['--env', 'Hopper-v3', '--traj', 'medium']
epoch: 0 training_loss 0.23903139255940914 test_loss: 0.19289804697036744
epoch: 1 training_loss 0.20509605593979358 test_loss: 0.21306324005126953
epoch: 2 training_loss 0.20115842014551163 test_loss: 0.20767321586608886
epoch: 3 training_loss 0.18957049913704396 test_loss: 0.18930861949920655
epoch: 4 training_loss 0.19911779522895812 test_loss: 0.19838868379592894
epoch: 5 training_loss 0.1829310442507267 test_loss: 0.18590471744537354
epoch: 6 training_loss 0.19264295056462288 test_loss: 0.19927598237991334
epoch: 7 training_loss 0.1920642966404557 test_loss: 0.19207738637924193
epoch: 8 training_loss 0.19324322625994683 test_loss: 0.17152975797653197
epoch: 9 training_loss 0.19961299397051335 test_loss: 0.18399595022201537
epoch: 10 training_loss 0.19163102947175503 test_loss: 0.18185417652130126
epoch: 11 training_loss 0.18925698168575764 test_loss: 0.1901837706565857
epoch: 12 training_loss 0.17935652971267702 test_loss: 0.19939807653427125
epoch: 13 training_loss 0.18652797758579254 test_loss: 0.16796205043792725
epoch: 14 training_loss 0.18577977187931538 test_loss: 0.1664711356163025
epoch: 15 training_loss 0.18008959166705607 test_loss: 0.19210880994796753
epoch: 16 training_loss 0.1882144571095705 test_loss: 0.17853413820266723
epoch: 17 training_loss 0.19068945288658143 test_loss: 0.18827683925628663
epoch: 18 training_loss 0.18090626515448094 test_loss: 0.17662614583969116
epoch: 19 training_loss 0.1835613404214382 test_loss: 0.14656661748886107
epoch: 20 training_loss 0.1872853996604681 test_loss: 0.17854611873626708
epoch: 21 training_loss 0.1809774522483349 test_loss: 0.16802825927734374
epoch: 22 training_loss 0.17787766374647618 test_loss: 0.18262095451354982
epoch: 23 training_loss 0.18111724108457566 test_loss: 0.18485411405563354
epoch: 24 training_loss 0.183316830098629 test_loss: 0.18135329484939575
epoch: 25 training_loss 0.18086880773305894 test_loss: 0.18909163475036622
epoch: 26 training_loss 0.18867808647453785 test_loss: 0.19963618516921997
epoch: 27 training_loss 0.18697814531624318 test_loss: 0.16846890449523927
epoch: 28 training_loss 0.1706480512022972 test_loss: 0.193838369846344
epoch: 29 training_loss 0.1782195507735014 test_loss: 0.15753482580184935
epoch: 30 training_loss 0.18146639853715896 test_loss: 0.1620318651199341
epoch: 31 training_loss 0.18692261293530466 test_loss: 0.1829914927482605
epoch: 32 training_loss 0.18720007538795472 test_loss: 0.18849340677261353
epoch: 33 training_loss 0.1810342986136675 test_loss: 0.18860796689987183
epoch: 34 training_loss 0.17969327993690967 test_loss: 0.20070738792419435
epoch: 35 training_loss 0.17998260609805583 test_loss: 0.19782369136810302
epoch: 36 training_loss 0.17865179643034934 test_loss: 0.17458206415176392
epoch: 37 training_loss 0.18097892448306083 test_loss: 0.15675323009490966
epoch: 38 training_loss 0.18245972387492657 test_loss: 0.16967262029647828
epoch: 39 training_loss 0.17528139151632785 test_loss: 0.18257429599761962
epoch: 40 training_loss 0.18102551713585854 test_loss: 0.19116830825805664
epoch: 41 training_loss 0.18497763201594353 test_loss: 0.1745687246322632
epoch: 42 training_loss 0.18085939198732376 test_loss: 0.21829721927642823
epoch: 43 training_loss 0.1794597837328911 test_loss: 0.1860156774520874
epoch: 44 training_loss 0.18069130495190622 test_loss: 0.1979604721069336
epoch: 45 training_loss 0.18267514891922473 test_loss: 0.20198521614074708
epoch: 46 training_loss 0.1694690800458193 test_loss: 0.1893458843231201
epoch: 47 training_loss 0.18264521464705466 test_loss: 0.17199150323867798
epoch: 48 training_loss 0.18073404237627982 test_loss: 0.18597933053970336
epoch: 49 training_loss 0.1790360327810049 test_loss: 0.19834455251693725
epoch: 50 training_loss 0.18399448007345198 test_loss: 0.19114192724227905
epoch: 51 training_loss 0.1777553514391184 test_loss: 0.187127685546875
epoch: 52 training_loss 0.18267934791743756 test_loss: 0.20119955539703369
epoch: 53 training_loss 0.18064751252532005 test_loss: 0.19591381549835205
epoch: 54 training_loss 0.18046519644558429 test_loss: 0.1698328137397766
epoch: 55 training_loss 0.1819302575290203 test_loss: 0.17673810720443725
epoch: 56 training_loss 0.1891503305733204 test_loss: 0.1671743869781494
epoch: 57 training_loss 0.18387695521116257 test_loss: 0.171130907535553
epoch: 58 training_loss 0.18086741410195828 test_loss: 0.15019770860671997
epoch: 59 training_loss 0.17613752245903014 test_loss: 0.17408041954040526
epoch: 60 training_loss 0.17603216029703617 test_loss: 0.19268981218338013
epoch: 61 training_loss 0.18633870020508767 test_loss: 0.18181697130203248
epoch: 62 training_loss 0.1808006362617016 test_loss: 0.1763890266418457
epoch: 63 training_loss 0.18401865355670452 test_loss: 0.20106661319732666
epoch: 64 training_loss 0.1714247453212738 test_loss: 0.1993628740310669
epoch: 65 training_loss 0.18198901265859604 test_loss: 0.19003995656967163
epoch: 66 training_loss 0.1735898245126009 test_loss: 0.16495540142059326
epoch: 67 training_loss 0.17860608011484147 test_loss: 0.16151617765426635
epoch: 68 training_loss 0.17574336241930724 test_loss: 0.15911239385604858
epoch: 69 training_loss 0.18209340617060663 test_loss: 0.16250252723693848
epoch: 70 training_loss 0.18182393297553062 test_loss: 0.1952824831008911
epoch: 71 training_loss 0.177472023665905 test_loss: 0.18781896829605102
epoch: 72 training_loss 0.17816553592681886 test_loss: 0.18271955251693725
epoch: 73 training_loss 0.1868000267073512 test_loss: 0.1572060465812683
epoch: 74 training_loss 0.17888728000223636 test_loss: 0.16008230447769164
epoch: 75 training_loss 0.17736438319087028 test_loss: 0.16839752197265626
epoch: 76 training_loss 0.18381998762488366 test_loss: 0.1864100456237793
epoch: 77 training_loss 0.17466172479093076 test_loss: 0.18704862594604493
epoch: 78 training_loss 0.17763271123170854 test_loss: 0.15364211797714233
epoch: 79 training_loss 0.1711890359222889 test_loss: 0.17580362558364868
epoch: 80 training_loss 0.18020102486014367 test_loss: 0.20932254791259766
epoch: 81 training_loss 0.17874712713062763 test_loss: 0.17991615533828736
epoch: 82 training_loss 0.1834772626683116 test_loss: 0.18651762008666992
epoch: 83 training_loss 0.17794686272740365 test_loss: 0.1536259651184082
epoch: 84 training_loss 0.17196077473461627 test_loss: 0.1766636848449707
epoch: 85 training_loss 0.1728590525686741 test_loss: 0.17537589073181153
epoch: 86 training_loss 0.17735000062733888 test_loss: 0.18420593738555907
epoch: 87 training_loss 0.18122675888240336 test_loss: 0.1480938196182251
epoch: 88 training_loss 0.18383236818015575 test_loss: 0.17419365644454957
epoch: 89 training_loss 0.18131555996835233 test_loss: 0.18142900466918946
epoch: 90 training_loss 0.17611066728830338 test_loss: 0.1900310516357422
epoch: 91 training_loss 0.1778350828588009 test_loss: 0.1788177728652954
epoch: 92 training_loss 0.17926033079624176 test_loss: 0.1708754301071167
epoch: 93 training_loss 0.17400886461138726 test_loss: 0.19562283754348755
epoch: 94 training_loss 0.1781005610525608 test_loss: 0.1547754406929016
epoch: 95 training_loss 0.17902797482907773 test_loss: 0.2160323143005371
epoch: 96 training_loss 0.18141749054193496 test_loss: 0.1668405055999756
epoch: 97 training_loss 0.1808723697066307 test_loss: 0.17842992544174194
epoch: 98 training_loss 0.1865619232133031 test_loss: 0.17658329010009766
epoch: 99 training_loss 0.17917690351605414 test_loss: 0.15671906471252442
epoch: 100 training_loss 0.1798316179215908 test_loss: 0.19096187353134156
epoch: 101 training_loss 0.1810279382020235 test_loss: 0.18909866809844972
epoch: 102 training_loss 0.17420338325202464 test_loss: 0.20488052368164061
epoch: 103 training_loss 0.17652957677841186 test_loss: 0.19149973392486572
epoch: 104 training_loss 0.17527819715440274 test_loss: 0.1648806095123291
epoch: 105 training_loss 0.17434903264045715 test_loss: 0.18343875408172608
epoch: 106 training_loss 0.1797089172154665 test_loss: 0.16888837814331054
epoch: 107 training_loss 0.1746052024513483 test_loss: 0.17774041891098022
epoch: 108 training_loss 0.17862048372626305 test_loss: 0.16121650934219361
epoch: 109 training_loss 0.17783888265490533 test_loss: 0.18412123918533324
epoch: 110 training_loss 0.1798762959986925 test_loss: 0.16487739086151124
epoch: 111 training_loss 0.17739839486777784 test_loss: 0.17960731983184813
epoch: 112 training_loss 0.18218486629426478 test_loss: 0.17152855396270753
epoch: 113 training_loss 0.18152826581150294 test_loss: 0.19335013628005981
epoch: 114 training_loss 0.1807192053645849 test_loss: 0.19375238418579102
epoch: 115 training_loss 0.17358303852379323 test_loss: 0.18545080423355104
epoch: 116 training_loss 0.17818751864135265 test_loss: 0.2061518907546997
epoch: 117 training_loss 0.1819745768606663 test_loss: 0.18514024019241332
epoch: 118 training_loss 0.17824971865862607 test_loss: 0.16790378093719482
epoch: 119 training_loss 0.17752544932067393 test_loss: 0.1733315706253052
epoch: 120 training_loss 0.17590936586260797 test_loss: 0.17732577323913573
epoch: 121 training_loss 0.17756411530077457 test_loss: 0.19334479570388793
epoch: 122 training_loss 0.17661508597433567 test_loss: 0.18598867654800416
epoch: 123 training_loss 0.1816753575950861 test_loss: 0.18005286455154418
epoch: 124 training_loss 0.1765795111656189 test_loss: 0.16371814012527466
epoch: 125 training_loss 0.17440717704594136 test_loss: 0.19825469255447387
epoch: 126 training_loss 0.17595017209649086 test_loss: 0.17924678325653076
epoch: 127 training_loss 0.1753362238407135 test_loss: 0.17493786811828613
epoch: 128 training_loss 0.17435990460217 test_loss: 0.2103281021118164
epoch: 129 training_loss 0.16990289375185966 test_loss: 0.17664271593093872
epoch: 130 training_loss 0.17751276202499866 test_loss: 0.1697678804397583
epoch: 131 training_loss 0.17141794256865978 test_loss: 0.17415558099746703
epoch: 132 training_loss 0.1742347738146782 test_loss: 0.16859980821609497
epoch: 133 training_loss 0.1790806633979082 test_loss: 0.19933388233184815
epoch: 134 training_loss 0.1797985491901636 test_loss: 0.2015598773956299
epoch: 135 training_loss 0.18195330090820788 test_loss: 0.189801824092865
epoch: 136 training_loss 0.1751379443705082 test_loss: 0.17039382457733154
epoch: 137 training_loss 0.17929374068975448 test_loss: 0.1760166883468628
epoch: 138 training_loss 0.17587229058146478 test_loss: 0.16534539461135864
epoch: 139 training_loss 0.17555023796856403 test_loss: 0.19470417499542236
epoch: 140 training_loss 0.17507592119276524 test_loss: 0.1889845609664917
epoch: 141 training_loss 0.17375537261366844 test_loss: 0.18361393213272095
epoch: 142 training_loss 0.17372494526207446 test_loss: 0.1850632905960083
epoch: 143 training_loss 0.1886642597615719 test_loss: 0.19055570363998414
epoch: 144 training_loss 0.17874902434647083 test_loss: 0.1534327745437622
epoch: 145 training_loss 0.18114653341472148 test_loss: 0.19428035020828247
epoch: 146 training_loss 0.17534768640995024 test_loss: 0.2047410011291504
epoch: 147 training_loss 0.17750100657343865 test_loss: 0.168262255191803
epoch: 148 training_loss 0.1767043440043926 test_loss: 0.16602905988693237
epoch: 149 training_loss 0.18224869966506957 test_loss: 0.17578281164169313
epoch: 0 training_loss 8.627940492630005 test_loss: 5.261022567749023
epoch: 1 training_loss 3.999111807346344 test_loss: 3.2292453765869142
epoch: 2 training_loss 2.717366726398468 test_loss: 2.3141738891601564
epoch: 3 training_loss 2.1239975786209104 test_loss: 1.9758508682250977
epoch: 4 training_loss 1.8390689957141877 test_loss: 1.7290908813476562
epoch: 5 training_loss 1.6406695222854615 test_loss: 1.5563002586364747
epoch: 6 training_loss 1.4865608215332031 test_loss: 1.434592342376709
epoch: 7 training_loss 1.3660775339603424 test_loss: 1.339559555053711
epoch: 8 training_loss 1.2727190375328064 test_loss: 1.254594612121582
epoch: 9 training_loss 1.2052911746501922 test_loss: 1.1335588455200196
epoch: 10 training_loss 1.159815358519554 test_loss: 1.077242374420166
epoch: 11 training_loss 1.105797369480133 test_loss: 1.0962122917175292
epoch: 12 training_loss 1.0469350039958953 test_loss: 1.003776741027832
epoch: 13 training_loss 1.0090019196271895 test_loss: 0.9646205902099609
epoch: 14 training_loss 0.9660630333423614 test_loss: 0.9671483993530273
epoch: 15 training_loss 0.9645965194702149 test_loss: 0.9544207572937011
epoch: 16 training_loss 0.9171602290868759 test_loss: 0.9185853004455566
epoch: 17 training_loss 0.9006308263540268 test_loss: 0.9037528991699219
epoch: 18 training_loss 0.8841315251588822 test_loss: 0.8546296119689941
epoch: 19 training_loss 0.8603772348165513 test_loss: 0.8586878776550293
epoch: 20 training_loss 0.8532199215888977 test_loss: 0.806540584564209
epoch: 21 training_loss 0.8269923150539398 test_loss: 0.8709300994873047
epoch: 22 training_loss 0.8316429948806763 test_loss: 0.8188345909118653
epoch: 23 training_loss 0.7991540169715882 test_loss: 0.7752020835876465
epoch: 24 training_loss 0.8099495279788971 test_loss: 0.7668686866760254
epoch: 25 training_loss 0.7909505492448807 test_loss: 0.809233570098877
epoch: 26 training_loss 0.7824766314029694 test_loss: 0.7459288597106933
epoch: 27 training_loss 0.7612869149446487 test_loss: 0.7565280437469483
epoch: 28 training_loss 0.761174156665802 test_loss: 0.7453655242919922
epoch: 29 training_loss 0.7486831396818161 test_loss: 0.7185163497924805
epoch: 30 training_loss 0.744466341137886 test_loss: 0.7270537376403808
epoch: 31 training_loss 0.7301986175775528 test_loss: 0.7089213848114013
epoch: 32 training_loss 0.7186596059799194 test_loss: 0.7066593647003174
epoch: 33 training_loss 0.7205021452903747 test_loss: 0.7255598545074463
epoch: 34 training_loss 0.7051161515712738 test_loss: 0.6957605361938477
epoch: 35 training_loss 0.7061212050914765 test_loss: 0.6918174743652343
epoch: 36 training_loss 0.6981106668710708 test_loss: 0.7076195240020752
epoch: 37 training_loss 0.695842964053154 test_loss: 0.6985836982727051
epoch: 38 training_loss 0.6904387247562408 test_loss: 0.6782878398895263
epoch: 39 training_loss 0.6801981514692307 test_loss: 0.7347771167755127
epoch: 40 training_loss 0.6876144075393676 test_loss: 0.6546133518218994
epoch: 41 training_loss 0.6692273390293121 test_loss: 0.6687644481658935
epoch: 42 training_loss 0.6762065917253495 test_loss: 0.70066819190979
epoch: 43 training_loss 0.6697008872032165 test_loss: 0.6692192554473877
epoch: 44 training_loss 0.6572990506887436 test_loss: 0.6588482856750488
epoch: 45 training_loss 0.6630520302057267 test_loss: 0.7037768363952637
epoch: 46 training_loss 0.6534453445672989 test_loss: 0.6427845478057861
epoch: 47 training_loss 0.6501243668794632 test_loss: 0.6561745166778564
epoch: 48 training_loss 0.6490736669301986 test_loss: 0.6643024921417237
epoch: 49 training_loss 0.6363636094331742 test_loss: 0.6753132820129395
epoch: 50 training_loss 0.6446835535764694 test_loss: 0.6535786628723145
epoch: 51 training_loss 0.6439303749799729 test_loss: 0.6010888576507568
epoch: 52 training_loss 0.6346648490428924 test_loss: 0.6224157333374023
epoch: 53 training_loss 0.6259901416301727 test_loss: 0.6220377922058106
epoch: 54 training_loss 0.6214170384407044 test_loss: 0.613941764831543
epoch: 55 training_loss 0.6231830006837845 test_loss: 0.5787791728973388
epoch: 56 training_loss 0.615513089299202 test_loss: 0.6194479465484619
epoch: 57 training_loss 0.6167352944612503 test_loss: 0.615748405456543
epoch: 58 training_loss 0.6150797522068023 test_loss: 0.5902803421020508
epoch: 59 training_loss 0.6140857577323914 test_loss: 0.5781805515289307
epoch: 60 training_loss 0.6070264410972596 test_loss: 0.5950254917144775
epoch: 61 training_loss 0.6149683558940887 test_loss: 0.5856457710266113
epoch: 62 training_loss 0.61394327044487 test_loss: 0.6052392959594727
epoch: 63 training_loss 0.6082587385177612 test_loss: 0.6388521194458008
epoch: 64 training_loss 0.5980937796831131 test_loss: 0.6070468902587891
epoch: 65 training_loss 0.5949787989258766 test_loss: 0.5759365558624268
epoch: 66 training_loss 0.589805713891983 test_loss: 0.5672276973724365
epoch: 67 training_loss 0.5779407358169556 test_loss: 0.5557517528533935
epoch: 68 training_loss 0.5751607209444046 test_loss: 0.560407018661499
epoch: 69 training_loss 0.5781128132343292 test_loss: 0.5830870151519776
epoch: 70 training_loss 0.5972786206007004 test_loss: 0.5717030048370362
epoch: 71 training_loss 0.575442379117012 test_loss: 0.5642329216003418
epoch: 72 training_loss 0.5831913167238235 test_loss: 0.5955729007720947
epoch: 73 training_loss 0.5682572790980339 test_loss: 0.5779827117919922
epoch: 74 training_loss 0.5767177987098694 test_loss: 0.5959968090057373
epoch: 75 training_loss 0.571414897441864 test_loss: 0.5637402057647705
epoch: 76 training_loss 0.5668543481826782 test_loss: 0.5673046588897706
epoch: 77 training_loss 0.5709030836820602 test_loss: 0.5958656311035156
epoch: 78 training_loss 0.5637714886665344 test_loss: 0.5670408248901367
epoch: 79 training_loss 0.564069305062294 test_loss: 0.5434555530548095
epoch: 80 training_loss 0.5702681037783622 test_loss: 0.5731889247894287
epoch: 81 training_loss 0.5445826724171638 test_loss: 0.5505956649780274
epoch: 82 training_loss 0.5542979648709297 test_loss: 0.5575037956237793
epoch: 83 training_loss 0.5577378764748573 test_loss: 0.5432661056518555
epoch: 84 training_loss 0.549955008327961 test_loss: 0.5379937171936036
epoch: 85 training_loss 0.5527153146266938 test_loss: 0.550638484954834
epoch: 86 training_loss 0.5542615422606468 test_loss: 0.5802157878875732
epoch: 87 training_loss 0.55153699696064 test_loss: 0.5344454765319824
epoch: 88 training_loss 0.5461100381612778 test_loss: 0.5671401977539062
epoch: 89 training_loss 0.5385605850815773 test_loss: 0.5481832504272461
epoch: 90 training_loss 0.5431119567155838 test_loss: 0.5495073318481445
epoch: 91 training_loss 0.5406666216254234 test_loss: 0.5424824237823487
epoch: 92 training_loss 0.5444800528883934 test_loss: 0.5233121871948242
epoch: 93 training_loss 0.5324182203412056 test_loss: 0.540489673614502
epoch: 94 training_loss 0.5354124736785889 test_loss: 0.5404890537261963
epoch: 95 training_loss 0.533150104880333 test_loss: 0.5189015865325928
epoch: 96 training_loss 0.5353885352611542 test_loss: 0.5140590190887451
epoch: 97 training_loss 0.5369631999731064 test_loss: 0.5465100765228271
epoch: 98 training_loss 0.5319240275025368 test_loss: 0.5294366836547851
epoch: 99 training_loss 0.5411142697930336 test_loss: 0.5515194892883301
epoch: 100 training_loss 0.5310241821408271 test_loss: 0.5499974727630615
epoch: 101 training_loss 0.5325901082158089 test_loss: 0.5251245498657227
epoch: 102 training_loss 0.5210789489746094 test_loss: 0.5295292854309082
epoch: 103 training_loss 0.5304132583737373 test_loss: 0.5250374794006347
epoch: 104 training_loss 0.526724471449852 test_loss: 0.5313878059387207
epoch: 105 training_loss 0.5299584823846817 test_loss: 0.5416345119476318
epoch: 106 training_loss 0.5301118701696396 test_loss: 0.534334373474121
epoch: 107 training_loss 0.5278852397203445 test_loss: 0.5100021839141846
epoch: 108 training_loss 0.5233414378762246 test_loss: 0.516188383102417
epoch: 109 training_loss 0.5270819336175918 test_loss: 0.5372737884521485
epoch: 110 training_loss 0.5190725085139275 test_loss: 0.5258023738861084
epoch: 111 training_loss 0.5220476543903351 test_loss: 0.5253344058990479
epoch: 112 training_loss 0.5172039929032326 test_loss: 0.5233885765075683
epoch: 113 training_loss 0.5198238509893417 test_loss: 0.49860501289367676
epoch: 114 training_loss 0.5144497662782669 test_loss: 0.4984574317932129
epoch: 115 training_loss 0.5152143675088883 test_loss: 0.5173518180847168
epoch: 116 training_loss 0.5106401497125626 test_loss: 0.5242916584014893
epoch: 117 training_loss 0.5023895314335823 test_loss: 0.5113413333892822
epoch: 118 training_loss 0.5101178205013275 test_loss: 0.5289405345916748
epoch: 119 training_loss 0.5179531294107437 test_loss: 0.4999980926513672
epoch: 120 training_loss 0.5068582808971405 test_loss: 0.49753570556640625
epoch: 121 training_loss 0.5065464922785758 test_loss: 0.5127533912658692
epoch: 122 training_loss 0.5064570418000222 test_loss: 0.5192156791687011
epoch: 123 training_loss 0.5195741546154022 test_loss: 0.5041380405426026
epoch: 124 training_loss 0.5074682101607323 test_loss: 0.5060535430908203
epoch: 125 training_loss 0.5043600115180016 test_loss: 0.4914689540863037
epoch: 126 training_loss 0.5089137175679207 test_loss: 0.48230996131896975
epoch: 127 training_loss 0.5050032502412796 test_loss: 0.5032814502716064
epoch: 128 training_loss 0.5104604542255402 test_loss: 0.49277939796447756
epoch: 129 training_loss 0.5065180417895317 test_loss: 0.5507462024688721
epoch: 130 training_loss 0.5006194826960564 test_loss: 0.5079213619232178
epoch: 131 training_loss 0.5006855475902557 test_loss: 0.4819315433502197
epoch: 132 training_loss 0.49671255141496656 test_loss: 0.5067702293395996
epoch: 133 training_loss 0.4994932895898819 test_loss: 0.5197307586669921
epoch: 134 training_loss 0.4988516703248024 test_loss: 0.510683536529541
epoch: 135 training_loss 0.4930928719043732 test_loss: 0.49955005645751954
epoch: 136 training_loss 0.4931410321593285 test_loss: 0.4962461471557617
epoch: 137 training_loss 0.4901555335521698 test_loss: 0.4896529674530029
epoch: 138 training_loss 0.4986761510372162 test_loss: 0.5370848655700684
epoch: 139 training_loss 0.48910187035799024 test_loss: 0.5010009288787842
epoch: 140 training_loss 0.4946884608268738 test_loss: 0.48110241889953614
epoch: 141 training_loss 0.491334208548069 test_loss: 0.5220232963562011
epoch: 142 training_loss 0.500028478205204 test_loss: 0.4770850658416748
epoch: 143 training_loss 0.4968551394343376 test_loss: 0.4867821216583252
epoch: 144 training_loss 0.4958877599239349 test_loss: 0.4846010208129883
epoch: 145 training_loss 0.4831987309455872 test_loss: 0.5011672019958496
epoch: 146 training_loss 0.4829492199420929 test_loss: 0.4955552577972412
epoch: 147 training_loss 0.495074580013752 test_loss: 0.48807501792907715
epoch: 148 training_loss 0.4909068602323532 test_loss: 0.48161730766296384
epoch: 149 training_loss 0.4862047025561333 test_loss: 0.4917566776275635
2963.668086374656
episode: 0 training return: tensor(-356.3149, device='cuda:0')
episode: 1 training return: tensor(-331.8992, device='cuda:0')
episode: 2 training return: tensor(302.5915, device='cuda:0')
episode: 3 training return: tensor(-125.3082, device='cuda:0')
epoch: 1 test_true_pfm: 1575.2736014407922 sim_pfm: -161.4640758744596
episode: 4 training return: tensor(-46.1802, device='cuda:0')
episode: 5 training return: tensor(309.2847, device='cuda:0')
episode: 6 training return: tensor(306.5784, device='cuda:0')
episode: 7 training return: tensor(-113.8327, device='cuda:0')
epoch: 2 test_true_pfm: 3290.334566782452 sim_pfm: 309.5027530261238
episode: 8 training return: tensor(-332.9071, device='cuda:0')
episode: 9 training return: tensor(251.3350, device='cuda:0')
episode: 10 training return: tensor(-320.0717, device='cuda:0')
episode: 11 training return: tensor(44.8680, device='cuda:0')
epoch: 3 test_true_pfm: 2518.5803717067133 sim_pfm: 124.7167638958587
episode: 12 training return: tensor(-132.9742, device='cuda:0')
episode: 13 training return: tensor(-392.8490, device='cuda:0')
episode: 14 training return: tensor(-294.9734, device='cuda:0')
episode: 15 training return: tensor(-394.3520, device='cuda:0')
epoch: 4 test_true_pfm: 1924.8897118750374 sim_pfm: -289.39851555763744
episode: 16 training return: tensor(-310.6038, device='cuda:0')
episode: 17 training return: tensor(-329.4901, device='cuda:0')
episode: 18 training return: tensor(-396.9359, device='cuda:0')
episode: 19 training return: tensor(291.4544, device='cuda:0')
epoch: 5 test_true_pfm: 2081.177571226628 sim_pfm: -233.8637739137436
episode: 20 training return: tensor(-356.4865, device='cuda:0')
episode: 21 training return: tensor(-397.6974, device='cuda:0')
episode: 22 training return: tensor(-389.4804, device='cuda:0')
episode: 23 training return: tensor(301.7514, device='cuda:0')
epoch: 6 test_true_pfm: 1411.8386555192149 sim_pfm: -339.40010832467425
episode: 24 training return: tensor(-315.7495, device='cuda:0')
episode: 25 training return: tensor(-352.7089, device='cuda:0')
episode: 26 training return: tensor(-405.2593, device='cuda:0')
episode: 27 training return: tensor(329.1611, device='cuda:0')
epoch: 7 test_true_pfm: 1450.6823400021947 sim_pfm: -274.08826422551647
episode: 28 training return: tensor(-199.2596, device='cuda:0')
episode: 29 training return: tensor(-358.6365, device='cuda:0')
episode: 30 training return: tensor(-396.4472, device='cuda:0')
episode: 31 training return: tensor(-391.9116, device='cuda:0')
epoch: 8 test_true_pfm: 1717.3798634699026 sim_pfm: -29.391721334812853
episode: 32 training return: tensor(-225.0806, device='cuda:0')
episode: 33 training return: tensor(286.6613, device='cuda:0')
episode: 34 training return: tensor(-310.8469, device='cuda:0')
episode: 35 training return: tensor(-105.1184, device='cuda:0')
epoch: 9 test_true_pfm: 2465.462466671277 sim_pfm: 177.11501067356826
episode: 36 training return: tensor(296.6559, device='cuda:0')
episode: 37 training return: tensor(-404.4167, device='cuda:0')
episode: 38 training return: tensor(-387.4532, device='cuda:0')
episode: 39 training return: tensor(-328.9996, device='cuda:0')
epoch: 10 test_true_pfm: 2681.4842978066736 sim_pfm: 8.58095255723068
episode: 40 training return: tensor(-240.5905, device='cuda:0')
episode: 41 training return: tensor(-363.4439, device='cuda:0')
episode: 42 training return: tensor(-331.3539, device='cuda:0')
episode: 43 training return: tensor(285.7428, device='cuda:0')
epoch: 11 test_true_pfm: 3241.5864487733675 sim_pfm: 191.82431817636825
episode: 44 training return: tensor(-385.7933, device='cuda:0')
episode: 45 training return: tensor(-294.9964, device='cuda:0')
episode: 46 training return: tensor(-324.3969, device='cuda:0')
episode: 47 training return: tensor(-292.5182, device='cuda:0')
epoch: 12 test_true_pfm: 2519.2989919907945 sim_pfm: 170.1033871098965
episode: 48 training return: tensor(-362.9088, device='cuda:0')
episode: 49 training return: tensor(-380.9518, device='cuda:0')
episode: 50 training return: tensor(-367.5576, device='cuda:0')
episode: 51 training return: tensor(-306.2493, device='cuda:0')
epoch: 13 test_true_pfm: 2175.996349313434 sim_pfm: 201.16740067648547
episode: 52 training return: tensor(-382.9312, device='cuda:0')
episode: 53 training return: tensor(-251.9036, device='cuda:0')
episode: 54 training return: tensor(-395.8301, device='cuda:0')
episode: 55 training return: tensor(298.4251, device='cuda:0')
epoch: 14 test_true_pfm: 2835.9333872968386 sim_pfm: 186.58905761238807
episode: 56 training return: tensor(-307.4973, device='cuda:0')
episode: 57 training return: tensor(-314.5291, device='cuda:0')
episode: 58 training return: tensor(-340.2531, device='cuda:0')
episode: 59 training return: tensor(350.7646, device='cuda:0')
epoch: 15 test_true_pfm: 3026.538040186751 sim_pfm: 173.5508556231313
episode: 60 training return: tensor(-218.9812, device='cuda:0')
episode: 61 training return: tensor(-307.5190, device='cuda:0')
episode: 62 training return: tensor(-359.6286, device='cuda:0')
episode: 63 training return: tensor(336.8596, device='cuda:0')
epoch: 16 test_true_pfm: 2974.0313569701993 sim_pfm: 204.3473524750831
episode: 64 training return: tensor(-329.4404, device='cuda:0')
episode: 65 training return: tensor(-398.0535, device='cuda:0')
episode: 66 training return: tensor(-106.7948, device='cuda:0')
episode: 67 training return: tensor(344.6107, device='cuda:0')
epoch: 17 test_true_pfm: 3208.7915780717794 sim_pfm: 156.23593012235747
episode: 68 training return: tensor(-237.7483, device='cuda:0')
episode: 69 training return: tensor(-322.3064, device='cuda:0')
episode: 70 training return: tensor(275.5104, device='cuda:0')
episode: 71 training return: tensor(-132.4913, device='cuda:0')
epoch: 18 test_true_pfm: 2796.0350709101826 sim_pfm: 155.18555816213484
episode: 72 training return: tensor(-44.9599, device='cuda:0')
episode: 73 training return: tensor(-287.9109, device='cuda:0')
episode: 74 training return: tensor(-391.7888, device='cuda:0')
episode: 75 training return: tensor(-127.1353, device='cuda:0')
epoch: 19 test_true_pfm: 2944.853229432613 sim_pfm: 190.61310369624212
episode: 76 training return: tensor(22.0229, device='cuda:0')
episode: 77 training return: tensor(363.7460, device='cuda:0')
episode: 78 training return: tensor(11.5025, device='cuda:0')
episode: 79 training return: tensor(141.5376, device='cuda:0')
epoch: 20 test_true_pfm: 2981.608881594737 sim_pfm: 266.62955180349917
episode: 80 training return: tensor(-249.4639, device='cuda:0')
episode: 81 training return: tensor(297.1323, device='cuda:0')
episode: 82 training return: tensor(-336.2927, device='cuda:0')
episode: 83 training return: tensor(-388.9249, device='cuda:0')
epoch: 21 test_true_pfm: 2841.262877640025 sim_pfm: 69.81690255038363
episode: 84 training return: tensor(-112.1720, device='cuda:0')
episode: 85 training return: tensor(322.5073, device='cuda:0')
episode: 86 training return: tensor(291.4370, device='cuda:0')
episode: 87 training return: tensor(-379.6719, device='cuda:0')
epoch: 22 test_true_pfm: 3064.1598285968653 sim_pfm: -114.47909042518586
episode: 88 training return: tensor(-290.7336, device='cuda:0')
episode: 89 training return: tensor(-322.5706, device='cuda:0')
episode: 90 training return: tensor(68.6334, device='cuda:0')
episode: 91 training return: tensor(-310.6402, device='cuda:0')
epoch: 23 test_true_pfm: 2850.003226740731 sim_pfm: 167.82558007722642
episode: 92 training return: tensor(335.8227, device='cuda:0')
episode: 93 training return: tensor(-215.2266, device='cuda:0')
episode: 94 training return: tensor(-293.7727, device='cuda:0')
episode: 95 training return: tensor(-294.8874, device='cuda:0')
epoch: 24 test_true_pfm: 2766.5475334015514 sim_pfm: 290.5291634432894
episode: 96 training return: tensor(-385.5916, device='cuda:0')
episode: 97 training return: tensor(-330.5269, device='cuda:0')
episode: 98 training return: tensor(223.7091, device='cuda:0')
episode: 99 training return: tensor(-324.8970, device='cuda:0')
epoch: 25 test_true_pfm: 3009.691287763662 sim_pfm: 240.08252564022163
episode: 100 training return: tensor(295.5670, device='cuda:0')
episode: 101 training return: tensor(-342.6270, device='cuda:0')
episode: 102 training return: tensor(301.8647, device='cuda:0')
episode: 103 training return: tensor(305.7509, device='cuda:0')
epoch: 26 test_true_pfm: 3228.836457633361 sim_pfm: 272.3184110756556
episode: 104 training return: tensor(-347.8285, device='cuda:0')
episode: 105 training return: tensor(-294.0993, device='cuda:0')
episode: 106 training return: tensor(-339.9605, device='cuda:0')
episode: 107 training return: tensor(-82.3192, device='cuda:0')
epoch: 27 test_true_pfm: 3128.0683087532543 sim_pfm: 88.47232998449665
episode: 108 training return: tensor(281.4821, device='cuda:0')
episode: 109 training return: tensor(173.6527, device='cuda:0')
episode: 110 training return: tensor(363.8241, device='cuda:0')
episode: 111 training return: tensor(-334.9357, device='cuda:0')
epoch: 28 test_true_pfm: 3035.9187063269005 sim_pfm: 158.31836788272872
episode: 112 training return: tensor(-204.9010, device='cuda:0')
episode: 113 training return: tensor(-321.5724, device='cuda:0')
episode: 114 training return: tensor(274.0476, device='cuda:0')
episode: 115 training return: tensor(-318.9179, device='cuda:0')
epoch: 29 test_true_pfm: 2678.204512450818 sim_pfm: -8.782674435254497
episode: 116 training return: tensor(-387.4775, device='cuda:0')
episode: 117 training return: tensor(-396.3743, device='cuda:0')
episode: 118 training return: tensor(90.7627, device='cuda:0')
episode: 119 training return: tensor(-331.2419, device='cuda:0')
epoch: 30 test_true_pfm: 3006.17574007214 sim_pfm: 306.7700723447294
episode: 120 training return: tensor(-284.8870, device='cuda:0')
episode: 121 training return: tensor(-111.5986, device='cuda:0')
episode: 122 training return: tensor(-288.3494, device='cuda:0')
episode: 123 training return: tensor(-95.3475, device='cuda:0')
epoch: 31 test_true_pfm: 2614.4192337709997 sim_pfm: -66.75495296441174
episode: 124 training return: tensor(326.3483, device='cuda:0')
episode: 125 training return: tensor(-356.4834, device='cuda:0')
episode: 126 training return: tensor(-312.8238, device='cuda:0')
episode: 127 training return: tensor(14.1514, device='cuda:0')
epoch: 32 test_true_pfm: 3244.825391275888 sim_pfm: 155.72406531015682
episode: 128 training return: tensor(-98.1098, device='cuda:0')
episode: 129 training return: tensor(283.6325, device='cuda:0')
episode: 130 training return: tensor(-318.6436, device='cuda:0')
episode: 131 training return: tensor(64.6724, device='cuda:0')
epoch: 33 test_true_pfm: 2363.7938500594546 sim_pfm: 60.879659155015055
episode: 132 training return: tensor(267.0811, device='cuda:0')
episode: 133 training return: tensor(-390.8777, device='cuda:0')
episode: 134 training return: tensor(-47.5795, device='cuda:0')
episode: 135 training return: tensor(141.7597, device='cuda:0')
epoch: 34 test_true_pfm: 2910.4240154048034 sim_pfm: 200.93134281745492
episode: 136 training return: tensor(-343.6687, device='cuda:0')
episode: 137 training return: tensor(-247.8428, device='cuda:0')
episode: 138 training return: tensor(-269.4410, device='cuda:0')
episode: 139 training return: tensor(-389.9142, device='cuda:0')
epoch: 35 test_true_pfm: 2048.9470954691183 sim_pfm: 64.89522040590721
episode: 140 training return: tensor(316.9782, device='cuda:0')
episode: 141 training return: tensor(-386.5515, device='cuda:0')
episode: 142 training return: tensor(-179.1009, device='cuda:0')
episode: 143 training return: tensor(-387.9270, device='cuda:0')
epoch: 36 test_true_pfm: 2694.1310034361245 sim_pfm: -60.44732793564132
episode: 144 training return: tensor(-394.6893, device='cuda:0')
episode: 145 training return: tensor(-393.1370, device='cuda:0')
episode: 146 training return: tensor(-384.3508, device='cuda:0')
episode: 147 training return: tensor(286.9300, device='cuda:0')
epoch: 37 test_true_pfm: 3068.7069135209535 sim_pfm: 39.24927216484988
episode: 148 training return: tensor(93.9483, device='cuda:0')
episode: 149 training return: tensor(306.4748, device='cuda:0')
episode: 150 training return: tensor(-289.4876, device='cuda:0')
episode: 151 training return: tensor(-9.3340, device='cuda:0')
epoch: 38 test_true_pfm: 2789.690652627855 sim_pfm: 28.16116693247265
episode: 152 training return: tensor(-345.6623, device='cuda:0')
episode: 153 training return: tensor(86.5533, device='cuda:0')
episode: 154 training return: tensor(-290.3452, device='cuda:0')
episode: 155 training return: tensor(158.6913, device='cuda:0')
epoch: 39 test_true_pfm: 2752.9189828620833 sim_pfm: 133.01595809298064
episode: 156 training return: tensor(300.5262, device='cuda:0')
episode: 157 training return: tensor(-291.9861, device='cuda:0')
episode: 158 training return: tensor(-299.3340, device='cuda:0')
episode: 159 training return: tensor(-353.6071, device='cuda:0')
epoch: 40 test_true_pfm: 2842.45639351834 sim_pfm: -30.754354948391363
episode: 160 training return: tensor(355.6585, device='cuda:0')
episode: 161 training return: tensor(-94.9112, device='cuda:0')
episode: 162 training return: tensor(290.3682, device='cuda:0')
episode: 163 training return: tensor(-11.0839, device='cuda:0')
epoch: 41 test_true_pfm: 3274.3410799997328 sim_pfm: 76.0990018445688
episode: 164 training return: tensor(-294.9477, device='cuda:0')
episode: 165 training return: tensor(287.6479, device='cuda:0')
episode: 166 training return: tensor(-206.6432, device='cuda:0')
episode: 167 training return: tensor(-233.1454, device='cuda:0')
epoch: 42 test_true_pfm: 2164.693951331732 sim_pfm: 171.77751302342708
episode: 168 training return: tensor(-0.2232, device='cuda:0')
episode: 169 training return: tensor(-108.1767, device='cuda:0')
episode: 170 training return: tensor(281.7815, device='cuda:0')
episode: 171 training return: tensor(88.1276, device='cuda:0')
epoch: 43 test_true_pfm: 2653.2420934229335 sim_pfm: 140.5317884881612
episode: 172 training return: tensor(-104.0341, device='cuda:0')
episode: 173 training return: tensor(-295.0038, device='cuda:0')
episode: 174 training return: tensor(-394.1462, device='cuda:0')
episode: 175 training return: tensor(326.7802, device='cuda:0')
epoch: 44 test_true_pfm: 2713.913814540663 sim_pfm: 74.49601825675927
episode: 176 training return: tensor(-340.2156, device='cuda:0')
episode: 177 training return: tensor(293.5940, device='cuda:0')
episode: 178 training return: tensor(274.1046, device='cuda:0')
episode: 179 training return: tensor(267.6192, device='cuda:0')
epoch: 45 test_true_pfm: 2399.7752753700647 sim_pfm: 172.88317961400995
episode: 180 training return: tensor(-7.3671, device='cuda:0')
episode: 181 training return: tensor(-316.2728, device='cuda:0')
episode: 182 training return: tensor(-59.1600, device='cuda:0')
episode: 183 training return: tensor(336.2126, device='cuda:0')
epoch: 46 test_true_pfm: 2414.575669583202 sim_pfm: 145.25074280487993
episode: 184 training return: tensor(84.3517, device='cuda:0')
episode: 185 training return: tensor(-84.6826, device='cuda:0')
episode: 186 training return: tensor(-81.4900, device='cuda:0')
episode: 187 training return: tensor(277.4716, device='cuda:0')
epoch: 47 test_true_pfm: 3298.2662040754185 sim_pfm: 173.33503421985856
episode: 188 training return: tensor(-319.8947, device='cuda:0')
episode: 189 training return: tensor(-292.0678, device='cuda:0')
episode: 190 training return: tensor(254.6848, device='cuda:0')
episode: 191 training return: tensor(-337.1845, device='cuda:0')
epoch: 48 test_true_pfm: 2849.1878983178826 sim_pfm: 177.7833461969761
episode: 192 training return: tensor(-393.0943, device='cuda:0')
episode: 193 training return: tensor(-288.8150, device='cuda:0')
episode: 194 training return: tensor(275.3160, device='cuda:0')
episode: 195 training return: tensor(259.0707, device='cuda:0')
epoch: 49 test_true_pfm: 2840.2525276438523 sim_pfm: 198.1741037366155
episode: 196 training return: tensor(-393.2383, device='cuda:0')
episode: 197 training return: tensor(-337.8138, device='cuda:0')
episode: 198 training return: tensor(-321.6811, device='cuda:0')
episode: 199 training return: tensor(165.9896, device='cuda:0')
epoch: 50 test_true_pfm: 2853.0322845067853 sim_pfm: 0.8463872047917297
episode: 200 training return: tensor(-50.3871, device='cuda:0')
episode: 201 training return: tensor(-344.4590, device='cuda:0')
episode: 202 training return: tensor(-362.9121, device='cuda:0')
episode: 203 training return: tensor(-140.1577, device='cuda:0')
epoch: 51 test_true_pfm: 2884.079761941683 sim_pfm: 331.0309557723037
episode: 204 training return: tensor(-387.9495, device='cuda:0')
episode: 205 training return: tensor(-208.0948, device='cuda:0')
episode: 206 training return: tensor(271.5931, device='cuda:0')
episode: 207 training return: tensor(-309.1913, device='cuda:0')
epoch: 52 test_true_pfm: 2870.9504223704084 sim_pfm: 17.95229930599453
episode: 208 training return: tensor(284.0941, device='cuda:0')
episode: 209 training return: tensor(-318.1589, device='cuda:0')
episode: 210 training return: tensor(-295.0269, device='cuda:0')
episode: 211 training return: tensor(-76.7841, device='cuda:0')
epoch: 53 test_true_pfm: 2198.6305783852545 sim_pfm: 119.24811085336842
episode: 212 training return: tensor(-384.0357, device='cuda:0')
episode: 213 training return: tensor(-307.1693, device='cuda:0')
episode: 214 training return: tensor(-289.4489, device='cuda:0')
episode: 215 training return: tensor(-201.6168, device='cuda:0')
epoch: 54 test_true_pfm: 2634.3813460960687 sim_pfm: 19.79614917456638
episode: 216 training return: tensor(-300.3621, device='cuda:0')
episode: 217 training return: tensor(285.5299, device='cuda:0')
episode: 218 training return: tensor(309.8813, device='cuda:0')
episode: 219 training return: tensor(-126.9806, device='cuda:0')
epoch: 55 test_true_pfm: 2916.715648244199 sim_pfm: 20.305294347548625
episode: 220 training return: tensor(-278.0497, device='cuda:0')
episode: 221 training return: tensor(279.5962, device='cuda:0')
episode: 222 training return: tensor(-291.3753, device='cuda:0')
episode: 223 training return: tensor(-212.8774, device='cuda:0')
epoch: 56 test_true_pfm: 3310.5814237282943 sim_pfm: 92.90054888273396
episode: 224 training return: tensor(55.8846, device='cuda:0')
episode: 225 training return: tensor(-118.1225, device='cuda:0')
episode: 226 training return: tensor(-395.9547, device='cuda:0')
episode: 227 training return: tensor(-319.8253, device='cuda:0')
epoch: 57 test_true_pfm: 2922.619093737536 sim_pfm: 290.88262695164303
episode: 228 training return: tensor(-334.6979, device='cuda:0')
episode: 229 training return: tensor(-342.9551, device='cuda:0')
episode: 230 training return: tensor(294.8628, device='cuda:0')
episode: 231 training return: tensor(293.3591, device='cuda:0')
epoch: 58 test_true_pfm: 2501.0418016447934 sim_pfm: 39.651074610378906
episode: 232 training return: tensor(-214.6298, device='cuda:0')
episode: 233 training return: tensor(-343.1612, device='cuda:0')
episode: 234 training return: tensor(295.4826, device='cuda:0')
episode: 235 training return: tensor(-292.1729, device='cuda:0')
epoch: 59 test_true_pfm: 3258.964176942474 sim_pfm: 195.48878966093375
episode: 236 training return: tensor(-260.1536, device='cuda:0')
episode: 237 training return: tensor(309.0591, device='cuda:0')
episode: 238 training return: tensor(-147.9199, device='cuda:0')
episode: 239 training return: tensor(-144.9295, device='cuda:0')
epoch: 60 test_true_pfm: 3263.7223769708994 sim_pfm: -8.235334144895509
episode: 240 training return: tensor(307.5719, device='cuda:0')
episode: 241 training return: tensor(268.4371, device='cuda:0')
episode: 242 training return: tensor(-381.7243, device='cuda:0')
episode: 243 training return: tensor(181.9044, device='cuda:0')
epoch: 61 test_true_pfm: 2722.230609053477 sim_pfm: 166.36322343322294
episode: 244 training return: tensor(45.8771, device='cuda:0')
episode: 245 training return: tensor(309.0299, device='cuda:0')
episode: 246 training return: tensor(-89.7082, device='cuda:0')
episode: 247 training return: tensor(-53.6443, device='cuda:0')
epoch: 62 test_true_pfm: 2451.15874724728 sim_pfm: 109.89150938768096
episode: 248 training return: tensor(-136.4878, device='cuda:0')
episode: 249 training return: tensor(-328.8988, device='cuda:0')
episode: 250 training return: tensor(271.8117, device='cuda:0')
episode: 251 training return: tensor(294.3770, device='cuda:0')
epoch: 63 test_true_pfm: 2762.3054339249734 sim_pfm: 290.75198347423185
episode: 252 training return: tensor(-390.2527, device='cuda:0')
episode: 253 training return: tensor(-392.2993, device='cuda:0')
episode: 254 training return: tensor(68.7534, device='cuda:0')
episode: 255 training return: tensor(27.0613, device='cuda:0')
epoch: 64 test_true_pfm: 2721.4557833285057 sim_pfm: 297.06450855892035
episode: 256 training return: tensor(-268.5454, device='cuda:0')
episode: 257 training return: tensor(-336.2715, device='cuda:0')
episode: 258 training return: tensor(-391.3141, device='cuda:0')
episode: 259 training return: tensor(-212.2894, device='cuda:0')
epoch: 65 test_true_pfm: 2816.5375307554973 sim_pfm: 275.56884450195747
episode: 260 training return: tensor(-320.7991, device='cuda:0')
episode: 261 training return: tensor(293.8117, device='cuda:0')
episode: 262 training return: tensor(-3.6999, device='cuda:0')
episode: 263 training return: tensor(-378.1026, device='cuda:0')
epoch: 66 test_true_pfm: 2878.016475158082 sim_pfm: 57.25492714110684
episode: 264 training return: tensor(-212.9017, device='cuda:0')
episode: 265 training return: tensor(305.4553, device='cuda:0')
episode: 266 training return: tensor(-344.8373, device='cuda:0')
episode: 267 training return: tensor(336.6190, device='cuda:0')
epoch: 67 test_true_pfm: 2688.375444334437 sim_pfm: 41.59789831391148
episode: 268 training return: tensor(-290.1644, device='cuda:0')
episode: 269 training return: tensor(321.5990, device='cuda:0')
episode: 270 training return: tensor(-294.6571, device='cuda:0')
episode: 271 training return: tensor(-232.7934, device='cuda:0')
epoch: 68 test_true_pfm: 2905.5732723446704 sim_pfm: 30.939415302564157
episode: 272 training return: tensor(288.7251, device='cuda:0')
episode: 273 training return: tensor(73.0093, device='cuda:0')
episode: 274 training return: tensor(339.0364, device='cuda:0')
episode: 275 training return: tensor(95.3479, device='cuda:0')
epoch: 69 test_true_pfm: 2474.2963577938376 sim_pfm: 72.08280548562955
episode: 276 training return: tensor(-250.8176, device='cuda:0')
episode: 277 training return: tensor(-391.6100, device='cuda:0')
episode: 278 training return: tensor(-292.8994, device='cuda:0')
episode: 279 training return: tensor(-334.3503, device='cuda:0')
epoch: 70 test_true_pfm: 2897.3931815782776 sim_pfm: 54.86977597583124
episode: 280 training return: tensor(71.9136, device='cuda:0')
episode: 281 training return: tensor(-326.1685, device='cuda:0')
episode: 282 training return: tensor(-79.0686, device='cuda:0')
episode: 283 training return: tensor(-395.3928, device='cuda:0')
epoch: 71 test_true_pfm: 2638.000725279862 sim_pfm: 32.36447434981043
episode: 284 training return: tensor(-307.0253, device='cuda:0')
episode: 285 training return: tensor(-379.5339, device='cuda:0')
episode: 286 training return: tensor(96.8135, device='cuda:0')
episode: 287 training return: tensor(281.6036, device='cuda:0')
epoch: 72 test_true_pfm: 2748.271182987976 sim_pfm: 120.81115151918493
episode: 288 training return: tensor(267.0231, device='cuda:0')
episode: 289 training return: tensor(-319.8533, device='cuda:0')
episode: 290 training return: tensor(-245.9248, device='cuda:0')
episode: 291 training return: tensor(274.4267, device='cuda:0')
epoch: 73 test_true_pfm: 2907.9848732115265 sim_pfm: 245.47508575974885
episode: 292 training return: tensor(-239.2223, device='cuda:0')
episode: 293 training return: tensor(-286.8263, device='cuda:0')
episode: 294 training return: tensor(270.9068, device='cuda:0')
episode: 295 training return: tensor(285.2820, device='cuda:0')
epoch: 74 test_true_pfm: 2692.879928851637 sim_pfm: 230.60279883425878
episode: 296 training return: tensor(291.7610, device='cuda:0')
episode: 297 training return: tensor(-389.8733, device='cuda:0')
episode: 298 training return: tensor(-399.2371, device='cuda:0')
episode: 299 training return: tensor(-18.4868, device='cuda:0')
epoch: 75 test_true_pfm: 2466.8159459866215 sim_pfm: 152.3655998087197
episode: 300 training return: tensor(-383.1552, device='cuda:0')
episode: 301 training return: tensor(-184.0726, device='cuda:0')
episode: 302 training return: tensor(264.1882, device='cuda:0')
episode: 303 training return: tensor(-302.2819, device='cuda:0')
epoch: 76 test_true_pfm: 2278.6573305126094 sim_pfm: 220.95988017958976
episode: 304 training return: tensor(125.7871, device='cuda:0')
episode: 305 training return: tensor(-300.2570, device='cuda:0')
episode: 306 training return: tensor(-361.8905, device='cuda:0')
episode: 307 training return: tensor(-394.3278, device='cuda:0')
epoch: 77 test_true_pfm: 2419.2105669118223 sim_pfm: -24.751421599105623
episode: 308 training return: tensor(-205.4941, device='cuda:0')
episode: 309 training return: tensor(-380.6223, device='cuda:0')
episode: 310 training return: tensor(-212.1021, device='cuda:0')
episode: 311 training return: tensor(-310.4055, device='cuda:0')
epoch: 78 test_true_pfm: 2705.1001096313107 sim_pfm: 163.23516519173668
episode: 312 training return: tensor(-348.9030, device='cuda:0')
episode: 313 training return: tensor(-389.7085, device='cuda:0')
episode: 314 training return: tensor(303.8721, device='cuda:0')
episode: 315 training return: tensor(306.3582, device='cuda:0')
epoch: 79 test_true_pfm: 2490.093644470818 sim_pfm: 208.33855283727948
episode: 316 training return: tensor(-393.8039, device='cuda:0')
episode: 317 training return: tensor(-401.0931, device='cuda:0')
episode: 318 training return: tensor(269.1155, device='cuda:0')
episode: 319 training return: tensor(-378.3301, device='cuda:0')
epoch: 80 test_true_pfm: 2851.4696564854307 sim_pfm: 232.06704790513808
episode: 320 training return: tensor(-398.7498, device='cuda:0')
episode: 321 training return: tensor(-387.7121, device='cuda:0')
episode: 322 training return: tensor(-386.0511, device='cuda:0')
episode: 323 training return: tensor(195.5489, device='cuda:0')
epoch: 81 test_true_pfm: 2731.722842298233 sim_pfm: -136.12322072603274
episode: 324 training return: tensor(-295.1303, device='cuda:0')
episode: 325 training return: tensor(159.9088, device='cuda:0')
episode: 326 training return: tensor(-290.6677, device='cuda:0')
episode: 327 training return: tensor(-306.0008, device='cuda:0')
epoch: 82 test_true_pfm: 2569.793963658359 sim_pfm: -13.885791547072586
episode: 328 training return: tensor(-282.3304, device='cuda:0')
episode: 329 training return: tensor(-317.6534, device='cuda:0')
episode: 330 training return: tensor(-66.9093, device='cuda:0')
episode: 331 training return: tensor(-337.7777, device='cuda:0')
epoch: 83 test_true_pfm: 2821.88543411428 sim_pfm: 326.6222625378966
episode: 332 training return: tensor(288.4990, device='cuda:0')
episode: 333 training return: tensor(-319.0313, device='cuda:0')
episode: 334 training return: tensor(-28.0344, device='cuda:0')
episode: 335 training return: tensor(-296.0504, device='cuda:0')
epoch: 84 test_true_pfm: 3080.9227396776555 sim_pfm: 169.87386778290966
episode: 336 training return: tensor(-390.0681, device='cuda:0')
episode: 337 training return: tensor(-125.5053, device='cuda:0')
episode: 338 training return: tensor(281.8993, device='cuda:0')
episode: 339 training return: tensor(-74.9397, device='cuda:0')
epoch: 85 test_true_pfm: 2853.3894123764107 sim_pfm: 110.02661093043086
episode: 340 training return: tensor(-251.0823, device='cuda:0')
episode: 341 training return: tensor(59.8888, device='cuda:0')
episode: 342 training return: tensor(-26.1311, device='cuda:0')
episode: 343 training return: tensor(-373.5424, device='cuda:0')
epoch: 86 test_true_pfm: 2702.1297844346714 sim_pfm: 260.2986832277772
episode: 344 training return: tensor(304.1207, device='cuda:0')
episode: 345 training return: tensor(203.0134, device='cuda:0')
episode: 346 training return: tensor(-397.7609, device='cuda:0')
episode: 347 training return: tensor(27.0576, device='cuda:0')
epoch: 87 test_true_pfm: 2115.2048355846837 sim_pfm: 205.8922092037586
episode: 348 training return: tensor(91.0910, device='cuda:0')
episode: 349 training return: tensor(-297.3027, device='cuda:0')
episode: 350 training return: tensor(68.5453, device='cuda:0')
episode: 351 training return: tensor(285.3871, device='cuda:0')
epoch: 88 test_true_pfm: 2608.0535755904752 sim_pfm: 110.48534449219005
episode: 352 training return: tensor(323.4868, device='cuda:0')
episode: 353 training return: tensor(-388.2927, device='cuda:0')
episode: 354 training return: tensor(-342.1567, device='cuda:0')
episode: 355 training return: tensor(-255.8112, device='cuda:0')
epoch: 89 test_true_pfm: 2800.0981525262564 sim_pfm: 119.62952902558027
episode: 356 training return: tensor(-215.6630, device='cuda:0')
episode: 357 training return: tensor(-206.9115, device='cuda:0')
episode: 358 training return: tensor(277.0979, device='cuda:0')
episode: 359 training return: tensor(-287.5773, device='cuda:0')
epoch: 90 test_true_pfm: 3247.1410565257197 sim_pfm: 85.0094858048833
episode: 360 training return: tensor(-334.9693, device='cuda:0')
episode: 361 training return: tensor(-342.2689, device='cuda:0')
episode: 362 training return: tensor(83.1126, device='cuda:0')
episode: 363 training return: tensor(307.4798, device='cuda:0')
epoch: 91 test_true_pfm: 2341.032607240519 sim_pfm: 139.6149966987723
episode: 364 training return: tensor(-339.1996, device='cuda:0')
episode: 365 training return: tensor(-105.3907, device='cuda:0')
episode: 366 training return: tensor(1.4708, device='cuda:0')
episode: 367 training return: tensor(-357.9291, device='cuda:0')
epoch: 92 test_true_pfm: 2436.0780064498435 sim_pfm: -87.06033435013767
episode: 368 training return: tensor(191.1416, device='cuda:0')
episode: 369 training return: tensor(-207.4518, device='cuda:0')
episode: 370 training return: tensor(-392.2652, device='cuda:0')
episode: 371 training return: tensor(-63.9057, device='cuda:0')
epoch: 93 test_true_pfm: 2452.6551330373863 sim_pfm: 23.867126377648674
episode: 372 training return: tensor(-356.8858, device='cuda:0')
episode: 373 training return: tensor(-331.0991, device='cuda:0')
episode: 374 training return: tensor(257.9547, device='cuda:0')
episode: 375 training return: tensor(-391.8596, device='cuda:0')
epoch: 94 test_true_pfm: 2874.648401384915 sim_pfm: 22.276263860985637
episode: 376 training return: tensor(-52.5753, device='cuda:0')
episode: 377 training return: tensor(159.3005, device='cuda:0')
episode: 378 training return: tensor(-368.0753, device='cuda:0')
episode: 379 training return: tensor(-376.3447, device='cuda:0')
epoch: 95 test_true_pfm: 2517.3283726222116 sim_pfm: 309.7727108045171
episode: 380 training return: tensor(-215.9713, device='cuda:0')
episode: 381 training return: tensor(274.4589, device='cuda:0')
episode: 382 training return: tensor(-331.8854, device='cuda:0')
episode: 383 training return: tensor(-381.8769, device='cuda:0')
epoch: 96 test_true_pfm: 2821.428902349795 sim_pfm: 165.42064103792654
episode: 384 training return: tensor(-380.5581, device='cuda:0')
episode: 385 training return: tensor(-205.4449, device='cuda:0')
episode: 386 training return: tensor(280.5085, device='cuda:0')
episode: 387 training return: tensor(-66.1092, device='cuda:0')
epoch: 97 test_true_pfm: 2931.8847248985235 sim_pfm: -92.9928776678086
episode: 388 training return: tensor(301.5315, device='cuda:0')
episode: 389 training return: tensor(-113.2688, device='cuda:0')
episode: 390 training return: tensor(-226.5922, device='cuda:0')
episode: 391 training return: tensor(312.6203, device='cuda:0')
epoch: 98 test_true_pfm: 3247.7835139685544 sim_pfm: 25.47830734788052
episode: 392 training return: tensor(-293.2418, device='cuda:0')
episode: 393 training return: tensor(19.3558, device='cuda:0')
episode: 394 training return: tensor(-327.9601, device='cuda:0')
episode: 395 training return: tensor(-250.1136, device='cuda:0')
epoch: 99 test_true_pfm: 3276.062904893277 sim_pfm: 164.3963607181407
episode: 396 training return: tensor(-389.4828, device='cuda:0')
episode: 397 training return: tensor(-295.4859, device='cuda:0')
episode: 398 training return: tensor(139.5980, device='cuda:0')
episode: 399 training return: tensor(-206.3591, device='cuda:0')
epoch: 100 test_true_pfm: 2868.720023205378 sim_pfm: 30.858856978127733
episode: 400 training return: tensor(-261.6466, device='cuda:0')
episode: 401 training return: tensor(-89.2666, device='cuda:0')
episode: 402 training return: tensor(-321.3910, device='cuda:0')
episode: 403 training return: tensor(-291.0590, device='cuda:0')
epoch: 101 test_true_pfm: 2601.889890403338 sim_pfm: 158.65305982699888
episode: 404 training return: tensor(-286.0503, device='cuda:0')
episode: 405 training return: tensor(210.7272, device='cuda:0')
episode: 406 training return: tensor(-390.7893, device='cuda:0')
episode: 407 training return: tensor(-342.0112, device='cuda:0')
epoch: 102 test_true_pfm: 3266.1950847987973 sim_pfm: 252.33690442397105
episode: 408 training return: tensor(-296.3344, device='cuda:0')
episode: 409 training return: tensor(-392.5747, device='cuda:0')
episode: 410 training return: tensor(-269.9645, device='cuda:0')
episode: 411 training return: tensor(-345.8034, device='cuda:0')
epoch: 103 test_true_pfm: 3267.328778662584 sim_pfm: 107.15368471713737
episode: 412 training return: tensor(-347.8327, device='cuda:0')
episode: 413 training return: tensor(-305.9391, device='cuda:0')
episode: 414 training return: tensor(361.0918, device='cuda:0')
episode: 415 training return: tensor(-278.0692, device='cuda:0')
epoch: 104 test_true_pfm: 3161.900896721318 sim_pfm: 196.38631350332676
episode: 416 training return: tensor(-275.0342, device='cuda:0')
episode: 417 training return: tensor(-228.1718, device='cuda:0')
episode: 418 training return: tensor(-326.7889, device='cuda:0')
episode: 419 training return: tensor(127.2246, device='cuda:0')
epoch: 105 test_true_pfm: 2849.082810377525 sim_pfm: 187.6985671572135
episode: 420 training return: tensor(-2.9771, device='cuda:0')
episode: 421 training return: tensor(278.1818, device='cuda:0')
episode: 422 training return: tensor(276.9617, device='cuda:0')
episode: 423 training return: tensor(-321.3870, device='cuda:0')
epoch: 106 test_true_pfm: 2543.6861826314744 sim_pfm: 294.60550199247274
episode: 424 training return: tensor(293.0434, device='cuda:0')
episode: 425 training return: tensor(-175.5825, device='cuda:0')
episode: 426 training return: tensor(-290.6114, device='cuda:0')
episode: 427 training return: tensor(-39.4661, device='cuda:0')
epoch: 107 test_true_pfm: 2540.9778605332663 sim_pfm: 41.223591965875436
episode: 428 training return: tensor(-304.8862, device='cuda:0')
episode: 429 training return: tensor(-385.8955, device='cuda:0')
episode: 430 training return: tensor(-400.5602, device='cuda:0')
episode: 431 training return: tensor(-208.8281, device='cuda:0')
epoch: 108 test_true_pfm: 3248.203102865619 sim_pfm: 105.08145290488999
episode: 432 training return: tensor(-398.6080, device='cuda:0')
episode: 433 training return: tensor(271.8430, device='cuda:0')
episode: 434 training return: tensor(-319.4182, device='cuda:0')
episode: 435 training return: tensor(261.1158, device='cuda:0')
epoch: 109 test_true_pfm: 2742.878959941389 sim_pfm: 159.11895309376027
episode: 436 training return: tensor(-105.4970, device='cuda:0')
episode: 437 training return: tensor(-281.5999, device='cuda:0')
episode: 438 training return: tensor(-336.1721, device='cuda:0')
episode: 439 training return: tensor(-331.4388, device='cuda:0')
epoch: 110 test_true_pfm: 3075.2156242049573 sim_pfm: 196.76519269750375
episode: 440 training return: tensor(264.7743, device='cuda:0')
episode: 441 training return: tensor(-285.4648, device='cuda:0')
episode: 442 training return: tensor(-63.5798, device='cuda:0')
episode: 443 training return: tensor(-351.1595, device='cuda:0')
epoch: 111 test_true_pfm: 3240.4258059449116 sim_pfm: 320.38553922903765
episode: 444 training return: tensor(-238.3893, device='cuda:0')
episode: 445 training return: tensor(-94.6309, device='cuda:0')
episode: 446 training return: tensor(297.5332, device='cuda:0')
episode: 447 training return: tensor(-16.0156, device='cuda:0')
epoch: 112 test_true_pfm: 2938.7703982286926 sim_pfm: 189.64680929280198
episode: 448 training return: tensor(-293.2096, device='cuda:0')
episode: 449 training return: tensor(46.7593, device='cuda:0')
episode: 450 training return: tensor(270.2614, device='cuda:0')
episode: 451 training return: tensor(-65.7739, device='cuda:0')
epoch: 113 test_true_pfm: 2831.9761802020057 sim_pfm: 277.09883457409643
episode: 452 training return: tensor(26.0655, device='cuda:0')
episode: 453 training return: tensor(-206.5945, device='cuda:0')
episode: 454 training return: tensor(-390.9882, device='cuda:0')
episode: 455 training return: tensor(-388.1488, device='cuda:0')
epoch: 114 test_true_pfm: 2415.3220497827874 sim_pfm: 101.48880416476943
episode: 456 training return: tensor(-389.2476, device='cuda:0')
episode: 457 training return: tensor(-363.6277, device='cuda:0')
episode: 458 training return: tensor(-391.2947, device='cuda:0')
episode: 459 training return: tensor(123.9219, device='cuda:0')
epoch: 115 test_true_pfm: 2547.143466102519 sim_pfm: 156.040923948196
episode: 460 training return: tensor(-120.5992, device='cuda:0')
episode: 461 training return: tensor(-106.4855, device='cuda:0')
episode: 462 training return: tensor(306.9419, device='cuda:0')
episode: 463 training return: tensor(-267.6389, device='cuda:0')
epoch: 116 test_true_pfm: 2606.5220911178935 sim_pfm: 167.30984466548156
episode: 464 training return: tensor(-367.2795, device='cuda:0')
episode: 465 training return: tensor(-391.8411, device='cuda:0')
episode: 466 training return: tensor(-320.7353, device='cuda:0')
episode: 467 training return: tensor(250.3682, device='cuda:0')
epoch: 117 test_true_pfm: 2965.6539970917624 sim_pfm: 196.98516172020268
episode: 468 training return: tensor(-295.8331, device='cuda:0')
episode: 469 training return: tensor(273.7146, device='cuda:0')
episode: 470 training return: tensor(100.4650, device='cuda:0')
episode: 471 training return: tensor(-236.7837, device='cuda:0')
epoch: 118 test_true_pfm: 2291.439382449269 sim_pfm: 50.420002871930286
episode: 472 training return: tensor(272.4938, device='cuda:0')
episode: 473 training return: tensor(-335.8072, device='cuda:0')
episode: 474 training return: tensor(137.5509, device='cuda:0')
episode: 475 training return: tensor(-298.8900, device='cuda:0')
epoch: 119 test_true_pfm: 2535.7752592548236 sim_pfm: 22.287569822956964
episode: 476 training return: tensor(-393.9306, device='cuda:0')
episode: 477 training return: tensor(-369.3128, device='cuda:0')
episode: 478 training return: tensor(-254.1294, device='cuda:0')
episode: 479 training return: tensor(-49.4147, device='cuda:0')
epoch: 120 test_true_pfm: 3136.9930727363076 sim_pfm: 192.14356824315232
episode: 480 training return: tensor(331.8538, device='cuda:0')
episode: 481 training return: tensor(-223.3056, device='cuda:0')
episode: 482 training return: tensor(141.6599, device='cuda:0')
episode: 483 training return: tensor(219.5704, device='cuda:0')
epoch: 121 test_true_pfm: 3277.71607990944 sim_pfm: 278.6399279071775
episode: 484 training return: tensor(-28.5390, device='cuda:0')
episode: 485 training return: tensor(-328.7116, device='cuda:0')
episode: 486 training return: tensor(-65.8939, device='cuda:0')
episode: 487 training return: tensor(-266.1004, device='cuda:0')
epoch: 122 test_true_pfm: 2785.0428127013656 sim_pfm: 307.5933663502122
episode: 488 training return: tensor(-289.7852, device='cuda:0')
episode: 489 training return: tensor(-292.8970, device='cuda:0')
episode: 490 training return: tensor(-285.5247, device='cuda:0')
episode: 491 training return: tensor(288.4756, device='cuda:0')
epoch: 123 test_true_pfm: 2621.6181333116683 sim_pfm: 8.691025702486513
episode: 492 training return: tensor(303.0735, device='cuda:0')
episode: 493 training return: tensor(-307.9050, device='cuda:0')
episode: 494 training return: tensor(-352.8501, device='cuda:0')
episode: 495 training return: tensor(-303.3741, device='cuda:0')
epoch: 124 test_true_pfm: 2440.9111786287676 sim_pfm: 292.3615683764995
episode: 496 training return: tensor(304.0928, device='cuda:0')
episode: 497 training return: tensor(-18.1939, device='cuda:0')
episode: 498 training return: tensor(-291.9046, device='cuda:0')
episode: 499 training return: tensor(-34.0716, device='cuda:0')
epoch: 125 test_true_pfm: 2479.147509244515 sim_pfm: 143.83228679804597
episode: 500 training return: tensor(-342.9472, device='cuda:0')
episode: 501 training return: tensor(234.9357, device='cuda:0')
episode: 502 training return: tensor(-87.3743, device='cuda:0')
episode: 503 training return: tensor(-243.7208, device='cuda:0')
epoch: 126 test_true_pfm: 3260.597963347105 sim_pfm: 78.896694207564
episode: 504 training return: tensor(-334.3800, device='cuda:0')
episode: 505 training return: tensor(-296.8613, device='cuda:0')
episode: 506 training return: tensor(15.1455, device='cuda:0')
episode: 507 training return: tensor(-299.2494, device='cuda:0')
epoch: 127 test_true_pfm: 2946.337166047781 sim_pfm: 215.8226419625183
episode: 508 training return: tensor(39.8695, device='cuda:0')
episode: 509 training return: tensor(-29.3098, device='cuda:0')
episode: 510 training return: tensor(347.6553, device='cuda:0')
episode: 511 training return: tensor(-23.3570, device='cuda:0')
epoch: 128 test_true_pfm: 2877.3619221928016 sim_pfm: 200.0510615907066
episode: 512 training return: tensor(-104.7948, device='cuda:0')
episode: 513 training return: tensor(-344.8526, device='cuda:0')
episode: 514 training return: tensor(-121.9971, device='cuda:0')
episode: 515 training return: tensor(-242.2838, device='cuda:0')
epoch: 129 test_true_pfm: 3176.128476116275 sim_pfm: 142.0708746058517
episode: 516 training return: tensor(-342.3185, device='cuda:0')
episode: 517 training return: tensor(292.2914, device='cuda:0')
episode: 518 training return: tensor(-102.8329, device='cuda:0')
episode: 519 training return: tensor(297.9479, device='cuda:0')
epoch: 130 test_true_pfm: 3258.39446650737 sim_pfm: 14.489213255195258
episode: 520 training return: tensor(161.6344, device='cuda:0')
episode: 521 training return: tensor(301.3255, device='cuda:0')
episode: 522 training return: tensor(-45.7121, device='cuda:0')
episode: 523 training return: tensor(-186.7086, device='cuda:0')
epoch: 131 test_true_pfm: 2948.1923182251485 sim_pfm: 206.3448816704913
episode: 524 training return: tensor(294.4477, device='cuda:0')
episode: 525 training return: tensor(-386.6396, device='cuda:0')
episode: 526 training return: tensor(297.0963, device='cuda:0')
episode: 527 training return: tensor(-380.0518, device='cuda:0')
epoch: 132 test_true_pfm: 3064.942628968472 sim_pfm: 160.391619002301
episode: 528 training return: tensor(-228.5454, device='cuda:0')
episode: 529 training return: tensor(114.7278, device='cuda:0')
episode: 530 training return: tensor(288.3265, device='cuda:0')
episode: 531 training return: tensor(62.8985, device='cuda:0')
epoch: 133 test_true_pfm: 3221.1237168849207 sim_pfm: 306.4316057484054
episode: 532 training return: tensor(-25.9142, device='cuda:0')
episode: 533 training return: tensor(78.9845, device='cuda:0')
episode: 534 training return: tensor(-309.5215, device='cuda:0')
episode: 535 training return: tensor(139.1847, device='cuda:0')
epoch: 134 test_true_pfm: 3079.560914310044 sim_pfm: 117.7783205016264
episode: 536 training return: tensor(-2.3974, device='cuda:0')
episode: 537 training return: tensor(-358.8913, device='cuda:0')
episode: 538 training return: tensor(-300.5410, device='cuda:0')
episode: 539 training return: tensor(289.4392, device='cuda:0')
epoch: 135 test_true_pfm: 2882.50050730558 sim_pfm: 282.1259959838838
episode: 540 training return: tensor(335.3399, device='cuda:0')
episode: 541 training return: tensor(-329.1187, device='cuda:0')
episode: 542 training return: tensor(-339.6740, device='cuda:0')
episode: 543 training return: tensor(-375.5683, device='cuda:0')
epoch: 136 test_true_pfm: 2902.981867934395 sim_pfm: 228.89289034185154
episode: 544 training return: tensor(-296.4370, device='cuda:0')
episode: 545 training return: tensor(-305.8929, device='cuda:0')
episode: 546 training return: tensor(-314.5435, device='cuda:0')
episode: 547 training return: tensor(110.3966, device='cuda:0')
epoch: 137 test_true_pfm: 2761.0618403914646 sim_pfm: 107.2152188521383
episode: 548 training return: tensor(-333.4865, device='cuda:0')
episode: 549 training return: tensor(288.5405, device='cuda:0')
episode: 550 training return: tensor(-393.3178, device='cuda:0')
episode: 551 training return: tensor(51.0283, device='cuda:0')
epoch: 138 test_true_pfm: 2531.7270026978854 sim_pfm: 229.46080766658997
episode: 552 training return: tensor(-343.5919, device='cuda:0')
episode: 553 training return: tensor(89.9808, device='cuda:0')
episode: 554 training return: tensor(-312.1389, device='cuda:0')
episode: 555 training return: tensor(326.8415, device='cuda:0')
epoch: 139 test_true_pfm: 2894.7937283342835 sim_pfm: 178.9672890775449
episode: 556 training return: tensor(297.7587, device='cuda:0')
episode: 557 training return: tensor(-387.0884, device='cuda:0')
episode: 558 training return: tensor(-332.2580, device='cuda:0')
episode: 559 training return: tensor(7.1607, device='cuda:0')
epoch: 140 test_true_pfm: 3258.724392268205 sim_pfm: 269.1355680498721
episode: 560 training return: tensor(-107.2107, device='cuda:0')
episode: 561 training return: tensor(68.0793, device='cuda:0')
episode: 562 training return: tensor(-211.8128, device='cuda:0')
episode: 563 training return: tensor(-337.8000, device='cuda:0')
epoch: 141 test_true_pfm: 3302.7077158239026 sim_pfm: 96.901867037445
episode: 564 training return: tensor(-184.1672, device='cuda:0')
episode: 565 training return: tensor(86.9910, device='cuda:0')
episode: 566 training return: tensor(-119.0570, device='cuda:0')
episode: 567 training return: tensor(-380.8408, device='cuda:0')
epoch: 142 test_true_pfm: 2941.037218116621 sim_pfm: 293.08583738297847
episode: 568 training return: tensor(-359.1696, device='cuda:0')
episode: 569 training return: tensor(299.3994, device='cuda:0')
episode: 570 training return: tensor(284.2131, device='cuda:0')
episode: 571 training return: tensor(-290.4146, device='cuda:0')
epoch: 143 test_true_pfm: 3277.2783417731002 sim_pfm: 126.67874444423553
episode: 572 training return: tensor(-336.0631, device='cuda:0')
episode: 573 training return: tensor(-394.8166, device='cuda:0')
episode: 574 training return: tensor(291.1586, device='cuda:0')
episode: 575 training return: tensor(329.9324, device='cuda:0')
epoch: 144 test_true_pfm: 3073.0749492599075 sim_pfm: 162.47721666644793
episode: 576 training return: tensor(-306.4562, device='cuda:0')
episode: 577 training return: tensor(-108.4455, device='cuda:0')
episode: 578 training return: tensor(-388.0030, device='cuda:0')
episode: 579 training return: tensor(-0.9088, device='cuda:0')
epoch: 145 test_true_pfm: 2922.5862928593856 sim_pfm: 64.78810532783973
episode: 580 training return: tensor(-310.0002, device='cuda:0')
episode: 581 training return: tensor(-352.1192, device='cuda:0')
episode: 582 training return: tensor(-337.8873, device='cuda:0')
episode: 583 training return: tensor(305.7462, device='cuda:0')
epoch: 146 test_true_pfm: 2544.1524154216872 sim_pfm: 241.10198673118916
episode: 584 training return: tensor(77.5995, device='cuda:0')
episode: 585 training return: tensor(-340.0919, device='cuda:0')
episode: 586 training return: tensor(-395.4339, device='cuda:0')
episode: 587 training return: tensor(-291.0848, device='cuda:0')
epoch: 147 test_true_pfm: 2520.9560389204476 sim_pfm: 193.14458019689968
episode: 588 training return: tensor(272.7924, device='cuda:0')
episode: 589 training return: tensor(288.4917, device='cuda:0')
episode: 590 training return: tensor(-118.3244, device='cuda:0')
episode: 591 training return: tensor(-238.2814, device='cuda:0')
epoch: 148 test_true_pfm: 2822.2812860553136 sim_pfm: 92.29760987043846
episode: 592 training return: tensor(-72.8017, device='cuda:0')
episode: 593 training return: tensor(303.6432, device='cuda:0')
episode: 594 training return: tensor(-382.3232, device='cuda:0')
episode: 595 training return: tensor(-291.7877, device='cuda:0')
epoch: 149 test_true_pfm: 2623.0184673088215 sim_pfm: 177.196974659552
episode: 596 training return: tensor(-290.6620, device='cuda:0')
episode: 597 training return: tensor(-70.8741, device='cuda:0')
episode: 598 training return: tensor(-381.3379, device='cuda:0')
episode: 599 training return: tensor(-16.0438, device='cuda:0')
epoch: 150 test_true_pfm: 2965.6178581916283 sim_pfm: 70.248698721601
