['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '1', '--data', '10000', '--sub']
epoch: 0 training_loss 0.27016684629023074 test_loss: 0.17595281600952148
epoch: 1 training_loss 0.16149956494569778 test_loss: 0.14236843585968018
epoch: 2 training_loss 0.15048717357218266 test_loss: 0.1347074866294861
epoch: 3 training_loss 0.1291399747505784 test_loss: 0.12046536207199096
epoch: 4 training_loss 0.1207475976459682 test_loss: 0.12262138128280639
epoch: 5 training_loss 0.10821969654411077 test_loss: 0.11528526544570923
epoch: 6 training_loss 0.1131627904623747 test_loss: 0.13583492040634154
epoch: 7 training_loss 0.11095787573605775 test_loss: 0.1176142692565918
epoch: 8 training_loss 0.10768811903893948 test_loss: 0.11967630386352539
epoch: 9 training_loss 0.10665526039898396 test_loss: 0.12088209390640259
epoch: 10 training_loss 0.10492426674813032 test_loss: 0.13487160205841064
epoch: 11 training_loss 0.10350201223045588 test_loss: 0.10680745840072632
epoch: 12 training_loss 0.10511673891916871 test_loss: 0.11427271366119385
epoch: 13 training_loss 0.11037841886281967 test_loss: 0.10925947427749634
epoch: 14 training_loss 0.10839433152228593 test_loss: 0.13655273914337157
epoch: 15 training_loss 0.1052751225233078 test_loss: 0.11610960960388184
epoch: 16 training_loss 0.10293653538450599 test_loss: 0.10988922119140625
epoch: 17 training_loss 0.10224310277029872 test_loss: 0.11813104152679443
epoch: 18 training_loss 0.09553499564528466 test_loss: 0.10869376659393311
epoch: 19 training_loss 0.09781315058469772 test_loss: 0.11380585432052612
epoch: 20 training_loss 0.09467285860329866 test_loss: 0.11289637088775635
epoch: 21 training_loss 0.10219756152480841 test_loss: 0.12353496551513672
epoch: 22 training_loss 0.09921212010085582 test_loss: 0.11107256412506103
epoch: 23 training_loss 0.09137662699446082 test_loss: 0.1160429835319519
epoch: 24 training_loss 0.09864330226555466 test_loss: 0.11375217437744141
epoch: 25 training_loss 0.0935409159772098 test_loss: 0.1075243592262268
epoch: 26 training_loss 0.09257750872522592 test_loss: 0.11089001893997193
epoch: 27 training_loss 0.0884648529626429 test_loss: 0.1179760217666626
epoch: 28 training_loss 0.09555565597489477 test_loss: 0.1058110237121582
epoch: 29 training_loss 0.09346518578007817 test_loss: 0.12829514741897582
epoch: 30 training_loss 0.09692291244864464 test_loss: 0.10607908964157105
epoch: 31 training_loss 0.09268414046615363 test_loss: 0.10279974937438965
epoch: 32 training_loss 0.09494844377040863 test_loss: 0.1088759422302246
epoch: 33 training_loss 0.09192523952573538 test_loss: 0.11798588037490845
epoch: 34 training_loss 0.08893882852047681 test_loss: 0.11408827304840088
epoch: 35 training_loss 0.0860426964983344 test_loss: 0.11420880556106568
epoch: 36 training_loss 0.09129868699237705 test_loss: 0.10575546026229858
epoch: 37 training_loss 0.09432394534349442 test_loss: 0.10479044914245605
epoch: 38 training_loss 0.0910954281874001 test_loss: 0.10955325365066529
epoch: 39 training_loss 0.09341910917311907 test_loss: 0.1111221194267273
epoch: 40 training_loss 0.08627928363159298 test_loss: 0.1095200777053833
epoch: 41 training_loss 0.0847750754468143 test_loss: 0.1064577579498291
epoch: 42 training_loss 0.08817816695198416 test_loss: 0.11726537942886353
epoch: 43 training_loss 0.08799747485667467 test_loss: 0.11277869939804078
epoch: 44 training_loss 0.09532717792317272 test_loss: 0.10688753128051758
epoch: 45 training_loss 0.08178927041590214 test_loss: 0.11889094114303589
epoch: 46 training_loss 0.08241544548422099 test_loss: 0.11644632816314697
epoch: 47 training_loss 0.08604588216170668 test_loss: 0.10810247659683228
epoch: 48 training_loss 0.08563781147822738 test_loss: 0.10825999975204467
epoch: 49 training_loss 0.09347104156389832 test_loss: 0.11485702991485595
epoch: 50 training_loss 0.08069899383932352 test_loss: 0.11626361608505249
epoch: 51 training_loss 0.08785710761323572 test_loss: 0.12808144092559814
epoch: 52 training_loss 0.08502187479287386 test_loss: 0.11701102256774902
epoch: 53 training_loss 0.08608448943123222 test_loss: 0.10378035306930541
epoch: 54 training_loss 0.0898880124464631 test_loss: 0.1281440019607544
epoch: 55 training_loss 0.0814273271895945 test_loss: 0.10148319005966186
epoch: 56 training_loss 0.08575878448784352 test_loss: 0.10638183355331421
epoch: 57 training_loss 0.08557269604876637 test_loss: 0.11114866733551025
epoch: 58 training_loss 0.08221653770655393 test_loss: 0.11426517963409424
epoch: 59 training_loss 0.08732219822704793 test_loss: 0.12157738208770752
epoch: 60 training_loss 0.08176825035363436 test_loss: 0.10823268890380859
epoch: 61 training_loss 0.08343504818156361 test_loss: 0.10199939012527466
epoch: 62 training_loss 0.08582392251119017 test_loss: 0.11953701972961425
epoch: 63 training_loss 0.08164622394368053 test_loss: 0.11677675247192383
epoch: 64 training_loss 0.08877684436738491 test_loss: 0.1169653058052063
epoch: 65 training_loss 0.08596858331933617 test_loss: 0.10952980518341064
epoch: 66 training_loss 0.0853653361927718 test_loss: 0.11596344709396363
epoch: 67 training_loss 0.07747448075562716 test_loss: 0.12081465721130372
epoch: 68 training_loss 0.08172977557405829 test_loss: 0.124954092502594
epoch: 69 training_loss 0.07741538139060139 test_loss: 0.1193811535835266
epoch: 70 training_loss 0.08180834498256445 test_loss: 0.12314826250076294
epoch: 71 training_loss 0.07352515406906605 test_loss: 0.12478359937667846
epoch: 72 training_loss 0.07202770361676812 test_loss: 0.12039830684661865
epoch: 73 training_loss 0.079105245154351 test_loss: 0.13409067392349244
epoch: 74 training_loss 0.0799490986391902 test_loss: 0.11873406171798706
epoch: 75 training_loss 0.07505839900113642 test_loss: 0.11408132314682007
epoch: 76 training_loss 0.07914881637319922 test_loss: 0.1320255994796753
epoch: 77 training_loss 0.07567314029671252 test_loss: 0.12166354656219483
epoch: 78 training_loss 0.07322858026251197 test_loss: 0.10944743156433105
epoch: 79 training_loss 0.07342039795592427 test_loss: 0.1388758659362793
epoch: 80 training_loss 0.07782972628250719 test_loss: 0.10553773641586303
epoch: 81 training_loss 0.07435135893523694 test_loss: 0.11634808778762817
epoch: 82 training_loss 0.07831646801903844 test_loss: 0.10935776233673096
epoch: 83 training_loss 0.07705140138044954 test_loss: 0.12435636520385743
epoch: 84 training_loss 0.07800506120547653 test_loss: 0.11818753480911255
epoch: 85 training_loss 0.07336644504219293 test_loss: 0.11109020709991455
epoch: 86 training_loss 0.0797961058281362 test_loss: 0.11736174821853637
epoch: 87 training_loss 0.08208238470368087 test_loss: 0.13962754011154174
epoch: 88 training_loss 0.07715224051848053 test_loss: 0.137909460067749
epoch: 89 training_loss 0.07615743435919285 test_loss: 0.1298137664794922
epoch: 90 training_loss 0.07910768207162619 test_loss: 0.11129533052444458
epoch: 91 training_loss 0.07585534311830998 test_loss: 0.1386344313621521
epoch: 92 training_loss 0.07824957222677767 test_loss: 0.12473727464675903
epoch: 93 training_loss 0.076598403993994 test_loss: 0.13242160081863402
epoch: 94 training_loss 0.06958081790246069 test_loss: 0.12024253606796265
epoch: 95 training_loss 0.07199048598296941 test_loss: 0.12778854370117188
epoch: 96 training_loss 0.08033797264099121 test_loss: 0.12813628911972047
epoch: 97 training_loss 0.07640929950401187 test_loss: 0.11587141752243042
epoch: 98 training_loss 0.07877347914502025 test_loss: 0.12062938213348388
epoch: 99 training_loss 0.07634913455694914 test_loss: 0.1522324800491333
epoch: 100 training_loss 0.07247662933543325 test_loss: 0.14355331659317017
epoch: 101 training_loss 0.07481855006888509 test_loss: 0.12448941469192505
epoch: 102 training_loss 0.06741255324333906 test_loss: 0.1354433059692383
epoch: 103 training_loss 0.07295131392776966 test_loss: 0.1327068567276001
epoch: 104 training_loss 0.07382227564230562 test_loss: 0.12470613718032837
epoch: 105 training_loss 0.07628368405625224 test_loss: 0.13956595659255983
epoch: 106 training_loss 0.07174127666279674 test_loss: 0.14676363468170167
epoch: 107 training_loss 0.07328310444485396 test_loss: 0.1426822066307068
epoch: 108 training_loss 0.06805034087970853 test_loss: 0.12457938194274902
epoch: 109 training_loss 0.07173243038356304 test_loss: 0.128614604473114
epoch: 110 training_loss 0.07201403772458434 test_loss: 0.12731965780258178
epoch: 111 training_loss 0.06861690480262041 test_loss: 0.12565815448760986
epoch: 112 training_loss 0.07046152958646416 test_loss: 0.14578529596328735
epoch: 113 training_loss 0.07215620446018875 test_loss: 0.13794457912445068
epoch: 114 training_loss 0.07595003195106984 test_loss: 0.1295819878578186
epoch: 115 training_loss 0.07561774543486535 test_loss: 0.128500497341156
epoch: 116 training_loss 0.0731099336501211 test_loss: 0.1503158450126648
epoch: 117 training_loss 0.07365136435255408 test_loss: 0.1360493779182434
epoch: 118 training_loss 0.06955357193946839 test_loss: 0.10952024459838867
epoch: 119 training_loss 0.06885107824578882 test_loss: 0.12964389324188233
epoch: 120 training_loss 0.07486932326108217 test_loss: 0.13311094045639038
epoch: 121 training_loss 0.06691693939268589 test_loss: 0.1314271092414856
epoch: 122 training_loss 0.07248678704723716 test_loss: 0.12314450740814209
epoch: 123 training_loss 0.06917983431369067 test_loss: 0.1216694474220276
epoch: 124 training_loss 0.06531736095435918 test_loss: 0.14456361532211304
epoch: 125 training_loss 0.06485283959656954 test_loss: 0.13651504516601562
epoch: 126 training_loss 0.0697597065102309 test_loss: 0.12522461414337158
epoch: 127 training_loss 0.06780578924342989 test_loss: 0.11762120723724365
epoch: 128 training_loss 0.0696920136269182 test_loss: 0.1395138382911682
epoch: 129 training_loss 0.0635074810590595 test_loss: 0.14916112422943115
epoch: 130 training_loss 0.06805791081860661 test_loss: 0.13672070503234862
epoch: 131 training_loss 0.06612447295337916 test_loss: 0.13245214223861695
epoch: 132 training_loss 0.06610026516951621 test_loss: 0.13980697393417357
epoch: 133 training_loss 0.0727993203792721 test_loss: 0.1401965856552124
epoch: 134 training_loss 0.06591881455853582 test_loss: 0.1356245160102844
epoch: 135 training_loss 0.06643450116738676 test_loss: 0.1413408875465393
epoch: 136 training_loss 0.06320446388795972 test_loss: 0.14896035194396973
epoch: 137 training_loss 0.06721880590543151 test_loss: 0.1517964243888855
epoch: 138 training_loss 0.06359168610535562 test_loss: 0.12763891220092774
epoch: 139 training_loss 0.07252214565873145 test_loss: 0.1364834189414978
epoch: 140 training_loss 0.06396963451057673 test_loss: 0.153922700881958
epoch: 141 training_loss 0.06523898852989078 test_loss: 0.1469330072402954
epoch: 142 training_loss 0.06727122735232115 test_loss: 0.1359914779663086
epoch: 143 training_loss 0.058651526095345616 test_loss: 0.14853261709213256
epoch: 144 training_loss 0.06281518124975265 test_loss: 0.15174174308776855
epoch: 145 training_loss 0.07339601125568151 test_loss: 0.1475313663482666
epoch: 146 training_loss 0.06830180322751403 test_loss: 0.1268505334854126
epoch: 147 training_loss 0.0664855614490807 test_loss: 0.14083237648010255
epoch: 148 training_loss 0.06585197293199599 test_loss: 0.13511463403701782
epoch: 149 training_loss 0.06709696158766747 test_loss: 0.1498034954071045
epoch: 0 training_loss 41.3811304473877 test_loss: 21.448391723632813
epoch: 1 training_loss 17.44464842796326 test_loss: 14.22924346923828
epoch: 2 training_loss 12.929105777740478 test_loss: 11.256828308105469
epoch: 3 training_loss 10.741720237731933 test_loss: 10.145621490478515
epoch: 4 training_loss 9.506770009994506 test_loss: 8.817768859863282
epoch: 5 training_loss 8.420443353652955 test_loss: 7.861946105957031
epoch: 6 training_loss 7.762438545227051 test_loss: 7.394542694091797
epoch: 7 training_loss 7.197790474891662 test_loss: 6.833929443359375
epoch: 8 training_loss 6.82326370716095 test_loss: 6.7453254699707035
epoch: 9 training_loss 6.42333860874176 test_loss: 6.319877243041992
epoch: 10 training_loss 6.116337141990662 test_loss: 5.963935852050781
epoch: 11 training_loss 5.898458256721496 test_loss: 5.637232971191406
epoch: 12 training_loss 5.699978437423706 test_loss: 5.618228149414063
epoch: 13 training_loss 5.371477551460266 test_loss: 5.290220642089844
epoch: 14 training_loss 5.194392485618591 test_loss: 5.036067962646484
epoch: 15 training_loss 4.994333446025848 test_loss: 5.0163921356201175
epoch: 16 training_loss 4.9065773296356205 test_loss: 4.793815612792969
epoch: 17 training_loss 4.727780606746673 test_loss: 4.642763137817383
epoch: 18 training_loss 4.685824956893921 test_loss: 4.587718200683594
epoch: 19 training_loss 4.50781103849411 test_loss: 4.571392440795899
epoch: 20 training_loss 4.41520192861557 test_loss: 4.467987060546875
epoch: 21 training_loss 4.328712117671967 test_loss: 4.145895767211914
epoch: 22 training_loss 4.180844867229462 test_loss: 4.203593826293945
epoch: 23 training_loss 4.122497885227204 test_loss: 4.087593841552734
epoch: 24 training_loss 4.07714011669159 test_loss: 4.061965560913086
epoch: 25 training_loss 4.005885024070739 test_loss: 3.9782142639160156
epoch: 26 training_loss 3.873166763782501 test_loss: 3.9433284759521485
epoch: 27 training_loss 3.8997472977638243 test_loss: 3.7369537353515625
epoch: 28 training_loss 3.8115791392326357 test_loss: 3.832860565185547
epoch: 29 training_loss 3.7696354818344116 test_loss: 3.6903507232666017
epoch: 30 training_loss 3.6604484486579896 test_loss: 3.6522499084472657
epoch: 31 training_loss 3.663422884941101 test_loss: 3.645438003540039
epoch: 32 training_loss 3.575900411605835 test_loss: 3.589292526245117
epoch: 33 training_loss 3.6256206226348877 test_loss: 3.6254669189453126
epoch: 34 training_loss 3.585297269821167 test_loss: 3.582577133178711
epoch: 35 training_loss 3.459600954055786 test_loss: 3.6542911529541016
epoch: 36 training_loss 3.489050726890564 test_loss: 3.4708744049072267
epoch: 37 training_loss 3.3595907950401305 test_loss: 3.531774139404297
epoch: 38 training_loss 3.397082030773163 test_loss: 3.383909225463867
epoch: 39 training_loss 3.3495738196372984 test_loss: 3.4228057861328125
epoch: 40 training_loss 3.3132326006889343 test_loss: 3.2734405517578127
epoch: 41 training_loss 3.3128478360176086 test_loss: 3.308856201171875
epoch: 42 training_loss 3.1443661570549013 test_loss: 3.2903228759765626
epoch: 43 training_loss 3.2023626232147215 test_loss: 3.118889808654785
epoch: 44 training_loss 3.2055471611022948 test_loss: 3.2363277435302735
epoch: 45 training_loss 3.188101439476013 test_loss: 3.0941905975341797
epoch: 46 training_loss 3.243830854892731 test_loss: 3.197269821166992
epoch: 47 training_loss 3.15275634765625 test_loss: 3.2150638580322264
epoch: 48 training_loss 3.0917409491539 test_loss: 3.215645599365234
epoch: 49 training_loss 3.068603842258453 test_loss: 3.2015625
epoch: 50 training_loss 3.0762914299964903 test_loss: 3.0750732421875
epoch: 51 training_loss 3.0649665236473083 test_loss: 3.1198297500610352
epoch: 52 training_loss 3.030774562358856 test_loss: 3.2033466339111327
epoch: 53 training_loss 2.985818610191345 test_loss: 3.0867984771728514
epoch: 54 training_loss 3.0126150608062745 test_loss: 2.9817474365234373
epoch: 55 training_loss 2.91457213640213 test_loss: 3.0319480895996094
epoch: 56 training_loss 3.0494696950912474 test_loss: 2.955971336364746
epoch: 57 training_loss 2.86189777135849 test_loss: 2.925969886779785
epoch: 58 training_loss 2.957077441215515 test_loss: 2.9450010299682616
epoch: 59 training_loss 2.8608486795425416 test_loss: 2.909700393676758
epoch: 60 training_loss 2.837638874053955 test_loss: 2.876420593261719
epoch: 61 training_loss 2.8120252180099485 test_loss: 2.959647369384766
epoch: 62 training_loss 2.8347572612762453 test_loss: 2.9860723495483397
epoch: 63 training_loss 2.738321831226349 test_loss: 2.9215532302856446
epoch: 64 training_loss 2.7805610847473146 test_loss: 2.958008575439453
epoch: 65 training_loss 2.7726363241672516 test_loss: 2.8774675369262694
epoch: 66 training_loss 2.7998892068862915 test_loss: 2.846136283874512
epoch: 67 training_loss 2.786610221862793 test_loss: 2.8135168075561525
epoch: 68 training_loss 2.6958212542533873 test_loss: 2.8272378921508787
epoch: 69 training_loss 2.7211445355415345 test_loss: 2.7376752853393556
epoch: 70 training_loss 2.7530115461349487 test_loss: 2.8018396377563475
epoch: 71 training_loss 2.6911429929733277 test_loss: 2.6461952209472654
epoch: 72 training_loss 2.721994979381561 test_loss: 2.794582748413086
epoch: 73 training_loss 2.6596046924591064 test_loss: 2.6288150787353515
epoch: 74 training_loss 2.706328237056732 test_loss: 2.7450504302978516
epoch: 75 training_loss 2.688655264377594 test_loss: 2.8656444549560547
epoch: 76 training_loss 2.680591642856598 test_loss: 2.777354431152344
epoch: 77 training_loss 2.66252774477005 test_loss: 2.8114458084106446
epoch: 78 training_loss 2.659597108364105 test_loss: 2.66937313079834
epoch: 79 training_loss 2.657054879665375 test_loss: 2.754093360900879
epoch: 80 training_loss 2.6284423637390137 test_loss: 2.651566505432129
epoch: 81 training_loss 2.627726182937622 test_loss: 2.6437471389770506
epoch: 82 training_loss 2.6531422924995423 test_loss: 2.587403678894043
epoch: 83 training_loss 2.5821641206741335 test_loss: 2.6095205307006837
epoch: 84 training_loss 2.575269273519516 test_loss: 2.6549684524536135
epoch: 85 training_loss 2.522799150943756 test_loss: 2.6417510986328123
epoch: 86 training_loss 2.553506271839142 test_loss: 2.678467559814453
epoch: 87 training_loss 2.5598690271377564 test_loss: 2.576318550109863
epoch: 88 training_loss 2.4795479774475098 test_loss: 2.5937238693237306
epoch: 89 training_loss 2.498732662200928 test_loss: 2.566935348510742
epoch: 90 training_loss 2.5758447551727297 test_loss: 2.600879669189453
epoch: 91 training_loss 2.572988247871399 test_loss: 2.560287857055664
epoch: 92 training_loss 2.5050079894065855 test_loss: 2.577579879760742
epoch: 93 training_loss 2.599711902141571 test_loss: 2.5094099044799805
epoch: 94 training_loss 2.537271122932434 test_loss: 2.5804224014282227
epoch: 95 training_loss 2.5129963898658754 test_loss: 2.5393293380737303
epoch: 96 training_loss 2.4898143362998963 test_loss: 2.5632667541503906
epoch: 97 training_loss 2.4753983402252198 test_loss: 2.5333681106567383
epoch: 98 training_loss 2.4879630005359648 test_loss: 2.54664306640625
epoch: 99 training_loss 2.4700732469558715 test_loss: 2.501799201965332
epoch: 100 training_loss 2.466763319969177 test_loss: 2.50402717590332
epoch: 101 training_loss 2.4925036334991457 test_loss: 2.534650421142578
epoch: 102 training_loss 2.4580414402484894 test_loss: 2.5213998794555663
epoch: 103 training_loss 2.4316373610496522 test_loss: 2.5486425399780273
epoch: 104 training_loss 2.3993321657180786 test_loss: 2.6016849517822265
epoch: 105 training_loss 2.3562528109550476 test_loss: 2.548919105529785
epoch: 106 training_loss 2.3921350550651552 test_loss: 2.5113277435302734
epoch: 107 training_loss 2.3917761182785036 test_loss: 2.4841997146606447
epoch: 108 training_loss 2.4033899223804474 test_loss: 2.463907814025879
epoch: 109 training_loss 2.367070207595825 test_loss: 2.5207691192626953
epoch: 110 training_loss 2.4434766137599944 test_loss: 2.5646268844604494
epoch: 111 training_loss 2.3991966712474824 test_loss: 2.5157018661499024
epoch: 112 training_loss 2.3816085982322694 test_loss: 2.521525764465332
epoch: 113 training_loss 2.3502645790576935 test_loss: 2.393115234375
epoch: 114 training_loss 2.3790060222148894 test_loss: 2.4657915115356444
epoch: 115 training_loss 2.3471943068504335 test_loss: 2.451331901550293
epoch: 116 training_loss 2.3995265102386476 test_loss: 2.5141510009765624
epoch: 117 training_loss 2.333836189508438 test_loss: 2.5281206130981446
epoch: 118 training_loss 2.3162439787387847 test_loss: 2.4107425689697264
epoch: 119 training_loss 2.369362111091614 test_loss: 2.4794391632080077
epoch: 120 training_loss 2.29871653676033 test_loss: 2.4536279678344726
epoch: 121 training_loss 2.318953130245209 test_loss: 2.4171417236328123
epoch: 122 training_loss 2.3418032240867617 test_loss: 2.415190315246582
epoch: 123 training_loss 2.316121884584427 test_loss: 2.405569076538086
epoch: 124 training_loss 2.336964979171753 test_loss: 2.406415557861328
epoch: 125 training_loss 2.2860970914363863 test_loss: 2.3912620544433594
epoch: 126 training_loss 2.277940870523453 test_loss: 2.3870962142944334
epoch: 127 training_loss 2.3103055572509765 test_loss: 2.4103660583496094
epoch: 128 training_loss 2.2762554693222046 test_loss: 2.457476806640625
epoch: 129 training_loss 2.294582077264786 test_loss: 2.362198257446289
epoch: 130 training_loss 2.2517779541015623 test_loss: 2.3507017135620116
epoch: 131 training_loss 2.2764369010925294 test_loss: 2.546110725402832
epoch: 132 training_loss 2.259755103588104 test_loss: 2.338919258117676
epoch: 133 training_loss 2.292593208551407 test_loss: 2.3245458602905273
epoch: 134 training_loss 2.328191283941269 test_loss: 2.3335037231445312
epoch: 135 training_loss 2.249076898097992 test_loss: 2.3232650756835938
epoch: 136 training_loss 2.3096196496486665 test_loss: 2.3294239044189453
epoch: 137 training_loss 2.216238522529602 test_loss: 2.3470975875854494
epoch: 138 training_loss 2.243590250015259 test_loss: 2.3915685653686523
epoch: 139 training_loss 2.2209819281101226 test_loss: 2.3821128845214843
epoch: 140 training_loss 2.2513760459423064 test_loss: 2.3575353622436523
epoch: 141 training_loss 2.2814784336090086 test_loss: 2.3537416458129883
epoch: 142 training_loss 2.2188261556625366 test_loss: 2.2984132766723633
epoch: 143 training_loss 2.2311194384098054 test_loss: 2.299365997314453
epoch: 144 training_loss 2.2863008046150206 test_loss: 2.352371025085449
epoch: 145 training_loss 2.2156963860988617 test_loss: 2.3263315200805663
epoch: 146 training_loss 2.256690422296524 test_loss: 2.3528314590454102
epoch: 147 training_loss 2.1389539206027983 test_loss: 2.3114498138427733
epoch: 148 training_loss 2.2253391015529633 test_loss: 2.386417198181152
epoch: 149 training_loss 2.182140840291977 test_loss: 2.300603485107422
2630.3322730731793
episode: 0 training return: tensor(177.1263, device='cuda:0')
episode: 1 training return: tensor(220.0550, device='cuda:0')
episode: 2 training return: tensor(246.0888, device='cuda:0')
episode: 3 training return: tensor(-71.1904, device='cuda:0')
epoch: 1 test_true_pfm: 2641.7634667112234 sim_pfm: 59.07450556072096
episode: 4 training return: tensor(-391.2522, device='cuda:0')
episode: 5 training return: tensor(-23.0054, device='cuda:0')
episode: 6 training return: tensor(-252.4126, device='cuda:0')
episode: 7 training return: tensor(-281.0261, device='cuda:0')
epoch: 2 test_true_pfm: 2923.589389829291 sim_pfm: 43.97305755997271
episode: 8 training return: tensor(-70.2667, device='cuda:0')
episode: 9 training return: tensor(236.9027, device='cuda:0')
episode: 10 training return: tensor(188.7816, device='cuda:0')
episode: 11 training return: tensor(89.3943, device='cuda:0')
epoch: 3 test_true_pfm: 2997.510018760439 sim_pfm: -41.14569484610305
episode: 12 training return: tensor(14.6009, device='cuda:0')
episode: 13 training return: tensor(17.6670, device='cuda:0')
episode: 14 training return: tensor(-272.3798, device='cuda:0')
episode: 15 training return: tensor(-263.3103, device='cuda:0')
epoch: 4 test_true_pfm: 3259.8641250576134 sim_pfm: 175.34474248632128
episode: 16 training return: tensor(302.7664, device='cuda:0')
episode: 17 training return: tensor(237.4819, device='cuda:0')
episode: 18 training return: tensor(238.0450, device='cuda:0')
episode: 19 training return: tensor(21.0337, device='cuda:0')
epoch: 5 test_true_pfm: 3391.992671282366 sim_pfm: 177.43034723760988
episode: 20 training return: tensor(277.3664, device='cuda:0')
episode: 21 training return: tensor(39.1574, device='cuda:0')
episode: 22 training return: tensor(203.3979, device='cuda:0')
episode: 23 training return: tensor(222.9393, device='cuda:0')
epoch: 6 test_true_pfm: 2594.440916295425 sim_pfm: 103.29148661283155
episode: 24 training return: tensor(193.7887, device='cuda:0')
episode: 25 training return: tensor(87.3653, device='cuda:0')
episode: 26 training return: tensor(-43.5970, device='cuda:0')
episode: 27 training return: tensor(-168.1274, device='cuda:0')
epoch: 7 test_true_pfm: 2708.202887122154 sim_pfm: 128.52056668759906
episode: 28 training return: tensor(-308.1347, device='cuda:0')
episode: 29 training return: tensor(160.6200, device='cuda:0')
episode: 30 training return: tensor(-237.1893, device='cuda:0')
episode: 31 training return: tensor(-251.6596, device='cuda:0')
epoch: 8 test_true_pfm: 2672.7962678809304 sim_pfm: 37.32630805525696
episode: 32 training return: tensor(269.4706, device='cuda:0')
episode: 33 training return: tensor(242.4468, device='cuda:0')
episode: 34 training return: tensor(285.4355, device='cuda:0')
episode: 35 training return: tensor(270.7861, device='cuda:0')
epoch: 9 test_true_pfm: 2815.554118503784 sim_pfm: 4.354556143439065
episode: 36 training return: tensor(267.2630, device='cuda:0')
episode: 37 training return: tensor(-89.2273, device='cuda:0')
episode: 38 training return: tensor(-69.2857, device='cuda:0')
episode: 39 training return: tensor(295.4083, device='cuda:0')
epoch: 10 test_true_pfm: 2536.267815645142 sim_pfm: -169.86780864669709
episode: 40 training return: tensor(185.3988, device='cuda:0')
episode: 41 training return: tensor(296.7545, device='cuda:0')
episode: 42 training return: tensor(262.9699, device='cuda:0')
episode: 43 training return: tensor(50.9532, device='cuda:0')
epoch: 11 test_true_pfm: 2708.522289703369 sim_pfm: 216.7439310355694
episode: 44 training return: tensor(-139.3527, device='cuda:0')
episode: 45 training return: tensor(173.6366, device='cuda:0')
episode: 46 training return: tensor(-153.2063, device='cuda:0')
episode: 47 training return: tensor(-236.3173, device='cuda:0')
epoch: 12 test_true_pfm: 3370.8280768376826 sim_pfm: 69.72362288240886
episode: 48 training return: tensor(279.6266, device='cuda:0')
episode: 49 training return: tensor(295.2264, device='cuda:0')
episode: 50 training return: tensor(269.1316, device='cuda:0')
episode: 51 training return: tensor(220.1497, device='cuda:0')
epoch: 13 test_true_pfm: 3153.041683664789 sim_pfm: -70.97323688241886
episode: 52 training return: tensor(-93.1168, device='cuda:0')
episode: 53 training return: tensor(222.4368, device='cuda:0')
episode: 54 training return: tensor(159.9076, device='cuda:0')
episode: 55 training return: tensor(295.4364, device='cuda:0')
epoch: 14 test_true_pfm: 3377.3690174914377 sim_pfm: 140.6527732849257
episode: 56 training return: tensor(333.5510, device='cuda:0')
episode: 57 training return: tensor(-305.0886, device='cuda:0')
episode: 58 training return: tensor(-4.5828, device='cuda:0')
episode: 59 training return: tensor(239.9623, device='cuda:0')
epoch: 15 test_true_pfm: 3103.068941177118 sim_pfm: 127.40828865485189
episode: 60 training return: tensor(250.7449, device='cuda:0')
episode: 61 training return: tensor(201.8585, device='cuda:0')
episode: 62 training return: tensor(-411.0880, device='cuda:0')
episode: 63 training return: tensor(221.6380, device='cuda:0')
epoch: 16 test_true_pfm: 3424.459974140303 sim_pfm: 274.44099764637457
episode: 64 training return: tensor(242.0151, device='cuda:0')
episode: 65 training return: tensor(206.8995, device='cuda:0')
episode: 66 training return: tensor(209.1234, device='cuda:0')
episode: 67 training return: tensor(143.6551, device='cuda:0')
epoch: 17 test_true_pfm: 3214.2186390655065 sim_pfm: -24.26345166833683
episode: 68 training return: tensor(210.7967, device='cuda:0')
episode: 69 training return: tensor(311.7545, device='cuda:0')
episode: 70 training return: tensor(218.1859, device='cuda:0')
episode: 71 training return: tensor(296.7711, device='cuda:0')
epoch: 18 test_true_pfm: 3103.052379588598 sim_pfm: 136.05528288876909
episode: 72 training return: tensor(256.9379, device='cuda:0')
episode: 73 training return: tensor(260.1029, device='cuda:0')
episode: 74 training return: tensor(57.8006, device='cuda:0')
episode: 75 training return: tensor(261.2223, device='cuda:0')
epoch: 19 test_true_pfm: 2660.737227204085 sim_pfm: 49.85814605748359
episode: 76 training return: tensor(257.9611, device='cuda:0')
episode: 77 training return: tensor(243.5599, device='cuda:0')
episode: 78 training return: tensor(262.1216, device='cuda:0')
episode: 79 training return: tensor(191.7343, device='cuda:0')
epoch: 20 test_true_pfm: 3374.0593166135095 sim_pfm: 58.255656846701946
episode: 80 training return: tensor(249.4217, device='cuda:0')
episode: 81 training return: tensor(237.9658, device='cuda:0')
episode: 82 training return: tensor(150.9646, device='cuda:0')
episode: 83 training return: tensor(256.9153, device='cuda:0')
epoch: 21 test_true_pfm: 3464.314647111811 sim_pfm: 213.86384925471307
episode: 84 training return: tensor(227.3238, device='cuda:0')
episode: 85 training return: tensor(159.3457, device='cuda:0')
episode: 86 training return: tensor(-185.5168, device='cuda:0')
episode: 87 training return: tensor(-122.7312, device='cuda:0')
epoch: 22 test_true_pfm: 2709.0782103443003 sim_pfm: 265.54874078250333
episode: 88 training return: tensor(297.9552, device='cuda:0')
episode: 89 training return: tensor(87.8242, device='cuda:0')
episode: 90 training return: tensor(264.7426, device='cuda:0')
episode: 91 training return: tensor(220.9827, device='cuda:0')
epoch: 23 test_true_pfm: 2479.8760834942677 sim_pfm: 197.44705901754787
episode: 92 training return: tensor(-68.2491, device='cuda:0')
episode: 93 training return: tensor(279.5236, device='cuda:0')
episode: 94 training return: tensor(-170.5798, device='cuda:0')
episode: 95 training return: tensor(-170.3814, device='cuda:0')
epoch: 24 test_true_pfm: 3293.759217970149 sim_pfm: 181.57110547062862
episode: 96 training return: tensor(282.1159, device='cuda:0')
episode: 97 training return: tensor(303.7970, device='cuda:0')
episode: 98 training return: tensor(373.0644, device='cuda:0')
episode: 99 training return: tensor(329.8814, device='cuda:0')
epoch: 25 test_true_pfm: 2974.551867049567 sim_pfm: 151.19082599477647
episode: 100 training return: tensor(268.6585, device='cuda:0')
episode: 101 training return: tensor(284.3096, device='cuda:0')
episode: 102 training return: tensor(249.4050, device='cuda:0')
episode: 103 training return: tensor(321.4259, device='cuda:0')
epoch: 26 test_true_pfm: 3216.2588661079903 sim_pfm: 227.57625153206754
episode: 104 training return: tensor(352.9264, device='cuda:0')
episode: 105 training return: tensor(155.8213, device='cuda:0')
episode: 106 training return: tensor(156.5657, device='cuda:0')
episode: 107 training return: tensor(247.1483, device='cuda:0')
epoch: 27 test_true_pfm: 3037.6062964148546 sim_pfm: 267.3816975338462
episode: 108 training return: tensor(27.9282, device='cuda:0')
episode: 109 training return: tensor(286.6360, device='cuda:0')
episode: 110 training return: tensor(196.9031, device='cuda:0')
episode: 111 training return: tensor(225.7177, device='cuda:0')
epoch: 28 test_true_pfm: 3429.777116514284 sim_pfm: 212.38006165297702
episode: 112 training return: tensor(256.1088, device='cuda:0')
episode: 113 training return: tensor(281.1596, device='cuda:0')
episode: 114 training return: tensor(139.2734, device='cuda:0')
episode: 115 training return: tensor(292.4642, device='cuda:0')
epoch: 29 test_true_pfm: 3363.1640135396665 sim_pfm: 157.51982848914727
episode: 116 training return: tensor(309.6371, device='cuda:0')
episode: 117 training return: tensor(231.9598, device='cuda:0')
episode: 118 training return: tensor(294.2902, device='cuda:0')
episode: 119 training return: tensor(200.1110, device='cuda:0')
epoch: 30 test_true_pfm: 3369.5178051587336 sim_pfm: 144.28333806194132
episode: 120 training return: tensor(308.4098, device='cuda:0')
episode: 121 training return: tensor(113.6773, device='cuda:0')
episode: 122 training return: tensor(205.1112, device='cuda:0')
episode: 123 training return: tensor(216.3132, device='cuda:0')
epoch: 31 test_true_pfm: 3421.707822271748 sim_pfm: 198.2521080575922
episode: 124 training return: tensor(176.0990, device='cuda:0')
episode: 125 training return: tensor(361.9326, device='cuda:0')
episode: 126 training return: tensor(61.2716, device='cuda:0')
episode: 127 training return: tensor(181.2045, device='cuda:0')
epoch: 32 test_true_pfm: 3417.1927679208784 sim_pfm: 310.1029702319259
episode: 128 training return: tensor(232.3469, device='cuda:0')
episode: 129 training return: tensor(285.3019, device='cuda:0')
episode: 130 training return: tensor(260.0687, device='cuda:0')
episode: 131 training return: tensor(309.7087, device='cuda:0')
epoch: 33 test_true_pfm: 3478.430136394289 sim_pfm: 262.7860596429673
episode: 132 training return: tensor(-173.4646, device='cuda:0')
episode: 133 training return: tensor(238.0248, device='cuda:0')
episode: 134 training return: tensor(215.0984, device='cuda:0')
episode: 135 training return: tensor(174.2903, device='cuda:0')
epoch: 34 test_true_pfm: 3420.5495664677323 sim_pfm: 276.13089769578073
episode: 136 training return: tensor(301.9550, device='cuda:0')
episode: 137 training return: tensor(276.4243, device='cuda:0')
episode: 138 training return: tensor(183.4507, device='cuda:0')
episode: 139 training return: tensor(81.5538, device='cuda:0')
epoch: 35 test_true_pfm: 3495.9968382804614 sim_pfm: 305.00119056697196
episode: 140 training return: tensor(306.8340, device='cuda:0')
episode: 141 training return: tensor(279.0897, device='cuda:0')
episode: 142 training return: tensor(322.9337, device='cuda:0')
episode: 143 training return: tensor(246.0270, device='cuda:0')
epoch: 36 test_true_pfm: 3410.234961643337 sim_pfm: 299.6313673519956
episode: 144 training return: tensor(-233.4236, device='cuda:0')
episode: 145 training return: tensor(302.7697, device='cuda:0')
episode: 146 training return: tensor(273.9719, device='cuda:0')
episode: 147 training return: tensor(205.9336, device='cuda:0')
epoch: 37 test_true_pfm: 3415.0577385811353 sim_pfm: 269.8375106538879
episode: 148 training return: tensor(258.1226, device='cuda:0')
episode: 149 training return: tensor(-224.6757, device='cuda:0')
episode: 150 training return: tensor(281.1648, device='cuda:0')
episode: 151 training return: tensor(204.4427, device='cuda:0')
epoch: 38 test_true_pfm: 3331.4246645568996 sim_pfm: 292.1279465009963
episode: 152 training return: tensor(242.0816, device='cuda:0')
episode: 153 training return: tensor(211.4639, device='cuda:0')
episode: 154 training return: tensor(168.8846, device='cuda:0')
episode: 155 training return: tensor(-62.7140, device='cuda:0')
epoch: 39 test_true_pfm: 3326.2498193698207 sim_pfm: 276.5593428716141
episode: 156 training return: tensor(299.5363, device='cuda:0')
episode: 157 training return: tensor(342.3876, device='cuda:0')
episode: 158 training return: tensor(287.2670, device='cuda:0')
episode: 159 training return: tensor(86.9967, device='cuda:0')
epoch: 40 test_true_pfm: 3409.701752071063 sim_pfm: 144.92137874519298
episode: 160 training return: tensor(309.8674, device='cuda:0')
episode: 161 training return: tensor(288.0948, device='cuda:0')
episode: 162 training return: tensor(232.3759, device='cuda:0')
episode: 163 training return: tensor(315.9337, device='cuda:0')
epoch: 41 test_true_pfm: 3345.749210197191 sim_pfm: 277.23517732074833
episode: 164 training return: tensor(204.5533, device='cuda:0')
episode: 165 training return: tensor(250.0968, device='cuda:0')
episode: 166 training return: tensor(186.7336, device='cuda:0')
episode: 167 training return: tensor(316.1288, device='cuda:0')
epoch: 42 test_true_pfm: 3426.3779272192346 sim_pfm: 201.38771111315387
episode: 168 training return: tensor(219.4936, device='cuda:0')
episode: 169 training return: tensor(269.3940, device='cuda:0')
episode: 170 training return: tensor(233.9203, device='cuda:0')
episode: 171 training return: tensor(375.5338, device='cuda:0')
epoch: 43 test_true_pfm: 3345.120170743894 sim_pfm: 127.69317984899196
episode: 172 training return: tensor(293.0035, device='cuda:0')
episode: 173 training return: tensor(304.6819, device='cuda:0')
episode: 174 training return: tensor(298.8180, device='cuda:0')
episode: 175 training return: tensor(295.4296, device='cuda:0')
epoch: 44 test_true_pfm: 3469.1771059836124 sim_pfm: 347.89454788186896
episode: 176 training return: tensor(194.1079, device='cuda:0')
episode: 177 training return: tensor(295.7887, device='cuda:0')
episode: 178 training return: tensor(254.7290, device='cuda:0')
episode: 179 training return: tensor(222.2862, device='cuda:0')
epoch: 45 test_true_pfm: 3442.9174245537492 sim_pfm: 153.63016865340373
episode: 180 training return: tensor(199.5032, device='cuda:0')
episode: 181 training return: tensor(-199.4691, device='cuda:0')
episode: 182 training return: tensor(284.4876, device='cuda:0')
episode: 183 training return: tensor(299.0669, device='cuda:0')
epoch: 46 test_true_pfm: 3366.488888660286 sim_pfm: 352.2097769250201
episode: 184 training return: tensor(234.5875, device='cuda:0')
episode: 185 training return: tensor(250.3038, device='cuda:0')
episode: 186 training return: tensor(178.6443, device='cuda:0')
episode: 187 training return: tensor(399.1897, device='cuda:0')
epoch: 47 test_true_pfm: 3458.072512148092 sim_pfm: 275.8846583927904
episode: 188 training return: tensor(268.8434, device='cuda:0')
episode: 189 training return: tensor(138.6914, device='cuda:0')
episode: 190 training return: tensor(-383.2983, device='cuda:0')
episode: 191 training return: tensor(292.2287, device='cuda:0')
epoch: 48 test_true_pfm: 3398.3697040301467 sim_pfm: 280.16221755885636
episode: 192 training return: tensor(-104.8128, device='cuda:0')
episode: 193 training return: tensor(313.6734, device='cuda:0')
episode: 194 training return: tensor(297.6058, device='cuda:0')
episode: 195 training return: tensor(116.2389, device='cuda:0')
epoch: 49 test_true_pfm: 3230.5866755696093 sim_pfm: 136.55237646749205
episode: 196 training return: tensor(252.5556, device='cuda:0')
episode: 197 training return: tensor(256.9584, device='cuda:0')
episode: 198 training return: tensor(278.4735, device='cuda:0')
episode: 199 training return: tensor(320.5574, device='cuda:0')
epoch: 50 test_true_pfm: 3457.382982818555 sim_pfm: 359.75530955654295
episode: 200 training return: tensor(346.4399, device='cuda:0')
episode: 201 training return: tensor(279.6939, device='cuda:0')
episode: 202 training return: tensor(333.4140, device='cuda:0')
episode: 203 training return: tensor(199.7144, device='cuda:0')
epoch: 51 test_true_pfm: 3366.315218044832 sim_pfm: 287.3369075023511
episode: 204 training return: tensor(286.9058, device='cuda:0')
episode: 205 training return: tensor(302.9560, device='cuda:0')
episode: 206 training return: tensor(-168.6170, device='cuda:0')
episode: 207 training return: tensor(156.5406, device='cuda:0')
epoch: 52 test_true_pfm: 3513.7102540787178 sim_pfm: 320.5459336501469
episode: 208 training return: tensor(165.3642, device='cuda:0')
episode: 209 training return: tensor(234.6942, device='cuda:0')
episode: 210 training return: tensor(140.3210, device='cuda:0')
episode: 211 training return: tensor(-254.5493, device='cuda:0')
epoch: 53 test_true_pfm: 3472.0057758267544 sim_pfm: 336.9199218384165
episode: 212 training return: tensor(218.8222, device='cuda:0')
episode: 213 training return: tensor(159.5633, device='cuda:0')
episode: 214 training return: tensor(141.6262, device='cuda:0')
episode: 215 training return: tensor(156.3258, device='cuda:0')
epoch: 54 test_true_pfm: 2847.037689028628 sim_pfm: 350.21280253808555
episode: 216 training return: tensor(332.0090, device='cuda:0')
episode: 217 training return: tensor(266.9808, device='cuda:0')
episode: 218 training return: tensor(337.4770, device='cuda:0')
episode: 219 training return: tensor(296.3727, device='cuda:0')
epoch: 55 test_true_pfm: 3551.394956675003 sim_pfm: 295.53220998396864
episode: 220 training return: tensor(208.6966, device='cuda:0')
episode: 221 training return: tensor(232.3636, device='cuda:0')
episode: 222 training return: tensor(289.4106, device='cuda:0')
episode: 223 training return: tensor(-75.8693, device='cuda:0')
epoch: 56 test_true_pfm: 3448.3592370100027 sim_pfm: 339.7806917040143
episode: 224 training return: tensor(-224.2489, device='cuda:0')
episode: 225 training return: tensor(225.1363, device='cuda:0')
episode: 226 training return: tensor(302.6053, device='cuda:0')
episode: 227 training return: tensor(302.3814, device='cuda:0')
epoch: 57 test_true_pfm: 2797.624814356332 sim_pfm: -156.4470405636142
episode: 228 training return: tensor(285.8701, device='cuda:0')
episode: 229 training return: tensor(287.3709, device='cuda:0')
episode: 230 training return: tensor(138.9587, device='cuda:0')
episode: 231 training return: tensor(-102.2578, device='cuda:0')
epoch: 58 test_true_pfm: 2394.678787669594 sim_pfm: 316.5741105564909
episode: 232 training return: tensor(-211.0279, device='cuda:0')
episode: 233 training return: tensor(206.6623, device='cuda:0')
episode: 234 training return: tensor(243.9034, device='cuda:0')
episode: 235 training return: tensor(234.9045, device='cuda:0')
epoch: 59 test_true_pfm: 3472.4895455721003 sim_pfm: 286.7253780037863
episode: 236 training return: tensor(266.9666, device='cuda:0')
episode: 237 training return: tensor(-105.6064, device='cuda:0')
episode: 238 training return: tensor(-38.4185, device='cuda:0')
episode: 239 training return: tensor(324.8022, device='cuda:0')
epoch: 60 test_true_pfm: 3377.7779432651864 sim_pfm: 289.94526100857183
episode: 240 training return: tensor(259.2956, device='cuda:0')
episode: 241 training return: tensor(-267.2253, device='cuda:0')
episode: 242 training return: tensor(192.9169, device='cuda:0')
episode: 243 training return: tensor(228.6762, device='cuda:0')
epoch: 61 test_true_pfm: 3505.335048614152 sim_pfm: 173.5620759454517
episode: 244 training return: tensor(325.2162, device='cuda:0')
episode: 245 training return: tensor(265.6596, device='cuda:0')
episode: 246 training return: tensor(260.7375, device='cuda:0')
episode: 247 training return: tensor(241.1192, device='cuda:0')
epoch: 62 test_true_pfm: 3539.1223060880734 sim_pfm: 344.2837256813752
episode: 248 training return: tensor(-50.6726, device='cuda:0')
episode: 249 training return: tensor(229.7454, device='cuda:0')
episode: 250 training return: tensor(241.1689, device='cuda:0')
episode: 251 training return: tensor(298.6305, device='cuda:0')
epoch: 63 test_true_pfm: 3358.6699744589205 sim_pfm: 299.7236360467311
episode: 252 training return: tensor(107.1922, device='cuda:0')
episode: 253 training return: tensor(325.5836, device='cuda:0')
episode: 254 training return: tensor(324.7518, device='cuda:0')
episode: 255 training return: tensor(291.9155, device='cuda:0')
epoch: 64 test_true_pfm: 3476.3361226188463 sim_pfm: 350.4259459063566
episode: 256 training return: tensor(-196.9589, device='cuda:0')
episode: 257 training return: tensor(301.1965, device='cuda:0')
episode: 258 training return: tensor(273.4970, device='cuda:0')
episode: 259 training return: tensor(297.0174, device='cuda:0')
epoch: 65 test_true_pfm: 3329.6334575286733 sim_pfm: 273.2598791019215
episode: 260 training return: tensor(-147.9551, device='cuda:0')
episode: 261 training return: tensor(-232.3530, device='cuda:0')
episode: 262 training return: tensor(279.7288, device='cuda:0')
episode: 263 training return: tensor(304.9413, device='cuda:0')
epoch: 66 test_true_pfm: 3454.0825312370885 sim_pfm: 341.04667470786563
episode: 264 training return: tensor(158.3543, device='cuda:0')
episode: 265 training return: tensor(-156.4652, device='cuda:0')
episode: 266 training return: tensor(277.8328, device='cuda:0')
episode: 267 training return: tensor(297.1715, device='cuda:0')
epoch: 67 test_true_pfm: 3432.5474252664885 sim_pfm: 334.2400342213805
episode: 268 training return: tensor(317.8395, device='cuda:0')
episode: 269 training return: tensor(311.0967, device='cuda:0')
episode: 270 training return: tensor(253.5013, device='cuda:0')
episode: 271 training return: tensor(285.4335, device='cuda:0')
epoch: 68 test_true_pfm: 3503.368245358622 sim_pfm: 360.2610483267733
episode: 272 training return: tensor(-140.3402, device='cuda:0')
episode: 273 training return: tensor(352.0660, device='cuda:0')
episode: 274 training return: tensor(342.2568, device='cuda:0')
episode: 275 training return: tensor(318.4290, device='cuda:0')
epoch: 69 test_true_pfm: 3432.470121829609 sim_pfm: 293.18481431845186
episode: 276 training return: tensor(343.4216, device='cuda:0')
episode: 277 training return: tensor(305.6599, device='cuda:0')
episode: 278 training return: tensor(264.5023, device='cuda:0')
episode: 279 training return: tensor(188.6589, device='cuda:0')
epoch: 70 test_true_pfm: 3456.6885820095026 sim_pfm: 363.3857269147314
episode: 280 training return: tensor(323.2339, device='cuda:0')
episode: 281 training return: tensor(360.4926, device='cuda:0')
episode: 282 training return: tensor(278.8059, device='cuda:0')
episode: 283 training return: tensor(303.7949, device='cuda:0')
epoch: 71 test_true_pfm: 3496.1955844466734 sim_pfm: 264.0101483610051
episode: 284 training return: tensor(281.1806, device='cuda:0')
episode: 285 training return: tensor(336.7472, device='cuda:0')
episode: 286 training return: tensor(286.4608, device='cuda:0')
episode: 287 training return: tensor(132.2587, device='cuda:0')
epoch: 72 test_true_pfm: 3461.14919887913 sim_pfm: 299.7670693429536
episode: 288 training return: tensor(-118.8359, device='cuda:0')
episode: 289 training return: tensor(292.4321, device='cuda:0')
episode: 290 training return: tensor(304.0600, device='cuda:0')
episode: 291 training return: tensor(333.9865, device='cuda:0')
epoch: 73 test_true_pfm: 3459.6650097511647 sim_pfm: 357.31081747009495
episode: 292 training return: tensor(277.3304, device='cuda:0')
episode: 293 training return: tensor(324.0330, device='cuda:0')
episode: 294 training return: tensor(302.2402, device='cuda:0')
episode: 295 training return: tensor(246.9118, device='cuda:0')
epoch: 74 test_true_pfm: 3140.0139015265963 sim_pfm: 300.27396066492656
episode: 296 training return: tensor(384.7220, device='cuda:0')
episode: 297 training return: tensor(276.1768, device='cuda:0')
episode: 298 training return: tensor(330.4542, device='cuda:0')
episode: 299 training return: tensor(157.9231, device='cuda:0')
epoch: 75 test_true_pfm: 3455.7331213154307 sim_pfm: 317.1233183753308
episode: 300 training return: tensor(257.7844, device='cuda:0')
episode: 301 training return: tensor(322.9940, device='cuda:0')
episode: 302 training return: tensor(284.8556, device='cuda:0')
episode: 303 training return: tensor(257.9073, device='cuda:0')
epoch: 76 test_true_pfm: 3504.629426530437 sim_pfm: 311.0181627510465
episode: 304 training return: tensor(288.6042, device='cuda:0')
episode: 305 training return: tensor(363.1620, device='cuda:0')
episode: 306 training return: tensor(350.3329, device='cuda:0')
episode: 307 training return: tensor(223.9211, device='cuda:0')
epoch: 77 test_true_pfm: 3510.760030061185 sim_pfm: 296.9099393149663
episode: 308 training return: tensor(-111.5909, device='cuda:0')
episode: 309 training return: tensor(226.6682, device='cuda:0')
episode: 310 training return: tensor(283.8589, device='cuda:0')
episode: 311 training return: tensor(330.0621, device='cuda:0')
epoch: 78 test_true_pfm: 3271.283803479295 sim_pfm: 200.34464046087427
episode: 312 training return: tensor(329.3575, device='cuda:0')
episode: 313 training return: tensor(277.5781, device='cuda:0')
episode: 314 training return: tensor(273.3754, device='cuda:0')
episode: 315 training return: tensor(218.2733, device='cuda:0')
epoch: 79 test_true_pfm: 3510.098803742441 sim_pfm: 334.1350801612619
episode: 316 training return: tensor(247.2991, device='cuda:0')
episode: 317 training return: tensor(225.8533, device='cuda:0')
episode: 318 training return: tensor(-77.8581, device='cuda:0')
episode: 319 training return: tensor(11.1323, device='cuda:0')
epoch: 80 test_true_pfm: 3507.4748985546853 sim_pfm: 376.51724188912584
episode: 320 training return: tensor(339.9171, device='cuda:0')
episode: 321 training return: tensor(213.3972, device='cuda:0')
episode: 322 training return: tensor(346.4276, device='cuda:0')
episode: 323 training return: tensor(190.2932, device='cuda:0')
epoch: 81 test_true_pfm: 3348.5011517176895 sim_pfm: 324.43245649013744
episode: 324 training return: tensor(297.4191, device='cuda:0')
episode: 325 training return: tensor(323.4194, device='cuda:0')
episode: 326 training return: tensor(195.2834, device='cuda:0')
episode: 327 training return: tensor(318.7620, device='cuda:0')
epoch: 82 test_true_pfm: 3515.5362389996935 sim_pfm: 337.97311438183533
episode: 328 training return: tensor(173.7134, device='cuda:0')
episode: 329 training return: tensor(322.1125, device='cuda:0')
episode: 330 training return: tensor(305.0780, device='cuda:0')
episode: 331 training return: tensor(293.3599, device='cuda:0')
epoch: 83 test_true_pfm: 3460.062452735141 sim_pfm: 348.0225554413046
episode: 332 training return: tensor(-214.2085, device='cuda:0')
episode: 333 training return: tensor(115.2157, device='cuda:0')
episode: 334 training return: tensor(224.3263, device='cuda:0')
episode: 335 training return: tensor(207.4156, device='cuda:0')
epoch: 84 test_true_pfm: 3515.996467883291 sim_pfm: 311.75478955466923
episode: 336 training return: tensor(384.1223, device='cuda:0')
episode: 337 training return: tensor(306.2023, device='cuda:0')
episode: 338 training return: tensor(288.4937, device='cuda:0')
episode: 339 training return: tensor(290.0725, device='cuda:0')
epoch: 85 test_true_pfm: 3475.571825436633 sim_pfm: 307.3483395277872
episode: 340 training return: tensor(330.3838, device='cuda:0')
episode: 341 training return: tensor(298.5045, device='cuda:0')
episode: 342 training return: tensor(313.2434, device='cuda:0')
episode: 343 training return: tensor(292.8707, device='cuda:0')
epoch: 86 test_true_pfm: 3456.6212925225886 sim_pfm: 255.3405751810739
episode: 344 training return: tensor(274.9696, device='cuda:0')
episode: 345 training return: tensor(350.3322, device='cuda:0')
episode: 346 training return: tensor(249.9258, device='cuda:0')
episode: 347 training return: tensor(282.5032, device='cuda:0')
epoch: 87 test_true_pfm: 3486.3476478313223 sim_pfm: 336.0943931959143
episode: 348 training return: tensor(340.0302, device='cuda:0')
episode: 349 training return: tensor(284.8578, device='cuda:0')
episode: 350 training return: tensor(303.4882, device='cuda:0')
episode: 351 training return: tensor(337.3849, device='cuda:0')
epoch: 88 test_true_pfm: 3485.939814709931 sim_pfm: 334.2959622547108
episode: 352 training return: tensor(304.6532, device='cuda:0')
episode: 353 training return: tensor(319.6158, device='cuda:0')
episode: 354 training return: tensor(269.6799, device='cuda:0')
episode: 355 training return: tensor(193.5324, device='cuda:0')
epoch: 89 test_true_pfm: 3455.370758392051 sim_pfm: 359.8544518756001
episode: 356 training return: tensor(234.7452, device='cuda:0')
episode: 357 training return: tensor(261.9584, device='cuda:0')
episode: 358 training return: tensor(293.3877, device='cuda:0')
episode: 359 training return: tensor(328.6673, device='cuda:0')
epoch: 90 test_true_pfm: 3409.669198390375 sim_pfm: 339.2830130892883
episode: 360 training return: tensor(-336.3456, device='cuda:0')
episode: 361 training return: tensor(293.9930, device='cuda:0')
episode: 362 training return: tensor(321.3889, device='cuda:0')
episode: 363 training return: tensor(261.1494, device='cuda:0')
epoch: 91 test_true_pfm: 3477.1804192966406 sim_pfm: 347.98458474481595
episode: 364 training return: tensor(353.6269, device='cuda:0')
episode: 365 training return: tensor(202.3485, device='cuda:0')
episode: 366 training return: tensor(227.3526, device='cuda:0')
episode: 367 training return: tensor(271.6194, device='cuda:0')
epoch: 92 test_true_pfm: 3490.771464321355 sim_pfm: 319.8585585608768
episode: 368 training return: tensor(327.9984, device='cuda:0')
episode: 369 training return: tensor(200.0191, device='cuda:0')
episode: 370 training return: tensor(240.9062, device='cuda:0')
episode: 371 training return: tensor(313.9143, device='cuda:0')
epoch: 93 test_true_pfm: 3480.0316295922657 sim_pfm: 305.05559641557437
episode: 372 training return: tensor(197.3037, device='cuda:0')
episode: 373 training return: tensor(282.9364, device='cuda:0')
episode: 374 training return: tensor(288.1286, device='cuda:0')
episode: 375 training return: tensor(190.2806, device='cuda:0')
epoch: 94 test_true_pfm: 3542.0397511630563 sim_pfm: 376.3855525839317
episode: 376 training return: tensor(259.8349, device='cuda:0')
episode: 377 training return: tensor(73.3409, device='cuda:0')
episode: 378 training return: tensor(249.1855, device='cuda:0')
episode: 379 training return: tensor(332.4582, device='cuda:0')
epoch: 95 test_true_pfm: 3530.3892684900025 sim_pfm: 316.2005207774637
episode: 380 training return: tensor(333.5837, device='cuda:0')
episode: 381 training return: tensor(257.5307, device='cuda:0')
episode: 382 training return: tensor(316.4432, device='cuda:0')
episode: 383 training return: tensor(376.4068, device='cuda:0')
epoch: 96 test_true_pfm: 3533.123473845157 sim_pfm: 387.2031807825163
episode: 384 training return: tensor(233.5793, device='cuda:0')
episode: 385 training return: tensor(304.9604, device='cuda:0')
episode: 386 training return: tensor(251.6756, device='cuda:0')
episode: 387 training return: tensor(249.9386, device='cuda:0')
epoch: 97 test_true_pfm: 3469.493181403546 sim_pfm: 298.31192913659225
episode: 388 training return: tensor(319.0448, device='cuda:0')
episode: 389 training return: tensor(359.2940, device='cuda:0')
episode: 390 training return: tensor(179.0889, device='cuda:0')
episode: 391 training return: tensor(320.1217, device='cuda:0')
epoch: 98 test_true_pfm: 3527.423083745051 sim_pfm: 380.29434538436664
episode: 392 training return: tensor(270.2714, device='cuda:0')
episode: 393 training return: tensor(-21.3213, device='cuda:0')
episode: 394 training return: tensor(325.1615, device='cuda:0')
episode: 395 training return: tensor(292.1024, device='cuda:0')
epoch: 99 test_true_pfm: 3208.292995534071 sim_pfm: 346.66997372252325
episode: 396 training return: tensor(243.5910, device='cuda:0')
episode: 397 training return: tensor(285.9385, device='cuda:0')
episode: 398 training return: tensor(283.2033, device='cuda:0')
episode: 399 training return: tensor(250.8170, device='cuda:0')
epoch: 100 test_true_pfm: 3473.771741381514 sim_pfm: 223.28337913916525
episode: 400 training return: tensor(236.4111, device='cuda:0')
episode: 401 training return: tensor(201.3189, device='cuda:0')
episode: 402 training return: tensor(240.2455, device='cuda:0')
episode: 403 training return: tensor(354.9054, device='cuda:0')
epoch: 101 test_true_pfm: 3527.33850594626 sim_pfm: 361.19918482768117
episode: 404 training return: tensor(338.5511, device='cuda:0')
episode: 405 training return: tensor(272.3861, device='cuda:0')
episode: 406 training return: tensor(332.7006, device='cuda:0')
episode: 407 training return: tensor(335.1957, device='cuda:0')
epoch: 102 test_true_pfm: 3530.472151932839 sim_pfm: 339.76734610148316
episode: 408 training return: tensor(273.7053, device='cuda:0')
episode: 409 training return: tensor(345.5421, device='cuda:0')
episode: 410 training return: tensor(305.5449, device='cuda:0')
episode: 411 training return: tensor(341.6246, device='cuda:0')
epoch: 103 test_true_pfm: 3521.7636546915924 sim_pfm: 328.03752831892535
episode: 412 training return: tensor(345.4062, device='cuda:0')
episode: 413 training return: tensor(287.6940, device='cuda:0')
episode: 414 training return: tensor(399.5684, device='cuda:0')
episode: 415 training return: tensor(383.0024, device='cuda:0')
epoch: 104 test_true_pfm: 3502.239527530756 sim_pfm: 338.9337444162423
episode: 416 training return: tensor(311.2867, device='cuda:0')
episode: 417 training return: tensor(283.6578, device='cuda:0')
episode: 418 training return: tensor(246.6072, device='cuda:0')
episode: 419 training return: tensor(241.0500, device='cuda:0')
epoch: 105 test_true_pfm: 3533.4557526972967 sim_pfm: 305.26886637468124
episode: 420 training return: tensor(328.4173, device='cuda:0')
episode: 421 training return: tensor(301.2828, device='cuda:0')
episode: 422 training return: tensor(319.2616, device='cuda:0')
episode: 423 training return: tensor(368.4158, device='cuda:0')
epoch: 106 test_true_pfm: 3526.6500930015495 sim_pfm: 342.25305013453664
episode: 424 training return: tensor(273.3984, device='cuda:0')
episode: 425 training return: tensor(268.1017, device='cuda:0')
episode: 426 training return: tensor(313.1286, device='cuda:0')
episode: 427 training return: tensor(330.3073, device='cuda:0')
epoch: 107 test_true_pfm: 3501.0995786172657 sim_pfm: 351.1247841883839
episode: 428 training return: tensor(292.6973, device='cuda:0')
episode: 429 training return: tensor(271.1762, device='cuda:0')
episode: 430 training return: tensor(258.9290, device='cuda:0')
episode: 431 training return: tensor(283.1719, device='cuda:0')
epoch: 108 test_true_pfm: 3526.8444560437106 sim_pfm: 348.40349076358444
episode: 432 training return: tensor(11.2927, device='cuda:0')
episode: 433 training return: tensor(306.1178, device='cuda:0')
episode: 434 training return: tensor(344.5593, device='cuda:0')
episode: 435 training return: tensor(308.4845, device='cuda:0')
epoch: 109 test_true_pfm: 3411.747238991544 sim_pfm: 334.48950038476806
episode: 436 training return: tensor(281.0736, device='cuda:0')
episode: 437 training return: tensor(216.2315, device='cuda:0')
episode: 438 training return: tensor(262.4649, device='cuda:0')
episode: 439 training return: tensor(331.7811, device='cuda:0')
epoch: 110 test_true_pfm: 3578.140819451486 sim_pfm: 370.5505954371086
episode: 440 training return: tensor(257.4109, device='cuda:0')
episode: 441 training return: tensor(241.9960, device='cuda:0')
episode: 442 training return: tensor(326.8478, device='cuda:0')
episode: 443 training return: tensor(365.5437, device='cuda:0')
epoch: 111 test_true_pfm: 3531.90252800011 sim_pfm: 359.0890492265656
episode: 444 training return: tensor(241.6177, device='cuda:0')
episode: 445 training return: tensor(219.8178, device='cuda:0')
episode: 446 training return: tensor(363.8846, device='cuda:0')
episode: 447 training return: tensor(335.3952, device='cuda:0')
epoch: 112 test_true_pfm: 3510.302897694301 sim_pfm: 324.30681463689933
episode: 448 training return: tensor(273.1338, device='cuda:0')
episode: 449 training return: tensor(328.8798, device='cuda:0')
episode: 450 training return: tensor(355.1566, device='cuda:0')
episode: 451 training return: tensor(357.7474, device='cuda:0')
epoch: 113 test_true_pfm: 3513.6489981423924 sim_pfm: 323.3369526383855
episode: 452 training return: tensor(336.1005, device='cuda:0')
episode: 453 training return: tensor(359.2518, device='cuda:0')
episode: 454 training return: tensor(347.6450, device='cuda:0')
episode: 455 training return: tensor(276.4055, device='cuda:0')
epoch: 114 test_true_pfm: 3496.818391098904 sim_pfm: 328.4134666660587
episode: 456 training return: tensor(327.0746, device='cuda:0')
episode: 457 training return: tensor(344.7455, device='cuda:0')
episode: 458 training return: tensor(337.7600, device='cuda:0')
episode: 459 training return: tensor(346.7647, device='cuda:0')
epoch: 115 test_true_pfm: 3524.677467070871 sim_pfm: 348.6315336053861
episode: 460 training return: tensor(279.5984, device='cuda:0')
episode: 461 training return: tensor(372.7087, device='cuda:0')
episode: 462 training return: tensor(304.4419, device='cuda:0')
episode: 463 training return: tensor(265.0272, device='cuda:0')
epoch: 116 test_true_pfm: 3554.542750435552 sim_pfm: 373.5559852551087
episode: 464 training return: tensor(330.6375, device='cuda:0')
episode: 465 training return: tensor(-93.4460, device='cuda:0')
episode: 466 training return: tensor(236.7128, device='cuda:0')
episode: 467 training return: tensor(-83.3321, device='cuda:0')
epoch: 117 test_true_pfm: 3403.581628441134 sim_pfm: 315.57182307739276
episode: 468 training return: tensor(355.2968, device='cuda:0')
episode: 469 training return: tensor(289.9977, device='cuda:0')
episode: 470 training return: tensor(249.0773, device='cuda:0')
episode: 471 training return: tensor(260.1731, device='cuda:0')
epoch: 118 test_true_pfm: 3026.772458437577 sim_pfm: 352.534799149648
episode: 472 training return: tensor(303.4877, device='cuda:0')
episode: 473 training return: tensor(-173.2662, device='cuda:0')
episode: 474 training return: tensor(274.0711, device='cuda:0')
episode: 475 training return: tensor(-190.7260, device='cuda:0')
epoch: 119 test_true_pfm: 3462.82431977884 sim_pfm: 331.47022987756645
episode: 476 training return: tensor(293.3480, device='cuda:0')
episode: 477 training return: tensor(178.1570, device='cuda:0')
episode: 478 training return: tensor(214.2317, device='cuda:0')
episode: 479 training return: tensor(208.2577, device='cuda:0')
epoch: 120 test_true_pfm: 3497.21914675147 sim_pfm: 247.66171288788124
episode: 480 training return: tensor(235.1420, device='cuda:0')
episode: 481 training return: tensor(319.6327, device='cuda:0')
episode: 482 training return: tensor(286.1385, device='cuda:0')
episode: 483 training return: tensor(338.1122, device='cuda:0')
epoch: 121 test_true_pfm: 3522.47589882357 sim_pfm: 374.76761541575735
episode: 484 training return: tensor(330.3595, device='cuda:0')
episode: 485 training return: tensor(315.4557, device='cuda:0')
episode: 486 training return: tensor(346.8245, device='cuda:0')
episode: 487 training return: tensor(409.8020, device='cuda:0')
epoch: 122 test_true_pfm: 3527.9985608660295 sim_pfm: 285.5406420254537
episode: 488 training return: tensor(287.1255, device='cuda:0')
episode: 489 training return: tensor(356.8359, device='cuda:0')
episode: 490 training return: tensor(321.9345, device='cuda:0')
episode: 491 training return: tensor(335.7153, device='cuda:0')
epoch: 123 test_true_pfm: 3520.657822565517 sim_pfm: 330.94130169887404
episode: 492 training return: tensor(315.3760, device='cuda:0')
episode: 493 training return: tensor(345.6693, device='cuda:0')
episode: 494 training return: tensor(368.4326, device='cuda:0')
episode: 495 training return: tensor(250.1763, device='cuda:0')
epoch: 124 test_true_pfm: 3509.0479954189136 sim_pfm: 349.84460890633636
episode: 496 training return: tensor(323.5226, device='cuda:0')
episode: 497 training return: tensor(244.8995, device='cuda:0')
episode: 498 training return: tensor(304.1326, device='cuda:0')
episode: 499 training return: tensor(281.2115, device='cuda:0')
epoch: 125 test_true_pfm: 3221.746979099206 sim_pfm: 379.6935291127108
episode: 500 training return: tensor(301.6526, device='cuda:0')
episode: 501 training return: tensor(308.0597, device='cuda:0')
episode: 502 training return: tensor(260.5413, device='cuda:0')
episode: 503 training return: tensor(384.3764, device='cuda:0')
epoch: 126 test_true_pfm: 3081.2439258899994 sim_pfm: 251.86328599023787
episode: 504 training return: tensor(212.2825, device='cuda:0')
episode: 505 training return: tensor(307.3314, device='cuda:0')
episode: 506 training return: tensor(321.5309, device='cuda:0')
episode: 507 training return: tensor(273.3881, device='cuda:0')
epoch: 127 test_true_pfm: 3472.4305987926123 sim_pfm: 213.07300619768407
episode: 508 training return: tensor(363.9995, device='cuda:0')
episode: 509 training return: tensor(322.3457, device='cuda:0')
episode: 510 training return: tensor(318.6063, device='cuda:0')
episode: 511 training return: tensor(333.1753, device='cuda:0')
epoch: 128 test_true_pfm: 3493.1612948628135 sim_pfm: 355.692442236051
episode: 512 training return: tensor(183.9110, device='cuda:0')
episode: 513 training return: tensor(376.0088, device='cuda:0')
episode: 514 training return: tensor(257.9320, device='cuda:0')
episode: 515 training return: tensor(325.6361, device='cuda:0')
epoch: 129 test_true_pfm: 3494.515673539987 sim_pfm: 357.53359566250583
episode: 516 training return: tensor(346.7668, device='cuda:0')
episode: 517 training return: tensor(301.4755, device='cuda:0')
episode: 518 training return: tensor(298.1464, device='cuda:0')
episode: 519 training return: tensor(44.7055, device='cuda:0')
epoch: 130 test_true_pfm: 3493.600975327138 sim_pfm: 358.92612429338624
episode: 520 training return: tensor(377.9032, device='cuda:0')
episode: 521 training return: tensor(319.8249, device='cuda:0')
episode: 522 training return: tensor(276.9516, device='cuda:0')
episode: 523 training return: tensor(357.6318, device='cuda:0')
epoch: 131 test_true_pfm: 3494.0905380462505 sim_pfm: 339.50171432548086
episode: 524 training return: tensor(357.8533, device='cuda:0')
episode: 525 training return: tensor(-109.6129, device='cuda:0')
episode: 526 training return: tensor(-210.0320, device='cuda:0')
episode: 527 training return: tensor(315.0268, device='cuda:0')
epoch: 132 test_true_pfm: 3539.477954635975 sim_pfm: 359.3022779056143
episode: 528 training return: tensor(321.8025, device='cuda:0')
episode: 529 training return: tensor(301.6100, device='cuda:0')
episode: 530 training return: tensor(315.9706, device='cuda:0')
episode: 531 training return: tensor(234.4375, device='cuda:0')
epoch: 133 test_true_pfm: 3508.0073760030878 sim_pfm: 337.1249516398918
episode: 532 training return: tensor(101.9391, device='cuda:0')
episode: 533 training return: tensor(273.7155, device='cuda:0')
episode: 534 training return: tensor(292.6983, device='cuda:0')
episode: 535 training return: tensor(215.0172, device='cuda:0')
epoch: 134 test_true_pfm: 3466.5017351848037 sim_pfm: 340.64656612920226
episode: 536 training return: tensor(350.1677, device='cuda:0')
episode: 537 training return: tensor(308.7642, device='cuda:0')
episode: 538 training return: tensor(373.8987, device='cuda:0')
episode: 539 training return: tensor(352.9407, device='cuda:0')
epoch: 135 test_true_pfm: 3519.7376823184327 sim_pfm: 324.184293450128
episode: 540 training return: tensor(249.0086, device='cuda:0')
episode: 541 training return: tensor(257.8903, device='cuda:0')
episode: 542 training return: tensor(-129.0305, device='cuda:0')
episode: 543 training return: tensor(338.2914, device='cuda:0')
epoch: 136 test_true_pfm: 3495.8292745849662 sim_pfm: 362.26797079694614
episode: 544 training return: tensor(362.0769, device='cuda:0')
episode: 545 training return: tensor(264.7103, device='cuda:0')
episode: 546 training return: tensor(366.0896, device='cuda:0')
episode: 547 training return: tensor(-177.6386, device='cuda:0')
epoch: 137 test_true_pfm: 3519.8479850790864 sim_pfm: 324.55933744996827
episode: 548 training return: tensor(333.4212, device='cuda:0')
episode: 549 training return: tensor(298.3332, device='cuda:0')
episode: 550 training return: tensor(328.5320, device='cuda:0')
episode: 551 training return: tensor(283.4287, device='cuda:0')
epoch: 138 test_true_pfm: 3552.7269094389117 sim_pfm: 361.6948523896863
episode: 552 training return: tensor(325.0845, device='cuda:0')
episode: 553 training return: tensor(335.4444, device='cuda:0')
episode: 554 training return: tensor(361.9994, device='cuda:0')
episode: 555 training return: tensor(295.7638, device='cuda:0')
epoch: 139 test_true_pfm: 3554.7075740225155 sim_pfm: 358.8127613268637
episode: 556 training return: tensor(206.4337, device='cuda:0')
episode: 557 training return: tensor(331.1178, device='cuda:0')
episode: 558 training return: tensor(311.9017, device='cuda:0')
episode: 559 training return: tensor(405.7117, device='cuda:0')
epoch: 140 test_true_pfm: 3519.59137821506 sim_pfm: 339.75486664896016
episode: 560 training return: tensor(389.3126, device='cuda:0')
episode: 561 training return: tensor(341.0866, device='cuda:0')
episode: 562 training return: tensor(293.9079, device='cuda:0')
episode: 563 training return: tensor(393.6598, device='cuda:0')
epoch: 141 test_true_pfm: 3504.668552737165 sim_pfm: 245.71647156604254
episode: 564 training return: tensor(370.5735, device='cuda:0')
episode: 565 training return: tensor(259.6758, device='cuda:0')
episode: 566 training return: tensor(261.4575, device='cuda:0')
episode: 567 training return: tensor(370.6161, device='cuda:0')
epoch: 142 test_true_pfm: 3529.678082532751 sim_pfm: 368.7935091604401
episode: 568 training return: tensor(337.0086, device='cuda:0')
episode: 569 training return: tensor(317.1707, device='cuda:0')
episode: 570 training return: tensor(357.5069, device='cuda:0')
episode: 571 training return: tensor(340.8254, device='cuda:0')
epoch: 143 test_true_pfm: 3530.707663875231 sim_pfm: 362.6010605111175
episode: 572 training return: tensor(259.2199, device='cuda:0')
episode: 573 training return: tensor(275.5196, device='cuda:0')
episode: 574 training return: tensor(-280.4766, device='cuda:0')
episode: 575 training return: tensor(356.4526, device='cuda:0')
epoch: 144 test_true_pfm: 3501.964169945437 sim_pfm: 341.6430460489452
episode: 576 training return: tensor(255.8785, device='cuda:0')
episode: 577 training return: tensor(366.9148, device='cuda:0')
episode: 578 training return: tensor(366.4291, device='cuda:0')
episode: 579 training return: tensor(244.3477, device='cuda:0')
epoch: 145 test_true_pfm: 3514.5188500407744 sim_pfm: 380.3732557746116
episode: 580 training return: tensor(324.6140, device='cuda:0')
episode: 581 training return: tensor(356.4973, device='cuda:0')
episode: 582 training return: tensor(276.4323, device='cuda:0')
episode: 583 training return: tensor(250.0432, device='cuda:0')
epoch: 146 test_true_pfm: 3528.1183171054436 sim_pfm: 335.7745955294037
episode: 584 training return: tensor(-203.4260, device='cuda:0')
episode: 585 training return: tensor(258.2487, device='cuda:0')
episode: 586 training return: tensor(247.8689, device='cuda:0')
episode: 587 training return: tensor(326.4117, device='cuda:0')
epoch: 147 test_true_pfm: 3540.8758325890194 sim_pfm: 362.69331926617696
episode: 588 training return: tensor(347.4377, device='cuda:0')
episode: 589 training return: tensor(386.9825, device='cuda:0')
episode: 590 training return: tensor(357.0094, device='cuda:0')
episode: 591 training return: tensor(348.8331, device='cuda:0')
epoch: 148 test_true_pfm: 3535.7836493019317 sim_pfm: 363.98190499888733
episode: 592 training return: tensor(341.8469, device='cuda:0')
episode: 593 training return: tensor(299.0421, device='cuda:0')
episode: 594 training return: tensor(217.6143, device='cuda:0')
episode: 595 training return: tensor(327.3208, device='cuda:0')
epoch: 149 test_true_pfm: 3520.788451112066 sim_pfm: 370.294038353158
episode: 596 training return: tensor(325.9348, device='cuda:0')
episode: 597 training return: tensor(347.9986, device='cuda:0')
episode: 598 training return: tensor(282.6085, device='cuda:0')
episode: 599 training return: tensor(317.2097, device='cuda:0')
epoch: 150 test_true_pfm: 3461.4140003477896 sim_pfm: 7.687573772816298
