['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '4', '--data', '10000', '--sub']
epoch: 0 training_loss 0.2636519727855921 test_loss: 0.17831199169158934
epoch: 1 training_loss 0.14719661932438613 test_loss: 0.14983893632888795
epoch: 2 training_loss 0.13870374049991369 test_loss: 0.1560987114906311
epoch: 3 training_loss 0.12667025823146105 test_loss: 0.12641003131866455
epoch: 4 training_loss 0.12358035568147897 test_loss: 0.1282695412635803
epoch: 5 training_loss 0.11919803414493799 test_loss: 0.11882266998291016
epoch: 6 training_loss 0.10880434688180685 test_loss: 0.14729321002960205
epoch: 7 training_loss 0.10887044180184603 test_loss: 0.12293092012405396
epoch: 8 training_loss 0.10485714258626104 test_loss: 0.13736869096755983
epoch: 9 training_loss 0.09858325570821762 test_loss: 0.13902647495269777
epoch: 10 training_loss 0.11154434204101563 test_loss: 0.12032104730606079
epoch: 11 training_loss 0.1054893209785223 test_loss: 0.1365370512008667
epoch: 12 training_loss 0.10137318905442953 test_loss: 0.11586143970489501
epoch: 13 training_loss 0.10434310972690582 test_loss: 0.1288533926010132
epoch: 14 training_loss 0.09809231117367745 test_loss: 0.11069869995117188
epoch: 15 training_loss 0.10217436181381345 test_loss: 0.11800402402877808
epoch: 16 training_loss 0.09883903428912162 test_loss: 0.11765820980072021
epoch: 17 training_loss 0.1017388110421598 test_loss: 0.11908661127090454
epoch: 18 training_loss 0.09958958275616168 test_loss: 0.11896347999572754
epoch: 19 training_loss 0.09871968291699887 test_loss: 0.12636057138442994
epoch: 20 training_loss 0.09515889851376415 test_loss: 0.12946237325668336
epoch: 21 training_loss 0.09122260536998511 test_loss: 0.11907871961593627
epoch: 22 training_loss 0.09108679592609406 test_loss: 0.1163948655128479
epoch: 23 training_loss 0.08923655139282345 test_loss: 0.12508009672164916
epoch: 24 training_loss 0.09330979324877262 test_loss: 0.1089634656906128
epoch: 25 training_loss 0.09146691283211111 test_loss: 0.10287277698516846
epoch: 26 training_loss 0.08847401041537523 test_loss: 0.11601405143737793
epoch: 27 training_loss 0.10113692138344049 test_loss: 0.11639753580093384
epoch: 28 training_loss 0.08694160521030427 test_loss: 0.10440630912780761
epoch: 29 training_loss 0.08573717337101698 test_loss: 0.12350698709487914
epoch: 30 training_loss 0.09177014775574208 test_loss: 0.09810617566108704
epoch: 31 training_loss 0.09133560644462704 test_loss: 0.11137927770614624
epoch: 32 training_loss 0.08687078250572085 test_loss: 0.11590685844421386
epoch: 33 training_loss 0.08792957572266459 test_loss: 0.10557984113693238
epoch: 34 training_loss 0.09342167967930436 test_loss: 0.12052079439163207
epoch: 35 training_loss 0.0891580232605338 test_loss: 0.11390197277069092
epoch: 36 training_loss 0.08238614071160555 test_loss: 0.10874431133270264
epoch: 37 training_loss 0.09111414887011052 test_loss: 0.1054263710975647
epoch: 38 training_loss 0.08805912707000971 test_loss: 0.11695557832717896
epoch: 39 training_loss 0.08825356783345342 test_loss: 0.11541644334793091
epoch: 40 training_loss 0.08691930258646607 test_loss: 0.11271044015884399
epoch: 41 training_loss 0.07952276648953557 test_loss: 0.10573166608810425
epoch: 42 training_loss 0.0814295001514256 test_loss: 0.12446272373199463
epoch: 43 training_loss 0.0837587758898735 test_loss: 0.1129568099975586
epoch: 44 training_loss 0.0921996008977294 test_loss: 0.1118661880493164
epoch: 45 training_loss 0.0877326806820929 test_loss: 0.11597520112991333
epoch: 46 training_loss 0.07826976614072918 test_loss: 0.11039497852325439
epoch: 47 training_loss 0.08737572835758328 test_loss: 0.11600364446640014
epoch: 48 training_loss 0.08078684696927667 test_loss: 0.1309111475944519
epoch: 49 training_loss 0.08122154325246811 test_loss: 0.11156346797943115
epoch: 50 training_loss 0.083817198574543 test_loss: 0.11078271865844727
epoch: 51 training_loss 0.0789198506437242 test_loss: 0.1211957335472107
epoch: 52 training_loss 0.07803735561668873 test_loss: 0.12220535278320313
epoch: 53 training_loss 0.07333762193098664 test_loss: 0.12373019456863403
epoch: 54 training_loss 0.08376010652631521 test_loss: 0.10903792381286621
epoch: 55 training_loss 0.08626488588750363 test_loss: 0.11126176118850709
epoch: 56 training_loss 0.08240859437733888 test_loss: 0.10494868755340576
epoch: 57 training_loss 0.07375378743745387 test_loss: 0.11240663528442382
epoch: 58 training_loss 0.08919725645333529 test_loss: 0.12366033792495727
epoch: 59 training_loss 0.0830311656370759 test_loss: 0.10226229429244996
epoch: 60 training_loss 0.08291919134557248 test_loss: 0.1136359453201294
epoch: 61 training_loss 0.08099597290158272 test_loss: 0.11833771467208862
epoch: 62 training_loss 0.07312371075153351 test_loss: 0.11026901006698608
epoch: 63 training_loss 0.07388037715107203 test_loss: 0.13242532014846803
epoch: 64 training_loss 0.07859943393617869 test_loss: 0.12707144021987915
epoch: 65 training_loss 0.0769072911515832 test_loss: 0.12428157329559326
epoch: 66 training_loss 0.0788206597417593 test_loss: 0.11715078353881836
epoch: 67 training_loss 0.08081579457968474 test_loss: 0.12017732858657837
epoch: 68 training_loss 0.07549293274059891 test_loss: 0.11355729103088379
epoch: 69 training_loss 0.0770491431094706 test_loss: 0.10785461664199829
epoch: 70 training_loss 0.07962093720212579 test_loss: 0.11700615882873536
epoch: 71 training_loss 0.07359794674441218 test_loss: 0.11478204727172851
epoch: 72 training_loss 0.07353954350575805 test_loss: 0.13147175312042236
epoch: 73 training_loss 0.07141570994630456 test_loss: 0.1161042332649231
epoch: 74 training_loss 0.07478830168023705 test_loss: 0.1291273355484009
epoch: 75 training_loss 0.07419267774559557 test_loss: 0.11733313798904418
epoch: 76 training_loss 0.07630789507180452 test_loss: 0.1335279107093811
epoch: 77 training_loss 0.06670568596571684 test_loss: 0.11195091009140015
epoch: 78 training_loss 0.07135026521980763 test_loss: 0.12095330953598023
epoch: 79 training_loss 0.07511337814852595 test_loss: 0.12787240743637085
epoch: 80 training_loss 0.07981735018081963 test_loss: 0.13182032108306885
epoch: 81 training_loss 0.07569983778521419 test_loss: 0.11723134517669678
epoch: 82 training_loss 0.0753644342534244 test_loss: 0.12488255500793458
epoch: 83 training_loss 0.0741446921788156 test_loss: 0.1186630368232727
epoch: 84 training_loss 0.06976228261366486 test_loss: 0.12529131174087524
epoch: 85 training_loss 0.06687446858733892 test_loss: 0.13227473497390746
epoch: 86 training_loss 0.06632128881290555 test_loss: 0.12927620410919188
epoch: 87 training_loss 0.0738726183027029 test_loss: 0.1304706335067749
epoch: 88 training_loss 0.07316251272335648 test_loss: 0.13268778324127198
epoch: 89 training_loss 0.07019018178805708 test_loss: 0.11180039644241332
epoch: 90 training_loss 0.07104510203003883 test_loss: 0.12183158397674561
epoch: 91 training_loss 0.07229260947555304 test_loss: 0.13236435651779174
epoch: 92 training_loss 0.0698141026031226 test_loss: 0.12357698678970337
epoch: 93 training_loss 0.07134005080908537 test_loss: 0.12903981208801268
epoch: 94 training_loss 0.06781918479129673 test_loss: 0.12314066886901856
epoch: 95 training_loss 0.06868139274418354 test_loss: 0.1183011531829834
epoch: 96 training_loss 0.0741435293853283 test_loss: 0.1393111228942871
epoch: 97 training_loss 0.07510645085945726 test_loss: 0.12945045232772828
epoch: 98 training_loss 0.06700139024294913 test_loss: 0.12554186582565308
epoch: 99 training_loss 0.06772517876699567 test_loss: 0.12414443492889404
epoch: 100 training_loss 0.0678629314340651 test_loss: 0.12900475263595582
epoch: 101 training_loss 0.06560404634103179 test_loss: 0.13049190044403075
epoch: 102 training_loss 0.07192326627671719 test_loss: 0.1310072660446167
epoch: 103 training_loss 0.06650537655688822 test_loss: 0.11990784406661988
epoch: 104 training_loss 0.07524887517094613 test_loss: 0.14736186265945433
epoch: 105 training_loss 0.06923433699645103 test_loss: 0.11797199249267579
epoch: 106 training_loss 0.0706134257465601 test_loss: 0.13223025798797608
epoch: 107 training_loss 0.07115194158628584 test_loss: 0.11520692110061645
epoch: 108 training_loss 0.06605315025895835 test_loss: 0.12901875972747803
epoch: 109 training_loss 0.06861863887868822 test_loss: 0.1132161021232605
epoch: 110 training_loss 0.06930381551384926 test_loss: 0.1469024896621704
epoch: 111 training_loss 0.07086379694752395 test_loss: 0.12485884428024292
epoch: 112 training_loss 0.06375057331286371 test_loss: 0.11985334157943725
epoch: 113 training_loss 0.06927291485946625 test_loss: 0.13704707622528076
epoch: 114 training_loss 0.06645051341503859 test_loss: 0.11300421953201294
epoch: 115 training_loss 0.07007927040569484 test_loss: 0.1329776167869568
epoch: 116 training_loss 0.06866313255392015 test_loss: 0.14447457790374757
epoch: 117 training_loss 0.06493908518925309 test_loss: 0.107364022731781
epoch: 118 training_loss 0.06748762431088835 test_loss: 0.12015448808670044
epoch: 119 training_loss 0.075543148573488 test_loss: 0.12575680017471313
epoch: 120 training_loss 0.06933745548129082 test_loss: 0.13459370136260987
epoch: 121 training_loss 0.06882385949604214 test_loss: 0.15154292583465576
epoch: 122 training_loss 0.06453126991167664 test_loss: 0.1450545072555542
epoch: 123 training_loss 0.06596875701099635 test_loss: 0.14537880420684815
epoch: 124 training_loss 0.07144607663154602 test_loss: 0.1211226224899292
epoch: 125 training_loss 0.06803563213907182 test_loss: 0.14331550598144532
epoch: 126 training_loss 0.059504584791138765 test_loss: 0.1582977890968323
epoch: 127 training_loss 0.06521796161308885 test_loss: 0.1438807487487793
epoch: 128 training_loss 0.06501190562732517 test_loss: 0.14022133350372315
epoch: 129 training_loss 0.0592912829760462 test_loss: 0.12108156681060792
epoch: 130 training_loss 0.06575016571208835 test_loss: 0.13556110858917236
epoch: 131 training_loss 0.05971463395282626 test_loss: 0.12503975629806519
epoch: 132 training_loss 0.065736453961581 test_loss: 0.1597524404525757
epoch: 133 training_loss 0.06796890618279576 test_loss: 0.1382654309272766
epoch: 134 training_loss 0.057285064412280914 test_loss: 0.12531131505966187
epoch: 135 training_loss 0.06959681319072843 test_loss: 0.13716819286346435
epoch: 136 training_loss 0.06865693794563413 test_loss: 0.11874768733978272
epoch: 137 training_loss 0.0728196674399078 test_loss: 0.14445470571517943
epoch: 138 training_loss 0.06294407033361495 test_loss: 0.1425890803337097
epoch: 139 training_loss 0.0699855530820787 test_loss: 0.12668421268463134
epoch: 140 training_loss 0.060044463155791164 test_loss: 0.12637643814086913
epoch: 141 training_loss 0.059979132134467365 test_loss: 0.1373183012008667
epoch: 142 training_loss 0.06152806276455522 test_loss: 0.13268156051635743
epoch: 143 training_loss 0.06166944081895053 test_loss: 0.1338020920753479
epoch: 144 training_loss 0.06931770990602672 test_loss: 0.12341787815093994
epoch: 145 training_loss 0.06409632979892194 test_loss: 0.1365818500518799
epoch: 146 training_loss 0.060317457905039194 test_loss: 0.15200674533843994
epoch: 147 training_loss 0.06449579857289792 test_loss: 0.14529068470001222
epoch: 148 training_loss 0.0648783559165895 test_loss: 0.145898699760437
epoch: 149 training_loss 0.06890817115083336 test_loss: 0.12320882081985474
epoch: 0 training_loss 39.97507423400879 test_loss: 22.78382568359375
epoch: 1 training_loss 17.891250772476198 test_loss: 15.363525390625
epoch: 2 training_loss 13.641345958709717 test_loss: 12.568227386474609
epoch: 3 training_loss 11.370560255050659 test_loss: 10.656676483154296
epoch: 4 training_loss 9.943961267471314 test_loss: 9.626763916015625
epoch: 5 training_loss 9.090665373802185 test_loss: 8.773086547851562
epoch: 6 training_loss 8.199442582130432 test_loss: 8.275303649902344
epoch: 7 training_loss 7.7279126071929936 test_loss: 7.865772247314453
epoch: 8 training_loss 7.214145245552063 test_loss: 7.282783508300781
epoch: 9 training_loss 6.809449181556702 test_loss: 6.874684906005859
epoch: 10 training_loss 6.428323421478272 test_loss: 6.470155334472656
epoch: 11 training_loss 6.192170605659485 test_loss: 6.148596954345703
epoch: 12 training_loss 5.914237470626831 test_loss: 5.947978210449219
epoch: 13 training_loss 5.668269348144531 test_loss: 5.798273086547852
epoch: 14 training_loss 5.642695622444153 test_loss: 5.725168991088867
epoch: 15 training_loss 5.323257975578308 test_loss: 5.536156463623047
epoch: 16 training_loss 5.174942879676819 test_loss: 5.393700408935547
epoch: 17 training_loss 5.082521545886993 test_loss: 5.227800369262695
epoch: 18 training_loss 4.888748450279236 test_loss: 5.012310409545899
epoch: 19 training_loss 4.7783419799804685 test_loss: 4.816059112548828
epoch: 20 training_loss 4.617064430713653 test_loss: 4.818915557861328
epoch: 21 training_loss 4.5011855053901675 test_loss: 4.775490951538086
epoch: 22 training_loss 4.497589161396027 test_loss: 4.490375900268555
epoch: 23 training_loss 4.393339414596557 test_loss: 4.341046905517578
epoch: 24 training_loss 4.244220108985901 test_loss: 4.529533767700196
epoch: 25 training_loss 4.265567886829376 test_loss: 4.347131729125977
epoch: 26 training_loss 4.121963548660278 test_loss: 4.2154487609863285
epoch: 27 training_loss 4.026689503192902 test_loss: 4.131681823730469
epoch: 28 training_loss 3.925983338356018 test_loss: 4.163228225708008
epoch: 29 training_loss 3.797005839347839 test_loss: 4.063022232055664
epoch: 30 training_loss 3.796186707019806 test_loss: 4.095744705200195
epoch: 31 training_loss 3.739574553966522 test_loss: 3.8806316375732424
epoch: 32 training_loss 3.737897343635559 test_loss: 3.986520767211914
epoch: 33 training_loss 3.625563769340515 test_loss: 3.8784488677978515
epoch: 34 training_loss 3.635588729381561 test_loss: 3.813630294799805
epoch: 35 training_loss 3.5903264236450196 test_loss: 3.8042369842529298
epoch: 36 training_loss 3.5010898661613465 test_loss: 3.8132083892822264
epoch: 37 training_loss 3.460603563785553 test_loss: 3.842509460449219
epoch: 38 training_loss 3.4001931047439573 test_loss: 3.6737506866455076
epoch: 39 training_loss 3.4126055240631104 test_loss: 3.5751461029052733
epoch: 40 training_loss 3.368149199485779 test_loss: 3.6084938049316406
epoch: 41 training_loss 3.301541829109192 test_loss: 3.574203872680664
epoch: 42 training_loss 3.283156213760376 test_loss: 3.529986572265625
epoch: 43 training_loss 3.2319963002204894 test_loss: 3.5151657104492187
epoch: 44 training_loss 3.2412685990333556 test_loss: 3.5380504608154295
epoch: 45 training_loss 3.2253140878677367 test_loss: 3.3933284759521483
epoch: 46 training_loss 3.21901154756546 test_loss: 3.421403503417969
epoch: 47 training_loss 3.1083644652366638 test_loss: 3.3640541076660155
epoch: 48 training_loss 3.086973776817322 test_loss: 3.256745529174805
epoch: 49 training_loss 3.073680636882782 test_loss: 3.41171875
epoch: 50 training_loss 3.075968496799469 test_loss: 3.274148941040039
epoch: 51 training_loss 3.0366479182243347 test_loss: 3.2170005798339845
epoch: 52 training_loss 2.9300000500679015 test_loss: 3.1221546173095702
epoch: 53 training_loss 2.9731110310554505 test_loss: 3.221760559082031
epoch: 54 training_loss 2.9474696850776674 test_loss: 3.136738967895508
epoch: 55 training_loss 2.9318718695640564 test_loss: 3.257864761352539
epoch: 56 training_loss 2.8912870621681215 test_loss: 3.1294593811035156
epoch: 57 training_loss 2.912384648323059 test_loss: 3.1077543258666993
epoch: 58 training_loss 2.870936098098755 test_loss: 3.111397361755371
epoch: 59 training_loss 2.8472731721401217 test_loss: 2.985893440246582
epoch: 60 training_loss 2.785767138004303 test_loss: 3.0408260345458986
epoch: 61 training_loss 2.8084255695343017 test_loss: 3.029718589782715
epoch: 62 training_loss 2.808178765773773 test_loss: 3.012652778625488
epoch: 63 training_loss 2.7552979969978333 test_loss: 3.026058578491211
epoch: 64 training_loss 2.7427880716323854 test_loss: 2.94067440032959
epoch: 65 training_loss 2.698096580505371 test_loss: 2.939848709106445
epoch: 66 training_loss 2.7416419196128845 test_loss: 2.998555564880371
epoch: 67 training_loss 2.6680000042915344 test_loss: 2.903845024108887
epoch: 68 training_loss 2.713023166656494 test_loss: 2.913610649108887
epoch: 69 training_loss 2.6835727286338806 test_loss: 2.9332576751708985
epoch: 70 training_loss 2.653174788951874 test_loss: 2.9140562057495116
epoch: 71 training_loss 2.713566379547119 test_loss: 2.847747039794922
epoch: 72 training_loss 2.5952579832077025 test_loss: 2.7532352447509765
epoch: 73 training_loss 2.6101653027534484 test_loss: 2.744239616394043
epoch: 74 training_loss 2.606593384742737 test_loss: 2.8118730545043946
epoch: 75 training_loss 2.628576775789261 test_loss: 2.782366180419922
epoch: 76 training_loss 2.58512659072876 test_loss: 2.8125164031982424
epoch: 77 training_loss 2.55407551407814 test_loss: 2.801801300048828
epoch: 78 training_loss 2.519491821527481 test_loss: 2.8353586196899414
epoch: 79 training_loss 2.6222615218162537 test_loss: 2.712298583984375
epoch: 80 training_loss 2.535137757062912 test_loss: 2.7784515380859376
epoch: 81 training_loss 2.5820390033721923 test_loss: 2.694003105163574
epoch: 82 training_loss 2.5014009296894075 test_loss: 2.7592248916625977
epoch: 83 training_loss 2.4977472400665284 test_loss: 2.6793371200561524
epoch: 84 training_loss 2.526251494884491 test_loss: 2.7615280151367188
epoch: 85 training_loss 2.4930766153335573 test_loss: 2.691900634765625
epoch: 86 training_loss 2.475553514957428 test_loss: 2.6861440658569338
epoch: 87 training_loss 2.5043494594097138 test_loss: 2.7755125045776365
epoch: 88 training_loss 2.445959895849228 test_loss: 2.7839544296264647
epoch: 89 training_loss 2.411010468006134 test_loss: 2.71262264251709
epoch: 90 training_loss 2.4871554875373842 test_loss: 2.7004487991333006
epoch: 91 training_loss 2.4240282452106476 test_loss: 2.7176630020141603
epoch: 92 training_loss 2.517253019809723 test_loss: 2.602724075317383
epoch: 93 training_loss 2.392910077571869 test_loss: 2.7308101654052734
epoch: 94 training_loss 2.4571642053127287 test_loss: 2.619025993347168
epoch: 95 training_loss 2.3897211039066315 test_loss: 2.6368295669555666
epoch: 96 training_loss 2.3879153323173523 test_loss: 2.6231618881225587
epoch: 97 training_loss 2.355873878002167 test_loss: 2.648242950439453
epoch: 98 training_loss 2.393678534030914 test_loss: 2.6399744033813475
epoch: 99 training_loss 2.371928230524063 test_loss: 2.579751205444336
epoch: 100 training_loss 2.373826268911362 test_loss: 2.6465127944946287
epoch: 101 training_loss 2.409880447387695 test_loss: 2.586164855957031
epoch: 102 training_loss 2.3629427540302275 test_loss: 2.600712776184082
epoch: 103 training_loss 2.3628294336795808 test_loss: 2.5731714248657225
epoch: 104 training_loss 2.319052336215973 test_loss: 2.6834857940673826
epoch: 105 training_loss 2.3322766864299775 test_loss: 2.539789581298828
epoch: 106 training_loss 2.339489974975586 test_loss: 2.6193309783935548
epoch: 107 training_loss 2.345658587217331 test_loss: 2.5767383575439453
epoch: 108 training_loss 2.3013099074363708 test_loss: 2.495662307739258
epoch: 109 training_loss 2.279005571603775 test_loss: 2.632257843017578
epoch: 110 training_loss 2.3061574041843413 test_loss: 2.489725875854492
epoch: 111 training_loss 2.3147212362289427 test_loss: 2.5462160110473633
epoch: 112 training_loss 2.2335548651218415 test_loss: 2.6052722930908203
epoch: 113 training_loss 2.269343398809433 test_loss: 2.557269477844238
epoch: 114 training_loss 2.2869650816917417 test_loss: 2.5202396392822264
epoch: 115 training_loss 2.2665369391441343 test_loss: 2.5401290893554687
epoch: 116 training_loss 2.2874525701999664 test_loss: 2.4704048156738283
epoch: 117 training_loss 2.3009379935264587 test_loss: 2.5007781982421875
epoch: 118 training_loss 2.306295953989029 test_loss: 2.585379791259766
epoch: 119 training_loss 2.228352748155594 test_loss: 2.4392152786254884
epoch: 120 training_loss 2.2726485180854796 test_loss: 2.44545841217041
epoch: 121 training_loss 2.217012392282486 test_loss: 2.453721809387207
epoch: 122 training_loss 2.233830704689026 test_loss: 2.4807580947875976
epoch: 123 training_loss 2.2247647857666015 test_loss: 2.543054389953613
epoch: 124 training_loss 2.242910569906235 test_loss: 2.461199951171875
epoch: 125 training_loss 2.2084408795833586 test_loss: 2.4919511795043947
epoch: 126 training_loss 2.2637351620197297 test_loss: 2.4631978988647463
epoch: 127 training_loss 2.2398930191993713 test_loss: 2.5175443649291993
epoch: 128 training_loss 2.237787549495697 test_loss: 2.401884841918945
epoch: 129 training_loss 2.2025133323669435 test_loss: 2.408183288574219
epoch: 130 training_loss 2.21388435959816 test_loss: 2.5419254302978516
epoch: 131 training_loss 2.211503039598465 test_loss: 2.525162696838379
epoch: 132 training_loss 2.202140339612961 test_loss: 2.403315544128418
epoch: 133 training_loss 2.2459417271614073 test_loss: 2.474641036987305
epoch: 134 training_loss 2.2402726304531098 test_loss: 2.3802654266357424
epoch: 135 training_loss 2.239120522737503 test_loss: 2.461928939819336
epoch: 136 training_loss 2.217318034172058 test_loss: 2.339920425415039
epoch: 137 training_loss 2.153551069498062 test_loss: 2.435740089416504
epoch: 138 training_loss 2.1808254146575927 test_loss: 2.3980600357055666
epoch: 139 training_loss 2.1747319746017455 test_loss: 2.3871606826782226
epoch: 140 training_loss 2.1512263476848603 test_loss: 2.46136474609375
epoch: 141 training_loss 2.203039675951004 test_loss: 2.4718755722045898
epoch: 142 training_loss 2.1827200543880463 test_loss: 2.443280029296875
epoch: 143 training_loss 2.1470471119880674 test_loss: 2.3560667037963867
epoch: 144 training_loss 2.1524267995357516 test_loss: 2.3697681427001953
epoch: 145 training_loss 2.1475401878356934 test_loss: 2.3332502365112306
epoch: 146 training_loss 2.1398593616485595 test_loss: 2.3820571899414062
epoch: 147 training_loss 2.153910074234009 test_loss: 2.3247026443481444
epoch: 148 training_loss 2.0954908335208895 test_loss: 2.3429147720336916
epoch: 149 training_loss 2.158775109052658 test_loss: 2.361882209777832
2880.301544249104
episode: 0 training return: tensor(-375.2087, device='cuda:0')
episode: 1 training return: tensor(-340.0695, device='cuda:0')
episode: 2 training return: tensor(111.2559, device='cuda:0')
episode: 3 training return: tensor(240.7609, device='cuda:0')
epoch: 1 test_true_pfm: 2723.4582891989903 sim_pfm: 1.8546959660986129
episode: 4 training return: tensor(231.3408, device='cuda:0')
episode: 5 training return: tensor(152.2918, device='cuda:0')
episode: 6 training return: tensor(-166.0316, device='cuda:0')
episode: 7 training return: tensor(-233.6851, device='cuda:0')
epoch: 2 test_true_pfm: 2709.4840353805507 sim_pfm: 171.8929062045645
episode: 8 training return: tensor(-59.4015, device='cuda:0')
episode: 9 training return: tensor(25.1393, device='cuda:0')
episode: 10 training return: tensor(-435.4163, device='cuda:0')
episode: 11 training return: tensor(-214.4786, device='cuda:0')
epoch: 3 test_true_pfm: 3330.4423252722027 sim_pfm: 239.1305645488125
episode: 12 training return: tensor(114.0842, device='cuda:0')
episode: 13 training return: tensor(-342.3846, device='cuda:0')
episode: 14 training return: tensor(104.0338, device='cuda:0')
episode: 15 training return: tensor(191.3251, device='cuda:0')
epoch: 4 test_true_pfm: 2860.75548722792 sim_pfm: -335.9032437226754
episode: 16 training return: tensor(186.7042, device='cuda:0')
episode: 17 training return: tensor(-274.1414, device='cuda:0')
episode: 18 training return: tensor(123.6211, device='cuda:0')
episode: 19 training return: tensor(-48.0809, device='cuda:0')
epoch: 5 test_true_pfm: 3059.9195235821876 sim_pfm: 67.12369760190875
episode: 20 training return: tensor(-265.1104, device='cuda:0')
episode: 21 training return: tensor(212.7686, device='cuda:0')
episode: 22 training return: tensor(-97.1083, device='cuda:0')
episode: 23 training return: tensor(192.8832, device='cuda:0')
epoch: 6 test_true_pfm: 2782.011519262022 sim_pfm: -168.95811619840484
episode: 24 training return: tensor(-84.2290, device='cuda:0')
episode: 25 training return: tensor(-86.6655, device='cuda:0')
episode: 26 training return: tensor(249.7716, device='cuda:0')
episode: 27 training return: tensor(183.7834, device='cuda:0')
epoch: 7 test_true_pfm: 2370.365224856639 sim_pfm: -2.9775037307990715
episode: 28 training return: tensor(-199.4135, device='cuda:0')
episode: 29 training return: tensor(136.9800, device='cuda:0')
episode: 30 training return: tensor(128.3906, device='cuda:0')
episode: 31 training return: tensor(-211.1326, device='cuda:0')
epoch: 8 test_true_pfm: 3282.4953788181956 sim_pfm: 161.91021916806736
episode: 32 training return: tensor(266.6112, device='cuda:0')
episode: 33 training return: tensor(180.5806, device='cuda:0')
episode: 34 training return: tensor(5.6844, device='cuda:0')
episode: 35 training return: tensor(-160.1136, device='cuda:0')
epoch: 9 test_true_pfm: 2858.447230039467 sim_pfm: 91.15524206374539
episode: 36 training return: tensor(197.8766, device='cuda:0')
episode: 37 training return: tensor(243.0772, device='cuda:0')
episode: 38 training return: tensor(109.6836, device='cuda:0')
episode: 39 training return: tensor(196.2452, device='cuda:0')
epoch: 10 test_true_pfm: 3230.9374893256813 sim_pfm: -25.990238961957704
episode: 40 training return: tensor(177.4256, device='cuda:0')
episode: 41 training return: tensor(43.9090, device='cuda:0')
episode: 42 training return: tensor(254.3026, device='cuda:0')
episode: 43 training return: tensor(-177.5513, device='cuda:0')
epoch: 11 test_true_pfm: 3068.1838513517773 sim_pfm: 97.93739488218368
episode: 44 training return: tensor(-357.2854, device='cuda:0')
episode: 45 training return: tensor(223.9768, device='cuda:0')
episode: 46 training return: tensor(170.7783, device='cuda:0')
episode: 47 training return: tensor(189.7384, device='cuda:0')
epoch: 12 test_true_pfm: 3410.312833759674 sim_pfm: -43.11166492487731
episode: 48 training return: tensor(24.4035, device='cuda:0')
episode: 49 training return: tensor(-181.7866, device='cuda:0')
episode: 50 training return: tensor(235.5007, device='cuda:0')
episode: 51 training return: tensor(216.7816, device='cuda:0')
epoch: 13 test_true_pfm: 2812.979538850879 sim_pfm: 27.163329570825834
episode: 52 training return: tensor(-323.5104, device='cuda:0')
episode: 53 training return: tensor(172.2815, device='cuda:0')
episode: 54 training return: tensor(-403.6059, device='cuda:0')
episode: 55 training return: tensor(-70.9007, device='cuda:0')
epoch: 14 test_true_pfm: 2725.9736353275143 sim_pfm: 226.61247902779724
episode: 56 training return: tensor(-201.8037, device='cuda:0')
episode: 57 training return: tensor(39.3860, device='cuda:0')
episode: 58 training return: tensor(-169.9134, device='cuda:0')
episode: 59 training return: tensor(227.2483, device='cuda:0')
epoch: 15 test_true_pfm: 2824.942416293898 sim_pfm: -61.851733533102866
episode: 60 training return: tensor(183.8594, device='cuda:0')
episode: 61 training return: tensor(-189.0434, device='cuda:0')
episode: 62 training return: tensor(-180.2441, device='cuda:0')
episode: 63 training return: tensor(181.0484, device='cuda:0')
epoch: 16 test_true_pfm: 3042.5391324100024 sim_pfm: -62.86986112801242
episode: 64 training return: tensor(161.6219, device='cuda:0')
episode: 65 training return: tensor(-199.8583, device='cuda:0')
episode: 66 training return: tensor(109.4202, device='cuda:0')
episode: 67 training return: tensor(-219.7765, device='cuda:0')
epoch: 17 test_true_pfm: 2146.527974027563 sim_pfm: 180.98862553204526
episode: 68 training return: tensor(61.3194, device='cuda:0')
episode: 69 training return: tensor(255.2720, device='cuda:0')
episode: 70 training return: tensor(270.9617, device='cuda:0')
episode: 71 training return: tensor(210.8962, device='cuda:0')
epoch: 18 test_true_pfm: 2935.358878538802 sim_pfm: -81.62470524558255
episode: 72 training return: tensor(178.3094, device='cuda:0')
episode: 73 training return: tensor(-217.8428, device='cuda:0')
episode: 74 training return: tensor(-219.4434, device='cuda:0')
episode: 75 training return: tensor(258.1950, device='cuda:0')
epoch: 19 test_true_pfm: 2359.5148774854824 sim_pfm: 155.90212028816072
episode: 76 training return: tensor(-81.3861, device='cuda:0')
episode: 77 training return: tensor(-103.9819, device='cuda:0')
episode: 78 training return: tensor(237.9196, device='cuda:0')
episode: 79 training return: tensor(-149.0982, device='cuda:0')
epoch: 20 test_true_pfm: 2963.9547337376293 sim_pfm: 159.91606078423987
episode: 80 training return: tensor(250.2434, device='cuda:0')
episode: 81 training return: tensor(88.1415, device='cuda:0')
episode: 82 training return: tensor(108.4195, device='cuda:0')
episode: 83 training return: tensor(-202.3368, device='cuda:0')
epoch: 21 test_true_pfm: 2965.649594592895 sim_pfm: 88.39974245188448
episode: 84 training return: tensor(272.7499, device='cuda:0')
episode: 85 training return: tensor(327.8302, device='cuda:0')
episode: 86 training return: tensor(-28.2715, device='cuda:0')
episode: 87 training return: tensor(275.2238, device='cuda:0')
epoch: 22 test_true_pfm: 2557.0583635354506 sim_pfm: 187.55946195414677
episode: 88 training return: tensor(209.5973, device='cuda:0')
episode: 89 training return: tensor(-124.2998, device='cuda:0')
episode: 90 training return: tensor(300.3810, device='cuda:0')
episode: 91 training return: tensor(-182.0086, device='cuda:0')
epoch: 23 test_true_pfm: 2996.4259760395394 sim_pfm: 238.25756770506268
episode: 92 training return: tensor(176.9839, device='cuda:0')
episode: 93 training return: tensor(207.6168, device='cuda:0')
episode: 94 training return: tensor(3.1890, device='cuda:0')
episode: 95 training return: tensor(-453.4342, device='cuda:0')
epoch: 24 test_true_pfm: 2253.971074097905 sim_pfm: 295.23485830944264
episode: 96 training return: tensor(-119.7729, device='cuda:0')
episode: 97 training return: tensor(-190.0095, device='cuda:0')
episode: 98 training return: tensor(251.7594, device='cuda:0')
episode: 99 training return: tensor(160.1648, device='cuda:0')
epoch: 25 test_true_pfm: 2902.921267483056 sim_pfm: 120.59487498090796
episode: 100 training return: tensor(178.6663, device='cuda:0')
episode: 101 training return: tensor(-220.3601, device='cuda:0')
episode: 102 training return: tensor(-316.0060, device='cuda:0')
episode: 103 training return: tensor(230.7544, device='cuda:0')
epoch: 26 test_true_pfm: 3172.708724987628 sim_pfm: 269.85822830108617
episode: 104 training return: tensor(95.9952, device='cuda:0')
episode: 105 training return: tensor(190.2341, device='cuda:0')
episode: 106 training return: tensor(259.5649, device='cuda:0')
episode: 107 training return: tensor(-443.0923, device='cuda:0')
epoch: 27 test_true_pfm: 2833.0830704383166 sim_pfm: 248.8368464257801
episode: 108 training return: tensor(274.2675, device='cuda:0')
episode: 109 training return: tensor(172.4155, device='cuda:0')
episode: 110 training return: tensor(118.5784, device='cuda:0')
episode: 111 training return: tensor(15.9962, device='cuda:0')
epoch: 28 test_true_pfm: 2723.7984462127656 sim_pfm: 25.765613928689465
episode: 112 training return: tensor(165.2847, device='cuda:0')
episode: 113 training return: tensor(230.8937, device='cuda:0')
episode: 114 training return: tensor(186.0828, device='cuda:0')
episode: 115 training return: tensor(182.4734, device='cuda:0')
epoch: 29 test_true_pfm: 3334.966836570699 sim_pfm: 25.758888489595847
episode: 116 training return: tensor(223.5355, device='cuda:0')
episode: 117 training return: tensor(120.4543, device='cuda:0')
episode: 118 training return: tensor(164.7725, device='cuda:0')
episode: 119 training return: tensor(288.5043, device='cuda:0')
epoch: 30 test_true_pfm: 3446.265421317403 sim_pfm: 255.59509228150515
episode: 120 training return: tensor(290.7740, device='cuda:0')
episode: 121 training return: tensor(119.7129, device='cuda:0')
episode: 122 training return: tensor(208.4673, device='cuda:0')
episode: 123 training return: tensor(170.6935, device='cuda:0')
epoch: 31 test_true_pfm: 3330.4828154562524 sim_pfm: 200.57900325387405
episode: 124 training return: tensor(197.8539, device='cuda:0')
episode: 125 training return: tensor(328.7553, device='cuda:0')
episode: 126 training return: tensor(190.7458, device='cuda:0')
episode: 127 training return: tensor(74.1125, device='cuda:0')
epoch: 32 test_true_pfm: 3049.817439077308 sim_pfm: 155.10853366703182
episode: 128 training return: tensor(209.4837, device='cuda:0')
episode: 129 training return: tensor(226.9135, device='cuda:0')
episode: 130 training return: tensor(206.0538, device='cuda:0')
episode: 131 training return: tensor(45.0532, device='cuda:0')
epoch: 33 test_true_pfm: 3139.157641951298 sim_pfm: 239.5595605870573
episode: 132 training return: tensor(109.1413, device='cuda:0')
episode: 133 training return: tensor(132.0428, device='cuda:0')
episode: 134 training return: tensor(228.7838, device='cuda:0')
episode: 135 training return: tensor(283.3721, device='cuda:0')
epoch: 34 test_true_pfm: 3093.059767958696 sim_pfm: 338.4913203851126
episode: 136 training return: tensor(245.8631, device='cuda:0')
episode: 137 training return: tensor(179.1595, device='cuda:0')
episode: 138 training return: tensor(-257.6616, device='cuda:0')
episode: 139 training return: tensor(230.7386, device='cuda:0')
epoch: 35 test_true_pfm: 3217.3092038031537 sim_pfm: 52.472538000709996
episode: 140 training return: tensor(323.0209, device='cuda:0')
episode: 141 training return: tensor(220.7256, device='cuda:0')
episode: 142 training return: tensor(234.5711, device='cuda:0')
episode: 143 training return: tensor(234.0804, device='cuda:0')
epoch: 36 test_true_pfm: 3060.0249004670072 sim_pfm: -87.33778056143395
episode: 144 training return: tensor(189.0004, device='cuda:0')
episode: 145 training return: tensor(212.7475, device='cuda:0')
episode: 146 training return: tensor(-254.7195, device='cuda:0')
episode: 147 training return: tensor(218.4834, device='cuda:0')
epoch: 37 test_true_pfm: 3393.525260709512 sim_pfm: 33.58535560163242
episode: 148 training return: tensor(304.6613, device='cuda:0')
episode: 149 training return: tensor(301.4813, device='cuda:0')
episode: 150 training return: tensor(238.8972, device='cuda:0')
episode: 151 training return: tensor(-51.7151, device='cuda:0')
epoch: 38 test_true_pfm: 3315.13993212566 sim_pfm: 256.98760614169686
episode: 152 training return: tensor(186.6539, device='cuda:0')
episode: 153 training return: tensor(216.6260, device='cuda:0')
episode: 154 training return: tensor(213.3924, device='cuda:0')
episode: 155 training return: tensor(277.6930, device='cuda:0')
epoch: 39 test_true_pfm: 3420.5872311618464 sim_pfm: 198.20638306526234
episode: 156 training return: tensor(174.3018, device='cuda:0')
episode: 157 training return: tensor(284.3062, device='cuda:0')
episode: 158 training return: tensor(64.7520, device='cuda:0')
episode: 159 training return: tensor(264.1309, device='cuda:0')
epoch: 40 test_true_pfm: 2910.991167579426 sim_pfm: 132.6553454733221
episode: 160 training return: tensor(206.3777, device='cuda:0')
episode: 161 training return: tensor(213.8622, device='cuda:0')
episode: 162 training return: tensor(329.2964, device='cuda:0')
episode: 163 training return: tensor(-144.8227, device='cuda:0')
epoch: 41 test_true_pfm: 3375.583842505839 sim_pfm: 103.41755743400427
episode: 164 training return: tensor(262.9007, device='cuda:0')
episode: 165 training return: tensor(207.5630, device='cuda:0')
episode: 166 training return: tensor(259.9840, device='cuda:0')
episode: 167 training return: tensor(282.7296, device='cuda:0')
epoch: 42 test_true_pfm: 2801.9712304974996 sim_pfm: 275.63161756122526
episode: 168 training return: tensor(149.5177, device='cuda:0')
episode: 169 training return: tensor(282.6154, device='cuda:0')
episode: 170 training return: tensor(181.3889, device='cuda:0')
episode: 171 training return: tensor(-316.0031, device='cuda:0')
epoch: 43 test_true_pfm: 3204.025119427692 sim_pfm: 183.1649454755825
episode: 172 training return: tensor(-80.9878, device='cuda:0')
episode: 173 training return: tensor(255.7142, device='cuda:0')
episode: 174 training return: tensor(-119.2109, device='cuda:0')
episode: 175 training return: tensor(339.7643, device='cuda:0')
epoch: 44 test_true_pfm: 2955.051265449958 sim_pfm: 228.78852398658637
episode: 176 training return: tensor(-318.8553, device='cuda:0')
episode: 177 training return: tensor(232.2870, device='cuda:0')
episode: 178 training return: tensor(199.2495, device='cuda:0')
episode: 179 training return: tensor(261.0505, device='cuda:0')
epoch: 45 test_true_pfm: 2470.0699267526093 sim_pfm: 74.93424365101964
episode: 180 training return: tensor(182.8923, device='cuda:0')
episode: 181 training return: tensor(263.1084, device='cuda:0')
episode: 182 training return: tensor(111.1641, device='cuda:0')
episode: 183 training return: tensor(273.0812, device='cuda:0')
epoch: 46 test_true_pfm: 3446.8216572998986 sim_pfm: 50.08107019190599
episode: 184 training return: tensor(259.8475, device='cuda:0')
episode: 185 training return: tensor(306.2635, device='cuda:0')
episode: 186 training return: tensor(212.0295, device='cuda:0')
episode: 187 training return: tensor(189.2573, device='cuda:0')
epoch: 47 test_true_pfm: 3395.636970455842 sim_pfm: 255.06162644313494
episode: 188 training return: tensor(294.8671, device='cuda:0')
episode: 189 training return: tensor(257.4495, device='cuda:0')
episode: 190 training return: tensor(306.1906, device='cuda:0')
episode: 191 training return: tensor(-232.5326, device='cuda:0')
epoch: 48 test_true_pfm: 3099.8687315330803 sim_pfm: 291.2782715768165
episode: 192 training return: tensor(268.0430, device='cuda:0')
episode: 193 training return: tensor(177.8188, device='cuda:0')
episode: 194 training return: tensor(209.6719, device='cuda:0')
episode: 195 training return: tensor(244.1356, device='cuda:0')
epoch: 49 test_true_pfm: 3378.638738530451 sim_pfm: 227.81972979409815
episode: 196 training return: tensor(257.6209, device='cuda:0')
episode: 197 training return: tensor(247.5243, device='cuda:0')
episode: 198 training return: tensor(266.5967, device='cuda:0')
episode: 199 training return: tensor(253.9648, device='cuda:0')
epoch: 50 test_true_pfm: 3378.338189481419 sim_pfm: 26.690418427383218
episode: 200 training return: tensor(225.5562, device='cuda:0')
episode: 201 training return: tensor(96.3135, device='cuda:0')
episode: 202 training return: tensor(-226.9974, device='cuda:0')
episode: 203 training return: tensor(316.2840, device='cuda:0')
epoch: 51 test_true_pfm: 3191.1605031928716 sim_pfm: 296.2851534135504
episode: 204 training return: tensor(10.0197, device='cuda:0')
episode: 205 training return: tensor(160.7646, device='cuda:0')
episode: 206 training return: tensor(212.4081, device='cuda:0')
episode: 207 training return: tensor(-225.8014, device='cuda:0')
epoch: 52 test_true_pfm: 3379.8974868766095 sim_pfm: 221.0626784520185
episode: 208 training return: tensor(267.4891, device='cuda:0')
episode: 209 training return: tensor(186.1828, device='cuda:0')
episode: 210 training return: tensor(290.9163, device='cuda:0')
episode: 211 training return: tensor(173.4766, device='cuda:0')
epoch: 53 test_true_pfm: 3061.0803882483233 sim_pfm: 302.81291892253404
episode: 212 training return: tensor(254.8930, device='cuda:0')
episode: 213 training return: tensor(264.4256, device='cuda:0')
episode: 214 training return: tensor(223.5150, device='cuda:0')
episode: 215 training return: tensor(344.3736, device='cuda:0')
epoch: 54 test_true_pfm: 3419.0003781129403 sim_pfm: 185.01906246657987
episode: 216 training return: tensor(325.9312, device='cuda:0')
episode: 217 training return: tensor(224.2442, device='cuda:0')
episode: 218 training return: tensor(-317.4645, device='cuda:0')
episode: 219 training return: tensor(265.7477, device='cuda:0')
epoch: 55 test_true_pfm: 3441.198206588839 sim_pfm: 227.75035450951933
episode: 220 training return: tensor(253.2473, device='cuda:0')
episode: 221 training return: tensor(210.4177, device='cuda:0')
episode: 222 training return: tensor(243.1039, device='cuda:0')
episode: 223 training return: tensor(230.0836, device='cuda:0')
epoch: 56 test_true_pfm: 3310.252726948787 sim_pfm: 273.0648470794743
episode: 224 training return: tensor(11.4630, device='cuda:0')
episode: 225 training return: tensor(219.9228, device='cuda:0')
episode: 226 training return: tensor(280.0826, device='cuda:0')
episode: 227 training return: tensor(275.0984, device='cuda:0')
epoch: 57 test_true_pfm: 3401.0078109573938 sim_pfm: 277.4358828078742
episode: 228 training return: tensor(294.8840, device='cuda:0')
episode: 229 training return: tensor(253.9660, device='cuda:0')
episode: 230 training return: tensor(250.2871, device='cuda:0')
episode: 231 training return: tensor(45.8690, device='cuda:0')
epoch: 58 test_true_pfm: 2877.545480626361 sim_pfm: 176.44270683724122
episode: 232 training return: tensor(324.4702, device='cuda:0')
episode: 233 training return: tensor(235.8535, device='cuda:0')
episode: 234 training return: tensor(-237.5771, device='cuda:0')
episode: 235 training return: tensor(201.6284, device='cuda:0')
epoch: 59 test_true_pfm: 3100.4693545557543 sim_pfm: 159.25519147813125
episode: 236 training return: tensor(253.2396, device='cuda:0')
episode: 237 training return: tensor(-288.9855, device='cuda:0')
episode: 238 training return: tensor(175.4120, device='cuda:0')
episode: 239 training return: tensor(225.3315, device='cuda:0')
epoch: 60 test_true_pfm: 3411.0021501243245 sim_pfm: 200.04666881986972
episode: 240 training return: tensor(-189.6036, device='cuda:0')
episode: 241 training return: tensor(-239.6999, device='cuda:0')
episode: 242 training return: tensor(203.0823, device='cuda:0')
episode: 243 training return: tensor(276.7106, device='cuda:0')
epoch: 61 test_true_pfm: 3213.700455267321 sim_pfm: 242.14497179870764
episode: 244 training return: tensor(242.4330, device='cuda:0')
episode: 245 training return: tensor(375.5058, device='cuda:0')
episode: 246 training return: tensor(210.2253, device='cuda:0')
episode: 247 training return: tensor(51.7953, device='cuda:0')
epoch: 62 test_true_pfm: 2775.6026148154256 sim_pfm: 262.4132709056624
episode: 248 training return: tensor(282.3561, device='cuda:0')
episode: 249 training return: tensor(285.9074, device='cuda:0')
episode: 250 training return: tensor(238.1588, device='cuda:0')
episode: 251 training return: tensor(328.3235, device='cuda:0')
epoch: 63 test_true_pfm: 2979.264015256837 sim_pfm: 138.92428553805803
episode: 252 training return: tensor(-241.0376, device='cuda:0')
episode: 253 training return: tensor(359.9220, device='cuda:0')
episode: 254 training return: tensor(195.7713, device='cuda:0')
episode: 255 training return: tensor(237.1579, device='cuda:0')
epoch: 64 test_true_pfm: 3427.946712305396 sim_pfm: 55.53738969464515
episode: 256 training return: tensor(-341.9363, device='cuda:0')
episode: 257 training return: tensor(322.5493, device='cuda:0')
episode: 258 training return: tensor(242.9241, device='cuda:0')
episode: 259 training return: tensor(315.7881, device='cuda:0')
epoch: 65 test_true_pfm: 2726.206518168141 sim_pfm: 315.787287303363
episode: 260 training return: tensor(227.2348, device='cuda:0')
episode: 261 training return: tensor(15.9630, device='cuda:0')
episode: 262 training return: tensor(263.6914, device='cuda:0')
episode: 263 training return: tensor(185.9952, device='cuda:0')
epoch: 66 test_true_pfm: 3369.3071717729777 sim_pfm: 228.6256181098191
episode: 264 training return: tensor(293.5660, device='cuda:0')
episode: 265 training return: tensor(281.3421, device='cuda:0')
episode: 266 training return: tensor(-266.9343, device='cuda:0')
episode: 267 training return: tensor(-172.1605, device='cuda:0')
epoch: 67 test_true_pfm: 2785.245432385644 sim_pfm: 46.08849102560392
episode: 268 training return: tensor(255.8805, device='cuda:0')
episode: 269 training return: tensor(-214.2402, device='cuda:0')
episode: 270 training return: tensor(210.3189, device='cuda:0')
episode: 271 training return: tensor(250.6914, device='cuda:0')
epoch: 68 test_true_pfm: 3008.994090227496 sim_pfm: 142.1428751787365
episode: 272 training return: tensor(-266.7047, device='cuda:0')
episode: 273 training return: tensor(185.9702, device='cuda:0')
episode: 274 training return: tensor(191.3585, device='cuda:0')
episode: 275 training return: tensor(258.1631, device='cuda:0')
epoch: 69 test_true_pfm: 2357.775561411196 sim_pfm: 251.86903315448822
episode: 276 training return: tensor(261.5718, device='cuda:0')
episode: 277 training return: tensor(333.4963, device='cuda:0')
episode: 278 training return: tensor(311.7771, device='cuda:0')
episode: 279 training return: tensor(237.9102, device='cuda:0')
epoch: 70 test_true_pfm: 3363.377177478475 sim_pfm: 98.67019978060853
episode: 280 training return: tensor(265.0271, device='cuda:0')
episode: 281 training return: tensor(-301.1062, device='cuda:0')
episode: 282 training return: tensor(242.4259, device='cuda:0')
episode: 283 training return: tensor(201.7272, device='cuda:0')
epoch: 71 test_true_pfm: 2854.025791918419 sim_pfm: 289.80727818552015
episode: 284 training return: tensor(-245.5025, device='cuda:0')
episode: 285 training return: tensor(-275.2917, device='cuda:0')
episode: 286 training return: tensor(224.8991, device='cuda:0')
episode: 287 training return: tensor(304.1963, device='cuda:0')
epoch: 72 test_true_pfm: 3380.691731053666 sim_pfm: 287.6759264655605
episode: 288 training return: tensor(270.8053, device='cuda:0')
episode: 289 training return: tensor(-208.8818, device='cuda:0')
episode: 290 training return: tensor(296.3619, device='cuda:0')
episode: 291 training return: tensor(300.0526, device='cuda:0')
epoch: 73 test_true_pfm: 3453.85681586528 sim_pfm: 88.05601925603696
episode: 292 training return: tensor(286.7214, device='cuda:0')
episode: 293 training return: tensor(235.9623, device='cuda:0')
episode: 294 training return: tensor(219.8320, device='cuda:0')
episode: 295 training return: tensor(305.8406, device='cuda:0')
epoch: 74 test_true_pfm: 3423.801282564879 sim_pfm: 229.26723816466983
episode: 296 training return: tensor(387.4212, device='cuda:0')
episode: 297 training return: tensor(309.8651, device='cuda:0')
episode: 298 training return: tensor(-330.2323, device='cuda:0')
episode: 299 training return: tensor(268.0315, device='cuda:0')
epoch: 75 test_true_pfm: 3431.8660875403743 sim_pfm: 310.5314530169223
episode: 300 training return: tensor(311.2204, device='cuda:0')
episode: 301 training return: tensor(-36.8703, device='cuda:0')
episode: 302 training return: tensor(235.6433, device='cuda:0')
episode: 303 training return: tensor(216.2294, device='cuda:0')
epoch: 76 test_true_pfm: 3355.4042649655203 sim_pfm: 272.76287721685367
episode: 304 training return: tensor(304.3493, device='cuda:0')
episode: 305 training return: tensor(250.5997, device='cuda:0')
episode: 306 training return: tensor(-259.0763, device='cuda:0')
episode: 307 training return: tensor(314.1622, device='cuda:0')
epoch: 77 test_true_pfm: 2696.2739224510974 sim_pfm: 105.32229854265461
episode: 308 training return: tensor(366.5934, device='cuda:0')
episode: 309 training return: tensor(316.0169, device='cuda:0')
episode: 310 training return: tensor(145.2899, device='cuda:0')
episode: 311 training return: tensor(309.8320, device='cuda:0')
epoch: 78 test_true_pfm: 3409.524257332263 sim_pfm: 258.8678277626944
episode: 312 training return: tensor(236.6947, device='cuda:0')
episode: 313 training return: tensor(284.5737, device='cuda:0')
episode: 314 training return: tensor(224.4345, device='cuda:0')
episode: 315 training return: tensor(269.8188, device='cuda:0')
epoch: 79 test_true_pfm: 3022.9564959354343 sim_pfm: 285.7065628622756
episode: 316 training return: tensor(274.8448, device='cuda:0')
episode: 317 training return: tensor(294.3079, device='cuda:0')
episode: 318 training return: tensor(200.1645, device='cuda:0')
episode: 319 training return: tensor(177.9131, device='cuda:0')
epoch: 80 test_true_pfm: 3061.43273068578 sim_pfm: 261.9393316182347
episode: 320 training return: tensor(290.8844, device='cuda:0')
episode: 321 training return: tensor(-77.9912, device='cuda:0')
episode: 322 training return: tensor(344.5944, device='cuda:0')
episode: 323 training return: tensor(252.7590, device='cuda:0')
epoch: 81 test_true_pfm: 3451.3972734059557 sim_pfm: 191.29827603210774
episode: 324 training return: tensor(269.4046, device='cuda:0')
episode: 325 training return: tensor(-187.5088, device='cuda:0')
episode: 326 training return: tensor(239.1534, device='cuda:0')
episode: 327 training return: tensor(-228.6902, device='cuda:0')
epoch: 82 test_true_pfm: 2811.7366110123567 sim_pfm: 282.13240363209235
episode: 328 training return: tensor(-246.3672, device='cuda:0')
episode: 329 training return: tensor(225.9471, device='cuda:0')
episode: 330 training return: tensor(278.3747, device='cuda:0')
episode: 331 training return: tensor(-118.2785, device='cuda:0')
epoch: 83 test_true_pfm: 3415.8002719543697 sim_pfm: 252.48721464787377
episode: 332 training return: tensor(249.2770, device='cuda:0')
episode: 333 training return: tensor(246.2840, device='cuda:0')
episode: 334 training return: tensor(306.7180, device='cuda:0')
episode: 335 training return: tensor(340.3390, device='cuda:0')
epoch: 84 test_true_pfm: 3398.8222559640467 sim_pfm: 276.7862774382229
episode: 336 training return: tensor(207.4087, device='cuda:0')
episode: 337 training return: tensor(168.5389, device='cuda:0')
episode: 338 training return: tensor(201.8304, device='cuda:0')
episode: 339 training return: tensor(238.0160, device='cuda:0')
epoch: 85 test_true_pfm: 3423.9772283654524 sim_pfm: 290.11970748763025
episode: 340 training return: tensor(329.8135, device='cuda:0')
episode: 341 training return: tensor(204.2182, device='cuda:0')
episode: 342 training return: tensor(226.7066, device='cuda:0')
episode: 343 training return: tensor(-433.8213, device='cuda:0')
epoch: 86 test_true_pfm: 2966.018014718931 sim_pfm: 280.9137554379801
episode: 344 training return: tensor(275.7045, device='cuda:0')
episode: 345 training return: tensor(216.3709, device='cuda:0')
episode: 346 training return: tensor(316.3492, device='cuda:0')
episode: 347 training return: tensor(274.5858, device='cuda:0')
epoch: 87 test_true_pfm: 3402.767768551115 sim_pfm: 133.6375870135768
episode: 348 training return: tensor(298.5808, device='cuda:0')
episode: 349 training return: tensor(318.5964, device='cuda:0')
episode: 350 training return: tensor(257.3205, device='cuda:0')
episode: 351 training return: tensor(177.6899, device='cuda:0')
epoch: 88 test_true_pfm: 3021.9523724525898 sim_pfm: -56.82127721943349
episode: 352 training return: tensor(271.9023, device='cuda:0')
episode: 353 training return: tensor(273.8202, device='cuda:0')
episode: 354 training return: tensor(341.7889, device='cuda:0')
episode: 355 training return: tensor(288.6565, device='cuda:0')
epoch: 89 test_true_pfm: 3468.2598121244732 sim_pfm: 223.0340308455634
episode: 356 training return: tensor(259.4063, device='cuda:0')
episode: 357 training return: tensor(228.4216, device='cuda:0')
episode: 358 training return: tensor(240.4153, device='cuda:0')
episode: 359 training return: tensor(227.3273, device='cuda:0')
epoch: 90 test_true_pfm: 2905.399927247299 sim_pfm: 255.7697442510398
episode: 360 training return: tensor(169.0168, device='cuda:0')
episode: 361 training return: tensor(378.5831, device='cuda:0')
episode: 362 training return: tensor(243.0258, device='cuda:0')
episode: 363 training return: tensor(184.0431, device='cuda:0')
epoch: 91 test_true_pfm: 3473.1388527278523 sim_pfm: 304.86608709505526
episode: 364 training return: tensor(247.3766, device='cuda:0')
episode: 365 training return: tensor(221.4512, device='cuda:0')
episode: 366 training return: tensor(-248.7778, device='cuda:0')
episode: 367 training return: tensor(-97.5810, device='cuda:0')
epoch: 92 test_true_pfm: 3416.5372295684633 sim_pfm: 138.29311310464982
episode: 368 training return: tensor(212.1208, device='cuda:0')
episode: 369 training return: tensor(244.8684, device='cuda:0')
episode: 370 training return: tensor(353.9459, device='cuda:0')
episode: 371 training return: tensor(208.4895, device='cuda:0')
epoch: 93 test_true_pfm: 3454.1977024519433 sim_pfm: 278.8431184819395
episode: 372 training return: tensor(226.9572, device='cuda:0')
episode: 373 training return: tensor(249.7898, device='cuda:0')
episode: 374 training return: tensor(257.0735, device='cuda:0')
episode: 375 training return: tensor(218.9703, device='cuda:0')
epoch: 94 test_true_pfm: 3429.093164270613 sim_pfm: 238.1260338247424
episode: 376 training return: tensor(258.4429, device='cuda:0')
episode: 377 training return: tensor(288.4762, device='cuda:0')
episode: 378 training return: tensor(236.7693, device='cuda:0')
episode: 379 training return: tensor(233.5580, device='cuda:0')
epoch: 95 test_true_pfm: 3438.915347133943 sim_pfm: 253.36769358362653
episode: 380 training return: tensor(7.4414, device='cuda:0')
episode: 381 training return: tensor(210.7569, device='cuda:0')
episode: 382 training return: tensor(-294.3842, device='cuda:0')
episode: 383 training return: tensor(292.0224, device='cuda:0')
epoch: 96 test_true_pfm: 3498.8859357715405 sim_pfm: 186.39471189973605
episode: 384 training return: tensor(339.5158, device='cuda:0')
episode: 385 training return: tensor(269.2309, device='cuda:0')
episode: 386 training return: tensor(270.8682, device='cuda:0')
episode: 387 training return: tensor(335.7218, device='cuda:0')
epoch: 97 test_true_pfm: 3471.2934755253423 sim_pfm: 280.99543352200027
episode: 388 training return: tensor(185.2421, device='cuda:0')
episode: 389 training return: tensor(67.1544, device='cuda:0')
episode: 390 training return: tensor(264.1208, device='cuda:0')
episode: 391 training return: tensor(255.5446, device='cuda:0')
epoch: 98 test_true_pfm: 3013.0915498655336 sim_pfm: 234.3835805178387
episode: 392 training return: tensor(-91.1844, device='cuda:0')
episode: 393 training return: tensor(-153.4903, device='cuda:0')
episode: 394 training return: tensor(-275.5002, device='cuda:0')
episode: 395 training return: tensor(241.0123, device='cuda:0')
epoch: 99 test_true_pfm: 3320.4051156902387 sim_pfm: 248.09638776381811
episode: 396 training return: tensor(243.8966, device='cuda:0')
episode: 397 training return: tensor(273.9224, device='cuda:0')
episode: 398 training return: tensor(242.8518, device='cuda:0')
episode: 399 training return: tensor(196.6770, device='cuda:0')
epoch: 100 test_true_pfm: 3417.4508147818683 sim_pfm: 141.52733260191357
episode: 400 training return: tensor(269.6203, device='cuda:0')
episode: 401 training return: tensor(284.2468, device='cuda:0')
episode: 402 training return: tensor(155.0462, device='cuda:0')
episode: 403 training return: tensor(165.5401, device='cuda:0')
epoch: 101 test_true_pfm: 3461.8211574988545 sim_pfm: 128.79128708371232
episode: 404 training return: tensor(246.8479, device='cuda:0')
episode: 405 training return: tensor(268.5073, device='cuda:0')
episode: 406 training return: tensor(262.8380, device='cuda:0')
episode: 407 training return: tensor(247.5945, device='cuda:0')
epoch: 102 test_true_pfm: 3446.479216880873 sim_pfm: 235.0535574227688
episode: 408 training return: tensor(285.1379, device='cuda:0')
episode: 409 training return: tensor(273.3252, device='cuda:0')
episode: 410 training return: tensor(205.4381, device='cuda:0')
episode: 411 training return: tensor(278.0700, device='cuda:0')
epoch: 103 test_true_pfm: 3431.233450911071 sim_pfm: 120.81107136203597
episode: 412 training return: tensor(289.4660, device='cuda:0')
episode: 413 training return: tensor(266.7362, device='cuda:0')
episode: 414 training return: tensor(-228.0594, device='cuda:0')
episode: 415 training return: tensor(260.5007, device='cuda:0')
epoch: 104 test_true_pfm: 3449.37023906373 sim_pfm: 277.5446487617931
episode: 416 training return: tensor(338.7253, device='cuda:0')
episode: 417 training return: tensor(284.4782, device='cuda:0')
episode: 418 training return: tensor(261.5236, device='cuda:0')
episode: 419 training return: tensor(295.6761, device='cuda:0')
epoch: 105 test_true_pfm: 2651.004519667587 sim_pfm: 126.76437142773648
episode: 420 training return: tensor(249.5611, device='cuda:0')
episode: 421 training return: tensor(318.3095, device='cuda:0')
episode: 422 training return: tensor(-255.2715, device='cuda:0')
episode: 423 training return: tensor(290.0245, device='cuda:0')
epoch: 106 test_true_pfm: 3440.8404781112076 sim_pfm: 279.8669345981713
episode: 424 training return: tensor(187.3826, device='cuda:0')
episode: 425 training return: tensor(229.1967, device='cuda:0')
episode: 426 training return: tensor(350.4420, device='cuda:0')
episode: 427 training return: tensor(302.9696, device='cuda:0')
epoch: 107 test_true_pfm: 3444.702214428465 sim_pfm: 293.26044928014744
episode: 428 training return: tensor(287.6579, device='cuda:0')
episode: 429 training return: tensor(431.0641, device='cuda:0')
episode: 430 training return: tensor(272.6183, device='cuda:0')
episode: 431 training return: tensor(377.6400, device='cuda:0')
epoch: 108 test_true_pfm: 3418.3674716372097 sim_pfm: 225.82731494901236
episode: 432 training return: tensor(300.0397, device='cuda:0')
episode: 433 training return: tensor(303.9074, device='cuda:0')
episode: 434 training return: tensor(300.7844, device='cuda:0')
episode: 435 training return: tensor(-164.3135, device='cuda:0')
epoch: 109 test_true_pfm: 3346.8778024454987 sim_pfm: 316.71360959354206
episode: 436 training return: tensor(158.3063, device='cuda:0')
episode: 437 training return: tensor(307.9890, device='cuda:0')
episode: 438 training return: tensor(281.7781, device='cuda:0')
episode: 439 training return: tensor(144.8000, device='cuda:0')
epoch: 110 test_true_pfm: 3480.107383715155 sim_pfm: 279.3571597197151
episode: 440 training return: tensor(185.9250, device='cuda:0')
episode: 441 training return: tensor(264.9155, device='cuda:0')
episode: 442 training return: tensor(222.3769, device='cuda:0')
episode: 443 training return: tensor(249.9321, device='cuda:0')
epoch: 111 test_true_pfm: 3440.799717163238 sim_pfm: 301.94016438749776
episode: 444 training return: tensor(314.6671, device='cuda:0')
episode: 445 training return: tensor(335.6642, device='cuda:0')
episode: 446 training return: tensor(256.2409, device='cuda:0')
episode: 447 training return: tensor(269.3195, device='cuda:0')
epoch: 112 test_true_pfm: 3450.1714778033042 sim_pfm: 262.0910904495104
episode: 448 training return: tensor(206.7641, device='cuda:0')
episode: 449 training return: tensor(340.1015, device='cuda:0')
episode: 450 training return: tensor(284.0326, device='cuda:0')
episode: 451 training return: tensor(187.8427, device='cuda:0')
epoch: 113 test_true_pfm: 3401.5185890215957 sim_pfm: 233.4653151911334
episode: 452 training return: tensor(200.6734, device='cuda:0')
episode: 453 training return: tensor(255.2211, device='cuda:0')
episode: 454 training return: tensor(269.6771, device='cuda:0')
episode: 455 training return: tensor(220.9173, device='cuda:0')
epoch: 114 test_true_pfm: 3146.416273709767 sim_pfm: 315.83031869331415
episode: 456 training return: tensor(258.5493, device='cuda:0')
episode: 457 training return: tensor(231.2126, device='cuda:0')
episode: 458 training return: tensor(229.2513, device='cuda:0')
episode: 459 training return: tensor(222.3172, device='cuda:0')
epoch: 115 test_true_pfm: 3432.735165668322 sim_pfm: 259.1338624500689
episode: 460 training return: tensor(199.8603, device='cuda:0')
episode: 461 training return: tensor(210.8691, device='cuda:0')
episode: 462 training return: tensor(278.6115, device='cuda:0')
episode: 463 training return: tensor(279.3763, device='cuda:0')
epoch: 116 test_true_pfm: 3004.6749157545105 sim_pfm: 281.4783646496944
episode: 464 training return: tensor(230.8030, device='cuda:0')
episode: 465 training return: tensor(237.4194, device='cuda:0')
episode: 466 training return: tensor(333.1747, device='cuda:0')
episode: 467 training return: tensor(300.4629, device='cuda:0')
epoch: 117 test_true_pfm: 3475.3490321021077 sim_pfm: 279.7491391916992
episode: 468 training return: tensor(233.9777, device='cuda:0')
episode: 469 training return: tensor(191.7513, device='cuda:0')
episode: 470 training return: tensor(-56.1368, device='cuda:0')
episode: 471 training return: tensor(236.4932, device='cuda:0')
epoch: 118 test_true_pfm: 3475.82199692591 sim_pfm: 126.64474842945735
episode: 472 training return: tensor(219.8513, device='cuda:0')
episode: 473 training return: tensor(311.7961, device='cuda:0')
episode: 474 training return: tensor(300.0092, device='cuda:0')
episode: 475 training return: tensor(-71.7999, device='cuda:0')
epoch: 119 test_true_pfm: 3455.1744615226016 sim_pfm: 229.26787821065713
episode: 476 training return: tensor(282.0487, device='cuda:0')
episode: 477 training return: tensor(254.4520, device='cuda:0')
episode: 478 training return: tensor(218.2620, device='cuda:0')
episode: 479 training return: tensor(247.8956, device='cuda:0')
epoch: 120 test_true_pfm: 3371.764877769127 sim_pfm: 229.27168406976853
episode: 480 training return: tensor(201.8423, device='cuda:0')
episode: 481 training return: tensor(244.2717, device='cuda:0')
episode: 482 training return: tensor(272.4065, device='cuda:0')
episode: 483 training return: tensor(268.9654, device='cuda:0')
epoch: 121 test_true_pfm: 3501.4597190469362 sim_pfm: 317.2225398318842
episode: 484 training return: tensor(-44.4732, device='cuda:0')
episode: 485 training return: tensor(26.0163, device='cuda:0')
episode: 486 training return: tensor(346.6906, device='cuda:0')
episode: 487 training return: tensor(327.8460, device='cuda:0')
epoch: 122 test_true_pfm: 3394.701733322328 sim_pfm: 258.0010043934938
episode: 488 training return: tensor(284.6675, device='cuda:0')
episode: 489 training return: tensor(209.1350, device='cuda:0')
episode: 490 training return: tensor(-240.1185, device='cuda:0')
episode: 491 training return: tensor(297.0034, device='cuda:0')
epoch: 123 test_true_pfm: 3412.1706545353277 sim_pfm: 253.6658652155796
episode: 492 training return: tensor(198.2957, device='cuda:0')
episode: 493 training return: tensor(391.7504, device='cuda:0')
episode: 494 training return: tensor(285.3056, device='cuda:0')
episode: 495 training return: tensor(277.7907, device='cuda:0')
epoch: 124 test_true_pfm: 3520.5351142912823 sim_pfm: 332.8821044052311
episode: 496 training return: tensor(203.1669, device='cuda:0')
episode: 497 training return: tensor(147.1261, device='cuda:0')
episode: 498 training return: tensor(213.9693, device='cuda:0')
episode: 499 training return: tensor(240.1501, device='cuda:0')
epoch: 125 test_true_pfm: 3396.534648387025 sim_pfm: 245.3875472158155
episode: 500 training return: tensor(-172.3071, device='cuda:0')
episode: 501 training return: tensor(210.7724, device='cuda:0')
episode: 502 training return: tensor(264.2690, device='cuda:0')
episode: 503 training return: tensor(202.8217, device='cuda:0')
epoch: 126 test_true_pfm: 3444.171644818444 sim_pfm: 235.8851585404967
episode: 504 training return: tensor(210.3920, device='cuda:0')
episode: 505 training return: tensor(253.3940, device='cuda:0')
episode: 506 training return: tensor(179.3788, device='cuda:0')
episode: 507 training return: tensor(329.2990, device='cuda:0')
epoch: 127 test_true_pfm: 3082.6918783275864 sim_pfm: 172.6678902375085
episode: 508 training return: tensor(231.1850, device='cuda:0')
episode: 509 training return: tensor(251.7741, device='cuda:0')
episode: 510 training return: tensor(280.3126, device='cuda:0')
episode: 511 training return: tensor(257.6386, device='cuda:0')
epoch: 128 test_true_pfm: 3396.8288754617824 sim_pfm: 258.93521469327
episode: 512 training return: tensor(283.4750, device='cuda:0')
episode: 513 training return: tensor(206.4586, device='cuda:0')
episode: 514 training return: tensor(252.1817, device='cuda:0')
episode: 515 training return: tensor(327.2456, device='cuda:0')
epoch: 129 test_true_pfm: 3420.8544663948155 sim_pfm: 207.5252327134464
episode: 516 training return: tensor(326.5925, device='cuda:0')
episode: 517 training return: tensor(208.5759, device='cuda:0')
episode: 518 training return: tensor(342.7386, device='cuda:0')
episode: 519 training return: tensor(197.4701, device='cuda:0')
epoch: 130 test_true_pfm: 3427.595008359372 sim_pfm: 252.5786237359474
episode: 520 training return: tensor(209.6456, device='cuda:0')
episode: 521 training return: tensor(312.3799, device='cuda:0')
episode: 522 training return: tensor(210.7693, device='cuda:0')
episode: 523 training return: tensor(-232.4002, device='cuda:0')
epoch: 131 test_true_pfm: 3400.3257023645656 sim_pfm: 253.1092983208558
episode: 524 training return: tensor(276.8960, device='cuda:0')
episode: 525 training return: tensor(273.5930, device='cuda:0')
episode: 526 training return: tensor(-98.2713, device='cuda:0')
episode: 527 training return: tensor(221.4543, device='cuda:0')
epoch: 132 test_true_pfm: 3406.484011059269 sim_pfm: 342.5594240927894
episode: 528 training return: tensor(301.1938, device='cuda:0')
episode: 529 training return: tensor(270.9122, device='cuda:0')
episode: 530 training return: tensor(114.4769, device='cuda:0')
episode: 531 training return: tensor(282.7578, device='cuda:0')
epoch: 133 test_true_pfm: 3113.7619014908473 sim_pfm: 290.16519645347336
episode: 532 training return: tensor(211.3086, device='cuda:0')
episode: 533 training return: tensor(341.4948, device='cuda:0')
episode: 534 training return: tensor(261.8416, device='cuda:0')
episode: 535 training return: tensor(353.3316, device='cuda:0')
epoch: 134 test_true_pfm: 3405.250623244164 sim_pfm: 103.531820180855
episode: 536 training return: tensor(239.5309, device='cuda:0')
episode: 537 training return: tensor(225.8425, device='cuda:0')
episode: 538 training return: tensor(235.7398, device='cuda:0')
episode: 539 training return: tensor(254.3088, device='cuda:0')
epoch: 135 test_true_pfm: 3433.809549944495 sim_pfm: 275.9249104162639
episode: 540 training return: tensor(-156.2089, device='cuda:0')
episode: 541 training return: tensor(267.6715, device='cuda:0')
episode: 542 training return: tensor(282.0341, device='cuda:0')
episode: 543 training return: tensor(268.3553, device='cuda:0')
epoch: 136 test_true_pfm: 3437.4955068516606 sim_pfm: 223.79418368903376
episode: 544 training return: tensor(245.0893, device='cuda:0')
episode: 545 training return: tensor(266.6467, device='cuda:0')
episode: 546 training return: tensor(326.6119, device='cuda:0')
episode: 547 training return: tensor(126.5995, device='cuda:0')
epoch: 137 test_true_pfm: 3054.4084174195523 sim_pfm: 312.2881844476021
episode: 548 training return: tensor(266.4780, device='cuda:0')
episode: 549 training return: tensor(303.0965, device='cuda:0')
episode: 550 training return: tensor(289.8408, device='cuda:0')
episode: 551 training return: tensor(284.6344, device='cuda:0')
epoch: 138 test_true_pfm: 3444.7085971764427 sim_pfm: 253.255498409863
episode: 552 training return: tensor(280.8156, device='cuda:0')
episode: 553 training return: tensor(260.7323, device='cuda:0')
episode: 554 training return: tensor(298.7787, device='cuda:0')
episode: 555 training return: tensor(275.0706, device='cuda:0')
epoch: 139 test_true_pfm: 3481.470505351022 sim_pfm: 276.4209453348497
episode: 556 training return: tensor(234.8841, device='cuda:0')
episode: 557 training return: tensor(247.1758, device='cuda:0')
episode: 558 training return: tensor(135.2201, device='cuda:0')
episode: 559 training return: tensor(338.9501, device='cuda:0')
epoch: 140 test_true_pfm: 3376.997935354257 sim_pfm: 305.17164811315405
episode: 560 training return: tensor(273.5612, device='cuda:0')
episode: 561 training return: tensor(197.6685, device='cuda:0')
episode: 562 training return: tensor(312.2170, device='cuda:0')
episode: 563 training return: tensor(221.2126, device='cuda:0')
epoch: 141 test_true_pfm: 3549.737306050956 sim_pfm: 334.0003603324876
episode: 564 training return: tensor(234.2489, device='cuda:0')
episode: 565 training return: tensor(326.3837, device='cuda:0')
episode: 566 training return: tensor(244.8859, device='cuda:0')
episode: 567 training return: tensor(261.5603, device='cuda:0')
epoch: 142 test_true_pfm: 3466.456732619625 sim_pfm: 287.52326640095754
episode: 568 training return: tensor(212.4550, device='cuda:0')
episode: 569 training return: tensor(-244.6064, device='cuda:0')
episode: 570 training return: tensor(-144.3895, device='cuda:0')
episode: 571 training return: tensor(327.1672, device='cuda:0')
epoch: 143 test_true_pfm: 3434.577163182821 sim_pfm: 238.58869879102954
episode: 572 training return: tensor(304.1300, device='cuda:0')
episode: 573 training return: tensor(353.0348, device='cuda:0')
episode: 574 training return: tensor(-230.7000, device='cuda:0')
episode: 575 training return: tensor(56.8560, device='cuda:0')
epoch: 144 test_true_pfm: 3494.5907898033533 sim_pfm: 286.8398786648565
episode: 576 training return: tensor(263.0023, device='cuda:0')
episode: 577 training return: tensor(280.8333, device='cuda:0')
episode: 578 training return: tensor(330.8223, device='cuda:0')
episode: 579 training return: tensor(258.6310, device='cuda:0')
epoch: 145 test_true_pfm: 3476.8185518003097 sim_pfm: 274.7279897402138
episode: 580 training return: tensor(226.1541, device='cuda:0')
episode: 581 training return: tensor(-50.6583, device='cuda:0')
episode: 582 training return: tensor(43.5784, device='cuda:0')
episode: 583 training return: tensor(213.6744, device='cuda:0')
epoch: 146 test_true_pfm: 3437.0548071371636 sim_pfm: 244.47658915352076
episode: 584 training return: tensor(282.9193, device='cuda:0')
episode: 585 training return: tensor(146.0844, device='cuda:0')
episode: 586 training return: tensor(237.6660, device='cuda:0')
episode: 587 training return: tensor(325.7108, device='cuda:0')
epoch: 147 test_true_pfm: 3459.0246204951886 sim_pfm: 261.3124328358778
episode: 588 training return: tensor(272.5607, device='cuda:0')
episode: 589 training return: tensor(91.6326, device='cuda:0')
episode: 590 training return: tensor(-305.2430, device='cuda:0')
episode: 591 training return: tensor(267.5247, device='cuda:0')
epoch: 148 test_true_pfm: 3450.9602664577214 sim_pfm: 280.07361002431327
episode: 592 training return: tensor(264.1098, device='cuda:0')
episode: 593 training return: tensor(318.9795, device='cuda:0')
episode: 594 training return: tensor(275.3947, device='cuda:0')
episode: 595 training return: tensor(316.5764, device='cuda:0')
epoch: 149 test_true_pfm: 3437.1739428216565 sim_pfm: 367.00638114548445
episode: 596 training return: tensor(243.7370, device='cuda:0')
episode: 597 training return: tensor(-176.4913, device='cuda:0')
episode: 598 training return: tensor(241.8499, device='cuda:0')
episode: 599 training return: tensor(334.9631, device='cuda:0')
epoch: 150 test_true_pfm: 3475.6350611964795 sim_pfm: 296.10235850309255
