['--env', 'Walker2d-v3', '--traj', 'medium']
epoch: 0 training_loss 0.2611122057586908 test_loss: 0.15256812572479247
epoch: 1 training_loss 0.14968697894364597 test_loss: 0.16021329164505005
epoch: 2 training_loss 0.12841035228222608 test_loss: 0.14505360126495362
epoch: 3 training_loss 0.12089094012975693 test_loss: 0.10051114559173584
epoch: 4 training_loss 0.1219503754004836 test_loss: 0.14649568796157836
epoch: 5 training_loss 0.11480761062353849 test_loss: 0.11608670949935913
epoch: 6 training_loss 0.11037089511752128 test_loss: 0.11689378023147583
epoch: 7 training_loss 0.1065702348574996 test_loss: 0.1111674189567566
epoch: 8 training_loss 0.10726620949804783 test_loss: 0.1189520001411438
epoch: 9 training_loss 0.10574786208570003 test_loss: 0.10196073055267334
epoch: 10 training_loss 0.10559055171906948 test_loss: 0.11188498735427857
epoch: 11 training_loss 0.10021064858883619 test_loss: 0.11460754871368409
epoch: 12 training_loss 0.103544612377882 test_loss: 0.11699693202972412
epoch: 13 training_loss 0.10578991152346134 test_loss: 0.08205128908157348
epoch: 14 training_loss 0.10265184268355369 test_loss: 0.11299548149108887
epoch: 15 training_loss 0.10079625111073255 test_loss: 0.12525428533554078
epoch: 16 training_loss 0.09635342182591558 test_loss: 0.11557111740112305
epoch: 17 training_loss 0.09056106695905328 test_loss: 0.0782210350036621
epoch: 18 training_loss 0.09791204072535038 test_loss: 0.0990626037120819
epoch: 19 training_loss 0.09521310348063708 test_loss: 0.11454453468322753
epoch: 20 training_loss 0.10081330781802535 test_loss: 0.1147347092628479
epoch: 21 training_loss 0.10533989656716586 test_loss: 0.11877379417419434
epoch: 22 training_loss 0.09534127803519368 test_loss: 0.10456472635269165
epoch: 23 training_loss 0.09759816091507673 test_loss: 0.10549638271331788
epoch: 24 training_loss 0.09761135336011648 test_loss: 0.09271635413169861
epoch: 25 training_loss 0.10327833414077758 test_loss: 0.11170687675476074
epoch: 26 training_loss 0.09855359764769674 test_loss: 0.09251608848571777
epoch: 27 training_loss 0.10402106773108244 test_loss: 0.11061776876449585
epoch: 28 training_loss 0.09716964229941367 test_loss: 0.08584018945693969
epoch: 29 training_loss 0.08637100761756301 test_loss: 0.08467310070991516
epoch: 30 training_loss 0.09568627089262009 test_loss: 0.11205875873565674
epoch: 31 training_loss 0.09380458027124405 test_loss: 0.07667389512062073
epoch: 32 training_loss 0.09936440017074347 test_loss: 0.07150323987007141
epoch: 33 training_loss 0.08853965483605862 test_loss: 0.10490592718124389
epoch: 34 training_loss 0.09778918657451868 test_loss: 0.09075110554695129
epoch: 35 training_loss 0.09977008026093244 test_loss: 0.08878924250602722
epoch: 36 training_loss 0.09587490640580654 test_loss: 0.08309412598609925
epoch: 37 training_loss 0.09148218210786581 test_loss: 0.10343990325927735
epoch: 38 training_loss 0.09259200312197208 test_loss: 0.08237252235412598
epoch: 39 training_loss 0.09563053580000996 test_loss: 0.08627876043319702
epoch: 40 training_loss 0.08701838221400976 test_loss: 0.10010652542114258
epoch: 41 training_loss 0.08967779878526926 test_loss: 0.09862265586853028
epoch: 42 training_loss 0.09130030028522014 test_loss: 0.11174036264419555
epoch: 43 training_loss 0.09095193343237043 test_loss: 0.10281523466110229
epoch: 44 training_loss 0.09244766103103758 test_loss: 0.09242038130760193
epoch: 45 training_loss 0.09446665786206722 test_loss: 0.10989960432052612
epoch: 46 training_loss 0.09841198241338134 test_loss: 0.09025580883026123
epoch: 47 training_loss 0.0934154842980206 test_loss: 0.09217169284820556
epoch: 48 training_loss 0.09091132601723075 test_loss: 0.08806968927383423
epoch: 49 training_loss 0.08888943161815405 test_loss: 0.08224241733551026
epoch: 50 training_loss 0.09611264104023576 test_loss: 0.11466636657714843
epoch: 51 training_loss 0.0936242536175996 test_loss: 0.09717248678207398
epoch: 52 training_loss 0.09014668069779873 test_loss: 0.10085904598236084
epoch: 53 training_loss 0.08461389314383268 test_loss: 0.10821374654769897
epoch: 54 training_loss 0.0970826493576169 test_loss: 0.0884908378124237
epoch: 55 training_loss 0.08717412523925304 test_loss: 0.07531834840774536
epoch: 56 training_loss 0.09230378776788711 test_loss: 0.07519735097885132
epoch: 57 training_loss 0.0906996469758451 test_loss: 0.10452715158462525
epoch: 58 training_loss 0.08089592693373561 test_loss: 0.10298632383346558
epoch: 59 training_loss 0.08442784709855915 test_loss: 0.09903433322906494
epoch: 60 training_loss 0.08876484486274422 test_loss: 0.09654819965362549
epoch: 61 training_loss 0.09286766972392797 test_loss: 0.08880311250686646
epoch: 62 training_loss 0.08540163099765778 test_loss: 0.08967145681381225
epoch: 63 training_loss 0.0920290687866509 test_loss: 0.0966759443283081
epoch: 64 training_loss 0.08684848375618458 test_loss: 0.0678685486316681
epoch: 65 training_loss 0.0945177404768765 test_loss: 0.0942592203617096
epoch: 66 training_loss 0.08756889341399074 test_loss: 0.09300827383995056
epoch: 67 training_loss 0.09309945868328214 test_loss: 0.10531944036483765
epoch: 68 training_loss 0.0942711484991014 test_loss: 0.08315476775169373
epoch: 69 training_loss 0.09431365512311458 test_loss: 0.09382845759391785
epoch: 70 training_loss 0.10650994390249252 test_loss: 0.09260694980621338
epoch: 71 training_loss 0.08436789017170668 test_loss: 0.08940814733505249
epoch: 72 training_loss 0.08699938289821148 test_loss: 0.07870217561721801
epoch: 73 training_loss 0.08928490733727813 test_loss: 0.08725013732910156
epoch: 74 training_loss 0.08738743165507913 test_loss: 0.08346349596977234
epoch: 75 training_loss 0.08862511133775115 test_loss: 0.07485148310661316
epoch: 76 training_loss 0.0890667274966836 test_loss: 0.09900918006896972
epoch: 77 training_loss 0.08835709448903799 test_loss: 0.0970984935760498
epoch: 78 training_loss 0.08781292283907532 test_loss: 0.1034305214881897
epoch: 79 training_loss 0.08617744339630008 test_loss: 0.10040034055709839
epoch: 80 training_loss 0.08432941112667322 test_loss: 0.0953663170337677
epoch: 81 training_loss 0.09256100617349147 test_loss: 0.11315516233444214
epoch: 82 training_loss 0.08212595835328101 test_loss: 0.11983282566070556
epoch: 83 training_loss 0.08792719980701805 test_loss: 0.073005211353302
epoch: 84 training_loss 0.08769172275438905 test_loss: 0.0914189100265503
epoch: 85 training_loss 0.08986832331866026 test_loss: 0.11926431655883789
epoch: 86 training_loss 0.08894912786781788 test_loss: 0.08857563734054566
epoch: 87 training_loss 0.09375873478129507 test_loss: 0.09054275751113891
epoch: 88 training_loss 0.09403153786435724 test_loss: 0.07585012316703796
epoch: 89 training_loss 0.09109944934025407 test_loss: 0.09144881963729859
epoch: 90 training_loss 0.0874694437533617 test_loss: 0.07828776836395264
epoch: 91 training_loss 0.08003680033609271 test_loss: 0.0875336229801178
epoch: 92 training_loss 0.08973863640800119 test_loss: 0.1017417550086975
epoch: 93 training_loss 0.08788699785247445 test_loss: 0.06918140053749085
epoch: 94 training_loss 0.08296451279893517 test_loss: 0.11730118989944457
epoch: 95 training_loss 0.09184056483209133 test_loss: 0.09812704920768738
epoch: 96 training_loss 0.08599191644228994 test_loss: 0.10789148807525635
epoch: 97 training_loss 0.08339231479912997 test_loss: 0.08240067958831787
epoch: 98 training_loss 0.08669527076184749 test_loss: 0.10407295227050781
epoch: 99 training_loss 0.08661050226539374 test_loss: 0.09454326033592224
epoch: 100 training_loss 0.09298015331849456 test_loss: 0.09892219305038452
epoch: 101 training_loss 0.09664749800227583 test_loss: 0.0927592396736145
epoch: 102 training_loss 0.09072945155203342 test_loss: 0.08243643045425415
epoch: 103 training_loss 0.09175673071295024 test_loss: 0.09545385241508483
epoch: 104 training_loss 0.0860198119468987 test_loss: 0.1009265661239624
epoch: 105 training_loss 0.08221798587590456 test_loss: 0.12020659446716309
epoch: 106 training_loss 0.08624273642897606 test_loss: 0.09332486987113953
epoch: 107 training_loss 0.08595435230061411 test_loss: 0.09506288170814514
epoch: 108 training_loss 0.08791694968938828 test_loss: 0.0877339243888855
epoch: 109 training_loss 0.08845709774643183 test_loss: 0.08847426176071167
epoch: 110 training_loss 0.09574475957080722 test_loss: 0.07685872912406921
epoch: 111 training_loss 0.08848383838310837 test_loss: 0.08464114665985108
epoch: 112 training_loss 0.09285480994731188 test_loss: 0.09723525643348693
epoch: 113 training_loss 0.09075521904975176 test_loss: 0.07535880208015441
epoch: 114 training_loss 0.08607465431094169 test_loss: 0.08711327910423279
epoch: 115 training_loss 0.08120733514428138 test_loss: 0.06807230710983277
epoch: 116 training_loss 0.09236119118519127 test_loss: 0.10013598203659058
epoch: 117 training_loss 0.09038743309676647 test_loss: 0.11386598348617553
epoch: 118 training_loss 0.08784173877909779 test_loss: 0.08551806807518006
epoch: 119 training_loss 0.0900126695074141 test_loss: 0.07979928851127624
epoch: 120 training_loss 0.08536033356562257 test_loss: 0.10878726243972778
epoch: 121 training_loss 0.08807415951043368 test_loss: 0.1023858666419983
epoch: 122 training_loss 0.08906282268464566 test_loss: 0.09398007988929749
epoch: 123 training_loss 0.08504216564819217 test_loss: 0.0959363341331482
epoch: 124 training_loss 0.0849265518411994 test_loss: 0.08777601718902588
epoch: 125 training_loss 0.08724099179729819 test_loss: 0.10147985219955444
epoch: 126 training_loss 0.0877978628128767 test_loss: 0.12683600187301636
epoch: 127 training_loss 0.08965023366734386 test_loss: 0.08027466535568237
epoch: 128 training_loss 0.08586478322744369 test_loss: 0.10569067001342773
epoch: 129 training_loss 0.08939255308359861 test_loss: 0.09632447957992554
epoch: 130 training_loss 0.08613246353343129 test_loss: 0.09657389521598816
epoch: 131 training_loss 0.0879431545175612 test_loss: 0.08779522776603699
epoch: 132 training_loss 0.0874545194581151 test_loss: 0.08482987880706787
epoch: 133 training_loss 0.08293351823464036 test_loss: 0.10168800354003907
epoch: 134 training_loss 0.08679372232407331 test_loss: 0.08243682384490966
epoch: 135 training_loss 0.08359002729877829 test_loss: 0.08835926651954651
epoch: 136 training_loss 0.09173308573663234 test_loss: 0.06840740442276001
epoch: 137 training_loss 0.08677775884047151 test_loss: 0.08339067697525024
epoch: 138 training_loss 0.08431715648621321 test_loss: 0.11204240322113038
epoch: 139 training_loss 0.0885204148106277 test_loss: 0.09465217590332031
epoch: 140 training_loss 0.090172986574471 test_loss: 0.09239329099655151
epoch: 141 training_loss 0.08854924336075783 test_loss: 0.08968324065208436
epoch: 142 training_loss 0.08759007856249809 test_loss: 0.07963239550590515
epoch: 143 training_loss 0.08816224317997694 test_loss: 0.09386778473854065
epoch: 144 training_loss 0.08784906474873423 test_loss: 0.06841830015182496
epoch: 145 training_loss 0.08854599237442017 test_loss: 0.08730067610740662
epoch: 146 training_loss 0.08190777402371169 test_loss: 0.08866429924964905
epoch: 147 training_loss 0.08488512467592954 test_loss: 0.12179642915725708
epoch: 148 training_loss 0.09973810505121947 test_loss: 0.09453383088111877
epoch: 149 training_loss 0.0884014380723238 test_loss: 0.0903343379497528
epoch: 0 training_loss 40.3863928604126 test_loss: 21.483860778808594
epoch: 1 training_loss 17.4449009513855 test_loss: 14.125848388671875
epoch: 2 training_loss 13.163952798843384 test_loss: 12.256578826904297
epoch: 3 training_loss 11.03343864440918 test_loss: 10.4423583984375
epoch: 4 training_loss 9.556714997291564 test_loss: 8.85833282470703
epoch: 5 training_loss 8.619261240959167 test_loss: 8.478016662597657
epoch: 6 training_loss 7.863986711502076 test_loss: 7.630545043945313
epoch: 7 training_loss 7.4915162944793705 test_loss: 7.505869293212891
epoch: 8 training_loss 7.003507628440857 test_loss: 7.003147888183594
epoch: 9 training_loss 6.635932273864746 test_loss: 6.363990020751953
epoch: 10 training_loss 6.17327036857605 test_loss: 5.904765319824219
epoch: 11 training_loss 5.978724036216736 test_loss: 5.747668838500976
epoch: 12 training_loss 5.878299307823181 test_loss: 6.380043029785156
epoch: 13 training_loss 5.67714626789093 test_loss: 5.827249908447266
epoch: 14 training_loss 5.419311480522156 test_loss: 5.5299842834472654
epoch: 15 training_loss 5.283209276199341 test_loss: 5.302222061157226
epoch: 16 training_loss 5.136592872142792 test_loss: 5.003205490112305
epoch: 17 training_loss 4.945522799491882 test_loss: 4.807109451293945
epoch: 18 training_loss 4.850041205883026 test_loss: 4.911886215209961
epoch: 19 training_loss 4.856866407394409 test_loss: 4.560599136352539
epoch: 20 training_loss 4.519458961486817 test_loss: 4.3752197265625
epoch: 21 training_loss 4.478479526042938 test_loss: 4.312744903564453
epoch: 22 training_loss 4.415950884819031 test_loss: 4.455846786499023
epoch: 23 training_loss 4.35336817741394 test_loss: 3.961107635498047
epoch: 24 training_loss 4.1327401375770565 test_loss: 4.17664909362793
epoch: 25 training_loss 4.157638006210327 test_loss: 3.840534973144531
epoch: 26 training_loss 4.056488864421844 test_loss: 3.864871597290039
epoch: 27 training_loss 4.051669430732727 test_loss: 3.7363521575927736
epoch: 28 training_loss 3.9261866760253907 test_loss: 4.090899276733398
epoch: 29 training_loss 3.89730890750885 test_loss: 3.8441303253173826
epoch: 30 training_loss 3.865276780128479 test_loss: 3.820654296875
epoch: 31 training_loss 3.7650211548805235 test_loss: 3.856884002685547
epoch: 32 training_loss 3.7832096791267396 test_loss: 3.5614452362060547
epoch: 33 training_loss 3.7103272104263305 test_loss: 3.8129276275634765
epoch: 34 training_loss 3.641331903934479 test_loss: 3.6618682861328127
epoch: 35 training_loss 3.589353983402252 test_loss: 3.880447006225586
epoch: 36 training_loss 3.4807768750190733 test_loss: 3.580828094482422
epoch: 37 training_loss 3.545139739513397 test_loss: 3.4548187255859375
epoch: 38 training_loss 3.4694475317001343 test_loss: 3.6020641326904297
epoch: 39 training_loss 3.4173607659339904 test_loss: 3.4086868286132814
epoch: 40 training_loss 3.338871123790741 test_loss: 3.2525299072265623
epoch: 41 training_loss 3.4408254337310793 test_loss: 3.150307464599609
epoch: 42 training_loss 3.3136991095542907 test_loss: 3.4901992797851564
epoch: 43 training_loss 3.3874538064002992 test_loss: 3.267935562133789
epoch: 44 training_loss 3.2831891989707946 test_loss: 3.1132482528686523
epoch: 45 training_loss 3.2473709034919738 test_loss: 3.312916946411133
epoch: 46 training_loss 3.3338914465904237 test_loss: 3.1997161865234376
epoch: 47 training_loss 3.2769682097434996 test_loss: 3.2613616943359376
epoch: 48 training_loss 3.2244444060325623 test_loss: 3.249441909790039
epoch: 49 training_loss 3.117781467437744 test_loss: 3.241899108886719
epoch: 50 training_loss 3.115961875915527 test_loss: 3.167117691040039
epoch: 51 training_loss 3.1206125044822692 test_loss: 2.79632682800293
epoch: 52 training_loss 3.1728656315803527 test_loss: 3.0441354751586913
epoch: 53 training_loss 3.1027610206604006 test_loss: 3.1192508697509767
epoch: 54 training_loss 3.0284578156471254 test_loss: 3.096743583679199
epoch: 55 training_loss 3.0657505130767824 test_loss: 3.1543014526367186
epoch: 56 training_loss 3.120633409023285 test_loss: 2.9814266204833983
epoch: 57 training_loss 2.940154972076416 test_loss: 3.000743865966797
epoch: 58 training_loss 3.0660721468925476 test_loss: 2.98223991394043
epoch: 59 training_loss 2.9319664454460144 test_loss: 2.817830276489258
epoch: 60 training_loss 3.011380512714386 test_loss: 2.8721561431884766
epoch: 61 training_loss 2.973940098285675 test_loss: 3.0113691329956054
epoch: 62 training_loss 2.9284573817253112 test_loss: 2.8620920181274414
epoch: 63 training_loss 2.887114827632904 test_loss: 2.903636360168457
epoch: 64 training_loss 2.8453872704505923 test_loss: 2.774271583557129
epoch: 65 training_loss 2.860040922164917 test_loss: 2.869704246520996
epoch: 66 training_loss 2.886065080165863 test_loss: 2.9401552200317385
epoch: 67 training_loss 2.881685247421265 test_loss: 2.698935890197754
epoch: 68 training_loss 2.8557729578018187 test_loss: 2.9016353607177736
epoch: 69 training_loss 2.831483020782471 test_loss: 2.857174110412598
epoch: 70 training_loss 2.8368661427497863 test_loss: 2.8411891937255858
epoch: 71 training_loss 2.859689748287201 test_loss: 2.773988723754883
epoch: 72 training_loss 2.7771571469306946 test_loss: 2.9288141250610353
epoch: 73 training_loss 2.777255218029022 test_loss: 2.7340024948120116
epoch: 74 training_loss 2.751512995958328 test_loss: 2.5865198135375977
epoch: 75 training_loss 2.8256556618213655 test_loss: 2.851504325866699
epoch: 76 training_loss 2.748666474819183 test_loss: 2.7288326263427733
epoch: 77 training_loss 2.7690231823921203 test_loss: 2.711246299743652
epoch: 78 training_loss 2.771013035774231 test_loss: 2.874375343322754
epoch: 79 training_loss 2.718060293197632 test_loss: 2.7330862045288087
epoch: 80 training_loss 2.6580679321289065 test_loss: 2.6709550857543944
epoch: 81 training_loss 2.711796672344208 test_loss: 2.7712692260742187
epoch: 82 training_loss 2.730461114645004 test_loss: 2.823272705078125
epoch: 83 training_loss 2.7121407341957093 test_loss: 2.8399948120117187
epoch: 84 training_loss 2.680428227186203 test_loss: 2.6333553314208986
epoch: 85 training_loss 2.7474015378952026 test_loss: 2.7682064056396483
epoch: 86 training_loss 2.630827351808548 test_loss: 2.682833671569824
epoch: 87 training_loss 2.6329386389255522 test_loss: 2.5745416641235352
epoch: 88 training_loss 2.6517589545249938 test_loss: 2.6108497619628905
epoch: 89 training_loss 2.627737727165222 test_loss: 2.7320579528808593
epoch: 90 training_loss 2.618881597518921 test_loss: 2.595577430725098
epoch: 91 training_loss 2.633523609638214 test_loss: 2.5953683853149414
epoch: 92 training_loss 2.677464084625244 test_loss: 2.6095611572265627
epoch: 93 training_loss 2.584238500595093 test_loss: 2.4942256927490236
epoch: 94 training_loss 2.611901967525482 test_loss: 2.3676570892333983
epoch: 95 training_loss 2.610351231098175 test_loss: 2.533324432373047
epoch: 96 training_loss 2.6223404598236084 test_loss: 2.464426803588867
epoch: 97 training_loss 2.533200541734695 test_loss: 2.456762504577637
epoch: 98 training_loss 2.5152777576446534 test_loss: 2.5168842315673827
epoch: 99 training_loss 2.568792015314102 test_loss: 2.5772802352905275
epoch: 100 training_loss 2.5247677040100096 test_loss: 2.4731830596923827
epoch: 101 training_loss 2.545159168243408 test_loss: 2.586595916748047
epoch: 102 training_loss 2.5033038532733918 test_loss: 2.463637924194336
epoch: 103 training_loss 2.50266357421875 test_loss: 2.3314918518066405
epoch: 104 training_loss 2.478604800701141 test_loss: 2.6712661743164063
epoch: 105 training_loss 2.5044930708408355 test_loss: 2.6004913330078123
epoch: 106 training_loss 2.483378530740738 test_loss: 2.467552375793457
epoch: 107 training_loss 2.478835173845291 test_loss: 2.7001459121704103
epoch: 108 training_loss 2.515029106140137 test_loss: 2.5915338516235353
epoch: 109 training_loss 2.498913536071777 test_loss: 2.328380012512207
epoch: 110 training_loss 2.4946481835842134 test_loss: 2.5230745315551757
epoch: 111 training_loss 2.4428349804878233 test_loss: 2.4416112899780273
epoch: 112 training_loss 2.5385948729515078 test_loss: 2.6458864212036133
epoch: 113 training_loss 2.4803285026550292 test_loss: 2.386417770385742
epoch: 114 training_loss 2.4885904574394226 test_loss: 2.5114376068115236
epoch: 115 training_loss 2.5335297811031343 test_loss: 2.350711441040039
epoch: 116 training_loss 2.5269735515117646 test_loss: 2.4660480499267576
epoch: 117 training_loss 2.3737906610965727 test_loss: 2.3742347717285157
epoch: 118 training_loss 2.460090810060501 test_loss: 2.4326030731201174
epoch: 119 training_loss 2.4352719461917878 test_loss: 2.3233322143554687
epoch: 120 training_loss 2.4073161244392396 test_loss: 2.5092273712158204
epoch: 121 training_loss 2.4036484026908873 test_loss: 2.2703786849975587
epoch: 122 training_loss 2.4179043912887574 test_loss: 2.374637985229492
epoch: 123 training_loss 2.382563146352768 test_loss: 2.3790586471557615
epoch: 124 training_loss 2.4106339907646177 test_loss: 2.5163911819458007
epoch: 125 training_loss 2.4200077974796295 test_loss: 2.242258644104004
epoch: 126 training_loss 2.4480773878097533 test_loss: 2.5447240829467774
epoch: 127 training_loss 2.449174944162369 test_loss: 2.459459114074707
epoch: 128 training_loss 2.379141422510147 test_loss: 2.3436748504638674
epoch: 129 training_loss 2.3856153774261473 test_loss: 2.497816467285156
epoch: 130 training_loss 2.387519578933716 test_loss: 2.3679304122924805
epoch: 131 training_loss 2.3333612966537474 test_loss: 2.3171619415283202
epoch: 132 training_loss 2.4610053730010986 test_loss: 2.406646728515625
epoch: 133 training_loss 2.3653158807754515 test_loss: 2.362381172180176
epoch: 134 training_loss 2.350551195144653 test_loss: 2.31256160736084
epoch: 135 training_loss 2.3774341523647307 test_loss: 2.443406105041504
epoch: 136 training_loss 2.3492381942272185 test_loss: 2.3742948532104493
epoch: 137 training_loss 2.376278269290924 test_loss: 2.360690879821777
epoch: 138 training_loss 2.349105418920517 test_loss: 2.1908802032470702
epoch: 139 training_loss 2.3227774465084075 test_loss: 2.203810119628906
epoch: 140 training_loss 2.359360346794128 test_loss: 2.274917411804199
epoch: 141 training_loss 2.343275557756424 test_loss: 2.564426231384277
epoch: 142 training_loss 2.3288084304332735 test_loss: 2.254330635070801
epoch: 143 training_loss 2.298107794523239 test_loss: 2.2426782608032227
epoch: 144 training_loss 2.2921626555919645 test_loss: 2.484366798400879
epoch: 145 training_loss 2.296792390346527 test_loss: 2.291263198852539
epoch: 146 training_loss 2.3084719920158387 test_loss: 2.3995805740356446
epoch: 147 training_loss 2.3458783972263335 test_loss: 2.3226579666137694
epoch: 148 training_loss 2.3171624684333803 test_loss: 2.324279022216797
epoch: 149 training_loss 2.304818251132965 test_loss: 2.1075448989868164
2759.135993438741
episode: 0 training return: tensor(103.9253, device='cuda:0')
episode: 1 training return: tensor(223.5017, device='cuda:0')
episode: 2 training return: tensor(335.8786, device='cuda:0')
episode: 3 training return: tensor(-79.5086, device='cuda:0')
epoch: 1 test_true_pfm: 2752.735911512958 sim_pfm: 203.8072434682302
episode: 4 training return: tensor(-247.7721, device='cuda:0')
episode: 5 training return: tensor(-255.0773, device='cuda:0')
episode: 6 training return: tensor(36.6334, device='cuda:0')
episode: 7 training return: tensor(353.9529, device='cuda:0')
epoch: 2 test_true_pfm: 2416.7600331289655 sim_pfm: 114.30804862691245
episode: 8 training return: tensor(202.1482, device='cuda:0')
episode: 9 training return: tensor(248.4157, device='cuda:0')
episode: 10 training return: tensor(347.5048, device='cuda:0')
episode: 11 training return: tensor(-29.7656, device='cuda:0')
epoch: 3 test_true_pfm: 3211.2184064849935 sim_pfm: 298.93255946355447
episode: 12 training return: tensor(214.0574, device='cuda:0')
episode: 13 training return: tensor(-167.6859, device='cuda:0')
episode: 14 training return: tensor(132.7067, device='cuda:0')
episode: 15 training return: tensor(266.3408, device='cuda:0')
epoch: 4 test_true_pfm: 2907.757492871709 sim_pfm: 104.91280053346418
episode: 16 training return: tensor(415.0095, device='cuda:0')
episode: 17 training return: tensor(285.3766, device='cuda:0')
episode: 18 training return: tensor(-366.3970, device='cuda:0')
episode: 19 training return: tensor(132.8291, device='cuda:0')
epoch: 5 test_true_pfm: 1859.4797480678992 sim_pfm: 183.37322868187525
episode: 20 training return: tensor(-243.3335, device='cuda:0')
episode: 21 training return: tensor(-60.6374, device='cuda:0')
episode: 22 training return: tensor(-42.2964, device='cuda:0')
episode: 23 training return: tensor(277.3254, device='cuda:0')
epoch: 6 test_true_pfm: 2838.2086318569527 sim_pfm: 157.45884009777606
episode: 24 training return: tensor(-209.2593, device='cuda:0')
episode: 25 training return: tensor(105.3014, device='cuda:0')
episode: 26 training return: tensor(382.9534, device='cuda:0')
episode: 27 training return: tensor(-19.9026, device='cuda:0')
epoch: 7 test_true_pfm: 2841.3119868320136 sim_pfm: 155.4901884502227
episode: 28 training return: tensor(383.4308, device='cuda:0')
episode: 29 training return: tensor(-49.9393, device='cuda:0')
episode: 30 training return: tensor(255.9317, device='cuda:0')
episode: 31 training return: tensor(351.9856, device='cuda:0')
epoch: 8 test_true_pfm: 2639.293857152307 sim_pfm: -10.969681055052206
episode: 32 training return: tensor(341.4931, device='cuda:0')
episode: 33 training return: tensor(-359.4889, device='cuda:0')
episode: 34 training return: tensor(310.0710, device='cuda:0')
episode: 35 training return: tensor(384.5990, device='cuda:0')
epoch: 9 test_true_pfm: 3048.3235213032635 sim_pfm: 221.8684465966071
episode: 36 training return: tensor(-206.1324, device='cuda:0')
episode: 37 training return: tensor(-89.2315, device='cuda:0')
episode: 38 training return: tensor(309.8343, device='cuda:0')
episode: 39 training return: tensor(-137.2243, device='cuda:0')
epoch: 10 test_true_pfm: 3276.7036988221585 sim_pfm: 138.43204809726254
episode: 40 training return: tensor(295.8983, device='cuda:0')
episode: 41 training return: tensor(344.1274, device='cuda:0')
episode: 42 training return: tensor(-5.1949, device='cuda:0')
episode: 43 training return: tensor(331.4747, device='cuda:0')
epoch: 11 test_true_pfm: 2183.5996031791815 sim_pfm: 55.74058523552958
episode: 44 training return: tensor(382.6389, device='cuda:0')
episode: 45 training return: tensor(318.2078, device='cuda:0')
episode: 46 training return: tensor(-163.4050, device='cuda:0')
episode: 47 training return: tensor(348.9902, device='cuda:0')
epoch: 12 test_true_pfm: 2731.1932285445523 sim_pfm: -110.91721960170737
episode: 48 training return: tensor(101.8449, device='cuda:0')
episode: 49 training return: tensor(-186.5473, device='cuda:0')
episode: 50 training return: tensor(150.1768, device='cuda:0')
episode: 51 training return: tensor(362.2643, device='cuda:0')
epoch: 13 test_true_pfm: 3179.899326317136 sim_pfm: 253.70723836197672
episode: 52 training return: tensor(377.3464, device='cuda:0')
episode: 53 training return: tensor(-152.9470, device='cuda:0')
episode: 54 training return: tensor(203.7824, device='cuda:0')
episode: 55 training return: tensor(225.4818, device='cuda:0')
epoch: 14 test_true_pfm: 2955.094189383061 sim_pfm: -24.44358255244636
episode: 56 training return: tensor(402.1592, device='cuda:0')
episode: 57 training return: tensor(326.4145, device='cuda:0')
episode: 58 training return: tensor(352.4768, device='cuda:0')
episode: 59 training return: tensor(321.7996, device='cuda:0')
epoch: 15 test_true_pfm: 3199.789777023174 sim_pfm: 165.71651291633802
episode: 60 training return: tensor(335.9945, device='cuda:0')
episode: 61 training return: tensor(284.6486, device='cuda:0')
episode: 62 training return: tensor(57.7705, device='cuda:0')
episode: 63 training return: tensor(-349.8136, device='cuda:0')
epoch: 16 test_true_pfm: 3440.0418308887124 sim_pfm: 95.22041310651305
episode: 64 training return: tensor(316.1500, device='cuda:0')
episode: 65 training return: tensor(-275.3997, device='cuda:0')
episode: 66 training return: tensor(187.1911, device='cuda:0')
episode: 67 training return: tensor(-43.6098, device='cuda:0')
epoch: 17 test_true_pfm: 3189.1663631444485 sim_pfm: -15.472602897808732
episode: 68 training return: tensor(285.8042, device='cuda:0')
episode: 69 training return: tensor(300.8574, device='cuda:0')
episode: 70 training return: tensor(-130.0791, device='cuda:0')
episode: 71 training return: tensor(417.1136, device='cuda:0')
epoch: 18 test_true_pfm: 3311.662719066197 sim_pfm: 351.1071471686203
episode: 72 training return: tensor(373.5135, device='cuda:0')
episode: 73 training return: tensor(-201.4981, device='cuda:0')
episode: 74 training return: tensor(67.4440, device='cuda:0')
episode: 75 training return: tensor(304.3014, device='cuda:0')
epoch: 19 test_true_pfm: 2195.674153163295 sim_pfm: 272.76646076499793
episode: 76 training return: tensor(381.7704, device='cuda:0')
episode: 77 training return: tensor(-8.0793, device='cuda:0')
episode: 78 training return: tensor(65.6026, device='cuda:0')
episode: 79 training return: tensor(369.9033, device='cuda:0')
epoch: 20 test_true_pfm: 2890.126455799235 sim_pfm: 306.8644173447974
episode: 80 training return: tensor(483.5786, device='cuda:0')
episode: 81 training return: tensor(303.3040, device='cuda:0')
episode: 82 training return: tensor(421.9196, device='cuda:0')
episode: 83 training return: tensor(379.3415, device='cuda:0')
epoch: 21 test_true_pfm: 3424.863739294459 sim_pfm: -77.6498323433043
episode: 84 training return: tensor(402.8050, device='cuda:0')
episode: 85 training return: tensor(226.8305, device='cuda:0')
episode: 86 training return: tensor(323.5486, device='cuda:0')
episode: 87 training return: tensor(343.9336, device='cuda:0')
epoch: 22 test_true_pfm: 3406.3134911391294 sim_pfm: 361.4492299879009
episode: 88 training return: tensor(287.9095, device='cuda:0')
episode: 89 training return: tensor(249.7026, device='cuda:0')
episode: 90 training return: tensor(380.3722, device='cuda:0')
episode: 91 training return: tensor(-185.8523, device='cuda:0')
epoch: 23 test_true_pfm: 3112.053680860134 sim_pfm: 283.6343008582092
episode: 92 training return: tensor(368.3358, device='cuda:0')
episode: 93 training return: tensor(351.1394, device='cuda:0')
episode: 94 training return: tensor(375.9639, device='cuda:0')
episode: 95 training return: tensor(300.3837, device='cuda:0')
epoch: 24 test_true_pfm: 3104.4201070750373 sim_pfm: 389.4092844744834
episode: 96 training return: tensor(83.1468, device='cuda:0')
episode: 97 training return: tensor(340.2798, device='cuda:0')
episode: 98 training return: tensor(403.5430, device='cuda:0')
episode: 99 training return: tensor(351.9883, device='cuda:0')
epoch: 25 test_true_pfm: 3438.047086401823 sim_pfm: 312.5968695090075
episode: 100 training return: tensor(248.7540, device='cuda:0')
episode: 101 training return: tensor(335.2929, device='cuda:0')
episode: 102 training return: tensor(306.6049, device='cuda:0')
episode: 103 training return: tensor(345.7641, device='cuda:0')
epoch: 26 test_true_pfm: 3504.0285590362655 sim_pfm: 373.71932629785925
episode: 104 training return: tensor(359.6047, device='cuda:0')
episode: 105 training return: tensor(256.1766, device='cuda:0')
episode: 106 training return: tensor(405.7396, device='cuda:0')
episode: 107 training return: tensor(193.6042, device='cuda:0')
epoch: 27 test_true_pfm: 3358.0146128941287 sim_pfm: 388.21173683767364
episode: 108 training return: tensor(368.2655, device='cuda:0')
episode: 109 training return: tensor(-140.5862, device='cuda:0')
episode: 110 training return: tensor(404.3429, device='cuda:0')
episode: 111 training return: tensor(227.2442, device='cuda:0')
epoch: 28 test_true_pfm: 3315.315354850758 sim_pfm: 328.3759718063423
episode: 112 training return: tensor(386.7650, device='cuda:0')
episode: 113 training return: tensor(423.1157, device='cuda:0')
episode: 114 training return: tensor(-165.4800, device='cuda:0')
episode: 115 training return: tensor(426.7917, device='cuda:0')
epoch: 29 test_true_pfm: 2594.919846772591 sim_pfm: 379.5015395784479
episode: 116 training return: tensor(453.3298, device='cuda:0')
episode: 117 training return: tensor(315.4130, device='cuda:0')
episode: 118 training return: tensor(-207.8549, device='cuda:0')
episode: 119 training return: tensor(474.5078, device='cuda:0')
epoch: 30 test_true_pfm: 3113.6358228159293 sim_pfm: 254.70511464669835
episode: 120 training return: tensor(408.3734, device='cuda:0')
episode: 121 training return: tensor(369.4698, device='cuda:0')
episode: 122 training return: tensor(-41.4192, device='cuda:0')
episode: 123 training return: tensor(353.0907, device='cuda:0')
epoch: 31 test_true_pfm: 3423.375724937076 sim_pfm: 392.5831522785981
episode: 124 training return: tensor(309.4338, device='cuda:0')
episode: 125 training return: tensor(361.6614, device='cuda:0')
episode: 126 training return: tensor(358.4106, device='cuda:0')
episode: 127 training return: tensor(376.3904, device='cuda:0')
epoch: 32 test_true_pfm: 3108.7011302551177 sim_pfm: 328.53159398564213
episode: 128 training return: tensor(324.5602, device='cuda:0')
episode: 129 training return: tensor(400.8531, device='cuda:0')
episode: 130 training return: tensor(-15.2263, device='cuda:0')
episode: 131 training return: tensor(413.0301, device='cuda:0')
epoch: 33 test_true_pfm: 3441.8570281090415 sim_pfm: 347.89465044486377
episode: 132 training return: tensor(371.7810, device='cuda:0')
episode: 133 training return: tensor(288.4342, device='cuda:0')
episode: 134 training return: tensor(280.0222, device='cuda:0')
episode: 135 training return: tensor(327.5180, device='cuda:0')
epoch: 34 test_true_pfm: 3382.1032429331954 sim_pfm: 248.05545927906255
episode: 136 training return: tensor(366.6487, device='cuda:0')
episode: 137 training return: tensor(344.8893, device='cuda:0')
episode: 138 training return: tensor(80.0740, device='cuda:0')
episode: 139 training return: tensor(309.1641, device='cuda:0')
epoch: 35 test_true_pfm: 3390.117731516644 sim_pfm: 398.6087874614556
episode: 140 training return: tensor(208.2957, device='cuda:0')
episode: 141 training return: tensor(143.0200, device='cuda:0')
episode: 142 training return: tensor(326.4565, device='cuda:0')
episode: 143 training return: tensor(340.7055, device='cuda:0')
epoch: 36 test_true_pfm: 3389.919346262059 sim_pfm: 330.03261466602754
episode: 144 training return: tensor(18.5124, device='cuda:0')
episode: 145 training return: tensor(432.4731, device='cuda:0')
episode: 146 training return: tensor(361.1845, device='cuda:0')
episode: 147 training return: tensor(278.9828, device='cuda:0')
epoch: 37 test_true_pfm: 2944.733433240497 sim_pfm: 349.0407084093701
episode: 148 training return: tensor(378.4038, device='cuda:0')
episode: 149 training return: tensor(375.4907, device='cuda:0')
episode: 150 training return: tensor(7.9082, device='cuda:0')
episode: 151 training return: tensor(429.6979, device='cuda:0')
epoch: 38 test_true_pfm: 3425.1115905314878 sim_pfm: 265.7603614864929
episode: 152 training return: tensor(406.2300, device='cuda:0')
episode: 153 training return: tensor(315.7546, device='cuda:0')
episode: 154 training return: tensor(314.0503, device='cuda:0')
episode: 155 training return: tensor(374.7335, device='cuda:0')
epoch: 39 test_true_pfm: 3324.5686355004086 sim_pfm: 364.14851766390103
episode: 156 training return: tensor(288.5796, device='cuda:0')
episode: 157 training return: tensor(121.6823, device='cuda:0')
episode: 158 training return: tensor(-442.6545, device='cuda:0')
episode: 159 training return: tensor(313.3311, device='cuda:0')
epoch: 40 test_true_pfm: 3387.830940813466 sim_pfm: 281.81390608932514
episode: 160 training return: tensor(397.0281, device='cuda:0')
episode: 161 training return: tensor(385.7140, device='cuda:0')
episode: 162 training return: tensor(73.0557, device='cuda:0')
episode: 163 training return: tensor(300.1479, device='cuda:0')
epoch: 41 test_true_pfm: 3201.3524631732994 sim_pfm: 328.91817941849393
episode: 164 training return: tensor(367.6864, device='cuda:0')
episode: 165 training return: tensor(339.8535, device='cuda:0')
episode: 166 training return: tensor(335.6326, device='cuda:0')
episode: 167 training return: tensor(385.5334, device='cuda:0')
epoch: 42 test_true_pfm: 3220.0771813127335 sim_pfm: 328.23419953649864
episode: 168 training return: tensor(385.7819, device='cuda:0')
episode: 169 training return: tensor(412.4969, device='cuda:0')
episode: 170 training return: tensor(286.6322, device='cuda:0')
episode: 171 training return: tensor(351.6183, device='cuda:0')
epoch: 43 test_true_pfm: 3447.477386070927 sim_pfm: 357.44796463800594
episode: 172 training return: tensor(387.6335, device='cuda:0')
episode: 173 training return: tensor(346.7199, device='cuda:0')
episode: 174 training return: tensor(319.2292, device='cuda:0')
episode: 175 training return: tensor(110.7272, device='cuda:0')
epoch: 44 test_true_pfm: 2953.8471958725568 sim_pfm: 380.8357134431232
episode: 176 training return: tensor(347.1216, device='cuda:0')
episode: 177 training return: tensor(296.8712, device='cuda:0')
episode: 178 training return: tensor(406.4034, device='cuda:0')
episode: 179 training return: tensor(87.3741, device='cuda:0')
epoch: 45 test_true_pfm: 3420.9234000698602 sim_pfm: 369.24638516353053
episode: 180 training return: tensor(340.8586, device='cuda:0')
episode: 181 training return: tensor(318.3972, device='cuda:0')
episode: 182 training return: tensor(393.2997, device='cuda:0')
episode: 183 training return: tensor(327.2610, device='cuda:0')
epoch: 46 test_true_pfm: 3406.933420483291 sim_pfm: 335.55981749412604
episode: 184 training return: tensor(302.1227, device='cuda:0')
episode: 185 training return: tensor(335.3536, device='cuda:0')
episode: 186 training return: tensor(337.0341, device='cuda:0')
episode: 187 training return: tensor(341.6557, device='cuda:0')
epoch: 47 test_true_pfm: 3370.51776705886 sim_pfm: 373.37612040558207
episode: 188 training return: tensor(338.7707, device='cuda:0')
episode: 189 training return: tensor(354.2016, device='cuda:0')
episode: 190 training return: tensor(384.0157, device='cuda:0')
episode: 191 training return: tensor(381.1873, device='cuda:0')
epoch: 48 test_true_pfm: 3426.803384865374 sim_pfm: 344.8624294854817
episode: 192 training return: tensor(282.8609, device='cuda:0')
episode: 193 training return: tensor(-58.5747, device='cuda:0')
episode: 194 training return: tensor(239.5079, device='cuda:0')
episode: 195 training return: tensor(-22.3737, device='cuda:0')
epoch: 49 test_true_pfm: 3433.841810275404 sim_pfm: 356.29316888941685
episode: 196 training return: tensor(357.6008, device='cuda:0')
episode: 197 training return: tensor(331.2699, device='cuda:0')
episode: 198 training return: tensor(340.2536, device='cuda:0')
episode: 199 training return: tensor(265.5318, device='cuda:0')
epoch: 50 test_true_pfm: 3187.4215153109894 sim_pfm: 106.03364839187513
episode: 200 training return: tensor(369.1148, device='cuda:0')
episode: 201 training return: tensor(154.3510, device='cuda:0')
episode: 202 training return: tensor(430.3907, device='cuda:0')
episode: 203 training return: tensor(295.4023, device='cuda:0')
epoch: 51 test_true_pfm: 2968.3025741723527 sim_pfm: 350.7667026346705
episode: 204 training return: tensor(394.3012, device='cuda:0')
episode: 205 training return: tensor(316.7545, device='cuda:0')
episode: 206 training return: tensor(303.7600, device='cuda:0')
episode: 207 training return: tensor(-1.5977, device='cuda:0')
epoch: 52 test_true_pfm: 3446.165942822198 sim_pfm: 363.61254878592445
episode: 208 training return: tensor(360.3999, device='cuda:0')
episode: 209 training return: tensor(325.8214, device='cuda:0')
episode: 210 training return: tensor(357.0835, device='cuda:0')
episode: 211 training return: tensor(327.3762, device='cuda:0')
epoch: 53 test_true_pfm: 3328.0681736175297 sim_pfm: 100.5159969284626
episode: 212 training return: tensor(399.1965, device='cuda:0')
episode: 213 training return: tensor(361.2969, device='cuda:0')
episode: 214 training return: tensor(243.9325, device='cuda:0')
episode: 215 training return: tensor(367.6354, device='cuda:0')
epoch: 54 test_true_pfm: 3094.5257862371177 sim_pfm: 375.4562915629746
episode: 216 training return: tensor(357.8936, device='cuda:0')
episode: 217 training return: tensor(-124.3883, device='cuda:0')
episode: 218 training return: tensor(280.2614, device='cuda:0')
episode: 219 training return: tensor(357.6011, device='cuda:0')
epoch: 55 test_true_pfm: 3409.4271815064967 sim_pfm: 323.6451360043332
episode: 220 training return: tensor(290.9982, device='cuda:0')
episode: 221 training return: tensor(336.9503, device='cuda:0')
episode: 222 training return: tensor(368.7813, device='cuda:0')
episode: 223 training return: tensor(415.1804, device='cuda:0')
epoch: 56 test_true_pfm: 3359.9403021534513 sim_pfm: 364.77917860309634
episode: 224 training return: tensor(362.9764, device='cuda:0')
episode: 225 training return: tensor(370.2831, device='cuda:0')
episode: 226 training return: tensor(348.6259, device='cuda:0')
episode: 227 training return: tensor(-124.0554, device='cuda:0')
epoch: 57 test_true_pfm: 3452.5451536238356 sim_pfm: 382.55729127425974
episode: 228 training return: tensor(399.1281, device='cuda:0')
episode: 229 training return: tensor(353.8677, device='cuda:0')
episode: 230 training return: tensor(-101.4480, device='cuda:0')
episode: 231 training return: tensor(401.3820, device='cuda:0')
epoch: 58 test_true_pfm: 3407.5928708037063 sim_pfm: 349.8773952375438
episode: 232 training return: tensor(322.8994, device='cuda:0')
episode: 233 training return: tensor(155.8530, device='cuda:0')
episode: 234 training return: tensor(97.2205, device='cuda:0')
episode: 235 training return: tensor(366.1126, device='cuda:0')
epoch: 59 test_true_pfm: 3421.9631937700924 sim_pfm: 345.44645886398695
episode: 236 training return: tensor(317.6416, device='cuda:0')
episode: 237 training return: tensor(397.0497, device='cuda:0')
episode: 238 training return: tensor(119.4115, device='cuda:0')
episode: 239 training return: tensor(375.1941, device='cuda:0')
epoch: 60 test_true_pfm: 3419.411260178862 sim_pfm: 309.4264331287607
episode: 240 training return: tensor(410.7681, device='cuda:0')
episode: 241 training return: tensor(371.4999, device='cuda:0')
episode: 242 training return: tensor(257.5123, device='cuda:0')
episode: 243 training return: tensor(351.8810, device='cuda:0')
epoch: 61 test_true_pfm: 3384.773412758486 sim_pfm: 292.19031995736685
episode: 244 training return: tensor(358.1065, device='cuda:0')
episode: 245 training return: tensor(382.8338, device='cuda:0')
episode: 246 training return: tensor(384.6337, device='cuda:0')
episode: 247 training return: tensor(-167.6149, device='cuda:0')
epoch: 62 test_true_pfm: 3174.9451609189164 sim_pfm: 360.3335392724742
episode: 248 training return: tensor(301.4542, device='cuda:0')
episode: 249 training return: tensor(371.7223, device='cuda:0')
episode: 250 training return: tensor(310.5281, device='cuda:0')
episode: 251 training return: tensor(62.4206, device='cuda:0')
epoch: 63 test_true_pfm: 2840.0807933587857 sim_pfm: 352.658387011829
episode: 252 training return: tensor(339.1395, device='cuda:0')
episode: 253 training return: tensor(194.2278, device='cuda:0')
episode: 254 training return: tensor(344.4255, device='cuda:0')
episode: 255 training return: tensor(365.9702, device='cuda:0')
epoch: 64 test_true_pfm: 3373.436889965779 sim_pfm: 387.37540484478814
episode: 256 training return: tensor(374.7289, device='cuda:0')
episode: 257 training return: tensor(305.9811, device='cuda:0')
episode: 258 training return: tensor(398.2325, device='cuda:0')
episode: 259 training return: tensor(244.1019, device='cuda:0')
epoch: 65 test_true_pfm: 3372.336392242992 sim_pfm: 383.3450490256364
episode: 260 training return: tensor(367.2633, device='cuda:0')
episode: 261 training return: tensor(399.7409, device='cuda:0')
episode: 262 training return: tensor(-325.1068, device='cuda:0')
episode: 263 training return: tensor(359.7112, device='cuda:0')
epoch: 66 test_true_pfm: 3372.6111108214627 sim_pfm: 297.2717590177878
episode: 264 training return: tensor(328.4833, device='cuda:0')
episode: 265 training return: tensor(25.2149, device='cuda:0')
episode: 266 training return: tensor(405.8036, device='cuda:0')
episode: 267 training return: tensor(331.1363, device='cuda:0')
epoch: 67 test_true_pfm: 3360.645983091405 sim_pfm: 370.2763702546945
episode: 268 training return: tensor(421.1909, device='cuda:0')
episode: 269 training return: tensor(315.3368, device='cuda:0')
episode: 270 training return: tensor(-45.2035, device='cuda:0')
episode: 271 training return: tensor(360.2010, device='cuda:0')
epoch: 68 test_true_pfm: 3420.0492795237556 sim_pfm: 377.1692868152847
episode: 272 training return: tensor(362.5731, device='cuda:0')
episode: 273 training return: tensor(349.3772, device='cuda:0')
episode: 274 training return: tensor(311.9565, device='cuda:0')
episode: 275 training return: tensor(395.4489, device='cuda:0')
epoch: 69 test_true_pfm: 3382.438044974728 sim_pfm: 358.61935997723293
episode: 276 training return: tensor(411.0640, device='cuda:0')
episode: 277 training return: tensor(368.6201, device='cuda:0')
episode: 278 training return: tensor(359.6160, device='cuda:0')
episode: 279 training return: tensor(376.8709, device='cuda:0')
epoch: 70 test_true_pfm: 3401.5653313771727 sim_pfm: 414.2204376066608
episode: 280 training return: tensor(470.3467, device='cuda:0')
episode: 281 training return: tensor(332.3018, device='cuda:0')
episode: 282 training return: tensor(304.1648, device='cuda:0')
episode: 283 training return: tensor(246.9746, device='cuda:0')
epoch: 71 test_true_pfm: 3308.5206173057936 sim_pfm: 310.3530759022494
episode: 284 training return: tensor(335.8335, device='cuda:0')
episode: 285 training return: tensor(402.4184, device='cuda:0')
episode: 286 training return: tensor(390.2752, device='cuda:0')
episode: 287 training return: tensor(387.1917, device='cuda:0')
epoch: 72 test_true_pfm: 3381.5084766331806 sim_pfm: 344.29177389732405
episode: 288 training return: tensor(381.2169, device='cuda:0')
episode: 289 training return: tensor(407.5962, device='cuda:0')
episode: 290 training return: tensor(350.6238, device='cuda:0')
episode: 291 training return: tensor(305.7456, device='cuda:0')
epoch: 73 test_true_pfm: 3406.336799011813 sim_pfm: 360.3028311970217
episode: 292 training return: tensor(364.7780, device='cuda:0')
episode: 293 training return: tensor(346.7970, device='cuda:0')
episode: 294 training return: tensor(385.8793, device='cuda:0')
episode: 295 training return: tensor(93.0637, device='cuda:0')
epoch: 74 test_true_pfm: 3414.0367088949006 sim_pfm: 381.3681430306751
episode: 296 training return: tensor(401.1718, device='cuda:0')
episode: 297 training return: tensor(-111.7928, device='cuda:0')
episode: 298 training return: tensor(281.2511, device='cuda:0')
episode: 299 training return: tensor(325.2419, device='cuda:0')
epoch: 75 test_true_pfm: 3484.962379184599 sim_pfm: 406.0458057710396
episode: 300 training return: tensor(336.8319, device='cuda:0')
episode: 301 training return: tensor(305.9724, device='cuda:0')
episode: 302 training return: tensor(444.9985, device='cuda:0')
episode: 303 training return: tensor(321.1203, device='cuda:0')
epoch: 76 test_true_pfm: 3408.8227320768597 sim_pfm: 337.01497186813504
episode: 304 training return: tensor(-158.5182, device='cuda:0')
episode: 305 training return: tensor(372.6331, device='cuda:0')
episode: 306 training return: tensor(10.6433, device='cuda:0')
episode: 307 training return: tensor(420.7385, device='cuda:0')
epoch: 77 test_true_pfm: 2885.9025305601876 sim_pfm: 346.6484772772722
episode: 308 training return: tensor(375.6932, device='cuda:0')
episode: 309 training return: tensor(-64.5778, device='cuda:0')
episode: 310 training return: tensor(384.0099, device='cuda:0')
episode: 311 training return: tensor(-90.5368, device='cuda:0')
epoch: 78 test_true_pfm: 3413.924339875684 sim_pfm: 361.0618445735211
episode: 312 training return: tensor(-411.4862, device='cuda:0')
episode: 313 training return: tensor(289.8915, device='cuda:0')
episode: 314 training return: tensor(324.2935, device='cuda:0')
episode: 315 training return: tensor(108.0844, device='cuda:0')
epoch: 79 test_true_pfm: 3444.7095169795098 sim_pfm: 316.12106590601616
episode: 316 training return: tensor(401.5907, device='cuda:0')
episode: 317 training return: tensor(431.5886, device='cuda:0')
episode: 318 training return: tensor(431.7060, device='cuda:0')
episode: 319 training return: tensor(339.2828, device='cuda:0')
epoch: 80 test_true_pfm: 3422.922259899058 sim_pfm: 399.77174237189075
episode: 320 training return: tensor(410.5348, device='cuda:0')
episode: 321 training return: tensor(386.1667, device='cuda:0')
episode: 322 training return: tensor(-250.5053, device='cuda:0')
episode: 323 training return: tensor(386.3918, device='cuda:0')
epoch: 81 test_true_pfm: 2927.4962917147895 sim_pfm: 124.78598974303652
episode: 324 training return: tensor(378.6965, device='cuda:0')
episode: 325 training return: tensor(302.1852, device='cuda:0')
episode: 326 training return: tensor(-317.4092, device='cuda:0')
episode: 327 training return: tensor(374.5877, device='cuda:0')
epoch: 82 test_true_pfm: 3269.4190247416645 sim_pfm: 378.2108915905507
episode: 328 training return: tensor(349.5044, device='cuda:0')
episode: 329 training return: tensor(442.7933, device='cuda:0')
episode: 330 training return: tensor(-352.5200, device='cuda:0')
episode: 331 training return: tensor(418.2643, device='cuda:0')
epoch: 83 test_true_pfm: 3523.2124013117555 sim_pfm: 393.962344320588
episode: 332 training return: tensor(365.0165, device='cuda:0')
episode: 333 training return: tensor(353.4506, device='cuda:0')
episode: 334 training return: tensor(182.1547, device='cuda:0')
episode: 335 training return: tensor(414.2160, device='cuda:0')
epoch: 84 test_true_pfm: 2947.8745879114263 sim_pfm: 354.14548161337734
episode: 336 training return: tensor(347.0731, device='cuda:0')
episode: 337 training return: tensor(405.6300, device='cuda:0')
episode: 338 training return: tensor(361.9199, device='cuda:0')
episode: 339 training return: tensor(-75.5112, device='cuda:0')
epoch: 85 test_true_pfm: 3059.5634085805737 sim_pfm: 266.09256483858917
episode: 340 training return: tensor(322.7312, device='cuda:0')
episode: 341 training return: tensor(325.6972, device='cuda:0')
episode: 342 training return: tensor(401.7100, device='cuda:0')
episode: 343 training return: tensor(321.7201, device='cuda:0')
epoch: 86 test_true_pfm: 3458.477353065859 sim_pfm: 370.9845732181954
episode: 344 training return: tensor(345.2603, device='cuda:0')
episode: 345 training return: tensor(349.4973, device='cuda:0')
episode: 346 training return: tensor(424.8349, device='cuda:0')
episode: 347 training return: tensor(346.6098, device='cuda:0')
epoch: 87 test_true_pfm: 3429.139648106404 sim_pfm: 354.7014903703239
episode: 348 training return: tensor(286.7145, device='cuda:0')
episode: 349 training return: tensor(389.0209, device='cuda:0')
episode: 350 training return: tensor(390.5205, device='cuda:0')
episode: 351 training return: tensor(388.0113, device='cuda:0')
epoch: 88 test_true_pfm: 3439.539630000311 sim_pfm: 368.6155292853364
episode: 352 training return: tensor(367.6095, device='cuda:0')
episode: 353 training return: tensor(376.7777, device='cuda:0')
episode: 354 training return: tensor(401.3618, device='cuda:0')
episode: 355 training return: tensor(323.9293, device='cuda:0')
epoch: 89 test_true_pfm: 3416.5074537663827 sim_pfm: 362.4747459551921
episode: 356 training return: tensor(364.9588, device='cuda:0')
episode: 357 training return: tensor(389.2297, device='cuda:0')
episode: 358 training return: tensor(339.9067, device='cuda:0')
episode: 359 training return: tensor(362.1761, device='cuda:0')
epoch: 90 test_true_pfm: 3379.883998329687 sim_pfm: 358.90998591296375
episode: 360 training return: tensor(-125.6870, device='cuda:0')
episode: 361 training return: tensor(391.4174, device='cuda:0')
episode: 362 training return: tensor(132.0200, device='cuda:0')
episode: 363 training return: tensor(302.5038, device='cuda:0')
epoch: 91 test_true_pfm: 3400.8643837977074 sim_pfm: 325.96504434246646
episode: 364 training return: tensor(320.0525, device='cuda:0')
episode: 365 training return: tensor(292.6788, device='cuda:0')
episode: 366 training return: tensor(293.5727, device='cuda:0')
episode: 367 training return: tensor(306.6559, device='cuda:0')
epoch: 92 test_true_pfm: 3422.701490560987 sim_pfm: 383.9996999572807
episode: 368 training return: tensor(-82.8047, device='cuda:0')
episode: 369 training return: tensor(392.9502, device='cuda:0')
episode: 370 training return: tensor(345.7333, device='cuda:0')
episode: 371 training return: tensor(376.2656, device='cuda:0')
epoch: 93 test_true_pfm: 3400.189660923992 sim_pfm: 379.08142477142
episode: 372 training return: tensor(390.4310, device='cuda:0')
episode: 373 training return: tensor(28.4026, device='cuda:0')
episode: 374 training return: tensor(457.4347, device='cuda:0')
episode: 375 training return: tensor(144.2928, device='cuda:0')
epoch: 94 test_true_pfm: 3396.9599621863345 sim_pfm: 364.0663699130043
episode: 376 training return: tensor(386.9174, device='cuda:0')
episode: 377 training return: tensor(361.5969, device='cuda:0')
episode: 378 training return: tensor(346.5092, device='cuda:0')
episode: 379 training return: tensor(330.6931, device='cuda:0')
epoch: 95 test_true_pfm: 3457.5405038145277 sim_pfm: 164.82684742630227
episode: 380 training return: tensor(398.7432, device='cuda:0')
episode: 381 training return: tensor(393.9441, device='cuda:0')
episode: 382 training return: tensor(366.4807, device='cuda:0')
episode: 383 training return: tensor(348.2220, device='cuda:0')
epoch: 96 test_true_pfm: 2525.888231265071 sim_pfm: 374.7723536798342
episode: 384 training return: tensor(378.6554, device='cuda:0')
episode: 385 training return: tensor(440.5142, device='cuda:0')
episode: 386 training return: tensor(344.9434, device='cuda:0')
episode: 387 training return: tensor(326.4663, device='cuda:0')
epoch: 97 test_true_pfm: 3517.6045877467463 sim_pfm: 417.43815799818066
episode: 388 training return: tensor(394.0095, device='cuda:0')
episode: 389 training return: tensor(480.2744, device='cuda:0')
episode: 390 training return: tensor(94.2785, device='cuda:0')
episode: 391 training return: tensor(422.4191, device='cuda:0')
epoch: 98 test_true_pfm: 3431.4516854413428 sim_pfm: 208.57169165613595
episode: 392 training return: tensor(-172.7030, device='cuda:0')
episode: 393 training return: tensor(449.9727, device='cuda:0')
episode: 394 training return: tensor(418.3336, device='cuda:0')
episode: 395 training return: tensor(376.6527, device='cuda:0')
epoch: 99 test_true_pfm: 3501.1071407095774 sim_pfm: 356.16419259577134
episode: 396 training return: tensor(407.9702, device='cuda:0')
episode: 397 training return: tensor(348.2926, device='cuda:0')
episode: 398 training return: tensor(347.5987, device='cuda:0')
episode: 399 training return: tensor(365.3872, device='cuda:0')
epoch: 100 test_true_pfm: 3426.869221347953 sim_pfm: 163.63109068589014
episode: 400 training return: tensor(430.3862, device='cuda:0')
episode: 401 training return: tensor(390.3243, device='cuda:0')
episode: 402 training return: tensor(415.5778, device='cuda:0')
episode: 403 training return: tensor(305.4487, device='cuda:0')
epoch: 101 test_true_pfm: 3425.0993327184565 sim_pfm: 300.6426784132491
episode: 404 training return: tensor(330.4185, device='cuda:0')
episode: 405 training return: tensor(328.7873, device='cuda:0')
episode: 406 training return: tensor(374.2182, device='cuda:0')
episode: 407 training return: tensor(342.0526, device='cuda:0')
epoch: 102 test_true_pfm: 3383.5035636238085 sim_pfm: 326.600802634086
episode: 408 training return: tensor(146.9995, device='cuda:0')
episode: 409 training return: tensor(333.6872, device='cuda:0')
episode: 410 training return: tensor(311.3661, device='cuda:0')
episode: 411 training return: tensor(337.3225, device='cuda:0')
epoch: 103 test_true_pfm: 2787.1798944986294 sim_pfm: 376.43688198008266
episode: 412 training return: tensor(412.7600, device='cuda:0')
episode: 413 training return: tensor(416.1329, device='cuda:0')
episode: 414 training return: tensor(345.7578, device='cuda:0')
episode: 415 training return: tensor(375.9951, device='cuda:0')
epoch: 104 test_true_pfm: 3354.0509893619546 sim_pfm: 330.0455832436758
episode: 416 training return: tensor(333.5146, device='cuda:0')
episode: 417 training return: tensor(354.2742, device='cuda:0')
episode: 418 training return: tensor(340.3630, device='cuda:0')
episode: 419 training return: tensor(440.5722, device='cuda:0')
epoch: 105 test_true_pfm: 3453.825195941486 sim_pfm: 225.07044101095138
episode: 420 training return: tensor(364.3471, device='cuda:0')
episode: 421 training return: tensor(368.0348, device='cuda:0')
episode: 422 training return: tensor(417.8445, device='cuda:0')
episode: 423 training return: tensor(330.9243, device='cuda:0')
epoch: 106 test_true_pfm: 3430.227609187425 sim_pfm: 379.4097449971402
episode: 424 training return: tensor(280.7628, device='cuda:0')
episode: 425 training return: tensor(336.6527, device='cuda:0')
episode: 426 training return: tensor(359.6165, device='cuda:0')
episode: 427 training return: tensor(-428.9749, device='cuda:0')
epoch: 107 test_true_pfm: 2953.4087509238598 sim_pfm: 413.6572486826335
episode: 428 training return: tensor(406.1680, device='cuda:0')
episode: 429 training return: tensor(321.8201, device='cuda:0')
episode: 430 training return: tensor(386.4955, device='cuda:0')
episode: 431 training return: tensor(403.5827, device='cuda:0')
epoch: 108 test_true_pfm: 3479.367802990104 sim_pfm: 405.0366967752537
episode: 432 training return: tensor(379.2113, device='cuda:0')
episode: 433 training return: tensor(350.1870, device='cuda:0')
episode: 434 training return: tensor(356.6516, device='cuda:0')
episode: 435 training return: tensor(374.0548, device='cuda:0')
epoch: 109 test_true_pfm: 3403.4968832389677 sim_pfm: 355.83529639483703
episode: 436 training return: tensor(342.9431, device='cuda:0')
episode: 437 training return: tensor(411.6809, device='cuda:0')
episode: 438 training return: tensor(308.1042, device='cuda:0')
episode: 439 training return: tensor(313.1594, device='cuda:0')
epoch: 110 test_true_pfm: 3384.1110127199154 sim_pfm: 322.35961341285537
episode: 440 training return: tensor(290.9825, device='cuda:0')
episode: 441 training return: tensor(355.3291, device='cuda:0')
episode: 442 training return: tensor(336.1694, device='cuda:0')
episode: 443 training return: tensor(-241.6813, device='cuda:0')
epoch: 111 test_true_pfm: 3355.5109834604154 sim_pfm: 357.9919234242213
episode: 444 training return: tensor(449.2777, device='cuda:0')
episode: 445 training return: tensor(358.9533, device='cuda:0')
episode: 446 training return: tensor(290.8856, device='cuda:0')
episode: 447 training return: tensor(402.4674, device='cuda:0')
epoch: 112 test_true_pfm: 3384.8938203790603 sim_pfm: 352.65364490341744
episode: 448 training return: tensor(403.6987, device='cuda:0')
episode: 449 training return: tensor(309.7527, device='cuda:0')
episode: 450 training return: tensor(335.3177, device='cuda:0')
episode: 451 training return: tensor(396.3191, device='cuda:0')
epoch: 113 test_true_pfm: 3405.4268397617266 sim_pfm: 353.1643065537889
episode: 452 training return: tensor(428.0006, device='cuda:0')
episode: 453 training return: tensor(334.7834, device='cuda:0')
episode: 454 training return: tensor(348.6139, device='cuda:0')
episode: 455 training return: tensor(336.6687, device='cuda:0')
epoch: 114 test_true_pfm: 3411.8355320598153 sim_pfm: 362.5583535285744
episode: 456 training return: tensor(-133.2182, device='cuda:0')
episode: 457 training return: tensor(307.1673, device='cuda:0')
episode: 458 training return: tensor(394.6402, device='cuda:0')
episode: 459 training return: tensor(389.6273, device='cuda:0')
epoch: 115 test_true_pfm: 3458.570902495135 sim_pfm: 399.3318374355634
episode: 460 training return: tensor(304.2389, device='cuda:0')
episode: 461 training return: tensor(340.5532, device='cuda:0')
episode: 462 training return: tensor(369.5292, device='cuda:0')
episode: 463 training return: tensor(454.5864, device='cuda:0')
epoch: 116 test_true_pfm: 3435.1863319709087 sim_pfm: 356.94565560951986
episode: 464 training return: tensor(419.7391, device='cuda:0')
episode: 465 training return: tensor(400.2900, device='cuda:0')
episode: 466 training return: tensor(328.9526, device='cuda:0')
episode: 467 training return: tensor(349.8184, device='cuda:0')
epoch: 117 test_true_pfm: 3423.1845875876156 sim_pfm: 386.46471948906157
episode: 468 training return: tensor(322.9728, device='cuda:0')
episode: 469 training return: tensor(376.1029, device='cuda:0')
episode: 470 training return: tensor(358.5693, device='cuda:0')
episode: 471 training return: tensor(347.0280, device='cuda:0')
epoch: 118 test_true_pfm: 3467.683774721414 sim_pfm: 368.0892418505391
episode: 472 training return: tensor(351.4811, device='cuda:0')
episode: 473 training return: tensor(335.6376, device='cuda:0')
episode: 474 training return: tensor(336.6711, device='cuda:0')
episode: 475 training return: tensor(363.1895, device='cuda:0')
epoch: 119 test_true_pfm: 3419.683830979882 sim_pfm: 378.13906345224433
episode: 476 training return: tensor(370.6792, device='cuda:0')
episode: 477 training return: tensor(365.4076, device='cuda:0')
episode: 478 training return: tensor(407.6467, device='cuda:0')
episode: 479 training return: tensor(392.1493, device='cuda:0')
epoch: 120 test_true_pfm: 3114.1977670696956 sim_pfm: 282.8151934002138
episode: 480 training return: tensor(329.8286, device='cuda:0')
episode: 481 training return: tensor(241.1236, device='cuda:0')
episode: 482 training return: tensor(359.6018, device='cuda:0')
episode: 483 training return: tensor(363.0394, device='cuda:0')
epoch: 121 test_true_pfm: 3379.7102671832386 sim_pfm: 382.51747802998096
episode: 484 training return: tensor(63.3026, device='cuda:0')
episode: 485 training return: tensor(374.5499, device='cuda:0')
episode: 486 training return: tensor(299.7018, device='cuda:0')
episode: 487 training return: tensor(406.7534, device='cuda:0')
epoch: 122 test_true_pfm: 3459.7594757684833 sim_pfm: 402.69881661244045
episode: 488 training return: tensor(350.5239, device='cuda:0')
episode: 489 training return: tensor(351.9328, device='cuda:0')
episode: 490 training return: tensor(403.2716, device='cuda:0')
episode: 491 training return: tensor(297.2396, device='cuda:0')
epoch: 123 test_true_pfm: 3152.36893792314 sim_pfm: 358.17637593028485
episode: 492 training return: tensor(379.1001, device='cuda:0')
episode: 493 training return: tensor(387.7810, device='cuda:0')
episode: 494 training return: tensor(350.1350, device='cuda:0')
episode: 495 training return: tensor(360.2319, device='cuda:0')
epoch: 124 test_true_pfm: 3498.473486311896 sim_pfm: 382.8829311754865
episode: 496 training return: tensor(345.3102, device='cuda:0')
episode: 497 training return: tensor(350.5569, device='cuda:0')
episode: 498 training return: tensor(361.9668, device='cuda:0')
episode: 499 training return: tensor(429.8945, device='cuda:0')
epoch: 125 test_true_pfm: 3342.299001494559 sim_pfm: 328.6750626783469
episode: 500 training return: tensor(371.5478, device='cuda:0')
episode: 501 training return: tensor(376.3480, device='cuda:0')
episode: 502 training return: tensor(356.4273, device='cuda:0')
episode: 503 training return: tensor(382.5773, device='cuda:0')
epoch: 126 test_true_pfm: 3481.9859545648164 sim_pfm: 169.1245391437939
episode: 504 training return: tensor(395.4259, device='cuda:0')
episode: 505 training return: tensor(311.3551, device='cuda:0')
episode: 506 training return: tensor(363.6894, device='cuda:0')
episode: 507 training return: tensor(363.2697, device='cuda:0')
epoch: 127 test_true_pfm: 3459.6159350171943 sim_pfm: 394.3289469819477
episode: 508 training return: tensor(370.5412, device='cuda:0')
episode: 509 training return: tensor(429.7122, device='cuda:0')
episode: 510 training return: tensor(387.0232, device='cuda:0')
episode: 511 training return: tensor(313.3147, device='cuda:0')
epoch: 128 test_true_pfm: 3360.672142939371 sim_pfm: 362.1248599943938
episode: 512 training return: tensor(366.4150, device='cuda:0')
episode: 513 training return: tensor(361.4124, device='cuda:0')
episode: 514 training return: tensor(379.0426, device='cuda:0')
episode: 515 training return: tensor(385.1437, device='cuda:0')
epoch: 129 test_true_pfm: 3408.6311833781024 sim_pfm: 384.87026900363463
episode: 516 training return: tensor(275.2542, device='cuda:0')
episode: 517 training return: tensor(-49.5285, device='cuda:0')
episode: 518 training return: tensor(328.4706, device='cuda:0')
episode: 519 training return: tensor(269.2255, device='cuda:0')
epoch: 130 test_true_pfm: 3430.838146161257 sim_pfm: 383.98502617426374
episode: 520 training return: tensor(77.0349, device='cuda:0')
episode: 521 training return: tensor(398.5775, device='cuda:0')
episode: 522 training return: tensor(343.4159, device='cuda:0')
episode: 523 training return: tensor(346.2003, device='cuda:0')
epoch: 131 test_true_pfm: 3379.248215390917 sim_pfm: 331.0012654624491
episode: 524 training return: tensor(387.6160, device='cuda:0')
episode: 525 training return: tensor(327.4377, device='cuda:0')
episode: 526 training return: tensor(351.0819, device='cuda:0')
episode: 527 training return: tensor(385.7176, device='cuda:0')
epoch: 132 test_true_pfm: 3469.728759488511 sim_pfm: 383.84401069168234
episode: 528 training return: tensor(370.4760, device='cuda:0')
episode: 529 training return: tensor(407.0840, device='cuda:0')
episode: 530 training return: tensor(336.5731, device='cuda:0')
episode: 531 training return: tensor(288.5883, device='cuda:0')
epoch: 133 test_true_pfm: 3399.5547305172204 sim_pfm: 312.56622731407214
episode: 532 training return: tensor(325.3772, device='cuda:0')
episode: 533 training return: tensor(367.6739, device='cuda:0')
episode: 534 training return: tensor(341.2875, device='cuda:0')
episode: 535 training return: tensor(430.0704, device='cuda:0')
epoch: 134 test_true_pfm: 3462.6809461773373 sim_pfm: 386.69045811804244
episode: 536 training return: tensor(398.4704, device='cuda:0')
episode: 537 training return: tensor(362.7445, device='cuda:0')
episode: 538 training return: tensor(362.3839, device='cuda:0')
episode: 539 training return: tensor(346.6736, device='cuda:0')
epoch: 135 test_true_pfm: 3503.520950332517 sim_pfm: 365.91647594451206
episode: 540 training return: tensor(383.0057, device='cuda:0')
episode: 541 training return: tensor(424.7393, device='cuda:0')
episode: 542 training return: tensor(357.7517, device='cuda:0')
episode: 543 training return: tensor(357.3452, device='cuda:0')
epoch: 136 test_true_pfm: 3437.3155210608925 sim_pfm: 302.6097433148922
episode: 544 training return: tensor(396.7177, device='cuda:0')
episode: 545 training return: tensor(290.9750, device='cuda:0')
episode: 546 training return: tensor(335.1469, device='cuda:0')
episode: 547 training return: tensor(360.5999, device='cuda:0')
epoch: 137 test_true_pfm: 3452.175729023164 sim_pfm: 370.2236432766852
episode: 548 training return: tensor(386.3709, device='cuda:0')
episode: 549 training return: tensor(350.6076, device='cuda:0')
episode: 550 training return: tensor(383.8217, device='cuda:0')
episode: 551 training return: tensor(362.0179, device='cuda:0')
epoch: 138 test_true_pfm: 3514.7882339030834 sim_pfm: 403.32919339603785
episode: 552 training return: tensor(328.2094, device='cuda:0')
episode: 553 training return: tensor(412.8891, device='cuda:0')
episode: 554 training return: tensor(386.2587, device='cuda:0')
episode: 555 training return: tensor(260.0284, device='cuda:0')
epoch: 139 test_true_pfm: 3460.128713648655 sim_pfm: 388.0032949713059
episode: 556 training return: tensor(416.5210, device='cuda:0')
episode: 557 training return: tensor(404.0784, device='cuda:0')
episode: 558 training return: tensor(388.6821, device='cuda:0')
episode: 559 training return: tensor(299.1500, device='cuda:0')
epoch: 140 test_true_pfm: 3431.3314929072094 sim_pfm: 270.65510447260266
episode: 560 training return: tensor(367.6072, device='cuda:0')
episode: 561 training return: tensor(376.8394, device='cuda:0')
episode: 562 training return: tensor(367.6538, device='cuda:0')
episode: 563 training return: tensor(376.5385, device='cuda:0')
epoch: 141 test_true_pfm: 2868.3807827416026 sim_pfm: 366.1394078570108
episode: 564 training return: tensor(355.6819, device='cuda:0')
episode: 565 training return: tensor(391.4904, device='cuda:0')
episode: 566 training return: tensor(368.4008, device='cuda:0')
episode: 567 training return: tensor(389.2260, device='cuda:0')
epoch: 142 test_true_pfm: 3481.831762861915 sim_pfm: 360.499188443219
episode: 568 training return: tensor(322.8734, device='cuda:0')
episode: 569 training return: tensor(391.1082, device='cuda:0')
episode: 570 training return: tensor(367.7080, device='cuda:0')
episode: 571 training return: tensor(453.2281, device='cuda:0')
epoch: 143 test_true_pfm: 3475.4138424703847 sim_pfm: 383.8000852883367
episode: 572 training return: tensor(388.1534, device='cuda:0')
episode: 573 training return: tensor(302.7680, device='cuda:0')
episode: 574 training return: tensor(462.7319, device='cuda:0')
episode: 575 training return: tensor(367.7979, device='cuda:0')
epoch: 144 test_true_pfm: 3402.8505464319 sim_pfm: 349.442100383807
episode: 576 training return: tensor(433.4928, device='cuda:0')
episode: 577 training return: tensor(359.5510, device='cuda:0')
episode: 578 training return: tensor(368.7448, device='cuda:0')
episode: 579 training return: tensor(-123.6008, device='cuda:0')
epoch: 145 test_true_pfm: 3411.2306047717752 sim_pfm: 346.9816270748658
episode: 580 training return: tensor(336.8365, device='cuda:0')
episode: 581 training return: tensor(355.3992, device='cuda:0')
episode: 582 training return: tensor(298.6524, device='cuda:0')
episode: 583 training return: tensor(366.6007, device='cuda:0')
epoch: 146 test_true_pfm: 2998.8063828167033 sim_pfm: 399.1206698786021
episode: 584 training return: tensor(421.6535, device='cuda:0')
episode: 585 training return: tensor(333.4922, device='cuda:0')
episode: 586 training return: tensor(464.3689, device='cuda:0')
episode: 587 training return: tensor(373.1682, device='cuda:0')
epoch: 147 test_true_pfm: 3425.2107958181896 sim_pfm: 344.1954625742898
episode: 588 training return: tensor(382.5469, device='cuda:0')
episode: 589 training return: tensor(387.0665, device='cuda:0')
episode: 590 training return: tensor(352.7743, device='cuda:0')
episode: 591 training return: tensor(344.2039, device='cuda:0')
epoch: 148 test_true_pfm: 3402.175570909181 sim_pfm: 300.21775160643546
episode: 592 training return: tensor(398.2617, device='cuda:0')
episode: 593 training return: tensor(397.8219, device='cuda:0')
episode: 594 training return: tensor(355.9338, device='cuda:0')
episode: 595 training return: tensor(433.8041, device='cuda:0')
epoch: 149 test_true_pfm: 3439.43071778464 sim_pfm: 351.4003468182248
episode: 596 training return: tensor(398.1322, device='cuda:0')
episode: 597 training return: tensor(154.0824, device='cuda:0')
episode: 598 training return: tensor(331.5194, device='cuda:0')
episode: 599 training return: tensor(402.2125, device='cuda:0')
epoch: 150 test_true_pfm: 3504.2338667878726 sim_pfm: 422.20175937354605
