['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '3']
epoch: 0 training_loss 0.4281345865130424 test_loss: 0.3032746553421021
epoch: 1 training_loss 0.3027735225856304 test_loss: 0.25018608570098877
epoch: 2 training_loss 0.26228746235370637 test_loss: 0.2605332612991333
epoch: 3 training_loss 0.24466239392757416 test_loss: 0.23505964279174804
epoch: 4 training_loss 0.22804050669074058 test_loss: 0.20720672607421875
epoch: 5 training_loss 0.2420404366403818 test_loss: 0.1985426664352417
epoch: 6 training_loss 0.2358826331794262 test_loss: 0.23582584857940675
epoch: 7 training_loss 0.22438391141593456 test_loss: 0.21219158172607422
epoch: 8 training_loss 0.22569043695926666 test_loss: 0.22561275959014893
epoch: 9 training_loss 0.21746251374483108 test_loss: 0.22669970989227295
epoch: 10 training_loss 0.21319376453757286 test_loss: 0.20080068111419677
epoch: 11 training_loss 0.21286311097443103 test_loss: 0.2144254684448242
epoch: 12 training_loss 0.2242736515402794 test_loss: 0.19683525562286378
epoch: 13 training_loss 0.2272313117980957 test_loss: 0.2073434352874756
epoch: 14 training_loss 0.21610772609710693 test_loss: 0.2141864538192749
epoch: 15 training_loss 0.20389889419078827 test_loss: 0.1980183243751526
epoch: 16 training_loss 0.22337582238018514 test_loss: 0.19785771369934083
epoch: 17 training_loss 0.20662429973483085 test_loss: 0.19983307123184205
epoch: 18 training_loss 0.22435130774974824 test_loss: 0.22666628360748292
epoch: 19 training_loss 0.21018016643822193 test_loss: 0.21948351860046386
epoch: 20 training_loss 0.20845128029584883 test_loss: 0.22089431285858155
epoch: 21 training_loss 0.20709170445799827 test_loss: 0.20072722434997559
epoch: 22 training_loss 0.21542900994420053 test_loss: 0.1881759524345398
epoch: 23 training_loss 0.2017263302206993 test_loss: 0.1962297558784485
epoch: 24 training_loss 0.2082136544585228 test_loss: 0.2415239095687866
epoch: 25 training_loss 0.21249589242041111 test_loss: 0.19001369476318358
epoch: 26 training_loss 0.20311886720359326 test_loss: 0.19267157316207886
epoch: 27 training_loss 0.20126964151859283 test_loss: 0.23489930629730224
epoch: 28 training_loss 0.19719560943543912 test_loss: 0.21898891925811767
epoch: 29 training_loss 0.19947983860969543 test_loss: 0.18755091428756715
epoch: 30 training_loss 0.19758610516786576 test_loss: 0.2213836669921875
epoch: 31 training_loss 0.20084261164069175 test_loss: 0.19458862543106079
epoch: 32 training_loss 0.2033933538198471 test_loss: 0.17948174476623535
epoch: 33 training_loss 0.19877611801028253 test_loss: 0.18383756875991822
epoch: 34 training_loss 0.19228361509740352 test_loss: 0.21882116794586182
epoch: 35 training_loss 0.20490850493311882 test_loss: 0.18330355882644653
epoch: 36 training_loss 0.19655235208570956 test_loss: 0.18360960483551025
epoch: 37 training_loss 0.1947826086729765 test_loss: 0.22135641574859619
epoch: 38 training_loss 0.19621479474008083 test_loss: 0.19435423612594604
epoch: 39 training_loss 0.20177726164460183 test_loss: 0.18825420141220092
epoch: 40 training_loss 0.19379058964550494 test_loss: 0.1934625506401062
epoch: 41 training_loss 0.1946724808961153 test_loss: 0.22738373279571533
epoch: 42 training_loss 0.194394261687994 test_loss: 0.1796430230140686
epoch: 43 training_loss 0.1959291195869446 test_loss: 0.20046122074127198
epoch: 44 training_loss 0.19293150790035724 test_loss: 0.17502913475036622
epoch: 45 training_loss 0.19595163375139235 test_loss: 0.17956695556640626
epoch: 46 training_loss 0.20461298182606696 test_loss: 0.1931661605834961
epoch: 47 training_loss 0.1931666872650385 test_loss: 0.21010234355926513
epoch: 48 training_loss 0.19273871779441834 test_loss: 0.19552440643310548
epoch: 49 training_loss 0.20249504193663598 test_loss: 0.2356769323348999
epoch: 50 training_loss 0.18923149339854717 test_loss: 0.20143322944641112
epoch: 51 training_loss 0.19389642275869845 test_loss: 0.17493298053741455
epoch: 52 training_loss 0.19593379601836206 test_loss: 0.21442506313323975
epoch: 53 training_loss 0.1943156060576439 test_loss: 0.1995559811592102
epoch: 54 training_loss 0.19605829484760762 test_loss: 0.21062536239624025
epoch: 55 training_loss 0.1940476258844137 test_loss: 0.1960983991622925
epoch: 56 training_loss 0.19232462525367736 test_loss: 0.19362515211105347
epoch: 57 training_loss 0.19152124516665936 test_loss: 0.18242883682250977
epoch: 58 training_loss 0.1942678862810135 test_loss: 0.18016204833984376
epoch: 59 training_loss 0.1912617313116789 test_loss: 0.1832931637763977
epoch: 60 training_loss 0.19391484841704368 test_loss: 0.1775652289390564
epoch: 61 training_loss 0.19401448734104634 test_loss: 0.18585954904556273
epoch: 62 training_loss 0.19778595015406608 test_loss: 0.1768728971481323
epoch: 63 training_loss 0.1952396449446678 test_loss: 0.20112123489379882
epoch: 64 training_loss 0.20206858076155185 test_loss: 0.18364888429641724
epoch: 65 training_loss 0.19647145606577396 test_loss: 0.17884514331817628
epoch: 66 training_loss 0.19200585715472698 test_loss: 0.1783428192138672
epoch: 67 training_loss 0.193904003277421 test_loss: 0.18137238025665284
epoch: 68 training_loss 0.18690273471176624 test_loss: 0.18933321237564088
epoch: 69 training_loss 0.18127279847860336 test_loss: 0.20348145961761474
epoch: 70 training_loss 0.1868657597899437 test_loss: 0.18332107067108155
epoch: 71 training_loss 0.18407111369073392 test_loss: 0.17751283645629884
epoch: 72 training_loss 0.19264163352549077 test_loss: 0.18628458976745604
epoch: 73 training_loss 0.19894228763878347 test_loss: 0.2177199125289917
epoch: 74 training_loss 0.19250582054257392 test_loss: 0.19063687324523926
epoch: 75 training_loss 0.18773944221436978 test_loss: 0.18671427965164183
epoch: 76 training_loss 0.1862987169623375 test_loss: 0.20843286514282228
epoch: 77 training_loss 0.18903677590191365 test_loss: 0.18246543407440186
epoch: 78 training_loss 0.18762753568589688 test_loss: 0.1977481722831726
epoch: 79 training_loss 0.18624752037227155 test_loss: 0.1805279016494751
epoch: 80 training_loss 0.1819503700733185 test_loss: 0.1877008080482483
epoch: 81 training_loss 0.1880607534945011 test_loss: 0.19707967042922975
epoch: 82 training_loss 0.18083841301500797 test_loss: 0.19642579555511475
epoch: 83 training_loss 0.18668804451823234 test_loss: 0.17165143489837648
epoch: 84 training_loss 0.18427988156676292 test_loss: 0.18400014638900758
epoch: 85 training_loss 0.18494985811412334 test_loss: 0.1904178023338318
epoch: 86 training_loss 0.19789489232003687 test_loss: 0.18618228435516357
epoch: 87 training_loss 0.18707118548452853 test_loss: 0.18346842527389526
epoch: 88 training_loss 0.1838776521384716 test_loss: 0.19033342599868774
epoch: 89 training_loss 0.1966299644857645 test_loss: 0.16996545791625978
epoch: 90 training_loss 0.18548937037587165 test_loss: 0.1893932819366455
epoch: 91 training_loss 0.1894537366181612 test_loss: 0.20143208503723145
epoch: 92 training_loss 0.18583277896046638 test_loss: 0.17047120332717897
epoch: 93 training_loss 0.18788243852555753 test_loss: 0.19832736253738403
epoch: 94 training_loss 0.18726836390793322 test_loss: 0.19140952825546265
epoch: 95 training_loss 0.19514164701104164 test_loss: 0.18954105377197267
epoch: 96 training_loss 0.19023256726562976 test_loss: 0.18764495849609375
epoch: 97 training_loss 0.18655944973230362 test_loss: 0.20555944442749025
epoch: 98 training_loss 0.17860498666763305 test_loss: 0.17091798782348633
epoch: 99 training_loss 0.19152412205934524 test_loss: 0.18285359144210817
epoch: 100 training_loss 0.1863893533498049 test_loss: 0.1927213191986084
epoch: 101 training_loss 0.18544050067663193 test_loss: 0.17260874509811402
epoch: 102 training_loss 0.1823790417611599 test_loss: 0.21619949340820313
epoch: 103 training_loss 0.18559640765190125 test_loss: 0.18831980228424072
epoch: 104 training_loss 0.19547599874436855 test_loss: 0.18116824626922606
epoch: 105 training_loss 0.18338371120393276 test_loss: 0.1805583953857422
epoch: 106 training_loss 0.18560913264751433 test_loss: 0.1869986891746521
epoch: 107 training_loss 0.1826771730184555 test_loss: 0.19136400222778321
epoch: 108 training_loss 0.18397709473967552 test_loss: 0.19351706504821778
epoch: 109 training_loss 0.18813439331948756 test_loss: 0.1973532557487488
epoch: 110 training_loss 0.17720183156430722 test_loss: 0.19723228216171265
epoch: 111 training_loss 0.1877670333534479 test_loss: 0.18223379850387572
epoch: 112 training_loss 0.1838763014227152 test_loss: 0.18170078992843627
epoch: 113 training_loss 0.19000269696116448 test_loss: 0.18908112049102782
epoch: 114 training_loss 0.17622309371829034 test_loss: 0.1774010419845581
epoch: 115 training_loss 0.18155420765280725 test_loss: 0.1695183515548706
epoch: 116 training_loss 0.19100943386554717 test_loss: 0.19908539056777955
epoch: 117 training_loss 0.18223180159926414 test_loss: 0.18419907093048096
epoch: 118 training_loss 0.1824818217754364 test_loss: 0.1892263650894165
epoch: 119 training_loss 0.17965708173811434 test_loss: 0.1837224245071411
epoch: 120 training_loss 0.18607040032744407 test_loss: 0.1736977815628052
epoch: 121 training_loss 0.1934779266268015 test_loss: 0.18333784341812134
epoch: 122 training_loss 0.19004536874592304 test_loss: 0.17207969427108766
epoch: 123 training_loss 0.17628978557884692 test_loss: 0.18623414039611816
epoch: 124 training_loss 0.18471706464886664 test_loss: 0.18531944751739501
epoch: 125 training_loss 0.18380379356443882 test_loss: 0.18824429512023927
epoch: 126 training_loss 0.18691626943647863 test_loss: 0.1834952116012573
epoch: 127 training_loss 0.1914659584313631 test_loss: 0.1798421025276184
epoch: 128 training_loss 0.18183845035731794 test_loss: 0.18457235097885133
epoch: 129 training_loss 0.18107096791267396 test_loss: 0.18461769819259644
epoch: 130 training_loss 0.18624499306082726 test_loss: 0.1779888391494751
epoch: 131 training_loss 0.1818577105551958 test_loss: 0.21288676261901857
epoch: 132 training_loss 0.18183555968105794 test_loss: 0.1912364363670349
epoch: 133 training_loss 0.1736878464370966 test_loss: 0.1923115611076355
epoch: 134 training_loss 0.185788379535079 test_loss: 0.16796722412109374
epoch: 135 training_loss 0.17895304270088672 test_loss: 0.16911325454711915
epoch: 136 training_loss 0.19386278003454208 test_loss: 0.19047783613204955
epoch: 137 training_loss 0.1862298434972763 test_loss: 0.19316773414611815
epoch: 138 training_loss 0.1834328356385231 test_loss: 0.196387779712677
epoch: 139 training_loss 0.18161260940134524 test_loss: 0.18665951490402222
epoch: 140 training_loss 0.17770573906600476 test_loss: 0.18810995817184448
epoch: 141 training_loss 0.18650352858006955 test_loss: 0.18545229434967042
epoch: 142 training_loss 0.17725036323070525 test_loss: 0.17568209171295165
epoch: 143 training_loss 0.18358449317514897 test_loss: 0.18603440523147582
epoch: 144 training_loss 0.17970356330275536 test_loss: 0.18922574520111085
epoch: 145 training_loss 0.1909028536826372 test_loss: 0.18065164089202881
epoch: 146 training_loss 0.18116304017603396 test_loss: 0.1709093689918518
epoch: 147 training_loss 0.18188963182270526 test_loss: 0.18248382806777955
epoch: 148 training_loss 0.18528340101242066 test_loss: 0.18564987182617188
epoch: 149 training_loss 0.18039995439350606 test_loss: 0.19143271446228027
epoch: 0 training_loss 45.6118881225586 test_loss: 24.850518798828126
epoch: 1 training_loss 20.138766288757324 test_loss: 17.438142395019533
epoch: 2 training_loss 16.1518541431427 test_loss: 14.448184204101562
epoch: 3 training_loss 13.19138313293457 test_loss: 12.415908050537109
epoch: 4 training_loss 11.947528114318848 test_loss: 11.481206512451172
epoch: 5 training_loss 10.917029275894166 test_loss: 10.511011505126953
epoch: 6 training_loss 10.230579261779786 test_loss: 9.872066497802734
epoch: 7 training_loss 9.657540311813355 test_loss: 9.103466033935547
epoch: 8 training_loss 9.087381300926209 test_loss: 8.681195068359376
epoch: 9 training_loss 8.56100344657898 test_loss: 8.140738677978515
epoch: 10 training_loss 7.976307377815247 test_loss: 7.973028564453125
epoch: 11 training_loss 7.605903043746948 test_loss: 7.344677734375
epoch: 12 training_loss 7.109191679954529 test_loss: 7.0944671630859375
epoch: 13 training_loss 6.763791732788086 test_loss: 6.632730865478516
epoch: 14 training_loss 6.5998059844970705 test_loss: 6.658837127685547
epoch: 15 training_loss 6.323080372810364 test_loss: 6.29151725769043
epoch: 16 training_loss 6.194412424564361 test_loss: 5.875312423706054
epoch: 17 training_loss 5.934168272018432 test_loss: 5.6466419219970705
epoch: 18 training_loss 5.77001437664032 test_loss: 5.523257064819336
epoch: 19 training_loss 5.727823529243469 test_loss: 5.717461395263672
epoch: 20 training_loss 5.528444476127625 test_loss: 5.166960144042969
epoch: 21 training_loss 5.280752000808715 test_loss: 5.130936813354492
epoch: 22 training_loss 5.2122389554977415 test_loss: 5.34284782409668
epoch: 23 training_loss 5.071255438327789 test_loss: 4.770270919799804
epoch: 24 training_loss 4.814984557628631 test_loss: 4.7407386779785154
epoch: 25 training_loss 4.8622223043441775 test_loss: 4.914017868041992
epoch: 26 training_loss 4.7584531164169315 test_loss: 4.379473876953125
epoch: 27 training_loss 4.723347134590149 test_loss: 4.707539749145508
epoch: 28 training_loss 4.636687796115876 test_loss: 4.322340393066407
epoch: 29 training_loss 4.559235146045685 test_loss: 4.449573135375976
epoch: 30 training_loss 4.468883919715881 test_loss: 4.445661926269532
epoch: 31 training_loss 4.451796345710754 test_loss: 4.226145553588867
epoch: 32 training_loss 4.419702022075653 test_loss: 3.9097755432128904
epoch: 33 training_loss 4.303137369155884 test_loss: 4.092598724365234
epoch: 34 training_loss 4.236147618293762 test_loss: 4.017813873291016
epoch: 35 training_loss 4.069558353424072 test_loss: 4.12945671081543
epoch: 36 training_loss 4.0353150248527525 test_loss: 4.030466079711914
epoch: 37 training_loss 4.125384595394134 test_loss: 3.962875747680664
epoch: 38 training_loss 3.942613968849182 test_loss: 3.7300914764404296
epoch: 39 training_loss 3.7949856424331667 test_loss: 3.706649398803711
epoch: 40 training_loss 3.7830233478546145 test_loss: 3.7220897674560547
epoch: 41 training_loss 3.6681046414375307 test_loss: 3.767198944091797
epoch: 42 training_loss 3.6409247636795046 test_loss: 3.6444469451904298
epoch: 43 training_loss 3.7483439564704897 test_loss: 3.417941665649414
epoch: 44 training_loss 3.588560516834259 test_loss: 3.5296371459960936
epoch: 45 training_loss 3.5896643781661988 test_loss: 3.3936363220214845
epoch: 46 training_loss 3.6429909086227417 test_loss: 3.3768524169921874
epoch: 47 training_loss 3.4629422402381898 test_loss: 3.346651077270508
epoch: 48 training_loss 3.3107616782188414 test_loss: 3.5410140991210937
epoch: 49 training_loss 3.164756133556366 test_loss: 3.093666648864746
epoch: 50 training_loss 3.1799145913124085 test_loss: 3.161380958557129
epoch: 51 training_loss 3.172950828075409 test_loss: 3.0241695404052735
epoch: 52 training_loss 3.2176436471939085 test_loss: 3.042757034301758
epoch: 53 training_loss 3.1206038761138917 test_loss: 3.1772336959838867
epoch: 54 training_loss 3.0380726408958436 test_loss: 2.9724430084228515
epoch: 55 training_loss 2.984567050933838 test_loss: 3.044915962219238
epoch: 56 training_loss 2.9489890336990356 test_loss: 3.1183732986450194
epoch: 57 training_loss 3.034036109447479 test_loss: 2.6816213607788084
epoch: 58 training_loss 2.9814493465423584 test_loss: 3.156755828857422
epoch: 59 training_loss 2.8908681654930115 test_loss: 2.8516674041748047
epoch: 60 training_loss 2.901297266483307 test_loss: 3.130328559875488
epoch: 61 training_loss 2.8252196097373963 test_loss: 3.12127742767334
epoch: 62 training_loss 3.0149507892131804 test_loss: 2.81127986907959
epoch: 63 training_loss 2.760449628829956 test_loss: 3.0462350845336914
epoch: 64 training_loss 2.952537627220154 test_loss: 2.851180839538574
epoch: 65 training_loss 2.8008946204185485 test_loss: 2.5891090393066407
epoch: 66 training_loss 2.6912776374816896 test_loss: 2.554022216796875
epoch: 67 training_loss 2.651711709499359 test_loss: 2.6761425018310545
epoch: 68 training_loss 2.610076105594635 test_loss: 2.575677680969238
epoch: 69 training_loss 2.6167163467407226 test_loss: 2.505967140197754
epoch: 70 training_loss 2.7527367198467254 test_loss: 2.5975807189941404
epoch: 71 training_loss 2.6353876316547393 test_loss: 2.4851856231689453
epoch: 72 training_loss 2.6099689388275147 test_loss: 2.480838966369629
epoch: 73 training_loss 2.577956153154373 test_loss: 2.3751399993896483
epoch: 74 training_loss 2.520328452587128 test_loss: 2.3056697845458984
epoch: 75 training_loss 2.4060110986232757 test_loss: 2.50988712310791
epoch: 76 training_loss 2.5617525327205657 test_loss: 2.563766288757324
epoch: 77 training_loss 2.4411652290821078 test_loss: 2.2462751388549806
epoch: 78 training_loss 2.485151973962784 test_loss: 2.819698715209961
epoch: 79 training_loss 2.4320926594734193 test_loss: 2.2518211364746095
epoch: 80 training_loss 2.4080237340927124 test_loss: 2.5974876403808596
epoch: 81 training_loss 2.413104850053787 test_loss: 2.3739768981933596
epoch: 82 training_loss 2.3906988525390624 test_loss: 2.658013916015625
epoch: 83 training_loss 2.366854040622711 test_loss: 2.2533859252929687
epoch: 84 training_loss 2.373380085229874 test_loss: 2.630605697631836
epoch: 85 training_loss 2.414335149526596 test_loss: 2.202682113647461
epoch: 86 training_loss 2.3551962673664093 test_loss: 2.844159698486328
epoch: 87 training_loss 2.3274000322818758 test_loss: 2.2593063354492187
epoch: 88 training_loss 2.3368261766433718 test_loss: 2.2176862716674806
epoch: 89 training_loss 2.2939825570583343 test_loss: 2.2220905303955076
epoch: 90 training_loss 2.2945021200180054 test_loss: 2.8729909896850585
epoch: 91 training_loss 2.4964569342136382 test_loss: 2.6758516311645506
epoch: 92 training_loss 2.4707190024852754 test_loss: 2.244608688354492
epoch: 93 training_loss 2.2097903645038603 test_loss: 2.1351526260375975
epoch: 94 training_loss 2.2913796246051787 test_loss: 2.1157485961914064
epoch: 95 training_loss 2.2867337119579316 test_loss: 2.3129154205322267
epoch: 96 training_loss 2.219761893749237 test_loss: 2.3854217529296875
epoch: 97 training_loss 2.1948512482643125 test_loss: 2.2077150344848633
epoch: 98 training_loss 2.2498978173732755 test_loss: 2.799734687805176
epoch: 99 training_loss 2.2837076485157013 test_loss: 2.13837890625
epoch: 100 training_loss 2.293853451013565 test_loss: 2.2621740341186523
epoch: 101 training_loss 2.2579989576339723 test_loss: 2.3432710647583006
epoch: 102 training_loss 2.201282603740692 test_loss: 2.063125228881836
epoch: 103 training_loss 2.079914857149124 test_loss: 2.0675226211547852
epoch: 104 training_loss 2.172699714899063 test_loss: 2.2357128143310545
epoch: 105 training_loss 2.198445335626602 test_loss: 2.1227481842041014
epoch: 106 training_loss 2.163528163433075 test_loss: 2.2782255172729493
epoch: 107 training_loss 2.125167809724808 test_loss: 2.4316074371337892
epoch: 108 training_loss 2.1335091817379 test_loss: 2.535721778869629
epoch: 109 training_loss 2.1524436354637144 test_loss: 2.1678428649902344
epoch: 110 training_loss 2.061875813007355 test_loss: 2.0870384216308593
epoch: 111 training_loss 2.191057862043381 test_loss: 2.0439138412475586
epoch: 112 training_loss 2.030066795349121 test_loss: 1.8482732772827148
epoch: 113 training_loss 2.0627683365345 test_loss: 1.935997200012207
epoch: 114 training_loss 1.9680464565753937 test_loss: 1.8259178161621095
epoch: 115 training_loss 2.0654201126098632 test_loss: 1.8417268753051759
epoch: 116 training_loss 1.954778573513031 test_loss: 1.8307558059692384
epoch: 117 training_loss 1.953087328672409 test_loss: 2.215069389343262
epoch: 118 training_loss 1.923287925720215 test_loss: 1.9284425735473634
epoch: 119 training_loss 1.9943554043769836 test_loss: 2.1164728164672852
epoch: 120 training_loss 1.887647920846939 test_loss: 1.755935287475586
epoch: 121 training_loss 1.8493328511714935 test_loss: 1.7759782791137695
epoch: 122 training_loss 1.8049584090709687 test_loss: 1.7663154602050781
epoch: 123 training_loss 1.8265739130973815 test_loss: 1.7815690994262696
epoch: 124 training_loss 1.8248406946659088 test_loss: 1.891092300415039
epoch: 125 training_loss 1.8748614180088043 test_loss: 2.1428848266601563
epoch: 126 training_loss 1.8463454627990723 test_loss: 1.7733386993408202
epoch: 127 training_loss 1.8446035587787628 test_loss: 1.9025672912597655
epoch: 128 training_loss 1.8848256814479827 test_loss: 1.8082380294799805
epoch: 129 training_loss 1.8088096475601196 test_loss: 1.898875617980957
epoch: 130 training_loss 1.905038094520569 test_loss: 1.7180976867675781
epoch: 131 training_loss 1.861078176498413 test_loss: 1.9019014358520507
epoch: 132 training_loss 1.8989383494853973 test_loss: 1.6367374420166017
epoch: 133 training_loss 1.7691430044174195 test_loss: 1.8566221237182616
epoch: 134 training_loss 1.8512648034095764 test_loss: 2.3233890533447266
epoch: 135 training_loss 1.8788382077217103 test_loss: 1.7592428207397461
epoch: 136 training_loss 1.8221841621398926 test_loss: 1.7268346786499023
epoch: 137 training_loss 1.7859333193302154 test_loss: 1.6453096389770507
epoch: 138 training_loss 1.7218291568756103 test_loss: 1.711724090576172
epoch: 139 training_loss 1.7890604221820832 test_loss: 1.4977804183959962
epoch: 140 training_loss 1.699257220029831 test_loss: 1.8198179244995116
epoch: 141 training_loss 1.7372778272628784 test_loss: 1.5321413040161134
epoch: 142 training_loss 1.7037871813774108 test_loss: 1.5848676681518554
epoch: 143 training_loss 1.6802394759655 test_loss: 1.9005212783813477
epoch: 144 training_loss 1.6937156021595001 test_loss: 1.6808841705322266
epoch: 145 training_loss 1.5862118935585021 test_loss: 1.5853551864624023
epoch: 146 training_loss 1.7437273573875427 test_loss: 1.6590150833129882
epoch: 147 training_loss 1.6689977967739105 test_loss: 1.5392459869384765
epoch: 148 training_loss 1.729633755683899 test_loss: 1.7737476348876953
epoch: 149 training_loss 1.7376927900314332 test_loss: 1.5795387268066405
73.47074261728494
episode: 0 training return: tensor(-159.1353, device='cuda:0')
episode: 1 training return: tensor(-185.4635, device='cuda:0')
episode: 2 training return: tensor(-182.1011, device='cuda:0')
episode: 3 training return: tensor(-100.6249, device='cuda:0')
epoch: 1 test_true_pfm: 65.47574919076263 sim_pfm: -134.72212089740205
episode: 4 training return: tensor(-155.6838, device='cuda:0')
episode: 5 training return: tensor(-67.3451, device='cuda:0')
episode: 6 training return: tensor(-94.7101, device='cuda:0')
episode: 7 training return: tensor(-166.0453, device='cuda:0')
epoch: 2 test_true_pfm: 75.80663818320221 sim_pfm: -176.82619431401835
episode: 8 training return: tensor(-163.0584, device='cuda:0')
episode: 9 training return: tensor(-156.7728, device='cuda:0')
episode: 10 training return: tensor(-87.3224, device='cuda:0')
episode: 11 training return: tensor(-117.6685, device='cuda:0')
epoch: 3 test_true_pfm: 58.27183341433804 sim_pfm: -138.0143229325302
episode: 12 training return: tensor(-94.3822, device='cuda:0')
episode: 13 training return: tensor(-97.6829, device='cuda:0')
episode: 14 training return: tensor(-177.0699, device='cuda:0')
episode: 15 training return: tensor(-85.9090, device='cuda:0')
epoch: 4 test_true_pfm: 70.12646878100685 sim_pfm: -151.70332791156252
episode: 16 training return: tensor(-79.7422, device='cuda:0')
episode: 17 training return: tensor(-84.0779, device='cuda:0')
episode: 18 training return: tensor(-146.0439, device='cuda:0')
episode: 19 training return: tensor(-77.4664, device='cuda:0')
epoch: 5 test_true_pfm: 79.6054459850576 sim_pfm: -141.47612782224897
episode: 20 training return: tensor(-179.0354, device='cuda:0')
episode: 21 training return: tensor(-80.1071, device='cuda:0')
episode: 22 training return: tensor(-178.7231, device='cuda:0')
episode: 23 training return: tensor(-93.9408, device='cuda:0')
epoch: 6 test_true_pfm: 66.13568430103619 sim_pfm: -124.43909507390345
episode: 24 training return: tensor(-190.6541, device='cuda:0')
episode: 25 training return: tensor(-92.3500, device='cuda:0')
episode: 26 training return: tensor(-199.8567, device='cuda:0')
episode: 27 training return: tensor(-192.3066, device='cuda:0')
epoch: 7 test_true_pfm: 73.25777094587966 sim_pfm: -173.67242894420633
episode: 28 training return: tensor(-90.4248, device='cuda:0')
episode: 29 training return: tensor(-105.0835, device='cuda:0')
episode: 30 training return: tensor(-82.1746, device='cuda:0')
episode: 31 training return: tensor(-97.0753, device='cuda:0')
epoch: 8 test_true_pfm: 65.85688598813203 sim_pfm: -125.02984765802394
episode: 32 training return: tensor(-76.3189, device='cuda:0')
episode: 33 training return: tensor(-172.9044, device='cuda:0')
episode: 34 training return: tensor(-186.2453, device='cuda:0')
episode: 35 training return: tensor(-160.4465, device='cuda:0')
epoch: 9 test_true_pfm: 47.37875509342483 sim_pfm: -125.29946231285575
episode: 36 training return: tensor(-170.6482, device='cuda:0')
episode: 37 training return: tensor(-171.0908, device='cuda:0')
episode: 38 training return: tensor(-171.9911, device='cuda:0')
episode: 39 training return: tensor(-90.9734, device='cuda:0')
epoch: 10 test_true_pfm: 65.58341888413601 sim_pfm: -126.64538854517741
episode: 40 training return: tensor(-161.9362, device='cuda:0')
episode: 41 training return: tensor(-76.3221, device='cuda:0')
episode: 42 training return: tensor(-86.9866, device='cuda:0')
episode: 43 training return: tensor(-104.4907, device='cuda:0')
epoch: 11 test_true_pfm: 56.112467106407486 sim_pfm: -151.6322923733096
episode: 44 training return: tensor(-173.8677, device='cuda:0')
episode: 45 training return: tensor(-138.9934, device='cuda:0')
episode: 46 training return: tensor(-114.3481, device='cuda:0')
episode: 47 training return: tensor(-121.1906, device='cuda:0')
epoch: 12 test_true_pfm: 54.94587114175145 sim_pfm: -160.793036332872
episode: 48 training return: tensor(-63.9458, device='cuda:0')
episode: 49 training return: tensor(-182.0252, device='cuda:0')
episode: 50 training return: tensor(-93.4571, device='cuda:0')
episode: 51 training return: tensor(-180.3563, device='cuda:0')
epoch: 13 test_true_pfm: 51.50838176643485 sim_pfm: -158.1191888645466
episode: 52 training return: tensor(-149.9562, device='cuda:0')
episode: 53 training return: tensor(-151.3309, device='cuda:0')
episode: 54 training return: tensor(-185.6370, device='cuda:0')
episode: 55 training return: tensor(-71.4743, device='cuda:0')
epoch: 14 test_true_pfm: 66.79801495159927 sim_pfm: -160.8833813668054
episode: 56 training return: tensor(-77.4542, device='cuda:0')
episode: 57 training return: tensor(-74.0886, device='cuda:0')
episode: 58 training return: tensor(-160.7547, device='cuda:0')
episode: 59 training return: tensor(-152.3089, device='cuda:0')
epoch: 15 test_true_pfm: 56.87304864030558 sim_pfm: -151.05714478491572
episode: 60 training return: tensor(-81.2874, device='cuda:0')
episode: 61 training return: tensor(-108.5249, device='cuda:0')
episode: 62 training return: tensor(-181.2851, device='cuda:0')
episode: 63 training return: tensor(-122.7840, device='cuda:0')
epoch: 16 test_true_pfm: 58.72338237068893 sim_pfm: -149.90454094576415
episode: 64 training return: tensor(-154.5355, device='cuda:0')
episode: 65 training return: tensor(-175.8720, device='cuda:0')
episode: 66 training return: tensor(-139.6089, device='cuda:0')
episode: 67 training return: tensor(-188.6128, device='cuda:0')
epoch: 17 test_true_pfm: 47.96212737761233 sim_pfm: -175.41248952804017
episode: 68 training return: tensor(-125.4725, device='cuda:0')
episode: 69 training return: tensor(-190.3322, device='cuda:0')
episode: 70 training return: tensor(-151.9797, device='cuda:0')
episode: 71 training return: tensor(-73.3137, device='cuda:0')
epoch: 18 test_true_pfm: 60.399788889345515 sim_pfm: -129.40507042894606
episode: 72 training return: tensor(-173.6342, device='cuda:0')
episode: 73 training return: tensor(-88.1030, device='cuda:0')
episode: 74 training return: tensor(-86.0238, device='cuda:0')
episode: 75 training return: tensor(-200.4013, device='cuda:0')
epoch: 19 test_true_pfm: 70.61659868992976 sim_pfm: -70.56405629907385
episode: 76 training return: tensor(-98.0756, device='cuda:0')
episode: 77 training return: tensor(-121.1497, device='cuda:0')
episode: 78 training return: tensor(-160.3042, device='cuda:0')
episode: 79 training return: tensor(-162.7640, device='cuda:0')
epoch: 20 test_true_pfm: 65.21122691299453 sim_pfm: -83.30927724210778
episode: 80 training return: tensor(-149.6307, device='cuda:0')
episode: 81 training return: tensor(-166.3890, device='cuda:0')
episode: 82 training return: tensor(-146.1339, device='cuda:0')
episode: 83 training return: tensor(-83.1386, device='cuda:0')
epoch: 21 test_true_pfm: 73.97726014839489 sim_pfm: -94.60195600102888
episode: 84 training return: tensor(-100.2359, device='cuda:0')
episode: 85 training return: tensor(-149.9584, device='cuda:0')
episode: 86 training return: tensor(-76.5036, device='cuda:0')
episode: 87 training return: tensor(-97.8508, device='cuda:0')
epoch: 22 test_true_pfm: 68.49868571489527 sim_pfm: -138.1639183486812
episode: 88 training return: tensor(-84.9520, device='cuda:0')
episode: 89 training return: tensor(-74.7440, device='cuda:0')
episode: 90 training return: tensor(-77.7995, device='cuda:0')
episode: 91 training return: tensor(-122.3332, device='cuda:0')
epoch: 23 test_true_pfm: 75.43116669905217 sim_pfm: -128.02905454270658
episode: 92 training return: tensor(-151.8595, device='cuda:0')
episode: 93 training return: tensor(-79.4587, device='cuda:0')
episode: 94 training return: tensor(-157.0702, device='cuda:0')
episode: 95 training return: tensor(-155.8843, device='cuda:0')
epoch: 24 test_true_pfm: 76.86900244152346 sim_pfm: -118.58814751337631
episode: 96 training return: tensor(-150.6067, device='cuda:0')
episode: 97 training return: tensor(-83.4549, device='cuda:0')
episode: 98 training return: tensor(-98.8465, device='cuda:0')
episode: 99 training return: tensor(-115.9067, device='cuda:0')
epoch: 25 test_true_pfm: 75.3621446725289 sim_pfm: -102.35285804870072
episode: 100 training return: tensor(-165.1361, device='cuda:0')
episode: 101 training return: tensor(-99.0319, device='cuda:0')
episode: 102 training return: tensor(-143.4695, device='cuda:0')
episode: 103 training return: tensor(-153.0589, device='cuda:0')
epoch: 26 test_true_pfm: 74.50291421749986 sim_pfm: -110.14259104332305
episode: 104 training return: tensor(-95.4730, device='cuda:0')
episode: 105 training return: tensor(-150.0952, device='cuda:0')
episode: 106 training return: tensor(-79.9405, device='cuda:0')
episode: 107 training return: tensor(-137.5995, device='cuda:0')
epoch: 27 test_true_pfm: 79.42306681463376 sim_pfm: -125.87797583884677
episode: 108 training return: tensor(-37.2935, device='cuda:0')
episode: 109 training return: tensor(-147.8166, device='cuda:0')
episode: 110 training return: tensor(-150.9108, device='cuda:0')
episode: 111 training return: tensor(-160.4501, device='cuda:0')
epoch: 28 test_true_pfm: 75.14769909910869 sim_pfm: -118.38502019975567
episode: 112 training return: tensor(-157.0469, device='cuda:0')
episode: 113 training return: tensor(-72.9868, device='cuda:0')
episode: 114 training return: tensor(-142.2740, device='cuda:0')
episode: 115 training return: tensor(-76.9967, device='cuda:0')
epoch: 29 test_true_pfm: 78.78998861854132 sim_pfm: -138.23507607502398
episode: 116 training return: tensor(-64.0940, device='cuda:0')
episode: 117 training return: tensor(-77.3865, device='cuda:0')
episode: 118 training return: tensor(-61.9834, device='cuda:0')
episode: 119 training return: tensor(-144.8597, device='cuda:0')
epoch: 30 test_true_pfm: 62.49066732576834 sim_pfm: -97.85071530298447
episode: 120 training return: tensor(-143.7672, device='cuda:0')
episode: 121 training return: tensor(-77.3727, device='cuda:0')
episode: 122 training return: tensor(-83.1932, device='cuda:0')
episode: 123 training return: tensor(-24.7331, device='cuda:0')
epoch: 31 test_true_pfm: 81.14003816737684 sim_pfm: -97.50058352397755
episode: 124 training return: tensor(-72.7577, device='cuda:0')
episode: 125 training return: tensor(-77.6469, device='cuda:0')
episode: 126 training return: tensor(-86.2471, device='cuda:0')
episode: 127 training return: tensor(-45.9313, device='cuda:0')
epoch: 32 test_true_pfm: 74.54061780677975 sim_pfm: -117.9981790055288
episode: 128 training return: tensor(-57.4172, device='cuda:0')
episode: 129 training return: tensor(-78.6856, device='cuda:0')
episode: 130 training return: tensor(-80.7019, device='cuda:0')
episode: 131 training return: tensor(-150.8138, device='cuda:0')
epoch: 33 test_true_pfm: 73.75280329382447 sim_pfm: -146.60865872371943
episode: 132 training return: tensor(-131.4643, device='cuda:0')
episode: 133 training return: tensor(-134.2112, device='cuda:0')
episode: 134 training return: tensor(-129.6260, device='cuda:0')
episode: 135 training return: tensor(-68.6496, device='cuda:0')
epoch: 34 test_true_pfm: 73.1222608398889 sim_pfm: -88.37134686273639
episode: 136 training return: tensor(-139.3163, device='cuda:0')
episode: 137 training return: tensor(-157.1380, device='cuda:0')
episode: 138 training return: tensor(-72.6617, device='cuda:0')
episode: 139 training return: tensor(-87.9917, device='cuda:0')
epoch: 35 test_true_pfm: 82.6804029599256 sim_pfm: -114.57093287967727
episode: 140 training return: tensor(-126.9219, device='cuda:0')
episode: 141 training return: tensor(-68.7052, device='cuda:0')
episode: 142 training return: tensor(-158.9311, device='cuda:0')
episode: 143 training return: tensor(-155.7027, device='cuda:0')
epoch: 36 test_true_pfm: 79.0238084531253 sim_pfm: -110.32834017049171
episode: 144 training return: tensor(-127.1686, device='cuda:0')
episode: 145 training return: tensor(-78.5339, device='cuda:0')
episode: 146 training return: tensor(-135.6305, device='cuda:0')
episode: 147 training return: tensor(-147.0009, device='cuda:0')
epoch: 37 test_true_pfm: 56.966119236503005 sim_pfm: -140.11085499664188
episode: 148 training return: tensor(-152.7264, device='cuda:0')
episode: 149 training return: tensor(-156.6276, device='cuda:0')
episode: 150 training return: tensor(-84.1583, device='cuda:0')
episode: 151 training return: tensor(-125.1553, device='cuda:0')
epoch: 38 test_true_pfm: 64.33742061520552 sim_pfm: -126.5527285075048
episode: 152 training return: tensor(-154.8955, device='cuda:0')
episode: 153 training return: tensor(-84.5547, device='cuda:0')
episode: 154 training return: tensor(-127.5317, device='cuda:0')
episode: 155 training return: tensor(-144.2901, device='cuda:0')
epoch: 39 test_true_pfm: 67.45757309821155 sim_pfm: -116.58841588970972
episode: 156 training return: tensor(-153.7798, device='cuda:0')
episode: 157 training return: tensor(-162.0683, device='cuda:0')
episode: 158 training return: tensor(-83.1461, device='cuda:0')
episode: 159 training return: tensor(-81.4309, device='cuda:0')
epoch: 40 test_true_pfm: 52.779317052604895 sim_pfm: -101.71152993168216
episode: 160 training return: tensor(-52.8866, device='cuda:0')
episode: 161 training return: tensor(-118.6753, device='cuda:0')
episode: 162 training return: tensor(-85.2359, device='cuda:0')
episode: 163 training return: tensor(-88.6674, device='cuda:0')
epoch: 41 test_true_pfm: 66.18054729878739 sim_pfm: -131.51098740241724
episode: 164 training return: tensor(-73.4385, device='cuda:0')
episode: 165 training return: tensor(-66.3537, device='cuda:0')
episode: 166 training return: tensor(-74.2123, device='cuda:0')
episode: 167 training return: tensor(-74.7758, device='cuda:0')
epoch: 42 test_true_pfm: 75.09572400526676 sim_pfm: -99.85765768980491
episode: 168 training return: tensor(-82.8876, device='cuda:0')
episode: 169 training return: tensor(-79.7232, device='cuda:0')
episode: 170 training return: tensor(-145.8330, device='cuda:0')
episode: 171 training return: tensor(-93.6223, device='cuda:0')
epoch: 43 test_true_pfm: 67.77069431786678 sim_pfm: -118.65962794953376
episode: 172 training return: tensor(-139.3536, device='cuda:0')
episode: 173 training return: tensor(-145.2978, device='cuda:0')
episode: 174 training return: tensor(-71.7106, device='cuda:0')
episode: 175 training return: tensor(-72.7071, device='cuda:0')
epoch: 44 test_true_pfm: 76.0292542085764 sim_pfm: -122.54106633599149
episode: 176 training return: tensor(-77.3514, device='cuda:0')
episode: 177 training return: tensor(-157.0725, device='cuda:0')
episode: 178 training return: tensor(-114.2262, device='cuda:0')
episode: 179 training return: tensor(-89.8887, device='cuda:0')
epoch: 45 test_true_pfm: 81.72522668865113 sim_pfm: -107.49365869340836
episode: 180 training return: tensor(-151.9769, device='cuda:0')
episode: 181 training return: tensor(-53.1108, device='cuda:0')
episode: 182 training return: tensor(-118.5477, device='cuda:0')
episode: 183 training return: tensor(-134.2442, device='cuda:0')
epoch: 46 test_true_pfm: 79.11610339032136 sim_pfm: -94.9752117912576
episode: 184 training return: tensor(-149.3221, device='cuda:0')
episode: 185 training return: tensor(-148.8407, device='cuda:0')
episode: 186 training return: tensor(-75.0104, device='cuda:0')
episode: 187 training return: tensor(-151.6704, device='cuda:0')
epoch: 47 test_true_pfm: 71.7432846064312 sim_pfm: -75.31911562683527
episode: 188 training return: tensor(-97.0049, device='cuda:0')
episode: 189 training return: tensor(-98.4206, device='cuda:0')
episode: 190 training return: tensor(-136.8511, device='cuda:0')
episode: 191 training return: tensor(-147.0915, device='cuda:0')
epoch: 48 test_true_pfm: 69.50090584976061 sim_pfm: -106.12643872578629
episode: 192 training return: tensor(-70.6697, device='cuda:0')
episode: 193 training return: tensor(-89.4471, device='cuda:0')
episode: 194 training return: tensor(-144.9398, device='cuda:0')
episode: 195 training return: tensor(-70.1025, device='cuda:0')
epoch: 49 test_true_pfm: 83.75728851087192 sim_pfm: -99.44703221494565
episode: 196 training return: tensor(-86.5594, device='cuda:0')
episode: 197 training return: tensor(-65.4109, device='cuda:0')
episode: 198 training return: tensor(-150.1485, device='cuda:0')
episode: 199 training return: tensor(-74.0072, device='cuda:0')
epoch: 50 test_true_pfm: 76.47731927115362 sim_pfm: -103.7615361678938
episode: 200 training return: tensor(-128.8868, device='cuda:0')
episode: 201 training return: tensor(-131.9536, device='cuda:0')
episode: 202 training return: tensor(-138.6561, device='cuda:0')
episode: 203 training return: tensor(-129.6727, device='cuda:0')
epoch: 51 test_true_pfm: 80.19440444845202 sim_pfm: -79.95038986409782
episode: 204 training return: tensor(-74.0709, device='cuda:0')
episode: 205 training return: tensor(-155.9029, device='cuda:0')
episode: 206 training return: tensor(-158.0242, device='cuda:0')
episode: 207 training return: tensor(-151.4064, device='cuda:0')
epoch: 52 test_true_pfm: 72.17065187305586 sim_pfm: -117.31103991818964
episode: 208 training return: tensor(-147.2662, device='cuda:0')
episode: 209 training return: tensor(-156.9204, device='cuda:0')
episode: 210 training return: tensor(-79.6283, device='cuda:0')
episode: 211 training return: tensor(-68.4378, device='cuda:0')
epoch: 53 test_true_pfm: 70.91769341910988 sim_pfm: -112.73905517338426
episode: 212 training return: tensor(-74.7974, device='cuda:0')
episode: 213 training return: tensor(-142.9311, device='cuda:0')
episode: 214 training return: tensor(-93.5769, device='cuda:0')
episode: 215 training return: tensor(-66.5417, device='cuda:0')
epoch: 54 test_true_pfm: 77.49407341091573 sim_pfm: -87.24183606570587
episode: 216 training return: tensor(-113.7026, device='cuda:0')
episode: 217 training return: tensor(-149.8817, device='cuda:0')
episode: 218 training return: tensor(-178.8915, device='cuda:0')
episode: 219 training return: tensor(-122.7808, device='cuda:0')
epoch: 55 test_true_pfm: 73.86853412321587 sim_pfm: -102.7033295986068
episode: 220 training return: tensor(-86.5999, device='cuda:0')
episode: 221 training return: tensor(-125.3497, device='cuda:0')
episode: 222 training return: tensor(-87.4237, device='cuda:0')
episode: 223 training return: tensor(-84.9568, device='cuda:0')
epoch: 56 test_true_pfm: 79.64130770725372 sim_pfm: -92.0885951211967
episode: 224 training return: tensor(-150.0010, device='cuda:0')
episode: 225 training return: tensor(-74.2598, device='cuda:0')
episode: 226 training return: tensor(-70.3470, device='cuda:0')
episode: 227 training return: tensor(-144.4938, device='cuda:0')
epoch: 57 test_true_pfm: 72.33592995601602 sim_pfm: -103.12326575824409
episode: 228 training return: tensor(-155.0787, device='cuda:0')
episode: 229 training return: tensor(-134.9861, device='cuda:0')
episode: 230 training return: tensor(-77.4127, device='cuda:0')
episode: 231 training return: tensor(-68.3786, device='cuda:0')
epoch: 58 test_true_pfm: 63.62419290524035 sim_pfm: -104.855618923367
episode: 232 training return: tensor(-137.3294, device='cuda:0')
episode: 233 training return: tensor(-62.0354, device='cuda:0')
episode: 234 training return: tensor(-68.8549, device='cuda:0')
episode: 235 training return: tensor(-87.1259, device='cuda:0')
epoch: 59 test_true_pfm: 53.136745294567184 sim_pfm: -112.8902292956016
episode: 236 training return: tensor(-139.9381, device='cuda:0')
episode: 237 training return: tensor(-71.3417, device='cuda:0')
episode: 238 training return: tensor(-150.5339, device='cuda:0')
episode: 239 training return: tensor(-89.0354, device='cuda:0')
epoch: 60 test_true_pfm: 61.77715582473259 sim_pfm: -124.43431665546377
episode: 240 training return: tensor(-172.3049, device='cuda:0')
episode: 241 training return: tensor(-71.2996, device='cuda:0')
episode: 242 training return: tensor(-140.9716, device='cuda:0')
episode: 243 training return: tensor(-68.9343, device='cuda:0')
epoch: 61 test_true_pfm: 69.0440625597008 sim_pfm: -83.08553193845437
episode: 244 training return: tensor(-83.0402, device='cuda:0')
episode: 245 training return: tensor(-82.7397, device='cuda:0')
episode: 246 training return: tensor(-75.9144, device='cuda:0')
episode: 247 training return: tensor(-139.6153, device='cuda:0')
epoch: 62 test_true_pfm: 62.69491520220841 sim_pfm: -117.99859274014598
episode: 248 training return: tensor(-130.6530, device='cuda:0')
episode: 249 training return: tensor(-168.8131, device='cuda:0')
episode: 250 training return: tensor(-160.3590, device='cuda:0')
episode: 251 training return: tensor(-140.8761, device='cuda:0')
epoch: 63 test_true_pfm: 77.0993146177861 sim_pfm: -98.18022336359135
episode: 252 training return: tensor(-154.1246, device='cuda:0')
episode: 253 training return: tensor(-71.9900, device='cuda:0')
episode: 254 training return: tensor(-76.8267, device='cuda:0')
episode: 255 training return: tensor(-93.0560, device='cuda:0')
epoch: 64 test_true_pfm: 81.99355344984546 sim_pfm: -108.02961464907858
episode: 256 training return: tensor(-74.6137, device='cuda:0')
episode: 257 training return: tensor(-65.2880, device='cuda:0')
episode: 258 training return: tensor(-71.3087, device='cuda:0')
episode: 259 training return: tensor(-135.6285, device='cuda:0')
epoch: 65 test_true_pfm: 78.38842441835698 sim_pfm: -95.40081008157577
episode: 260 training return: tensor(-94.7069, device='cuda:0')
episode: 261 training return: tensor(-56.1377, device='cuda:0')
episode: 262 training return: tensor(-134.8439, device='cuda:0')
episode: 263 training return: tensor(-86.8906, device='cuda:0')
epoch: 66 test_true_pfm: 66.98384603405002 sim_pfm: -119.22787348109996
episode: 264 training return: tensor(-103.8640, device='cuda:0')
episode: 265 training return: tensor(-143.0817, device='cuda:0')
episode: 266 training return: tensor(-128.7736, device='cuda:0')
episode: 267 training return: tensor(-167.0293, device='cuda:0')
epoch: 67 test_true_pfm: 69.50870552330073 sim_pfm: -110.76923076871898
episode: 268 training return: tensor(-120.8324, device='cuda:0')
episode: 269 training return: tensor(-143.3054, device='cuda:0')
episode: 270 training return: tensor(-157.8000, device='cuda:0')
episode: 271 training return: tensor(-120.2584, device='cuda:0')
epoch: 68 test_true_pfm: 68.99623825350245 sim_pfm: -98.76299074562849
episode: 272 training return: tensor(-149.7782, device='cuda:0')
episode: 273 training return: tensor(-100.4913, device='cuda:0')
episode: 274 training return: tensor(-81.6664, device='cuda:0')
episode: 275 training return: tensor(-154.2012, device='cuda:0')
epoch: 69 test_true_pfm: 80.85113497414585 sim_pfm: -104.08622656213701
episode: 276 training return: tensor(-77.1723, device='cuda:0')
episode: 277 training return: tensor(-74.4307, device='cuda:0')
episode: 278 training return: tensor(-59.6201, device='cuda:0')
episode: 279 training return: tensor(-149.9854, device='cuda:0')
epoch: 70 test_true_pfm: 74.78769181831316 sim_pfm: -79.5520659480535
episode: 280 training return: tensor(-147.1299, device='cuda:0')
episode: 281 training return: tensor(-74.9307, device='cuda:0')
episode: 282 training return: tensor(-80.6947, device='cuda:0')
episode: 283 training return: tensor(-61.7394, device='cuda:0')
epoch: 71 test_true_pfm: 80.81847984247722 sim_pfm: -109.4510807949584
episode: 284 training return: tensor(-127.2722, device='cuda:0')
episode: 285 training return: tensor(-147.6664, device='cuda:0')
episode: 286 training return: tensor(-130.6749, device='cuda:0')
episode: 287 training return: tensor(-132.8082, device='cuda:0')
epoch: 72 test_true_pfm: 59.73029772889845 sim_pfm: -98.0729125715443
episode: 288 training return: tensor(-95.7117, device='cuda:0')
episode: 289 training return: tensor(-89.8477, device='cuda:0')
episode: 290 training return: tensor(-80.3461, device='cuda:0')
episode: 291 training return: tensor(-151.3333, device='cuda:0')
epoch: 73 test_true_pfm: 70.7170039702084 sim_pfm: -118.69625155564282
episode: 292 training return: tensor(-140.1022, device='cuda:0')
episode: 293 training return: tensor(-141.4215, device='cuda:0')
episode: 294 training return: tensor(-99.2296, device='cuda:0')
episode: 295 training return: tensor(-91.2924, device='cuda:0')
epoch: 74 test_true_pfm: 57.93546587964894 sim_pfm: -109.67510547210695
episode: 296 training return: tensor(-123.7132, device='cuda:0')
episode: 297 training return: tensor(-147.3010, device='cuda:0')
episode: 298 training return: tensor(-62.4376, device='cuda:0')
episode: 299 training return: tensor(-73.9808, device='cuda:0')
epoch: 75 test_true_pfm: 73.18175049864175 sim_pfm: -95.314188584988
episode: 300 training return: tensor(-78.0686, device='cuda:0')
episode: 301 training return: tensor(-50.3337, device='cuda:0')
episode: 302 training return: tensor(-142.4019, device='cuda:0')
episode: 303 training return: tensor(-162.8941, device='cuda:0')
epoch: 76 test_true_pfm: 65.81799266297192 sim_pfm: -84.67857496006181
episode: 304 training return: tensor(-146.2500, device='cuda:0')
episode: 305 training return: tensor(-62.3368, device='cuda:0')
episode: 306 training return: tensor(-125.1420, device='cuda:0')
episode: 307 training return: tensor(-94.3863, device='cuda:0')
epoch: 77 test_true_pfm: 76.90144909592725 sim_pfm: -74.5676553000987
episode: 308 training return: tensor(-57.3693, device='cuda:0')
episode: 309 training return: tensor(-62.0656, device='cuda:0')
episode: 310 training return: tensor(-64.8901, device='cuda:0')
episode: 311 training return: tensor(-69.2711, device='cuda:0')
epoch: 78 test_true_pfm: 67.32349490692724 sim_pfm: -101.16835462243762
episode: 312 training return: tensor(-149.7303, device='cuda:0')
episode: 313 training return: tensor(-73.3784, device='cuda:0')
episode: 314 training return: tensor(-138.7757, device='cuda:0')
episode: 315 training return: tensor(-63.3271, device='cuda:0')
epoch: 79 test_true_pfm: 75.04963635006848 sim_pfm: -107.38624308535364
episode: 316 training return: tensor(-122.2224, device='cuda:0')
episode: 317 training return: tensor(-148.4284, device='cuda:0')
episode: 318 training return: tensor(-135.7513, device='cuda:0')
episode: 319 training return: tensor(-66.1522, device='cuda:0')
epoch: 80 test_true_pfm: 76.30558922197028 sim_pfm: -91.67642320774613
episode: 320 training return: tensor(-49.0958, device='cuda:0')
episode: 321 training return: tensor(-138.0625, device='cuda:0')
episode: 322 training return: tensor(-129.4539, device='cuda:0')
episode: 323 training return: tensor(-67.0744, device='cuda:0')
epoch: 81 test_true_pfm: 81.85165224660231 sim_pfm: -98.10716868858435
episode: 324 training return: tensor(-75.4160, device='cuda:0')
episode: 325 training return: tensor(-60.8950, device='cuda:0')
episode: 326 training return: tensor(-77.2179, device='cuda:0')
episode: 327 training return: tensor(-83.6055, device='cuda:0')
epoch: 82 test_true_pfm: 68.01594939440608 sim_pfm: -96.81155766363955
episode: 328 training return: tensor(-55.2460, device='cuda:0')
episode: 329 training return: tensor(-132.5436, device='cuda:0')
episode: 330 training return: tensor(-73.2001, device='cuda:0')
episode: 331 training return: tensor(-59.5429, device='cuda:0')
epoch: 83 test_true_pfm: 56.541142642728474 sim_pfm: -142.2165670167189
episode: 332 training return: tensor(-125.9603, device='cuda:0')
episode: 333 training return: tensor(-126.8879, device='cuda:0')
episode: 334 training return: tensor(-92.4704, device='cuda:0')
episode: 335 training return: tensor(-131.4011, device='cuda:0')
epoch: 84 test_true_pfm: 73.88155546534647 sim_pfm: -105.61876075742767
episode: 336 training return: tensor(-58.4317, device='cuda:0')
episode: 337 training return: tensor(-83.6818, device='cuda:0')
episode: 338 training return: tensor(-77.6352, device='cuda:0')
episode: 339 training return: tensor(-103.9677, device='cuda:0')
epoch: 85 test_true_pfm: 72.28276964302458 sim_pfm: -121.37016491988325
episode: 340 training return: tensor(-72.4797, device='cuda:0')
episode: 341 training return: tensor(-136.3559, device='cuda:0')
episode: 342 training return: tensor(-125.6923, device='cuda:0')
episode: 343 training return: tensor(-177.4900, device='cuda:0')
epoch: 86 test_true_pfm: 65.04800808049322 sim_pfm: -77.303786032059
episode: 344 training return: tensor(-56.8632, device='cuda:0')
episode: 345 training return: tensor(-66.0918, device='cuda:0')
episode: 346 training return: tensor(-55.7517, device='cuda:0')
episode: 347 training return: tensor(-180.2743, device='cuda:0')
epoch: 87 test_true_pfm: 60.602091780604084 sim_pfm: -107.24963340868707
episode: 348 training return: tensor(-132.9180, device='cuda:0')
episode: 349 training return: tensor(-64.7354, device='cuda:0')
episode: 350 training return: tensor(-178.9606, device='cuda:0')
episode: 351 training return: tensor(-178.6052, device='cuda:0')
epoch: 88 test_true_pfm: 64.91003249370178 sim_pfm: -140.21383907067357
episode: 352 training return: tensor(-62.7387, device='cuda:0')
episode: 353 training return: tensor(-186.3017, device='cuda:0')
episode: 354 training return: tensor(-131.3482, device='cuda:0')
episode: 355 training return: tensor(-145.5196, device='cuda:0')
epoch: 89 test_true_pfm: 79.4046055738334 sim_pfm: -108.32167054075398
episode: 356 training return: tensor(-130.9785, device='cuda:0')
episode: 357 training return: tensor(-115.2436, device='cuda:0')
episode: 358 training return: tensor(-180.8788, device='cuda:0')
episode: 359 training return: tensor(-62.1796, device='cuda:0')
epoch: 90 test_true_pfm: 83.42243763918513 sim_pfm: -91.9680015830323
episode: 360 training return: tensor(-95.8920, device='cuda:0')
episode: 361 training return: tensor(-75.1918, device='cuda:0')
episode: 362 training return: tensor(-149.4845, device='cuda:0')
episode: 363 training return: tensor(-123.0796, device='cuda:0')
epoch: 91 test_true_pfm: 76.0939822672474 sim_pfm: -84.11302011821536
episode: 364 training return: tensor(-74.6436, device='cuda:0')
episode: 365 training return: tensor(-123.4850, device='cuda:0')
episode: 366 training return: tensor(-68.3160, device='cuda:0')
episode: 367 training return: tensor(-82.5687, device='cuda:0')
epoch: 92 test_true_pfm: 89.78653940298737 sim_pfm: -102.55709351892001
episode: 368 training return: tensor(-88.3759, device='cuda:0')
episode: 369 training return: tensor(-65.5690, device='cuda:0')
episode: 370 training return: tensor(-118.8248, device='cuda:0')
episode: 371 training return: tensor(-59.2760, device='cuda:0')
epoch: 93 test_true_pfm: 71.20551680225476 sim_pfm: -96.28973077987321
episode: 372 training return: tensor(-145.1817, device='cuda:0')
episode: 373 training return: tensor(-125.1183, device='cuda:0')
episode: 374 training return: tensor(-67.6834, device='cuda:0')
episode: 375 training return: tensor(-130.9116, device='cuda:0')
epoch: 94 test_true_pfm: 63.921368292877446 sim_pfm: -119.92161183633725
episode: 376 training return: tensor(-143.5545, device='cuda:0')
episode: 377 training return: tensor(-129.3518, device='cuda:0')
episode: 378 training return: tensor(-150.0973, device='cuda:0')
episode: 379 training return: tensor(-154.5737, device='cuda:0')
epoch: 95 test_true_pfm: 77.8199582445716 sim_pfm: -114.18331792548997
episode: 380 training return: tensor(-70.3398, device='cuda:0')
episode: 381 training return: tensor(-138.7683, device='cuda:0')
episode: 382 training return: tensor(-136.7920, device='cuda:0')
episode: 383 training return: tensor(-65.4767, device='cuda:0')
epoch: 96 test_true_pfm: 68.31292284762252 sim_pfm: -99.07089491783991
episode: 384 training return: tensor(-132.8060, device='cuda:0')
episode: 385 training return: tensor(-76.1483, device='cuda:0')
episode: 386 training return: tensor(-51.5855, device='cuda:0')
episode: 387 training return: tensor(-64.5753, device='cuda:0')
epoch: 97 test_true_pfm: 80.11672077638306 sim_pfm: -137.0109516066499
episode: 388 training return: tensor(-142.2006, device='cuda:0')
episode: 389 training return: tensor(-68.8024, device='cuda:0')
episode: 390 training return: tensor(-63.3493, device='cuda:0')
episode: 391 training return: tensor(-73.4742, device='cuda:0')
epoch: 98 test_true_pfm: 60.98962502944096 sim_pfm: -151.28162955214503
episode: 392 training return: tensor(-124.6256, device='cuda:0')
episode: 393 training return: tensor(-137.4679, device='cuda:0')
episode: 394 training return: tensor(-83.0559, device='cuda:0')
episode: 395 training return: tensor(-157.9806, device='cuda:0')
epoch: 99 test_true_pfm: 84.00069372074329 sim_pfm: -100.93506869079428
episode: 396 training return: tensor(-72.2858, device='cuda:0')
episode: 397 training return: tensor(-138.1577, device='cuda:0')
episode: 398 training return: tensor(-129.6287, device='cuda:0')
episode: 399 training return: tensor(-136.8743, device='cuda:0')
epoch: 100 test_true_pfm: 72.1712351797896 sim_pfm: -99.7813295295462
episode: 400 training return: tensor(-97.1684, device='cuda:0')
episode: 401 training return: tensor(-134.2474, device='cuda:0')
episode: 402 training return: tensor(-95.9816, device='cuda:0')
episode: 403 training return: tensor(-63.1513, device='cuda:0')
epoch: 101 test_true_pfm: 61.815090490744566 sim_pfm: -102.32915777514572
episode: 404 training return: tensor(-127.4211, device='cuda:0')
episode: 405 training return: tensor(-102.3183, device='cuda:0')
episode: 406 training return: tensor(-55.5868, device='cuda:0')
episode: 407 training return: tensor(-66.5526, device='cuda:0')
epoch: 102 test_true_pfm: 68.5376439084574 sim_pfm: -119.35501874269684
episode: 408 training return: tensor(-71.6432, device='cuda:0')
episode: 409 training return: tensor(-57.6806, device='cuda:0')
episode: 410 training return: tensor(-178.8042, device='cuda:0')
episode: 411 training return: tensor(-130.7655, device='cuda:0')
epoch: 103 test_true_pfm: 50.50578542292958 sim_pfm: -161.79871749144513
episode: 412 training return: tensor(-130.5094, device='cuda:0')
episode: 413 training return: tensor(-141.5639, device='cuda:0')
episode: 414 training return: tensor(-83.8841, device='cuda:0')
episode: 415 training return: tensor(-159.1250, device='cuda:0')
epoch: 104 test_true_pfm: 69.83360801932625 sim_pfm: -81.62733118878677
episode: 416 training return: tensor(-164.0290, device='cuda:0')
episode: 417 training return: tensor(-118.3994, device='cuda:0')
episode: 418 training return: tensor(-73.8418, device='cuda:0')
episode: 419 training return: tensor(-64.8012, device='cuda:0')
epoch: 105 test_true_pfm: 82.73133501180283 sim_pfm: -113.49441547089373
episode: 420 training return: tensor(-138.0220, device='cuda:0')
episode: 421 training return: tensor(-132.2128, device='cuda:0')
episode: 422 training return: tensor(-64.7415, device='cuda:0')
episode: 423 training return: tensor(-133.1629, device='cuda:0')
epoch: 106 test_true_pfm: 76.47625056262127 sim_pfm: -93.02422450867016
episode: 424 training return: tensor(-88.7570, device='cuda:0')
episode: 425 training return: tensor(-107.1160, device='cuda:0')
episode: 426 training return: tensor(-58.0409, device='cuda:0')
episode: 427 training return: tensor(-122.6623, device='cuda:0')
epoch: 107 test_true_pfm: 72.29095101163065 sim_pfm: -108.92764940869529
episode: 428 training return: tensor(-129.3879, device='cuda:0')
episode: 429 training return: tensor(-118.9010, device='cuda:0')
episode: 430 training return: tensor(-134.0384, device='cuda:0')
episode: 431 training return: tensor(-122.9707, device='cuda:0')
epoch: 108 test_true_pfm: 66.846511238668 sim_pfm: -116.2847585427924
episode: 432 training return: tensor(-65.4107, device='cuda:0')
episode: 433 training return: tensor(-73.8214, device='cuda:0')
episode: 434 training return: tensor(-149.3814, device='cuda:0')
episode: 435 training return: tensor(-127.7235, device='cuda:0')
epoch: 109 test_true_pfm: 82.63609083150462 sim_pfm: -108.83905376798357
episode: 436 training return: tensor(-75.7068, device='cuda:0')
episode: 437 training return: tensor(-126.8006, device='cuda:0')
episode: 438 training return: tensor(-135.8746, device='cuda:0')
episode: 439 training return: tensor(-143.2702, device='cuda:0')
epoch: 110 test_true_pfm: 53.92315548858844 sim_pfm: -93.31756487225648
episode: 440 training return: tensor(-132.8025, device='cuda:0')
episode: 441 training return: tensor(-65.1738, device='cuda:0')
episode: 442 training return: tensor(-64.8292, device='cuda:0')
episode: 443 training return: tensor(-72.4353, device='cuda:0')
epoch: 111 test_true_pfm: 75.73085708514147 sim_pfm: -98.8257931037806
episode: 444 training return: tensor(-144.4873, device='cuda:0')
episode: 445 training return: tensor(-141.1564, device='cuda:0')
episode: 446 training return: tensor(-99.7314, device='cuda:0')
episode: 447 training return: tensor(-122.5109, device='cuda:0')
epoch: 112 test_true_pfm: 64.65919062122762 sim_pfm: -95.96430822698167
episode: 448 training return: tensor(-123.6371, device='cuda:0')
episode: 449 training return: tensor(-88.6289, device='cuda:0')
episode: 450 training return: tensor(-124.7970, device='cuda:0')
episode: 451 training return: tensor(-67.4275, device='cuda:0')
epoch: 113 test_true_pfm: 85.50264201913194 sim_pfm: -98.62844230136834
episode: 452 training return: tensor(-134.2200, device='cuda:0')
episode: 453 training return: tensor(-56.2994, device='cuda:0')
episode: 454 training return: tensor(-79.5903, device='cuda:0')
episode: 455 training return: tensor(-133.7187, device='cuda:0')
epoch: 114 test_true_pfm: 63.51414261034464 sim_pfm: -154.19251260229504
episode: 456 training return: tensor(-136.0860, device='cuda:0')
episode: 457 training return: tensor(-142.5316, device='cuda:0')
episode: 458 training return: tensor(-131.6835, device='cuda:0')
episode: 459 training return: tensor(-111.4223, device='cuda:0')
epoch: 115 test_true_pfm: 59.22508907257077 sim_pfm: -124.49882740026806
episode: 460 training return: tensor(-72.9837, device='cuda:0')
episode: 461 training return: tensor(-74.6747, device='cuda:0')
episode: 462 training return: tensor(-148.0010, device='cuda:0')
episode: 463 training return: tensor(-148.5065, device='cuda:0')
epoch: 116 test_true_pfm: 70.9577649157068 sim_pfm: -115.98772237183293
episode: 464 training return: tensor(-159.2089, device='cuda:0')
episode: 465 training return: tensor(-121.8954, device='cuda:0')
episode: 466 training return: tensor(-127.1050, device='cuda:0')
episode: 467 training return: tensor(-100.7727, device='cuda:0')
epoch: 117 test_true_pfm: 85.67374979458604 sim_pfm: -106.07182075816672
episode: 468 training return: tensor(-123.9550, device='cuda:0')
episode: 469 training return: tensor(-143.8424, device='cuda:0')
episode: 470 training return: tensor(-65.4695, device='cuda:0')
episode: 471 training return: tensor(-80.3444, device='cuda:0')
epoch: 118 test_true_pfm: 69.30344283480062 sim_pfm: -89.71172972714994
episode: 472 training return: tensor(-75.9930, device='cuda:0')
episode: 473 training return: tensor(-57.6515, device='cuda:0')
episode: 474 training return: tensor(-173.2135, device='cuda:0')
episode: 475 training return: tensor(-68.7960, device='cuda:0')
epoch: 119 test_true_pfm: 76.33336765502034 sim_pfm: -83.89198312649387
episode: 476 training return: tensor(-132.9471, device='cuda:0')
episode: 477 training return: tensor(-152.5787, device='cuda:0')
episode: 478 training return: tensor(-176.5208, device='cuda:0')
episode: 479 training return: tensor(-56.4916, device='cuda:0')
epoch: 120 test_true_pfm: 64.89985799022062 sim_pfm: -111.47202803344699
episode: 480 training return: tensor(-127.7610, device='cuda:0')
episode: 481 training return: tensor(-85.6332, device='cuda:0')
episode: 482 training return: tensor(-56.5493, device='cuda:0')
episode: 483 training return: tensor(-82.1007, device='cuda:0')
epoch: 121 test_true_pfm: 67.49124018110139 sim_pfm: -87.83475193082704
episode: 484 training return: tensor(-61.5090, device='cuda:0')
episode: 485 training return: tensor(-131.3493, device='cuda:0')
episode: 486 training return: tensor(-156.2222, device='cuda:0')
episode: 487 training return: tensor(-136.2639, device='cuda:0')
epoch: 122 test_true_pfm: 52.35005458852944 sim_pfm: -131.3101055820007
episode: 488 training return: tensor(-121.9080, device='cuda:0')
episode: 489 training return: tensor(-122.9106, device='cuda:0')
episode: 490 training return: tensor(-67.4883, device='cuda:0')
episode: 491 training return: tensor(-145.0620, device='cuda:0')
epoch: 123 test_true_pfm: 70.37764688744018 sim_pfm: -69.3128429840901
episode: 492 training return: tensor(-76.1433, device='cuda:0')
episode: 493 training return: tensor(-123.2500, device='cuda:0')
episode: 494 training return: tensor(-128.9240, device='cuda:0')
episode: 495 training return: tensor(-123.1129, device='cuda:0')
epoch: 124 test_true_pfm: 74.66379517856873 sim_pfm: -74.7505644339486
episode: 496 training return: tensor(-71.9214, device='cuda:0')
episode: 497 training return: tensor(-139.1862, device='cuda:0')
episode: 498 training return: tensor(-128.6873, device='cuda:0')
episode: 499 training return: tensor(-122.3997, device='cuda:0')
epoch: 125 test_true_pfm: 52.493485843271095 sim_pfm: -119.38232017655973
episode: 500 training return: tensor(-141.1858, device='cuda:0')
episode: 501 training return: tensor(-45.2994, device='cuda:0')
episode: 502 training return: tensor(-89.7013, device='cuda:0')
episode: 503 training return: tensor(-128.5576, device='cuda:0')
epoch: 126 test_true_pfm: 91.90189135715946 sim_pfm: -105.75575024053687
episode: 504 training return: tensor(-101.3158, device='cuda:0')
episode: 505 training return: tensor(-119.4405, device='cuda:0')
episode: 506 training return: tensor(-76.4410, device='cuda:0')
episode: 507 training return: tensor(-62.4948, device='cuda:0')
epoch: 127 test_true_pfm: 77.97385443766788 sim_pfm: -81.69534824144793
episode: 508 training return: tensor(-130.6913, device='cuda:0')
episode: 509 training return: tensor(-124.9823, device='cuda:0')
episode: 510 training return: tensor(-63.1692, device='cuda:0')
episode: 511 training return: tensor(-64.6662, device='cuda:0')
epoch: 128 test_true_pfm: 77.67816800793733 sim_pfm: -126.45128488230985
episode: 512 training return: tensor(-152.3745, device='cuda:0')
episode: 513 training return: tensor(-51.9601, device='cuda:0')
episode: 514 training return: tensor(-66.6633, device='cuda:0')
episode: 515 training return: tensor(-148.2012, device='cuda:0')
epoch: 129 test_true_pfm: 80.6784497723419 sim_pfm: -86.54537941812305
episode: 516 training return: tensor(-49.4687, device='cuda:0')
episode: 517 training return: tensor(-88.2184, device='cuda:0')
episode: 518 training return: tensor(-145.0661, device='cuda:0')
episode: 519 training return: tensor(-141.5780, device='cuda:0')
epoch: 130 test_true_pfm: 73.07015151178521 sim_pfm: -103.96099687607493
episode: 520 training return: tensor(-142.3214, device='cuda:0')
episode: 521 training return: tensor(-129.4458, device='cuda:0')
episode: 522 training return: tensor(-108.2662, device='cuda:0')
episode: 523 training return: tensor(-59.3087, device='cuda:0')
epoch: 131 test_true_pfm: 75.53150826722712 sim_pfm: -113.40786803056253
episode: 524 training return: tensor(-84.4201, device='cuda:0')
episode: 525 training return: tensor(-66.3700, device='cuda:0')
episode: 526 training return: tensor(-53.6781, device='cuda:0')
episode: 527 training return: tensor(-71.4801, device='cuda:0')
epoch: 132 test_true_pfm: 65.9737243855456 sim_pfm: -89.65079133968102
episode: 528 training return: tensor(-158.3234, device='cuda:0')
episode: 529 training return: tensor(-123.8363, device='cuda:0')
episode: 530 training return: tensor(-86.2777, device='cuda:0')
episode: 531 training return: tensor(-108.7102, device='cuda:0')
epoch: 133 test_true_pfm: 64.74151591243637 sim_pfm: -97.75009133396671
episode: 532 training return: tensor(-133.4294, device='cuda:0')
episode: 533 training return: tensor(-53.9561, device='cuda:0')
episode: 534 training return: tensor(-73.4727, device='cuda:0')
episode: 535 training return: tensor(-149.7784, device='cuda:0')
epoch: 134 test_true_pfm: 55.5984231375369 sim_pfm: -122.18764592570952
episode: 536 training return: tensor(-75.9819, device='cuda:0')
episode: 537 training return: tensor(-64.4939, device='cuda:0')
episode: 538 training return: tensor(-66.5995, device='cuda:0')
episode: 539 training return: tensor(-144.2256, device='cuda:0')
epoch: 135 test_true_pfm: 69.61290383611983 sim_pfm: -134.2185789917712
episode: 540 training return: tensor(-138.4452, device='cuda:0')
episode: 541 training return: tensor(-60.0258, device='cuda:0')
episode: 542 training return: tensor(-152.3131, device='cuda:0')
episode: 543 training return: tensor(-69.4609, device='cuda:0')
epoch: 136 test_true_pfm: 77.14717999924996 sim_pfm: -101.79854958585346
episode: 544 training return: tensor(-109.7714, device='cuda:0')
episode: 545 training return: tensor(-83.3428, device='cuda:0')
episode: 546 training return: tensor(-56.1806, device='cuda:0')
episode: 547 training return: tensor(-127.0091, device='cuda:0')
epoch: 137 test_true_pfm: 74.45870489953023 sim_pfm: -102.319378883217
episode: 548 training return: tensor(-142.7003, device='cuda:0')
episode: 549 training return: tensor(-108.1870, device='cuda:0')
episode: 550 training return: tensor(-122.1759, device='cuda:0')
episode: 551 training return: tensor(-92.9642, device='cuda:0')
epoch: 138 test_true_pfm: 85.53581081453076 sim_pfm: -94.93874342573108
episode: 552 training return: tensor(-45.9186, device='cuda:0')
episode: 553 training return: tensor(-73.0698, device='cuda:0')
episode: 554 training return: tensor(-166.2456, device='cuda:0')
episode: 555 training return: tensor(-125.2680, device='cuda:0')
epoch: 139 test_true_pfm: 71.04323799360353 sim_pfm: -125.43381720518228
episode: 556 training return: tensor(-49.4151, device='cuda:0')
episode: 557 training return: tensor(-135.9743, device='cuda:0')
episode: 558 training return: tensor(-60.0804, device='cuda:0')
episode: 559 training return: tensor(-110.8390, device='cuda:0')
epoch: 140 test_true_pfm: 54.65763224684923 sim_pfm: -103.15712163642165
episode: 560 training return: tensor(-65.8736, device='cuda:0')
episode: 561 training return: tensor(-67.9359, device='cuda:0')
episode: 562 training return: tensor(-177.2709, device='cuda:0')
episode: 563 training return: tensor(-155.7926, device='cuda:0')
epoch: 141 test_true_pfm: 57.14613170193981 sim_pfm: -124.27875534312334
episode: 564 training return: tensor(-134.1933, device='cuda:0')
episode: 565 training return: tensor(-68.8960, device='cuda:0')
episode: 566 training return: tensor(-121.0182, device='cuda:0')
episode: 567 training return: tensor(-191.2175, device='cuda:0')
epoch: 142 test_true_pfm: 71.92541322719727 sim_pfm: -100.36266974898754
episode: 568 training return: tensor(-125.7822, device='cuda:0')
episode: 569 training return: tensor(-133.8089, device='cuda:0')
episode: 570 training return: tensor(-69.0996, device='cuda:0')
episode: 571 training return: tensor(-125.3854, device='cuda:0')
epoch: 143 test_true_pfm: 82.19045774972649 sim_pfm: -104.82925554038374
episode: 572 training return: tensor(-90.3053, device='cuda:0')
episode: 573 training return: tensor(-89.4100, device='cuda:0')
episode: 574 training return: tensor(-114.9674, device='cuda:0')
episode: 575 training return: tensor(-158.0575, device='cuda:0')
epoch: 144 test_true_pfm: 82.14284337345275 sim_pfm: -94.10216153318179
episode: 576 training return: tensor(-135.8245, device='cuda:0')
episode: 577 training return: tensor(-130.4784, device='cuda:0')
episode: 578 training return: tensor(-110.9481, device='cuda:0')
episode: 579 training return: tensor(-175.6679, device='cuda:0')
epoch: 145 test_true_pfm: 82.48832116113434 sim_pfm: -118.12429033744266
episode: 580 training return: tensor(-71.3137, device='cuda:0')
episode: 581 training return: tensor(-126.7519, device='cuda:0')
episode: 582 training return: tensor(-140.0809, device='cuda:0')
episode: 583 training return: tensor(-126.4456, device='cuda:0')
epoch: 146 test_true_pfm: 63.11370436214222 sim_pfm: -130.54123761551455
episode: 584 training return: tensor(-137.6731, device='cuda:0')
episode: 585 training return: tensor(-141.1233, device='cuda:0')
episode: 586 training return: tensor(-87.2820, device='cuda:0')
episode: 587 training return: tensor(-75.1515, device='cuda:0')
epoch: 147 test_true_pfm: 78.61091230958765 sim_pfm: -83.83588404209586
episode: 588 training return: tensor(-75.7691, device='cuda:0')
episode: 589 training return: tensor(-60.7831, device='cuda:0')
episode: 590 training return: tensor(-128.0427, device='cuda:0')
episode: 591 training return: tensor(-155.1542, device='cuda:0')
epoch: 148 test_true_pfm: 60.00763477144396 sim_pfm: -114.29785742540261
episode: 592 training return: tensor(-72.8805, device='cuda:0')
episode: 593 training return: tensor(-76.5699, device='cuda:0')
episode: 594 training return: tensor(-120.9262, device='cuda:0')
episode: 595 training return: tensor(-177.3975, device='cuda:0')
epoch: 149 test_true_pfm: 61.60992634591754 sim_pfm: -110.04569137340295
episode: 596 training return: tensor(-122.0199, device='cuda:0')
episode: 597 training return: tensor(-80.4345, device='cuda:0')
episode: 598 training return: tensor(-180.3372, device='cuda:0')
episode: 599 training return: tensor(-126.8118, device='cuda:0')
epoch: 150 test_true_pfm: 91.79889658496839 sim_pfm: -139.4682953015901
