epoch: 0 training_loss 0.33120076209306715 test_loss: 0.26731076240539553
epoch: 1 training_loss 0.22277364999055863 test_loss: 0.19701581001281737
epoch: 2 training_loss 0.19461078837513923 test_loss: 0.18977069854736328
epoch: 3 training_loss 0.1645626626908779 test_loss: 0.16820824146270752
epoch: 4 training_loss 0.16174467630684375 test_loss: 0.1739922881126404
epoch: 5 training_loss 0.16014422670006753 test_loss: 0.1453403949737549
epoch: 6 training_loss 0.15078098863363265 test_loss: 0.1708085060119629
epoch: 7 training_loss 0.1433061884343624 test_loss: 0.11998175382614136
epoch: 8 training_loss 0.1381562876328826 test_loss: 0.16926718950271608
epoch: 9 training_loss 0.13420696903020143 test_loss: 0.1542101263999939
epoch: 10 training_loss 0.13856215804815292 test_loss: 0.12265567779541016
epoch: 11 training_loss 0.13237071350216867 test_loss: 0.14384926557540895
epoch: 12 training_loss 0.13876179490238427 test_loss: 0.13062044382095336
epoch: 13 training_loss 0.12883858572691678 test_loss: 0.1292984127998352
epoch: 14 training_loss 0.12420594990253449 test_loss: 0.15081844329833985
epoch: 15 training_loss 0.13923309661448002 test_loss: 0.12516683340072632
epoch: 16 training_loss 0.12842271979898215 test_loss: 0.1241498351097107
epoch: 17 training_loss 0.12916250605136156 test_loss: 0.10817286968231202
epoch: 18 training_loss 0.11834622327238321 test_loss: 0.12476446628570556
epoch: 19 training_loss 0.12366461399942637 test_loss: 0.12307858467102051
epoch: 20 training_loss 0.11863102436065674 test_loss: 0.1312306761741638
epoch: 21 training_loss 0.11226583264768124 test_loss: 0.1386982321739197
epoch: 22 training_loss 0.116422396376729 test_loss: 0.1121724009513855
epoch: 23 training_loss 0.12524254627525808 test_loss: 0.13491199016571045
epoch: 24 training_loss 0.12594974394887687 test_loss: 0.13694525957107545
epoch: 25 training_loss 0.12236188225448132 test_loss: 0.117012619972229
epoch: 26 training_loss 0.1265564700961113 test_loss: 0.1451251983642578
epoch: 27 training_loss 0.11336356110870838 test_loss: 0.1027022123336792
epoch: 28 training_loss 0.11592167807742954 test_loss: 0.12353898286819458
epoch: 29 training_loss 0.11579192623496055 test_loss: 0.11981619596481323
epoch: 30 training_loss 0.11436535701155663 test_loss: 0.11764986515045166
epoch: 31 training_loss 0.11495102249085903 test_loss: 0.14249011278152465
epoch: 32 training_loss 0.11294707711786031 test_loss: 0.13290395736694335
epoch: 33 training_loss 0.11510297179222106 test_loss: 0.11054891347885132
epoch: 34 training_loss 0.12348554331809282 test_loss: 0.11015430688858033
epoch: 35 training_loss 0.11404695685952902 test_loss: 0.10737892389297485
epoch: 36 training_loss 0.11802541602402926 test_loss: 0.0962054967880249
epoch: 37 training_loss 0.11645487770438194 test_loss: 0.14524295330047607
epoch: 38 training_loss 0.11898288525640964 test_loss: 0.12593864202499389
epoch: 39 training_loss 0.11692800875753165 test_loss: 0.10570474863052368
epoch: 40 training_loss 0.11142228431999683 test_loss: 0.13432638645172118
epoch: 41 training_loss 0.11818870764225721 test_loss: 0.10624938011169434
epoch: 42 training_loss 0.11263599123805762 test_loss: 0.09951695203781127
epoch: 43 training_loss 0.11927404154092074 test_loss: 0.13350013494491578
epoch: 44 training_loss 0.11140540927648544 test_loss: 0.12002679109573364
epoch: 45 training_loss 0.12188735723495484 test_loss: 0.11938681602478027
epoch: 46 training_loss 0.11407444257289172 test_loss: 0.12609196901321412
epoch: 47 training_loss 0.10260562989860773 test_loss: 0.13355616331100464
epoch: 48 training_loss 0.12165744967758656 test_loss: 0.09920786023139953
epoch: 49 training_loss 0.11541583266109229 test_loss: 0.11184102296829224
epoch: 50 training_loss 0.11017830746248364 test_loss: 0.11543294191360473
epoch: 51 training_loss 0.10821641925722361 test_loss: 0.12349075078964233
epoch: 52 training_loss 0.11183953752741217 test_loss: 0.11139955520629882
epoch: 53 training_loss 0.11090326961129904 test_loss: 0.12915642261505128
epoch: 54 training_loss 0.1085361704044044 test_loss: 0.1122780442237854
epoch: 55 training_loss 0.11786803506314754 test_loss: 0.1061165452003479
epoch: 56 training_loss 0.11739493852481246 test_loss: 0.11602166891098023
epoch: 57 training_loss 0.11415633890777827 test_loss: 0.13349689245224
epoch: 58 training_loss 0.1134183962456882 test_loss: 0.1218505859375
epoch: 59 training_loss 0.11863833103328943 test_loss: 0.11155822277069091
epoch: 60 training_loss 0.11054045947268605 test_loss: 0.10558761358261108
epoch: 61 training_loss 0.11598843839019538 test_loss: 0.09180696606636048
epoch: 62 training_loss 0.10805622341111303 test_loss: 0.10541220903396606
epoch: 63 training_loss 0.10963051375001669 test_loss: 0.1540538787841797
epoch: 64 training_loss 0.11111630683764816 test_loss: 0.09663888812065125
epoch: 65 training_loss 0.103174584582448 test_loss: 0.12490077018737793
epoch: 66 training_loss 0.10786550600081682 test_loss: 0.10016520023345947
epoch: 67 training_loss 0.11008828956633807 test_loss: 0.11324557065963745
epoch: 68 training_loss 0.1066839661821723 test_loss: 0.11950187683105469
epoch: 69 training_loss 0.11600672300904989 test_loss: 0.11246720552444459
epoch: 70 training_loss 0.11045395389199257 test_loss: 0.11649131774902344
epoch: 71 training_loss 0.10972103254869581 test_loss: 0.11109331846237183
epoch: 72 training_loss 0.10382878353819251 test_loss: 0.10880471467971801
epoch: 73 training_loss 0.10821233704686165 test_loss: 0.09775636196136475
epoch: 74 training_loss 0.11233299180865287 test_loss: 0.11051956415176392
epoch: 75 training_loss 0.1057416358217597 test_loss: 0.12173799276351929
epoch: 76 training_loss 0.10593715159222483 test_loss: 0.11753689050674439
epoch: 77 training_loss 0.10852118272334338 test_loss: 0.11383885145187378
epoch: 78 training_loss 0.10839677531272172 test_loss: 0.12088985443115234
epoch: 79 training_loss 0.10806623060256243 test_loss: 0.09780252575874329
epoch: 80 training_loss 0.10892555212602019 test_loss: 0.1294979691505432
epoch: 81 training_loss 0.11133445218205452 test_loss: 0.11238683462142944
epoch: 82 training_loss 0.10915479347109795 test_loss: 0.10612382888793945
epoch: 83 training_loss 0.11030458722263575 test_loss: 0.12347769737243652
epoch: 84 training_loss 0.11029666993767023 test_loss: 0.10716935396194457
epoch: 85 training_loss 0.10910072557628155 test_loss: 0.1220393419265747
epoch: 86 training_loss 0.11095600532367826 test_loss: 0.11253943443298339
epoch: 87 training_loss 0.10532297872006893 test_loss: 0.11672784090042114
epoch: 88 training_loss 0.11275637030601501 test_loss: 0.10156877040863037
epoch: 89 training_loss 0.10641074081882834 test_loss: 0.1290561318397522
epoch: 90 training_loss 0.10598803563043475 test_loss: 0.11192785501480103
epoch: 91 training_loss 0.10593779480084776 test_loss: 0.10503381490707397
epoch: 92 training_loss 0.116934714037925 test_loss: 0.10937769412994384
epoch: 93 training_loss 0.10774883419275284 test_loss: 0.0997623324394226
epoch: 94 training_loss 0.10678346171975135 test_loss: 0.11020088195800781
epoch: 95 training_loss 0.11341643603518606 test_loss: 0.10350757837295532
epoch: 96 training_loss 0.10909245938062667 test_loss: 0.09000488519668579
epoch: 97 training_loss 0.11320763988420367 test_loss: 0.08946804404258728
epoch: 98 training_loss 0.10866074044257402 test_loss: 0.11381971836090088
epoch: 99 training_loss 0.1107760365307331 test_loss: 0.14959585666656494
epoch: 100 training_loss 0.11079153191298247 test_loss: 0.10292129516601563
epoch: 101 training_loss 0.10710959360003472 test_loss: 0.12218683958053589
epoch: 102 training_loss 0.10517506247386336 test_loss: 0.12274771928787231
epoch: 103 training_loss 0.11172037400305271 test_loss: 0.135292387008667
epoch: 104 training_loss 0.1055137349292636 test_loss: 0.12278133630752563
epoch: 105 training_loss 0.11193638941273093 test_loss: 0.12878966331481934
epoch: 106 training_loss 0.10841427311301231 test_loss: 0.129527747631073
epoch: 107 training_loss 0.10998691984452308 test_loss: 0.11239475011825562
epoch: 108 training_loss 0.10382432747632266 test_loss: 0.12898547649383546
epoch: 109 training_loss 0.11816299837082625 test_loss: 0.08799607753753662
epoch: 110 training_loss 0.11010452348738908 test_loss: 0.11200970411300659
epoch: 111 training_loss 0.10785486228764057 test_loss: 0.12344205379486084
epoch: 112 training_loss 0.10561313353478909 test_loss: 0.12283954620361329
epoch: 113 training_loss 0.10321631710976362 test_loss: 0.10177328586578369
epoch: 114 training_loss 0.09712022967636585 test_loss: 0.12168715000152588
epoch: 115 training_loss 0.11307979758828879 test_loss: 0.11759121417999267
epoch: 116 training_loss 0.11529692210257053 test_loss: 0.1223970890045166
epoch: 117 training_loss 0.10439194682985545 test_loss: 0.1168548583984375
epoch: 118 training_loss 0.10055449195206165 test_loss: 0.13630216121673583
epoch: 119 training_loss 0.09954353865236044 test_loss: 0.12065795660018921
epoch: 0 training_loss 47.37212224960327 test_loss: 26.108889770507812
epoch: 1 training_loss 20.32572946548462 test_loss: 17.5053466796875
epoch: 2 training_loss 14.913137235641479 test_loss: 13.704335021972657
epoch: 3 training_loss 12.400173540115356 test_loss: 10.86502685546875
epoch: 4 training_loss 10.482276954650878 test_loss: 9.91057891845703
epoch: 5 training_loss 9.135162672996522 test_loss: 8.888202667236328
epoch: 6 training_loss 8.456743783950806 test_loss: 8.122834014892579
epoch: 7 training_loss 7.740054383277893 test_loss: 7.3853706359863285
epoch: 8 training_loss 7.179287710189819 test_loss: 6.575731658935547
epoch: 9 training_loss 6.59790385723114 test_loss: 6.540753173828125
epoch: 10 training_loss 6.3026398229599 test_loss: 5.999489974975586
epoch: 11 training_loss 6.039628524780273 test_loss: 5.978433609008789
epoch: 12 training_loss 5.71575216293335 test_loss: 5.393084716796875
epoch: 13 training_loss 5.488786334991455 test_loss: 5.754590606689453
epoch: 14 training_loss 5.367388591766358 test_loss: 5.2373199462890625
epoch: 15 training_loss 5.102336220741272 test_loss: 5.478384399414063
epoch: 16 training_loss 4.9915357065200805 test_loss: 5.160860061645508
epoch: 17 training_loss 4.959742126464843 test_loss: 4.872937774658203
epoch: 18 training_loss 4.693798351287842 test_loss: 4.9402507781982425
epoch: 19 training_loss 4.7417123723030095 test_loss: 4.873858261108398
epoch: 20 training_loss 4.610957071781159 test_loss: 4.729713058471679
epoch: 21 training_loss 4.393597195148468 test_loss: 4.2535545349121096
epoch: 22 training_loss 4.335598726272583 test_loss: 4.080412673950195
epoch: 23 training_loss 4.3068278336524966 test_loss: 4.449750518798828
epoch: 24 training_loss 4.144636127948761 test_loss: 4.103544616699219
epoch: 25 training_loss 4.06647032737732 test_loss: 4.012295532226562
epoch: 26 training_loss 3.942015860080719 test_loss: 4.187449645996094
epoch: 27 training_loss 3.9009410333633423 test_loss: 4.004784774780274
epoch: 28 training_loss 3.9019758343696593 test_loss: 3.8282703399658202
epoch: 29 training_loss 3.8131243658065794 test_loss: 3.592927169799805
epoch: 30 training_loss 3.706352391242981 test_loss: 3.5421630859375
epoch: 31 training_loss 3.7575188422203065 test_loss: 3.5768123626708985
epoch: 32 training_loss 3.625775332450867 test_loss: 3.8102336883544923
epoch: 33 training_loss 3.606507041454315 test_loss: 3.4388805389404298
epoch: 34 training_loss 3.526252021789551 test_loss: 3.4396999359130858
epoch: 35 training_loss 3.51314888715744 test_loss: 3.440266418457031
epoch: 36 training_loss 3.411373162269592 test_loss: 3.5182750701904295
epoch: 37 training_loss 3.3543767619132994 test_loss: 3.5069881439208985
epoch: 38 training_loss 3.3582915568351748 test_loss: 3.359706497192383
epoch: 39 training_loss 3.2535090804100038 test_loss: 3.293363571166992
epoch: 40 training_loss 3.260534152984619 test_loss: 3.265654373168945
epoch: 41 training_loss 3.258062798976898 test_loss: 3.431167221069336
epoch: 42 training_loss 3.1732807326316834 test_loss: 3.3493896484375
epoch: 43 training_loss 3.145274088382721 test_loss: 3.2061397552490236
epoch: 44 training_loss 3.1259924817085265 test_loss: 3.3259662628173827
epoch: 45 training_loss 3.020059275627136 test_loss: 3.1059783935546874
epoch: 46 training_loss 3.0076222038269043 test_loss: 2.916332817077637
epoch: 47 training_loss 3.087449862957001 test_loss: 3.0877262115478517
epoch: 48 training_loss 3.001459517478943 test_loss: 3.0777507781982423
epoch: 49 training_loss 2.972995934486389 test_loss: 3.1373172760009767
epoch: 50 training_loss 2.954913818836212 test_loss: 2.706494903564453
epoch: 51 training_loss 2.8914363741874696 test_loss: 2.9470252990722656
epoch: 52 training_loss 2.8547811818122866 test_loss: 3.100658416748047
epoch: 53 training_loss 2.825473461151123 test_loss: 3.0560222625732423
epoch: 54 training_loss 2.853389394283295 test_loss: 2.7485260009765624
epoch: 55 training_loss 2.845220730304718 test_loss: 2.9557043075561524
epoch: 56 training_loss 2.86346715927124 test_loss: 2.8559803009033202
epoch: 57 training_loss 2.8352104091644286 test_loss: 3.108021926879883
epoch: 58 training_loss 2.736016085147858 test_loss: 2.7485845565795897
epoch: 59 training_loss 2.751525468826294 test_loss: 2.8590795516967775
epoch: 60 training_loss 2.7431165170669556 test_loss: 2.532905387878418
epoch: 61 training_loss 2.7199645757675173 test_loss: 2.739137649536133
epoch: 62 training_loss 2.7027318966388703 test_loss: 2.629426383972168
epoch: 63 training_loss 2.64690500497818 test_loss: 2.7502527236938477
epoch: 64 training_loss 2.683769201040268 test_loss: 2.593293571472168
epoch: 65 training_loss 2.6882871174812317 test_loss: 3.0101896286010743
epoch: 66 training_loss 2.574717186689377 test_loss: 2.6088600158691406
epoch: 67 training_loss 2.626746742725372 test_loss: 2.5182138442993165
epoch: 68 training_loss 2.572183527946472 test_loss: 2.4291011810302736
epoch: 69 training_loss 2.5347156810760496 test_loss: 2.9558622360229494
epoch: 70 training_loss 2.5752681827545167 test_loss: 2.5326374053955076
epoch: 71 training_loss 2.540325789451599 test_loss: 2.719326210021973
epoch: 72 training_loss 2.4344263792037966 test_loss: 2.3939464569091795
epoch: 73 training_loss 2.5142305088043213 test_loss: 2.700782585144043
epoch: 74 training_loss 2.5659173572063447 test_loss: 2.795277214050293
epoch: 75 training_loss 2.4497139823436735 test_loss: 2.5385128021240235
epoch: 76 training_loss 2.4331450390815736 test_loss: 2.5381731033325194
epoch: 77 training_loss 2.4202814531326293 test_loss: 2.4950490951538087
epoch: 78 training_loss 2.455361775159836 test_loss: 2.4394622802734376
epoch: 79 training_loss 2.4278436839580535 test_loss: 2.308350944519043
epoch: 80 training_loss 2.4256057119369507 test_loss: 2.180935096740723
epoch: 81 training_loss 2.3451920199394225 test_loss: 2.4289630889892577
epoch: 82 training_loss 2.373807810544968 test_loss: 2.395185089111328
epoch: 83 training_loss 2.359225836992264 test_loss: 2.354556083679199
epoch: 84 training_loss 2.3417269086837766 test_loss: 2.4727241516113283
epoch: 85 training_loss 2.3679611992836 test_loss: 2.590901565551758
epoch: 86 training_loss 2.3400730061531068 test_loss: 2.3586376190185545
epoch: 87 training_loss 2.3194723761081697 test_loss: 2.3706546783447267
epoch: 88 training_loss 2.278787615299225 test_loss: 2.313986396789551
epoch: 89 training_loss 2.3408178555965424 test_loss: 2.307289695739746
epoch: 90 training_loss 2.2654661667346954 test_loss: 2.391519546508789
epoch: 91 training_loss 2.2900157773494723 test_loss: 2.381943702697754
epoch: 92 training_loss 2.238690193891525 test_loss: 2.2672145843505858
epoch: 93 training_loss 2.2782531642913817 test_loss: 2.242123031616211
epoch: 94 training_loss 2.239688266515732 test_loss: 2.2259103775024416
epoch: 95 training_loss 2.2129786467552184 test_loss: 2.2742074966430663
epoch: 96 training_loss 2.2074689793586733 test_loss: 2.2967126846313475
epoch: 97 training_loss 2.2358677220344543 test_loss: 2.226231002807617
epoch: 98 training_loss 2.1596144604682923 test_loss: 2.2018003463745117
epoch: 99 training_loss 2.1712910497188567 test_loss: 2.21290283203125
epoch: 100 training_loss 2.178971130847931 test_loss: 2.0713708877563475
epoch: 101 training_loss 2.2184049129486083 test_loss: 1.9729825973510742
epoch: 102 training_loss 2.107158771753311 test_loss: 2.1645668029785154
epoch: 103 training_loss 2.1285131859779356 test_loss: 2.0041004180908204
epoch: 104 training_loss 2.1652590453624727 test_loss: 2.146995735168457
epoch: 105 training_loss 2.150007345676422 test_loss: 2.297289276123047
epoch: 106 training_loss 2.1239510655403135 test_loss: 2.035927391052246
epoch: 107 training_loss 2.0466156804561617 test_loss: 2.0517751693725588
epoch: 108 training_loss 2.1051807403564453 test_loss: 2.094333839416504
epoch: 109 training_loss 2.1301614308357237 test_loss: 2.3382242202758787
epoch: 110 training_loss 2.1037502443790435 test_loss: 2.042095756530762
epoch: 111 training_loss 2.065476598739624 test_loss: 2.113401412963867
epoch: 112 training_loss 2.0529611921310424 test_loss: 2.1712337493896485
epoch: 113 training_loss 2.0449416649341585 test_loss: 2.0101123809814454
epoch: 114 training_loss 2.0536166322231293 test_loss: 1.978807258605957
epoch: 115 training_loss 2.030497261285782 test_loss: 2.0687808990478516
epoch: 116 training_loss 2.01182977437973 test_loss: 2.219155120849609
epoch: 117 training_loss 2.027718517780304 test_loss: 2.052733039855957
epoch: 118 training_loss 2.0469600331783293 test_loss: 2.070015716552734
epoch: 119 training_loss 2.039771155118942 test_loss: 1.8872695922851563
episode: 0 training return: tensor(-969.0649, device='cuda:0')
episode: 1 training return: tensor(-570.0922, device='cuda:0')
episode: 2 training return: tensor(-999.9861, device='cuda:0')
episode: 3 training return: tensor(-988.6429, device='cuda:0')
epoch: 1 test_true_pfm: 3081.4683180263123 sim_pfm: -516.265172635011
episode: 4 training return: tensor(-999.9995, device='cuda:0')
episode: 5 training return: tensor(-994.6934, device='cuda:0')
episode: 6 training return: tensor(-999.9906, device='cuda:0')
episode: 7 training return: tensor(-849.9496, device='cuda:0')
epoch: 2 test_true_pfm: 2506.7620901546347 sim_pfm: -777.6551498463377
episode: 8 training return: tensor(-468.2753, device='cuda:0')
episode: 9 training return: tensor(-268.1474, device='cuda:0')
episode: 10 training return: tensor(-563.2643, device='cuda:0')
episode: 11 training return: tensor(-680.2853, device='cuda:0')
epoch: 3 test_true_pfm: 3876.694186918125 sim_pfm: -399.6018069028699
episode: 12 training return: tensor(-999.9984, device='cuda:0')
episode: 13 training return: tensor(-872.6536, device='cuda:0')
episode: 14 training return: tensor(-999.9991, device='cuda:0')
episode: 15 training return: tensor(-740.7616, device='cuda:0')
epoch: 4 test_true_pfm: 9098.11961964017 sim_pfm: -725.3462187819338
episode: 16 training return: tensor(-597.6049, device='cuda:0')
episode: 17 training return: tensor(-995.8851, device='cuda:0')
episode: 18 training return: tensor(-998.8036, device='cuda:0')
episode: 19 training return: tensor(-950.4745, device='cuda:0')
epoch: 5 test_true_pfm: 6548.293535406793 sim_pfm: -237.51403973961715
episode: 20 training return: tensor(-998.8792, device='cuda:0')
episode: 21 training return: tensor(-999.9998, device='cuda:0')
episode: 22 training return: tensor(-843.1669, device='cuda:0')
episode: 23 training return: tensor(-918.0024, device='cuda:0')
epoch: 6 test_true_pfm: 7064.336419164647 sim_pfm: -176.87160117767053
episode: 24 training return: tensor(-231.2757, device='cuda:0')
episode: 25 training return: tensor(-999.9938, device='cuda:0')
episode: 26 training return: tensor(-781.3873, device='cuda:0')
episode: 27 training return: tensor(-936.2460, device='cuda:0')
epoch: 7 test_true_pfm: 3623.0747780199786 sim_pfm: -128.45560164545896
episode: 28 training return: tensor(-407.8740, device='cuda:0')
episode: 29 training return: tensor(-999.9997, device='cuda:0')
episode: 30 training return: tensor(-217.5783, device='cuda:0')
episode: 31 training return: tensor(-838.2997, device='cuda:0')
epoch: 8 test_true_pfm: 4718.692792169802 sim_pfm: -695.5902442727917
episode: 32 training return: tensor(-509.2774, device='cuda:0')
episode: 33 training return: tensor(-659.1011, device='cuda:0')
episode: 34 training return: tensor(-258.3935, device='cuda:0')
episode: 35 training return: tensor(-391.1523, device='cuda:0')
epoch: 9 test_true_pfm: 4894.227073752437 sim_pfm: -646.5938940831887
episode: 36 training return: tensor(-999.7788, device='cuda:0')
episode: 37 training return: tensor(-230.2940, device='cuda:0')
episode: 38 training return: tensor(-915.9579, device='cuda:0')
episode: 39 training return: tensor(-268.6088, device='cuda:0')
epoch: 10 test_true_pfm: 3377.3957606726594 sim_pfm: -287.37679343522177
episode: 40 training return: tensor(-999.8905, device='cuda:0')
episode: 41 training return: tensor(-997.7059, device='cuda:0')
episode: 42 training return: tensor(-550.9495, device='cuda:0')
episode: 43 training return: tensor(-362.2021, device='cuda:0')
epoch: 11 test_true_pfm: 3942.572804355557 sim_pfm: -387.33918311827193
episode: 44 training return: tensor(-986.4932, device='cuda:0')
episode: 45 training return: tensor(-551.9594, device='cuda:0')
episode: 46 training return: tensor(-287.0607, device='cuda:0')
episode: 47 training return: tensor(-382.5988, device='cuda:0')
epoch: 12 test_true_pfm: 6570.367230713505 sim_pfm: -412.6871958555421
episode: 48 training return: tensor(-159.2024, device='cuda:0')
episode: 49 training return: tensor(-484.2019, device='cuda:0')
episode: 50 training return: tensor(-100.9169, device='cuda:0')
episode: 51 training return: tensor(-66.4369, device='cuda:0')
epoch: 13 test_true_pfm: 10150.825264781306 sim_pfm: -86.41773401048461
episode: 52 training return: tensor(-383.5114, device='cuda:0')
episode: 53 training return: tensor(-999.9999, device='cuda:0')
episode: 54 training return: tensor(-208.9936, device='cuda:0')
episode: 55 training return: tensor(-487.4907, device='cuda:0')
epoch: 14 test_true_pfm: 4099.734944485834 sim_pfm: -672.4306820903827
episode: 56 training return: tensor(-636.5070, device='cuda:0')
episode: 57 training return: tensor(-999.9991, device='cuda:0')
episode: 58 training return: tensor(-723.9204, device='cuda:0')
episode: 59 training return: tensor(-629.5148, device='cuda:0')
epoch: 15 test_true_pfm: 6257.600750224691 sim_pfm: -126.73380151895496
episode: 60 training return: tensor(-452.0786, device='cuda:0')
episode: 61 training return: tensor(-999.8297, device='cuda:0')
episode: 62 training return: tensor(-61.1886, device='cuda:0')
episode: 63 training return: tensor(-189.0252, device='cuda:0')
epoch: 16 test_true_pfm: 2550.2886879848465 sim_pfm: -346.3947217257228
episode: 64 training return: tensor(-999.9610, device='cuda:0')
episode: 65 training return: tensor(-999.9995, device='cuda:0')
episode: 66 training return: tensor(-882.8151, device='cuda:0')
episode: 67 training return: tensor(-75.6637, device='cuda:0')
epoch: 17 test_true_pfm: 5867.220143421621 sim_pfm: -548.012177601544
episode: 68 training return: tensor(-583.9780, device='cuda:0')
episode: 69 training return: tensor(-999.9993, device='cuda:0')
episode: 70 training return: tensor(-999.9997, device='cuda:0')
episode: 71 training return: tensor(-757.9916, device='cuda:0')
epoch: 18 test_true_pfm: 9550.14326178475 sim_pfm: -673.1861445412505
episode: 72 training return: tensor(-461.9800, device='cuda:0')
episode: 73 training return: tensor(-341.7440, device='cuda:0')
episode: 74 training return: tensor(-999.9993, device='cuda:0')
episode: 75 training return: tensor(-442.0278, device='cuda:0')
epoch: 19 test_true_pfm: 6690.841465178619 sim_pfm: -401.0034544469672
episode: 76 training return: tensor(-999.9778, device='cuda:0')
episode: 77 training return: tensor(-313.3326, device='cuda:0')
episode: 78 training return: tensor(-688.7145, device='cuda:0')
episode: 79 training return: tensor(-999.9995, device='cuda:0')
epoch: 20 test_true_pfm: 4006.7998078472956 sim_pfm: -162.66458978237156
episode: 80 training return: tensor(-998.0489, device='cuda:0')
episode: 81 training return: tensor(-999.9059, device='cuda:0')
episode: 82 training return: tensor(-990.8278, device='cuda:0')
episode: 83 training return: tensor(-176.9695, device='cuda:0')
epoch: 21 test_true_pfm: 4202.642887375396 sim_pfm: -442.4149410537696
episode: 84 training return: tensor(-999.9996, device='cuda:0')
episode: 85 training return: tensor(-837.1904, device='cuda:0')
episode: 86 training return: tensor(-999.9994, device='cuda:0')
episode: 87 training return: tensor(-131.0257, device='cuda:0')
epoch: 22 test_true_pfm: 4101.053744140917 sim_pfm: -304.5707806434075
episode: 88 training return: tensor(-999.9821, device='cuda:0')
episode: 89 training return: tensor(-60.2508, device='cuda:0')
episode: 90 training return: tensor(-1000., device='cuda:0')
episode: 91 training return: tensor(-206.2437, device='cuda:0')
epoch: 23 test_true_pfm: 4456.332967384528 sim_pfm: -690.5887561106356
episode: 92 training return: tensor(-736.1265, device='cuda:0')
episode: 93 training return: tensor(-354.0366, device='cuda:0')
episode: 94 training return: tensor(-267.9102, device='cuda:0')
episode: 95 training return: tensor(-158.4221, device='cuda:0')
epoch: 24 test_true_pfm: 8380.111048665613 sim_pfm: -999.9057067831358
episode: 96 training return: tensor(-387.0551, device='cuda:0')
episode: 97 training return: tensor(-719.2202, device='cuda:0')
episode: 98 training return: tensor(-995.7886, device='cuda:0')
episode: 99 training return: tensor(-987.2068, device='cuda:0')
epoch: 25 test_true_pfm: 4984.899620852195 sim_pfm: -765.7083045460555
episode: 100 training return: tensor(-511.5123, device='cuda:0')
episode: 101 training return: tensor(-1000., device='cuda:0')
episode: 102 training return: tensor(-999.8070, device='cuda:0')
episode: 103 training return: tensor(-999.9984, device='cuda:0')
epoch: 26 test_true_pfm: 3099.8798075715927 sim_pfm: -417.4925037348876
episode: 104 training return: tensor(-82.4305, device='cuda:0')
episode: 105 training return: tensor(-368.7126, device='cuda:0')
episode: 106 training return: tensor(-303.8641, device='cuda:0')
episode: 107 training return: tensor(-986.6479, device='cuda:0')
epoch: 27 test_true_pfm: 3301.3674050210006 sim_pfm: -444.7640861483912
episode: 108 training return: tensor(-962.2626, device='cuda:0')
episode: 109 training return: tensor(25.7632, device='cuda:0')
episode: 110 training return: tensor(-357.3367, device='cuda:0')
episode: 111 training return: tensor(-991.4798, device='cuda:0')
epoch: 28 test_true_pfm: 7642.656973753551 sim_pfm: -357.9852208108641
episode: 112 training return: tensor(-999.6702, device='cuda:0')
episode: 113 training return: tensor(-999.9990, device='cuda:0')
episode: 114 training return: tensor(-999.9880, device='cuda:0')
episode: 115 training return: tensor(-474.4344, device='cuda:0')
epoch: 29 test_true_pfm: 10181.399295254281 sim_pfm: -336.0831968594769
episode: 116 training return: tensor(-125.6790, device='cuda:0')
episode: 117 training return: tensor(-232.2838, device='cuda:0')
episode: 118 training return: tensor(-999.9995, device='cuda:0')
episode: 119 training return: tensor(-946.4030, device='cuda:0')
epoch: 30 test_true_pfm: 3696.9103526343156 sim_pfm: -621.3253367044963
episode: 120 training return: tensor(-996.6215, device='cuda:0')
episode: 121 training return: tensor(-954.5800, device='cuda:0')
episode: 122 training return: tensor(-622.8356, device='cuda:0')
episode: 123 training return: tensor(-999.9981, device='cuda:0')
epoch: 31 test_true_pfm: 6656.856302885833 sim_pfm: -290.07820186344907
episode: 124 training return: tensor(-1.3486, device='cuda:0')
episode: 125 training return: tensor(-999.9988, device='cuda:0')
episode: 126 training return: tensor(-201.4516, device='cuda:0')
episode: 127 training return: tensor(-250.6270, device='cuda:0')
epoch: 32 test_true_pfm: 2844.7300391537774 sim_pfm: -44.31079870521595
episode: 128 training return: tensor(-891.3536, device='cuda:0')
episode: 129 training return: tensor(-494.2526, device='cuda:0')
episode: 130 training return: tensor(-41.8436, device='cuda:0')
episode: 131 training return: tensor(-999.8900, device='cuda:0')
epoch: 33 test_true_pfm: 5254.724632737722 sim_pfm: -611.8123683961263
episode: 132 training return: tensor(-999.9999, device='cuda:0')
episode: 133 training return: tensor(-724.1752, device='cuda:0')
episode: 134 training return: tensor(-999.9971, device='cuda:0')
episode: 135 training return: tensor(-232.8680, device='cuda:0')
epoch: 34 test_true_pfm: 5703.076151537272 sim_pfm: -448.36813238689984
episode: 136 training return: tensor(-64.7435, device='cuda:0')
episode: 137 training return: tensor(-89.4874, device='cuda:0')
episode: 138 training return: tensor(-467.2256, device='cuda:0')
episode: 139 training return: tensor(-999.9968, device='cuda:0')
epoch: 35 test_true_pfm: 10299.046510775606 sim_pfm: -614.5759584721333
episode: 140 training return: tensor(-999.9882, device='cuda:0')
episode: 141 training return: tensor(-146.1485, device='cuda:0')
episode: 142 training return: tensor(-999.9998, device='cuda:0')
episode: 143 training return: tensor(-999.9996, device='cuda:0')
epoch: 36 test_true_pfm: 6714.956339646618 sim_pfm: -446.3269676674584
episode: 144 training return: tensor(-999.6629, device='cuda:0')
episode: 145 training return: tensor(-656.5509, device='cuda:0')
episode: 146 training return: tensor(-442.7185, device='cuda:0')
episode: 147 training return: tensor(-85.2121, device='cuda:0')
epoch: 37 test_true_pfm: 6669.769254966045 sim_pfm: -635.2175926820686
episode: 148 training return: tensor(-909.2354, device='cuda:0')
episode: 149 training return: tensor(-245.4543, device='cuda:0')
episode: 150 training return: tensor(-999.9966, device='cuda:0')
episode: 151 training return: tensor(-864.2567, device='cuda:0')
epoch: 38 test_true_pfm: 2351.551653137509 sim_pfm: -151.21809132650378
episode: 152 training return: tensor(-999.8665, device='cuda:0')
episode: 153 training return: tensor(8.9315, device='cuda:0')
episode: 154 training return: tensor(-999.9998, device='cuda:0')
episode: 155 training return: tensor(-999.7815, device='cuda:0')
epoch: 39 test_true_pfm: 5968.066044088669 sim_pfm: -294.50865808701684
episode: 156 training return: tensor(-915.2256, device='cuda:0')
episode: 157 training return: tensor(-545.1113, device='cuda:0')
episode: 158 training return: tensor(-173.6351, device='cuda:0')
episode: 159 training return: tensor(-58.4783, device='cuda:0')
epoch: 40 test_true_pfm: 6169.266170543936 sim_pfm: -510.98911601256503
episode: 160 training return: tensor(-226.2822, device='cuda:0')
episode: 161 training return: tensor(-932.4028, device='cuda:0')
episode: 162 training return: tensor(-841.9108, device='cuda:0')
episode: 163 training return: tensor(-609.4578, device='cuda:0')
epoch: 41 test_true_pfm: 10032.696555039643 sim_pfm: -470.84886509465287
episode: 164 training return: tensor(-288.5428, device='cuda:0')
episode: 165 training return: tensor(-370.3506, device='cuda:0')
episode: 166 training return: tensor(-694.3826, device='cuda:0')
episode: 167 training return: tensor(-715.1207, device='cuda:0')
epoch: 42 test_true_pfm: 6548.865946543973 sim_pfm: -602.080397169746
episode: 168 training return: tensor(-999.6807, device='cuda:0')
episode: 169 training return: tensor(-999.9972, device='cuda:0')
episode: 170 training return: tensor(-202.8560, device='cuda:0')
episode: 171 training return: tensor(-915.8049, device='cuda:0')
epoch: 43 test_true_pfm: 7486.804277915285 sim_pfm: -319.4522169912428
episode: 172 training return: tensor(-656.8345, device='cuda:0')
episode: 173 training return: tensor(-420.2285, device='cuda:0')
episode: 174 training return: tensor(-270.9363, device='cuda:0')
episode: 175 training return: tensor(-10.5756, device='cuda:0')
epoch: 44 test_true_pfm: 10299.06723322124 sim_pfm: 21.471388898673467
episode: 176 training return: tensor(-998.4226, device='cuda:0')
episode: 177 training return: tensor(-860.8022, device='cuda:0')
episode: 178 training return: tensor(-29.8636, device='cuda:0')
episode: 179 training return: tensor(-326.7071, device='cuda:0')
epoch: 45 test_true_pfm: -67.44790344585229 sim_pfm: -536.9044411821136
episode: 180 training return: tensor(-96.1878, device='cuda:0')
episode: 181 training return: tensor(-253.0514, device='cuda:0')
episode: 182 training return: tensor(-999.9946, device='cuda:0')
episode: 183 training return: tensor(-539.0237, device='cuda:0')
epoch: 46 test_true_pfm: 10066.75708572855 sim_pfm: 145.91535818875613
episode: 184 training return: tensor(-999.9077, device='cuda:0')
episode: 185 training return: tensor(-999.9968, device='cuda:0')
episode: 186 training return: tensor(-992.6310, device='cuda:0')
episode: 187 training return: tensor(-711.8427, device='cuda:0')
epoch: 47 test_true_pfm: 3379.079269886454 sim_pfm: -683.3998729081164
episode: 188 training return: tensor(-999.8419, device='cuda:0')
episode: 189 training return: tensor(-655.0146, device='cuda:0')
episode: 190 training return: tensor(-999.9996, device='cuda:0')
episode: 191 training return: tensor(-999.7151, device='cuda:0')
epoch: 48 test_true_pfm: 5575.498255229439 sim_pfm: -377.44833435929223
episode: 192 training return: tensor(-796.4521, device='cuda:0')
episode: 193 training return: tensor(-998.5140, device='cuda:0')
episode: 194 training return: tensor(-999.9996, device='cuda:0')
episode: 195 training return: tensor(-757.7067, device='cuda:0')
epoch: 49 test_true_pfm: 2479.038100216722 sim_pfm: -332.04473562073935
episode: 196 training return: tensor(-300.8599, device='cuda:0')
episode: 197 training return: tensor(-648.1583, device='cuda:0')
episode: 198 training return: tensor(-999.9983, device='cuda:0')
episode: 199 training return: tensor(-999.9655, device='cuda:0')
epoch: 50 test_true_pfm: 5579.909964607909 sim_pfm: -427.5951223652616
episode: 200 training return: tensor(-999.9991, device='cuda:0')
episode: 201 training return: tensor(28.2395, device='cuda:0')
episode: 202 training return: tensor(-84.1682, device='cuda:0')
episode: 203 training return: tensor(-999.9626, device='cuda:0')
epoch: 51 test_true_pfm: 8107.81275437344 sim_pfm: -570.9895915186402
episode: 204 training return: tensor(-163.8422, device='cuda:0')
episode: 205 training return: tensor(-373.4732, device='cuda:0')
episode: 206 training return: tensor(-999.9979, device='cuda:0')
episode: 207 training return: tensor(-999.8928, device='cuda:0')
epoch: 52 test_true_pfm: -83.7369879262518 sim_pfm: -322.1202604849047
episode: 208 training return: tensor(-194.9823, device='cuda:0')
episode: 209 training return: tensor(66.8703, device='cuda:0')
episode: 210 training return: tensor(-237.2135, device='cuda:0')
episode: 211 training return: tensor(-634.7594, device='cuda:0')
epoch: 53 test_true_pfm: 6840.406166583674 sim_pfm: -187.66039283247665
episode: 212 training return: tensor(96.9498, device='cuda:0')
episode: 213 training return: tensor(-999.9733, device='cuda:0')
episode: 214 training return: tensor(-543.7265, device='cuda:0')
episode: 215 training return: tensor(-999.5391, device='cuda:0')
epoch: 54 test_true_pfm: 6578.6883520384 sim_pfm: -216.08976225423007
episode: 216 training return: tensor(-103.5471, device='cuda:0')
episode: 217 training return: tensor(-999.9703, device='cuda:0')
episode: 218 training return: tensor(-355.3353, device='cuda:0')
episode: 219 training return: tensor(-454.2894, device='cuda:0')
epoch: 55 test_true_pfm: 9654.743148199437 sim_pfm: -414.91213592364994
episode: 220 training return: tensor(-999.6589, device='cuda:0')
episode: 221 training return: tensor(-291.1916, device='cuda:0')
episode: 222 training return: tensor(-999.9958, device='cuda:0')
episode: 223 training return: tensor(-999.8750, device='cuda:0')
epoch: 56 test_true_pfm: -115.87080489102566 sim_pfm: -674.4930431699225
episode: 224 training return: tensor(-999.9998, device='cuda:0')
episode: 225 training return: tensor(-999.9996, device='cuda:0')
episode: 226 training return: tensor(-694.2971, device='cuda:0')
episode: 227 training return: tensor(-78.8750, device='cuda:0')
epoch: 57 test_true_pfm: 10373.16723903616 sim_pfm: -281.8066438677294
episode: 228 training return: tensor(-136.2081, device='cuda:0')
episode: 229 training return: tensor(-315.5542, device='cuda:0')
episode: 230 training return: tensor(83.1126, device='cuda:0')
episode: 231 training return: tensor(-999.9995, device='cuda:0')
epoch: 58 test_true_pfm: 5114.694305431784 sim_pfm: -249.84478231581548
episode: 232 training return: tensor(-174.6829, device='cuda:0')
episode: 233 training return: tensor(-46.1339, device='cuda:0')
episode: 234 training return: tensor(-720.1431, device='cuda:0')
episode: 235 training return: tensor(-990.4335, device='cuda:0')
epoch: 59 test_true_pfm: 10232.119918251628 sim_pfm: -324.3589234713193
episode: 236 training return: tensor(1.3534, device='cuda:0')
episode: 237 training return: tensor(-116.2032, device='cuda:0')
episode: 238 training return: tensor(-999.9998, device='cuda:0')
episode: 239 training return: tensor(-999.9999, device='cuda:0')
epoch: 60 test_true_pfm: 6924.378549225435 sim_pfm: -337.5217401028106
episode: 240 training return: tensor(-999.1729, device='cuda:0')
episode: 241 training return: tensor(-941.5910, device='cuda:0')
episode: 242 training return: tensor(-985.0145, device='cuda:0')
episode: 243 training return: tensor(-999.9945, device='cuda:0')
epoch: 61 test_true_pfm: 9984.05592189088 sim_pfm: -189.15909649343425
episode: 244 training return: tensor(-999.9999, device='cuda:0')
episode: 245 training return: tensor(-999.1680, device='cuda:0')
episode: 246 training return: tensor(-729.3175, device='cuda:0')
episode: 247 training return: tensor(-999.8427, device='cuda:0')
epoch: 62 test_true_pfm: 7370.144274435282 sim_pfm: -1.0908073535150227
episode: 248 training return: tensor(-108.5624, device='cuda:0')
episode: 249 training return: tensor(-122.0227, device='cuda:0')
episode: 250 training return: tensor(-999.9998, device='cuda:0')
episode: 251 training return: tensor(-229.0642, device='cuda:0')
epoch: 63 test_true_pfm: 6775.524178354591 sim_pfm: -233.95936634902804
episode: 252 training return: tensor(-999.9995, device='cuda:0')
episode: 253 training return: tensor(-165.7347, device='cuda:0')
episode: 254 training return: tensor(-1000., device='cuda:0')
episode: 255 training return: tensor(-999.9995, device='cuda:0')
epoch: 64 test_true_pfm: 3291.9592384539646 sim_pfm: -887.9077555835635
episode: 256 training return: tensor(-999.9996, device='cuda:0')
episode: 257 training return: tensor(-999.9995, device='cuda:0')
episode: 258 training return: tensor(-999.9600, device='cuda:0')
episode: 259 training return: tensor(-165.8249, device='cuda:0')
epoch: 65 test_true_pfm: 6358.676008964595 sim_pfm: -633.671286804912
episode: 260 training return: tensor(-589.1597, device='cuda:0')
episode: 261 training return: tensor(-77.3608, device='cuda:0')
episode: 262 training return: tensor(-999.9995, device='cuda:0')
episode: 263 training return: tensor(-442.2052, device='cuda:0')
epoch: 66 test_true_pfm: 2322.66888621081 sim_pfm: -273.6069567687421
episode: 264 training return: tensor(5.0546, device='cuda:0')
episode: 265 training return: tensor(-925.5186, device='cuda:0')
episode: 266 training return: tensor(-999.9998, device='cuda:0')
episode: 267 training return: tensor(-715.9215, device='cuda:0')
epoch: 67 test_true_pfm: 8340.31534771279 sim_pfm: -583.2046599152673
episode: 268 training return: tensor(-348.6563, device='cuda:0')
episode: 269 training return: tensor(-665.7985, device='cuda:0')
episode: 270 training return: tensor(-999.9783, device='cuda:0')
episode: 271 training return: tensor(-999.9962, device='cuda:0')
epoch: 68 test_true_pfm: 6825.852902283786 sim_pfm: 68.18526218784002
episode: 272 training return: tensor(-999.9906, device='cuda:0')
episode: 273 training return: tensor(-636.7523, device='cuda:0')
episode: 274 training return: tensor(-29.2087, device='cuda:0')
episode: 275 training return: tensor(-812.6321, device='cuda:0')
epoch: 69 test_true_pfm: 10177.667780704012 sim_pfm: -658.2665046340165
episode: 276 training return: tensor(-1.2971, device='cuda:0')
episode: 277 training return: tensor(-999.9999, device='cuda:0')
episode: 278 training return: tensor(-46.2130, device='cuda:0')
episode: 279 training return: tensor(-999.9991, device='cuda:0')
epoch: 70 test_true_pfm: 3786.307592495395 sim_pfm: -106.49710254376987
episode: 280 training return: tensor(-60.5420, device='cuda:0')
episode: 281 training return: tensor(-632.3362, device='cuda:0')
episode: 282 training return: tensor(-629.7493, device='cuda:0')
episode: 283 training return: tensor(-999.9991, device='cuda:0')
epoch: 71 test_true_pfm: 1050.3287563444837 sim_pfm: -473.5891885956128
episode: 284 training return: tensor(-58.7677, device='cuda:0')
episode: 285 training return: tensor(-999.9987, device='cuda:0')
episode: 286 training return: tensor(-162.7890, device='cuda:0')
episode: 287 training return: tensor(-74.0892, device='cuda:0')
epoch: 72 test_true_pfm: 8862.67260434208 sim_pfm: -329.57135755449417
episode: 288 training return: tensor(0.3361, device='cuda:0')
episode: 289 training return: tensor(-30.3758, device='cuda:0')
episode: 290 training return: tensor(-817.7040, device='cuda:0')
episode: 291 training return: tensor(-591.4445, device='cuda:0')
epoch: 73 test_true_pfm: 7452.933347395466 sim_pfm: -396.8558171124702
episode: 292 training return: tensor(3.2458, device='cuda:0')
episode: 293 training return: tensor(-52.6526, device='cuda:0')
episode: 294 training return: tensor(-70.1586, device='cuda:0')
episode: 295 training return: tensor(-667.7981, device='cuda:0')
epoch: 74 test_true_pfm: 3437.6350924176 sim_pfm: -174.0163464436579
episode: 296 training return: tensor(-945.3381, device='cuda:0')
episode: 297 training return: tensor(-172.6848, device='cuda:0')
episode: 298 training return: tensor(-833.3714, device='cuda:0')
episode: 299 training return: tensor(-964.1110, device='cuda:0')
epoch: 75 test_true_pfm: 5072.869960857905 sim_pfm: -794.3079673597822
episode: 300 training return: tensor(-999.9691, device='cuda:0')
episode: 301 training return: tensor(69.0724, device='cuda:0')
episode: 302 training return: tensor(-141.3146, device='cuda:0')
episode: 303 training return: tensor(-999.9982, device='cuda:0')
epoch: 76 test_true_pfm: 7240.504006386377 sim_pfm: -324.9608335356461
episode: 304 training return: tensor(-107.5580, device='cuda:0')
episode: 305 training return: tensor(-144.3581, device='cuda:0')
episode: 306 training return: tensor(7.4831, device='cuda:0')
episode: 307 training return: tensor(-170.0222, device='cuda:0')
epoch: 77 test_true_pfm: 7476.409957777786 sim_pfm: 121.09644309524447
episode: 308 training return: tensor(-220.0620, device='cuda:0')
episode: 309 training return: tensor(-999.9997, device='cuda:0')
episode: 310 training return: tensor(-776.2759, device='cuda:0')
episode: 311 training return: tensor(-927.2024, device='cuda:0')
epoch: 78 test_true_pfm: 7203.263629585753 sim_pfm: -621.5210434794814
episode: 312 training return: tensor(-998.0480, device='cuda:0')
episode: 313 training return: tensor(-483.4979, device='cuda:0')
episode: 314 training return: tensor(-998.7473, device='cuda:0')
episode: 315 training return: tensor(-161.3260, device='cuda:0')
epoch: 79 test_true_pfm: 9847.142077873854 sim_pfm: -365.4647337143736
episode: 316 training return: tensor(-40.3381, device='cuda:0')
episode: 317 training return: tensor(-151.3549, device='cuda:0')
episode: 318 training return: tensor(-999.9957, device='cuda:0')
episode: 319 training return: tensor(-21.3645, device='cuda:0')
epoch: 80 test_true_pfm: 3804.808817469717 sim_pfm: -174.77438083694628
episode: 320 training return: tensor(-423.6067, device='cuda:0')
episode: 321 training return: tensor(40.0376, device='cuda:0')
episode: 322 training return: tensor(-575.5686, device='cuda:0')
episode: 323 training return: tensor(-815.9526, device='cuda:0')
epoch: 81 test_true_pfm: 6836.640661850771 sim_pfm: -176.7388011480992
episode: 324 training return: tensor(-57.1769, device='cuda:0')
episode: 325 training return: tensor(-356.0071, device='cuda:0')
episode: 326 training return: tensor(-999.9998, device='cuda:0')
episode: 327 training return: tensor(2.6161, device='cuda:0')
epoch: 82 test_true_pfm: 10299.269784779483 sim_pfm: -262.9121809795033
episode: 328 training return: tensor(-13.5944, device='cuda:0')
episode: 329 training return: tensor(-999.9998, device='cuda:0')
episode: 330 training return: tensor(-37.9060, device='cuda:0')
episode: 331 training return: tensor(-90.7206, device='cuda:0')
epoch: 83 test_true_pfm: 5319.797260692231 sim_pfm: -643.2965306902964
episode: 332 training return: tensor(-256.8288, device='cuda:0')
episode: 333 training return: tensor(-35.3308, device='cuda:0')
episode: 334 training return: tensor(-176.4192, device='cuda:0')
episode: 335 training return: tensor(-999.9603, device='cuda:0')
epoch: 84 test_true_pfm: 6715.085155417233 sim_pfm: -300.3249622834458
episode: 336 training return: tensor(-423.4937, device='cuda:0')
episode: 337 training return: tensor(-149.4753, device='cuda:0')
episode: 338 training return: tensor(-999.9862, device='cuda:0')
episode: 339 training return: tensor(-999.9993, device='cuda:0')
epoch: 85 test_true_pfm: 3851.1221032628837 sim_pfm: 104.45813748662476
episode: 340 training return: tensor(-49.2702, device='cuda:0')
episode: 341 training return: tensor(-999.8574, device='cuda:0')
episode: 342 training return: tensor(-999.9998, device='cuda:0')
episode: 343 training return: tensor(-999.8718, device='cuda:0')
epoch: 86 test_true_pfm: 6912.50812944761 sim_pfm: 98.05230057113415
episode: 344 training return: tensor(15.4460, device='cuda:0')
episode: 345 training return: tensor(-999.9926, device='cuda:0')
episode: 346 training return: tensor(-999.9999, device='cuda:0')
episode: 347 training return: tensor(-87.3019, device='cuda:0')
epoch: 87 test_true_pfm: 7437.184420291381 sim_pfm: -361.46468933254556
episode: 348 training return: tensor(92.1380, device='cuda:0')
episode: 349 training return: tensor(-999.9784, device='cuda:0')
episode: 350 training return: tensor(-84.4437, device='cuda:0')
episode: 351 training return: tensor(-999.9997, device='cuda:0')
epoch: 88 test_true_pfm: 10300.636029511128 sim_pfm: -853.7702601012619
episode: 352 training return: tensor(-127.2165, device='cuda:0')
episode: 353 training return: tensor(139.8674, device='cuda:0')
episode: 354 training return: tensor(-26.5153, device='cuda:0')
episode: 355 training return: tensor(-999.9995, device='cuda:0')
epoch: 89 test_true_pfm: 10307.542131117203 sim_pfm: -66.3103843201922
episode: 356 training return: tensor(-89.5811, device='cuda:0')
episode: 357 training return: tensor(-999.9999, device='cuda:0')
episode: 358 training return: tensor(-82.7481, device='cuda:0')
episode: 359 training return: tensor(-999.9891, device='cuda:0')
epoch: 90 test_true_pfm: 6914.952852665861 sim_pfm: -252.6061930207555
episode: 360 training return: tensor(-999.9988, device='cuda:0')
episode: 361 training return: tensor(-999.9791, device='cuda:0')
episode: 362 training return: tensor(-356.3001, device='cuda:0')
episode: 363 training return: tensor(42.4838, device='cuda:0')
epoch: 91 test_true_pfm: 6852.538802871767 sim_pfm: 120.41161734896014
episode: 364 training return: tensor(19.5650, device='cuda:0')
episode: 365 training return: tensor(-2.6882, device='cuda:0')
episode: 366 training return: tensor(-699.2270, device='cuda:0')
episode: 367 training return: tensor(-51.8222, device='cuda:0')
epoch: 92 test_true_pfm: -99.51410299641934 sim_pfm: 121.76071033044718
episode: 368 training return: tensor(-90.4097, device='cuda:0')
episode: 369 training return: tensor(-999.9996, device='cuda:0')
episode: 370 training return: tensor(-39.0167, device='cuda:0')
episode: 371 training return: tensor(-999.9998, device='cuda:0')
epoch: 93 test_true_pfm: 6212.297520595311 sim_pfm: -73.12954878659609
episode: 372 training return: tensor(-546.3522, device='cuda:0')
episode: 373 training return: tensor(-14.7920, device='cuda:0')
episode: 374 training return: tensor(-999.8502, device='cuda:0')
episode: 375 training return: tensor(-564.1090, device='cuda:0')
epoch: 94 test_true_pfm: 6978.171607407108 sim_pfm: -600.6134559310254
episode: 376 training return: tensor(-331.9656, device='cuda:0')
episode: 377 training return: tensor(-999.9998, device='cuda:0')
episode: 378 training return: tensor(-929.8136, device='cuda:0')
episode: 379 training return: tensor(-97.1356, device='cuda:0')
epoch: 95 test_true_pfm: 6679.805287619423 sim_pfm: -50.01908456149977
episode: 380 training return: tensor(-999.9988, device='cuda:0')
episode: 381 training return: tensor(-999.9990, device='cuda:0')
episode: 382 training return: tensor(-710.7091, device='cuda:0')
episode: 383 training return: tensor(-999.9117, device='cuda:0')
epoch: 96 test_true_pfm: 5313.774950782069 sim_pfm: -143.37786190786088
episode: 384 training return: tensor(-30.7182, device='cuda:0')
episode: 385 training return: tensor(-919.2086, device='cuda:0')
episode: 386 training return: tensor(77.8303, device='cuda:0')
episode: 387 training return: tensor(-382.2919, device='cuda:0')
epoch: 97 test_true_pfm: 6847.701451982448 sim_pfm: -313.21877440726774
episode: 388 training return: tensor(-1000., device='cuda:0')
episode: 389 training return: tensor(-999.8243, device='cuda:0')
episode: 390 training return: tensor(-999.9999, device='cuda:0')
episode: 391 training return: tensor(-999.9735, device='cuda:0')
epoch: 98 test_true_pfm: 6815.266753747167 sim_pfm: 0.021619824091127764
episode: 392 training return: tensor(-506.7462, device='cuda:0')
episode: 393 training return: tensor(-999.4904, device='cuda:0')
episode: 394 training return: tensor(-135.3447, device='cuda:0')
episode: 395 training return: tensor(-153.9776, device='cuda:0')
epoch: 99 test_true_pfm: 10132.520623736807 sim_pfm: -999.9340026179949
episode: 396 training return: tensor(-926.9303, device='cuda:0')
episode: 397 training return: tensor(-539.6745, device='cuda:0')
episode: 398 training return: tensor(-780.1888, device='cuda:0')
episode: 399 training return: tensor(-13.2487, device='cuda:0')
epoch: 100 test_true_pfm: 6660.683754072626 sim_pfm: 7.172679458977655
episode: 400 training return: tensor(-999.9991, device='cuda:0')
episode: 401 training return: tensor(-258.7549, device='cuda:0')
episode: 402 training return: tensor(-563.4941, device='cuda:0')
episode: 403 training return: tensor(-999.9593, device='cuda:0')
epoch: 101 test_true_pfm: 3378.042304014416 sim_pfm: -999.8490642110506
episode: 404 training return: tensor(-51.4190, device='cuda:0')
episode: 405 training return: tensor(-228.6376, device='cuda:0')
episode: 406 training return: tensor(-434.0466, device='cuda:0')
episode: 407 training return: tensor(-40.7921, device='cuda:0')
epoch: 102 test_true_pfm: 6301.784292663103 sim_pfm: 79.6508700265161
episode: 408 training return: tensor(-999.9864, device='cuda:0')
episode: 409 training return: tensor(-999.9985, device='cuda:0')
episode: 410 training return: tensor(-64.7715, device='cuda:0')
episode: 411 training return: tensor(27.7477, device='cuda:0')
epoch: 103 test_true_pfm: 8675.138780656625 sim_pfm: -187.75229846906345
episode: 412 training return: tensor(110.5744, device='cuda:0')
episode: 413 training return: tensor(-999.9991, device='cuda:0')
episode: 414 training return: tensor(-97.5241, device='cuda:0')
episode: 415 training return: tensor(-102.2581, device='cuda:0')
epoch: 104 test_true_pfm: 8375.251574274016 sim_pfm: -404.067493878693
episode: 416 training return: tensor(-526.5622, device='cuda:0')
episode: 417 training return: tensor(-999.9767, device='cuda:0')
episode: 418 training return: tensor(-115.8194, device='cuda:0')
episode: 419 training return: tensor(-77.3966, device='cuda:0')
epoch: 105 test_true_pfm: 3294.7201273662354 sim_pfm: -622.0568485570839
episode: 420 training return: tensor(-319.9813, device='cuda:0')
episode: 421 training return: tensor(-999.9998, device='cuda:0')
episode: 422 training return: tensor(-278.2424, device='cuda:0')
episode: 423 training return: tensor(-36.1896, device='cuda:0')
epoch: 106 test_true_pfm: 10069.026189965458 sim_pfm: -278.2792488831328
episode: 424 training return: tensor(-999.7989, device='cuda:0')
episode: 425 training return: tensor(93.9960, device='cuda:0')
episode: 426 training return: tensor(-346.8110, device='cuda:0')
episode: 427 training return: tensor(-454.6864, device='cuda:0')
epoch: 107 test_true_pfm: 5294.777991851082 sim_pfm: 143.4311920356413
episode: 428 training return: tensor(-54.4434, device='cuda:0')
episode: 429 training return: tensor(-205.8975, device='cuda:0')
episode: 430 training return: tensor(-888.5944, device='cuda:0')
episode: 431 training return: tensor(197.2380, device='cuda:0')
epoch: 108 test_true_pfm: 6984.973658358217 sim_pfm: -172.92631275307699
episode: 432 training return: tensor(-999.9997, device='cuda:0')
episode: 433 training return: tensor(-999.9714, device='cuda:0')
episode: 434 training return: tensor(-395.8317, device='cuda:0')
episode: 435 training return: tensor(-17.0966, device='cuda:0')
epoch: 109 test_true_pfm: 10105.045966643615 sim_pfm: 92.22654668838368
episode: 436 training return: tensor(-161.8632, device='cuda:0')
episode: 437 training return: tensor(-999.9995, device='cuda:0')
episode: 438 training return: tensor(-999.9997, device='cuda:0')
episode: 439 training return: tensor(-90.2169, device='cuda:0')
epoch: 110 test_true_pfm: 8733.920458828772 sim_pfm: 174.5889499624512
episode: 440 training return: tensor(-999.9954, device='cuda:0')
episode: 441 training return: tensor(-159.9870, device='cuda:0')
episode: 442 training return: tensor(-999.5444, device='cuda:0')
episode: 443 training return: tensor(-423.5301, device='cuda:0')
epoch: 111 test_true_pfm: 10351.230279484786 sim_pfm: -289.24764680385124
episode: 444 training return: tensor(-94.0905, device='cuda:0')
episode: 445 training return: tensor(49.7890, device='cuda:0')
episode: 446 training return: tensor(-152.5393, device='cuda:0')
episode: 447 training return: tensor(-45.3174, device='cuda:0')
epoch: 112 test_true_pfm: 10283.180648632175 sim_pfm: 22.27906567345296
episode: 448 training return: tensor(0.8641, device='cuda:0')
episode: 449 training return: tensor(31.2949, device='cuda:0')
episode: 450 training return: tensor(-999.9998, device='cuda:0')
episode: 451 training return: tensor(-257.5637, device='cuda:0')
epoch: 113 test_true_pfm: 5605.604839615723 sim_pfm: -740.4793358587389
episode: 452 training return: tensor(-36.2991, device='cuda:0')
episode: 453 training return: tensor(-999.9993, device='cuda:0')
episode: 454 training return: tensor(-34.9658, device='cuda:0')
episode: 455 training return: tensor(-171.0421, device='cuda:0')
epoch: 114 test_true_pfm: 3334.998738524995 sim_pfm: 11.795638016522085
episode: 456 training return: tensor(-88.7572, device='cuda:0')
episode: 457 training return: tensor(-999.9230, device='cuda:0')
episode: 458 training return: tensor(-90.4657, device='cuda:0')
episode: 459 training return: tensor(7.8428, device='cuda:0')
epoch: 115 test_true_pfm: 6790.564715442723 sim_pfm: 67.83347278343474
episode: 460 training return: tensor(59.5271, device='cuda:0')
episode: 461 training return: tensor(-931.5553, device='cuda:0')
episode: 462 training return: tensor(-999.9987, device='cuda:0')
episode: 463 training return: tensor(-296.7640, device='cuda:0')
epoch: 116 test_true_pfm: 3260.508495704267 sim_pfm: -196.8703440108317
episode: 464 training return: tensor(-209.4016, device='cuda:0')
episode: 465 training return: tensor(-330.3051, device='cuda:0')
episode: 466 training return: tensor(-999.9998, device='cuda:0')
episode: 467 training return: tensor(-999.9971, device='cuda:0')
epoch: 117 test_true_pfm: 6873.7102524396105 sim_pfm: -230.56984384501507
episode: 468 training return: tensor(93.0167, device='cuda:0')
episode: 469 training return: tensor(-999.9979, device='cuda:0')
episode: 470 training return: tensor(63.1341, device='cuda:0')
episode: 471 training return: tensor(-1.9122, device='cuda:0')
epoch: 118 test_true_pfm: 10375.426562048533 sim_pfm: -508.19992627568234
episode: 472 training return: tensor(-999.8239, device='cuda:0')
episode: 473 training return: tensor(-789.9509, device='cuda:0')
episode: 474 training return: tensor(-194.2882, device='cuda:0')
episode: 475 training return: tensor(-848.1333, device='cuda:0')
epoch: 119 test_true_pfm: 10291.413275368554 sim_pfm: 109.43313912985225
episode: 476 training return: tensor(133.2923, device='cuda:0')
episode: 477 training return: tensor(-68.7613, device='cuda:0')
episode: 478 training return: tensor(42.2824, device='cuda:0')
episode: 479 training return: tensor(-238.3166, device='cuda:0')
epoch: 120 test_true_pfm: 6087.642480326648 sim_pfm: -587.4751553583192
episode: 480 training return: tensor(-71.7632, device='cuda:0')
episode: 481 training return: tensor(111.0415, device='cuda:0')
episode: 482 training return: tensor(56.2793, device='cuda:0')
episode: 483 training return: tensor(-999.6932, device='cuda:0')
epoch: 121 test_true_pfm: 10186.366748646464 sim_pfm: -270.300117926837
episode: 484 training return: tensor(34.0121, device='cuda:0')
episode: 485 training return: tensor(-317.0524, device='cuda:0')
episode: 486 training return: tensor(39.9159, device='cuda:0')
episode: 487 training return: tensor(170.1772, device='cuda:0')
epoch: 122 test_true_pfm: 7747.87033528139 sim_pfm: -201.54758986406765
episode: 488 training return: tensor(-999.5660, device='cuda:0')
episode: 489 training return: tensor(89.2914, device='cuda:0')
episode: 490 training return: tensor(163.4643, device='cuda:0')
episode: 491 training return: tensor(73.1701, device='cuda:0')
epoch: 123 test_true_pfm: 10380.269232423923 sim_pfm: -471.5186560398045
episode: 492 training return: tensor(-999.4247, device='cuda:0')
episode: 493 training return: tensor(-999.9241, device='cuda:0')
episode: 494 training return: tensor(-999.9998, device='cuda:0')
episode: 495 training return: tensor(-38.4905, device='cuda:0')
epoch: 124 test_true_pfm: 6802.020769243605 sim_pfm: -280.74397339103353
episode: 496 training return: tensor(-996.7507, device='cuda:0')
episode: 497 training return: tensor(-999.7590, device='cuda:0')
episode: 498 training return: tensor(-9.1724, device='cuda:0')
episode: 499 training return: tensor(-577.5526, device='cuda:0')
epoch: 125 test_true_pfm: 3460.3158049797908 sim_pfm: -629.2750747808605
episode: 500 training return: tensor(-182.3971, device='cuda:0')
episode: 501 training return: tensor(-998.7873, device='cuda:0')
episode: 502 training return: tensor(-21.4534, device='cuda:0')
episode: 503 training return: tensor(-322.9619, device='cuda:0')
epoch: 126 test_true_pfm: 6963.222273655469 sim_pfm: -186.05937301115287
episode: 504 training return: tensor(-98.9301, device='cuda:0')
episode: 505 training return: tensor(2.6933, device='cuda:0')
episode: 506 training return: tensor(-152.1602, device='cuda:0')
episode: 507 training return: tensor(21.4297, device='cuda:0')
epoch: 127 test_true_pfm: 10444.973003121828 sim_pfm: 14.391403477328518
episode: 508 training return: tensor(-999.9991, device='cuda:0')
episode: 509 training return: tensor(29.7960, device='cuda:0')
episode: 510 training return: tensor(39.0476, device='cuda:0')
episode: 511 training return: tensor(-999.9999, device='cuda:0')
epoch: 128 test_true_pfm: 9289.977071574487 sim_pfm: -325.98607796490734
episode: 512 training return: tensor(-999.9990, device='cuda:0')
episode: 513 training return: tensor(-219.0203, device='cuda:0')
episode: 514 training return: tensor(47.6912, device='cuda:0')
episode: 515 training return: tensor(-95.5795, device='cuda:0')
epoch: 129 test_true_pfm: 6611.110434294998 sim_pfm: -244.73726007835162
episode: 516 training return: tensor(-999.9996, device='cuda:0')
episode: 517 training return: tensor(21.4525, device='cuda:0')
episode: 518 training return: tensor(-413.0453, device='cuda:0')
episode: 519 training return: tensor(-33.8743, device='cuda:0')
epoch: 130 test_true_pfm: 3420.919783569861 sim_pfm: -193.9526979275009
episode: 520 training return: tensor(-999.9996, device='cuda:0')
episode: 521 training return: tensor(-518.2686, device='cuda:0')
episode: 522 training return: tensor(21.0323, device='cuda:0')
episode: 523 training return: tensor(90.6618, device='cuda:0')
epoch: 131 test_true_pfm: 9224.62420877809 sim_pfm: -12.426961232209578
episode: 524 training return: tensor(-48.0221, device='cuda:0')
episode: 525 training return: tensor(115.6543, device='cuda:0')
episode: 526 training return: tensor(-112.2455, device='cuda:0')
episode: 527 training return: tensor(-936.9537, device='cuda:0')
epoch: 132 test_true_pfm: 4644.964674893944 sim_pfm: -343.0314678459351
episode: 528 training return: tensor(-999.9995, device='cuda:0')
episode: 529 training return: tensor(-999.1629, device='cuda:0')
episode: 530 training return: tensor(-999.9999, device='cuda:0')
episode: 531 training return: tensor(-999.9351, device='cuda:0')
epoch: 133 test_true_pfm: 10256.937727409613 sim_pfm: -999.9990873932838
episode: 532 training return: tensor(-563.3838, device='cuda:0')
episode: 533 training return: tensor(-69.2870, device='cuda:0')
episode: 534 training return: tensor(-52.5231, device='cuda:0')
episode: 535 training return: tensor(-38.8809, device='cuda:0')
epoch: 134 test_true_pfm: 6567.722028034584 sim_pfm: -349.08011738135247
episode: 536 training return: tensor(-999.9965, device='cuda:0')
episode: 537 training return: tensor(-999.9914, device='cuda:0')
episode: 538 training return: tensor(-742.5140, device='cuda:0')
episode: 539 training return: tensor(45.7522, device='cuda:0')
epoch: 135 test_true_pfm: 7751.741113307152 sim_pfm: -285.09181451917783
episode: 540 training return: tensor(-45.9349, device='cuda:0')
episode: 541 training return: tensor(50.0834, device='cuda:0')
episode: 542 training return: tensor(191.0535, device='cuda:0')
episode: 543 training return: tensor(-999.9949, device='cuda:0')
epoch: 136 test_true_pfm: 10475.91421298925 sim_pfm: -329.56141432130244
episode: 544 training return: tensor(-283.5754, device='cuda:0')
episode: 545 training return: tensor(72.9945, device='cuda:0')
episode: 546 training return: tensor(19.9374, device='cuda:0')
episode: 547 training return: tensor(-66.7341, device='cuda:0')
epoch: 137 test_true_pfm: 8237.342093202067 sim_pfm: -34.43161266293222
episode: 548 training return: tensor(-999.9836, device='cuda:0')
episode: 549 training return: tensor(-42.5929, device='cuda:0')
episode: 550 training return: tensor(72.5086, device='cuda:0')
episode: 551 training return: tensor(-223.0843, device='cuda:0')
epoch: 138 test_true_pfm: 10518.380885727007 sim_pfm: 101.36659875126982
episode: 552 training return: tensor(-999.9993, device='cuda:0')
episode: 553 training return: tensor(59.4510, device='cuda:0')
episode: 554 training return: tensor(-98.7253, device='cuda:0')
episode: 555 training return: tensor(-91.6598, device='cuda:0')
epoch: 139 test_true_pfm: 6871.171214922801 sim_pfm: -427.59870351903373
episode: 556 training return: tensor(156.2150, device='cuda:0')
episode: 557 training return: tensor(-51.6592, device='cuda:0')
episode: 558 training return: tensor(77.7853, device='cuda:0')
episode: 559 training return: tensor(76.7247, device='cuda:0')
epoch: 140 test_true_pfm: 10387.724945124524 sim_pfm: 86.66904360339201
episode: 560 training return: tensor(-72.0441, device='cuda:0')
episode: 561 training return: tensor(86.2650, device='cuda:0')
episode: 562 training return: tensor(172.6919, device='cuda:0')
episode: 563 training return: tensor(-225.6455, device='cuda:0')
epoch: 141 test_true_pfm: 3502.8522090347083 sim_pfm: 260.3534729171467
episode: 564 training return: tensor(-270.9681, device='cuda:0')
episode: 565 training return: tensor(-34.1239, device='cuda:0')
episode: 566 training return: tensor(103.5191, device='cuda:0')
episode: 567 training return: tensor(-999.9992, device='cuda:0')
epoch: 142 test_true_pfm: 3229.0115442350034 sim_pfm: -18.136532301519765
episode: 568 training return: tensor(-999.9995, device='cuda:0')
episode: 569 training return: tensor(-849.5943, device='cuda:0')
episode: 570 training return: tensor(158.6125, device='cuda:0')
episode: 571 training return: tensor(164.8398, device='cuda:0')
epoch: 143 test_true_pfm: 5866.382588943544 sim_pfm: 128.3261371400828
episode: 572 training return: tensor(217.9503, device='cuda:0')
episode: 573 training return: tensor(-999.7979, device='cuda:0')
episode: 574 training return: tensor(-79.4709, device='cuda:0')
episode: 575 training return: tensor(-397.7492, device='cuda:0')
epoch: 144 test_true_pfm: 6739.589870213965 sim_pfm: -299.30625151815667
episode: 576 training return: tensor(-999.9254, device='cuda:0')
episode: 577 training return: tensor(170.3067, device='cuda:0')
episode: 578 training return: tensor(-803.9906, device='cuda:0')
episode: 579 training return: tensor(-996.9420, device='cuda:0')
epoch: 145 test_true_pfm: 6917.643571744959 sim_pfm: -535.2893927827632
episode: 580 training return: tensor(-79.2714, device='cuda:0')
episode: 581 training return: tensor(25.1393, device='cuda:0')
episode: 582 training return: tensor(-999.9979, device='cuda:0')
episode: 583 training return: tensor(-999.9994, device='cuda:0')
epoch: 146 test_true_pfm: 6736.119303813907 sim_pfm: -69.63224666191188
episode: 584 training return: tensor(-85.9244, device='cuda:0')
episode: 585 training return: tensor(-917.5802, device='cuda:0')
episode: 586 training return: tensor(-999.9997, device='cuda:0')
episode: 587 training return: tensor(-999.9993, device='cuda:0')
epoch: 147 test_true_pfm: 10128.480410629782 sim_pfm: -138.00434691936243
episode: 588 training return: tensor(-999.9976, device='cuda:0')
episode: 589 training return: tensor(-146.7375, device='cuda:0')
episode: 590 training return: tensor(-1.5844, device='cuda:0')
episode: 591 training return: tensor(144.3878, device='cuda:0')
epoch: 148 test_true_pfm: -136.40570318501133 sim_pfm: -597.9468051382573
episode: 592 training return: tensor(-999.9989, device='cuda:0')
episode: 593 training return: tensor(68.0274, device='cuda:0')
episode: 594 training return: tensor(-7.3862, device='cuda:0')
episode: 595 training return: tensor(-999.2931, device='cuda:0')
epoch: 149 test_true_pfm: 7812.20907075772 sim_pfm: -630.6863632629005
episode: 596 training return: tensor(57.4337, device='cuda:0')
episode: 597 training return: tensor(-999.9993, device='cuda:0')
episode: 598 training return: tensor(-59.6269, device='cuda:0')
episode: 599 training return: tensor(86.7488, device='cuda:0')
epoch: 150 test_true_pfm: 5208.68151419667 sim_pfm: -271.2763603196751
