['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '2']
epoch: 0 training_loss 0.4178093099594116 test_loss: 0.3237724304199219
epoch: 1 training_loss 0.30234852820634844 test_loss: 0.25831894874572753
epoch: 2 training_loss 0.26548662438988685 test_loss: 0.23788075447082518
epoch: 3 training_loss 0.2316312625259161 test_loss: 0.24292433261871338
epoch: 4 training_loss 0.2437150999903679 test_loss: 0.2390160083770752
epoch: 5 training_loss 0.2417002421617508 test_loss: 0.22511754035949708
epoch: 6 training_loss 0.23311440229415895 test_loss: 0.23090291023254395
epoch: 7 training_loss 0.2244246370345354 test_loss: 0.20860505104064941
epoch: 8 training_loss 0.22764794245362283 test_loss: 0.22249119281768798
epoch: 9 training_loss 0.22148166581988335 test_loss: 0.22312376499176026
epoch: 10 training_loss 0.22437816724181175 test_loss: 0.19153616428375245
epoch: 11 training_loss 0.22230258584022522 test_loss: 0.20813119411468506
epoch: 12 training_loss 0.21269717901945115 test_loss: 0.2035388946533203
epoch: 13 training_loss 0.2092665410041809 test_loss: 0.20795576572418212
epoch: 14 training_loss 0.2141292680799961 test_loss: 0.20590126514434814
epoch: 15 training_loss 0.2046846006810665 test_loss: 0.23545873165130615
epoch: 16 training_loss 0.20459837287664415 test_loss: 0.22932944297790528
epoch: 17 training_loss 0.20291979782283306 test_loss: 0.22422420978546143
epoch: 18 training_loss 0.20650468453764914 test_loss: 0.21581747531890869
epoch: 19 training_loss 0.21798123508691788 test_loss: 0.24948477745056152
epoch: 20 training_loss 0.2020806849002838 test_loss: 0.21892185211181642
epoch: 21 training_loss 0.21126587949693204 test_loss: 0.2161479949951172
epoch: 22 training_loss 0.21155257657170295 test_loss: 0.20570619106292726
epoch: 23 training_loss 0.20838589839637278 test_loss: 0.19422394037246704
epoch: 24 training_loss 0.21120482750236988 test_loss: 0.20643360614776612
epoch: 25 training_loss 0.2034986162930727 test_loss: 0.20835304260253906
epoch: 26 training_loss 0.19898128613829613 test_loss: 0.19877321720123292
epoch: 27 training_loss 0.20035392947494984 test_loss: 0.19607830047607422
epoch: 28 training_loss 0.19817017175257207 test_loss: 0.2083808183670044
epoch: 29 training_loss 0.2027596677094698 test_loss: 0.20861608982086183
epoch: 30 training_loss 0.20747774593532087 test_loss: 0.19152309894561767
epoch: 31 training_loss 0.1865473684668541 test_loss: 0.2134801149368286
epoch: 32 training_loss 0.19821724273264407 test_loss: 0.18240222930908204
epoch: 33 training_loss 0.2056735373288393 test_loss: 0.1853928565979004
epoch: 34 training_loss 0.20824662379920483 test_loss: 0.21640114784240722
epoch: 35 training_loss 0.20429818391799925 test_loss: 0.19615839719772338
epoch: 36 training_loss 0.19416117675602437 test_loss: 0.2034346342086792
epoch: 37 training_loss 0.19502397045493125 test_loss: 0.18155310153961182
epoch: 38 training_loss 0.2050572669506073 test_loss: 0.1875402808189392
epoch: 39 training_loss 0.2029870765656233 test_loss: 0.18678680658340455
epoch: 40 training_loss 0.19542060747742654 test_loss: 0.18750450611114503
epoch: 41 training_loss 0.19327766351401807 test_loss: 0.19763617515563964
epoch: 42 training_loss 0.19749238766729832 test_loss: 0.18270554542541503
epoch: 43 training_loss 0.20048088654875756 test_loss: 0.18487117290496827
epoch: 44 training_loss 0.19496480569243432 test_loss: 0.21502878665924072
epoch: 45 training_loss 0.1948784251511097 test_loss: 0.18944833278656006
epoch: 46 training_loss 0.20227625206112862 test_loss: 0.22044978141784669
epoch: 47 training_loss 0.19672030590474607 test_loss: 0.19344813823699952
epoch: 48 training_loss 0.1937201713770628 test_loss: 0.17885143756866456
epoch: 49 training_loss 0.19622727662324904 test_loss: 0.18831415176391603
epoch: 50 training_loss 0.19557324327528477 test_loss: 0.2012247323989868
epoch: 51 training_loss 0.19561949238181114 test_loss: 0.1759764790534973
epoch: 52 training_loss 0.20170041479170323 test_loss: 0.20848605632781983
epoch: 53 training_loss 0.194106408059597 test_loss: 0.1832301139831543
epoch: 54 training_loss 0.19446415334939957 test_loss: 0.2070441722869873
epoch: 55 training_loss 0.19660817593336105 test_loss: 0.20147500038146973
epoch: 56 training_loss 0.1897622711211443 test_loss: 0.17464873790740967
epoch: 57 training_loss 0.19170094214379788 test_loss: 0.19948675632476806
epoch: 58 training_loss 0.20523735851049424 test_loss: 0.18900562524795533
epoch: 59 training_loss 0.19501734465360643 test_loss: 0.18850804567337037
epoch: 60 training_loss 0.19128366313874723 test_loss: 0.17274885177612304
epoch: 61 training_loss 0.19740832574665546 test_loss: 0.2069761037826538
epoch: 62 training_loss 0.19217381112277507 test_loss: 0.18191312551498412
epoch: 63 training_loss 0.19169175654649734 test_loss: 0.21830005645751954
epoch: 64 training_loss 0.1887321338802576 test_loss: 0.17949706315994263
epoch: 65 training_loss 0.1908396067470312 test_loss: 0.19568350315093994
epoch: 66 training_loss 0.19141842529177666 test_loss: 0.19619859457015992
epoch: 67 training_loss 0.19626946970820427 test_loss: 0.1937633514404297
epoch: 68 training_loss 0.19117394499480725 test_loss: 0.20050840377807616
epoch: 69 training_loss 0.1934638834744692 test_loss: 0.1874469041824341
epoch: 70 training_loss 0.1882708941400051 test_loss: 0.17279834747314454
epoch: 71 training_loss 0.19014523431658745 test_loss: 0.1895180106163025
epoch: 72 training_loss 0.19105636663734912 test_loss: 0.19409626722335815
epoch: 73 training_loss 0.18648493357002735 test_loss: 0.18477702140808105
epoch: 74 training_loss 0.18937906250357628 test_loss: 0.1822899341583252
epoch: 75 training_loss 0.19105637744069098 test_loss: 0.19781020879745484
epoch: 76 training_loss 0.19489116705954074 test_loss: 0.1980506420135498
epoch: 77 training_loss 0.18929725781083107 test_loss: 0.19399958848953247
epoch: 78 training_loss 0.18758835785090924 test_loss: 0.19503870010375976
epoch: 79 training_loss 0.19390595003962516 test_loss: 0.20091240406036376
epoch: 80 training_loss 0.19876569002866745 test_loss: 0.20920073986053467
epoch: 81 training_loss 0.17746385917067528 test_loss: 0.18523037433624268
epoch: 82 training_loss 0.18273028694093227 test_loss: 0.19985321760177613
epoch: 83 training_loss 0.18651796117424965 test_loss: 0.19566770792007446
epoch: 84 training_loss 0.1819721832871437 test_loss: 0.1910329580307007
epoch: 85 training_loss 0.19071924708783627 test_loss: 0.18792346715927125
epoch: 86 training_loss 0.17678786419332027 test_loss: 0.1657091736793518
epoch: 87 training_loss 0.18366991944611072 test_loss: 0.19396306276321412
epoch: 88 training_loss 0.19039157174527646 test_loss: 0.1920618534088135
epoch: 89 training_loss 0.1797970449924469 test_loss: 0.17001332044601442
epoch: 90 training_loss 0.18886362105607987 test_loss: 0.17892132997512816
epoch: 91 training_loss 0.19807708129286766 test_loss: 0.17067570686340333
epoch: 92 training_loss 0.18322263680398465 test_loss: 0.17134782075881957
epoch: 93 training_loss 0.19284700490534307 test_loss: 0.18610048294067383
epoch: 94 training_loss 0.18895813211798668 test_loss: 0.1709856152534485
epoch: 95 training_loss 0.1827288691699505 test_loss: 0.17631791830062865
epoch: 96 training_loss 0.19122876942157746 test_loss: 0.1870781421661377
epoch: 97 training_loss 0.18312208607792854 test_loss: 0.1797500491142273
epoch: 98 training_loss 0.1843050029873848 test_loss: 0.20186009407043456
epoch: 99 training_loss 0.1765599802136421 test_loss: 0.20992398262023926
epoch: 100 training_loss 0.18593734048306942 test_loss: 0.16517159938812256
epoch: 101 training_loss 0.18216352194547653 test_loss: 0.19613779783248902
epoch: 102 training_loss 0.1818903522193432 test_loss: 0.17707110643386842
epoch: 103 training_loss 0.17850887954235076 test_loss: 0.20008115768432616
epoch: 104 training_loss 0.18594862081110478 test_loss: 0.18821825981140136
epoch: 105 training_loss 0.18416214756667615 test_loss: 0.19509557485580445
epoch: 106 training_loss 0.1713326682150364 test_loss: 0.17098491191864013
epoch: 107 training_loss 0.18654054932296277 test_loss: 0.1832077145576477
epoch: 108 training_loss 0.18084470361471175 test_loss: 0.17081550359725953
epoch: 109 training_loss 0.185252927467227 test_loss: 0.18977240324020386
epoch: 110 training_loss 0.18579199716448783 test_loss: 0.19469813108444214
epoch: 111 training_loss 0.18000473879277706 test_loss: 0.17569421529769896
epoch: 112 training_loss 0.1849798332154751 test_loss: 0.1721533417701721
epoch: 113 training_loss 0.18140590138733387 test_loss: 0.19853161573410033
epoch: 114 training_loss 0.18258433647453784 test_loss: 0.1843450903892517
epoch: 115 training_loss 0.1795778451859951 test_loss: 0.17983450889587402
epoch: 116 training_loss 0.18541992232203483 test_loss: 0.19734439849853516
epoch: 117 training_loss 0.18739358134567738 test_loss: 0.182534122467041
epoch: 118 training_loss 0.18872972071170807 test_loss: 0.18237656354904175
epoch: 119 training_loss 0.18242890417575836 test_loss: 0.16721577644348146
epoch: 120 training_loss 0.1810124208778143 test_loss: 0.16648126840591432
epoch: 121 training_loss 0.19017005167901516 test_loss: 0.17526096105575562
epoch: 122 training_loss 0.18535847492516042 test_loss: 0.18685926198959352
epoch: 123 training_loss 0.178548678830266 test_loss: 0.18383655548095704
epoch: 124 training_loss 0.1795164877176285 test_loss: 0.18052301406860352
epoch: 125 training_loss 0.18621845997869968 test_loss: 0.16260708570480348
epoch: 126 training_loss 0.1857382959127426 test_loss: 0.1974746346473694
epoch: 127 training_loss 0.17857016555964947 test_loss: 0.16953027248382568
epoch: 128 training_loss 0.18369016990065576 test_loss: 0.18852441310882567
epoch: 129 training_loss 0.19170971035957338 test_loss: 0.1690617799758911
epoch: 130 training_loss 0.17636629149317742 test_loss: 0.18074241876602173
epoch: 131 training_loss 0.18354545250535012 test_loss: 0.17569432258605958
epoch: 132 training_loss 0.18008360393345357 test_loss: 0.17891157865524293
epoch: 133 training_loss 0.18027287997305394 test_loss: 0.17529878616333008
epoch: 134 training_loss 0.1800602327287197 test_loss: 0.17139177322387694
epoch: 135 training_loss 0.1831635447591543 test_loss: 0.16097922325134278
epoch: 136 training_loss 0.1784134428948164 test_loss: 0.18293083906173707
epoch: 137 training_loss 0.18122075852006675 test_loss: 0.18218919038772582
epoch: 138 training_loss 0.17259808167815208 test_loss: 0.18474225997924804
epoch: 139 training_loss 0.17917404919862748 test_loss: 0.20078463554382325
epoch: 140 training_loss 0.18553462378680707 test_loss: 0.18920112848281861
epoch: 141 training_loss 0.18741078227758406 test_loss: 0.180521559715271
epoch: 142 training_loss 0.17738351456820964 test_loss: 0.17342625856399535
epoch: 143 training_loss 0.1822501128911972 test_loss: 0.18402504920959473
epoch: 144 training_loss 0.17750585667788982 test_loss: 0.18947241306304932
epoch: 145 training_loss 0.1969161853939295 test_loss: 0.16912297010421753
epoch: 146 training_loss 0.1768358850479126 test_loss: 0.17335082292556764
epoch: 147 training_loss 0.17842162773013115 test_loss: 0.1854490876197815
epoch: 148 training_loss 0.18407347440719604 test_loss: 0.17656372785568236
epoch: 149 training_loss 0.1784745728969574 test_loss: 0.18504686355590821
epoch: 0 training_loss 44.39861988067627 test_loss: 25.224122619628908
epoch: 1 training_loss 19.738508405685426 test_loss: 16.38542022705078
epoch: 2 training_loss 14.880955724716186 test_loss: 13.455722045898437
epoch: 3 training_loss 12.915562667846679 test_loss: 11.883993530273438
epoch: 4 training_loss 11.491664009094238 test_loss: 10.61669921875
epoch: 5 training_loss 10.527529935836792 test_loss: 10.411770629882813
epoch: 6 training_loss 9.802772808074952 test_loss: 9.328887176513671
epoch: 7 training_loss 9.141899127960205 test_loss: 8.668189239501952
epoch: 8 training_loss 8.808167004585266 test_loss: 8.569486236572265
epoch: 9 training_loss 8.257330350875854 test_loss: 8.007798767089843
epoch: 10 training_loss 7.90700131893158 test_loss: 7.463863372802734
epoch: 11 training_loss 7.520673971176148 test_loss: 7.043096923828125
epoch: 12 training_loss 7.289227390289307 test_loss: 7.091243743896484
epoch: 13 training_loss 6.982702865600586 test_loss: 6.849752044677734
epoch: 14 training_loss 6.821129508018494 test_loss: 6.831353759765625
epoch: 15 training_loss 6.658793382644653 test_loss: 6.875346374511719
epoch: 16 training_loss 6.362051467895508 test_loss: 6.31318473815918
epoch: 17 training_loss 6.182519254684448 test_loss: 5.944565200805664
epoch: 18 training_loss 6.112334561347962 test_loss: 6.041362762451172
epoch: 19 training_loss 5.87156035900116 test_loss: 5.652828598022461
epoch: 20 training_loss 5.857562437057495 test_loss: 5.972448348999023
epoch: 21 training_loss 5.64261146068573 test_loss: 5.616732788085938
epoch: 22 training_loss 5.550599246025086 test_loss: 5.218366241455078
epoch: 23 training_loss 5.370172362327576 test_loss: 5.129890823364258
epoch: 24 training_loss 5.293268728256225 test_loss: 5.241893005371094
epoch: 25 training_loss 5.110516936779022 test_loss: 4.8566242218017575
epoch: 26 training_loss 5.155470271110534 test_loss: 4.806206893920899
epoch: 27 training_loss 4.88801558971405 test_loss: 4.562183380126953
epoch: 28 training_loss 4.958790273666382 test_loss: 4.657092666625976
epoch: 29 training_loss 4.802945656776428 test_loss: 4.762014007568359
epoch: 30 training_loss 4.879973707199096 test_loss: 4.496866607666016
epoch: 31 training_loss 4.719338083267212 test_loss: 4.557154846191406
epoch: 32 training_loss 4.830679178237915 test_loss: 4.229672241210937
epoch: 33 training_loss 4.540529432296753 test_loss: 4.359076690673828
epoch: 34 training_loss 4.592092559337616 test_loss: 4.960895538330078
epoch: 35 training_loss 4.539209575653076 test_loss: 4.586466979980469
epoch: 36 training_loss 4.51671065568924 test_loss: 4.7800640106201175
epoch: 37 training_loss 4.44499135017395 test_loss: 4.440771102905273
epoch: 38 training_loss 4.411274311542511 test_loss: 4.330158996582031
epoch: 39 training_loss 4.296443486213684 test_loss: 4.2099658966064455
epoch: 40 training_loss 4.260340678691864 test_loss: 4.302838516235352
epoch: 41 training_loss 4.2858483862876895 test_loss: 4.340128707885742
epoch: 42 training_loss 4.149660060405731 test_loss: 3.8539356231689452
epoch: 43 training_loss 4.1524800777435305 test_loss: 4.142361831665039
epoch: 44 training_loss 3.9541378092765807 test_loss: 3.874139404296875
epoch: 45 training_loss 4.134219431877137 test_loss: 4.363434982299805
epoch: 46 training_loss 4.0787901377677915 test_loss: 3.923208236694336
epoch: 47 training_loss 3.8821709418296813 test_loss: 3.6444137573242186
epoch: 48 training_loss 3.76695791721344 test_loss: 3.727570343017578
epoch: 49 training_loss 3.9808696603775022 test_loss: 3.7874488830566406
epoch: 50 training_loss 3.884092400074005 test_loss: 3.4539505004882813
epoch: 51 training_loss 3.9052075695991517 test_loss: 4.023918151855469
epoch: 52 training_loss 3.7439309906959535 test_loss: 3.792502593994141
epoch: 53 training_loss 3.749414222240448 test_loss: 3.792033004760742
epoch: 54 training_loss 3.5883369302749633 test_loss: 3.7099918365478515
epoch: 55 training_loss 3.744860818386078 test_loss: 3.7413745880126954
epoch: 56 training_loss 3.5510866236686707 test_loss: 3.4872406005859373
epoch: 57 training_loss 3.68566214799881 test_loss: 3.607654571533203
epoch: 58 training_loss 3.5490410709381104 test_loss: 3.6576629638671876
epoch: 59 training_loss 3.4616974401474 test_loss: 3.301456832885742
epoch: 60 training_loss 3.5066396141052247 test_loss: 3.540070724487305
epoch: 61 training_loss 3.4606922936439513 test_loss: 3.0292707443237306
epoch: 62 training_loss 3.4188455939292908 test_loss: 3.5005470275878907
epoch: 63 training_loss 3.5570471048355103 test_loss: 3.5171924591064454
epoch: 64 training_loss 3.347423074245453 test_loss: 3.2650882720947267
epoch: 65 training_loss 3.2760769867897035 test_loss: 3.320445251464844
epoch: 66 training_loss 3.3601377534866335 test_loss: 3.1207061767578126
epoch: 67 training_loss 3.4855954217910767 test_loss: 3.0418466567993163
epoch: 68 training_loss 3.2706025409698487 test_loss: 3.1632669448852537
epoch: 69 training_loss 3.331487057209015 test_loss: 3.4805534362792967
epoch: 70 training_loss 3.2313756155967712 test_loss: 2.9815576553344725
epoch: 71 training_loss 3.2214892387390135 test_loss: 3.152665901184082
epoch: 72 training_loss 3.089906704425812 test_loss: 3.5011402130126954
epoch: 73 training_loss 3.171583399772644 test_loss: 2.9389375686645507
epoch: 74 training_loss 3.051046805381775 test_loss: 2.987639045715332
epoch: 75 training_loss 3.0089685904979704 test_loss: 3.056126022338867
epoch: 76 training_loss 2.8586374521255493 test_loss: 3.050063705444336
epoch: 77 training_loss 3.1250195240974428 test_loss: 3.109127235412598
epoch: 78 training_loss 3.0566882419586183 test_loss: 2.8737197875976563
epoch: 79 training_loss 2.979587595462799 test_loss: 3.2053260803222656
epoch: 80 training_loss 3.0183424806594847 test_loss: 2.6449392318725584
epoch: 81 training_loss 2.8843347811698914 test_loss: 3.767842102050781
epoch: 82 training_loss 2.8557635390758516 test_loss: 2.7618553161621096
epoch: 83 training_loss 2.9093475353717806 test_loss: 3.1232297897338865
epoch: 84 training_loss 2.7966118919849396 test_loss: 2.542921447753906
epoch: 85 training_loss 2.7433717501163484 test_loss: 2.9546070098876953
epoch: 86 training_loss 2.7326473498344424 test_loss: 3.053731155395508
epoch: 87 training_loss 2.76639861702919 test_loss: 3.1716468811035154
epoch: 88 training_loss 2.793896474838257 test_loss: 2.693970489501953
epoch: 89 training_loss 2.9658106648921967 test_loss: 2.857613372802734
epoch: 90 training_loss 2.709736841917038 test_loss: 2.407572937011719
epoch: 91 training_loss 2.6899397802352905 test_loss: 2.8039949417114256
epoch: 92 training_loss 2.5624928736686705 test_loss: 2.8332090377807617
epoch: 93 training_loss 2.6344835782051086 test_loss: 2.5914890289306642
epoch: 94 training_loss 2.691784290075302 test_loss: 2.324154090881348
epoch: 95 training_loss 2.630877560377121 test_loss: 2.622500419616699
epoch: 96 training_loss 2.624056897163391 test_loss: 2.669628143310547
epoch: 97 training_loss 2.6186858797073365 test_loss: 2.5042818069458006
epoch: 98 training_loss 2.6682481741905213 test_loss: 2.5158185958862305
epoch: 99 training_loss 2.7126470386981962 test_loss: 3.110848808288574
epoch: 100 training_loss 2.624716305732727 test_loss: 2.2274654388427733
epoch: 101 training_loss 2.5616962563991548 test_loss: 2.651475524902344
epoch: 102 training_loss 2.612331051826477 test_loss: 2.353848457336426
epoch: 103 training_loss 2.4189041805267335 test_loss: 2.1524511337280274
epoch: 104 training_loss 2.3443339002132415 test_loss: 2.406698799133301
epoch: 105 training_loss 2.520230436325073 test_loss: 2.6026254653930665
epoch: 106 training_loss 2.349168096780777 test_loss: 2.0536197662353515
epoch: 107 training_loss 2.461627781391144 test_loss: 2.494681739807129
epoch: 108 training_loss 2.4256036138534545 test_loss: 2.582012748718262
epoch: 109 training_loss 2.4275888848304747 test_loss: 2.095838928222656
epoch: 110 training_loss 2.453712434768677 test_loss: 2.2795385360717773
epoch: 111 training_loss 2.426946233510971 test_loss: 2.3559986114501954
epoch: 112 training_loss 2.4310257911682127 test_loss: 2.3321159362792967
epoch: 113 training_loss 2.3702544939517973 test_loss: 2.1485353469848634
epoch: 114 training_loss 2.3226754236221314 test_loss: 2.447406196594238
epoch: 115 training_loss 2.4211694693565367 test_loss: 2.080600929260254
epoch: 116 training_loss 2.391907786130905 test_loss: 2.167399215698242
epoch: 117 training_loss 2.3363089883327484 test_loss: 2.0837636947631837
epoch: 118 training_loss 2.2525850355625154 test_loss: 2.192476272583008
epoch: 119 training_loss 2.318290950059891 test_loss: 2.1897382736206055
epoch: 120 training_loss 2.2652358770370484 test_loss: 2.197543716430664
epoch: 121 training_loss 2.206111334562302 test_loss: 2.4932390213012696
epoch: 122 training_loss 2.45335064291954 test_loss: 3.1661344528198243
epoch: 123 training_loss 2.2199835669994354 test_loss: 2.2502634048461916
epoch: 124 training_loss 2.310955740213394 test_loss: 2.417593002319336
epoch: 125 training_loss 2.3338613522052767 test_loss: 2.2309953689575197
epoch: 126 training_loss 2.0834490036964417 test_loss: 1.8698627471923828
epoch: 127 training_loss 2.3291263544559477 test_loss: 2.2102275848388673
epoch: 128 training_loss 2.065206528902054 test_loss: 2.090610313415527
epoch: 129 training_loss 2.1257224357128144 test_loss: 1.9963119506835938
epoch: 130 training_loss 2.4829841697216035 test_loss: 3.034590721130371
epoch: 131 training_loss 2.22296457529068 test_loss: 1.8178964614868165
epoch: 132 training_loss 2.1721479308605196 test_loss: 2.107284927368164
epoch: 133 training_loss 2.042401829957962 test_loss: 1.873491096496582
epoch: 134 training_loss 2.060552719831467 test_loss: 2.129167366027832
epoch: 135 training_loss 2.0814768242836 test_loss: 2.6315639495849608
epoch: 136 training_loss 2.1189998817443847 test_loss: 2.1693777084350585
epoch: 137 training_loss 2.2175231325626372 test_loss: 1.8728654861450196
epoch: 138 training_loss 2.0299424266815187 test_loss: 1.8925172805786132
epoch: 139 training_loss 1.9856678092479705 test_loss: 2.125212860107422
epoch: 140 training_loss 2.1241876435279847 test_loss: 2.2055158615112305
epoch: 141 training_loss 2.156543138027191 test_loss: 1.935936737060547
epoch: 142 training_loss 1.9588097286224366 test_loss: 2.0352546691894533
epoch: 143 training_loss 2.0023804235458376 test_loss: 2.2773805618286134
epoch: 144 training_loss 2.1135821962356567 test_loss: 1.9665924072265626
epoch: 145 training_loss 2.1329419016838074 test_loss: 1.832793617248535
epoch: 146 training_loss 2.0881020498275755 test_loss: 2.2067060470581055
epoch: 147 training_loss 2.0275790762901305 test_loss: 2.065708351135254
epoch: 148 training_loss 2.206593302488327 test_loss: 2.0078182220458984
epoch: 149 training_loss 2.0751922059059145 test_loss: 2.3170867919921876
70.69001612235824
episode: 0 training return: tensor(-70.5174, device='cuda:0')
episode: 1 training return: tensor(-95.7085, device='cuda:0')
episode: 2 training return: tensor(-101.7533, device='cuda:0')
episode: 3 training return: tensor(-123.6971, device='cuda:0')
epoch: 1 test_true_pfm: 69.12477724196765 sim_pfm: -108.18799593491713
episode: 4 training return: tensor(-145.4118, device='cuda:0')
episode: 5 training return: tensor(-86.3212, device='cuda:0')
episode: 6 training return: tensor(-93.8940, device='cuda:0')
episode: 7 training return: tensor(-94.0998, device='cuda:0')
epoch: 2 test_true_pfm: 79.59303367438797 sim_pfm: -106.35751317214454
episode: 8 training return: tensor(-216.5417, device='cuda:0')
episode: 9 training return: tensor(-149.8180, device='cuda:0')
episode: 10 training return: tensor(-95.6646, device='cuda:0')
episode: 11 training return: tensor(-141.4629, device='cuda:0')
epoch: 3 test_true_pfm: 80.19904823073117 sim_pfm: -109.83952452587546
episode: 12 training return: tensor(-151.4237, device='cuda:0')
episode: 13 training return: tensor(-94.1029, device='cuda:0')
episode: 14 training return: tensor(-97.9253, device='cuda:0')
episode: 15 training return: tensor(-97.7566, device='cuda:0')
epoch: 4 test_true_pfm: 91.16488377889527 sim_pfm: -89.3441042770457
episode: 16 training return: tensor(-117.2057, device='cuda:0')
episode: 17 training return: tensor(-117.9535, device='cuda:0')
episode: 18 training return: tensor(-102.1085, device='cuda:0')
episode: 19 training return: tensor(-102.8061, device='cuda:0')
epoch: 5 test_true_pfm: 58.316956317672705 sim_pfm: -112.52906449546572
episode: 20 training return: tensor(-122.8589, device='cuda:0')
episode: 21 training return: tensor(-128.1906, device='cuda:0')
episode: 22 training return: tensor(-97.0166, device='cuda:0')
episode: 23 training return: tensor(-115.5127, device='cuda:0')
epoch: 6 test_true_pfm: 59.491737581691226 sim_pfm: -110.1563217294286
episode: 24 training return: tensor(-124.5838, device='cuda:0')
episode: 25 training return: tensor(-122.6632, device='cuda:0')
episode: 26 training return: tensor(-109.9675, device='cuda:0')
episode: 27 training return: tensor(-120.6966, device='cuda:0')
epoch: 7 test_true_pfm: 86.09041798807839 sim_pfm: -119.50101798097603
episode: 28 training return: tensor(-111.1014, device='cuda:0')
episode: 29 training return: tensor(-81.7062, device='cuda:0')
episode: 30 training return: tensor(-104.2362, device='cuda:0')
episode: 31 training return: tensor(-133.1341, device='cuda:0')
epoch: 8 test_true_pfm: 57.56507022280725 sim_pfm: -106.77958484561532
episode: 32 training return: tensor(-98.7545, device='cuda:0')
episode: 33 training return: tensor(-97.4904, device='cuda:0')
episode: 34 training return: tensor(-99.0181, device='cuda:0')
episode: 35 training return: tensor(-104.5878, device='cuda:0')
epoch: 9 test_true_pfm: 82.24628592818632 sim_pfm: -114.3373439161398
episode: 36 training return: tensor(-145.9899, device='cuda:0')
episode: 37 training return: tensor(-104.7328, device='cuda:0')
episode: 38 training return: tensor(-134.8012, device='cuda:0')
episode: 39 training return: tensor(-95.0239, device='cuda:0')
epoch: 10 test_true_pfm: 49.385621489045796 sim_pfm: -103.42342417765175
episode: 40 training return: tensor(-102.0114, device='cuda:0')
episode: 41 training return: tensor(-108.4613, device='cuda:0')
episode: 42 training return: tensor(-110.0939, device='cuda:0')
episode: 43 training return: tensor(-105.9943, device='cuda:0')
epoch: 11 test_true_pfm: 86.60506590483354 sim_pfm: -118.06818160839029
episode: 44 training return: tensor(-148.5503, device='cuda:0')
episode: 45 training return: tensor(-104.9502, device='cuda:0')
episode: 46 training return: tensor(-93.1558, device='cuda:0')
episode: 47 training return: tensor(-100.9815, device='cuda:0')
epoch: 12 test_true_pfm: 71.51614501368574 sim_pfm: -116.69487949566683
episode: 48 training return: tensor(-150.1824, device='cuda:0')
episode: 49 training return: tensor(-145.7572, device='cuda:0')
episode: 50 training return: tensor(-146.8987, device='cuda:0')
episode: 51 training return: tensor(-80.5663, device='cuda:0')
epoch: 13 test_true_pfm: 71.0598487669231 sim_pfm: -110.32260138665443
episode: 52 training return: tensor(-85.9072, device='cuda:0')
episode: 53 training return: tensor(-90.1795, device='cuda:0')
episode: 54 training return: tensor(-99.6676, device='cuda:0')
episode: 55 training return: tensor(-134.9270, device='cuda:0')
epoch: 14 test_true_pfm: 51.26758953029919 sim_pfm: -113.56054610773572
episode: 56 training return: tensor(-93.0593, device='cuda:0')
episode: 57 training return: tensor(-145.7201, device='cuda:0')
episode: 58 training return: tensor(-150.8131, device='cuda:0')
episode: 59 training return: tensor(-86.0633, device='cuda:0')
epoch: 15 test_true_pfm: 84.61873243370182 sim_pfm: -134.66557449447572
episode: 60 training return: tensor(-88.9953, device='cuda:0')
episode: 61 training return: tensor(-105.9742, device='cuda:0')
episode: 62 training return: tensor(-101.6722, device='cuda:0')
episode: 63 training return: tensor(-104.9397, device='cuda:0')
epoch: 16 test_true_pfm: 76.03547966378581 sim_pfm: -146.9611923268647
episode: 64 training return: tensor(-143.8166, device='cuda:0')
episode: 65 training return: tensor(-116.1918, device='cuda:0')
episode: 66 training return: tensor(-157.3281, device='cuda:0')
episode: 67 training return: tensor(-149.0947, device='cuda:0')
epoch: 17 test_true_pfm: 71.99480455998923 sim_pfm: -150.39173659220106
episode: 68 training return: tensor(-67.2068, device='cuda:0')
episode: 69 training return: tensor(-124.9426, device='cuda:0')
episode: 70 training return: tensor(-143.8734, device='cuda:0')
episode: 71 training return: tensor(-148.5605, device='cuda:0')
epoch: 18 test_true_pfm: 77.28122325070103 sim_pfm: -135.32459584744646
episode: 72 training return: tensor(-97.7693, device='cuda:0')
episode: 73 training return: tensor(-99.2858, device='cuda:0')
episode: 74 training return: tensor(-118.4851, device='cuda:0')
episode: 75 training return: tensor(-138.2352, device='cuda:0')
epoch: 19 test_true_pfm: 67.22019997839364 sim_pfm: -98.04914642933291
episode: 76 training return: tensor(-133.5601, device='cuda:0')
episode: 77 training return: tensor(-90.3422, device='cuda:0')
episode: 78 training return: tensor(-128.2272, device='cuda:0')
episode: 79 training return: tensor(-91.6155, device='cuda:0')
epoch: 20 test_true_pfm: 67.6028063035226 sim_pfm: -111.07241447824053
episode: 80 training return: tensor(-142.8423, device='cuda:0')
episode: 81 training return: tensor(-141.2433, device='cuda:0')
episode: 82 training return: tensor(-138.3940, device='cuda:0')
episode: 83 training return: tensor(-94.2269, device='cuda:0')
epoch: 21 test_true_pfm: 56.02140965980961 sim_pfm: -124.30118227395579
episode: 84 training return: tensor(-150.3947, device='cuda:0')
episode: 85 training return: tensor(-142.6966, device='cuda:0')
episode: 86 training return: tensor(-190.9016, device='cuda:0')
episode: 87 training return: tensor(-90.4246, device='cuda:0')
epoch: 22 test_true_pfm: 58.52509315517358 sim_pfm: -123.43787748829928
episode: 88 training return: tensor(-80.7761, device='cuda:0')
episode: 89 training return: tensor(-84.6143, device='cuda:0')
episode: 90 training return: tensor(-119.8392, device='cuda:0')
episode: 91 training return: tensor(-65.5589, device='cuda:0')
epoch: 23 test_true_pfm: 89.65690492205303 sim_pfm: -121.214875353378
episode: 92 training return: tensor(-139.3182, device='cuda:0')
episode: 93 training return: tensor(-167.4200, device='cuda:0')
episode: 94 training return: tensor(-143.1706, device='cuda:0')
episode: 95 training return: tensor(-131.8377, device='cuda:0')
epoch: 24 test_true_pfm: 67.35544698975548 sim_pfm: -116.89601151902461
episode: 96 training return: tensor(-86.8089, device='cuda:0')
episode: 97 training return: tensor(-97.8540, device='cuda:0')
episode: 98 training return: tensor(-125.7771, device='cuda:0')
episode: 99 training return: tensor(-102.4346, device='cuda:0')
epoch: 25 test_true_pfm: 58.33018278386858 sim_pfm: -98.62326231578481
episode: 100 training return: tensor(-157.9558, device='cuda:0')
episode: 101 training return: tensor(-92.6675, device='cuda:0')
episode: 102 training return: tensor(-145.7302, device='cuda:0')
episode: 103 training return: tensor(-81.9483, device='cuda:0')
epoch: 26 test_true_pfm: 55.672484153791586 sim_pfm: -108.15906648552046
episode: 104 training return: tensor(-143.8273, device='cuda:0')
episode: 105 training return: tensor(-118.2822, device='cuda:0')
episode: 106 training return: tensor(-134.7991, device='cuda:0')
episode: 107 training return: tensor(-142.0599, device='cuda:0')
epoch: 27 test_true_pfm: 57.99163737649328 sim_pfm: -118.52643881805707
episode: 108 training return: tensor(-89.0983, device='cuda:0')
episode: 109 training return: tensor(-146.4490, device='cuda:0')
episode: 110 training return: tensor(-99.3285, device='cuda:0')
episode: 111 training return: tensor(-125.1758, device='cuda:0')
epoch: 28 test_true_pfm: 57.909495521047646 sim_pfm: -119.1828211815271
episode: 112 training return: tensor(-109.0489, device='cuda:0')
episode: 113 training return: tensor(-82.9187, device='cuda:0')
episode: 114 training return: tensor(-148.4889, device='cuda:0')
episode: 115 training return: tensor(-91.1522, device='cuda:0')
epoch: 29 test_true_pfm: 51.36455552630923 sim_pfm: -129.1755102085881
episode: 116 training return: tensor(-129.2677, device='cuda:0')
episode: 117 training return: tensor(-69.7660, device='cuda:0')
episode: 118 training return: tensor(-118.0281, device='cuda:0')
episode: 119 training return: tensor(-96.5405, device='cuda:0')
epoch: 30 test_true_pfm: 70.79703080858641 sim_pfm: -120.68127351559815
episode: 120 training return: tensor(-140.9264, device='cuda:0')
episode: 121 training return: tensor(-131.3267, device='cuda:0')
episode: 122 training return: tensor(-88.6958, device='cuda:0')
episode: 123 training return: tensor(-89.3379, device='cuda:0')
epoch: 31 test_true_pfm: 50.587825807702316 sim_pfm: -114.18099385929527
episode: 124 training return: tensor(-100.3694, device='cuda:0')
episode: 125 training return: tensor(-103.5038, device='cuda:0')
episode: 126 training return: tensor(-140.5884, device='cuda:0')
episode: 127 training return: tensor(-91.1118, device='cuda:0')
epoch: 32 test_true_pfm: 69.54660662234825 sim_pfm: -99.18864574665204
episode: 128 training return: tensor(-136.5463, device='cuda:0')
episode: 129 training return: tensor(-140.1179, device='cuda:0')
episode: 130 training return: tensor(-88.7103, device='cuda:0')
episode: 131 training return: tensor(-85.6426, device='cuda:0')
epoch: 33 test_true_pfm: 61.06507499816919 sim_pfm: -103.09890439840964
episode: 132 training return: tensor(-130.7275, device='cuda:0')
episode: 133 training return: tensor(-145.2961, device='cuda:0')
episode: 134 training return: tensor(-134.7548, device='cuda:0')
episode: 135 training return: tensor(-152.1971, device='cuda:0')
epoch: 34 test_true_pfm: 67.09765426066875 sim_pfm: -122.91787920786301
episode: 136 training return: tensor(-84.0013, device='cuda:0')
episode: 137 training return: tensor(-77.2900, device='cuda:0')
episode: 138 training return: tensor(-140.7345, device='cuda:0')
episode: 139 training return: tensor(-136.8935, device='cuda:0')
epoch: 35 test_true_pfm: 59.48342783599234 sim_pfm: -128.47960149939172
episode: 140 training return: tensor(-73.9458, device='cuda:0')
episode: 141 training return: tensor(-71.7838, device='cuda:0')
episode: 142 training return: tensor(-83.3515, device='cuda:0')
episode: 143 training return: tensor(-76.6378, device='cuda:0')
epoch: 36 test_true_pfm: 81.86227601781499 sim_pfm: -124.60262574362568
episode: 144 training return: tensor(-74.0245, device='cuda:0')
episode: 145 training return: tensor(-217.9345, device='cuda:0')
episode: 146 training return: tensor(-88.1580, device='cuda:0')
episode: 147 training return: tensor(-68.3197, device='cuda:0')
epoch: 37 test_true_pfm: 61.47237301157709 sim_pfm: -127.70338754819822
episode: 148 training return: tensor(-76.6635, device='cuda:0')
episode: 149 training return: tensor(-143.7923, device='cuda:0')
episode: 150 training return: tensor(-85.6840, device='cuda:0')
episode: 151 training return: tensor(-87.8878, device='cuda:0')
epoch: 38 test_true_pfm: 83.57902959324785 sim_pfm: -105.30239620297216
episode: 152 training return: tensor(-74.0205, device='cuda:0')
episode: 153 training return: tensor(-153.4620, device='cuda:0')
episode: 154 training return: tensor(-92.1581, device='cuda:0')
episode: 155 training return: tensor(-144.4239, device='cuda:0')
epoch: 39 test_true_pfm: 69.62549294710585 sim_pfm: -118.45210713930427
episode: 156 training return: tensor(-127.8372, device='cuda:0')
episode: 157 training return: tensor(-157.3811, device='cuda:0')
episode: 158 training return: tensor(-83.5586, device='cuda:0')
episode: 159 training return: tensor(-92.7217, device='cuda:0')
epoch: 40 test_true_pfm: 69.98982823645257 sim_pfm: -139.27590256261175
episode: 160 training return: tensor(-89.0684, device='cuda:0')
episode: 161 training return: tensor(-99.6716, device='cuda:0')
episode: 162 training return: tensor(-142.7799, device='cuda:0')
episode: 163 training return: tensor(-80.8845, device='cuda:0')
epoch: 41 test_true_pfm: 75.87335380272557 sim_pfm: -93.83466152626788
episode: 164 training return: tensor(-74.6130, device='cuda:0')
episode: 165 training return: tensor(-75.6862, device='cuda:0')
episode: 166 training return: tensor(-85.4753, device='cuda:0')
episode: 167 training return: tensor(-77.7683, device='cuda:0')
epoch: 42 test_true_pfm: 68.17556243456436 sim_pfm: -103.03248068462126
episode: 168 training return: tensor(-98.0829, device='cuda:0')
episode: 169 training return: tensor(-73.0571, device='cuda:0')
episode: 170 training return: tensor(-142.0462, device='cuda:0')
episode: 171 training return: tensor(-82.5820, device='cuda:0')
epoch: 43 test_true_pfm: 71.93957683658155 sim_pfm: -131.22191528225085
episode: 172 training return: tensor(-91.8722, device='cuda:0')
episode: 173 training return: tensor(-205.4029, device='cuda:0')
episode: 174 training return: tensor(-133.8246, device='cuda:0')
episode: 175 training return: tensor(-157.3571, device='cuda:0')
epoch: 44 test_true_pfm: 69.39807113896288 sim_pfm: -118.5428474025859
episode: 176 training return: tensor(-72.2768, device='cuda:0')
episode: 177 training return: tensor(-214.6674, device='cuda:0')
episode: 178 training return: tensor(-97.4568, device='cuda:0')
episode: 179 training return: tensor(-147.4234, device='cuda:0')
epoch: 45 test_true_pfm: 91.00788818778487 sim_pfm: -102.35943182087503
episode: 180 training return: tensor(-84.7832, device='cuda:0')
episode: 181 training return: tensor(-107.6583, device='cuda:0')
episode: 182 training return: tensor(-84.7113, device='cuda:0')
episode: 183 training return: tensor(-141.5691, device='cuda:0')
epoch: 46 test_true_pfm: 68.06025291425398 sim_pfm: -92.28157910468872
episode: 184 training return: tensor(-77.3767, device='cuda:0')
episode: 185 training return: tensor(-140.4411, device='cuda:0')
episode: 186 training return: tensor(-80.1520, device='cuda:0')
episode: 187 training return: tensor(-91.2965, device='cuda:0')
epoch: 47 test_true_pfm: 60.69235210140628 sim_pfm: -115.14471195593941
episode: 188 training return: tensor(-154.4964, device='cuda:0')
episode: 189 training return: tensor(-74.4923, device='cuda:0')
episode: 190 training return: tensor(-94.3782, device='cuda:0')
episode: 191 training return: tensor(-125.3684, device='cuda:0')
epoch: 48 test_true_pfm: 81.5326275247781 sim_pfm: -126.64778474943014
episode: 192 training return: tensor(-145.9431, device='cuda:0')
episode: 193 training return: tensor(-121.8842, device='cuda:0')
episode: 194 training return: tensor(-90.9540, device='cuda:0')
episode: 195 training return: tensor(-142.4891, device='cuda:0')
epoch: 49 test_true_pfm: 45.36372529689113 sim_pfm: -153.33823997897562
episode: 196 training return: tensor(-136.1366, device='cuda:0')
episode: 197 training return: tensor(-118.9814, device='cuda:0')
episode: 198 training return: tensor(-212.8485, device='cuda:0')
episode: 199 training return: tensor(-140.8447, device='cuda:0')
epoch: 50 test_true_pfm: 52.3657860605547 sim_pfm: -184.42189616406102
episode: 200 training return: tensor(-130.8847, device='cuda:0')
episode: 201 training return: tensor(-134.4129, device='cuda:0')
episode: 202 training return: tensor(-72.4348, device='cuda:0')
episode: 203 training return: tensor(-85.1300, device='cuda:0')
epoch: 51 test_true_pfm: 54.12509418031785 sim_pfm: -144.4991906820447
episode: 204 training return: tensor(-126.5487, device='cuda:0')
episode: 205 training return: tensor(-139.8547, device='cuda:0')
episode: 206 training return: tensor(-70.4326, device='cuda:0')
episode: 207 training return: tensor(-207.5600, device='cuda:0')
epoch: 52 test_true_pfm: 71.41360740539156 sim_pfm: -121.4785642137227
episode: 208 training return: tensor(-78.9869, device='cuda:0')
episode: 209 training return: tensor(-215.1751, device='cuda:0')
episode: 210 training return: tensor(-216.2336, device='cuda:0')
episode: 211 training return: tensor(-144.4176, device='cuda:0')
epoch: 53 test_true_pfm: 80.02824129628705 sim_pfm: -123.82041493818397
episode: 212 training return: tensor(-84.0611, device='cuda:0')
episode: 213 training return: tensor(-127.3353, device='cuda:0')
episode: 214 training return: tensor(-105.7466, device='cuda:0')
episode: 215 training return: tensor(-135.0328, device='cuda:0')
epoch: 54 test_true_pfm: 74.69004439178859 sim_pfm: -119.96585194845684
episode: 216 training return: tensor(-213.1945, device='cuda:0')
episode: 217 training return: tensor(-106.0979, device='cuda:0')
episode: 218 training return: tensor(-65.6106, device='cuda:0')
episode: 219 training return: tensor(-134.9485, device='cuda:0')
epoch: 55 test_true_pfm: 61.823756418154915 sim_pfm: -91.69197646412067
episode: 220 training return: tensor(-90.3993, device='cuda:0')
episode: 221 training return: tensor(-125.4935, device='cuda:0')
episode: 222 training return: tensor(-77.4808, device='cuda:0')
episode: 223 training return: tensor(-162.2927, device='cuda:0')
epoch: 56 test_true_pfm: 76.74543011447959 sim_pfm: -128.14001193879523
episode: 224 training return: tensor(-96.3571, device='cuda:0')
episode: 225 training return: tensor(-81.9029, device='cuda:0')
episode: 226 training return: tensor(-138.9468, device='cuda:0')
episode: 227 training return: tensor(-63.2401, device='cuda:0')
epoch: 57 test_true_pfm: 73.87925610467262 sim_pfm: -117.69248301895568
episode: 228 training return: tensor(-145.5214, device='cuda:0')
episode: 229 training return: tensor(-95.4105, device='cuda:0')
episode: 230 training return: tensor(-174.8027, device='cuda:0')
episode: 231 training return: tensor(-89.3424, device='cuda:0')
epoch: 58 test_true_pfm: 90.3091163446901 sim_pfm: -139.02398900407132
episode: 232 training return: tensor(-167.3712, device='cuda:0')
episode: 233 training return: tensor(-90.9411, device='cuda:0')
episode: 234 training return: tensor(-156.3020, device='cuda:0')
episode: 235 training return: tensor(-68.7370, device='cuda:0')
epoch: 59 test_true_pfm: 64.99389069517657 sim_pfm: -105.1952453675738
episode: 236 training return: tensor(-205.1436, device='cuda:0')
episode: 237 training return: tensor(-209.6046, device='cuda:0')
episode: 238 training return: tensor(-206.1254, device='cuda:0')
episode: 239 training return: tensor(-63.9827, device='cuda:0')
epoch: 60 test_true_pfm: 81.02222028911459 sim_pfm: -123.35282470721867
episode: 240 training return: tensor(-150.3481, device='cuda:0')
episode: 241 training return: tensor(-149.6060, device='cuda:0')
episode: 242 training return: tensor(-74.6532, device='cuda:0')
episode: 243 training return: tensor(-93.4217, device='cuda:0')
epoch: 61 test_true_pfm: 50.521654457434195 sim_pfm: -120.94274518984602
episode: 244 training return: tensor(-146.6584, device='cuda:0')
episode: 245 training return: tensor(-144.9553, device='cuda:0')
episode: 246 training return: tensor(-79.0206, device='cuda:0')
episode: 247 training return: tensor(-86.0813, device='cuda:0')
epoch: 62 test_true_pfm: 68.45791051502005 sim_pfm: -109.35366412859294
episode: 248 training return: tensor(-81.6707, device='cuda:0')
episode: 249 training return: tensor(-67.9141, device='cuda:0')
episode: 250 training return: tensor(-82.2469, device='cuda:0')
episode: 251 training return: tensor(-97.1216, device='cuda:0')
epoch: 63 test_true_pfm: 58.60679113904017 sim_pfm: -97.70374011666281
episode: 252 training return: tensor(-76.2591, device='cuda:0')
episode: 253 training return: tensor(-125.4393, device='cuda:0')
episode: 254 training return: tensor(-113.3374, device='cuda:0')
episode: 255 training return: tensor(-136.0968, device='cuda:0')
epoch: 64 test_true_pfm: 76.88379907963926 sim_pfm: -97.39127151745488
episode: 256 training return: tensor(-82.7399, device='cuda:0')
episode: 257 training return: tensor(-73.7185, device='cuda:0')
episode: 258 training return: tensor(-86.8558, device='cuda:0')
episode: 259 training return: tensor(-139.6999, device='cuda:0')
epoch: 65 test_true_pfm: 69.96440246865834 sim_pfm: -100.54666869752108
episode: 260 training return: tensor(-118.7665, device='cuda:0')
episode: 261 training return: tensor(-141.9715, device='cuda:0')
episode: 262 training return: tensor(-71.2538, device='cuda:0')
episode: 263 training return: tensor(-135.9972, device='cuda:0')
epoch: 66 test_true_pfm: 74.4166290967058 sim_pfm: -112.47432392053307
episode: 264 training return: tensor(-87.2453, device='cuda:0')
episode: 265 training return: tensor(-80.0611, device='cuda:0')
episode: 266 training return: tensor(-138.6965, device='cuda:0')
episode: 267 training return: tensor(-155.5320, device='cuda:0')
epoch: 67 test_true_pfm: 54.45451033888794 sim_pfm: -125.66967872800305
episode: 268 training return: tensor(-175.2417, device='cuda:0')
episode: 269 training return: tensor(-85.7593, device='cuda:0')
episode: 270 training return: tensor(-80.8355, device='cuda:0')
episode: 271 training return: tensor(-75.7641, device='cuda:0')
epoch: 68 test_true_pfm: 69.79376508958498 sim_pfm: -109.95394262049813
episode: 272 training return: tensor(-84.6162, device='cuda:0')
episode: 273 training return: tensor(-95.2640, device='cuda:0')
episode: 274 training return: tensor(-150.5599, device='cuda:0')
episode: 275 training return: tensor(-77.3439, device='cuda:0')
epoch: 69 test_true_pfm: 41.862961841491405 sim_pfm: -130.4398066505615
episode: 276 training return: tensor(-207.8136, device='cuda:0')
episode: 277 training return: tensor(-129.6815, device='cuda:0')
episode: 278 training return: tensor(-91.9908, device='cuda:0')
episode: 279 training return: tensor(-137.1603, device='cuda:0')
epoch: 70 test_true_pfm: 61.47778755428091 sim_pfm: -127.49764020219445
episode: 280 training return: tensor(-70.1487, device='cuda:0')
episode: 281 training return: tensor(-72.4714, device='cuda:0')
episode: 282 training return: tensor(-142.1580, device='cuda:0')
episode: 283 training return: tensor(-123.9130, device='cuda:0')
epoch: 71 test_true_pfm: 65.64417137014904 sim_pfm: -153.56628975702915
episode: 284 training return: tensor(-87.5920, device='cuda:0')
episode: 285 training return: tensor(-96.8355, device='cuda:0')
episode: 286 training return: tensor(-84.6343, device='cuda:0')
episode: 287 training return: tensor(-206.4524, device='cuda:0')
epoch: 72 test_true_pfm: 70.40360945212008 sim_pfm: -100.51107609450119
episode: 288 training return: tensor(-84.8671, device='cuda:0')
episode: 289 training return: tensor(-94.7720, device='cuda:0')
episode: 290 training return: tensor(-84.7451, device='cuda:0')
episode: 291 training return: tensor(-203.0123, device='cuda:0')
epoch: 73 test_true_pfm: 61.54491516003111 sim_pfm: -100.12447209005477
episode: 292 training return: tensor(-85.9180, device='cuda:0')
episode: 293 training return: tensor(-122.3743, device='cuda:0')
episode: 294 training return: tensor(-84.7143, device='cuda:0')
episode: 295 training return: tensor(-132.3235, device='cuda:0')
epoch: 74 test_true_pfm: 71.27344529297373 sim_pfm: -145.2593628719158
episode: 296 training return: tensor(-98.7226, device='cuda:0')
episode: 297 training return: tensor(-92.5817, device='cuda:0')
episode: 298 training return: tensor(-200.6402, device='cuda:0')
episode: 299 training return: tensor(-146.9048, device='cuda:0')
epoch: 75 test_true_pfm: 60.836420432671616 sim_pfm: -103.94220357145532
episode: 300 training return: tensor(-88.0827, device='cuda:0')
episode: 301 training return: tensor(-88.5015, device='cuda:0')
episode: 302 training return: tensor(-91.1239, device='cuda:0')
episode: 303 training return: tensor(-124.7286, device='cuda:0')
epoch: 76 test_true_pfm: 52.65817683904372 sim_pfm: -115.37469738414511
episode: 304 training return: tensor(-68.3732, device='cuda:0')
episode: 305 training return: tensor(-143.9389, device='cuda:0')
episode: 306 training return: tensor(-121.1961, device='cuda:0')
episode: 307 training return: tensor(-202.9784, device='cuda:0')
epoch: 77 test_true_pfm: 52.77821551668544 sim_pfm: -95.88045145560754
episode: 308 training return: tensor(-134.6389, device='cuda:0')
episode: 309 training return: tensor(-78.3536, device='cuda:0')
episode: 310 training return: tensor(-146.7418, device='cuda:0')
episode: 311 training return: tensor(-115.1050, device='cuda:0')
epoch: 78 test_true_pfm: 68.72004653620606 sim_pfm: -110.83990510171861
episode: 312 training return: tensor(-95.3380, device='cuda:0')
episode: 313 training return: tensor(-112.2479, device='cuda:0')
episode: 314 training return: tensor(-135.2800, device='cuda:0')
episode: 315 training return: tensor(-112.4998, device='cuda:0')
epoch: 79 test_true_pfm: 58.89391884267204 sim_pfm: -105.72412690572091
episode: 316 training return: tensor(-67.7399, device='cuda:0')
episode: 317 training return: tensor(-209.9393, device='cuda:0')
episode: 318 training return: tensor(-103.4675, device='cuda:0')
episode: 319 training return: tensor(-86.6278, device='cuda:0')
epoch: 80 test_true_pfm: 79.10098948879113 sim_pfm: -147.11381268096738
episode: 320 training return: tensor(-78.9712, device='cuda:0')
episode: 321 training return: tensor(-136.5810, device='cuda:0')
episode: 322 training return: tensor(-68.2991, device='cuda:0')
episode: 323 training return: tensor(-67.5831, device='cuda:0')
epoch: 81 test_true_pfm: 70.97532592340221 sim_pfm: -88.32224608893156
episode: 324 training return: tensor(-141.4345, device='cuda:0')
episode: 325 training return: tensor(-120.2788, device='cuda:0')
episode: 326 training return: tensor(-111.8800, device='cuda:0')
episode: 327 training return: tensor(-211.2666, device='cuda:0')
epoch: 82 test_true_pfm: 78.05840579797808 sim_pfm: -99.17290642472798
episode: 328 training return: tensor(-117.4920, device='cuda:0')
episode: 329 training return: tensor(-99.6166, device='cuda:0')
episode: 330 training return: tensor(-94.3993, device='cuda:0')
episode: 331 training return: tensor(-127.2046, device='cuda:0')
epoch: 83 test_true_pfm: 89.40370052486398 sim_pfm: -124.22698830848677
episode: 332 training return: tensor(-125.4764, device='cuda:0')
episode: 333 training return: tensor(-121.7708, device='cuda:0')
episode: 334 training return: tensor(-210.5941, device='cuda:0')
episode: 335 training return: tensor(-218.9709, device='cuda:0')
epoch: 84 test_true_pfm: 66.06692518890566 sim_pfm: -128.76661866391078
episode: 336 training return: tensor(-106.9643, device='cuda:0')
episode: 337 training return: tensor(-134.0529, device='cuda:0')
episode: 338 training return: tensor(-79.4514, device='cuda:0')
episode: 339 training return: tensor(-213.3225, device='cuda:0')
epoch: 85 test_true_pfm: 61.7325088003583 sim_pfm: -131.24117161151952
episode: 340 training return: tensor(-105.1364, device='cuda:0')
episode: 341 training return: tensor(-151.1766, device='cuda:0')
episode: 342 training return: tensor(-144.0305, device='cuda:0')
episode: 343 training return: tensor(-200.6916, device='cuda:0')
epoch: 86 test_true_pfm: 55.67036379923711 sim_pfm: -149.8339110728004
episode: 344 training return: tensor(-151.1004, device='cuda:0')
episode: 345 training return: tensor(-130.6739, device='cuda:0')
episode: 346 training return: tensor(-124.4155, device='cuda:0')
episode: 347 training return: tensor(-129.3938, device='cuda:0')
epoch: 87 test_true_pfm: 70.97015884174907 sim_pfm: -140.59033555072966
episode: 348 training return: tensor(-143.1544, device='cuda:0')
episode: 349 training return: tensor(-124.0009, device='cuda:0')
episode: 350 training return: tensor(-153.6608, device='cuda:0')
episode: 351 training return: tensor(-92.4910, device='cuda:0')
epoch: 88 test_true_pfm: 61.88788874488465 sim_pfm: -110.79260979899554
episode: 352 training return: tensor(-127.4263, device='cuda:0')
episode: 353 training return: tensor(-51.1528, device='cuda:0')
episode: 354 training return: tensor(-212.5696, device='cuda:0')
episode: 355 training return: tensor(-150.4694, device='cuda:0')
epoch: 89 test_true_pfm: 79.60030440499672 sim_pfm: -119.98862154252711
episode: 356 training return: tensor(-96.7980, device='cuda:0')
episode: 357 training return: tensor(-66.9654, device='cuda:0')
episode: 358 training return: tensor(-122.1782, device='cuda:0')
episode: 359 training return: tensor(-115.4285, device='cuda:0')
epoch: 90 test_true_pfm: 64.46247204013059 sim_pfm: -162.04908373310462
episode: 360 training return: tensor(-61.4952, device='cuda:0')
episode: 361 training return: tensor(-91.6856, device='cuda:0')
episode: 362 training return: tensor(-114.0909, device='cuda:0')
episode: 363 training return: tensor(-201.4858, device='cuda:0')
epoch: 91 test_true_pfm: 87.64764029654863 sim_pfm: -128.34744248491478
episode: 364 training return: tensor(-88.8643, device='cuda:0')
episode: 365 training return: tensor(-71.1482, device='cuda:0')
episode: 366 training return: tensor(-93.7766, device='cuda:0')
episode: 367 training return: tensor(-210.2081, device='cuda:0')
epoch: 92 test_true_pfm: 78.01450374456226 sim_pfm: -108.53246063874685
episode: 368 training return: tensor(-93.9768, device='cuda:0')
episode: 369 training return: tensor(-121.9568, device='cuda:0')
episode: 370 training return: tensor(-207.1918, device='cuda:0')
episode: 371 training return: tensor(-86.7852, device='cuda:0')
epoch: 93 test_true_pfm: 60.24073057579087 sim_pfm: -143.32627190701896
episode: 372 training return: tensor(-120.4125, device='cuda:0')
episode: 373 training return: tensor(-80.8275, device='cuda:0')
episode: 374 training return: tensor(-107.4045, device='cuda:0')
episode: 375 training return: tensor(-65.0490, device='cuda:0')
epoch: 94 test_true_pfm: 62.267802057928876 sim_pfm: -102.69936132476433
episode: 376 training return: tensor(-93.9930, device='cuda:0')
episode: 377 training return: tensor(-214.5697, device='cuda:0')
episode: 378 training return: tensor(-210.4700, device='cuda:0')
episode: 379 training return: tensor(-94.8585, device='cuda:0')
epoch: 95 test_true_pfm: 43.83724859477178 sim_pfm: -108.22062077709124
episode: 380 training return: tensor(-92.9241, device='cuda:0')
episode: 381 training return: tensor(-95.7802, device='cuda:0')
episode: 382 training return: tensor(-154.7627, device='cuda:0')
episode: 383 training return: tensor(-81.8337, device='cuda:0')
epoch: 96 test_true_pfm: 50.3570442331613 sim_pfm: -180.25091023292626
episode: 384 training return: tensor(-86.9375, device='cuda:0')
episode: 385 training return: tensor(-140.9306, device='cuda:0')
episode: 386 training return: tensor(-65.4272, device='cuda:0')
episode: 387 training return: tensor(-139.4167, device='cuda:0')
epoch: 97 test_true_pfm: 78.68320310022669 sim_pfm: -133.65390261072315
episode: 388 training return: tensor(-97.0264, device='cuda:0')
episode: 389 training return: tensor(-208.8590, device='cuda:0')
episode: 390 training return: tensor(-62.4215, device='cuda:0')
episode: 391 training return: tensor(-145.5979, device='cuda:0')
epoch: 98 test_true_pfm: 54.125251657706414 sim_pfm: -74.08813340257038
episode: 392 training return: tensor(-147.8196, device='cuda:0')
episode: 393 training return: tensor(-80.9252, device='cuda:0')
episode: 394 training return: tensor(-147.9897, device='cuda:0')
episode: 395 training return: tensor(-96.8021, device='cuda:0')
epoch: 99 test_true_pfm: 63.48205500903374 sim_pfm: -101.99847128595574
episode: 396 training return: tensor(-98.4945, device='cuda:0')
episode: 397 training return: tensor(-78.5268, device='cuda:0')
episode: 398 training return: tensor(-201.8768, device='cuda:0')
episode: 399 training return: tensor(-132.5873, device='cuda:0')
epoch: 100 test_true_pfm: 70.29614061636323 sim_pfm: -131.58351996873972
episode: 400 training return: tensor(-144.4065, device='cuda:0')
episode: 401 training return: tensor(-127.9251, device='cuda:0')
episode: 402 training return: tensor(-199.8302, device='cuda:0')
episode: 403 training return: tensor(-139.1712, device='cuda:0')
epoch: 101 test_true_pfm: 43.79917600400522 sim_pfm: -99.43544975235127
episode: 404 training return: tensor(-99.9089, device='cuda:0')
episode: 405 training return: tensor(-76.8396, device='cuda:0')
episode: 406 training return: tensor(-74.7252, device='cuda:0')
episode: 407 training return: tensor(-79.7258, device='cuda:0')
epoch: 102 test_true_pfm: 68.62511137338663 sim_pfm: -123.22095501060831
episode: 408 training return: tensor(-115.8016, device='cuda:0')
episode: 409 training return: tensor(-131.1536, device='cuda:0')
episode: 410 training return: tensor(-133.9333, device='cuda:0')
episode: 411 training return: tensor(-201.6503, device='cuda:0')
epoch: 103 test_true_pfm: 81.72489880678006 sim_pfm: -78.25968428777996
episode: 412 training return: tensor(-83.4989, device='cuda:0')
episode: 413 training return: tensor(-97.0700, device='cuda:0')
episode: 414 training return: tensor(-80.9634, device='cuda:0')
episode: 415 training return: tensor(-139.9686, device='cuda:0')
epoch: 104 test_true_pfm: 55.133514715319755 sim_pfm: -129.14297105538427
episode: 416 training return: tensor(-157.0784, device='cuda:0')
episode: 417 training return: tensor(-134.6047, device='cuda:0')
episode: 418 training return: tensor(-138.8161, device='cuda:0')
episode: 419 training return: tensor(-113.7192, device='cuda:0')
epoch: 105 test_true_pfm: 68.3368135082285 sim_pfm: -96.77187396453228
episode: 420 training return: tensor(-96.1154, device='cuda:0')
episode: 421 training return: tensor(-82.9370, device='cuda:0')
episode: 422 training return: tensor(-117.4192, device='cuda:0')
episode: 423 training return: tensor(-140.4225, device='cuda:0')
epoch: 106 test_true_pfm: 66.94470785028254 sim_pfm: -120.34765170910396
episode: 424 training return: tensor(-135.8580, device='cuda:0')
episode: 425 training return: tensor(-123.6072, device='cuda:0')
episode: 426 training return: tensor(-80.4404, device='cuda:0')
episode: 427 training return: tensor(-202.4913, device='cuda:0')
epoch: 107 test_true_pfm: 60.86246854251503 sim_pfm: -102.52448044706834
episode: 428 training return: tensor(-70.4693, device='cuda:0')
episode: 429 training return: tensor(-132.0742, device='cuda:0')
episode: 430 training return: tensor(-81.6291, device='cuda:0')
episode: 431 training return: tensor(-73.7746, device='cuda:0')
epoch: 108 test_true_pfm: 64.08227438342017 sim_pfm: -118.4918645249796
episode: 432 training return: tensor(-108.5064, device='cuda:0')
episode: 433 training return: tensor(-100.3131, device='cuda:0')
episode: 434 training return: tensor(-75.7142, device='cuda:0')
episode: 435 training return: tensor(-64.1205, device='cuda:0')
epoch: 109 test_true_pfm: 53.88066959034946 sim_pfm: -131.98598641924326
episode: 436 training return: tensor(-80.1978, device='cuda:0')
episode: 437 training return: tensor(-103.4514, device='cuda:0')
episode: 438 training return: tensor(-80.5020, device='cuda:0')
episode: 439 training return: tensor(-83.5819, device='cuda:0')
epoch: 110 test_true_pfm: 79.43668215595038 sim_pfm: -102.7170764742652
episode: 440 training return: tensor(-69.0624, device='cuda:0')
episode: 441 training return: tensor(-76.3966, device='cuda:0')
episode: 442 training return: tensor(-74.7500, device='cuda:0')
episode: 443 training return: tensor(-117.7312, device='cuda:0')
epoch: 111 test_true_pfm: 71.9443109342533 sim_pfm: -134.04443645084976
episode: 444 training return: tensor(-81.4375, device='cuda:0')
episode: 445 training return: tensor(-200.9328, device='cuda:0')
episode: 446 training return: tensor(-75.8963, device='cuda:0')
episode: 447 training return: tensor(-116.6289, device='cuda:0')
epoch: 112 test_true_pfm: 76.93460764709235 sim_pfm: -125.60737675598357
episode: 448 training return: tensor(-141.5447, device='cuda:0')
episode: 449 training return: tensor(-91.9163, device='cuda:0')
episode: 450 training return: tensor(-67.7239, device='cuda:0')
episode: 451 training return: tensor(-109.5795, device='cuda:0')
epoch: 113 test_true_pfm: 73.4715503865325 sim_pfm: -127.04503605910577
episode: 452 training return: tensor(-75.9346, device='cuda:0')
episode: 453 training return: tensor(-94.0515, device='cuda:0')
episode: 454 training return: tensor(-123.9038, device='cuda:0')
episode: 455 training return: tensor(-207.4159, device='cuda:0')
epoch: 114 test_true_pfm: 52.731925610630086 sim_pfm: -95.78545590115246
episode: 456 training return: tensor(-108.1938, device='cuda:0')
episode: 457 training return: tensor(-118.9877, device='cuda:0')
episode: 458 training return: tensor(-85.5325, device='cuda:0')
episode: 459 training return: tensor(-159.1666, device='cuda:0')
epoch: 115 test_true_pfm: 80.85009466777694 sim_pfm: -133.14171182266438
episode: 460 training return: tensor(-93.5541, device='cuda:0')
episode: 461 training return: tensor(-95.5950, device='cuda:0')
episode: 462 training return: tensor(-118.2357, device='cuda:0')
episode: 463 training return: tensor(-159.9601, device='cuda:0')
epoch: 116 test_true_pfm: 62.85997231783417 sim_pfm: -155.1317350920057
episode: 464 training return: tensor(-204.3418, device='cuda:0')
episode: 465 training return: tensor(-97.2903, device='cuda:0')
episode: 466 training return: tensor(-206.9563, device='cuda:0')
episode: 467 training return: tensor(-135.7080, device='cuda:0')
epoch: 117 test_true_pfm: 74.0344295935389 sim_pfm: -122.1824637191894
episode: 468 training return: tensor(-64.3230, device='cuda:0')
episode: 469 training return: tensor(-212.7988, device='cuda:0')
episode: 470 training return: tensor(-81.4087, device='cuda:0')
episode: 471 training return: tensor(-76.6170, device='cuda:0')
epoch: 118 test_true_pfm: 80.05512267540983 sim_pfm: -117.19889318908099
episode: 472 training return: tensor(-136.5486, device='cuda:0')
episode: 473 training return: tensor(-202.1226, device='cuda:0')
episode: 474 training return: tensor(-123.9570, device='cuda:0')
episode: 475 training return: tensor(-140.5875, device='cuda:0')
epoch: 119 test_true_pfm: 70.96419605095551 sim_pfm: -91.25431870615576
episode: 476 training return: tensor(-144.2050, device='cuda:0')
episode: 477 training return: tensor(-62.5123, device='cuda:0')
episode: 478 training return: tensor(-115.8902, device='cuda:0')
episode: 479 training return: tensor(-95.3938, device='cuda:0')
epoch: 120 test_true_pfm: 73.59866661953424 sim_pfm: -133.62910850506742
episode: 480 training return: tensor(-131.3049, device='cuda:0')
episode: 481 training return: tensor(-82.8857, device='cuda:0')
episode: 482 training return: tensor(-65.4906, device='cuda:0')
episode: 483 training return: tensor(-92.4624, device='cuda:0')
epoch: 121 test_true_pfm: 84.71749341893577 sim_pfm: -101.04062742380192
episode: 484 training return: tensor(-134.3094, device='cuda:0')
episode: 485 training return: tensor(-89.2833, device='cuda:0')
episode: 486 training return: tensor(-126.4472, device='cuda:0')
episode: 487 training return: tensor(-55.8572, device='cuda:0')
epoch: 122 test_true_pfm: 80.60014201641256 sim_pfm: -81.9483846437768
episode: 488 training return: tensor(-64.4944, device='cuda:0')
episode: 489 training return: tensor(-59.2231, device='cuda:0')
episode: 490 training return: tensor(-133.8797, device='cuda:0')
episode: 491 training return: tensor(-127.2850, device='cuda:0')
epoch: 123 test_true_pfm: 72.73213504052248 sim_pfm: -147.50845292703016
episode: 492 training return: tensor(-83.0025, device='cuda:0')
episode: 493 training return: tensor(-86.2780, device='cuda:0')
episode: 494 training return: tensor(-123.8407, device='cuda:0')
episode: 495 training return: tensor(-80.2470, device='cuda:0')
epoch: 124 test_true_pfm: 63.85501381101418 sim_pfm: -116.74900248313206
episode: 496 training return: tensor(-64.5519, device='cuda:0')
episode: 497 training return: tensor(-67.2122, device='cuda:0')
episode: 498 training return: tensor(-99.1009, device='cuda:0')
episode: 499 training return: tensor(-79.1750, device='cuda:0')
epoch: 125 test_true_pfm: 61.14703382009054 sim_pfm: -95.55212252096389
episode: 500 training return: tensor(-141.6442, device='cuda:0')
episode: 501 training return: tensor(-206.9420, device='cuda:0')
episode: 502 training return: tensor(-83.2744, device='cuda:0')
episode: 503 training return: tensor(-209.2880, device='cuda:0')
epoch: 126 test_true_pfm: 78.20302835790505 sim_pfm: -100.68679394343053
episode: 504 training return: tensor(-70.6787, device='cuda:0')
episode: 505 training return: tensor(-58.8527, device='cuda:0')
episode: 506 training return: tensor(-56.5988, device='cuda:0')
episode: 507 training return: tensor(-61.4684, device='cuda:0')
epoch: 127 test_true_pfm: 73.52624872397331 sim_pfm: -77.97645968841971
episode: 508 training return: tensor(-62.6334, device='cuda:0')
episode: 509 training return: tensor(-55.8583, device='cuda:0')
episode: 510 training return: tensor(-74.6430, device='cuda:0')
episode: 511 training return: tensor(-73.7419, device='cuda:0')
epoch: 128 test_true_pfm: 77.77068862974656 sim_pfm: -103.0349382424727
episode: 512 training return: tensor(-130.3766, device='cuda:0')
episode: 513 training return: tensor(-101.4743, device='cuda:0')
episode: 514 training return: tensor(-70.8380, device='cuda:0')
episode: 515 training return: tensor(-163.8930, device='cuda:0')
epoch: 129 test_true_pfm: 83.48624733195636 sim_pfm: -83.18552221765276
episode: 516 training return: tensor(-208.2435, device='cuda:0')
episode: 517 training return: tensor(-83.9469, device='cuda:0')
episode: 518 training return: tensor(-140.7308, device='cuda:0')
episode: 519 training return: tensor(-115.2328, device='cuda:0')
epoch: 130 test_true_pfm: 79.93877847586683 sim_pfm: -160.54895047496538
episode: 520 training return: tensor(-64.0576, device='cuda:0')
episode: 521 training return: tensor(-156.5330, device='cuda:0')
episode: 522 training return: tensor(-66.9532, device='cuda:0')
episode: 523 training return: tensor(-113.5268, device='cuda:0')
epoch: 131 test_true_pfm: 69.93552317527728 sim_pfm: -87.99150049544987
episode: 524 training return: tensor(-137.2439, device='cuda:0')
episode: 525 training return: tensor(-126.8743, device='cuda:0')
episode: 526 training return: tensor(-92.1940, device='cuda:0')
episode: 527 training return: tensor(-79.2335, device='cuda:0')
epoch: 132 test_true_pfm: 77.77873392897477 sim_pfm: -157.99411564781332
episode: 528 training return: tensor(-210.2203, device='cuda:0')
episode: 529 training return: tensor(-141.2063, device='cuda:0')
episode: 530 training return: tensor(-55.3050, device='cuda:0')
episode: 531 training return: tensor(-59.2332, device='cuda:0')
epoch: 133 test_true_pfm: 80.10230392213712 sim_pfm: -116.09209724747343
episode: 532 training return: tensor(-80.0127, device='cuda:0')
episode: 533 training return: tensor(-158.0490, device='cuda:0')
episode: 534 training return: tensor(-134.4543, device='cuda:0')
episode: 535 training return: tensor(-113.2013, device='cuda:0')
epoch: 134 test_true_pfm: 69.2547009237611 sim_pfm: -110.86021831014659
episode: 536 training return: tensor(-137.4959, device='cuda:0')
episode: 537 training return: tensor(-123.5320, device='cuda:0')
episode: 538 training return: tensor(-71.4135, device='cuda:0')
episode: 539 training return: tensor(-127.1510, device='cuda:0')
epoch: 135 test_true_pfm: 62.233218549041865 sim_pfm: -98.41028545099543
episode: 540 training return: tensor(-219.9063, device='cuda:0')
episode: 541 training return: tensor(-97.8062, device='cuda:0')
episode: 542 training return: tensor(-68.0453, device='cuda:0')
episode: 543 training return: tensor(-132.7067, device='cuda:0')
epoch: 136 test_true_pfm: 72.36759526761347 sim_pfm: -120.5078834043583
episode: 544 training return: tensor(-72.4255, device='cuda:0')
episode: 545 training return: tensor(-112.9124, device='cuda:0')
episode: 546 training return: tensor(-131.9667, device='cuda:0')
episode: 547 training return: tensor(-64.8056, device='cuda:0')
epoch: 137 test_true_pfm: 89.79996009298475 sim_pfm: -124.87339479880174
episode: 548 training return: tensor(-117.0824, device='cuda:0')
episode: 549 training return: tensor(-110.1464, device='cuda:0')
episode: 550 training return: tensor(-64.5947, device='cuda:0')
episode: 551 training return: tensor(-75.3385, device='cuda:0')
epoch: 138 test_true_pfm: 61.372249459270265 sim_pfm: -108.52432708107517
episode: 552 training return: tensor(-79.7762, device='cuda:0')
episode: 553 training return: tensor(-134.4766, device='cuda:0')
episode: 554 training return: tensor(-62.5650, device='cuda:0')
episode: 555 training return: tensor(-84.7341, device='cuda:0')
epoch: 139 test_true_pfm: 67.72913414084084 sim_pfm: -94.4392296644568
episode: 556 training return: tensor(-126.7075, device='cuda:0')
episode: 557 training return: tensor(-114.0347, device='cuda:0')
episode: 558 training return: tensor(-216.2471, device='cuda:0')
episode: 559 training return: tensor(-61.1335, device='cuda:0')
epoch: 140 test_true_pfm: 67.7677842237686 sim_pfm: -108.95526817400824
episode: 560 training return: tensor(-92.8112, device='cuda:0')
episode: 561 training return: tensor(-59.4896, device='cuda:0')
episode: 562 training return: tensor(-75.9217, device='cuda:0')
episode: 563 training return: tensor(-133.0289, device='cuda:0')
epoch: 141 test_true_pfm: 72.40310905545377 sim_pfm: -99.75205815981026
episode: 564 training return: tensor(-112.4543, device='cuda:0')
episode: 565 training return: tensor(-66.4377, device='cuda:0')
episode: 566 training return: tensor(-73.1843, device='cuda:0')
episode: 567 training return: tensor(-145.6583, device='cuda:0')
epoch: 142 test_true_pfm: 60.93023920597633 sim_pfm: -140.22680880608385
episode: 568 training return: tensor(-74.6667, device='cuda:0')
episode: 569 training return: tensor(-132.7853, device='cuda:0')
episode: 570 training return: tensor(-82.4836, device='cuda:0')
episode: 571 training return: tensor(-213.6363, device='cuda:0')
epoch: 143 test_true_pfm: 59.36449932644361 sim_pfm: -90.06841886339825
episode: 572 training return: tensor(-74.1950, device='cuda:0')
episode: 573 training return: tensor(-63.4458, device='cuda:0')
episode: 574 training return: tensor(-117.2757, device='cuda:0')
episode: 575 training return: tensor(-69.1585, device='cuda:0')
epoch: 144 test_true_pfm: 70.5763598158833 sim_pfm: -108.6406590554514
episode: 576 training return: tensor(-69.7919, device='cuda:0')
episode: 577 training return: tensor(-53.5898, device='cuda:0')
episode: 578 training return: tensor(-91.7198, device='cuda:0')
episode: 579 training return: tensor(-106.8682, device='cuda:0')
epoch: 145 test_true_pfm: 62.560507187480894 sim_pfm: -117.82526980078546
episode: 580 training return: tensor(-127.5825, device='cuda:0')
episode: 581 training return: tensor(-77.2662, device='cuda:0')
episode: 582 training return: tensor(-67.4225, device='cuda:0')
episode: 583 training return: tensor(-76.4477, device='cuda:0')
epoch: 146 test_true_pfm: 52.314429935312276 sim_pfm: -81.07291333138127
episode: 584 training return: tensor(-88.7494, device='cuda:0')
episode: 585 training return: tensor(-62.5315, device='cuda:0')
episode: 586 training return: tensor(-51.1122, device='cuda:0')
episode: 587 training return: tensor(-82.3398, device='cuda:0')
epoch: 147 test_true_pfm: 80.00950511095533 sim_pfm: -113.56197672922863
episode: 588 training return: tensor(-75.0001, device='cuda:0')
episode: 589 training return: tensor(-81.1156, device='cuda:0')
episode: 590 training return: tensor(-95.8694, device='cuda:0')
episode: 591 training return: tensor(-57.8811, device='cuda:0')
epoch: 148 test_true_pfm: 89.27170615221809 sim_pfm: -98.27105507539235
episode: 592 training return: tensor(-108.5728, device='cuda:0')
episode: 593 training return: tensor(-84.4042, device='cuda:0')
episode: 594 training return: tensor(-84.0795, device='cuda:0')
episode: 595 training return: tensor(-140.2178, device='cuda:0')
epoch: 149 test_true_pfm: 83.78079869969955 sim_pfm: -99.33184708807384
episode: 596 training return: tensor(-76.8845, device='cuda:0')
episode: 597 training return: tensor(-68.3305, device='cuda:0')
episode: 598 training return: tensor(-86.8749, device='cuda:0')
episode: 599 training return: tensor(-218.0570, device='cuda:0')
epoch: 150 test_true_pfm: 69.651046412913 sim_pfm: -96.51921971628909
