['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'behavior', '--traj', 'medium', '--seed', '3', '--data', '3000']
epoch: 0 training_loss 0.29624471373856065 test_loss: 0.09723067283630371
epoch: 1 training_loss 0.14635097332298755 test_loss: 0.07369722127914428
epoch: 2 training_loss 0.11449558794498443 test_loss: 0.0753713846206665
epoch: 3 training_loss 0.09515419125556945 test_loss: 0.07174334526062012
epoch: 4 training_loss 0.08999315962195396 test_loss: 0.0745543360710144
epoch: 5 training_loss 0.07734197624027729 test_loss: 0.06661092638969421
epoch: 6 training_loss 0.07532860768958927 test_loss: 0.0723188579082489
epoch: 7 training_loss 0.06796849714592099 test_loss: 0.07358809113502503
epoch: 8 training_loss 0.05971873400732875 test_loss: 0.07752852439880371
epoch: 9 training_loss 0.06329614801332355 test_loss: 0.07178040146827698
epoch: 10 training_loss 0.05822447397746146 test_loss: 0.082872873544693
epoch: 11 training_loss 0.060443085990846156 test_loss: 0.07622435688972473
epoch: 12 training_loss 0.05344099143519997 test_loss: 0.07089568972587586
epoch: 13 training_loss 0.05205447777174413 test_loss: 0.07106888294219971
epoch: 14 training_loss 0.05188100069761276 test_loss: 0.07989978194236755
epoch: 15 training_loss 0.04261019124649465 test_loss: 0.07629286646842956
epoch: 16 training_loss 0.04710365515202284 test_loss: 0.07335638403892517
epoch: 17 training_loss 0.03727049936540425 test_loss: 0.07512494325637817
epoch: 18 training_loss 0.04047991664148867 test_loss: 0.07493041157722473
epoch: 19 training_loss 0.03270794154144824 test_loss: 0.0786634624004364
epoch: 20 training_loss 0.031073543415404855 test_loss: 0.08159089088439941
epoch: 21 training_loss 0.031044871769845484 test_loss: 0.07507672309875488
epoch: 22 training_loss 0.03949747807346284 test_loss: 0.08066672086715698
epoch: 23 training_loss 0.0299071093602106 test_loss: 0.07832103371620178
epoch: 24 training_loss 0.026587138902395963 test_loss: 0.07966570854187012
epoch: 25 training_loss 0.02691129906103015 test_loss: 0.07555793523788452
epoch: 26 training_loss 0.026579689355567097 test_loss: 0.085101318359375
epoch: 27 training_loss 0.02190254874760285 test_loss: 0.08776832818984985
epoch: 28 training_loss 0.03326402230653912 test_loss: 0.08506833910942077
epoch: 29 training_loss 0.023656810908578338 test_loss: 0.0817756175994873
epoch: 30 training_loss 0.028915887121111154 test_loss: 0.08205954432487488
epoch: 31 training_loss 0.016956864474341273 test_loss: 0.08676031827926636
epoch: 32 training_loss 0.02443786037620157 test_loss: 0.0838356375694275
epoch: 33 training_loss 0.015863826130516828 test_loss: 0.08736899495124817
epoch: 34 training_loss 0.012414790377952158 test_loss: 0.089853835105896
epoch: 35 training_loss 0.015840601148083805 test_loss: 0.08539574146270752
epoch: 36 training_loss 0.011787720955908298 test_loss: 0.0920182704925537
epoch: 37 training_loss 0.011464202143251896 test_loss: 0.08719426393508911
epoch: 38 training_loss 0.014694246866274624 test_loss: 0.09238365888595582
epoch: 39 training_loss 0.013503462034277618 test_loss: 0.10996780395507813
epoch: 40 training_loss 0.019999927650205793 test_loss: 0.0968204379081726
epoch: 41 training_loss 0.017967038345523177 test_loss: 0.09754053354263306
epoch: 42 training_loss 0.01064797620056197 test_loss: 0.09228664636611938
epoch: 43 training_loss 0.0522957541141659 test_loss: 0.12347195148468018
epoch: 44 training_loss 0.07180028948001564 test_loss: 0.0822350800037384
epoch: 45 training_loss 0.017767295097000896 test_loss: 0.08007456660270691
epoch: 46 training_loss 0.01260085380403325 test_loss: 0.08301018476486206
epoch: 47 training_loss 0.010456887863110751 test_loss: 0.09210250973701477
epoch: 48 training_loss 0.009420644924975932 test_loss: 0.09112167954444886
epoch: 49 training_loss 0.008633884987793862 test_loss: 0.09630844593048096
epoch: 50 training_loss 0.007516363186296076 test_loss: 0.09505442380905152
epoch: 51 training_loss 0.006750030186958611 test_loss: 0.09235084652900696
epoch: 52 training_loss 0.006968397861346603 test_loss: 0.09652762413024903
epoch: 53 training_loss 0.0062297440390102566 test_loss: 0.09675039649009705
epoch: 54 training_loss 0.011472010759171099 test_loss: 0.10378458499908447
epoch: 55 training_loss 0.0447232507634908 test_loss: 0.10758641958236695
epoch: 56 training_loss 0.051168842436745764 test_loss: 0.09417623281478882
epoch: 57 training_loss 0.017556909273844214 test_loss: 0.0945901095867157
epoch: 58 training_loss 0.009336857912130654 test_loss: 0.09438467621803284
epoch: 59 training_loss 0.008023384232074023 test_loss: 0.09685224890708924
epoch: 60 training_loss 0.00722055492689833 test_loss: 0.09663810133934021
epoch: 61 training_loss 0.006245381181361154 test_loss: 0.09778155088424682
epoch: 62 training_loss 0.0068993929377757016 test_loss: 0.10905506610870361
epoch: 63 training_loss 0.0059299930091947315 test_loss: 0.10005522966384887
epoch: 64 training_loss 0.005643855663947761 test_loss: 0.0997307538986206
epoch: 65 training_loss 0.005751287706661969 test_loss: 0.09872997999191284
epoch: 66 training_loss 0.004774580118246377 test_loss: 0.09892698526382446
epoch: 67 training_loss 0.0044365772488527 test_loss: 0.09837221503257751
epoch: 68 training_loss 0.004556105501251295 test_loss: 0.09495818018913268
epoch: 69 training_loss 0.004756571953184903 test_loss: 0.09835910201072692
epoch: 70 training_loss 0.006643518316559493 test_loss: 0.10298914909362793
epoch: 71 training_loss 0.005400064716814086 test_loss: 0.10270850658416748
epoch: 72 training_loss 0.0043021191575098785 test_loss: 0.10443180799484253
epoch: 73 training_loss 0.0045327843935228885 test_loss: 0.11234884262084961
epoch: 74 training_loss 0.09205800016177818 test_loss: 0.2020946502685547
epoch: 75 training_loss 0.14152833921834826 test_loss: 0.08104361891746521
epoch: 76 training_loss 0.040368478493764993 test_loss: 0.08530027270317078
epoch: 77 training_loss 0.024005728028714656 test_loss: 0.0852221429347992
epoch: 78 training_loss 0.01781514771748334 test_loss: 0.09772168397903443
epoch: 79 training_loss 0.011149110873229801 test_loss: 0.09472684860229492
epoch: 80 training_loss 0.009060900926124304 test_loss: 0.09818440675735474
epoch: 81 training_loss 0.008422174039296806 test_loss: 0.09842892289161682
epoch: 82 training_loss 0.006883208518847823 test_loss: 0.09889835119247437
epoch: 83 training_loss 0.006959902532398701 test_loss: 0.10041770935058594
epoch: 84 training_loss 0.006190669891657308 test_loss: 0.10336697101593018
epoch: 85 training_loss 0.006151233703130856 test_loss: 0.10301995277404785
epoch: 86 training_loss 0.005618892232887447 test_loss: 0.10686755180358887
epoch: 87 training_loss 0.005169556575128809 test_loss: 0.10919933319091797
epoch: 88 training_loss 0.004642208823934197 test_loss: 0.11075283288955688
epoch: 89 training_loss 0.00448004602571018 test_loss: 0.11540660858154297
epoch: 90 training_loss 0.004546279427595437 test_loss: 0.11422884464263916
epoch: 91 training_loss 0.004026776851387695 test_loss: 0.1122024416923523
epoch: 92 training_loss 0.003489653276046738 test_loss: 0.11481742858886719
epoch: 93 training_loss 0.0038948304648511113 test_loss: 0.11141294240951538
epoch: 94 training_loss 0.003516577476402745 test_loss: 0.11730852127075195
epoch: 95 training_loss 0.0032521466247271745 test_loss: 0.11433354616165162
epoch: 96 training_loss 0.0031563871272373943 test_loss: 0.11749098300933838
epoch: 97 training_loss 0.03972994254203513 test_loss: 0.13853831291198732
epoch: 98 training_loss 0.1430768735706806 test_loss: 0.08086061477661133
epoch: 99 training_loss 0.03485966367647052 test_loss: 0.08551508784294129
epoch: 100 training_loss 0.015427136104553938 test_loss: 0.09655396342277527
epoch: 101 training_loss 0.01056107871932909 test_loss: 0.09659631252288818
epoch: 102 training_loss 0.00688853288302198 test_loss: 0.09965221285820007
epoch: 103 training_loss 0.005300845816964284 test_loss: 0.09933545589447021
epoch: 104 training_loss 0.005003690217854455 test_loss: 0.097934889793396
epoch: 105 training_loss 0.004508348123636097 test_loss: 0.09952055215835572
epoch: 106 training_loss 0.004047651184955612 test_loss: 0.1069806694984436
epoch: 107 training_loss 0.00366140031372197 test_loss: 0.10618889331817627
epoch: 108 training_loss 0.0036033997451886536 test_loss: 0.10705051422119141
epoch: 109 training_loss 0.0033114751835819334 test_loss: 0.10872373580932618
epoch: 110 training_loss 0.0034616305830422788 test_loss: 0.10743751525878906
epoch: 111 training_loss 0.00281665091344621 test_loss: 0.10614721775054932
epoch: 112 training_loss 0.0028034223953727635 test_loss: 0.10810720920562744
epoch: 113 training_loss 0.0029478679038584233 test_loss: 0.11146597862243653
epoch: 114 training_loss 0.0024657830595970153 test_loss: 0.10693535804748536
epoch: 115 training_loss 0.0024924492853460834 test_loss: 0.10972126722335815
epoch: 116 training_loss 0.0023674988938728347 test_loss: 0.11456420421600341
epoch: 117 training_loss 0.0021367713779909536 test_loss: 0.1127897024154663
epoch: 118 training_loss 0.00223649867111817 test_loss: 0.11283253431320191
epoch: 119 training_loss 0.0022711809969041498 test_loss: 0.1128926396369934
epoch: 120 training_loss 0.0025772022613091395 test_loss: 0.11044112443923951
epoch: 121 training_loss 0.002031298032379709 test_loss: 0.11445395946502686
epoch: 122 training_loss 0.0018810220068553464 test_loss: 0.11299742460250854
epoch: 123 training_loss 0.001894009699462913 test_loss: 0.11678394079208373
epoch: 124 training_loss 0.0022305369673995303 test_loss: 0.11900564432144164
epoch: 125 training_loss 0.00296666908019688 test_loss: 0.12477672100067139
epoch: 126 training_loss 0.2571762641891837 test_loss: 0.08394854068756104
epoch: 127 training_loss 0.06107855476438999 test_loss: 0.0809688150882721
epoch: 128 training_loss 0.03756370744667947 test_loss: 0.08506015539169312
epoch: 129 training_loss 0.027048443388193847 test_loss: 0.09427026510238648
epoch: 130 training_loss 0.021047609900124373 test_loss: 0.09277409315109253
epoch: 131 training_loss 0.013178669628687203 test_loss: 0.09821546077728271
epoch: 132 training_loss 0.010088180077727884 test_loss: 0.1057966709136963
epoch: 133 training_loss 0.009221463419962675 test_loss: 0.10148624181747437
epoch: 134 training_loss 0.008805300777312368 test_loss: 0.10761607885360717
epoch: 135 training_loss 0.006922974234912544 test_loss: 0.106659996509552
epoch: 136 training_loss 0.00656740389065817 test_loss: 0.10753997564315795
epoch: 137 training_loss 0.005981019528117031 test_loss: 0.10628303289413452
epoch: 138 training_loss 0.00561977363191545 test_loss: 0.10400441884994507
epoch: 139 training_loss 0.005282520593609661 test_loss: 0.10739413499832154
epoch: 140 training_loss 0.005077737643150612 test_loss: 0.11182405948638915
epoch: 141 training_loss 0.004330165951978415 test_loss: 0.11527117490768432
epoch: 142 training_loss 0.003965634792111814 test_loss: 0.10745973587036133
epoch: 143 training_loss 0.003738574724411592 test_loss: 0.11865521669387817
epoch: 144 training_loss 0.006149404671741649 test_loss: 0.11918240785598755
epoch: 145 training_loss 0.004535151936579496 test_loss: 0.10610193014144897
epoch: 146 training_loss 0.0034702088194899262 test_loss: 0.11473116874694825
epoch: 147 training_loss 0.0029349812609143554 test_loss: 0.11748713254928589
epoch: 148 training_loss 0.0045326839713379745 test_loss: 0.12239979505538941
epoch: 149 training_loss 0.006975069047184661 test_loss: 0.11260353326797486
epoch: 0 training_loss 50.98283180236817 test_loss: 11.601934814453125
epoch: 1 training_loss 18.582830018997193 test_loss: 7.062349700927735
epoch: 2 training_loss 13.085731267929077 test_loss: 5.497480773925782
epoch: 3 training_loss 10.4030433177948 test_loss: 4.5513042449951175
epoch: 4 training_loss 8.849697012901306 test_loss: 4.004472732543945
epoch: 5 training_loss 7.666603317260742 test_loss: 3.609942626953125
epoch: 6 training_loss 6.700609111785889 test_loss: 3.286786651611328
epoch: 7 training_loss 6.087996926307678 test_loss: 2.9478992462158202
epoch: 8 training_loss 5.552020201683044 test_loss: 2.7592445373535157
epoch: 9 training_loss 5.177045021057129 test_loss: 2.545909118652344
epoch: 10 training_loss 4.716751894950867 test_loss: 2.4140758514404297
epoch: 11 training_loss 4.458039700984955 test_loss: 2.281300163269043
epoch: 12 training_loss 4.229479897022247 test_loss: 2.1737428665161134
epoch: 13 training_loss 3.967719430923462 test_loss: 2.0936235427856444
epoch: 14 training_loss 3.8097480511665345 test_loss: 1.998986053466797
epoch: 15 training_loss 3.655621283054352 test_loss: 1.9087770462036133
epoch: 16 training_loss 3.4657521748542788 test_loss: 1.856712532043457
epoch: 17 training_loss 3.3980118870735168 test_loss: 1.7759878158569335
epoch: 18 training_loss 3.2197912383079528 test_loss: 1.7331487655639648
epoch: 19 training_loss 3.182705354690552 test_loss: 1.6912109375
epoch: 20 training_loss 3.1594038462638854 test_loss: 1.6710691452026367
epoch: 21 training_loss 3.049686644077301 test_loss: 1.6222558975219727
epoch: 22 training_loss 2.88528710603714 test_loss: 1.5551060676574706
epoch: 23 training_loss 2.811699779033661 test_loss: 1.5275056838989258
epoch: 24 training_loss 2.790426058769226 test_loss: 1.5048395156860352
epoch: 25 training_loss 2.713222854137421 test_loss: 1.463058090209961
epoch: 26 training_loss 2.613155300617218 test_loss: 1.4576645851135255
epoch: 27 training_loss 2.600970034599304 test_loss: 1.4160314559936524
epoch: 28 training_loss 2.5597423267364503 test_loss: 1.4148039817810059
epoch: 29 training_loss 2.5479950189590452 test_loss: 1.3780853271484375
epoch: 30 training_loss 2.474120831489563 test_loss: 1.3688286781311034
epoch: 31 training_loss 2.467848582267761 test_loss: 1.3372767448425293
epoch: 32 training_loss 2.354925310611725 test_loss: 1.3395891189575195
epoch: 33 training_loss 2.356094949245453 test_loss: 1.3101221084594727
epoch: 34 training_loss 2.30311990737915 test_loss: 1.298445701599121
epoch: 35 training_loss 2.3073281908035277 test_loss: 1.2745657920837403
epoch: 36 training_loss 2.286565682888031 test_loss: 1.267059898376465
epoch: 37 training_loss 2.2402007246017455 test_loss: 1.2673974990844727
epoch: 38 training_loss 2.1761964786052705 test_loss: 1.2511393547058105
epoch: 39 training_loss 2.2253477013111116 test_loss: 1.228788185119629
epoch: 40 training_loss 2.1498636209964754 test_loss: 1.2104853630065917
epoch: 41 training_loss 2.1072022378444673 test_loss: 1.190844440460205
epoch: 42 training_loss 2.0578182983398436 test_loss: 1.2016058921813966
epoch: 43 training_loss 2.091203647851944 test_loss: 1.178840446472168
epoch: 44 training_loss 2.068883428573608 test_loss: 1.1575541496276855
epoch: 45 training_loss 2.0272051596641543 test_loss: 1.155561351776123
epoch: 46 training_loss 2.0493824493885042 test_loss: 1.1572340965270995
epoch: 47 training_loss 1.9898103332519532 test_loss: 1.1447029113769531
epoch: 48 training_loss 1.9951231110095977 test_loss: 1.1348995208740233
epoch: 49 training_loss 1.959058336019516 test_loss: 1.1342556953430176
epoch: 50 training_loss 1.9243292152881621 test_loss: 1.122757911682129
epoch: 51 training_loss 1.9872825253009796 test_loss: 1.1070560455322265
epoch: 52 training_loss 1.9120560598373413 test_loss: 1.1083503723144532
epoch: 53 training_loss 1.9577650260925292 test_loss: 1.0925898551940918
epoch: 54 training_loss 1.934427856206894 test_loss: 1.0870281219482423
epoch: 55 training_loss 1.8873617458343506 test_loss: 1.0807095527648927
epoch: 56 training_loss 1.8599525392055511 test_loss: 1.0733070373535156
epoch: 57 training_loss 1.8367204403877258 test_loss: 1.0828536033630372
epoch: 58 training_loss 1.8751038420200348 test_loss: 1.0503834724426269
epoch: 59 training_loss 1.832168072462082 test_loss: 1.0546392440795898
epoch: 60 training_loss 1.8587839460372926 test_loss: 1.0557921409606934
epoch: 61 training_loss 1.8579984211921692 test_loss: 1.0745050430297851
epoch: 62 training_loss 1.7922867548465728 test_loss: 1.0612128257751465
epoch: 63 training_loss 1.7981032121181488 test_loss: 1.030298614501953
epoch: 64 training_loss 1.7957630002498626 test_loss: 1.0507566452026367
epoch: 65 training_loss 1.7696246790885926 test_loss: 1.045063591003418
epoch: 66 training_loss 1.7958404982089997 test_loss: 1.0182290077209473
epoch: 67 training_loss 1.7816520822048187 test_loss: 1.0297388076782226
epoch: 68 training_loss 1.7380717980861664 test_loss: 1.0269187927246093
epoch: 69 training_loss 1.7448440194129944 test_loss: 1.0057541847229003
epoch: 70 training_loss 1.722580828666687 test_loss: 1.0069021224975585
epoch: 71 training_loss 1.7545741021633148 test_loss: 1.0078442573547364
epoch: 72 training_loss 1.6857786071300507 test_loss: 0.9940018653869629
epoch: 73 training_loss 1.6879183948040009 test_loss: 1.0028797149658204
epoch: 74 training_loss 1.7042453575134278 test_loss: 0.9805405616760254
epoch: 75 training_loss 1.653900363445282 test_loss: 0.9882571220397949
epoch: 76 training_loss 1.6707565402984619 test_loss: 0.9819995880126953
epoch: 77 training_loss 1.6269483733177186 test_loss: 0.9849180221557617
epoch: 78 training_loss 1.6746947300434112 test_loss: 0.9621465682983399
epoch: 79 training_loss 1.6723794519901276 test_loss: 0.9760243415832519
epoch: 80 training_loss 1.6484722316265106 test_loss: 0.9666708946228028
epoch: 81 training_loss 1.6788140058517456 test_loss: 0.956658935546875
epoch: 82 training_loss 1.6031046438217162 test_loss: 0.9597366333007813
epoch: 83 training_loss 1.6403579366207124 test_loss: 0.9539725303649902
epoch: 84 training_loss 1.615469242334366 test_loss: 0.9650972366333008
epoch: 85 training_loss 1.620355758666992 test_loss: 0.9880675315856934
epoch: 86 training_loss 1.6168640887737273 test_loss: 0.9448371887207031
epoch: 87 training_loss 1.6329524898529053 test_loss: 0.9419414520263671
epoch: 88 training_loss 1.6246246325969695 test_loss: 0.9345835685729981
epoch: 89 training_loss 1.5944367027282715 test_loss: 0.9633643150329589
epoch: 90 training_loss 1.5755777060985565 test_loss: 0.9362211227416992
epoch: 91 training_loss 1.5885831570625306 test_loss: 0.9430985450744629
epoch: 92 training_loss 1.631962732076645 test_loss: 0.928856372833252
epoch: 93 training_loss 1.5791799759864806 test_loss: 0.9306134223937989
epoch: 94 training_loss 1.6014524173736573 test_loss: 0.9367846488952637
epoch: 95 training_loss 1.5690073108673095 test_loss: 0.9192990303039551
epoch: 96 training_loss 1.5999810993671417 test_loss: 0.9244172096252441
epoch: 97 training_loss 1.5482099056243896 test_loss: 0.9589095115661621
epoch: 98 training_loss 1.5316469621658326 test_loss: 0.9215797424316406
epoch: 99 training_loss 1.53131187915802 test_loss: 0.9242449760437011
epoch: 100 training_loss 1.527777316570282 test_loss: 0.910917854309082
epoch: 101 training_loss 1.576453663110733 test_loss: 0.9355340003967285
epoch: 102 training_loss 1.5433553493022918 test_loss: 0.918724536895752
epoch: 103 training_loss 1.561257063150406 test_loss: 0.9098511695861816
epoch: 104 training_loss 1.558416782617569 test_loss: 0.9145204544067382
epoch: 105 training_loss 1.5219759380817413 test_loss: 0.8990483283996582
epoch: 106 training_loss 1.4935267615318297 test_loss: 0.9022347450256347
epoch: 107 training_loss 1.5308989655971528 test_loss: 0.894682788848877
epoch: 108 training_loss 1.5249018621444703 test_loss: 0.9054603576660156
epoch: 109 training_loss 1.530099527835846 test_loss: 0.8997532844543457
epoch: 110 training_loss 1.5216471922397614 test_loss: 0.8957198143005372
epoch: 111 training_loss 1.5083737516403197 test_loss: 0.8896428108215332
epoch: 112 training_loss 1.5243949866294861 test_loss: 0.9089552879333496
epoch: 113 training_loss 1.521328066587448 test_loss: 0.8849871635437012
epoch: 114 training_loss 1.4948611426353455 test_loss: 0.8820975303649903
epoch: 115 training_loss 1.4755684340000152 test_loss: 0.9016985893249512
epoch: 116 training_loss 1.5196129322052 test_loss: 0.8812549591064454
epoch: 117 training_loss 1.4834271121025084 test_loss: 0.89130859375
epoch: 118 training_loss 1.4768594682216645 test_loss: 0.8773733139038086
epoch: 119 training_loss 1.514498074054718 test_loss: 0.8793503761291503
epoch: 120 training_loss 1.4600664007663726 test_loss: 0.8723769187927246
epoch: 121 training_loss 1.5130479121208191 test_loss: 0.8830842971801758
epoch: 122 training_loss 1.445386735200882 test_loss: 0.8715395927429199
epoch: 123 training_loss 1.4748619318008422 test_loss: 0.8652166366577149
epoch: 124 training_loss 1.437839959859848 test_loss: 0.8658616065979003
epoch: 125 training_loss 1.471577091217041 test_loss: 0.8688826560974121
epoch: 126 training_loss 1.4759414267539979 test_loss: 0.8581254005432128
epoch: 127 training_loss 1.4490295207500459 test_loss: 0.8567721366882324
epoch: 128 training_loss 1.4629520738124848 test_loss: 0.8652604103088379
epoch: 129 training_loss 1.4794003212451934 test_loss: 0.8712658882141113
epoch: 130 training_loss 1.443946579694748 test_loss: 0.9015688896179199
epoch: 131 training_loss 1.4612711894512176 test_loss: 0.8532924652099609
epoch: 132 training_loss 1.4270569384098053 test_loss: 0.8540822982788085
epoch: 133 training_loss 1.4396152555942536 test_loss: 0.8557334899902344
epoch: 134 training_loss 1.4454931449890136 test_loss: 0.843165111541748
epoch: 135 training_loss 1.4381702327728272 test_loss: 0.8411540031433106
epoch: 136 training_loss 1.4503861796855926 test_loss: 0.8481343269348145
epoch: 137 training_loss 1.4233897590637208 test_loss: 0.8402957916259766
epoch: 138 training_loss 1.4319409132003784 test_loss: 0.8432535171508789
epoch: 139 training_loss 1.4255387055873872 test_loss: 0.8396987915039062
epoch: 140 training_loss 1.4256044101715089 test_loss: 0.8426987648010253
epoch: 141 training_loss 1.3983507072925567 test_loss: 0.8303141593933105
epoch: 142 training_loss 1.4048236513137817 test_loss: 0.845455551147461
epoch: 143 training_loss 1.402440414428711 test_loss: 0.8355719566345214
epoch: 144 training_loss 1.391863386631012 test_loss: 0.8237592697143554
epoch: 145 training_loss 1.4056462228298188 test_loss: 0.8334256172180176
epoch: 146 training_loss 1.416523860692978 test_loss: 0.82986478805542
epoch: 147 training_loss 1.385644187927246 test_loss: 0.8254673957824707
epoch: 148 training_loss 1.4142627310752869 test_loss: 0.8234065055847168
epoch: 149 training_loss 1.4247608828544616 test_loss: 0.8385090827941895
5070.036828522911
episode: 0 training return: tensor(-43.4657, device='cuda:0')
episode: 1 training return: tensor(-70.5221, device='cuda:0')
episode: 2 training return: tensor(86.4012, device='cuda:0')
episode: 3 training return: tensor(153.5710, device='cuda:0')
epoch: 1 test_true_pfm: 5184.192479977196 sim_pfm: 126.7582865067913
episode: 4 training return: tensor(62.6500, device='cuda:0')
episode: 5 training return: tensor(162.2781, device='cuda:0')
episode: 6 training return: tensor(312.5262, device='cuda:0')
episode: 7 training return: tensor(66.7579, device='cuda:0')
epoch: 2 test_true_pfm: 5147.19221001551 sim_pfm: 79.26103832627025
episode: 8 training return: tensor(-92.6616, device='cuda:0')
episode: 9 training return: tensor(-28.8932, device='cuda:0')
episode: 10 training return: tensor(-101.0192, device='cuda:0')
episode: 11 training return: tensor(42.0576, device='cuda:0')
epoch: 3 test_true_pfm: 4978.6629781339725 sim_pfm: 116.61701143385532
episode: 12 training return: tensor(233.9799, device='cuda:0')
episode: 13 training return: tensor(164.7910, device='cuda:0')
episode: 14 training return: tensor(130.2061, device='cuda:0')
episode: 15 training return: tensor(-14.7043, device='cuda:0')
epoch: 4 test_true_pfm: 5128.9435766458855 sim_pfm: 98.93116465435985
episode: 16 training return: tensor(35.1336, device='cuda:0')
episode: 17 training return: tensor(34.9694, device='cuda:0')
episode: 18 training return: tensor(-88.9052, device='cuda:0')
episode: 19 training return: tensor(136.9212, device='cuda:0')
epoch: 5 test_true_pfm: 5180.379543941773 sim_pfm: 180.5851205928775
episode: 20 training return: tensor(169.6967, device='cuda:0')
episode: 21 training return: tensor(135.4660, device='cuda:0')
episode: 22 training return: tensor(24.0556, device='cuda:0')
episode: 23 training return: tensor(147.0334, device='cuda:0')
epoch: 6 test_true_pfm: 5089.607055410212 sim_pfm: 97.24074260345272
episode: 24 training return: tensor(117.4750, device='cuda:0')
episode: 25 training return: tensor(170.6980, device='cuda:0')
episode: 26 training return: tensor(-37.3606, device='cuda:0')
episode: 27 training return: tensor(48.4200, device='cuda:0')
epoch: 7 test_true_pfm: 5059.630272743704 sim_pfm: 145.84185712412
episode: 28 training return: tensor(197.2546, device='cuda:0')
episode: 29 training return: tensor(108.8041, device='cuda:0')
episode: 30 training return: tensor(-48.1168, device='cuda:0')
episode: 31 training return: tensor(73.1219, device='cuda:0')
epoch: 8 test_true_pfm: 5166.918802940572 sim_pfm: -28.648441480948048
episode: 32 training return: tensor(-30.7004, device='cuda:0')
episode: 33 training return: tensor(141.2823, device='cuda:0')
episode: 34 training return: tensor(19.5932, device='cuda:0')
episode: 35 training return: tensor(208.0076, device='cuda:0')
epoch: 9 test_true_pfm: 5129.953582154827 sim_pfm: 158.57791263610125
episode: 36 training return: tensor(-34.2456, device='cuda:0')
episode: 37 training return: tensor(-58.5866, device='cuda:0')
episode: 38 training return: tensor(244.7816, device='cuda:0')
episode: 39 training return: tensor(96.3504, device='cuda:0')
epoch: 10 test_true_pfm: 5128.899564205233 sim_pfm: 152.57843630888965
episode: 40 training return: tensor(38.0283, device='cuda:0')
episode: 41 training return: tensor(25.3565, device='cuda:0')
episode: 42 training return: tensor(11.2996, device='cuda:0')
episode: 43 training return: tensor(-0.7882, device='cuda:0')
epoch: 11 test_true_pfm: 5163.7296836127025 sim_pfm: 188.06411112581068
episode: 44 training return: tensor(-108.5977, device='cuda:0')
episode: 45 training return: tensor(-21.9687, device='cuda:0')
episode: 46 training return: tensor(146.3079, device='cuda:0')
episode: 47 training return: tensor(15.3790, device='cuda:0')
epoch: 12 test_true_pfm: 5254.631742810218 sim_pfm: 187.5909754257494
episode: 48 training return: tensor(-33.9612, device='cuda:0')
episode: 49 training return: tensor(389.3841, device='cuda:0')
episode: 50 training return: tensor(153.1818, device='cuda:0')
episode: 51 training return: tensor(-72.7884, device='cuda:0')
epoch: 13 test_true_pfm: 5300.658861267487 sim_pfm: 198.42359348984124
episode: 52 training return: tensor(102.4587, device='cuda:0')
episode: 53 training return: tensor(254.4772, device='cuda:0')
episode: 54 training return: tensor(-31.3924, device='cuda:0')
episode: 55 training return: tensor(116.5156, device='cuda:0')
epoch: 14 test_true_pfm: 5121.104159447002 sim_pfm: 199.54081951580397
episode: 56 training return: tensor(201.2035, device='cuda:0')
episode: 57 training return: tensor(216.1724, device='cuda:0')
episode: 58 training return: tensor(138.8825, device='cuda:0')
episode: 59 training return: tensor(88.0417, device='cuda:0')
epoch: 15 test_true_pfm: 5320.20597502321 sim_pfm: 149.3216790529162
episode: 60 training return: tensor(-117.1834, device='cuda:0')
episode: 61 training return: tensor(139.1664, device='cuda:0')
episode: 62 training return: tensor(203.7392, device='cuda:0')
episode: 63 training return: tensor(153.2612, device='cuda:0')
epoch: 16 test_true_pfm: 5302.579700157084 sim_pfm: 187.81267954665236
episode: 64 training return: tensor(192.3566, device='cuda:0')
episode: 65 training return: tensor(188.5312, device='cuda:0')
episode: 66 training return: tensor(-33.3796, device='cuda:0')
episode: 67 training return: tensor(168.2791, device='cuda:0')
epoch: 17 test_true_pfm: 5265.665930558096 sim_pfm: 357.8263631850714
episode: 68 training return: tensor(195.4842, device='cuda:0')
episode: 69 training return: tensor(204.1052, device='cuda:0')
episode: 70 training return: tensor(281.1188, device='cuda:0')
episode: 71 training return: tensor(16.5123, device='cuda:0')
epoch: 18 test_true_pfm: 5290.011715309379 sim_pfm: 325.3922884904314
episode: 72 training return: tensor(213.7366, device='cuda:0')
episode: 73 training return: tensor(351.8079, device='cuda:0')
episode: 74 training return: tensor(254.8367, device='cuda:0')
episode: 75 training return: tensor(227.1305, device='cuda:0')
epoch: 19 test_true_pfm: 5255.565004950901 sim_pfm: 281.5650586996926
episode: 76 training return: tensor(83.3048, device='cuda:0')
episode: 77 training return: tensor(244.3071, device='cuda:0')
episode: 78 training return: tensor(186.7249, device='cuda:0')
episode: 79 training return: tensor(297.6520, device='cuda:0')
epoch: 20 test_true_pfm: 5245.228799945608 sim_pfm: 358.3580904204864
episode: 80 training return: tensor(99.4494, device='cuda:0')
episode: 81 training return: tensor(235.8235, device='cuda:0')
episode: 82 training return: tensor(301.3520, device='cuda:0')
episode: 83 training return: tensor(134.1695, device='cuda:0')
epoch: 21 test_true_pfm: 5307.927464127931 sim_pfm: 359.15329833421856
episode: 84 training return: tensor(259.2112, device='cuda:0')
episode: 85 training return: tensor(216.6931, device='cuda:0')
episode: 86 training return: tensor(332.5186, device='cuda:0')
episode: 87 training return: tensor(220.4512, device='cuda:0')
epoch: 22 test_true_pfm: 5145.22166082211 sim_pfm: 308.43104544926126
episode: 88 training return: tensor(188.6568, device='cuda:0')
episode: 89 training return: tensor(220.7518, device='cuda:0')
episode: 90 training return: tensor(50.7792, device='cuda:0')
episode: 91 training return: tensor(232.4069, device='cuda:0')
epoch: 23 test_true_pfm: 5352.621425078162 sim_pfm: 311.378001228751
episode: 92 training return: tensor(67.9720, device='cuda:0')
episode: 93 training return: tensor(179.8139, device='cuda:0')
episode: 94 training return: tensor(321.3652, device='cuda:0')
episode: 95 training return: tensor(-8.1531, device='cuda:0')
epoch: 24 test_true_pfm: 5345.189295546515 sim_pfm: 295.70122763634816
episode: 96 training return: tensor(350.5737, device='cuda:0')
episode: 97 training return: tensor(390.7144, device='cuda:0')
episode: 98 training return: tensor(226.7500, device='cuda:0')
episode: 99 training return: tensor(222.4204, device='cuda:0')
epoch: 25 test_true_pfm: 5462.904943832215 sim_pfm: 435.7035563656439
episode: 100 training return: tensor(361.3705, device='cuda:0')
episode: 101 training return: tensor(135.4359, device='cuda:0')
episode: 102 training return: tensor(198.4949, device='cuda:0')
episode: 103 training return: tensor(244.1140, device='cuda:0')
epoch: 26 test_true_pfm: 5283.441275220312 sim_pfm: 351.32451548955095
episode: 104 training return: tensor(304.1801, device='cuda:0')
episode: 105 training return: tensor(126.8674, device='cuda:0')
episode: 106 training return: tensor(184.5207, device='cuda:0')
episode: 107 training return: tensor(135.9045, device='cuda:0')
epoch: 27 test_true_pfm: 5368.1219493730805 sim_pfm: 315.7432013261229
episode: 108 training return: tensor(118.7912, device='cuda:0')
episode: 109 training return: tensor(216.4150, device='cuda:0')
episode: 110 training return: tensor(133.9840, device='cuda:0')
episode: 111 training return: tensor(236.5391, device='cuda:0')
epoch: 28 test_true_pfm: 5399.7205718624555 sim_pfm: 303.34095283516217
episode: 112 training return: tensor(389.9641, device='cuda:0')
episode: 113 training return: tensor(241.5323, device='cuda:0')
episode: 114 training return: tensor(402.4709, device='cuda:0')
episode: 115 training return: tensor(346.2539, device='cuda:0')
epoch: 29 test_true_pfm: 5396.1493012923975 sim_pfm: 402.63223651299876
episode: 116 training return: tensor(190.9521, device='cuda:0')
episode: 117 training return: tensor(196.8121, device='cuda:0')
episode: 118 training return: tensor(359.2436, device='cuda:0')
episode: 119 training return: tensor(262.8089, device='cuda:0')
epoch: 30 test_true_pfm: 5402.155732453187 sim_pfm: 448.47861203718156
episode: 120 training return: tensor(108.6515, device='cuda:0')
episode: 121 training return: tensor(403.6801, device='cuda:0')
episode: 122 training return: tensor(306.4737, device='cuda:0')
episode: 123 training return: tensor(312.8481, device='cuda:0')
epoch: 31 test_true_pfm: 5558.782060246434 sim_pfm: 365.4277641143805
episode: 124 training return: tensor(243.1761, device='cuda:0')
episode: 125 training return: tensor(191.6684, device='cuda:0')
episode: 126 training return: tensor(260.4431, device='cuda:0')
episode: 127 training return: tensor(212.1093, device='cuda:0')
epoch: 32 test_true_pfm: 5345.633603081722 sim_pfm: 448.2648923951977
episode: 128 training return: tensor(351.5402, device='cuda:0')
episode: 129 training return: tensor(276.0291, device='cuda:0')
episode: 130 training return: tensor(413.7620, device='cuda:0')
episode: 131 training return: tensor(383.3325, device='cuda:0')
epoch: 33 test_true_pfm: 5462.909012240713 sim_pfm: 313.1624568164989
episode: 132 training return: tensor(241.7699, device='cuda:0')
episode: 133 training return: tensor(348.5408, device='cuda:0')
episode: 134 training return: tensor(47.2983, device='cuda:0')
episode: 135 training return: tensor(286.0154, device='cuda:0')
epoch: 34 test_true_pfm: 5312.727077155023 sim_pfm: 404.8890339761662
episode: 136 training return: tensor(352.5425, device='cuda:0')
episode: 137 training return: tensor(128.8534, device='cuda:0')
episode: 138 training return: tensor(138.9102, device='cuda:0')
episode: 139 training return: tensor(193.3963, device='cuda:0')
epoch: 35 test_true_pfm: 5312.461107629744 sim_pfm: 355.6494569449763
episode: 140 training return: tensor(308.3537, device='cuda:0')
episode: 141 training return: tensor(289.5945, device='cuda:0')
episode: 142 training return: tensor(404.8505, device='cuda:0')
episode: 143 training return: tensor(322.1858, device='cuda:0')
epoch: 36 test_true_pfm: 5441.019561016987 sim_pfm: 503.9135935031809
episode: 144 training return: tensor(239.3415, device='cuda:0')
episode: 145 training return: tensor(383.1810, device='cuda:0')
episode: 146 training return: tensor(358.1852, device='cuda:0')
episode: 147 training return: tensor(65.4233, device='cuda:0')
epoch: 37 test_true_pfm: 5310.840368159318 sim_pfm: 402.92578064717236
episode: 148 training return: tensor(333.5613, device='cuda:0')
episode: 149 training return: tensor(432.2489, device='cuda:0')
episode: 150 training return: tensor(412.4462, device='cuda:0')
episode: 151 training return: tensor(300.4209, device='cuda:0')
epoch: 38 test_true_pfm: 5424.234712006478 sim_pfm: 401.36990488134325
episode: 152 training return: tensor(362.9644, device='cuda:0')
episode: 153 training return: tensor(309.7706, device='cuda:0')
episode: 154 training return: tensor(356.8149, device='cuda:0')
episode: 155 training return: tensor(332.3715, device='cuda:0')
epoch: 39 test_true_pfm: 4764.231845017235 sim_pfm: 363.17704100487754
episode: 156 training return: tensor(353.2978, device='cuda:0')
episode: 157 training return: tensor(270.2980, device='cuda:0')
episode: 158 training return: tensor(443.3344, device='cuda:0')
episode: 159 training return: tensor(393.5217, device='cuda:0')
epoch: 40 test_true_pfm: 5530.674815283298 sim_pfm: 449.4766053095809
episode: 160 training return: tensor(290.4790, device='cuda:0')
episode: 161 training return: tensor(353.6913, device='cuda:0')
episode: 162 training return: tensor(304.4149, device='cuda:0')
episode: 163 training return: tensor(491.5953, device='cuda:0')
epoch: 41 test_true_pfm: 5546.855178748437 sim_pfm: 593.7790049309842
episode: 164 training return: tensor(189.5527, device='cuda:0')
episode: 165 training return: tensor(257.6592, device='cuda:0')
episode: 166 training return: tensor(358.7823, device='cuda:0')
episode: 167 training return: tensor(211.8556, device='cuda:0')
epoch: 42 test_true_pfm: 5440.85160786058 sim_pfm: 493.1642416793038
episode: 168 training return: tensor(500.1638, device='cuda:0')
episode: 169 training return: tensor(443.5232, device='cuda:0')
episode: 170 training return: tensor(189.5970, device='cuda:0')
episode: 171 training return: tensor(227.2060, device='cuda:0')
epoch: 43 test_true_pfm: 5490.750376989777 sim_pfm: 324.5034668032701
episode: 172 training return: tensor(479.5444, device='cuda:0')
episode: 173 training return: tensor(330.7651, device='cuda:0')
episode: 174 training return: tensor(416.1653, device='cuda:0')
episode: 175 training return: tensor(346.1168, device='cuda:0')
epoch: 44 test_true_pfm: 5528.08647294568 sim_pfm: 439.89379273048445
episode: 176 training return: tensor(331.7765, device='cuda:0')
episode: 177 training return: tensor(393.6882, device='cuda:0')
episode: 178 training return: tensor(286.8627, device='cuda:0')
episode: 179 training return: tensor(321.6624, device='cuda:0')
epoch: 45 test_true_pfm: 5404.314137878979 sim_pfm: 409.9047236715948
episode: 180 training return: tensor(216.4661, device='cuda:0')
episode: 181 training return: tensor(373.3397, device='cuda:0')
episode: 182 training return: tensor(280.1770, device='cuda:0')
episode: 183 training return: tensor(475.0992, device='cuda:0')
epoch: 46 test_true_pfm: 5532.093944687632 sim_pfm: 426.5277119749614
episode: 184 training return: tensor(358.0071, device='cuda:0')
episode: 185 training return: tensor(285.6908, device='cuda:0')
episode: 186 training return: tensor(213.3223, device='cuda:0')
episode: 187 training return: tensor(199.9405, device='cuda:0')
epoch: 47 test_true_pfm: 5463.809169780304 sim_pfm: 478.6035852048274
episode: 188 training return: tensor(470.7245, device='cuda:0')
episode: 189 training return: tensor(379.2006, device='cuda:0')
episode: 190 training return: tensor(148.9615, device='cuda:0')
episode: 191 training return: tensor(353.9692, device='cuda:0')
epoch: 48 test_true_pfm: 5544.285683864294 sim_pfm: 392.90074752894
episode: 192 training return: tensor(393.7570, device='cuda:0')
episode: 193 training return: tensor(305.5415, device='cuda:0')
episode: 194 training return: tensor(497.2698, device='cuda:0')
episode: 195 training return: tensor(433.8311, device='cuda:0')
epoch: 49 test_true_pfm: 5515.210460179037 sim_pfm: 466.76842559951666
episode: 196 training return: tensor(260.8983, device='cuda:0')
episode: 197 training return: tensor(322.1763, device='cuda:0')
episode: 198 training return: tensor(154.6057, device='cuda:0')
episode: 199 training return: tensor(361.8585, device='cuda:0')
epoch: 50 test_true_pfm: 5411.9396691583015 sim_pfm: 514.4567790198101
episode: 200 training return: tensor(445.7232, device='cuda:0')
episode: 201 training return: tensor(457.1419, device='cuda:0')
episode: 202 training return: tensor(325.3551, device='cuda:0')
episode: 203 training return: tensor(402.1697, device='cuda:0')
epoch: 51 test_true_pfm: 5396.661959497588 sim_pfm: 549.5565529981977
episode: 204 training return: tensor(493.3616, device='cuda:0')
episode: 205 training return: tensor(435.2686, device='cuda:0')
episode: 206 training return: tensor(375.8623, device='cuda:0')
episode: 207 training return: tensor(425.7538, device='cuda:0')
epoch: 52 test_true_pfm: 5563.296010541701 sim_pfm: 484.02034366480075
episode: 208 training return: tensor(323.3708, device='cuda:0')
episode: 209 training return: tensor(289.8854, device='cuda:0')
episode: 210 training return: tensor(441.1462, device='cuda:0')
episode: 211 training return: tensor(379.8244, device='cuda:0')
epoch: 53 test_true_pfm: 5527.855597229477 sim_pfm: 505.2601124898065
episode: 212 training return: tensor(297.3709, device='cuda:0')
episode: 213 training return: tensor(374.7021, device='cuda:0')
episode: 214 training return: tensor(419.8740, device='cuda:0')
episode: 215 training return: tensor(284.5069, device='cuda:0')
epoch: 54 test_true_pfm: 5587.870449086459 sim_pfm: 511.263462416168
episode: 216 training return: tensor(362.2197, device='cuda:0')
episode: 217 training return: tensor(231.2765, device='cuda:0')
episode: 218 training return: tensor(355.2119, device='cuda:0')
episode: 219 training return: tensor(278.1802, device='cuda:0')
epoch: 55 test_true_pfm: 5533.20261701048 sim_pfm: 493.8228198439853
episode: 220 training return: tensor(347.3265, device='cuda:0')
episode: 221 training return: tensor(345.0547, device='cuda:0')
episode: 222 training return: tensor(485.2333, device='cuda:0')
episode: 223 training return: tensor(155.9485, device='cuda:0')
epoch: 56 test_true_pfm: 5576.292406935274 sim_pfm: 553.3858539731785
episode: 224 training return: tensor(452.9653, device='cuda:0')
episode: 225 training return: tensor(351.8209, device='cuda:0')
episode: 226 training return: tensor(301.8409, device='cuda:0')
episode: 227 training return: tensor(261.8110, device='cuda:0')
epoch: 57 test_true_pfm: 5499.3012577613745 sim_pfm: 497.0595255026322
episode: 228 training return: tensor(463.1495, device='cuda:0')
episode: 229 training return: tensor(406.2609, device='cuda:0')
episode: 230 training return: tensor(359.4597, device='cuda:0')
episode: 231 training return: tensor(447.4438, device='cuda:0')
epoch: 58 test_true_pfm: 5518.20888282302 sim_pfm: 489.51968719274737
episode: 232 training return: tensor(376.7415, device='cuda:0')
episode: 233 training return: tensor(247.1161, device='cuda:0')
episode: 234 training return: tensor(304.0319, device='cuda:0')
episode: 235 training return: tensor(266.5669, device='cuda:0')
epoch: 59 test_true_pfm: 5572.126187300538 sim_pfm: 518.9893434693804
episode: 236 training return: tensor(438.4344, device='cuda:0')
episode: 237 training return: tensor(426.0915, device='cuda:0')
episode: 238 training return: tensor(444.3892, device='cuda:0')
episode: 239 training return: tensor(572.5300, device='cuda:0')
epoch: 60 test_true_pfm: 5532.319309426956 sim_pfm: 542.3823248303185
episode: 240 training return: tensor(235.6725, device='cuda:0')
episode: 241 training return: tensor(301.7255, device='cuda:0')
episode: 242 training return: tensor(532.4225, device='cuda:0')
episode: 243 training return: tensor(385.7457, device='cuda:0')
epoch: 61 test_true_pfm: 5628.779480760289 sim_pfm: 503.78504860538914
episode: 244 training return: tensor(397.2391, device='cuda:0')
episode: 245 training return: tensor(287.0123, device='cuda:0')
episode: 246 training return: tensor(396.8659, device='cuda:0')
episode: 247 training return: tensor(408.9013, device='cuda:0')
epoch: 62 test_true_pfm: 5528.693808897042 sim_pfm: 522.4641799374949
episode: 248 training return: tensor(328.6552, device='cuda:0')
episode: 249 training return: tensor(336.5005, device='cuda:0')
episode: 250 training return: tensor(383.2517, device='cuda:0')
episode: 251 training return: tensor(328.4747, device='cuda:0')
epoch: 63 test_true_pfm: 5526.4673909006115 sim_pfm: 530.857043155857
episode: 252 training return: tensor(375.7827, device='cuda:0')
episode: 253 training return: tensor(288.1570, device='cuda:0')
episode: 254 training return: tensor(399.5400, device='cuda:0')
episode: 255 training return: tensor(197.2691, device='cuda:0')
epoch: 64 test_true_pfm: 5648.191171113605 sim_pfm: 597.2873640168303
episode: 256 training return: tensor(463.4075, device='cuda:0')
episode: 257 training return: tensor(371.8257, device='cuda:0')
episode: 258 training return: tensor(392.4660, device='cuda:0')
episode: 259 training return: tensor(260.1509, device='cuda:0')
epoch: 65 test_true_pfm: 5573.416748032815 sim_pfm: 543.8690471203687
episode: 260 training return: tensor(342.4821, device='cuda:0')
episode: 261 training return: tensor(446.0626, device='cuda:0')
episode: 262 training return: tensor(293.6003, device='cuda:0')
episode: 263 training return: tensor(332.9584, device='cuda:0')
epoch: 66 test_true_pfm: 5594.9532254984515 sim_pfm: 590.32625216494
episode: 264 training return: tensor(533.7145, device='cuda:0')
episode: 265 training return: tensor(451.8639, device='cuda:0')
episode: 266 training return: tensor(363.8749, device='cuda:0')
episode: 267 training return: tensor(583.5033, device='cuda:0')
epoch: 67 test_true_pfm: 5576.626218276753 sim_pfm: 582.6977170281656
episode: 268 training return: tensor(489.4655, device='cuda:0')
episode: 269 training return: tensor(616.6912, device='cuda:0')
episode: 270 training return: tensor(537.8980, device='cuda:0')
episode: 271 training return: tensor(450.0181, device='cuda:0')
epoch: 68 test_true_pfm: 5638.797050508518 sim_pfm: 563.3032255903527
episode: 272 training return: tensor(328.0564, device='cuda:0')
episode: 273 training return: tensor(330.2206, device='cuda:0')
episode: 274 training return: tensor(429.5139, device='cuda:0')
episode: 275 training return: tensor(478.3856, device='cuda:0')
epoch: 69 test_true_pfm: 5593.52555355686 sim_pfm: 569.0614180333602
episode: 276 training return: tensor(489.6196, device='cuda:0')
episode: 277 training return: tensor(375.2169, device='cuda:0')
episode: 278 training return: tensor(359.7302, device='cuda:0')
episode: 279 training return: tensor(398.1233, device='cuda:0')
epoch: 70 test_true_pfm: 5552.6229455778375 sim_pfm: 545.7977235163562
episode: 280 training return: tensor(393.1515, device='cuda:0')
episode: 281 training return: tensor(496.5103, device='cuda:0')
episode: 282 training return: tensor(425.9523, device='cuda:0')
episode: 283 training return: tensor(247.8572, device='cuda:0')
epoch: 71 test_true_pfm: 5682.569873462777 sim_pfm: 438.00499509220634
episode: 284 training return: tensor(318.6553, device='cuda:0')
episode: 285 training return: tensor(453.8936, device='cuda:0')
episode: 286 training return: tensor(380.4858, device='cuda:0')
episode: 287 training return: tensor(276.8230, device='cuda:0')
epoch: 72 test_true_pfm: 5605.913499343147 sim_pfm: 594.5448919799722
episode: 288 training return: tensor(391.3788, device='cuda:0')
episode: 289 training return: tensor(377.0396, device='cuda:0')
episode: 290 training return: tensor(394.0911, device='cuda:0')
episode: 291 training return: tensor(354.1076, device='cuda:0')
epoch: 73 test_true_pfm: 5627.293319163012 sim_pfm: 472.7918607537479
episode: 292 training return: tensor(567.4454, device='cuda:0')
episode: 293 training return: tensor(501.5332, device='cuda:0')
episode: 294 training return: tensor(488.7286, device='cuda:0')
episode: 295 training return: tensor(409.8980, device='cuda:0')
epoch: 74 test_true_pfm: 5569.806322321428 sim_pfm: 619.8353330780907
episode: 296 training return: tensor(234.6132, device='cuda:0')
episode: 297 training return: tensor(372.2316, device='cuda:0')
episode: 298 training return: tensor(336.2812, device='cuda:0')
episode: 299 training return: tensor(485.9129, device='cuda:0')
epoch: 75 test_true_pfm: 5628.2080688442065 sim_pfm: 630.472241879596
episode: 300 training return: tensor(387.5652, device='cuda:0')
episode: 301 training return: tensor(427.8613, device='cuda:0')
episode: 302 training return: tensor(461.0606, device='cuda:0')
episode: 303 training return: tensor(400.6646, device='cuda:0')
epoch: 76 test_true_pfm: 5661.913724651949 sim_pfm: 587.9897017649297
episode: 304 training return: tensor(444.4068, device='cuda:0')
episode: 305 training return: tensor(506.8394, device='cuda:0')
episode: 306 training return: tensor(478.4366, device='cuda:0')
episode: 307 training return: tensor(555.1970, device='cuda:0')
epoch: 77 test_true_pfm: 5625.440300520014 sim_pfm: 604.389098975303
episode: 308 training return: tensor(389.2449, device='cuda:0')
episode: 309 training return: tensor(322.5287, device='cuda:0')
episode: 310 training return: tensor(509.7779, device='cuda:0')
episode: 311 training return: tensor(544.2732, device='cuda:0')
epoch: 78 test_true_pfm: 5632.89614656254 sim_pfm: 570.3231604673589
episode: 312 training return: tensor(432.0863, device='cuda:0')
episode: 313 training return: tensor(268.1181, device='cuda:0')
episode: 314 training return: tensor(526.5496, device='cuda:0')
episode: 315 training return: tensor(214.8284, device='cuda:0')
epoch: 79 test_true_pfm: 5741.776068915995 sim_pfm: 637.4398208997251
episode: 316 training return: tensor(452.7445, device='cuda:0')
episode: 317 training return: tensor(377.5846, device='cuda:0')
episode: 318 training return: tensor(511.9511, device='cuda:0')
episode: 319 training return: tensor(319.2378, device='cuda:0')
epoch: 80 test_true_pfm: 5655.166873990612 sim_pfm: 514.8659298136384
episode: 320 training return: tensor(337.5558, device='cuda:0')
episode: 321 training return: tensor(298.7737, device='cuda:0')
episode: 322 training return: tensor(436.2570, device='cuda:0')
episode: 323 training return: tensor(468.3841, device='cuda:0')
epoch: 81 test_true_pfm: 5697.471865886543 sim_pfm: 628.0136848838301
episode: 324 training return: tensor(-35.7307, device='cuda:0')
episode: 325 training return: tensor(314.2718, device='cuda:0')
episode: 326 training return: tensor(368.1626, device='cuda:0')
episode: 327 training return: tensor(551.1589, device='cuda:0')
epoch: 82 test_true_pfm: 5651.819209658461 sim_pfm: 601.9218240392705
episode: 328 training return: tensor(424.6508, device='cuda:0')
episode: 329 training return: tensor(376.6735, device='cuda:0')
episode: 330 training return: tensor(648.8118, device='cuda:0')
episode: 331 training return: tensor(444.2089, device='cuda:0')
epoch: 83 test_true_pfm: 5631.057634641486 sim_pfm: 541.0956320458403
episode: 332 training return: tensor(378.1103, device='cuda:0')
episode: 333 training return: tensor(476.6937, device='cuda:0')
episode: 334 training return: tensor(310.4653, device='cuda:0')
episode: 335 training return: tensor(565.4600, device='cuda:0')
epoch: 84 test_true_pfm: 5596.580150096252 sim_pfm: 631.2565601605456
episode: 336 training return: tensor(538.0925, device='cuda:0')
episode: 337 training return: tensor(522.2935, device='cuda:0')
episode: 338 training return: tensor(288.5040, device='cuda:0')
episode: 339 training return: tensor(548.7552, device='cuda:0')
epoch: 85 test_true_pfm: 5668.30879543543 sim_pfm: 601.1625453875167
episode: 340 training return: tensor(345.7442, device='cuda:0')
episode: 341 training return: tensor(420.1535, device='cuda:0')
episode: 342 training return: tensor(516.9575, device='cuda:0')
episode: 343 training return: tensor(387.6090, device='cuda:0')
epoch: 86 test_true_pfm: 5654.868356624177 sim_pfm: 582.2783028240083
episode: 344 training return: tensor(-333.4318, device='cuda:0')
episode: 345 training return: tensor(456.7367, device='cuda:0')
episode: 346 training return: tensor(342.8798, device='cuda:0')
episode: 347 training return: tensor(355.4691, device='cuda:0')
epoch: 87 test_true_pfm: 5700.228526216843 sim_pfm: 606.7867979810107
episode: 348 training return: tensor(524.9316, device='cuda:0')
episode: 349 training return: tensor(488.0688, device='cuda:0')
episode: 350 training return: tensor(338.9738, device='cuda:0')
episode: 351 training return: tensor(403.9341, device='cuda:0')
epoch: 88 test_true_pfm: 5621.772996480656 sim_pfm: 588.0705064362846
episode: 352 training return: tensor(384.9383, device='cuda:0')
episode: 353 training return: tensor(498.1173, device='cuda:0')
episode: 354 training return: tensor(481.3974, device='cuda:0')
episode: 355 training return: tensor(432.6210, device='cuda:0')
epoch: 89 test_true_pfm: 5641.250552733225 sim_pfm: 573.7793454661345
episode: 356 training return: tensor(424.1770, device='cuda:0')
episode: 357 training return: tensor(477.1559, device='cuda:0')
episode: 358 training return: tensor(584.5658, device='cuda:0')
episode: 359 training return: tensor(558.6407, device='cuda:0')
epoch: 90 test_true_pfm: 5603.3805788816835 sim_pfm: 598.9791715570027
episode: 360 training return: tensor(530.8329, device='cuda:0')
episode: 361 training return: tensor(453.2498, device='cuda:0')
episode: 362 training return: tensor(511.9284, device='cuda:0')
episode: 363 training return: tensor(399.2855, device='cuda:0')
epoch: 91 test_true_pfm: 5704.7306482338345 sim_pfm: 566.6673248958541
episode: 364 training return: tensor(455.1865, device='cuda:0')
episode: 365 training return: tensor(468.9304, device='cuda:0')
episode: 366 training return: tensor(517.5725, device='cuda:0')
episode: 367 training return: tensor(444.7894, device='cuda:0')
epoch: 92 test_true_pfm: 5659.836511655422 sim_pfm: 566.6837799959467
episode: 368 training return: tensor(452.3561, device='cuda:0')
episode: 369 training return: tensor(475.0409, device='cuda:0')
episode: 370 training return: tensor(567.3834, device='cuda:0')
episode: 371 training return: tensor(538.3344, device='cuda:0')
epoch: 93 test_true_pfm: 5666.529597451823 sim_pfm: 601.544662228281
episode: 372 training return: tensor(568.6583, device='cuda:0')
episode: 373 training return: tensor(479.7504, device='cuda:0')
episode: 374 training return: tensor(488.2847, device='cuda:0')
episode: 375 training return: tensor(490.0241, device='cuda:0')
epoch: 94 test_true_pfm: 5627.729339988405 sim_pfm: 618.2291532840172
episode: 376 training return: tensor(463.6462, device='cuda:0')
episode: 377 training return: tensor(440.8326, device='cuda:0')
episode: 378 training return: tensor(473.5226, device='cuda:0')
episode: 379 training return: tensor(310.1881, device='cuda:0')
epoch: 95 test_true_pfm: 5751.0706451487895 sim_pfm: 573.8583301979719
episode: 380 training return: tensor(393.8370, device='cuda:0')
episode: 381 training return: tensor(370.7480, device='cuda:0')
episode: 382 training return: tensor(426.6522, device='cuda:0')
episode: 383 training return: tensor(556.7850, device='cuda:0')
epoch: 96 test_true_pfm: 5681.85035816885 sim_pfm: 545.601223761371
episode: 384 training return: tensor(529.5483, device='cuda:0')
episode: 385 training return: tensor(547.8570, device='cuda:0')
episode: 386 training return: tensor(451.5742, device='cuda:0')
episode: 387 training return: tensor(489.7291, device='cuda:0')
epoch: 97 test_true_pfm: 5659.0035134222935 sim_pfm: 539.2921937518598
episode: 388 training return: tensor(520.1054, device='cuda:0')
episode: 389 training return: tensor(512.8265, device='cuda:0')
episode: 390 training return: tensor(537.8246, device='cuda:0')
episode: 391 training return: tensor(432.2178, device='cuda:0')
epoch: 98 test_true_pfm: 5606.7091133092 sim_pfm: 530.2063641794181
episode: 392 training return: tensor(309.2503, device='cuda:0')
episode: 393 training return: tensor(555.0878, device='cuda:0')
episode: 394 training return: tensor(641.5363, device='cuda:0')
episode: 395 training return: tensor(590.2504, device='cuda:0')
epoch: 99 test_true_pfm: 5655.592678904399 sim_pfm: 515.7735208193772
episode: 396 training return: tensor(525.2567, device='cuda:0')
episode: 397 training return: tensor(522.1122, device='cuda:0')
episode: 398 training return: tensor(505.8164, device='cuda:0')
episode: 399 training return: tensor(457.9509, device='cuda:0')
epoch: 100 test_true_pfm: 5767.156272322183 sim_pfm: 656.1302678063512
episode: 400 training return: tensor(540.5643, device='cuda:0')
episode: 401 training return: tensor(444.2565, device='cuda:0')
episode: 402 training return: tensor(559.5771, device='cuda:0')
episode: 403 training return: tensor(429.7300, device='cuda:0')
epoch: 101 test_true_pfm: 5625.110756161412 sim_pfm: 616.3050357761676
episode: 404 training return: tensor(424.1819, device='cuda:0')
episode: 405 training return: tensor(492.3034, device='cuda:0')
episode: 406 training return: tensor(399.7511, device='cuda:0')
episode: 407 training return: tensor(440.0339, device='cuda:0')
epoch: 102 test_true_pfm: 5733.555218926446 sim_pfm: 610.1919758305885
episode: 408 training return: tensor(568.4517, device='cuda:0')
episode: 409 training return: tensor(497.7481, device='cuda:0')
episode: 410 training return: tensor(477.7017, device='cuda:0')
episode: 411 training return: tensor(380.6485, device='cuda:0')
epoch: 103 test_true_pfm: 5707.719048683767 sim_pfm: 708.4468990604704
episode: 412 training return: tensor(571.8485, device='cuda:0')
episode: 413 training return: tensor(626.9416, device='cuda:0')
episode: 414 training return: tensor(413.2978, device='cuda:0')
episode: 415 training return: tensor(610.2650, device='cuda:0')
epoch: 104 test_true_pfm: 5525.036057694301 sim_pfm: 581.4637022512421
episode: 416 training return: tensor(258.6377, device='cuda:0')
episode: 417 training return: tensor(396.9529, device='cuda:0')
episode: 418 training return: tensor(383.5763, device='cuda:0')
episode: 419 training return: tensor(531.0380, device='cuda:0')
epoch: 105 test_true_pfm: 5660.468018475546 sim_pfm: 563.2819636321316
episode: 420 training return: tensor(602.6906, device='cuda:0')
episode: 421 training return: tensor(452.8752, device='cuda:0')
episode: 422 training return: tensor(475.6620, device='cuda:0')
episode: 423 training return: tensor(-643.8382, device='cuda:0')
epoch: 106 test_true_pfm: 5714.5718678975145 sim_pfm: 552.6134394551627
episode: 424 training return: tensor(452.7165, device='cuda:0')
episode: 425 training return: tensor(426.7939, device='cuda:0')
episode: 426 training return: tensor(547.8935, device='cuda:0')
episode: 427 training return: tensor(498.4373, device='cuda:0')
epoch: 107 test_true_pfm: 5750.480233101399 sim_pfm: 629.3345896434427
episode: 428 training return: tensor(504.2684, device='cuda:0')
episode: 429 training return: tensor(490.7774, device='cuda:0')
episode: 430 training return: tensor(383.6397, device='cuda:0')
episode: 431 training return: tensor(420.9816, device='cuda:0')
epoch: 108 test_true_pfm: 5553.618673900425 sim_pfm: 539.2417446757512
episode: 432 training return: tensor(414.2777, device='cuda:0')
episode: 433 training return: tensor(404.0661, device='cuda:0')
episode: 434 training return: tensor(481.3887, device='cuda:0')
episode: 435 training return: tensor(447.5168, device='cuda:0')
epoch: 109 test_true_pfm: 5670.1885649626865 sim_pfm: 575.225752110302
episode: 436 training return: tensor(393.4676, device='cuda:0')
episode: 437 training return: tensor(449.7655, device='cuda:0')
episode: 438 training return: tensor(398.3717, device='cuda:0')
episode: 439 training return: tensor(530.3265, device='cuda:0')
epoch: 110 test_true_pfm: 5689.727734833295 sim_pfm: 633.2228334834411
episode: 440 training return: tensor(606.6688, device='cuda:0')
episode: 441 training return: tensor(482.6759, device='cuda:0')
episode: 442 training return: tensor(546.6331, device='cuda:0')
episode: 443 training return: tensor(452.4081, device='cuda:0')
epoch: 111 test_true_pfm: 5624.843320322427 sim_pfm: 560.9218477144992
episode: 444 training return: tensor(556.5790, device='cuda:0')
episode: 445 training return: tensor(506.6195, device='cuda:0')
episode: 446 training return: tensor(611.5868, device='cuda:0')
episode: 447 training return: tensor(474.5854, device='cuda:0')
epoch: 112 test_true_pfm: 5651.445979147968 sim_pfm: 616.5842374155958
episode: 448 training return: tensor(495.3906, device='cuda:0')
episode: 449 training return: tensor(617.3727, device='cuda:0')
episode: 450 training return: tensor(442.2087, device='cuda:0')
episode: 451 training return: tensor(672.1821, device='cuda:0')
epoch: 113 test_true_pfm: 5683.071125239488 sim_pfm: 609.5238281027414
episode: 452 training return: tensor(576.4423, device='cuda:0')
episode: 453 training return: tensor(485.7753, device='cuda:0')
episode: 454 training return: tensor(420.3921, device='cuda:0')
episode: 455 training return: tensor(448.5740, device='cuda:0')
epoch: 114 test_true_pfm: 5650.388894626784 sim_pfm: 636.6717759839763
episode: 456 training return: tensor(464.4399, device='cuda:0')
episode: 457 training return: tensor(553.9567, device='cuda:0')
episode: 458 training return: tensor(489.9997, device='cuda:0')
episode: 459 training return: tensor(489.0943, device='cuda:0')
epoch: 115 test_true_pfm: 5668.502807204008 sim_pfm: 615.1435871276577
episode: 460 training return: tensor(512.3255, device='cuda:0')
episode: 461 training return: tensor(487.3032, device='cuda:0')
episode: 462 training return: tensor(449.7377, device='cuda:0')
episode: 463 training return: tensor(454.7737, device='cuda:0')
epoch: 116 test_true_pfm: 5680.0045045843835 sim_pfm: 639.2689703584183
episode: 464 training return: tensor(479.0067, device='cuda:0')
episode: 465 training return: tensor(419.9668, device='cuda:0')
episode: 466 training return: tensor(541.2852, device='cuda:0')
episode: 467 training return: tensor(474.5499, device='cuda:0')
epoch: 117 test_true_pfm: 5699.395608257557 sim_pfm: 619.0651393821463
episode: 468 training return: tensor(558.9617, device='cuda:0')
episode: 469 training return: tensor(414.3249, device='cuda:0')
episode: 470 training return: tensor(510.9427, device='cuda:0')
episode: 471 training return: tensor(528.8635, device='cuda:0')
epoch: 118 test_true_pfm: 5805.893290066313 sim_pfm: 597.5574699052377
episode: 472 training return: tensor(558.6804, device='cuda:0')
episode: 473 training return: tensor(606.5128, device='cuda:0')
episode: 474 training return: tensor(645.8782, device='cuda:0')
episode: 475 training return: tensor(529.8801, device='cuda:0')
epoch: 119 test_true_pfm: 5650.322835747822 sim_pfm: 661.8539180032288
episode: 476 training return: tensor(540.6681, device='cuda:0')
episode: 477 training return: tensor(370.9668, device='cuda:0')
episode: 478 training return: tensor(521.1606, device='cuda:0')
episode: 479 training return: tensor(462.3325, device='cuda:0')
epoch: 120 test_true_pfm: 5650.081443431856 sim_pfm: 597.887538757796
episode: 480 training return: tensor(494.4158, device='cuda:0')
episode: 481 training return: tensor(450.5810, device='cuda:0')
episode: 482 training return: tensor(570.2847, device='cuda:0')
episode: 483 training return: tensor(386.4572, device='cuda:0')
epoch: 121 test_true_pfm: 5720.258148715767 sim_pfm: 616.3001155939419
episode: 484 training return: tensor(567.2026, device='cuda:0')
episode: 485 training return: tensor(511.3596, device='cuda:0')
episode: 486 training return: tensor(582.9163, device='cuda:0')
episode: 487 training return: tensor(473.2300, device='cuda:0')
epoch: 122 test_true_pfm: 5736.294460777001 sim_pfm: 605.5270063166972
episode: 488 training return: tensor(431.5065, device='cuda:0')
episode: 489 training return: tensor(498.2921, device='cuda:0')
episode: 490 training return: tensor(546.9429, device='cuda:0')
episode: 491 training return: tensor(476.9774, device='cuda:0')
epoch: 123 test_true_pfm: 5674.5831326863445 sim_pfm: 627.4269352213402
episode: 492 training return: tensor(403.7701, device='cuda:0')
episode: 493 training return: tensor(455.5889, device='cuda:0')
episode: 494 training return: tensor(406.4619, device='cuda:0')
episode: 495 training return: tensor(545.7432, device='cuda:0')
epoch: 124 test_true_pfm: 5761.388399698747 sim_pfm: 610.1858481855597
episode: 496 training return: tensor(548.9135, device='cuda:0')
episode: 497 training return: tensor(458.9173, device='cuda:0')
episode: 498 training return: tensor(431.0080, device='cuda:0')
episode: 499 training return: tensor(606.1153, device='cuda:0')
epoch: 125 test_true_pfm: 5740.728557811235 sim_pfm: 640.6584775262551
episode: 500 training return: tensor(453.3560, device='cuda:0')
episode: 501 training return: tensor(498.3056, device='cuda:0')
episode: 502 training return: tensor(385.6991, device='cuda:0')
episode: 503 training return: tensor(571.0267, device='cuda:0')
epoch: 126 test_true_pfm: 5726.632805859153 sim_pfm: 692.8716465805968
episode: 504 training return: tensor(381.3991, device='cuda:0')
episode: 505 training return: tensor(560.4772, device='cuda:0')
episode: 506 training return: tensor(515.8426, device='cuda:0')
episode: 507 training return: tensor(551.5841, device='cuda:0')
epoch: 127 test_true_pfm: 5725.2981792929595 sim_pfm: 560.8172944993227
episode: 508 training return: tensor(504.1103, device='cuda:0')
episode: 509 training return: tensor(403.1679, device='cuda:0')
episode: 510 training return: tensor(504.3352, device='cuda:0')
episode: 511 training return: tensor(523.0432, device='cuda:0')
epoch: 128 test_true_pfm: 5640.1270462955 sim_pfm: 591.2728294995613
episode: 512 training return: tensor(547.8537, device='cuda:0')
episode: 513 training return: tensor(571.6188, device='cuda:0')
episode: 514 training return: tensor(373.8480, device='cuda:0')
episode: 515 training return: tensor(499.7959, device='cuda:0')
epoch: 129 test_true_pfm: 5729.336574443008 sim_pfm: 693.5980017551532
episode: 516 training return: tensor(418.4547, device='cuda:0')
episode: 517 training return: tensor(398.0659, device='cuda:0')
episode: 518 training return: tensor(501.8470, device='cuda:0')
episode: 519 training return: tensor(535.5076, device='cuda:0')
epoch: 130 test_true_pfm: 5660.120683474972 sim_pfm: 613.4163795805847
episode: 520 training return: tensor(604.2643, device='cuda:0')
episode: 521 training return: tensor(543.9008, device='cuda:0')
episode: 522 training return: tensor(331.9215, device='cuda:0')
episode: 523 training return: tensor(464.1090, device='cuda:0')
epoch: 131 test_true_pfm: 5695.202725978911 sim_pfm: 634.7180257728323
episode: 524 training return: tensor(491.8483, device='cuda:0')
episode: 525 training return: tensor(580.0032, device='cuda:0')
episode: 526 training return: tensor(501.8667, device='cuda:0')
episode: 527 training return: tensor(619.7850, device='cuda:0')
epoch: 132 test_true_pfm: 5647.6908774357935 sim_pfm: 592.2387542943083
episode: 528 training return: tensor(379.2872, device='cuda:0')
episode: 529 training return: tensor(430.5053, device='cuda:0')
episode: 530 training return: tensor(507.9933, device='cuda:0')
episode: 531 training return: tensor(564.5931, device='cuda:0')
epoch: 133 test_true_pfm: 5719.632557605338 sim_pfm: 609.361436737779
episode: 532 training return: tensor(377.5153, device='cuda:0')
episode: 533 training return: tensor(550.6420, device='cuda:0')
episode: 534 training return: tensor(325.7289, device='cuda:0')
episode: 535 training return: tensor(368.9963, device='cuda:0')
epoch: 134 test_true_pfm: 5694.813533331155 sim_pfm: 116.32643470090504
episode: 536 training return: tensor(533.4069, device='cuda:0')
episode: 537 training return: tensor(509.8109, device='cuda:0')
episode: 538 training return: tensor(344.1937, device='cuda:0')
episode: 539 training return: tensor(512.1170, device='cuda:0')
epoch: 135 test_true_pfm: 5688.7703534806715 sim_pfm: 680.6350608166152
episode: 540 training return: tensor(525.6879, device='cuda:0')
episode: 541 training return: tensor(445.6404, device='cuda:0')
episode: 542 training return: tensor(487.5980, device='cuda:0')
episode: 543 training return: tensor(465.4259, device='cuda:0')
epoch: 136 test_true_pfm: 5694.25428891466 sim_pfm: 580.7096971829887
episode: 544 training return: tensor(505.4892, device='cuda:0')
episode: 545 training return: tensor(599.4004, device='cuda:0')
episode: 546 training return: tensor(533.6766, device='cuda:0')
episode: 547 training return: tensor(512.1079, device='cuda:0')
epoch: 137 test_true_pfm: 5689.129788123821 sim_pfm: 650.4138450628767
episode: 548 training return: tensor(559.4054, device='cuda:0')
episode: 549 training return: tensor(445.5616, device='cuda:0')
episode: 550 training return: tensor(397.7549, device='cuda:0')
episode: 551 training return: tensor(592.2507, device='cuda:0')
epoch: 138 test_true_pfm: 5655.461577173338 sim_pfm: 588.2036819514275
episode: 552 training return: tensor(601.2834, device='cuda:0')
episode: 553 training return: tensor(421.3521, device='cuda:0')
episode: 554 training return: tensor(404.1822, device='cuda:0')
episode: 555 training return: tensor(378.8270, device='cuda:0')
epoch: 139 test_true_pfm: 5688.5549965814635 sim_pfm: 599.0082251313142
episode: 556 training return: tensor(530.4261, device='cuda:0')
episode: 557 training return: tensor(557.2917, device='cuda:0')
episode: 558 training return: tensor(624.5460, device='cuda:0')
episode: 559 training return: tensor(534.7552, device='cuda:0')
epoch: 140 test_true_pfm: 5608.087558109512 sim_pfm: 641.2717089726744
episode: 560 training return: tensor(430.3331, device='cuda:0')
episode: 561 training return: tensor(509.8125, device='cuda:0')
episode: 562 training return: tensor(391.1560, device='cuda:0')
episode: 563 training return: tensor(589.1553, device='cuda:0')
epoch: 141 test_true_pfm: 5657.6236382885545 sim_pfm: 664.2373986183666
episode: 564 training return: tensor(507.4798, device='cuda:0')
episode: 565 training return: tensor(554.1263, device='cuda:0')
episode: 566 training return: tensor(519.8193, device='cuda:0')
episode: 567 training return: tensor(583.7114, device='cuda:0')
epoch: 142 test_true_pfm: 5676.958629430831 sim_pfm: 671.2267917049272
episode: 568 training return: tensor(537.6828, device='cuda:0')
episode: 569 training return: tensor(399.8196, device='cuda:0')
episode: 570 training return: tensor(547.9582, device='cuda:0')
episode: 571 training return: tensor(285.6882, device='cuda:0')
epoch: 143 test_true_pfm: 5707.490519404099 sim_pfm: 674.6739497290304
episode: 572 training return: tensor(449.6886, device='cuda:0')
episode: 573 training return: tensor(583.8012, device='cuda:0')
episode: 574 training return: tensor(589.6144, device='cuda:0')
episode: 575 training return: tensor(555.4597, device='cuda:0')
epoch: 144 test_true_pfm: 5736.9833979124305 sim_pfm: 670.869927320707
episode: 576 training return: tensor(616.0040, device='cuda:0')
episode: 577 training return: tensor(396.4897, device='cuda:0')
episode: 578 training return: tensor(613.7542, device='cuda:0')
episode: 579 training return: tensor(567.4784, device='cuda:0')
epoch: 145 test_true_pfm: 5620.954991600954 sim_pfm: 595.9038721943119
episode: 580 training return: tensor(580.9567, device='cuda:0')
episode: 581 training return: tensor(467.2741, device='cuda:0')
episode: 582 training return: tensor(579.3222, device='cuda:0')
episode: 583 training return: tensor(593.6835, device='cuda:0')
epoch: 146 test_true_pfm: 5699.3875935416845 sim_pfm: 717.6840937838424
episode: 584 training return: tensor(519.9752, device='cuda:0')
episode: 585 training return: tensor(571.6281, device='cuda:0')
episode: 586 training return: tensor(527.8872, device='cuda:0')
episode: 587 training return: tensor(407.6511, device='cuda:0')
epoch: 147 test_true_pfm: 5661.397571551685 sim_pfm: 615.5351936467147
episode: 588 training return: tensor(553.5473, device='cuda:0')
episode: 589 training return: tensor(536.2792, device='cuda:0')
episode: 590 training return: tensor(415.0783, device='cuda:0')
episode: 591 training return: tensor(412.8893, device='cuda:0')
epoch: 148 test_true_pfm: 5727.535858176348 sim_pfm: 657.7649061596798
episode: 592 training return: tensor(519.4711, device='cuda:0')
episode: 593 training return: tensor(574.7719, device='cuda:0')
episode: 594 training return: tensor(545.8630, device='cuda:0')
episode: 595 training return: tensor(495.5853, device='cuda:0')
epoch: 149 test_true_pfm: 5744.012597727616 sim_pfm: 602.3215584723899
episode: 596 training return: tensor(462.7850, device='cuda:0')
episode: 597 training return: tensor(512.1917, device='cuda:0')
episode: 598 training return: tensor(601.5666, device='cuda:0')
episode: 599 training return: tensor(545.7879, device='cuda:0')
epoch: 150 test_true_pfm: 5689.3851683650855 sim_pfm: 645.4280088616846
