['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'behavior', '--traj', 'mixed', '--seed', '0', '--data', '100000']
epoch: 0 training_loss 0.4170395837724209 test_loss: 0.35729925632476806
epoch: 1 training_loss 0.3627537499368191 test_loss: 0.35564484596252444
epoch: 2 training_loss 0.355889091193676 test_loss: 0.36901724338531494
epoch: 3 training_loss 0.3598450145125389 test_loss: 0.36903316974639894
epoch: 4 training_loss 0.35519785910844803 test_loss: 0.37797505855560304
epoch: 5 training_loss 0.3511764557659626 test_loss: 0.36136887073516843
epoch: 6 training_loss 0.3548172490298748 test_loss: 0.365359902381897
epoch: 7 training_loss 0.35037809789180757 test_loss: 0.3566669702529907
epoch: 8 training_loss 0.34985650077462194 test_loss: 0.3721403360366821
epoch: 9 training_loss 0.3453849025070667 test_loss: 0.3537696361541748
epoch: 10 training_loss 0.35374299824237826 test_loss: 0.3417024612426758
epoch: 11 training_loss 0.3438234831392765 test_loss: 0.3436346769332886
epoch: 12 training_loss 0.3415533539652824 test_loss: 0.3281067371368408
epoch: 13 training_loss 0.34661742120981215 test_loss: 0.3219795227050781
epoch: 14 training_loss 0.3522252209484577 test_loss: 0.33836138248443604
epoch: 15 training_loss 0.3337038853764534 test_loss: 0.3518792152404785
epoch: 16 training_loss 0.34244789436459544 test_loss: 0.36098670959472656
epoch: 17 training_loss 0.34900027215480806 test_loss: 0.35681843757629395
epoch: 18 training_loss 0.35127136409282683 test_loss: 0.35697550773620607
epoch: 19 training_loss 0.35008506894111635 test_loss: 0.34313414096832273
epoch: 20 training_loss 0.3507508781552315 test_loss: 0.3601524829864502
epoch: 21 training_loss 0.34663426741957665 test_loss: 0.31141507625579834
epoch: 22 training_loss 0.3403767508268356 test_loss: 0.31903390884399413
epoch: 23 training_loss 0.3374986980855465 test_loss: 0.3526421070098877
epoch: 24 training_loss 0.3607077640295029 test_loss: 0.33273816108703613
epoch: 25 training_loss 0.34697800382971766 test_loss: 0.3400980234146118
epoch: 26 training_loss 0.33311195760965345 test_loss: 0.3459266424179077
epoch: 27 training_loss 0.34617620944976807 test_loss: 0.3414472103118896
epoch: 28 training_loss 0.34430859088897703 test_loss: 0.3421472549438477
epoch: 29 training_loss 0.34821989357471467 test_loss: 0.34485764503479005
epoch: 30 training_loss 0.3408096067607403 test_loss: 0.36036345958709715
epoch: 31 training_loss 0.33680130273103714 test_loss: 0.356953763961792
epoch: 32 training_loss 0.33965821489691733 test_loss: 0.3406084060668945
epoch: 33 training_loss 0.3320560294389725 test_loss: 0.32113146781921387
epoch: 34 training_loss 0.3458734546601772 test_loss: 0.3505265235900879
epoch: 35 training_loss 0.3418854996562004 test_loss: 0.33808026313781736
epoch: 36 training_loss 0.3489543254673481 test_loss: 0.3521613597869873
epoch: 37 training_loss 0.3441120015084744 test_loss: 0.34299848079681394
epoch: 38 training_loss 0.3415722523629665 test_loss: 0.3387863874435425
epoch: 39 training_loss 0.3307568384706974 test_loss: 0.3448939800262451
epoch: 40 training_loss 0.3515517722070217 test_loss: 0.3307302474975586
epoch: 41 training_loss 0.347685981541872 test_loss: 0.3379749059677124
epoch: 42 training_loss 0.332050786614418 test_loss: 0.3428253173828125
epoch: 43 training_loss 0.3306376335024834 test_loss: 0.3353969812393188
epoch: 44 training_loss 0.33423988536000254 test_loss: 0.3369931221008301
epoch: 45 training_loss 0.3400434792041779 test_loss: 0.3335242986679077
epoch: 46 training_loss 0.3390218096971512 test_loss: 0.3450706958770752
epoch: 47 training_loss 0.34791082501411436 test_loss: 0.34174978733062744
epoch: 48 training_loss 0.3369652646780014 test_loss: 0.342911958694458
epoch: 49 training_loss 0.33574302956461904 test_loss: 0.34598076343536377
epoch: 50 training_loss 0.3362614868581295 test_loss: 0.35327351093292236
epoch: 51 training_loss 0.34136949688196183 test_loss: 0.3822401762008667
epoch: 52 training_loss 0.33902502223849296 test_loss: 0.3281551837921143
epoch: 53 training_loss 0.3424339608848095 test_loss: 0.3769346237182617
epoch: 54 training_loss 0.3378202997148037 test_loss: 0.34512600898742674
epoch: 55 training_loss 0.349393325150013 test_loss: 0.3306939125061035
epoch: 56 training_loss 0.32710488870739934 test_loss: 0.3315871238708496
epoch: 57 training_loss 0.3481687432527542 test_loss: 0.3580836057662964
epoch: 58 training_loss 0.3447490771114826 test_loss: 0.3065286159515381
epoch: 59 training_loss 0.3479188686609268 test_loss: 0.34818577766418457
epoch: 60 training_loss 0.33424286380410195 test_loss: 0.30851380825042723
epoch: 61 training_loss 0.33192508056759834 test_loss: 0.33980934619903563
epoch: 62 training_loss 0.341622154712677 test_loss: 0.33518955707550047
epoch: 63 training_loss 0.33049198403954505 test_loss: 0.3272238254547119
epoch: 64 training_loss 0.345729866027832 test_loss: 0.33795335292816164
epoch: 65 training_loss 0.3411205604672432 test_loss: 0.34441771507263186
epoch: 66 training_loss 0.3399981062114239 test_loss: 0.33753385543823244
epoch: 67 training_loss 0.3504647667706013 test_loss: 0.3245967626571655
epoch: 68 training_loss 0.3452720619738102 test_loss: 0.3400511503219604
epoch: 69 training_loss 0.33888156101107597 test_loss: 0.3372291326522827
epoch: 70 training_loss 0.348653627038002 test_loss: 0.3412280797958374
epoch: 71 training_loss 0.34213934957981107 test_loss: 0.3522618770599365
epoch: 72 training_loss 0.3329461893439293 test_loss: 0.3458064317703247
epoch: 73 training_loss 0.3445244565606117 test_loss: 0.3196394443511963
epoch: 74 training_loss 0.3342371328175068 test_loss: 0.3492537021636963
epoch: 75 training_loss 0.33824301436543464 test_loss: 0.368195915222168
epoch: 76 training_loss 0.34352554082870485 test_loss: 0.36106836795806885
epoch: 77 training_loss 0.3367617045342922 test_loss: 0.34732699394226074
epoch: 78 training_loss 0.33869180738925936 test_loss: 0.3321314811706543
epoch: 79 training_loss 0.338118354678154 test_loss: 0.33931128978729247
epoch: 80 training_loss 0.34153496503829955 test_loss: 0.35414857864379884
epoch: 81 training_loss 0.3415244701504707 test_loss: 0.34954285621643066
epoch: 82 training_loss 0.3353128072619438 test_loss: 0.3725713014602661
epoch: 83 training_loss 0.3343319699168205 test_loss: 0.34209499359130857
epoch: 84 training_loss 0.35308089420199396 test_loss: 0.32864763736724856
epoch: 85 training_loss 0.33739991262555125 test_loss: 0.331725549697876
epoch: 86 training_loss 0.3390590104460716 test_loss: 0.3348410129547119
epoch: 87 training_loss 0.3330840763449669 test_loss: 0.33690905570983887
epoch: 88 training_loss 0.3547267252206802 test_loss: 0.33420910835266116
epoch: 89 training_loss 0.33942812487483026 test_loss: 0.3243205785751343
epoch: 90 training_loss 0.3399593034386635 test_loss: 0.34277312755584716
epoch: 91 training_loss 0.3384431192278862 test_loss: 0.3400366544723511
epoch: 92 training_loss 0.3430355966091156 test_loss: 0.338735032081604
epoch: 93 training_loss 0.33473956525325776 test_loss: 0.33570160865783694
epoch: 94 training_loss 0.3322864021360874 test_loss: 0.3468335151672363
epoch: 95 training_loss 0.3373763057589531 test_loss: 0.33527412414550783
epoch: 96 training_loss 0.3446372427046299 test_loss: 0.3375048875808716
epoch: 97 training_loss 0.3339742995798588 test_loss: 0.364084529876709
epoch: 98 training_loss 0.33997839778661726 test_loss: 0.33776350021362306
epoch: 99 training_loss 0.3387238484621048 test_loss: 0.3395689487457275
epoch: 100 training_loss 0.334942374676466 test_loss: 0.348272967338562
epoch: 101 training_loss 0.3426388391852379 test_loss: 0.36301870346069337
epoch: 102 training_loss 0.33405491650104524 test_loss: 0.30904550552368165
epoch: 103 training_loss 0.3433912043273449 test_loss: 0.329451584815979
epoch: 104 training_loss 0.3365070240199566 test_loss: 0.3409160852432251
epoch: 105 training_loss 0.3278857569396496 test_loss: 0.3418839931488037
epoch: 106 training_loss 0.3442604258656502 test_loss: 0.3498953580856323
epoch: 107 training_loss 0.32364140927791596 test_loss: 0.350640082359314
epoch: 108 training_loss 0.3325633952021599 test_loss: 0.3384211301803589
epoch: 109 training_loss 0.34460902735590937 test_loss: 0.30638370513916013
epoch: 110 training_loss 0.3367340809106827 test_loss: 0.3092122316360474
epoch: 111 training_loss 0.3332925893366337 test_loss: 0.35090224742889403
epoch: 112 training_loss 0.3402656291425228 test_loss: 0.3571533203125
epoch: 113 training_loss 0.34169036239385603 test_loss: 0.3610674858093262
epoch: 114 training_loss 0.3312815317511559 test_loss: 0.3354945659637451
epoch: 115 training_loss 0.3389947286248207 test_loss: 0.3480034351348877
epoch: 116 training_loss 0.33974826127290725 test_loss: 0.34099593162536623
epoch: 117 training_loss 0.32219953045248984 test_loss: 0.3576096773147583
epoch: 118 training_loss 0.32615522608160974 test_loss: 0.3530564308166504
epoch: 119 training_loss 0.34054300770163537 test_loss: 0.35030622482299806
epoch: 120 training_loss 0.33238332718610764 test_loss: 0.3431232452392578
epoch: 121 training_loss 0.3380824090540409 test_loss: 0.3054118871688843
epoch: 122 training_loss 0.34041520282626153 test_loss: 0.32787511348724363
epoch: 123 training_loss 0.34143888682127 test_loss: 0.3610014200210571
epoch: 124 training_loss 0.3338875660300255 test_loss: 0.33453705310821535
epoch: 125 training_loss 0.33296307295560834 test_loss: 0.3225783109664917
epoch: 126 training_loss 0.33924940004944804 test_loss: 0.3467393159866333
epoch: 127 training_loss 0.34397428840398786 test_loss: 0.34886372089385986
epoch: 128 training_loss 0.3393002201616764 test_loss: 0.31843743324279783
epoch: 129 training_loss 0.3350249801576137 test_loss: 0.3248365640640259
epoch: 130 training_loss 0.32983130812644956 test_loss: 0.3399932384490967
epoch: 131 training_loss 0.3474995598196983 test_loss: 0.32352898120880125
epoch: 132 training_loss 0.32404870763421056 test_loss: 0.33123364448547366
epoch: 133 training_loss 0.33702477157115934 test_loss: 0.35807955265045166
epoch: 134 training_loss 0.3469098471105099 test_loss: 0.3205708026885986
epoch: 135 training_loss 0.33360655888915064 test_loss: 0.3212295055389404
epoch: 136 training_loss 0.3417560890316963 test_loss: 0.35032870769500735
epoch: 137 training_loss 0.3362651351094246 test_loss: 0.3327591896057129
epoch: 138 training_loss 0.34269149661064147 test_loss: 0.3450508117675781
epoch: 139 training_loss 0.33576032176613807 test_loss: 0.3444467544555664
epoch: 140 training_loss 0.3268168227374554 test_loss: 0.3507460832595825
epoch: 141 training_loss 0.3382279171049595 test_loss: 0.3315739631652832
epoch: 142 training_loss 0.34111278906464576 test_loss: 0.3326763153076172
epoch: 143 training_loss 0.3433647854626179 test_loss: 0.3192124843597412
epoch: 144 training_loss 0.3396082253754139 test_loss: 0.37205705642700193
epoch: 145 training_loss 0.3397183783352375 test_loss: 0.33380415439605715
epoch: 146 training_loss 0.33183316737413404 test_loss: 0.3509528636932373
epoch: 147 training_loss 0.3391585072875023 test_loss: 0.3214352369308472
epoch: 148 training_loss 0.3413461101055145 test_loss: 0.35934512615203856
epoch: 149 training_loss 0.34226681604981424 test_loss: 0.3233972072601318
epoch: 0 training_loss 37.87408760070801 test_loss: 28.159307861328124
epoch: 1 training_loss 23.30816982269287 test_loss: 19.29674530029297
epoch: 2 training_loss 18.254496517181398 test_loss: 16.844706726074218
epoch: 3 training_loss 15.564637937545776 test_loss: 14.661610412597657
epoch: 4 training_loss 13.834927988052367 test_loss: 13.378068542480468
epoch: 5 training_loss 12.662342710494995 test_loss: 12.163997650146484
epoch: 6 training_loss 11.674134445190429 test_loss: 11.170548248291016
epoch: 7 training_loss 10.9707666015625 test_loss: 10.686854553222656
epoch: 8 training_loss 10.54064248085022 test_loss: 10.08160171508789
epoch: 9 training_loss 10.029354391098023 test_loss: 10.117716217041016
epoch: 10 training_loss 9.648562173843384 test_loss: 9.804462432861328
epoch: 11 training_loss 9.543838057518006 test_loss: 9.312692260742187
epoch: 12 training_loss 9.477141704559326 test_loss: 8.787058258056641
epoch: 13 training_loss 9.028540306091308 test_loss: 9.150643157958985
epoch: 14 training_loss 8.873143129348755 test_loss: 9.210513305664062
epoch: 15 training_loss 8.718280057907105 test_loss: 8.673770904541016
epoch: 16 training_loss 8.41407075881958 test_loss: 8.400428009033202
epoch: 17 training_loss 8.47111569404602 test_loss: 8.280510711669923
epoch: 18 training_loss 8.15640233039856 test_loss: 7.987248229980469
epoch: 19 training_loss 7.971136364936829 test_loss: 8.214038848876953
epoch: 20 training_loss 7.715192980766297 test_loss: 8.052867126464843
epoch: 21 training_loss 7.745575723648071 test_loss: 7.869589233398438
epoch: 22 training_loss 7.734363241195679 test_loss: 7.663648986816407
epoch: 23 training_loss 7.598942322731018 test_loss: 7.701027679443359
epoch: 24 training_loss 7.382556014060974 test_loss: 7.090569305419922
epoch: 25 training_loss 7.495751214027405 test_loss: 8.063140869140625
epoch: 26 training_loss 7.0952935838699345 test_loss: 7.031848907470703
epoch: 27 training_loss 7.063738021850586 test_loss: 7.234256744384766
epoch: 28 training_loss 6.974701404571533 test_loss: 7.39141616821289
epoch: 29 training_loss 6.871934833526612 test_loss: 6.90621337890625
epoch: 30 training_loss 6.9921027946472165 test_loss: 6.889397430419922
epoch: 31 training_loss 6.799482064247131 test_loss: 6.669239044189453
epoch: 32 training_loss 6.705781130790711 test_loss: 6.7137397766113285
epoch: 33 training_loss 6.591361193656922 test_loss: 6.640888214111328
epoch: 34 training_loss 6.645224022865295 test_loss: 6.7732078552246096
epoch: 35 training_loss 6.672238717079162 test_loss: 6.589009857177734
epoch: 36 training_loss 6.459007525444031 test_loss: 6.061919784545898
epoch: 37 training_loss 6.548215899467468 test_loss: 6.622581481933594
epoch: 38 training_loss 6.525299711227417 test_loss: 6.485192108154297
epoch: 39 training_loss 6.3854347467422485 test_loss: 6.66858139038086
epoch: 40 training_loss 6.322946844100952 test_loss: 6.153436660766602
epoch: 41 training_loss 6.3012980413436885 test_loss: 5.976081466674804
epoch: 42 training_loss 6.225558166503906 test_loss: 6.2426715850830075
epoch: 43 training_loss 6.270754261016846 test_loss: 6.76586685180664
epoch: 44 training_loss 6.263118152618408 test_loss: 6.018981552124023
epoch: 45 training_loss 6.203621950149536 test_loss: 5.817377090454102
epoch: 46 training_loss 6.163676328659058 test_loss: 6.210423278808594
epoch: 47 training_loss 6.146282906532288 test_loss: 6.000085067749024
epoch: 48 training_loss 6.12566563129425 test_loss: 6.258813095092774
epoch: 49 training_loss 6.128038463592529 test_loss: 5.603374481201172
epoch: 50 training_loss 5.939977331161499 test_loss: 6.014398574829102
epoch: 51 training_loss 6.004777226448059 test_loss: 5.675238418579101
epoch: 52 training_loss 5.850563807487488 test_loss: 5.858573532104492
epoch: 53 training_loss 5.733991742134094 test_loss: 5.912672805786133
epoch: 54 training_loss 5.776196036338806 test_loss: 5.943808364868164
epoch: 55 training_loss 5.822476344108582 test_loss: 5.619693756103516
epoch: 56 training_loss 5.777623076438903 test_loss: 5.708597564697266
epoch: 57 training_loss 5.792066016197205 test_loss: 5.983077621459961
epoch: 58 training_loss 5.771133403778077 test_loss: 5.767210388183594
epoch: 59 training_loss 5.584201502799988 test_loss: 5.611763763427734
epoch: 60 training_loss 5.681937851905823 test_loss: 5.875842666625976
epoch: 61 training_loss 5.615189890861512 test_loss: 5.858381271362305
epoch: 62 training_loss 5.631967113018036 test_loss: 5.32984504699707
epoch: 63 training_loss 5.575676579475402 test_loss: 5.914836120605469
epoch: 64 training_loss 5.480963215827942 test_loss: 5.614782333374023
epoch: 65 training_loss 5.436057572364807 test_loss: 5.36975212097168
epoch: 66 training_loss 5.317398118972778 test_loss: 6.000430297851563
epoch: 67 training_loss 5.468213720321655 test_loss: 5.557933044433594
epoch: 68 training_loss 5.339930708408356 test_loss: 5.376381683349609
epoch: 69 training_loss 5.322194530963897 test_loss: 5.204395294189453
epoch: 70 training_loss 5.463365955352783 test_loss: 5.215179443359375
epoch: 71 training_loss 5.229068922996521 test_loss: 5.515100479125977
epoch: 72 training_loss 5.176351096630096 test_loss: 5.895396041870117
epoch: 73 training_loss 5.292450275421142 test_loss: 5.5461784362792965
epoch: 74 training_loss 5.220833232402802 test_loss: 5.174266815185547
epoch: 75 training_loss 5.365724654197693 test_loss: 5.356240463256836
epoch: 76 training_loss 5.243118185997009 test_loss: 5.393141555786133
epoch: 77 training_loss 5.093344485759735 test_loss: 5.151106643676758
epoch: 78 training_loss 5.170394444465638 test_loss: 5.125156402587891
epoch: 79 training_loss 5.267986428737641 test_loss: 5.1560321807861325
epoch: 80 training_loss 5.295703239440918 test_loss: 5.001747512817383
epoch: 81 training_loss 5.085905191898346 test_loss: 5.045127105712891
epoch: 82 training_loss 5.112801201343537 test_loss: 4.8401939392089846
epoch: 83 training_loss 5.192906243801117 test_loss: 5.937377548217773
epoch: 84 training_loss 5.126991884708405 test_loss: 5.0092521667480465
epoch: 85 training_loss 5.023177773952484 test_loss: 5.0603076934814455
epoch: 86 training_loss 4.972438814640046 test_loss: 5.23151741027832
epoch: 87 training_loss 5.209821152687073 test_loss: 4.808428573608398
epoch: 88 training_loss 5.020027384757996 test_loss: 5.197367477416992
epoch: 89 training_loss 5.036790292263031 test_loss: 5.220577239990234
epoch: 90 training_loss 5.054374625682831 test_loss: 5.036251068115234
epoch: 91 training_loss 4.930029079914093 test_loss: 4.7608192443847654
epoch: 92 training_loss 5.282561650276184 test_loss: 5.332047653198242
epoch: 93 training_loss 4.965351927280426 test_loss: 4.708816909790039
epoch: 94 training_loss 4.864383342266083 test_loss: 4.917367935180664
epoch: 95 training_loss 4.8542760825157165 test_loss: 4.806522369384766
epoch: 96 training_loss 5.001356549263001 test_loss: 4.860707092285156
epoch: 97 training_loss 4.8508618712425235 test_loss: 4.994818115234375
epoch: 98 training_loss 4.947237813472748 test_loss: 4.977048873901367
epoch: 99 training_loss 4.999310617446899 test_loss: 4.640097427368164
epoch: 100 training_loss 4.8526169872283935 test_loss: 4.806195831298828
epoch: 101 training_loss 4.785555455684662 test_loss: 4.755624389648437
epoch: 102 training_loss 4.673208801746369 test_loss: 4.938184356689453
epoch: 103 training_loss 4.812894909381867 test_loss: 4.495652770996093
epoch: 104 training_loss 4.599629826545716 test_loss: 4.674028396606445
epoch: 105 training_loss 4.841251263618469 test_loss: 4.695838546752929
epoch: 106 training_loss 4.610211472511292 test_loss: 4.6485343933105465
epoch: 107 training_loss 4.594995348453522 test_loss: 4.3238262176513675
epoch: 108 training_loss 4.791668093204498 test_loss: 4.642480850219727
epoch: 109 training_loss 4.7763899183273315 test_loss: 4.52342414855957
epoch: 110 training_loss 4.608661358356476 test_loss: 4.687967300415039
epoch: 111 training_loss 4.528388967514038 test_loss: 4.310210418701172
epoch: 112 training_loss 4.500316495895386 test_loss: 4.348062133789062
epoch: 113 training_loss 4.5709852027893065 test_loss: 4.593039703369141
epoch: 114 training_loss 4.546636815071106 test_loss: 4.4769233703613285
epoch: 115 training_loss 4.609067547321319 test_loss: 4.364663696289062
epoch: 116 training_loss 4.393606915473938 test_loss: 4.589396667480469
epoch: 117 training_loss 4.632173011302948 test_loss: 4.584746170043945
epoch: 118 training_loss 4.658150892257691 test_loss: 4.472382354736328
epoch: 119 training_loss 4.5450120091438295 test_loss: 4.384817504882813
epoch: 120 training_loss 4.506655783653259 test_loss: 4.699749374389649
epoch: 121 training_loss 4.380083792209625 test_loss: 4.737800598144531
epoch: 122 training_loss 4.379167528152466 test_loss: 4.406821060180664
epoch: 123 training_loss 4.505692274570465 test_loss: 4.27849006652832
epoch: 124 training_loss 4.398581788539887 test_loss: 4.30108871459961
epoch: 125 training_loss 4.457404508590698 test_loss: 4.426296615600586
epoch: 126 training_loss 4.435586667060852 test_loss: 4.342654800415039
epoch: 127 training_loss 4.396897695064545 test_loss: 4.295748901367188
epoch: 128 training_loss 4.390812213420868 test_loss: 4.696698760986328
epoch: 129 training_loss 4.389326212406158 test_loss: 4.432303619384766
epoch: 130 training_loss 4.416917822360992 test_loss: 4.644324874877929
epoch: 131 training_loss 4.508532433509827 test_loss: 4.954023742675782
epoch: 132 training_loss 4.5324567246437075 test_loss: 4.134317398071289
epoch: 133 training_loss 4.320207986831665 test_loss: 4.340177154541015
epoch: 134 training_loss 4.341289920806885 test_loss: 4.369984436035156
epoch: 135 training_loss 4.259973366260528 test_loss: 4.1932220458984375
epoch: 136 training_loss 4.261938920021057 test_loss: 4.33917236328125
epoch: 137 training_loss 4.251387691497802 test_loss: 4.412247848510742
epoch: 138 training_loss 4.381855502128601 test_loss: 4.365729904174804
epoch: 139 training_loss 4.3491970777511595 test_loss: 4.574238204956055
epoch: 140 training_loss 4.381413369178772 test_loss: 4.323479461669922
epoch: 141 training_loss 4.300822293758392 test_loss: 4.492556762695313
epoch: 142 training_loss 4.26981320142746 test_loss: 4.256323623657226
epoch: 143 training_loss 4.179135179519653 test_loss: 4.4197742462158205
epoch: 144 training_loss 4.272421231269837 test_loss: 4.359714508056641
epoch: 145 training_loss 4.340093035697937 test_loss: 4.181798934936523
epoch: 146 training_loss 4.273105206489563 test_loss: 4.293046188354492
epoch: 147 training_loss 4.245306730270386 test_loss: 4.178368759155274
epoch: 148 training_loss 4.156771886348724 test_loss: 4.110982894897461
epoch: 149 training_loss 4.343862421512604 test_loss: 4.593523406982422
75.38845400244783
episode: 0 training return: tensor(41.7012, device='cuda:0')
episode: 1 training return: tensor(45.6688, device='cuda:0')
episode: 2 training return: tensor(44.6519, device='cuda:0')
episode: 3 training return: tensor(49.8853, device='cuda:0')
epoch: 1 test_true_pfm: 50.87907408051783 sim_pfm: 10.46374610865023
episode: 4 training return: tensor(15.5088, device='cuda:0')
episode: 5 training return: tensor(44.9250, device='cuda:0')
episode: 6 training return: tensor(43.4913, device='cuda:0')
episode: 7 training return: tensor(25.0672, device='cuda:0')
epoch: 2 test_true_pfm: 46.355072649117076 sim_pfm: 12.038253689877456
episode: 8 training return: tensor(12.8310, device='cuda:0')
episode: 9 training return: tensor(42.2696, device='cuda:0')
episode: 10 training return: tensor(38.4830, device='cuda:0')
episode: 11 training return: tensor(39.9742, device='cuda:0')
epoch: 3 test_true_pfm: 48.736290727790575 sim_pfm: 22.728882288106252
episode: 12 training return: tensor(41.4754, device='cuda:0')
episode: 13 training return: tensor(19.2558, device='cuda:0')
episode: 14 training return: tensor(24.2080, device='cuda:0')
episode: 15 training return: tensor(52.2702, device='cuda:0')
epoch: 4 test_true_pfm: 106.06754719728274 sim_pfm: 35.86350903961575
episode: 16 training return: tensor(41.3157, device='cuda:0')
episode: 17 training return: tensor(48.0338, device='cuda:0')
episode: 18 training return: tensor(62.5090, device='cuda:0')
episode: 19 training return: tensor(40.4527, device='cuda:0')
epoch: 5 test_true_pfm: 79.60051069515671 sim_pfm: 39.535509938123866
episode: 20 training return: tensor(45.5346, device='cuda:0')
episode: 21 training return: tensor(43.2401, device='cuda:0')
episode: 22 training return: tensor(43.2255, device='cuda:0')
episode: 23 training return: tensor(43.7928, device='cuda:0')
epoch: 6 test_true_pfm: 83.47027393475793 sim_pfm: 39.05741874750238
episode: 24 training return: tensor(44.1421, device='cuda:0')
episode: 25 training return: tensor(43.6756, device='cuda:0')
episode: 26 training return: tensor(43.1408, device='cuda:0')
episode: 27 training return: tensor(43.3022, device='cuda:0')
epoch: 7 test_true_pfm: 80.15573827883097 sim_pfm: 33.58247904255986
episode: 28 training return: tensor(44.1591, device='cuda:0')
episode: 29 training return: tensor(49.5534, device='cuda:0')
episode: 30 training return: tensor(40.0374, device='cuda:0')
episode: 31 training return: tensor(41.3512, device='cuda:0')
epoch: 8 test_true_pfm: 80.36639924578446 sim_pfm: 42.63711827673833
episode: 32 training return: tensor(42.2973, device='cuda:0')
episode: 33 training return: tensor(44.8562, device='cuda:0')
episode: 34 training return: tensor(44.3048, device='cuda:0')
episode: 35 training return: tensor(44.2785, device='cuda:0')
epoch: 9 test_true_pfm: 81.1744087791344 sim_pfm: 46.04597189090564
episode: 36 training return: tensor(45.4387, device='cuda:0')
episode: 37 training return: tensor(47.7559, device='cuda:0')
episode: 38 training return: tensor(41.0121, device='cuda:0')
episode: 39 training return: tensor(44.4267, device='cuda:0')
epoch: 10 test_true_pfm: 79.56754881006405 sim_pfm: 37.70138279600651
episode: 40 training return: tensor(48.5636, device='cuda:0')
episode: 41 training return: tensor(47.9529, device='cuda:0')
episode: 42 training return: tensor(45.9843, device='cuda:0')
episode: 43 training return: tensor(40.7337, device='cuda:0')
epoch: 11 test_true_pfm: 78.03848657154234 sim_pfm: 47.2008003272349
episode: 44 training return: tensor(45.5763, device='cuda:0')
episode: 45 training return: tensor(11.7783, device='cuda:0')
episode: 46 training return: tensor(-9.1457, device='cuda:0')
episode: 47 training return: tensor(-12.1158, device='cuda:0')
epoch: 12 test_true_pfm: 62.762600052411926 sim_pfm: -10.970492002915126
episode: 48 training return: tensor(49.1363, device='cuda:0')
episode: 49 training return: tensor(48.4398, device='cuda:0')
episode: 50 training return: tensor(-21.9364, device='cuda:0')
episode: 51 training return: tensor(27.6273, device='cuda:0')
epoch: 13 test_true_pfm: 57.77568789657346 sim_pfm: 16.811615731334314
episode: 52 training return: tensor(48.5829, device='cuda:0')
episode: 53 training return: tensor(48.4043, device='cuda:0')
episode: 54 training return: tensor(49.1264, device='cuda:0')
episode: 55 training return: tensor(46.4050, device='cuda:0')
epoch: 14 test_true_pfm: 54.742798830700416 sim_pfm: 1.3937754700018559
episode: 56 training return: tensor(16.8771, device='cuda:0')
episode: 57 training return: tensor(-22.4182, device='cuda:0')
episode: 58 training return: tensor(47.0773, device='cuda:0')
episode: 59 training return: tensor(26.8479, device='cuda:0')
epoch: 15 test_true_pfm: 56.19113655899025 sim_pfm: 32.19935767201241
episode: 60 training return: tensor(46.8701, device='cuda:0')
episode: 61 training return: tensor(46.2503, device='cuda:0')
episode: 62 training return: tensor(22.9963, device='cuda:0')
episode: 63 training return: tensor(27.2141, device='cuda:0')
epoch: 16 test_true_pfm: 66.23410640036226 sim_pfm: 12.765933640376897
episode: 64 training return: tensor(44.3494, device='cuda:0')
episode: 65 training return: tensor(43.1000, device='cuda:0')
episode: 66 training return: tensor(48.1604, device='cuda:0')
episode: 67 training return: tensor(51.4908, device='cuda:0')
epoch: 17 test_true_pfm: 80.6689582473247 sim_pfm: 37.66702229733928
episode: 68 training return: tensor(52.2819, device='cuda:0')
episode: 69 training return: tensor(-13.8437, device='cuda:0')
episode: 70 training return: tensor(48.4859, device='cuda:0')
episode: 71 training return: tensor(44.9530, device='cuda:0')
epoch: 18 test_true_pfm: 77.19826483169231 sim_pfm: 50.790977900277355
episode: 72 training return: tensor(46.8602, device='cuda:0')
episode: 73 training return: tensor(46.9982, device='cuda:0')
episode: 74 training return: tensor(47.3888, device='cuda:0')
episode: 75 training return: tensor(44.3985, device='cuda:0')
epoch: 19 test_true_pfm: 79.40725579715405 sim_pfm: 50.03334263226716
episode: 76 training return: tensor(53.6159, device='cuda:0')
episode: 77 training return: tensor(49.8658, device='cuda:0')
episode: 78 training return: tensor(54.8678, device='cuda:0')
episode: 79 training return: tensor(48.8227, device='cuda:0')
epoch: 20 test_true_pfm: 77.01909450647145 sim_pfm: 49.43119953518035
episode: 80 training return: tensor(47.8712, device='cuda:0')
episode: 81 training return: tensor(52.9599, device='cuda:0')
episode: 82 training return: tensor(47.9901, device='cuda:0')
episode: 83 training return: tensor(47.8717, device='cuda:0')
epoch: 21 test_true_pfm: 79.55303455806629 sim_pfm: 49.377022949809906
episode: 84 training return: tensor(46.9773, device='cuda:0')
episode: 85 training return: tensor(51.5138, device='cuda:0')
episode: 86 training return: tensor(45.0291, device='cuda:0')
episode: 87 training return: tensor(47.6545, device='cuda:0')
epoch: 22 test_true_pfm: 77.1120024345034 sim_pfm: 46.1937728060002
episode: 88 training return: tensor(45.5125, device='cuda:0')
episode: 89 training return: tensor(45.9332, device='cuda:0')
episode: 90 training return: tensor(48.5206, device='cuda:0')
episode: 91 training return: tensor(44.2368, device='cuda:0')
epoch: 23 test_true_pfm: 78.04624626681507 sim_pfm: 47.04842429790297
episode: 92 training return: tensor(41.6863, device='cuda:0')
episode: 93 training return: tensor(46.5943, device='cuda:0')
episode: 94 training return: tensor(48.5932, device='cuda:0')
episode: 95 training return: tensor(47.5911, device='cuda:0')
epoch: 24 test_true_pfm: 80.66885342283894 sim_pfm: 50.27927193104988
episode: 96 training return: tensor(52.4092, device='cuda:0')
episode: 97 training return: tensor(52.9960, device='cuda:0')
episode: 98 training return: tensor(51.4285, device='cuda:0')
episode: 99 training return: tensor(50.1639, device='cuda:0')
epoch: 25 test_true_pfm: 78.84509032770087 sim_pfm: 40.933708248630865
episode: 100 training return: tensor(55.1215, device='cuda:0')
episode: 101 training return: tensor(51.5906, device='cuda:0')
episode: 102 training return: tensor(49.2658, device='cuda:0')
episode: 103 training return: tensor(49.6536, device='cuda:0')
epoch: 26 test_true_pfm: 78.54642609302675 sim_pfm: 37.292468358040786
episode: 104 training return: tensor(51.6005, device='cuda:0')
episode: 105 training return: tensor(49.9889, device='cuda:0')
episode: 106 training return: tensor(47.4477, device='cuda:0')
episode: 107 training return: tensor(48.8906, device='cuda:0')
epoch: 27 test_true_pfm: 78.33068853472658 sim_pfm: 31.063304088753647
episode: 108 training return: tensor(19.6286, device='cuda:0')
episode: 109 training return: tensor(-9.8362, device='cuda:0')
episode: 110 training return: tensor(-10.3267, device='cuda:0')
episode: 111 training return: tensor(49.5054, device='cuda:0')
epoch: 28 test_true_pfm: 54.445156013002965 sim_pfm: 9.028920791548444
episode: 112 training return: tensor(6.0507, device='cuda:0')
episode: 113 training return: tensor(48.8473, device='cuda:0')
episode: 114 training return: tensor(52.2580, device='cuda:0')
episode: 115 training return: tensor(39.8871, device='cuda:0')
epoch: 29 test_true_pfm: 81.75030010769638 sim_pfm: 52.97164543888066
episode: 116 training return: tensor(50.7658, device='cuda:0')
episode: 117 training return: tensor(48.1626, device='cuda:0')
episode: 118 training return: tensor(51.2381, device='cuda:0')
episode: 119 training return: tensor(52.8388, device='cuda:0')
epoch: 30 test_true_pfm: 71.86601887001947 sim_pfm: 50.404104286059734
episode: 120 training return: tensor(46.2688, device='cuda:0')
episode: 121 training return: tensor(50.0681, device='cuda:0')
episode: 122 training return: tensor(52.9099, device='cuda:0')
episode: 123 training return: tensor(52.7056, device='cuda:0')
epoch: 31 test_true_pfm: 86.34482755794001 sim_pfm: 46.66997134833946
episode: 124 training return: tensor(49.8098, device='cuda:0')
episode: 125 training return: tensor(52.9412, device='cuda:0')
episode: 126 training return: tensor(52.2619, device='cuda:0')
episode: 127 training return: tensor(49.7461, device='cuda:0')
epoch: 32 test_true_pfm: 71.76755884408958 sim_pfm: 48.10848326871055
episode: 128 training return: tensor(48.3881, device='cuda:0')
episode: 129 training return: tensor(53.7978, device='cuda:0')
episode: 130 training return: tensor(50.5354, device='cuda:0')
episode: 131 training return: tensor(45.8729, device='cuda:0')
epoch: 33 test_true_pfm: 74.46961598595685 sim_pfm: 49.58097578362212
episode: 132 training return: tensor(54.4404, device='cuda:0')
episode: 133 training return: tensor(45.3740, device='cuda:0')
episode: 134 training return: tensor(51.6347, device='cuda:0')
episode: 135 training return: tensor(45.7143, device='cuda:0')
epoch: 34 test_true_pfm: 72.94713734824772 sim_pfm: 49.38796229782747
episode: 136 training return: tensor(50.5564, device='cuda:0')
episode: 137 training return: tensor(49.1359, device='cuda:0')
episode: 138 training return: tensor(45.3374, device='cuda:0')
episode: 139 training return: tensor(-13.5961, device='cuda:0')
epoch: 35 test_true_pfm: 81.07902017617 sim_pfm: 48.47976811822737
episode: 140 training return: tensor(47.7095, device='cuda:0')
episode: 141 training return: tensor(47.6386, device='cuda:0')
episode: 142 training return: tensor(44.5271, device='cuda:0')
episode: 143 training return: tensor(44.3516, device='cuda:0')
epoch: 36 test_true_pfm: 79.06153293942808 sim_pfm: 44.750312662502985
episode: 144 training return: tensor(49.5570, device='cuda:0')
episode: 145 training return: tensor(46.5555, device='cuda:0')
episode: 146 training return: tensor(47.2694, device='cuda:0')
episode: 147 training return: tensor(48.6415, device='cuda:0')
epoch: 37 test_true_pfm: 71.31097924598984 sim_pfm: 46.47387206770363
episode: 148 training return: tensor(48.3304, device='cuda:0')
episode: 149 training return: tensor(47.8567, device='cuda:0')
episode: 150 training return: tensor(47.9666, device='cuda:0')
episode: 151 training return: tensor(50.2494, device='cuda:0')
epoch: 38 test_true_pfm: 77.89630498236218 sim_pfm: 44.98082522807526
episode: 152 training return: tensor(42.8672, device='cuda:0')
episode: 153 training return: tensor(46.1845, device='cuda:0')
episode: 154 training return: tensor(45.8432, device='cuda:0')
episode: 155 training return: tensor(44.0484, device='cuda:0')
epoch: 39 test_true_pfm: 85.42136508394381 sim_pfm: 45.6810792169068
episode: 156 training return: tensor(48.0028, device='cuda:0')
episode: 157 training return: tensor(45.8239, device='cuda:0')
episode: 158 training return: tensor(48.5067, device='cuda:0')
episode: 159 training return: tensor(51.6929, device='cuda:0')
epoch: 40 test_true_pfm: 81.65718668065838 sim_pfm: 48.75527317078085
episode: 160 training return: tensor(53.2068, device='cuda:0')
episode: 161 training return: tensor(49.2829, device='cuda:0')
episode: 162 training return: tensor(43.4928, device='cuda:0')
episode: 163 training return: tensor(49.2521, device='cuda:0')
epoch: 41 test_true_pfm: 75.03753741628927 sim_pfm: 56.5875735319918
episode: 164 training return: tensor(50.4087, device='cuda:0')
episode: 165 training return: tensor(43.3341, device='cuda:0')
episode: 166 training return: tensor(48.8584, device='cuda:0')
episode: 167 training return: tensor(11.6243, device='cuda:0')
epoch: 42 test_true_pfm: 79.88934426655385 sim_pfm: 41.01987287519732
episode: 168 training return: tensor(46.9224, device='cuda:0')
episode: 169 training return: tensor(49.5323, device='cuda:0')
episode: 170 training return: tensor(46.9611, device='cuda:0')
episode: 171 training return: tensor(47.8590, device='cuda:0')
epoch: 43 test_true_pfm: 80.72412139375588 sim_pfm: 44.18405884230742
episode: 172 training return: tensor(50.7712, device='cuda:0')
episode: 173 training return: tensor(53.6930, device='cuda:0')
episode: 174 training return: tensor(45.6740, device='cuda:0')
episode: 175 training return: tensor(50.5149, device='cuda:0')
epoch: 44 test_true_pfm: 74.57244841800346 sim_pfm: 41.51369391163462
episode: 176 training return: tensor(51.8648, device='cuda:0')
episode: 177 training return: tensor(48.6169, device='cuda:0')
episode: 178 training return: tensor(52.2508, device='cuda:0')
episode: 179 training return: tensor(49.6621, device='cuda:0')
epoch: 45 test_true_pfm: 73.85414160568739 sim_pfm: 48.26970384154701
episode: 180 training return: tensor(48.4661, device='cuda:0')
episode: 181 training return: tensor(46.2702, device='cuda:0')
episode: 182 training return: tensor(50.1655, device='cuda:0')
episode: 183 training return: tensor(47.4812, device='cuda:0')
epoch: 46 test_true_pfm: 72.89289419992885 sim_pfm: 47.09063948474941
episode: 184 training return: tensor(46.9488, device='cuda:0')
episode: 185 training return: tensor(48.4135, device='cuda:0')
episode: 186 training return: tensor(50.5127, device='cuda:0')
episode: 187 training return: tensor(47.2405, device='cuda:0')
epoch: 47 test_true_pfm: 80.67500182327277 sim_pfm: 49.07620036829612
episode: 188 training return: tensor(52.7537, device='cuda:0')
episode: 189 training return: tensor(48.4108, device='cuda:0')
episode: 190 training return: tensor(48.8188, device='cuda:0')
episode: 191 training return: tensor(44.8652, device='cuda:0')
epoch: 48 test_true_pfm: 80.57119397342272 sim_pfm: 50.56520747517934
episode: 192 training return: tensor(49.7310, device='cuda:0')
episode: 193 training return: tensor(50.7072, device='cuda:0')
episode: 194 training return: tensor(52.5386, device='cuda:0')
episode: 195 training return: tensor(53.0942, device='cuda:0')
epoch: 49 test_true_pfm: 80.89955110224568 sim_pfm: 51.490473687596385
episode: 196 training return: tensor(31.7455, device='cuda:0')
episode: 197 training return: tensor(52.2314, device='cuda:0')
episode: 198 training return: tensor(47.9528, device='cuda:0')
episode: 199 training return: tensor(47.7834, device='cuda:0')
epoch: 50 test_true_pfm: 79.45635044918701 sim_pfm: 52.214107993186914
episode: 200 training return: tensor(50.9274, device='cuda:0')
episode: 201 training return: tensor(54.7161, device='cuda:0')
episode: 202 training return: tensor(50.4475, device='cuda:0')
episode: 203 training return: tensor(46.3315, device='cuda:0')
epoch: 51 test_true_pfm: 79.43868309485768 sim_pfm: 51.80501649890211
episode: 204 training return: tensor(49.7791, device='cuda:0')
episode: 205 training return: tensor(54.9467, device='cuda:0')
episode: 206 training return: tensor(54.5129, device='cuda:0')
episode: 207 training return: tensor(50.9868, device='cuda:0')
epoch: 52 test_true_pfm: 58.17828724971406 sim_pfm: 49.5728718174214
episode: 208 training return: tensor(43.7818, device='cuda:0')
episode: 209 training return: tensor(48.4205, device='cuda:0')
episode: 210 training return: tensor(46.4771, device='cuda:0')
episode: 211 training return: tensor(49.0341, device='cuda:0')
epoch: 53 test_true_pfm: 71.09957493460675 sim_pfm: 50.100912343361415
episode: 212 training return: tensor(50.5919, device='cuda:0')
episode: 213 training return: tensor(48.7644, device='cuda:0')
episode: 214 training return: tensor(48.3699, device='cuda:0')
episode: 215 training return: tensor(49.6583, device='cuda:0')
epoch: 54 test_true_pfm: 73.86596513434661 sim_pfm: 37.74884059411124
episode: 216 training return: tensor(48.0702, device='cuda:0')
episode: 217 training return: tensor(25.2099, device='cuda:0')
episode: 218 training return: tensor(49.4419, device='cuda:0')
episode: 219 training return: tensor(46.8652, device='cuda:0')
epoch: 55 test_true_pfm: 78.68181351851969 sim_pfm: 48.1642026658461
episode: 220 training return: tensor(49.3846, device='cuda:0')
episode: 221 training return: tensor(48.9650, device='cuda:0')
episode: 222 training return: tensor(35.0686, device='cuda:0')
episode: 223 training return: tensor(42.4383, device='cuda:0')
epoch: 56 test_true_pfm: 78.62120997225244 sim_pfm: 50.419477839261525
episode: 224 training return: tensor(47.3435, device='cuda:0')
episode: 225 training return: tensor(44.7085, device='cuda:0')
episode: 226 training return: tensor(44.9491, device='cuda:0')
episode: 227 training return: tensor(50.5928, device='cuda:0')
epoch: 57 test_true_pfm: 80.41942411892927 sim_pfm: 50.280358258116756
episode: 228 training return: tensor(45.8988, device='cuda:0')
episode: 229 training return: tensor(36.1057, device='cuda:0')
episode: 230 training return: tensor(52.8719, device='cuda:0')
episode: 231 training return: tensor(46.6486, device='cuda:0')
epoch: 58 test_true_pfm: 82.66342915502973 sim_pfm: 51.38639275184251
episode: 232 training return: tensor(51.2004, device='cuda:0')
episode: 233 training return: tensor(50.4505, device='cuda:0')
episode: 234 training return: tensor(51.0698, device='cuda:0')
episode: 235 training return: tensor(50.9184, device='cuda:0')
epoch: 59 test_true_pfm: 80.13960604704621 sim_pfm: 52.08071125276619
episode: 236 training return: tensor(48.6998, device='cuda:0')
episode: 237 training return: tensor(62.1477, device='cuda:0')
episode: 238 training return: tensor(51.4743, device='cuda:0')
episode: 239 training return: tensor(52.8739, device='cuda:0')
epoch: 60 test_true_pfm: 93.63711030743984 sim_pfm: 51.32653838894912
episode: 240 training return: tensor(51.9471, device='cuda:0')
episode: 241 training return: tensor(49.7365, device='cuda:0')
episode: 242 training return: tensor(48.1401, device='cuda:0')
episode: 243 training return: tensor(49.6478, device='cuda:0')
epoch: 61 test_true_pfm: 74.75922933083338 sim_pfm: 50.416965237399566
episode: 244 training return: tensor(40.3667, device='cuda:0')
episode: 245 training return: tensor(50.1446, device='cuda:0')
episode: 246 training return: tensor(-13.0189, device='cuda:0')
episode: 247 training return: tensor(38.4622, device='cuda:0')
epoch: 62 test_true_pfm: 81.53212490794309 sim_pfm: 49.8911071244278
episode: 248 training return: tensor(48.0163, device='cuda:0')
episode: 249 training return: tensor(49.0079, device='cuda:0')
episode: 250 training return: tensor(40.6253, device='cuda:0')
episode: 251 training return: tensor(50.5884, device='cuda:0')
epoch: 63 test_true_pfm: 73.72401265481899 sim_pfm: 44.29315787912928
episode: 252 training return: tensor(52.6420, device='cuda:0')
episode: 253 training return: tensor(29.8370, device='cuda:0')
episode: 254 training return: tensor(51.6597, device='cuda:0')
episode: 255 training return: tensor(48.9967, device='cuda:0')
epoch: 64 test_true_pfm: 82.2006424383163 sim_pfm: 53.70318111956003
episode: 256 training return: tensor(50.9754, device='cuda:0')
episode: 257 training return: tensor(50.9408, device='cuda:0')
episode: 258 training return: tensor(51.2271, device='cuda:0')
episode: 259 training return: tensor(53.9281, device='cuda:0')
epoch: 65 test_true_pfm: 80.44508894256742 sim_pfm: 51.678200888866556
episode: 260 training return: tensor(52.6572, device='cuda:0')
episode: 261 training return: tensor(47.8332, device='cuda:0')
episode: 262 training return: tensor(48.8332, device='cuda:0')
episode: 263 training return: tensor(48.6656, device='cuda:0')
epoch: 66 test_true_pfm: 79.84485071424469 sim_pfm: 51.251017068902726
episode: 264 training return: tensor(52.6853, device='cuda:0')
episode: 265 training return: tensor(52.6178, device='cuda:0')
episode: 266 training return: tensor(52.0544, device='cuda:0')
episode: 267 training return: tensor(53.3719, device='cuda:0')
epoch: 67 test_true_pfm: 86.63864612465541 sim_pfm: 50.65407498489367
episode: 268 training return: tensor(53.5804, device='cuda:0')
episode: 269 training return: tensor(51.7010, device='cuda:0')
episode: 270 training return: tensor(51.1876, device='cuda:0')
episode: 271 training return: tensor(49.7364, device='cuda:0')
epoch: 68 test_true_pfm: 72.60079141432213 sim_pfm: 51.90237472225563
episode: 272 training return: tensor(53.4891, device='cuda:0')
episode: 273 training return: tensor(52.4612, device='cuda:0')
episode: 274 training return: tensor(52.3614, device='cuda:0')
episode: 275 training return: tensor(47.6982, device='cuda:0')
epoch: 69 test_true_pfm: 81.29247152401135 sim_pfm: 48.90625907405047
episode: 276 training return: tensor(53.4824, device='cuda:0')
episode: 277 training return: tensor(-9.3678, device='cuda:0')
episode: 278 training return: tensor(51.7180, device='cuda:0')
episode: 279 training return: tensor(49.9045, device='cuda:0')
epoch: 70 test_true_pfm: 74.06050486793113 sim_pfm: 48.00232745934627
episode: 280 training return: tensor(48.7353, device='cuda:0')
episode: 281 training return: tensor(49.4077, device='cuda:0')
episode: 282 training return: tensor(47.4533, device='cuda:0')
episode: 283 training return: tensor(53.9492, device='cuda:0')
epoch: 71 test_true_pfm: 86.07857267959443 sim_pfm: 50.48355267639854
episode: 284 training return: tensor(43.7178, device='cuda:0')
episode: 285 training return: tensor(50.2437, device='cuda:0')
episode: 286 training return: tensor(50.4792, device='cuda:0')
episode: 287 training return: tensor(-11.3802, device='cuda:0')
epoch: 72 test_true_pfm: 77.99874417867332 sim_pfm: 48.355188746342904
episode: 288 training return: tensor(53.5264, device='cuda:0')
episode: 289 training return: tensor(49.7373, device='cuda:0')
episode: 290 training return: tensor(51.5143, device='cuda:0')
episode: 291 training return: tensor(50.9391, device='cuda:0')
epoch: 73 test_true_pfm: 81.66916613914044 sim_pfm: 51.55120649196906
episode: 292 training return: tensor(44.0368, device='cuda:0')
episode: 293 training return: tensor(52.3808, device='cuda:0')
episode: 294 training return: tensor(52.0521, device='cuda:0')
episode: 295 training return: tensor(48.8732, device='cuda:0')
epoch: 74 test_true_pfm: 88.91480745351737 sim_pfm: 52.31876766810892
episode: 296 training return: tensor(51.8611, device='cuda:0')
episode: 297 training return: tensor(50.7016, device='cuda:0')
episode: 298 training return: tensor(25.0503, device='cuda:0')
episode: 299 training return: tensor(54.5075, device='cuda:0')
epoch: 75 test_true_pfm: 79.45868975177355 sim_pfm: 51.95122810708126
episode: 300 training return: tensor(48.4060, device='cuda:0')
episode: 301 training return: tensor(49.8309, device='cuda:0')
episode: 302 training return: tensor(50.7934, device='cuda:0')
episode: 303 training return: tensor(52.3416, device='cuda:0')
epoch: 76 test_true_pfm: 86.83891600188966 sim_pfm: 49.25963734819088
episode: 304 training return: tensor(51.4359, device='cuda:0')
episode: 305 training return: tensor(53.6151, device='cuda:0')
episode: 306 training return: tensor(-18.1233, device='cuda:0')
episode: 307 training return: tensor(53.6768, device='cuda:0')
epoch: 77 test_true_pfm: 81.6279083654151 sim_pfm: 54.4989881792164
episode: 308 training return: tensor(54.6067, device='cuda:0')
episode: 309 training return: tensor(53.5147, device='cuda:0')
episode: 310 training return: tensor(50.4376, device='cuda:0')
episode: 311 training return: tensor(55.6162, device='cuda:0')
epoch: 78 test_true_pfm: 81.29825091859172 sim_pfm: 52.478346136730394
episode: 312 training return: tensor(49.1696, device='cuda:0')
episode: 313 training return: tensor(55.2350, device='cuda:0')
episode: 314 training return: tensor(51.2621, device='cuda:0')
episode: 315 training return: tensor(52.5271, device='cuda:0')
epoch: 79 test_true_pfm: 84.49153716797096 sim_pfm: 51.64476218472119
episode: 316 training return: tensor(53.6428, device='cuda:0')
episode: 317 training return: tensor(50.5078, device='cuda:0')
episode: 318 training return: tensor(49.0289, device='cuda:0')
episode: 319 training return: tensor(53.4336, device='cuda:0')
epoch: 80 test_true_pfm: 87.24417987727998 sim_pfm: 53.27169076913269
episode: 320 training return: tensor(50.6632, device='cuda:0')
episode: 321 training return: tensor(52.2530, device='cuda:0')
episode: 322 training return: tensor(50.6422, device='cuda:0')
episode: 323 training return: tensor(52.6858, device='cuda:0')
epoch: 81 test_true_pfm: 83.0176219892483 sim_pfm: 51.71147769669187
episode: 324 training return: tensor(47.6219, device='cuda:0')
episode: 325 training return: tensor(51.0909, device='cuda:0')
episode: 326 training return: tensor(49.6738, device='cuda:0')
episode: 327 training return: tensor(-12.1931, device='cuda:0')
epoch: 82 test_true_pfm: 79.24605997384356 sim_pfm: 51.670382543327285
episode: 328 training return: tensor(49.0483, device='cuda:0')
episode: 329 training return: tensor(52.3694, device='cuda:0')
episode: 330 training return: tensor(51.9268, device='cuda:0')
episode: 331 training return: tensor(53.0304, device='cuda:0')
epoch: 83 test_true_pfm: 89.63894871866526 sim_pfm: 51.96089665544569
episode: 332 training return: tensor(52.4827, device='cuda:0')
episode: 333 training return: tensor(50.5530, device='cuda:0')
episode: 334 training return: tensor(51.7097, device='cuda:0')
episode: 335 training return: tensor(51.6979, device='cuda:0')
epoch: 84 test_true_pfm: 83.05019231317196 sim_pfm: 50.031252373271855
episode: 336 training return: tensor(51.0636, device='cuda:0')
episode: 337 training return: tensor(53.3553, device='cuda:0')
episode: 338 training return: tensor(53.6476, device='cuda:0')
episode: 339 training return: tensor(51.9660, device='cuda:0')
epoch: 85 test_true_pfm: 74.36841198702339 sim_pfm: 53.122459544212326
episode: 340 training return: tensor(54.9584, device='cuda:0')
episode: 341 training return: tensor(52.4737, device='cuda:0')
episode: 342 training return: tensor(53.2409, device='cuda:0')
episode: 343 training return: tensor(52.6387, device='cuda:0')
epoch: 86 test_true_pfm: 81.41989306050804 sim_pfm: 51.54330836154404
episode: 344 training return: tensor(53.3066, device='cuda:0')
episode: 345 training return: tensor(49.5155, device='cuda:0')
episode: 346 training return: tensor(48.6064, device='cuda:0')
episode: 347 training return: tensor(52.4576, device='cuda:0')
epoch: 87 test_true_pfm: 80.32668217436819 sim_pfm: 53.90881462037796
episode: 348 training return: tensor(49.5343, device='cuda:0')
episode: 349 training return: tensor(53.0560, device='cuda:0')
episode: 350 training return: tensor(55.4069, device='cuda:0')
episode: 351 training return: tensor(49.8297, device='cuda:0')
epoch: 88 test_true_pfm: 80.42013053898792 sim_pfm: 53.241651652852305
episode: 352 training return: tensor(50.6241, device='cuda:0')
episode: 353 training return: tensor(50.5125, device='cuda:0')
episode: 354 training return: tensor(54.8420, device='cuda:0')
episode: 355 training return: tensor(52.6960, device='cuda:0')
epoch: 89 test_true_pfm: 83.21267238920673 sim_pfm: 53.13058672590414
episode: 356 training return: tensor(52.8717, device='cuda:0')
episode: 357 training return: tensor(51.3859, device='cuda:0')
episode: 358 training return: tensor(51.0568, device='cuda:0')
episode: 359 training return: tensor(50.2924, device='cuda:0')
epoch: 90 test_true_pfm: 78.98634798386465 sim_pfm: 47.40696314357338
episode: 360 training return: tensor(51.3835, device='cuda:0')
episode: 361 training return: tensor(52.3847, device='cuda:0')
episode: 362 training return: tensor(45.9948, device='cuda:0')
episode: 363 training return: tensor(50.4454, device='cuda:0')
epoch: 91 test_true_pfm: 82.05222618522687 sim_pfm: 52.05686745917774
episode: 364 training return: tensor(49.6061, device='cuda:0')
episode: 365 training return: tensor(50.3892, device='cuda:0')
episode: 366 training return: tensor(51.2521, device='cuda:0')
episode: 367 training return: tensor(49.2891, device='cuda:0')
epoch: 92 test_true_pfm: 89.89191547234334 sim_pfm: 50.026404923415974
episode: 368 training return: tensor(49.9054, device='cuda:0')
episode: 369 training return: tensor(49.8178, device='cuda:0')
episode: 370 training return: tensor(51.5042, device='cuda:0')
episode: 371 training return: tensor(49.7466, device='cuda:0')
epoch: 93 test_true_pfm: 81.12143789300919 sim_pfm: 51.675127667479686
episode: 372 training return: tensor(52.8494, device='cuda:0')
episode: 373 training return: tensor(45.0607, device='cuda:0')
episode: 374 training return: tensor(49.9908, device='cuda:0')
episode: 375 training return: tensor(52.9070, device='cuda:0')
epoch: 94 test_true_pfm: 73.07909345536216 sim_pfm: 45.378155586484354
episode: 376 training return: tensor(50.3348, device='cuda:0')
episode: 377 training return: tensor(49.9444, device='cuda:0')
episode: 378 training return: tensor(47.4308, device='cuda:0')
episode: 379 training return: tensor(49.4349, device='cuda:0')
epoch: 95 test_true_pfm: 89.81414534905564 sim_pfm: 51.656463780836205
episode: 380 training return: tensor(50.1031, device='cuda:0')
episode: 381 training return: tensor(49.1283, device='cuda:0')
episode: 382 training return: tensor(50.7488, device='cuda:0')
episode: 383 training return: tensor(51.7371, device='cuda:0')
epoch: 96 test_true_pfm: 73.85945200500352 sim_pfm: 51.70209862743504
episode: 384 training return: tensor(50.9958, device='cuda:0')
episode: 385 training return: tensor(51.5555, device='cuda:0')
episode: 386 training return: tensor(49.5852, device='cuda:0')
episode: 387 training return: tensor(51.5050, device='cuda:0')
epoch: 97 test_true_pfm: 88.26282175842661 sim_pfm: 48.092374328529694
episode: 388 training return: tensor(51.3204, device='cuda:0')
episode: 389 training return: tensor(42.7303, device='cuda:0')
episode: 390 training return: tensor(46.3890, device='cuda:0')
episode: 391 training return: tensor(47.3641, device='cuda:0')
epoch: 98 test_true_pfm: 79.97313248408607 sim_pfm: 51.49839045251137
episode: 392 training return: tensor(52.8152, device='cuda:0')
episode: 393 training return: tensor(52.8836, device='cuda:0')
episode: 394 training return: tensor(49.4625, device='cuda:0')
episode: 395 training return: tensor(50.4661, device='cuda:0')
epoch: 99 test_true_pfm: 91.87773912667048 sim_pfm: 49.2677685624396
episode: 396 training return: tensor(45.4755, device='cuda:0')
episode: 397 training return: tensor(48.3048, device='cuda:0')
episode: 398 training return: tensor(55.2542, device='cuda:0')
episode: 399 training return: tensor(46.7112, device='cuda:0')
epoch: 100 test_true_pfm: 99.86897735835039 sim_pfm: 53.14878820324666
episode: 400 training return: tensor(51.9891, device='cuda:0')
episode: 401 training return: tensor(49.2091, device='cuda:0')
episode: 402 training return: tensor(49.2200, device='cuda:0')
episode: 403 training return: tensor(53.2944, device='cuda:0')
epoch: 101 test_true_pfm: 80.75212660307228 sim_pfm: 53.93698834364186
episode: 404 training return: tensor(50.9386, device='cuda:0')
episode: 405 training return: tensor(45.7502, device='cuda:0')
episode: 406 training return: tensor(50.1967, device='cuda:0')
episode: 407 training return: tensor(53.2998, device='cuda:0')
epoch: 102 test_true_pfm: 81.18981126314627 sim_pfm: 52.15545509153744
episode: 408 training return: tensor(51.7600, device='cuda:0')
episode: 409 training return: tensor(50.6575, device='cuda:0')
episode: 410 training return: tensor(38.5984, device='cuda:0')
episode: 411 training return: tensor(52.4594, device='cuda:0')
epoch: 103 test_true_pfm: 78.3364616145058 sim_pfm: 41.614277057751316
episode: 412 training return: tensor(50.3967, device='cuda:0')
episode: 413 training return: tensor(53.4456, device='cuda:0')
episode: 414 training return: tensor(50.0862, device='cuda:0')
episode: 415 training return: tensor(52.0862, device='cuda:0')
epoch: 104 test_true_pfm: 80.61495611299054 sim_pfm: 50.64001866247854
episode: 416 training return: tensor(50.6219, device='cuda:0')
episode: 417 training return: tensor(52.6021, device='cuda:0')
episode: 418 training return: tensor(51.2172, device='cuda:0')
episode: 419 training return: tensor(51.1876, device='cuda:0')
epoch: 105 test_true_pfm: 78.06248358089533 sim_pfm: 47.75428741685464
episode: 420 training return: tensor(49.5372, device='cuda:0')
episode: 421 training return: tensor(39.6541, device='cuda:0')
episode: 422 training return: tensor(50.2128, device='cuda:0')
episode: 423 training return: tensor(53.2426, device='cuda:0')
epoch: 106 test_true_pfm: 82.16190517876186 sim_pfm: 49.70294361268752
episode: 424 training return: tensor(-7.8837, device='cuda:0')
episode: 425 training return: tensor(49.5787, device='cuda:0')
episode: 426 training return: tensor(51.0228, device='cuda:0')
episode: 427 training return: tensor(39.4494, device='cuda:0')
epoch: 107 test_true_pfm: 80.65635904817745 sim_pfm: 51.80657789617544
episode: 428 training return: tensor(49.9305, device='cuda:0')
episode: 429 training return: tensor(53.4234, device='cuda:0')
episode: 430 training return: tensor(52.6998, device='cuda:0')
episode: 431 training return: tensor(27.3525, device='cuda:0')
epoch: 108 test_true_pfm: 81.24552695533762 sim_pfm: 51.222286698641255
episode: 432 training return: tensor(52.5735, device='cuda:0')
episode: 433 training return: tensor(52.6813, device='cuda:0')
episode: 434 training return: tensor(54.1084, device='cuda:0')
episode: 435 training return: tensor(53.3212, device='cuda:0')
epoch: 109 test_true_pfm: 80.21937796715079 sim_pfm: 50.745253311825216
episode: 436 training return: tensor(52.7590, device='cuda:0')
episode: 437 training return: tensor(52.5983, device='cuda:0')
episode: 438 training return: tensor(54.7119, device='cuda:0')
episode: 439 training return: tensor(54.9014, device='cuda:0')
epoch: 110 test_true_pfm: 81.19961163568448 sim_pfm: 50.44704223176232
episode: 440 training return: tensor(52.4408, device='cuda:0')
episode: 441 training return: tensor(50.5289, device='cuda:0')
episode: 442 training return: tensor(51.7738, device='cuda:0')
episode: 443 training return: tensor(49.1673, device='cuda:0')
epoch: 111 test_true_pfm: 80.18674017518343 sim_pfm: 52.441303447500104
episode: 444 training return: tensor(42.7578, device='cuda:0')
episode: 445 training return: tensor(53.5967, device='cuda:0')
episode: 446 training return: tensor(51.2902, device='cuda:0')
episode: 447 training return: tensor(50.2779, device='cuda:0')
epoch: 112 test_true_pfm: 79.70763023406543 sim_pfm: 52.395973992318616
episode: 448 training return: tensor(51.9052, device='cuda:0')
episode: 449 training return: tensor(46.8601, device='cuda:0')
episode: 450 training return: tensor(50.2802, device='cuda:0')
episode: 451 training return: tensor(52.0155, device='cuda:0')
epoch: 113 test_true_pfm: 80.61373113938146 sim_pfm: 50.4940188867331
episode: 452 training return: tensor(50.7292, device='cuda:0')
episode: 453 training return: tensor(52.0490, device='cuda:0')
episode: 454 training return: tensor(-11.9475, device='cuda:0')
episode: 455 training return: tensor(51.2493, device='cuda:0')
epoch: 114 test_true_pfm: 88.95506863085394 sim_pfm: 52.70511840320542
episode: 456 training return: tensor(49.0526, device='cuda:0')
episode: 457 training return: tensor(42.7401, device='cuda:0')
episode: 458 training return: tensor(46.6730, device='cuda:0')
episode: 459 training return: tensor(54.1828, device='cuda:0')
epoch: 115 test_true_pfm: 83.49898700082905 sim_pfm: 52.00230408910429
episode: 460 training return: tensor(52.3627, device='cuda:0')
episode: 461 training return: tensor(50.3599, device='cuda:0')
episode: 462 training return: tensor(52.5504, device='cuda:0')
episode: 463 training return: tensor(53.0206, device='cuda:0')
epoch: 116 test_true_pfm: 89.54289105073941 sim_pfm: 53.27143057874637
episode: 464 training return: tensor(55.2041, device='cuda:0')
episode: 465 training return: tensor(-12.7329, device='cuda:0')
episode: 466 training return: tensor(52.5992, device='cuda:0')
episode: 467 training return: tensor(51.4651, device='cuda:0')
epoch: 117 test_true_pfm: 81.21989381477945 sim_pfm: 53.2719341355958
episode: 468 training return: tensor(51.4451, device='cuda:0')
episode: 469 training return: tensor(50.4015, device='cuda:0')
episode: 470 training return: tensor(52.3471, device='cuda:0')
episode: 471 training return: tensor(51.7546, device='cuda:0')
epoch: 118 test_true_pfm: 80.14969630805463 sim_pfm: 49.74745824353886
episode: 472 training return: tensor(22.1938, device='cuda:0')
episode: 473 training return: tensor(50.4273, device='cuda:0')
episode: 474 training return: tensor(48.7633, device='cuda:0')
episode: 475 training return: tensor(54.3934, device='cuda:0')
epoch: 119 test_true_pfm: 80.45454238855999 sim_pfm: 54.31043081032694
episode: 476 training return: tensor(48.4457, device='cuda:0')
episode: 477 training return: tensor(52.6760, device='cuda:0')
episode: 478 training return: tensor(53.1494, device='cuda:0')
episode: 479 training return: tensor(50.1662, device='cuda:0')
epoch: 120 test_true_pfm: 81.30048117931884 sim_pfm: 50.81264350825804
episode: 480 training return: tensor(50.8337, device='cuda:0')
episode: 481 training return: tensor(49.5193, device='cuda:0')
episode: 482 training return: tensor(47.8892, device='cuda:0')
episode: 483 training return: tensor(52.2396, device='cuda:0')
epoch: 121 test_true_pfm: 73.8995883572884 sim_pfm: 49.23492884075968
episode: 484 training return: tensor(51.0280, device='cuda:0')
episode: 485 training return: tensor(52.5405, device='cuda:0')
episode: 486 training return: tensor(47.9851, device='cuda:0')
episode: 487 training return: tensor(54.6721, device='cuda:0')
epoch: 122 test_true_pfm: 79.08319785264989 sim_pfm: 35.79206513964455
episode: 488 training return: tensor(50.8737, device='cuda:0')
episode: 489 training return: tensor(53.4824, device='cuda:0')
episode: 490 training return: tensor(50.1300, device='cuda:0')
episode: 491 training return: tensor(48.1094, device='cuda:0')
epoch: 123 test_true_pfm: 89.6806744181341 sim_pfm: 50.752923954214204
episode: 492 training return: tensor(49.7858, device='cuda:0')
episode: 493 training return: tensor(52.1190, device='cuda:0')
episode: 494 training return: tensor(52.2987, device='cuda:0')
episode: 495 training return: tensor(50.6353, device='cuda:0')
epoch: 124 test_true_pfm: 89.26866769578191 sim_pfm: 35.85889284096775
episode: 496 training return: tensor(49.8028, device='cuda:0')
episode: 497 training return: tensor(52.8587, device='cuda:0')
episode: 498 training return: tensor(50.8945, device='cuda:0')
episode: 499 training return: tensor(50.1359, device='cuda:0')
epoch: 125 test_true_pfm: 87.66699194688104 sim_pfm: 46.27741195316776
episode: 500 training return: tensor(52.9396, device='cuda:0')
episode: 501 training return: tensor(49.5525, device='cuda:0')
episode: 502 training return: tensor(50.6561, device='cuda:0')
episode: 503 training return: tensor(51.4290, device='cuda:0')
epoch: 126 test_true_pfm: 73.02621017980323 sim_pfm: 45.05937491194927
episode: 504 training return: tensor(49.3148, device='cuda:0')
episode: 505 training return: tensor(49.6206, device='cuda:0')
episode: 506 training return: tensor(50.6121, device='cuda:0')
episode: 507 training return: tensor(53.5797, device='cuda:0')
epoch: 127 test_true_pfm: 88.00006463744519 sim_pfm: 53.2545900502184
episode: 508 training return: tensor(50.4077, device='cuda:0')
episode: 509 training return: tensor(50.4642, device='cuda:0')
episode: 510 training return: tensor(52.0769, device='cuda:0')
episode: 511 training return: tensor(50.4863, device='cuda:0')
epoch: 128 test_true_pfm: 81.38089842077727 sim_pfm: 51.67169521637843
episode: 512 training return: tensor(43.6088, device='cuda:0')
episode: 513 training return: tensor(52.5123, device='cuda:0')
episode: 514 training return: tensor(49.4464, device='cuda:0')
episode: 515 training return: tensor(50.3084, device='cuda:0')
epoch: 129 test_true_pfm: 79.95385477283985 sim_pfm: 50.81857665812713
episode: 516 training return: tensor(47.8509, device='cuda:0')
episode: 517 training return: tensor(48.9669, device='cuda:0')
episode: 518 training return: tensor(52.0195, device='cuda:0')
episode: 519 training return: tensor(49.4233, device='cuda:0')
epoch: 130 test_true_pfm: 87.98496608786775 sim_pfm: 53.236354967067015
episode: 520 training return: tensor(50.5051, device='cuda:0')
episode: 521 training return: tensor(47.1874, device='cuda:0')
episode: 522 training return: tensor(52.0613, device='cuda:0')
episode: 523 training return: tensor(50.9220, device='cuda:0')
epoch: 131 test_true_pfm: 80.99507291411405 sim_pfm: 49.96434081966872
episode: 524 training return: tensor(51.3769, device='cuda:0')
episode: 525 training return: tensor(49.5958, device='cuda:0')
episode: 526 training return: tensor(50.3796, device='cuda:0')
episode: 527 training return: tensor(50.8928, device='cuda:0')
epoch: 132 test_true_pfm: 80.23256995145186 sim_pfm: 49.3721194897138
episode: 528 training return: tensor(46.7651, device='cuda:0')
episode: 529 training return: tensor(54.0754, device='cuda:0')
episode: 530 training return: tensor(50.2036, device='cuda:0')
episode: 531 training return: tensor(53.5784, device='cuda:0')
epoch: 133 test_true_pfm: 81.53393773153933 sim_pfm: 51.66441146598081
episode: 532 training return: tensor(50.4660, device='cuda:0')
episode: 533 training return: tensor(49.5762, device='cuda:0')
episode: 534 training return: tensor(49.8286, device='cuda:0')
episode: 535 training return: tensor(50.5172, device='cuda:0')
epoch: 134 test_true_pfm: 75.08844746231998 sim_pfm: 49.75105808218359
episode: 536 training return: tensor(50.8752, device='cuda:0')
episode: 537 training return: tensor(50.2758, device='cuda:0')
episode: 538 training return: tensor(48.3652, device='cuda:0')
episode: 539 training return: tensor(54.7492, device='cuda:0')
epoch: 135 test_true_pfm: 80.02052584517867 sim_pfm: 47.288887297839395
episode: 540 training return: tensor(49.5202, device='cuda:0')
episode: 541 training return: tensor(50.3359, device='cuda:0')
episode: 542 training return: tensor(51.5288, device='cuda:0')
episode: 543 training return: tensor(50.5492, device='cuda:0')
epoch: 136 test_true_pfm: 73.2769069962895 sim_pfm: 49.93532826867886
episode: 544 training return: tensor(48.6744, device='cuda:0')
episode: 545 training return: tensor(49.3072, device='cuda:0')
episode: 546 training return: tensor(46.1308, device='cuda:0')
episode: 547 training return: tensor(49.2188, device='cuda:0')
epoch: 137 test_true_pfm: 80.4453545292495 sim_pfm: 48.26439144254546
episode: 548 training return: tensor(50.5775, device='cuda:0')
episode: 549 training return: tensor(50.1477, device='cuda:0')
episode: 550 training return: tensor(48.9556, device='cuda:0')
episode: 551 training return: tensor(60.3053, device='cuda:0')
epoch: 138 test_true_pfm: 82.36839484563953 sim_pfm: 27.201803558098618
episode: 552 training return: tensor(50.3950, device='cuda:0')
episode: 553 training return: tensor(54.7314, device='cuda:0')
episode: 554 training return: tensor(49.2509, device='cuda:0')
episode: 555 training return: tensor(51.3411, device='cuda:0')
epoch: 139 test_true_pfm: 73.04903604805808 sim_pfm: 51.78697515054373
episode: 556 training return: tensor(53.3418, device='cuda:0')
episode: 557 training return: tensor(49.6343, device='cuda:0')
episode: 558 training return: tensor(47.4841, device='cuda:0')
episode: 559 training return: tensor(49.8398, device='cuda:0')
epoch: 140 test_true_pfm: 80.91665555953739 sim_pfm: 48.51587117997114
episode: 560 training return: tensor(48.1816, device='cuda:0')
episode: 561 training return: tensor(51.7253, device='cuda:0')
episode: 562 training return: tensor(46.9084, device='cuda:0')
episode: 563 training return: tensor(55.5939, device='cuda:0')
epoch: 141 test_true_pfm: 74.14838335092031 sim_pfm: 46.447611379920275
episode: 564 training return: tensor(49.7696, device='cuda:0')
episode: 565 training return: tensor(74.2601, device='cuda:0')
episode: 566 training return: tensor(50.9787, device='cuda:0')
episode: 567 training return: tensor(51.9082, device='cuda:0')
epoch: 142 test_true_pfm: 80.35779757949356 sim_pfm: 52.736440547526584
episode: 568 training return: tensor(50.8431, device='cuda:0')
episode: 569 training return: tensor(52.6283, device='cuda:0')
episode: 570 training return: tensor(53.3545, device='cuda:0')
episode: 571 training return: tensor(49.3185, device='cuda:0')
epoch: 143 test_true_pfm: 88.2307264205991 sim_pfm: 51.44722976047196
episode: 572 training return: tensor(50.5505, device='cuda:0')
episode: 573 training return: tensor(52.7735, device='cuda:0')
episode: 574 training return: tensor(50.1178, device='cuda:0')
episode: 575 training return: tensor(49.5997, device='cuda:0')
epoch: 144 test_true_pfm: 81.83387392184194 sim_pfm: 48.11643659974798
episode: 576 training return: tensor(50.4862, device='cuda:0')
episode: 577 training return: tensor(53.6978, device='cuda:0')
episode: 578 training return: tensor(50.8903, device='cuda:0')
episode: 579 training return: tensor(52.5709, device='cuda:0')
epoch: 145 test_true_pfm: 81.06830354899027 sim_pfm: 48.949486739304845
episode: 580 training return: tensor(48.7719, device='cuda:0')
episode: 581 training return: tensor(48.7936, device='cuda:0')
episode: 582 training return: tensor(45.9797, device='cuda:0')
episode: 583 training return: tensor(48.6804, device='cuda:0')
epoch: 146 test_true_pfm: 86.48054973389867 sim_pfm: 48.041551014658765
episode: 584 training return: tensor(48.3055, device='cuda:0')
episode: 585 training return: tensor(49.0620, device='cuda:0')
episode: 586 training return: tensor(50.5570, device='cuda:0')
episode: 587 training return: tensor(51.8947, device='cuda:0')
epoch: 147 test_true_pfm: 80.33556334257855 sim_pfm: 50.282965955499094
episode: 588 training return: tensor(50.3496, device='cuda:0')
episode: 589 training return: tensor(50.2755, device='cuda:0')
episode: 590 training return: tensor(52.8999, device='cuda:0')
episode: 591 training return: tensor(51.4255, device='cuda:0')
epoch: 148 test_true_pfm: 73.61404212162225 sim_pfm: 51.179765345185295
episode: 592 training return: tensor(49.3217, device='cuda:0')
episode: 593 training return: tensor(53.0580, device='cuda:0')
episode: 594 training return: tensor(50.1132, device='cuda:0')
episode: 595 training return: tensor(51.8766, device='cuda:0')
epoch: 149 test_true_pfm: 80.32082276345318 sim_pfm: 51.759736013098156
episode: 596 training return: tensor(49.8748, device='cuda:0')
episode: 597 training return: tensor(51.8402, device='cuda:0')
episode: 598 training return: tensor(25.0562, device='cuda:0')
episode: 599 training return: tensor(48.2952, device='cuda:0')
epoch: 150 test_true_pfm: 81.87384546206677 sim_pfm: 51.56647964661242
