068828713148832 test_loss: 0.1119417428970337
epoch: 122 training_loss 0.10700207263231278 test_loss: 0.11391786336898804
epoch: 123 training_loss 0.1135104601457715 test_loss: 0.09923493266105651
epoch: 124 training_loss 0.11278882868587971 test_loss: 0.10147104263305665
epoch: 125 training_loss 0.11276589632034302 test_loss: 0.11438922882080078
epoch: 126 training_loss 0.11128313265740872 test_loss: 0.11393562555313111
epoch: 127 training_loss 0.10874595236033201 test_loss: 0.1088113784790039
epoch: 128 training_loss 0.11025524068623781 test_loss: 0.09435139298439026
epoch: 129 training_loss 0.10815914053469897 test_loss: 0.11740633249282836
epoch: 130 training_loss 0.1132540288567543 test_loss: 0.11248347759246827
epoch: 131 training_loss 0.11520429976284503 test_loss: 0.1059535026550293
epoch: 132 training_loss 0.11508242763578892 test_loss: 0.10848374366760254
epoch: 133 training_loss 0.1068564385548234 test_loss: 0.1077013611793518
epoch: 134 training_loss 0.10941727332770824 test_loss: 0.11950267553329467
epoch: 135 training_loss 0.11648083254694938 test_loss: 0.12278389930725098
epoch: 136 training_loss 0.11378331992775202 test_loss: 0.09793735146522523
epoch: 137 training_loss 0.11415636997669935 test_loss: 0.10726858377456665
epoch: 138 training_loss 0.10512839462608099 test_loss: 0.10376683473587037
epoch: 139 training_loss 0.11731522105634212 test_loss: 0.11077313423156739
epoch: 140 training_loss 0.11870318673551082 test_loss: 0.10787134170532227
epoch: 141 training_loss 0.10676074627786875 test_loss: 0.11305733919143676
epoch: 142 training_loss 0.11592406194657087 test_loss: 0.10348759889602661
epoch: 143 training_loss 0.11694215979427099 test_loss: 0.09869258403778076
epoch: 144 training_loss 0.11849247716367245 test_loss: 0.10843534469604492
epoch: 145 training_loss 0.11605918522924184 test_loss: 0.10909404754638671
epoch: 146 training_loss 0.1161619284003973 test_loss: 0.11602997779846191
epoch: 147 training_loss 0.11430281672626734 test_loss: 0.10036908388137818
epoch: 148 training_loss 0.11210189577192069 test_loss: 0.10723057985305787
epoch: 149 training_loss 0.11034577552229166 test_loss: 0.09777202010154724
epoch: 0 training_loss 21.64043550491333 test_loss: 16.99508056640625
epoch: 1 training_loss 13.429580430984497 test_loss: 10.037208557128906
epoch: 2 training_loss 8.924122610092162 test_loss: 8.152965545654297
epoch: 3 training_loss 7.659620232582093 test_loss: 7.2756706237792965
epoch: 4 training_loss 6.9988695240020755 test_loss: 6.854705047607422
epoch: 5 training_loss 6.45337112903595 test_loss: 6.111611938476562
epoch: 6 training_loss 5.872073316574097 test_loss: 5.766089630126953
epoch: 7 training_loss 5.469618921279907 test_loss: 5.421919631958008
epoch: 8 training_loss 5.273872942924499 test_loss: 5.11024169921875
epoch: 9 training_loss 4.962872416973114 test_loss: 4.7763103485107425
epoch: 10 training_loss 4.628246693611145 test_loss: 4.5678447723388675
epoch: 11 training_loss 4.596655974388122 test_loss: 4.457022094726563
epoch: 12 training_loss 4.331123528480529 test_loss: 4.074269485473633
epoch: 13 training_loss 4.142749998569489 test_loss: 4.031179428100586
epoch: 14 training_loss 4.131144785881043 test_loss: 4.275350570678711
epoch: 15 training_loss 3.9161499404907225 test_loss: 4.011803436279297
epoch: 16 training_loss 3.9283023118972777 test_loss: 3.761001968383789
epoch: 17 training_loss 3.8651494932174684 test_loss: 3.7112945556640624
epoch: 18 training_loss 3.674515302181244 test_loss: 3.7113574981689452
epoch: 19 training_loss 3.652067847251892 test_loss: 3.744024658203125
epoch: 20 training_loss 3.4817631530761717 test_loss: 3.6340801239013674
epoch: 21 training_loss 3.351734116077423 test_loss: 3.337276077270508
epoch: 22 training_loss 3.3739489364624022 test_loss: 3.393190383911133
epoch: 23 training_loss 3.2557835483551028 test_loss: 3.1679555892944338
epoch: 24 training_loss 3.160461094379425 test_loss: 3.2936771392822264
epoch: 25 training_loss 3.189473180770874 test_loss: 3.0223663330078123
epoch: 26 training_loss 3.139961664676666 test_loss: 3.3093845367431642
epoch: 27 training_loss 3.0079968214035033 test_loss: 3.204046630859375
epoch: 28 training_loss 3.1215082812309265 test_loss: 3.115134620666504
epoch: 29 training_loss 3.018783702850342 test_loss: 2.8145050048828124
epoch: 30 training_loss 2.964411532878876 test_loss: 2.9667470932006834
epoch: 31 training_loss 2.866307785511017 test_loss: 2.848698043823242
epoch: 32 training_loss 2.817058808803558 test_loss: 2.718000793457031
epoch: 33 training_loss 2.825869176387787 test_loss: 2.9856689453125
epoch: 34 training_loss 2.808178446292877 test_loss: 2.808714485168457
epoch: 35 training_loss 2.801551902294159 test_loss: 2.715256690979004
epoch: 36 training_loss 2.8182000875473023 test_loss: 2.779692459106445
epoch: 37 training_loss 2.757251824140549 test_loss: 2.632940101623535
epoch: 38 training_loss 2.669537229537964 test_loss: 2.8010889053344727
epoch: 39 training_loss 2.5908949971199036 test_loss: 2.615709114074707
epoch: 40 training_loss 2.5848739409446715 test_loss: 2.485651206970215
epoch: 41 training_loss 2.700816562175751 test_loss: 2.767284393310547
epoch: 42 training_loss 2.4972780561447143 test_loss: 2.4463773727416993
epoch: 43 training_loss 2.567009118795395 test_loss: 2.4458620071411135
epoch: 44 training_loss 2.5280485343933106 test_loss: 2.6445507049560546
epoch: 45 training_loss 2.5070663702487948 test_loss: 2.6120704650878905
epoch: 46 training_loss 2.4703085696697236 test_loss: 2.4226892471313475
epoch: 47 training_loss 2.452842026948929 test_loss: 2.467564582824707
epoch: 48 training_loss 2.4131385791301727 test_loss: 2.354122352600098
epoch: 49 training_loss 2.3146071553230287 test_loss: 2.4614410400390625
epoch: 50 training_loss 2.339042309522629 test_loss: 2.3555559158325194
epoch: 51 training_loss 2.431407309770584 test_loss: 2.3931602478027343
epoch: 52 training_loss 2.355288728475571 test_loss: 2.475772476196289
epoch: 53 training_loss 2.3065082252025606 test_loss: 2.251445198059082
epoch: 54 training_loss 2.3328584170341493 test_loss: 2.4612991333007814
epoch: 55 training_loss 2.2794944036006926 test_loss: 2.296598434448242
epoch: 56 training_loss 2.249680277109146 test_loss: 2.378829765319824
epoch: 57 training_loss 2.2950191676616667 test_loss: 2.259020233154297
epoch: 58 training_loss 2.327919763326645 test_loss: 2.161366653442383
epoch: 59 training_loss 2.2783883953094484 test_loss: 2.6936532974243166
epoch: 60 training_loss 2.2509948587417603 test_loss: 2.2961715698242187
epoch: 61 training_loss 2.294981527328491 test_loss: 2.3870689392089846
epoch: 62 training_loss 2.2161202573776246 test_loss: 2.267853927612305
epoch: 63 training_loss 2.334035654067993 test_loss: 2.201863098144531
epoch: 64 training_loss 2.14163477063179 test_loss: 2.1982986450195314
epoch: 65 training_loss 2.198471955060959 test_loss: 2.1116264343261717
epoch: 66 training_loss 2.237212929725647 test_loss: 2.160866355895996
epoch: 67 training_loss 2.125459326505661 test_loss: 2.082366180419922
epoch: 68 training_loss 2.170878219604492 test_loss: 2.0684183120727537
epoch: 69 training_loss 2.2029561412334444 test_loss: 2.3090768814086915
epoch: 70 training_loss 2.140221917629242 test_loss: 2.1812501907348634
epoch: 71 training_loss 2.1385333943367004 test_loss: 2.217852783203125
epoch: 72 training_loss 2.050679008960724 test_loss: 2.0661401748657227
epoch: 73 training_loss 2.071778427362442 test_loss: 2.131644630432129
epoch: 74 training_loss 2.0464740014076233 test_loss: 1.988469123840332
epoch: 75 training_loss 2.084918249845505 test_loss: 2.0894046783447267
epoch: 76 training_loss 2.1237211084365843 test_loss: 2.1401859283447267
epoch: 77 training_loss 2.070532478094101 test_loss: 2.2142606735229493
epoch: 78 training_loss 2.0975248765945436 test_loss: 2.157575225830078
epoch: 79 training_loss 2.017233076095581 test_loss: 2.1883073806762696
epoch: 80 training_loss 2.111302698850632 test_loss: 2.087327766418457
epoch: 81 training_loss 2.021203405857086 test_loss: 2.2684047698974608
epoch: 82 training_loss 2.0454279100894928 test_loss: 2.044363021850586
epoch: 83 training_loss 2.068660898208618 test_loss: 2.0157447814941407
epoch: 84 training_loss 2.020077908039093 test_loss: 1.8643842697143556
epoch: 85 training_loss 1.9330940747261047 test_loss: 2.056475830078125
epoch: 86 training_loss 1.984950383901596 test_loss: 2.145950508117676
epoch: 87 training_loss 2.028395060300827 test_loss: 1.976987075805664
epoch: 88 training_loss 2.0113196659088133 test_loss: 1.9615234375
epoch: 89 training_loss 2.013323585987091 test_loss: 1.8464469909667969
epoch: 90 training_loss 1.9507900309562682 test_loss: 1.896710205078125
epoch: 91 training_loss 1.9805385649204255 test_loss: 2.065278434753418
epoch: 92 training_loss 1.984317545890808 test_loss: 1.8760414123535156
epoch: 93 training_loss 1.9965806579589844 test_loss: 1.9578571319580078
epoch: 94 training_loss 1.9547368216514587 test_loss: 1.809952163696289
epoch: 95 training_loss 1.9386826074123382 test_loss: 1.793234634399414
epoch: 96 training_loss 1.8944828510284424 test_loss: 1.9149284362792969
epoch: 97 training_loss 1.8997948253154755 test_loss: 1.7953666687011718
epoch: 98 training_loss 1.975919748544693 test_loss: 2.086264801025391
epoch: 99 training_loss 1.9404752087593078 test_loss: 2.010434150695801
epoch: 100 training_loss 1.9472663402557373 test_loss: 1.9359163284301757
epoch: 101 training_loss 1.9090561270713806 test_loss: 1.8583633422851562
epoch: 102 training_loss 1.9178673923015594 test_loss: 1.8206186294555664
epoch: 103 training_loss 1.871849457025528 test_loss: 1.7995582580566407
epoch: 104 training_loss 1.9041811871528624 test_loss: 1.7182842254638673
epoch: 105 training_loss 1.8680953526496886 test_loss: 1.9863994598388672
epoch: 106 training_loss 1.9143676471710205 test_loss: 1.9978076934814453
epoch: 107 training_loss 1.852549936771393 test_loss: 1.7753326416015625
epoch: 108 training_loss 1.9136606681346893 test_loss: 1.7794761657714844
epoch: 109 training_loss 1.9728004050254822 test_loss: 1.944137954711914
epoch: 110 training_loss 1.8512635660171508 test_loss: 1.8481801986694335
epoch: 111 training_loss 1.881460655927658 test_loss: 1.8906614303588867
epoch: 112 training_loss 1.8552254855632782 test_loss: 1.8256832122802735
epoch: 113 training_loss 1.8254430389404297 test_loss: 1.9009326934814452
epoch: 114 training_loss 1.8124536311626434 test_loss: 1.66979923248291
epoch: 115 training_loss 1.7608859395980836 test_loss: 1.8123895645141601
epoch: 116 training_loss 1.809766992330551 test_loss: 1.821467399597168
epoch: 117 training_loss 1.8581267154216767 test_loss: 1.792523193359375
epoch: 118 training_loss 1.895783452987671 test_loss: 1.87210693359375
epoch: 119 training_loss 1.89779949426651 test_loss: 1.8273799896240235
epoch: 120 training_loss 1.8685636615753174 test_loss: 1.9295656204223632
epoch: 121 training_loss 1.8149398744106293 test_loss: 1.8603975296020507
epoch: 122 training_loss 1.7471608328819275 test_loss: 1.8721160888671875
epoch: 123 training_loss 1.7817406368255615 test_loss: 1.622891616821289
epoch: 124 training_loss 1.7451362216472626 test_loss: 1.7000604629516602
epoch: 125 training_loss 1.7550586128234864 test_loss: 1.8850147247314453
epoch: 126 training_loss 1.7624622464179993 test_loss: 1.7608312606811523
epoch: 127 training_loss 1.76088574051857 test_loss: 1.6163715362548827
epoch: 128 training_loss 1.7674242436885834 test_loss: 1.6474323272705078
epoch: 129 training_loss 1.8757348537445069 test_loss: 1.7566301345825195
epoch: 130 training_loss 1.721966596841812 test_loss: 1.759181022644043
epoch: 131 training_loss 1.8232348358631134 test_loss: 1.7306188583374023
epoch: 132 training_loss 1.7928002786636352 test_loss: 1.6340852737426759
epoch: 133 training_loss 1.7419632661342621 test_loss: 1.5879820823669433
epoch: 134 training_loss 1.71660959482193 test_loss: 1.7172374725341797
epoch: 135 training_loss 1.735780302286148 test_loss: 1.6938255310058594
epoch: 136 training_loss 1.7665736818313598 test_loss: 1.9051591873168945
epoch: 137 training_loss 1.7338685834407805 test_loss: 1.7370859146118165
epoch: 138 training_loss 1.746989268064499 test_loss: 1.6960081100463866
epoch: 139 training_loss 1.715493505001068 test_loss: 1.6806953430175782
epoch: 140 training_loss 1.7112364041805268 test_loss: 1.774363899230957
epoch: 141 training_loss 1.7056440222263336 test_loss: 1.7515947341918945
epoch: 142 training_loss 1.6857965576648712 test_loss: 1.7710939407348634
epoch: 143 training_loss 1.6835120296478272 test_loss: 1.7837785720825194
epoch: 144 training_loss 1.657758275270462 test_loss: 1.7139669418334962
epoch: 145 training_loss 1.6461123824119568 test_loss: 1.720562744140625
epoch: 146 training_loss 1.7629486048221588 test_loss: 1.919558334350586
epoch: 147 training_loss 1.7020668077468872 test_loss: 1.740190315246582
epoch: 148 training_loss 1.8087905585765838 test_loss: 1.7656574249267578
epoch: 149 training_loss 1.7334662663936615 test_loss: 1.6468118667602538
134.22582525797637
episode: 0 training return: tensor(121.7698, device='cuda:0')
episode: 1 training return: tensor(124.6683, device='cuda:0')
episode: 2 training return: tensor(117.3773, device='cuda:0')
episode: 3 training return: tensor(130.1943, device='cuda:0')
epoch: 1 test_true_pfm: 132.77141637438595 sim_pfm: 124.91466776825837
episode: 4 training return: tensor(125.9279, device='cuda:0')
episode: 5 training return: tensor(117.1344, device='cuda:0')
episode: 6 training return: tensor(120.1543, device='cuda:0')
episode: 7 training return: tensor(120.6247, device='cuda:0')
epoch: 2 test_true_pfm: 126.74605640817997 sim_pfm: 125.73205111096613
episode: 8 training return: tensor(117.0738, device='cuda:0')
episode: 9 training return: tensor(110.3543, device='cuda:0')
episode: 10 training return: tensor(128.3796, device='cuda:0')
episode: 11 training return: tensor(115.8223, device='cuda:0')
epoch: 3 test_true_pfm: 127.04820432027509 sim_pfm: 127.00760370694334
episode: 12 training return: tensor(130.0820, device='cuda:0')
episode: 13 training return: tensor(109.2653, device='cuda:0')
episode: 14 training return: tensor(108.0567, device='cuda:0')
episode: 15 training return: tensor(125.5894, device='cuda:0')
epoch: 4 test_true_pfm: 131.76108591733032 sim_pfm: 132.16873871964054
episode: 16 training return: tensor(127.1255, device='cuda:0')
episode: 17 training return: tensor(134.6050, device='cuda:0')
episode: 18 training return: tensor(125.3009, device='cuda:0')
episode: 19 training return: tensor(123.2720, device='cuda:0')
epoch: 5 test_true_pfm: 137.6566529211349 sim_pfm: 129.56391467823997
episode: 20 training return: tensor(124.1103, device='cuda:0')
episode: 21 training return: tensor(125.2928, device='cuda:0')
episode: 22 training return: tensor(129.8347, device='cuda:0')
episode: 23 training return: tensor(123.4151, device='cuda:0')
epoch: 6 test_true_pfm: 129.95839792745997 sim_pfm: 130.11327640945674
episode: 24 training return: tensor(133.5045, device='cuda:0')
episode: 25 training return: tensor(124.2320, device='cuda:0')
episode: 26 training return: tensor(142.4805, device='cuda:0')
episode: 27 training return: tensor(134.7435, device='cuda:0')
epoch: 7 test_true_pfm: 130.35811209549576 sim_pfm: 130.73442880664953
episode: 28 training return: tensor(137.3707, device='cuda:0')
episode: 29 training return: tensor(126.8483, device='cuda:0')
episode: 30 training return: tensor(128.8506, device='cuda:0')
episode: 31 training return: tensor(120.6813, device='cuda:0')
epoch: 8 test_true_pfm: 131.46507295792753 sim_pfm: 130.35063076383085
episode: 32 training return: tensor(126.2617, device='cuda:0')
episode: 33 training return: tensor(129.5786, device='cuda:0')
episode: 34 training return: tensor(133.0454, device='cuda:0')
episode: 35 training return: tensor(138.8701, device='cuda:0')
epoch: 9 test_true_pfm: 131.32369456448626 sim_pfm: 131.39386659998564
episode: 36 training return: tensor(131.6643, device='cuda:0')
episode: 37 training return: tensor(120.5951, device='cuda:0')
episode: 38 training return: tensor(130.6142, device='cuda:0')
episode: 39 training return: tensor(126.3215, device='cuda:0')
epoch: 10 test_true_pfm: 129.48933978746373 sim_pfm: 129.01960783716058
episode: 40 training return: tensor(130.4272, device='cuda:0')
episode: 41 training return: tensor(126.8741, device='cuda:0')
episode: 42 training return: tensor(123.4183, device='cuda:0')
episode: 43 training return: tensor(132.0384, device='cuda:0')
epoch: 11 test_true_pfm: 129.76676326598823 sim_pfm: 130.9612979033147
episode: 44 training return: tensor(137.0071, device='cuda:0')
episode: 45 training return: tensor(133.9335, device='cuda:0')
episode: 46 training return: tensor(136.2870, device='cuda:0')
episode: 47 training return: tensor(128.5097, device='cuda:0')
epoch: 12 test_true_pfm: 130.7836683280734 sim_pfm: 131.30805445756414
episode: 48 training return: tensor(138.6710, device='cuda:0')
episode: 49 training return: tensor(135.0386, device='cuda:0')
episode: 50 training return: tensor(132.9416, device='cuda:0')
episode: 51 training return: tensor(133.8453, device='cuda:0')
epoch: 13 test_true_pfm: 128.94809886810697 sim_pfm: 128.53417042711516
episode: 52 training return: tensor(131.4606, device='cuda:0')
episode: 53 training return: tensor(135.0431, device='cuda:0')
episode: 54 training return: tensor(141.9737, device='cuda:0')
episode: 55 training return: tensor(142.3454, device='cuda:0')
epoch: 14 test_true_pfm: 128.10792135452272 sim_pfm: 136.9414614598849
episode: 56 training return: tensor(139.2154, device='cuda:0')
episode: 57 training return: tensor(135.9775, device='cuda:0')
episode: 58 training return: tensor(132.2436, device='cuda:0')
episode: 59 training return: tensor(131.3082, device='cuda:0')
epoch: 15 test_true_pfm: 129.40006001794282 sim_pfm: 131.00088577210553
episode: 60 training return: tensor(124.2290, device='cuda:0')
episode: 61 training return: tensor(140.9245, device='cuda:0')
episode: 62 training return: tensor(141.6621, device='cuda:0')
episode: 63 training return: tensor(130.5490, device='cuda:0')
epoch: 16 test_true_pfm: 129.99413402070186 sim_pfm: 134.9809476331342
episode: 64 training return: tensor(129.9648, device='cuda:0')
episode: 65 training return: tensor(134.7464, device='cuda:0')
episode: 66 training return: tensor(144.2445, device='cuda:0')
episode: 67 training return: tensor(143.6380, device='cuda:0')
epoch: 17 test_true_pfm: 131.3686235610242 sim_pfm: 137.45622790796915
episode: 68 training return: tensor(142.4156, device='cuda:0')
episode: 69 training return: tensor(141.3245, device='cuda:0')
episode: 70 training return: tensor(144.7455, device='cuda:0')
episode: 71 training return: tensor(142.4894, device='cuda:0')
epoch: 18 test_true_pfm: 130.90519211470436 sim_pfm: 138.64154555284767
episode: 72 training return: tensor(142.5560, device='cuda:0')
episode: 73 training return: tensor(141.1308, device='cuda:0')
episode: 74 training return: tensor(149.8206, device='cuda:0')
episode: 75 training return: tensor(148.0263, device='cuda:0')
epoch: 19 test_true_pfm: 127.21624706656448 sim_pfm: 141.67633187386673
episode: 76 training return: tensor(140.9140, device='cuda:0')
episode: 77 training return: tensor(132.6959, device='cuda:0')
episode: 78 training return: tensor(145.7415, device='cuda:0')
episode: 79 training return: tensor(136.9555, device='cuda:0')
epoch: 20 test_true_pfm: 126.6350332245419 sim_pfm: 141.08259263387882
episode: 80 training return: tensor(149.2148, device='cuda:0')
episode: 81 training return: tensor(127.5943, device='cuda:0')
episode: 82 training return: tensor(133.3717, device='cuda:0')
episode: 83 training return: tensor(136.0604, device='cuda:0')
epoch: 21 test_true_pfm: 131.4833449521816 sim_pfm: 141.13995742070256
episode: 84 training return: tensor(150.9712, device='cuda:0')
episode: 85 training return: tensor(144.8318, device='cuda:0')
episode: 86 training return: tensor(131.5453, device='cuda:0')
episode: 87 training return: tensor(140.6160, device='cuda:0')
epoch: 22 test_true_pfm: 133.55734109936222 sim_pfm: 142.0283231422771
episode: 88 training return: tensor(136.3688, device='cuda:0')
episode: 89 training return: tensor(145.7296, device='cuda:0')
episode: 90 training return: tensor(142.6323, device='cuda:0')
episode: 91 training return: tensor(145.6998, device='cuda:0')
epoch: 23 test_true_pfm: 131.1253506454251 sim_pfm: 143.48518677877146
episode: 92 training return: tensor(142.4549, device='cuda:0')
episode: 93 training return: tensor(136.6138, device='cuda:0')
episode: 94 training return: tensor(141.3418, device='cuda:0')
episode: 95 training return: tensor(147.0437, device='cuda:0')
epoch: 24 test_true_pfm: 133.43418069500302 sim_pfm: 136.54987966900225
episode: 96 training return: tensor(143.0887, device='cuda:0')
episode: 97 training return: tensor(133.1282, device='cuda:0')
episode: 98 training return: tensor(146.1367, device='cuda:0')
episode: 99 training return: tensor(141.7469, device='cuda:0')
epoch: 25 test_true_pfm: 129.87500016004105 sim_pfm: 137.88082334654754
episode: 100 training return: tensor(140.6636, device='cuda:0')
episode: 101 training return: tensor(131.9178, device='cuda:0')
episode: 102 training return: tensor(135.0108, device='cuda:0')
episode: 103 training return: tensor(143.7991, device='cuda:0')
epoch: 26 test_true_pfm: 130.9778558642423 sim_pfm: 143.1077290928457
episode: 104 training return: tensor(130.8477, device='cuda:0')
episode: 105 training return: tensor(135.6173, device='cuda:0')
episode: 106 training return: tensor(131.3133, device='cuda:0')
episode: 107 training return: tensor(128.6028, device='cuda:0')
epoch: 27 test_true_pfm: 129.64065001560624 sim_pfm: 137.5165139911929
episode: 108 training return: tensor(140.9174, device='cuda:0')
episode: 109 training return: tensor(144.9576, device='cuda:0')
episode: 110 training return: tensor(141.5048, device='cuda:0')
episode: 111 training return: tensor(136.3256, device='cuda:0')
epoch: 28 test_true_pfm: 129.89553049222076 sim_pfm: 135.68488493855693
episode: 112 training return: tensor(136.9818, device='cuda:0')
episode: 113 training return: tensor(118.1890, device='cuda:0')
episode: 114 training return: tensor(139.2608, device='cuda:0')
episode: 115 training return: tensor(148.4849, device='cuda:0')
epoch: 29 test_true_pfm: 127.3091829227119 sim_pfm: 142.4939436509856
episode: 116 training return: tensor(138.2879, device='cuda:0')
episode: 117 training return: tensor(139.3452, device='cuda:0')
episode: 118 training return: tensor(147.5670, device='cuda:0')
episode: 119 training return: tensor(142.9328, device='cuda:0')
epoch: 30 test_true_pfm: 132.72757218717237 sim_pfm: 136.91878311802867
episode: 120 training return: tensor(149.0585, device='cuda:0')
episode: 121 training return: tensor(139.1394, device='cuda:0')
episode: 122 training return: tensor(146.8981, device='cuda:0')
episode: 123 training return: tensor(135.5999, device='cuda:0')
epoch: 31 test_true_pfm: 129.45064367802473 sim_pfm: 148.07420360653197
episode: 124 training return: tensor(146.4657, device='cuda:0')
episode: 125 training return: tensor(132.8085, device='cuda:0')
episode: 126 training return: tensor(138.9793, device='cuda:0')
episode: 127 training return: tensor(133.0800, device='cuda:0')
epoch: 32 test_true_pfm: 129.77147373380222 sim_pfm: 139.858032282372
episode: 128 training return: tensor(152.4537, device='cuda:0')
episode: 129 training return: tensor(147.9162, device='cuda:0')
episode: 130 training return: tensor(151.6005, device='cuda:0')
episode: 131 training return: tensor(130.6930, device='cuda:0')
epoch: 33 test_true_pfm: 130.44254966222846 sim_pfm: 145.0242236659047
episode: 132 training return: tensor(149.3561, device='cuda:0')
episode: 133 training return: tensor(126.4108, device='cuda:0')
episode: 134 training return: tensor(142.2891, device='cuda:0')
episode: 135 training return: tensor(136.2354, device='cuda:0')
epoch: 34 test_true_pfm: 127.17774315749902 sim_pfm: 132.0376219520287
episode: 136 training return: tensor(137.4885, device='cuda:0')
episode: 137 training return: tensor(139.0719, device='cuda:0')
episode: 138 training return: tensor(130.2397, device='cuda:0')
episode: 139 training return: tensor(130.3068, device='cuda:0')
epoch: 35 test_true_pfm: 132.13981563963483 sim_pfm: 140.4361629351275
episode: 140 training return: tensor(150.8447, device='cuda:0')
episode: 141 training return: tensor(140.6400, device='cuda:0')
episode: 142 training return: tensor(132.5949, device='cuda:0')
episode: 143 training return: tensor(145.5452, device='cuda:0')
epoch: 36 test_true_pfm: 131.7772423382362 sim_pfm: 143.00565541269606
episode: 144 training return: tensor(137.5533, device='cuda:0')
episode: 145 training return: tensor(140.7279, device='cuda:0')
episode: 146 training return: tensor(140.2194, device='cuda:0')
episode: 147 training return: tensor(145.7397, device='cuda:0')
epoch: 37 test_true_pfm: 129.4935424741243 sim_pfm: 139.36746566814836
episode: 148 training return: tensor(135.0944, device='cuda:0')
episode: 149 training return: tensor(145.6336, device='cuda:0')
episode: 150 training return: tensor(146.8920, device='cuda:0')
episode: 151 training return: tensor(140.3992, device='cuda:0')
epoch: 38 test_true_pfm: 126.41681695624136 sim_pfm: 137.10680578980828
episode: 152 training return: tensor(145.6576, device='cuda:0')
episode: 153 training return: tensor(136.2474, device='cuda:0')
episode: 154 training return: tensor(137.8009, device='cuda:0')
episode: 155 training return: tensor(124.0665, device='cuda:0')
epoch: 39 test_true_pfm: 129.049492199212 sim_pfm: 137.66312800233135
episode: 156 training return: tensor(134.3884, device='cuda:0')
episode: 157 training return: tensor(131.4951, device='cuda:0')
episode: 158 training return: tensor(153.2168, device='cuda:0')
episode: 159 training return: tensor(134.4737, device='cuda:0')
epoch: 40 test_true_pfm: 126.44446785989581 sim_pfm: 139.81658505295636
episode: 160 training return: tensor(146.5345, device='cuda:0')
episode: 161 training return: tensor(151.8164, device='cuda:0')
episode: 162 training return: tensor(145.5755, device='cuda:0')
episode: 163 training return: tensor(137.6056, device='cuda:0')
epoch: 41 test_true_pfm: 131.37841268603285 sim_pfm: 135.95534161016113
episode: 164 training return: tensor(142.3552, device='cuda:0')
episode: 165 training return: tensor(129.9932, device='cuda:0')
episode: 166 training return: tensor(129.4143, device='cuda:0')
episode: 167 training return: tensor(140.9117, device='cuda:0')
epoch: 42 test_true_pfm: 130.29976693883424 sim_pfm: 132.80184446617494
episode: 168 training return: tensor(134.4223, device='cuda:0')
episode: 169 training return: tensor(141.0814, device='cuda:0')
episode: 170 training return: tensor(148.3199, device='cuda:0')
episode: 171 training return: tensor(147.4181, device='cuda:0')
epoch: 43 test_true_pfm: 130.09076329672578 sim_pfm: 137.72444379674272
episode: 172 training return: tensor(149.5809, device='cuda:0')
episode: 173 training return: tensor(141.0002, device='cuda:0')
episode: 174 training return: tensor(137.7373, device='cuda:0')
episode: 175 training return: tensor(130.9005, device='cuda:0')
epoch: 44 test_true_pfm: 127.22696688561545 sim_pfm: 151.42624211534857
episode: 176 training return: tensor(137.4540, device='cuda:0')
episode: 177 training return: tensor(140.3258, device='cuda:0')
episode: 178 training return: tensor(144.3209, device='cuda:0')
episode: 179 training return: tensor(141.5351, device='cuda:0')
epoch: 45 test_true_pfm: 127.50267548324507 sim_pfm: 134.67200802552398
episode: 180 training return: tensor(135.3922, device='cuda:0')
episode: 181 training return: tensor(137.4829, device='cuda:0')
episode: 182 training return: tensor(160.7583, device='cuda:0')
episode: 183 training return: tensor(142.6309, device='cuda:0')
epoch: 46 test_true_pfm: 132.54272420518828 sim_pfm: 137.37508596162078
episode: 184 training return: tensor(135.4749, device='cuda:0')
episode: 185 training return: tensor(136.1559, device='cuda:0')
episode: 186 training return: tensor(135.6126, device='cuda:0')
episode: 187 training return: tensor(149.1803, device='cuda:0')
epoch: 47 test_true_pfm: 130.49802417121114 sim_pfm: 146.86284529895056
episode: 188 training return: tensor(128.3450, device='cuda:0')
episode: 189 training return: tensor(140.7752, device='cuda:0')
episode: 190 training return: tensor(140.8381, device='cuda:0')
episode: 191 training return: tensor(137.1303, device='cuda:0')
epoch: 48 test_true_pfm: 129.35000529076987 sim_pfm: 142.06152265254642
episode: 192 training return: tensor(131.5880, device='cuda:0')
episode: 193 training return: tensor(146.7291, device='cuda:0')
episode: 194 training return: tensor(133.0144, device='cuda:0')
episode: 195 training return: tensor(132.0923, device='cuda:0')
epoch: 49 test_true_pfm: 128.0656416568442 sim_pfm: 136.23480807103914
episode: 196 training return: tensor(139.7533, device='cuda:0')
episode: 197 training return: tensor(139.9361, device='cuda:0')
episode: 198 training return: tensor(128.2087, device='cuda:0')
episode: 199 training return: tensor(143.9552, device='cuda:0')
epoch: 50 test_true_pfm: 128.3552620041822 sim_pfm: 139.1273174055619
episode: 200 training return: tensor(157.5562, device='cuda:0')
episode: 201 training return: tensor(149.3788, device='cuda:0')
episode: 202 training return: tensor(140.0011, device='cuda:0')
episode: 203 training return: tensor(147.5873, device='cuda:0')
epoch: 51 test_true_pfm: 126.69737434097331 sim_pfm: 140.20884402870433
episode: 204 training return: tensor(125.7730, device='cuda:0')
episode: 205 training return: tensor(135.4983, device='cuda:0')
episode: 206 training return: tensor(138.8461, device='cuda:0')
episode: 207 training return: tensor(129.3193, device='cuda:0')
epoch: 52 test_true_pfm: 131.537386677504 sim_pfm: 146.96003941668314
episode: 208 training return: tensor(132.1786, device='cuda:0')
episode: 209 training return: tensor(146.1206, device='cuda:0')
episode: 210 training return: tensor(146.3632, device='cuda:0')
episode: 211 training return: tensor(130.7010, device='cuda:0')
epoch: 53 test_true_pfm: 132.55304377837382 sim_pfm: 136.11493767845678
episode: 212 training return: tensor(133.1144, device='cuda:0')
episode: 213 training return: tensor(127.7238, device='cuda:0')
episode: 214 training return: tensor(150.9583, device='cuda:0')
episode: 215 training return: tensor(150.6548, device='cuda:0')
epoch: 54 test_true_pfm: 127.87497650705416 sim_pfm: 145.22203821142904
episode: 216 training return: tensor(144.7961, device='cuda:0')
episode: 217 training return: tensor(144.3898, device='cuda:0')
episode: 218 training return: tensor(158.2322, device='cuda:0')
episode: 219 training return: tensor(152.4281, device='cuda:0')
epoch: 55 test_true_pfm: 132.27181251558181 sim_pfm: 141.70421470711008
episode: 220 training return: tensor(154.8794, device='cuda:0')
episode: 221 training return: tensor(140.0139, device='cuda:0')
episode: 222 training return: tensor(145.9815, device='cuda:0')
episode: 223 training return: tensor(153.2178, device='cuda:0')
epoch: 56 test_true_pfm: 132.85002665998982 sim_pfm: 146.520859855687
episode: 224 training return: tensor(155.6595, device='cuda:0')
episode: 225 training return: tensor(141.5572, device='cuda:0')
episode: 226 training return: tensor(144.3367, device='cuda:0')
episode: 227 training return: tensor(139.5962, device='cuda:0')
epoch: 57 test_true_pfm: 127.38374816376708 sim_pfm: 136.49108086045598
episode: 228 training return: tensor(140.8898, device='cuda:0')
episode: 229 training return: tensor(154.5706, device='cuda:0')
episode: 230 training return: tensor(140.6329, device='cuda:0')
episode: 231 training return: tensor(149.2446, device='cuda:0')
epoch: 58 test_true_pfm: 126.02463663659964 sim_pfm: 133.73699326412753
episode: 232 training return: tensor(127.0046, device='cuda:0')
episode: 233 training return: tensor(148.2834, device='cuda:0')
episode: 234 training return: tensor(147.6115, device='cuda:0')
episode: 235 training return: tensor(151.1616, device='cuda:0')
epoch: 59 test_true_pfm: 124.34322897107518 sim_pfm: 142.61501223438535
episode: 236 training return: tensor(129.0655, device='cuda:0')
episode: 237 training return: tensor(154.7017, device='cuda:0')
episode: 238 training return: tensor(136.5218, device='cuda:0')
episode: 239 training return: tensor(147.2403, device='cuda:0')
epoch: 60 test_true_pfm: 132.08388704721898 sim_pfm: 147.21098555127392
episode: 240 training return: tensor(151.6279, device='cuda:0')
episode: 241 training return: tensor(151.5795, device='cuda:0')
episode: 242 training return: tensor(137.7668, device='cuda:0')
episode: 243 training return: tensor(135.7363, device='cuda:0')
epoch: 61 test_true_pfm: 127.8874828989414 sim_pfm: 142.8115767778363
episode: 244 training return: tensor(144.6211, device='cuda:0')
episode: 245 training return: tensor(158.9505, device='cuda:0')
episode: 246 training return: tensor(151.6175, device='cuda:0')
episode: 247 training return: tensor(149.7904, device='cuda:0')
epoch: 62 test_true_pfm: 134.42045139507792 sim_pfm: 142.09349904766424
episode: 248 training return: tensor(157.8258, device='cuda:0')
episode: 249 training return: tensor(145.9430, device='cuda:0')
episode: 250 training return: tensor(145.3048, device='cuda:0')
episode: 251 training return: tensor(147.1756, device='cuda:0')
epoch: 63 test_true_pfm: 130.99626422836656 sim_pfm: 143.72769541175802
episode: 252 training return: tensor(149.4324, device='cuda:0')
episode: 253 training return: tensor(138.0198, device='cuda:0')
episode: 254 training return: tensor(138.5315, device='cuda:0')
episode: 255 training return: tensor(140.4389, device='cuda:0')
epoch: 64 test_true_pfm: 125.35344483703923 sim_pfm: 145.89523311507074
episode: 256 training return: tensor(138.2453, device='cuda:0')
episode: 257 training return: tensor(138.7732, device='cuda:0')
episode: 258 training return: tensor(130.8218, device='cuda:0')
episode: 259 training return: tensor(161.0903, device='cuda:0')
epoch: 65 test_true_pfm: 131.94006171408404 sim_pfm: 146.88842728113522
episode: 260 training return: tensor(149.5119, device='cuda:0')
episode: 261 training return: tensor(149.5607, device='cuda:0')
episode: 262 training return: tensor(140.4121, device='cuda:0')
episode: 263 training return: tensor(142.7782, device='cuda:0')
epoch: 66 test_true_pfm: 126.90789040101424 sim_pfm: 140.28502496220753
episode: 264 training return: tensor(150.2874, device='cuda:0')
episode: 265 training return: tensor(138.0327, device='cuda:0')
episode: 266 training return: tensor(135.4103, device='cuda:0')
episode: 267 training return: tensor(155.5913, device='cuda:0')
epoch: 67 test_true_pfm: 127.01738513404875 sim_pfm: 140.17243011613027
episode: 268 training return: tensor(150.0601, device='cuda:0')
episode: 269 training return: tensor(140.3996, device='cuda:0')
episode: 270 training return: tensor(142.2822, device='cuda:0')
episode: 271 training return: tensor(143.3589, device='cuda:0')
epoch: 68 test_true_pfm: 129.24483231688174 sim_pfm: 140.5188322970527
episode: 272 training return: tensor(146.4321, device='cuda:0')
episode: 273 training return: tensor(146.1250, device='cuda:0')
episode: 274 training return: tensor(138.7739, device='cuda:0')
episode: 275 training return: tensor(139.7126, device='cuda:0')
epoch: 69 test_true_pfm: 131.694395217245 sim_pfm: 144.56914390302845
episode: 276 training return: tensor(134.6254, device='cuda:0')
episode: 277 training return: tensor(146.8069, device='cuda:0')
episode: 278 training return: tensor(137.2437, device='cuda:0')
episode: 279 training return: tensor(136.6752, device='cuda:0')
epoch: 70 test_true_pfm: 129.66184602296477 sim_pfm: 144.72185896278242
episode: 280 training return: tensor(136.8928, device='cuda:0')
episode: 281 training return: tensor(136.1664, device='cuda:0')
episode: 282 training return: tensor(138.1988, device='cuda:0')
episode: 283 training return: tensor(138.8826, device='cuda:0')
epoch: 71 test_true_pfm: 127.36998844516566 sim_pfm: 139.39260875593172
episode: 284 training return: tensor(148.5560, device='cuda:0')
episode: 285 training return: tensor(152.7124, device='cuda:0')
episode: 286 training return: tensor(140.9552, device='cuda:0')
episode: 287 training return: tensor(145.6630, device='cuda:0')
epoch: 72 test_true_pfm: 128.8766070532182 sim_pfm: 143.652334655507
episode: 288 training return: tensor(143.5090, device='cuda:0')
episode: 289 training return: tensor(143.9802, device='cuda:0')
episode: 290 training return: tensor(167.7509, device='cuda:0')
episode: 291 training return: tensor(141.7460, device='cuda:0')
epoch: 73 test_true_pfm: 129.5238110323678 sim_pfm: 144.0496679454227
episode: 292 training return: tensor(142.0959, device='cuda:0')
episode: 293 training return: tensor(138.2033, device='cuda:0')
episode: 294 training return: tensor(160.9937, device='cuda:0')
episode: 295 training return: tensor(143.0300, device='cuda:0')
epoch: 74 test_true_pfm: 126.95024075743402 sim_pfm: 137.89024340378236
episode: 296 training return: tensor(127.5954, device='cuda:0')
episode: 297 training return: tensor(156.8722, device='cuda:0')
episode: 298 training return: tensor(142.7742, device='cuda:0')
episode: 299 training return: tensor(158.4106, device='cuda:0')
epoch: 75 test_true_pfm: 132.35424662389164 sim_pfm: 139.65482287328922
episode: 300 training return: tensor(140.3345, device='cuda:0')
episode: 301 training return: tensor(150.1680, device='cuda:0')
episode: 302 training return: tensor(147.2378, device='cuda:0')
episode: 303 training return: tensor(139.9455, device='cuda:0')
epoch: 76 test_true_pfm: 133.16005497133966 sim_pfm: 147.3056651233288
episode: 304 training return: tensor(157.6559, device='cuda:0')
episode: 305 training return: tensor(157.0565, device='cuda:0')
episode: 306 training return: tensor(146.8157, device='cuda:0')
episode: 307 training return: tensor(136.1963, device='cuda:0')
epoch: 77 test_true_pfm: 126.66591454825034 sim_pfm: 141.08788628384937
episode: 308 training return: tensor(134.4932, device='cuda:0')
episode: 309 training return: tensor(141.7235, device='cuda:0')
episode: 310 training return: tensor(153.9027, device='cuda:0')
episode: 311 training return: tensor(138.0493, device='cuda:0')
epoch: 78 test_true_pfm: 130.76649525121564 sim_pfm: 135.97495689615025
episode: 312 training return: tensor(144.9025, device='cuda:0')
episode: 313 training return: tensor(152.8152, device='cuda:0')
episode: 314 training return: tensor(134.4871, device='cuda:0')
episode: 315 training return: tensor(139.5306, device='cuda:0')
epoch: 79 test_true_pfm: 129.18874128955596 sim_pfm: 137.94009543416323
episode: 316 training return: tensor(150.2560, device='cuda:0')
episode: 317 training return: tensor(146.5463, device='cuda:0')
episode: 318 training return: tensor(144.6483, device='cuda:0')
episode: 319 training return: tensor(127.2815, device='cuda:0')
epoch: 80 test_true_pfm: 129.5515203662409 sim_pfm: 147.31255197663558
episode: 320 training return: tensor(165.5893, device='cuda:0')
episode: 321 training return: tensor(143.0677, device='cuda:0')
episode: 322 training return: tensor(149.7430, device='cuda:0')
episode: 323 training return: tensor(158.8457, device='cuda:0')
epoch: 81 test_true_pfm: 132.7710436959104 sim_pfm: 139.67349529688363
episode: 324 training return: tensor(136.5629, device='cuda:0')
episode: 325 training return: tensor(148.4680, device='cuda:0')
episode: 326 training return: tensor(137.2560, device='cuda:0')
episode: 327 training return: tensor(140.9005, device='cuda:0')
epoch: 82 test_true_pfm: 130.94676066650817 sim_pfm: 152.32696353313514
episode: 328 training return: tensor(151.1751, device='cuda:0')
episode: 329 training return: tensor(147.8282, device='cuda:0')
episode: 330 training return: tensor(136.4987, device='cuda:0')
episode: 331 training return: tensor(158.1243, device='cuda:0')
epoch: 83 test_true_pfm: 130.43257606337815 sim_pfm: 151.7366945489659
episode: 332 training return: tensor(141.1424, device='cuda:0')
episode: 333 training return: tensor(144.7980, device='cuda:0')
episode: 334 training return: tensor(150.6208, device='cuda:0')
episode: 335 training return: tensor(141.1051, device='cuda:0')
epoch: 84 test_true_pfm: 123.33601375612928 sim_pfm: 148.28765991666006
episode: 336 training return: tensor(134.2427, device='cuda:0')
episode: 337 training return: tensor(143.4777, device='cuda:0')
episode: 338 training return: tensor(139.2963, device='cuda:0')
episode: 339 training return: tensor(132.0630, device='cuda:0')
epoch: 85 test_true_pfm: 130.13524157739914 sim_pfm: 134.59108899398706
episode: 340 training return: tensor(137.0320, device='cuda:0')
episode: 341 training return: tensor(139.2742, device='cuda:0')
episode: 342 training return: tensor(152.6273, device='cuda:0')
episode: 343 training return: tensor(144.8432, device='cuda:0')
epoch: 86 test_true_pfm: 129.87817056004405 sim_pfm: 142.94929824278807
episode: 344 training return: tensor(143.1634, device='cuda:0')
episode: 345 training return: tensor(144.0648, device='cuda:0')
episode: 346 training return: tensor(137.1990, device='cuda:0')
episode: 347 training return: tensor(139.8885, device='cuda:0')
epoch: 87 test_true_pfm: 127.44398776515736 sim_pfm: 137.87619727139244
episode: 348 training return: tensor(146.1379, device='cuda:0')
episode: 349 training return: tensor(148.9292, device='cuda:0')
episode: 350 training return: tensor(145.1577, device='cuda:0')
episode: 351 training return: tensor(144.8877, device='cuda:0')
epoch: 88 test_true_pfm: 129.26012268928002 sim_pfm: 147.602711726306
episode: 352 training return: tensor(156.2202, device='cuda:0')
episode: 353 training return: tensor(158.9464, device='cuda:0')
episode: 354 training return: tensor(131.9007, device='cuda:0')
episode: 355 training return: tensor(142.0944, device='cuda:0')
epoch: 89 test_true_pfm: 134.13715817744773 sim_pfm: 158.3055192220141
episode: 356 training return: tensor(142.5858, device='cuda:0')
episode: 357 training return: tensor(149.7270, device='cuda:0')
episode: 358 training return: tensor(135.6576, device='cuda:0')
episode: 359 training return: tensor(158.4355, device='cuda:0')
epoch: 90 test_true_pfm: 134.29387864263543 sim_pfm: 160.13082187250257
episode: 360 training return: tensor(143.8615, device='cuda:0')
episode: 361 training return: tensor(153.4564, device='cuda:0')
episode: 362 training return: tensor(162.8280, device='cuda:0')
episode: 363 training return: tensor(167.8973, device='cuda:0')
epoch: 91 test_true_pfm: 136.4535824756598 sim_pfm: 152.16279821014032
episode: 364 training return: tensor(159.4505, device='cuda:0')
episode: 365 training return: tensor(141.9939, device='cuda:0')
episode: 366 training return: tensor(153.7800, device='cuda:0')
episode: 367 training return: tensor(162.1740, device='cuda:0')
epoch: 92 test_true_pfm: 132.54492853761857 sim_pfm: 145.70111530844588
episode: 368 training return: tensor(147.2898, device='cuda:0')
episode: 369 training return: tensor(134.1360, device='cuda:0')
episode: 370 training return: tensor(142.6991, device='cuda:0')
episode: 371 training return: tensor(143.9445, device='cuda:0')
epoch: 93 test_true_pfm: 131.55147562066594 sim_pfm: 155.21056197766447
episode: 372 training return: tensor(136.1923, device='cuda:0')
episode: 373 training return: tensor(155.4595, device='cuda:0')
episode: 374 training return: tensor(141.8336, device='cuda:0')
episode: 375 training return: tensor(160.3040, device='cuda:0')
epoch: 94 test_true_pfm: 134.32791062494908 sim_pfm: 146.0654027382494
episode: 376 training return: tensor(163.7526, device='cuda:0')
episode: 377 training return: tensor(160.7240, device='cuda:0')
episode: 378 training return: tensor(136.3520, device='cuda:0')
episode: 379 training return: tensor(148.7150, device='cuda:0')
epoch: 95 test_true_pfm: 131.67989915055244 sim_pfm: 148.51564600208658
episode: 380 training return: tensor(145.9272, device='cuda:0')
episode: 381 training return: tensor(156.4695, device='cuda:0')
episode: 382 training return: tensor(153.5345, device='cuda:0')
episode: 383 training return: tensor(162.1228, device='cuda:0')
epoch: 96 test_true_pfm: 134.45388212381664 sim_pfm: 147.15322762280704
episode: 384 training return: tensor(167.2536, device='cuda:0')
episode: 385 training return: tensor(152.7761, device='cuda:0')
episode: 386 training return: tensor(133.8256, device='cuda:0')
episode: 387 training return: tensor(158.2920, device='cuda:0')
epoch: 97 test_true_pfm: 134.84852980670587 sim_pfm: 155.88996957984054
episode: 388 training return: tensor(148.5411, device='cuda:0')
episode: 389 training return: tensor(152.1887, device='cuda:0')
episode: 390 training return: tensor(139.8906, device='cuda:0')
episode: 391 training return: tensor(161.5105, device='cuda:0')
epoch: 98 test_true_pfm: 135.27179635547608 sim_pfm: 156.82775039781117
episode: 392 training return: tensor(142.4219, device='cuda:0')
episode: 393 training return: tensor(135.3878, device='cuda:0')
episode: 394 training return: tensor(168.3295, device='cuda:0')
episode: 395 training return: tensor(163.9109, device='cuda:0')
epoch: 99 test_true_pfm: 133.89792092319937 sim_pfm: 155.12108317521634
episode: 396 training return: tensor(162.0740, device='cuda:0')
episode: 397 training return: tensor(161.0643, device='cuda:0')
episode: 398 training return: tensor(139.3248, device='cuda:0')
episode: 399 training return: tensor(154.2562, device='cuda:0')
epoch: 100 test_true_pfm: 136.70957441886415 sim_pfm: 148.5804526451393
episode: 400 training return: tensor(159.4690, device='cuda:0')
episode: 401 training return: tensor(140.3167, device='cuda:0')
episode: 402 training return: tensor(154.2330, device='cuda:0')
episode: 403 training return: tensor(140.7956, device='cuda:0')
epoch: 101 test_true_pfm: 133.09755433582595 sim_pfm: 148.06509651946254
episode: 404 training return: tensor(154.3012, device='cuda:0')
episode: 405 training return: tensor(143.7675, device='cuda:0')
episode: 406 training return: tensor(144.6108, device='cuda:0')
episode: 407 training return: tensor(142.2773, device='cuda:0')
epoch: 102 test_true_pfm: 130.3516042457407 sim_pfm: 141.65967267098603
episode: 408 training return: tensor(154.4080, device='cuda:0')
episode: 409 training return: tensor(136.2163, device='cuda:0')
episode: 410 training return: tensor(164.4400, device='cuda:0')
episode: 411 training return: tensor(139.5982, device='cuda:0')
epoch: 103 test_true_pfm: 131.5205911162671 sim_pfm: 150.92203864196782
episode: 412 training return: tensor(152.7227, device='cuda:0')
episode: 413 training return: tensor(156.9361, device='cuda:0')
episode: 414 training return: tensor(149.7593, device='cuda:0')
episode: 415 training return: tensor(139.8623, device='cuda:0')
epoch: 104 test_true_pfm: 132.68999446101427 sim_pfm: 148.23024897845463
episode: 416 training return: tensor(154.9763, device='cuda:0')
episode: 417 training return: tensor(138.5927, device='cuda:0')
episode: 418 training return: tensor(148.0165, device='cuda:0')
episode: 419 training return: tensor(151.9790, device='cuda:0')
epoch: 105 test_true_pfm: 135.9780522447852 sim_pfm: 152.61534900671685
episode: 420 training return: tensor(147.5874, device='cuda:0')
episode: 421 training return: tensor(141.4468, device='cuda:0')
episode: 422 training return: tensor(160.7181, device='cuda:0')
episode: 423 training return: tensor(146.0760, device='cuda:0')
epoch: 106 test_true_pfm: 138.3894762561792 sim_pfm: 155.51204568558606
episode: 424 training return: tensor(138.6358, device='cuda:0')
episode: 425 training return: tensor(156.5975, device='cuda:0')
episode: 426 training return: tensor(139.9915, device='cuda:0')
episode: 427 training return: tensor(167.3828, device='cuda:0')
epoch: 107 test_true_pfm: 135.51854629110903 sim_pfm: 151.75970017955405
episode: 428 training return: tensor(130.0890, device='cuda:0')
episode: 429 training return: tensor(154.1290, device='cuda:0')
episode: 430 training return: tensor(162.6972, device='cuda:0')
episode: 431 training return: tensor(155.8080, device='cuda:0')
epoch: 108 test_true_pfm: 134.14445341446793 sim_pfm: 142.32438753520256
episode: 432 training return: tensor(151.8556, device='cuda:0')
episode: 433 training return: tensor(138.5520, device='cuda:0')
episode: 434 training return: tensor(156.0059, device='cuda:0')
episode: 435 training return: tensor(168.7612, device='cuda:0')
epoch: 109 test_true_pfm: 132.6108700622009 sim_pfm: 160.34156148127514
episode: 436 training return: tensor(155.6277, device='cuda:0')
episode: 437 training return: tensor(146.3713, device='cuda:0')
episode: 438 training return: tensor(146.8675, device='cuda:0')
episode: 439 training return: tensor(163.3257, device='cuda:0')
epoch: 110 test_true_pfm: 135.13568316329298 sim_pfm: 157.0069330534199
episode: 440 training return: tensor(154.4202, device='cuda:0')
episode: 441 training return: tensor(152.2104, device='cuda:0')
episode: 442 training return: tensor(143.3314, device='cuda:0')
episode: 443 training return: tensor(152.6903, device='cuda:0')
epoch: 111 test_true_pfm: 135.02719554716467 sim_pfm: 148.71314654867166
episode: 444 training return: tensor(148.4480, device='cuda:0')
episode: 445 training return: tensor(142.1057, device='cuda:0')
episode: 446 training return: tensor(157.4368, device='cuda:0')
episode: 447 training return: tensor(168.3574, device='cuda:0')
epoch: 112 test_true_pfm: 132.29243866400438 sim_pfm: 160.71285609351472
episode: 448 training return: tensor(152.2860, device='cuda:0')
episode: 449 training return: tensor(152.8982, device='cuda:0')
episode: 450 training return: tensor(160.8177, device='cuda:0')
episode: 451 training return: tensor(148.8658, device='cuda:0')
epoch: 113 test_true_pfm: 125.10833665621786 sim_pfm: 150.38571118322434
episode: 452 training return: tensor(145.2114, device='cuda:0')
episode: 453 training return: tensor(147.7697, device='cuda:0')
episode: 454 training return: tensor(140.9109, device='cuda:0')
episode: 455 training return: tensor(140.8494, device='cuda:0')
epoch: 114 test_true_pfm: 130.54806184751487 sim_pfm: 149.6756906544324
episode: 456 training return: tensor(149.5970, device='cuda:0')
episode: 457 training return: tensor(148.0755, device='cuda:0')
episode: 458 training return: tensor(151.1650, device='cuda:0')
episode: 459 training return: tensor(164.6155, device='cuda:0')
epoch: 115 test_true_pfm: 129.67809494162685 sim_pfm: 148.95916323360288
episode: 460 training return: tensor(163.0769, device='cuda:0')
episode: 461 training return: tensor(139.4352, device='cuda:0')
episode: 462 training return: tensor(144.1900, device='cuda:0')
episode: 463 training return: tensor(152.6574, device='cuda:0')
epoch: 116 test_true_pfm: 134.3529577335014 sim_pfm: 162.9636155851593
episode: 464 training return: tensor(163.8442, device='cuda:0')
episode: 465 training return: tensor(164.0254, device='cuda:0')
episode: 466 training return: tensor(167.2584, device='cuda:0')
episode: 467 training return: tensor(158.5536, device='cuda:0')
epoch: 117 test_true_pfm: 134.14083888272157 sim_pfm: 164.56738420601468
episode: 468 training return: tensor(155.5592, device='cuda:0')
episode: 469 training return: tensor(164.5860, device='cuda:0')
episode: 470 training return: tensor(166.0864, device='cuda:0')
episode: 471 training return: tensor(137.7114, device='cuda:0')
epoch: 118 test_true_pfm: 131.31014825219398 sim_pfm: 145.01474773649244
episode: 472 training return: tensor(149.3418, device='cuda:0')
episode: 473 training return: tensor(141.0535, device='cuda:0')
episode: 474 training return: tensor(142.5844, device='cuda:0')
episode: 475 training return: tensor(161.3655, device='cuda:0')
epoch: 119 test_true_pfm: 132.30260830533018 sim_pfm: 151.92826973069458
episode: 476 training return: tensor(145.3401, device='cuda:0')
episode: 477 training return: tensor(161.7377, device='cuda:0')
episode: 478 training return: tensor(148.1196, device='cuda:0')
episode: 479 training return: tensor(159.0058, device='cuda:0')
epoch: 120 test_true_pfm: 136.05205593333946 sim_pfm: 152.40020855948677
episode: 480 training return: tensor(170.3836, device='cuda:0')
episode: 481 training return: tensor(162.2935, device='cuda:0')
episode: 482 training return: tensor(162.4544, device='cuda:0')
episode: 483 training return: tensor(159.5929, device='cuda:0')
epoch: 121 test_true_pfm: 133.87905864264502 sim_pfm: 149.11117060685064
episode: 484 training return: tensor(153.5460, device='cuda:0')
episode: 485 training return: tensor(152.8400, device='cuda:0')
episode: 486 training return: tensor(176.8124, device='cuda:0')
episode: 487 training return: tensor(165.9864, device='cuda:0')
epoch: 122 test_true_pfm: 131.3370366798515 sim_pfm: 157.69209358592053
episode: 488 training return: tensor(168.6776, device='cuda:0')
episode: 489 training return: tensor(162.5017, device='cuda:0')
episode: 490 training return: tensor(151.3421, device='cuda:0')
episode: 491 training return: tensor(146.1937, device='cuda:0')
epoch: 123 test_true_pfm: 133.1099969598509 sim_pfm: 155.23603905341005
episode: 492 training return: tensor(157.6897, device='cuda:0')
episode: 493 training return: tensor(159.2615, device='cuda:0')
episode: 494 training return: tensor(157.4694, device='cuda:0')
episode: 495 training return: tensor(158.5313, device='cuda:0')
epoch: 124 test_true_pfm: 132.45227574153674 sim_pfm: 156.60846365177423
episode: 496 training return: tensor(166.3975, device='cuda:0')
episode: 497 training return: tensor(162.1471, device='cuda:0')
episode: 498 training return: tensor(159.8294, device='cuda:0')
episode: 499 training return: tensor(151.0549, device='cuda:0')
epoch: 125 test_true_pfm: 135.38260708661346 sim_pfm: 151.01143785231397
episode: 500 training return: tensor(158.8411, device='cuda:0')
episode: 501 training return: tensor(139.4983, device='cuda:0')
episode: 502 training return: tensor(152.5748, device='cuda:0')
episode: 503 training return: tensor(181.7181, device='cuda:0')
epoch: 126 test_true_pfm: 134.75424612378504 sim_pfm: 159.6323033323162
episode: 504 training return: tensor(147.3700, device='cuda:0')
episode: 505 training return: tensor(138.3584, device='cuda:0')
episode: 506 training return: tensor(164.4310, device='cuda:0')
episode: 507 training return: tensor(158.7132, device='cuda:0')
epoch: 127 test_true_pfm: 129.10072532455888 sim_pfm: 160.71688796002417
episode: 508 training return: tensor(148.8859, device='cuda:0')
episode: 509 training return: tensor(153.3337, device='cuda:0')
episode: 510 training return: tensor(162.0277, device='cuda:0')
episode: 511 training return: tensor(155.4891, device='cuda:0')
epoch: 128 test_true_pfm: 133.5725204345066 sim_pfm: 160.40504862159725
episode: 512 training return: tensor(160.9449, device='cuda:0')
episode: 513 training return: tensor(145.4208, device='cuda:0')
episode: 514 training return: tensor(137.3396, device='cuda:0')
episode: 515 training return: tensor(163.9769, device='cuda:0')
epoch: 129 test_true_pfm: 133.49908594570272 sim_pfm: 145.73115012153283
episode: 516 training return: tensor(152.0221, device='cuda:0')
episode: 517 training return: tensor(161.2031, device='cuda:0')
episode: 518 training return: tensor(147.3110, device='cuda:0')
episode: 519 training return: tensor(158.6133, device='cuda:0')
epoch: 130 test_true_pfm: 138.11264132991604 sim_pfm: 152.27165800782387
episode: 520 training return: tensor(178.3575, device='cuda:0')
episode: 521 training return: tensor(165.7640, device='cuda:0')
episode: 522 training return: tensor(154.5325, device='cuda:0')
episode: 523 training return: tensor(154.3150, device='cuda:0')
epoch: 131 test_true_pfm: 134.79821865515888 sim_pfm: 154.92642114929623
episode: 524 training return: tensor(170.5310, device='cuda:0')
episode: 525 training return: tensor(165.6787, device='cuda:0')
episode: 526 training return: tensor(169.1669, device='cuda:0')
episode: 527 training return: tensor(175.8740, device='cuda:0')
epoch: 132 test_true_pfm: 128.62278938222624 sim_pfm: 153.09244541102672
episode: 528 training return: tensor(151.5910, device='cuda:0')
episode: 529 training return: tensor(137.1510, device='cuda:0')
episode: 530 training return: tensor(165.4402, device='cuda:0')
episode: 531 training return: tensor(142.5606, device='cuda:0')
epoch: 133 test_true_pfm: 130.27664191591776 sim_pfm: 144.55897671888815
episode: 532 training return: tensor(151.1240, device='cuda:0')
episode: 533 training return: tensor(149.1475, device='cuda:0')
episode: 534 training return: tensor(165.7552, device='cuda:0')
episode: 535 training return: tensor(146.2698, device='cuda:0')
epoch: 134 test_true_pfm: 136.44577093858817 sim_pfm: 153.25703564368888
episode: 536 training return: tensor(164.9398, device='cuda:0')
episode: 537 training return: tensor(136.0804, device='cuda:0')
episode: 538 training return: tensor(156.3976, device='cuda:0')
episode: 539 training return: tensor(161.7480, device='cuda:0')
epoch: 135 test_true_pfm: 135.6477076101009 sim_pfm: 162.10894470983186
episode: 540 training return: tensor(157.1561, device='cuda:0')
episode: 541 training return: tensor(145.3154, device='cuda:0')
episode: 542 training return: tensor(160.2534, device='cuda:0')
episode: 543 training return: tensor(138.6184, device='cuda:0')
epoch: 136 test_true_pfm: 136.24492864204953 sim_pfm: 155.51876604735736
episode: 544 training return: tensor(150.6320, device='cuda:0')
episode: 545 training return: tensor(139.9844, device='cuda:0')
episode: 546 training return: tensor(165.8530, device='cuda:0')
episode: 547 training return: tensor(140.4409, device='cuda:0')
epoch: 137 test_true_pfm: 131.16086353247013 sim_pfm: 146.51280127944773
episode: 548 training return: tensor(149.2612, device='cuda:0')
episode: 549 training return: tensor(165.2831, device='cuda:0')
episode: 550 training return: tensor(139.3314, device='cuda:0')
episode: 551 training return: tensor(147.7006, device='cuda:0')
epoch: 138 test_true_pfm: 136.02884937047844 sim_pfm: 151.93439721006433
episode: 552 training return: tensor(148.5846, device='cuda:0')
episode: 553 training return: tensor(146.1788, device='cuda:0')
episode: 554 training return: tensor(146.9612, device='cuda:0')
episode: 555 training return: tensor(150.6939, device='cuda:0')
epoch: 139 test_true_pfm: 132.8564692511183 sim_pfm: 153.50956750232726
episode: 556 training return: tensor(155.4370, device='cuda:0')
episode: 557 training return: tensor(152.3324, device='cuda:0')
episode: 558 training return: tensor(137.0601, device='cuda:0')
episode: 559 training return: tensor(151.8132, device='cuda:0')
epoch: 140 test_true_pfm: 133.5905004994176 sim_pfm: 150.50640344624406
episode: 560 training return: tensor(150.0596, device='cuda:0')
episode: 561 training return: tensor(160.5430, device='cuda:0')
episode: 562 training return: tensor(148.5944, device='cuda:0')
episode: 563 training return: tensor(141.5899, device='cuda:0')
epoch: 141 test_true_pfm: 133.41019557641135 sim_pfm: 150.27745368874167
episode: 564 training return: tensor(156.5729, device='cuda:0')
episode: 565 training return: tensor(144.7175, device='cuda:0')
episode: 566 training return: tensor(143.8421, device='cuda:0')
episode: 567 training return: tensor(161.0312, device='cuda:0')
epoch: 142 test_true_pfm: 132.71813863401394 sim_pfm: 166.2287860623328
episode: 568 training return: tensor(154.3262, device='cuda:0')
episode: 569 training return: tensor(160.5451, device='cuda:0')
episode: 570 training return: tensor(154.7890, device='cuda:0')
episode: 571 training return: tensor(153.7283, device='cuda:0')
epoch: 143 test_true_pfm: 132.41392321011568 sim_pfm: 155.26708702172618
episode: 572 training return: tensor(155.2819, device='cuda:0')
episode: 573 training return: tensor(156.4406, device='cuda:0')
episode: 574 training return: tensor(146.3847, device='cuda:0')
episode: 575 training return: tensor(139.7501, device='cuda:0')
epoch: 144 test_true_pfm: 132.6156268275944 sim_pfm: 154.14367593452917
episode: 576 training return: tensor(171.2761, device='cuda:0')
episode: 577 training return: tensor(139.4414, device='cuda:0')
episode: 578 training return: tensor(160.9193, device='cuda:0')
episode: 579 training return: tensor(150.0090, device='cuda:0')
epoch: 145 test_true_pfm: 134.89908021891955 sim_pfm: 152.90936488609296
episode: 580 training return: tensor(154.1101, device='cuda:0')
episode: 581 training return: tensor(139.4137, device='cuda:0')
episode: 582 training return: tensor(163.3527, device='cuda:0')
episode: 583 training return: tensor(154.9574, device='cuda:0')
epoch: 146 test_true_pfm: 136.46957633661216 sim_pfm: 155.78390839464265
episode: 584 training return: tensor(149.1262, device='cuda:0')
episode: 585 training return: tensor(148.7817, device='cuda:0')
episode: 586 training return: tensor(139.2525, device='cuda:0')
episode: 587 training return: tensor(165.3874, device='cuda:0')
epoch: 147 test_true_pfm: 136.65694999773308 sim_pfm: 155.57697667144822
episode: 588 training return: tensor(178.2495, device='cuda:0')
episode: 589 training return: tensor(152.1445, device='cuda:0')
episode: 590 training return: tensor(167.0457, device='cuda:0')
episode: 591 training return: tensor(165.6503, device='cuda:0')
epoch: 148 test_true_pfm: 136.88588545301576 sim_pfm: 166.85787987268995
episode: 592 training return: tensor(163.8591, device='cuda:0')
episode: 593 training return: tensor(159.2319, device='cuda:0')
episode: 594 training return: tensor(135.4064, device='cuda:0')
episode: 595 training return: tensor(168.0817, device='cuda:0')
epoch: 149 test_true_pfm: 131.79390190662102 sim_pfm: 158.52749098686618
episode: 596 training return: tensor(154.9934, device='cuda:0')
episode: 597 training return: tensor(158.0493, device='cuda:0')
episode: 598 training return: tensor(142.1231, device='cuda:0')
episode: 599 training return: tensor(159.4568, device='cuda:0')
epoch: 150 test_true_pfm: 130.81585013950715 sim_pfm: 158.5398486856371
