['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '1']
epoch: 0 training_loss 0.26334068953990936 test_loss: 0.1940143585205078
epoch: 1 training_loss 0.19641304366290568 test_loss: 0.20675349235534668
epoch: 2 training_loss 0.1971780042350292 test_loss: 0.18158859014511108
epoch: 3 training_loss 0.19760813757777215 test_loss: 0.21351678371429444
epoch: 4 training_loss 0.1874241203069687 test_loss: 0.18939898014068604
epoch: 5 training_loss 0.18809880316257477 test_loss: 0.18993650674819945
epoch: 6 training_loss 0.1821683833003044 test_loss: 0.18256248235702516
epoch: 7 training_loss 0.19635865308344364 test_loss: 0.20271220207214355
epoch: 8 training_loss 0.19405687168240549 test_loss: 0.19997185468673706
epoch: 9 training_loss 0.19138370722532272 test_loss: 0.20394413471221923
epoch: 10 training_loss 0.18981346413493155 test_loss: 0.20316648483276367
epoch: 11 training_loss 0.18466436095535754 test_loss: 0.18405919075012206
epoch: 12 training_loss 0.1853953465074301 test_loss: 0.2000422477722168
epoch: 13 training_loss 0.18963125467300415 test_loss: 0.19397006034851075
epoch: 14 training_loss 0.19361657328903675 test_loss: 0.18237208127975463
epoch: 15 training_loss 0.17448567874729634 test_loss: 0.18838975429534913
epoch: 16 training_loss 0.19447023246437312 test_loss: 0.20254795551300048
epoch: 17 training_loss 0.18387751564383506 test_loss: 0.16677747964859008
epoch: 18 training_loss 0.17930955976247787 test_loss: 0.1963423013687134
epoch: 19 training_loss 0.19361649185419083 test_loss: 0.20343964099884032
epoch: 20 training_loss 0.18012002654373646 test_loss: 0.17009346485137938
epoch: 21 training_loss 0.18142382495105266 test_loss: 0.18178346157073974
epoch: 22 training_loss 0.18002177394926547 test_loss: 0.17665565013885498
epoch: 23 training_loss 0.18266342967748642 test_loss: 0.1968526601791382
epoch: 24 training_loss 0.1730197387933731 test_loss: 0.18730313777923585
epoch: 25 training_loss 0.186364224627614 test_loss: 0.2033724308013916
epoch: 26 training_loss 0.1829897541552782 test_loss: 0.19252437353134155
epoch: 27 training_loss 0.1774540378898382 test_loss: 0.19353199005126953
epoch: 28 training_loss 0.18118313312530518 test_loss: 0.17092026472091676
epoch: 29 training_loss 0.1812448228150606 test_loss: 0.18303651809692384
epoch: 30 training_loss 0.1915073251724243 test_loss: 0.1968762159347534
epoch: 31 training_loss 0.18016083367168903 test_loss: 0.19230260848999023
epoch: 32 training_loss 0.18458012498915197 test_loss: 0.19697531461715698
epoch: 33 training_loss 0.1841453341394663 test_loss: 0.18381600379943847
epoch: 34 training_loss 0.18974986486136913 test_loss: 0.18215008974075317
epoch: 35 training_loss 0.18287391580641268 test_loss: 0.1839097857475281
epoch: 36 training_loss 0.18574643485248088 test_loss: 0.18545563220977784
epoch: 37 training_loss 0.18135726667940616 test_loss: 0.17791320085525514
epoch: 38 training_loss 0.182111476957798 test_loss: 0.1842820405960083
epoch: 39 training_loss 0.1813373129814863 test_loss: 0.1728588581085205
epoch: 40 training_loss 0.18470803409814834 test_loss: 0.1735093355178833
epoch: 41 training_loss 0.17923097044229508 test_loss: 0.19151612520217895
epoch: 42 training_loss 0.18534068636596202 test_loss: 0.1860805869102478
epoch: 43 training_loss 0.1734061452001333 test_loss: 0.19232991933822632
epoch: 44 training_loss 0.18625720649957656 test_loss: 0.1805172085762024
epoch: 45 training_loss 0.17652448371052742 test_loss: 0.17717652320861815
epoch: 46 training_loss 0.18116987258195877 test_loss: 0.17200083732604982
epoch: 47 training_loss 0.1750702752918005 test_loss: 0.17470529079437255
epoch: 48 training_loss 0.17581523083150385 test_loss: 0.1839950442314148
epoch: 49 training_loss 0.17789516381919385 test_loss: 0.1770260214805603
epoch: 50 training_loss 0.17115843296051025 test_loss: 0.17229211330413818
epoch: 51 training_loss 0.170876774340868 test_loss: 0.18890599012374878
epoch: 52 training_loss 0.17517246693372726 test_loss: 0.18310774564743043
epoch: 53 training_loss 0.1837459985166788 test_loss: 0.19800353050231934
epoch: 54 training_loss 0.17299057841300963 test_loss: 0.18483116626739501
epoch: 55 training_loss 0.17885809265077113 test_loss: 0.18186978101730347
epoch: 56 training_loss 0.17740217365324498 test_loss: 0.19765086174011232
epoch: 57 training_loss 0.18442441783845426 test_loss: 0.188672935962677
epoch: 58 training_loss 0.1797668182104826 test_loss: 0.18399262428283691
epoch: 59 training_loss 0.17978683911263943 test_loss: 0.1799132227897644
epoch: 60 training_loss 0.18134673669934273 test_loss: 0.16772537231445311
epoch: 61 training_loss 0.17741967231035233 test_loss: 0.18894360065460206
epoch: 62 training_loss 0.17634127914905548 test_loss: 0.18609822988510133
epoch: 63 training_loss 0.17968510396778584 test_loss: 0.19830634593963622
epoch: 64 training_loss 0.18211473435163497 test_loss: 0.18205540180206298
epoch: 65 training_loss 0.17131824240088464 test_loss: 0.16449050903320311
epoch: 66 training_loss 0.1766632030159235 test_loss: 0.18019229173660278
epoch: 67 training_loss 0.1816534911096096 test_loss: 0.19842369556427003
epoch: 68 training_loss 0.17730810679495335 test_loss: 0.19340943098068236
epoch: 69 training_loss 0.17773105278611184 test_loss: 0.18666409254074096
epoch: 70 training_loss 0.17178980223834514 test_loss: 0.16299442052841187
epoch: 71 training_loss 0.17175064258277417 test_loss: 0.18780221939086914
epoch: 72 training_loss 0.18069031238555908 test_loss: 0.19450916051864625
epoch: 73 training_loss 0.17682383500039578 test_loss: 0.174260151386261
epoch: 74 training_loss 0.17857005052268504 test_loss: 0.18533675670623778
epoch: 75 training_loss 0.18935356348752974 test_loss: 0.18286598920822145
epoch: 76 training_loss 0.17276703543961047 test_loss: 0.17457448244094848
epoch: 77 training_loss 0.17910691753029823 test_loss: 0.17830194234848024
epoch: 78 training_loss 0.1839243257045746 test_loss: 0.1973387837409973
epoch: 79 training_loss 0.18327130444347858 test_loss: 0.17495977878570557
epoch: 80 training_loss 0.17735057190060616 test_loss: 0.17931921482086183
epoch: 81 training_loss 0.17908973045647145 test_loss: 0.178231143951416
epoch: 82 training_loss 0.18544909119606018 test_loss: 0.17838871479034424
epoch: 83 training_loss 0.18008257899433375 test_loss: 0.18589812517166138
epoch: 84 training_loss 0.17960928045213223 test_loss: 0.1663672685623169
epoch: 85 training_loss 0.17390987768769264 test_loss: 0.19108272790908815
epoch: 86 training_loss 0.18119582742452622 test_loss: 0.17108771800994874
epoch: 87 training_loss 0.17281897358596324 test_loss: 0.20405380725860595
epoch: 88 training_loss 0.17673209242522717 test_loss: 0.19591976404190065
epoch: 89 training_loss 0.17682576775550843 test_loss: 0.17133647203445435
epoch: 90 training_loss 0.17904710233211518 test_loss: 0.17787052392959596
epoch: 91 training_loss 0.18180106602609158 test_loss: 0.17991652488708496
epoch: 92 training_loss 0.17655308119952678 test_loss: 0.182508647441864
epoch: 93 training_loss 0.18499890148639678 test_loss: 0.18783971071243286
epoch: 94 training_loss 0.18050459012389183 test_loss: 0.17758584022521973
epoch: 95 training_loss 0.17927810586988926 test_loss: 0.1773279905319214
epoch: 96 training_loss 0.18011021219193935 test_loss: 0.19167965650558472
epoch: 97 training_loss 0.17746066212654113 test_loss: 0.17300858497619628
epoch: 98 training_loss 0.18106665752828122 test_loss: 0.17624218463897706
epoch: 99 training_loss 0.18162885084748268 test_loss: 0.1794774651527405
epoch: 100 training_loss 0.1745770912617445 test_loss: 0.18091148138046265
epoch: 101 training_loss 0.18612372748553752 test_loss: 0.19038997888565062
epoch: 102 training_loss 0.17440882161259652 test_loss: 0.18160996437072754
epoch: 103 training_loss 0.18242865890264512 test_loss: 0.17781187295913697
epoch: 104 training_loss 0.17131043151021003 test_loss: 0.1844973683357239
epoch: 105 training_loss 0.17810740478336812 test_loss: 0.20030708312988282
epoch: 106 training_loss 0.17497629359364508 test_loss: 0.17270714044570923
epoch: 107 training_loss 0.18443028427660466 test_loss: 0.17610864639282225
epoch: 108 training_loss 0.1857241651415825 test_loss: 0.16948572397232056
epoch: 109 training_loss 0.17785759180784225 test_loss: 0.161915385723114
epoch: 110 training_loss 0.18014061823487282 test_loss: 0.17586320638656616
epoch: 111 training_loss 0.17366002760827542 test_loss: 0.16619731187820436
epoch: 112 training_loss 0.18031282886862754 test_loss: 0.1899956226348877
epoch: 113 training_loss 0.1799882375448942 test_loss: 0.18339576721191406
epoch: 114 training_loss 0.17705139584839344 test_loss: 0.17114709615707396
epoch: 115 training_loss 0.16786155812442302 test_loss: 0.18725404739379883
epoch: 116 training_loss 0.18290216587483882 test_loss: 0.16908841133117675
epoch: 117 training_loss 0.17442648991942405 test_loss: 0.1698014259338379
epoch: 118 training_loss 0.17493461064994334 test_loss: 0.1922313690185547
epoch: 119 training_loss 0.17584099188447 test_loss: 0.1801142454147339
epoch: 120 training_loss 0.17671571016311646 test_loss: 0.17445769309997558
epoch: 121 training_loss 0.17364005979150535 test_loss: 0.17783306837081908
epoch: 122 training_loss 0.18484128676354886 test_loss: 0.17877871990203859
epoch: 123 training_loss 0.1792860659211874 test_loss: 0.16359803676605225
epoch: 124 training_loss 0.182459828928113 test_loss: 0.1864788293838501
epoch: 125 training_loss 0.1822856356203556 test_loss: 0.16487689018249513
epoch: 126 training_loss 0.17370923720300196 test_loss: 0.18511749505996705
epoch: 127 training_loss 0.18505448363721372 test_loss: 0.18696494102478028
epoch: 128 training_loss 0.1755566620081663 test_loss: 0.1715742230415344
epoch: 129 training_loss 0.17810060508549214 test_loss: 0.1910543441772461
epoch: 130 training_loss 0.1768013072758913 test_loss: 0.16083214282989503
epoch: 131 training_loss 0.17528809536248446 test_loss: 0.17450230121612548
epoch: 132 training_loss 0.18294719785451888 test_loss: 0.17773548364639283
epoch: 133 training_loss 0.1819115764647722 test_loss: 0.17834177017211914
epoch: 134 training_loss 0.18223297387361526 test_loss: 0.16996749639511108
epoch: 135 training_loss 0.17561098657548427 test_loss: 0.18296871185302735
epoch: 136 training_loss 0.1824652310460806 test_loss: 0.17948625087738038
epoch: 137 training_loss 0.16663597840815783 test_loss: 0.18958935737609864
epoch: 138 training_loss 0.17144377417862416 test_loss: 0.18590180873870848
epoch: 139 training_loss 0.1793965131416917 test_loss: 0.1751227617263794
epoch: 140 training_loss 0.17851531222462655 test_loss: 0.18963710069656373
epoch: 141 training_loss 0.17136841371655465 test_loss: 0.16667152643203736
epoch: 142 training_loss 0.1791379678249359 test_loss: 0.16695151329040528
epoch: 143 training_loss 0.18533309496939182 test_loss: 0.18114088773727416
epoch: 144 training_loss 0.18029685869812964 test_loss: 0.16864138841629028
epoch: 145 training_loss 0.17332616284489633 test_loss: 0.17161207199096679
epoch: 146 training_loss 0.18949617490172385 test_loss: 0.171709406375885
epoch: 147 training_loss 0.17886401765048504 test_loss: 0.17627440690994262
epoch: 148 training_loss 0.17277639836072922 test_loss: 0.16822009086608886
epoch: 149 training_loss 0.17572572261095046 test_loss: 0.1668156385421753
epoch: 0 training_loss 7.921665415763855 test_loss: 5.117586517333985
epoch: 1 training_loss 3.939348108768463 test_loss: 3.123926544189453
epoch: 2 training_loss 2.693276370763779 test_loss: 2.269346237182617
epoch: 3 training_loss 2.087473886013031 test_loss: 1.9570867538452148
epoch: 4 training_loss 1.809453887939453 test_loss: 1.671144676208496
epoch: 5 training_loss 1.624742476940155 test_loss: 1.5644681930541993
epoch: 6 training_loss 1.4775967717170715 test_loss: 1.4716452598571776
epoch: 7 training_loss 1.405740110874176 test_loss: 1.377422046661377
epoch: 8 training_loss 1.3130331861972808 test_loss: 1.2953469276428222
epoch: 9 training_loss 1.247383486032486 test_loss: 1.228384780883789
epoch: 10 training_loss 1.1887419921159745 test_loss: 1.1454349517822267
epoch: 11 training_loss 1.1328250288963317 test_loss: 1.0959277153015137
epoch: 12 training_loss 1.096772579550743 test_loss: 1.083134078979492
epoch: 13 training_loss 1.044104809165001 test_loss: 1.0061599731445312
epoch: 14 training_loss 1.02395722925663 test_loss: 1.0532820701599122
epoch: 15 training_loss 0.9867760515213013 test_loss: 0.973448657989502
epoch: 16 training_loss 0.9624691361188888 test_loss: 0.990427303314209
epoch: 17 training_loss 0.9421472126245498 test_loss: 0.9452989578247071
epoch: 18 training_loss 0.9287073683738708 test_loss: 0.8868272781372071
epoch: 19 training_loss 0.9004315865039826 test_loss: 0.8742393493652344
epoch: 20 training_loss 0.874729397892952 test_loss: 0.8444489479064942
epoch: 21 training_loss 0.8600772297382355 test_loss: 0.8405071258544922
epoch: 22 training_loss 0.8511828231811523 test_loss: 0.8486783027648925
epoch: 23 training_loss 0.8299350208044052 test_loss: 0.8224129676818848
epoch: 24 training_loss 0.809978513121605 test_loss: 0.7961469173431397
epoch: 25 training_loss 0.793235958814621 test_loss: 0.7954225063323974
epoch: 26 training_loss 0.7716625356674194 test_loss: 0.7871990203857422
epoch: 27 training_loss 0.7804933542013168 test_loss: 0.8051065444946289
epoch: 28 training_loss 0.7739239513874054 test_loss: 0.7534595966339112
epoch: 29 training_loss 0.7836933547258377 test_loss: 0.7225141525268555
epoch: 30 training_loss 0.7382946646213532 test_loss: 0.7318606853485108
epoch: 31 training_loss 0.7295676738023757 test_loss: 0.7360922813415527
epoch: 32 training_loss 0.7442393839359284 test_loss: 0.7212509632110595
epoch: 33 training_loss 0.728197094798088 test_loss: 0.7110006809234619
epoch: 34 training_loss 0.7148976236581802 test_loss: 0.6988162040710449
epoch: 35 training_loss 0.715382884144783 test_loss: 0.7743980884552002
epoch: 36 training_loss 0.704726819396019 test_loss: 0.6853405475616455
epoch: 37 training_loss 0.7021838039159775 test_loss: 0.6915894508361816
epoch: 38 training_loss 0.6927248024940491 test_loss: 0.7054530143737793
epoch: 39 training_loss 0.6952584284543991 test_loss: 0.6967142581939697
epoch: 40 training_loss 0.6940096002817154 test_loss: 0.7048771858215332
epoch: 41 training_loss 0.6690667629241943 test_loss: 0.6510207176208496
epoch: 42 training_loss 0.6708486306667328 test_loss: 0.6751564979553223
epoch: 43 training_loss 0.6627179741859436 test_loss: 0.6835237979888916
epoch: 44 training_loss 0.6615318590402604 test_loss: 0.6426464080810547
epoch: 45 training_loss 0.6649324727058411 test_loss: 0.6761616706848145
epoch: 46 training_loss 0.6483926486968994 test_loss: 0.6429266452789306
epoch: 47 training_loss 0.6535426038503647 test_loss: 0.6725754737854004
epoch: 48 training_loss 0.6412082469463348 test_loss: 0.6244387626647949
epoch: 49 training_loss 0.6479815602302551 test_loss: 0.6444166660308838
epoch: 50 training_loss 0.6417556542158127 test_loss: 0.6294329166412354
epoch: 51 training_loss 0.6265927040576935 test_loss: 0.6221168994903564
epoch: 52 training_loss 0.6295767867565155 test_loss: 0.630252742767334
epoch: 53 training_loss 0.6354032576084137 test_loss: 0.6142445087432862
epoch: 54 training_loss 0.6235927492380142 test_loss: 0.6143438816070557
epoch: 55 training_loss 0.6308111590147019 test_loss: 0.6270042419433594
epoch: 56 training_loss 0.624125418663025 test_loss: 0.6201488018035889
epoch: 57 training_loss 0.6173243743181228 test_loss: 0.6188737392425537
epoch: 58 training_loss 0.6166512912511826 test_loss: 0.5909975051879883
epoch: 59 training_loss 0.596963102221489 test_loss: 0.5960756301879883
epoch: 60 training_loss 0.603600702881813 test_loss: 0.5970839500427246
epoch: 61 training_loss 0.5958945769071579 test_loss: 0.5932678699493408
epoch: 62 training_loss 0.6067578774690628 test_loss: 0.6402112007141113
epoch: 63 training_loss 0.6065579080581665 test_loss: 0.5854970932006835
epoch: 64 training_loss 0.5913796257972718 test_loss: 0.6068970680236816
epoch: 65 training_loss 0.5931877499818802 test_loss: 0.5872008323669433
epoch: 66 training_loss 0.5865066894888877 test_loss: 0.619839096069336
epoch: 67 training_loss 0.5938544464111328 test_loss: 0.609016227722168
epoch: 68 training_loss 0.5837221294641495 test_loss: 0.587371826171875
epoch: 69 training_loss 0.5928493851423263 test_loss: 0.569221019744873
epoch: 70 training_loss 0.5717474013566971 test_loss: 0.5771358489990235
epoch: 71 training_loss 0.5756842401623726 test_loss: 0.5615064620971679
epoch: 72 training_loss 0.5721651685237884 test_loss: 0.5744380474090576
epoch: 73 training_loss 0.5714757707715035 test_loss: 0.571804428100586
epoch: 74 training_loss 0.5768994629383087 test_loss: 0.5508074283599853
epoch: 75 training_loss 0.5676585978269577 test_loss: 0.5743166446685791
epoch: 76 training_loss 0.585558260679245 test_loss: 0.5957225322723388
epoch: 77 training_loss 0.5659316286444664 test_loss: 0.5862000942230224
epoch: 78 training_loss 0.5633911123871803 test_loss: 0.5713272571563721
epoch: 79 training_loss 0.5625659254193306 test_loss: 0.5511651515960694
epoch: 80 training_loss 0.5545821383595466 test_loss: 0.5384976863861084
epoch: 81 training_loss 0.5544529449939728 test_loss: 0.529570198059082
epoch: 82 training_loss 0.548845624923706 test_loss: 0.5456488609313965
epoch: 83 training_loss 0.5595599484443664 test_loss: 0.5585298061370849
epoch: 84 training_loss 0.5581749817728996 test_loss: 0.5686554908752441
epoch: 85 training_loss 0.553708265721798 test_loss: 0.5457169532775878
epoch: 86 training_loss 0.5481880387663841 test_loss: 0.5306137561798095
epoch: 87 training_loss 0.5510722550749779 test_loss: 0.5559154033660889
epoch: 88 training_loss 0.5527690216898918 test_loss: 0.5401358127593994
epoch: 89 training_loss 0.5373103335499764 test_loss: 0.5436718463897705
epoch: 90 training_loss 0.5469069319963455 test_loss: 0.5499142169952392
epoch: 91 training_loss 0.5407426449656486 test_loss: 0.5430785179138183
epoch: 92 training_loss 0.5384537401795387 test_loss: 0.5392145633697509
epoch: 93 training_loss 0.551805602312088 test_loss: 0.5431390762329101
epoch: 94 training_loss 0.5454786878824234 test_loss: 0.5270507335662842
epoch: 95 training_loss 0.5430379024147988 test_loss: 0.5386103630065918
epoch: 96 training_loss 0.52939915984869 test_loss: 0.5454147815704345
epoch: 97 training_loss 0.5233021971583366 test_loss: 0.5219535827636719
epoch: 98 training_loss 0.5325393208861351 test_loss: 0.5395125389099121
epoch: 99 training_loss 0.5398490512371064 test_loss: 0.5274561882019043
epoch: 100 training_loss 0.5324995976686477 test_loss: 0.513027572631836
epoch: 101 training_loss 0.5246729555726052 test_loss: 0.5397070407867431
epoch: 102 training_loss 0.5331343331933022 test_loss: 0.517567253112793
epoch: 103 training_loss 0.523525542318821 test_loss: 0.5453296184539795
epoch: 104 training_loss 0.529093773663044 test_loss: 0.5170705318450928
epoch: 105 training_loss 0.5281103324890136 test_loss: 0.5255073070526123
epoch: 106 training_loss 0.5310395526885986 test_loss: 0.5216395378112793
epoch: 107 training_loss 0.5251961162686348 test_loss: 0.5318552494049072
epoch: 108 training_loss 0.5195985946059227 test_loss: 0.5446131706237793
epoch: 109 training_loss 0.5138454514741898 test_loss: 0.5082796096801758
epoch: 110 training_loss 0.5277533239126205 test_loss: 0.5333802223205566
epoch: 111 training_loss 0.5209389469027519 test_loss: 0.5049375534057617
epoch: 112 training_loss 0.5177598750591278 test_loss: 0.5112625598907471
epoch: 113 training_loss 0.5134162786602974 test_loss: 0.5356968879699707
epoch: 114 training_loss 0.5160167583823204 test_loss: 0.52886962890625
epoch: 115 training_loss 0.510757502913475 test_loss: 0.5146162509918213
epoch: 116 training_loss 0.5066013768315315 test_loss: 0.5215250968933105
epoch: 117 training_loss 0.5185804972052575 test_loss: 0.5216844558715821
epoch: 118 training_loss 0.5146851944923401 test_loss: 0.5273263931274415
epoch: 119 training_loss 0.511044999063015 test_loss: 0.5064440727233886
epoch: 120 training_loss 0.5041902720928192 test_loss: 0.49141292572021483
epoch: 121 training_loss 0.5136671701073646 test_loss: 0.5065347671508789
epoch: 122 training_loss 0.5130072769522667 test_loss: 0.5236055850982666
epoch: 123 training_loss 0.5024060279130935 test_loss: 0.4963801383972168
epoch: 124 training_loss 0.5165285873413086 test_loss: 0.49680228233337403
epoch: 125 training_loss 0.5058627054095268 test_loss: 0.507052230834961
epoch: 126 training_loss 0.5073240810632705 test_loss: 0.5073204517364502
epoch: 127 training_loss 0.5071699085831642 test_loss: 0.4902505397796631
epoch: 128 training_loss 0.5135971236228943 test_loss: 0.4854133129119873
epoch: 129 training_loss 0.5122508203983307 test_loss: 0.48423590660095217
epoch: 130 training_loss 0.5002982291579247 test_loss: 0.5080753803253174
epoch: 131 training_loss 0.5053604009747505 test_loss: 0.47872276306152345
epoch: 132 training_loss 0.49880197703838347 test_loss: 0.4836970329284668
epoch: 133 training_loss 0.4944195136427879 test_loss: 0.4931195259094238
epoch: 134 training_loss 0.49556771337985994 test_loss: 0.48266286849975587
epoch: 135 training_loss 0.4976386195421219 test_loss: 0.4875071048736572
epoch: 136 training_loss 0.49691262394189833 test_loss: 0.49098668098449705
epoch: 137 training_loss 0.49757644414901736 test_loss: 0.49657382965087893
epoch: 138 training_loss 0.49602649360895157 test_loss: 0.49469804763793945
epoch: 139 training_loss 0.49374787241220475 test_loss: 0.486759614944458
epoch: 140 training_loss 0.4911729192733765 test_loss: 0.4963205814361572
epoch: 141 training_loss 0.49214857250452043 test_loss: 0.5122219562530518
epoch: 142 training_loss 0.49232624530792235 test_loss: 0.4827286243438721
epoch: 143 training_loss 0.4904629981517792 test_loss: 0.49040398597717283
epoch: 144 training_loss 0.48800515741109846 test_loss: 0.48143582344055175
epoch: 145 training_loss 0.4821644774079323 test_loss: 0.49211745262145995
epoch: 146 training_loss 0.48843360632658006 test_loss: 0.47244877815246583
epoch: 147 training_loss 0.4902889370918274 test_loss: 0.5174174308776855
epoch: 148 training_loss 0.498383364379406 test_loss: 0.49051270484924314
epoch: 149 training_loss 0.49630398660898206 test_loss: 0.48693008422851564
2576.3702239152126
episode: 0 training return: tensor(-245.1838, device='cuda:0')
episode: 1 training return: tensor(-129.2768, device='cuda:0')
episode: 2 training return: tensor(-352.0885, device='cuda:0')
episode: 3 training return: tensor(-230.3761, device='cuda:0')
epoch: 1 test_true_pfm: 2904.7633837041926 sim_pfm: 95.82073102556751
episode: 4 training return: tensor(-366.8087, device='cuda:0')
episode: 5 training return: tensor(-410.0557, device='cuda:0')
episode: 6 training return: tensor(-140.0576, device='cuda:0')
episode: 7 training return: tensor(190.1714, device='cuda:0')
epoch: 2 test_true_pfm: 2791.59871552128 sim_pfm: 30.67369248981898
episode: 8 training return: tensor(-177.6945, device='cuda:0')
episode: 9 training return: tensor(-26.5299, device='cuda:0')
episode: 10 training return: tensor(-345.7050, device='cuda:0')
episode: 11 training return: tensor(-357.1031, device='cuda:0')
epoch: 3 test_true_pfm: 3279.3154533376455 sim_pfm: 131.9939692504122
episode: 12 training return: tensor(-401.0125, device='cuda:0')
episode: 13 training return: tensor(-339.2252, device='cuda:0')
episode: 14 training return: tensor(-291.3057, device='cuda:0')
episode: 15 training return: tensor(-362.7193, device='cuda:0')
epoch: 4 test_true_pfm: 2984.8836978238373 sim_pfm: 200.75277491740417
episode: 16 training return: tensor(-378.5208, device='cuda:0')
episode: 17 training return: tensor(-138.8431, device='cuda:0')
episode: 18 training return: tensor(-340.1960, device='cuda:0')
episode: 19 training return: tensor(27.9409, device='cuda:0')
epoch: 5 test_true_pfm: 2563.6484642663504 sim_pfm: -94.35973220419449
episode: 20 training return: tensor(-393.3517, device='cuda:0')
episode: 21 training return: tensor(-329.4113, device='cuda:0')
episode: 22 training return: tensor(-59.4916, device='cuda:0')
episode: 23 training return: tensor(-316.4031, device='cuda:0')
epoch: 6 test_true_pfm: 2794.7925462401613 sim_pfm: 77.78964632345985
episode: 24 training return: tensor(-17.7716, device='cuda:0')
episode: 25 training return: tensor(-389.4052, device='cuda:0')
episode: 26 training return: tensor(-185.4660, device='cuda:0')
episode: 27 training return: tensor(-342.5248, device='cuda:0')
epoch: 7 test_true_pfm: 2607.185841178407 sim_pfm: -52.773295966209844
episode: 28 training return: tensor(-178.3291, device='cuda:0')
episode: 29 training return: tensor(10.7220, device='cuda:0')
episode: 30 training return: tensor(-375.7848, device='cuda:0')
episode: 31 training return: tensor(-310.4689, device='cuda:0')
epoch: 8 test_true_pfm: 3009.5525346401737 sim_pfm: -8.283159773855004
episode: 32 training return: tensor(-361.6606, device='cuda:0')
episode: 33 training return: tensor(315.5945, device='cuda:0')
episode: 34 training return: tensor(-162.1491, device='cuda:0')
episode: 35 training return: tensor(-167.0937, device='cuda:0')
epoch: 9 test_true_pfm: 2758.521828716884 sim_pfm: -44.917224634807404
episode: 36 training return: tensor(-359.9368, device='cuda:0')
episode: 37 training return: tensor(143.7532, device='cuda:0')
episode: 38 training return: tensor(-304.4814, device='cuda:0')
episode: 39 training return: tensor(-105.9003, device='cuda:0')
epoch: 10 test_true_pfm: 3174.733580760898 sim_pfm: 100.87370472948533
episode: 40 training return: tensor(51.9762, device='cuda:0')
episode: 41 training return: tensor(-303.5233, device='cuda:0')
episode: 42 training return: tensor(-373.8701, device='cuda:0')
episode: 43 training return: tensor(246.9464, device='cuda:0')
epoch: 11 test_true_pfm: 2755.2892307512993 sim_pfm: 109.66801822984901
episode: 44 training return: tensor(-107.0673, device='cuda:0')
episode: 45 training return: tensor(-405.2645, device='cuda:0')
episode: 46 training return: tensor(7.7299, device='cuda:0')
episode: 47 training return: tensor(-321.1091, device='cuda:0')
epoch: 12 test_true_pfm: 2701.650954826187 sim_pfm: 62.315073285348866
episode: 48 training return: tensor(-49.6719, device='cuda:0')
episode: 49 training return: tensor(81.5865, device='cuda:0')
episode: 50 training return: tensor(55.9310, device='cuda:0')
episode: 51 training return: tensor(149.9231, device='cuda:0')
epoch: 13 test_true_pfm: 2233.7803478208616 sim_pfm: 173.6175253026498
episode: 52 training return: tensor(-158.0843, device='cuda:0')
episode: 53 training return: tensor(319.8199, device='cuda:0')
episode: 54 training return: tensor(-174.9234, device='cuda:0')
episode: 55 training return: tensor(-344.2175, device='cuda:0')
epoch: 14 test_true_pfm: 2481.4780206952278 sim_pfm: 153.5146572565815
episode: 56 training return: tensor(-79.8794, device='cuda:0')
episode: 57 training return: tensor(262.6677, device='cuda:0')
episode: 58 training return: tensor(-159.6798, device='cuda:0')
episode: 59 training return: tensor(-349.2672, device='cuda:0')
epoch: 15 test_true_pfm: 2578.962352029151 sim_pfm: 99.95523783343378
episode: 60 training return: tensor(-408.0197, device='cuda:0')
episode: 61 training return: tensor(-64.9307, device='cuda:0')
episode: 62 training return: tensor(-302.7299, device='cuda:0')
episode: 63 training return: tensor(-384.3018, device='cuda:0')
epoch: 16 test_true_pfm: 2380.6656769458946 sim_pfm: 127.21370016405126
episode: 64 training return: tensor(-127.1318, device='cuda:0')
episode: 65 training return: tensor(-411.6429, device='cuda:0')
episode: 66 training return: tensor(-354.8372, device='cuda:0')
episode: 67 training return: tensor(-340.7287, device='cuda:0')
epoch: 17 test_true_pfm: 2669.666708712515 sim_pfm: 154.57425544814518
episode: 68 training return: tensor(-334.8593, device='cuda:0')
episode: 69 training return: tensor(224.5226, device='cuda:0')
episode: 70 training return: tensor(-24.1042, device='cuda:0')
episode: 71 training return: tensor(-80.0712, device='cuda:0')
epoch: 18 test_true_pfm: 2295.554201833247 sim_pfm: -1.6603528905155447
episode: 72 training return: tensor(-82.0288, device='cuda:0')
episode: 73 training return: tensor(-250.3860, device='cuda:0')
episode: 74 training return: tensor(-320.0416, device='cuda:0')
episode: 75 training return: tensor(-196.8548, device='cuda:0')
epoch: 19 test_true_pfm: 2882.4442345120065 sim_pfm: 255.45227259731232
episode: 76 training return: tensor(294.1815, device='cuda:0')
episode: 77 training return: tensor(-160.7469, device='cuda:0')
episode: 78 training return: tensor(-133.3952, device='cuda:0')
episode: 79 training return: tensor(-328.3056, device='cuda:0')
epoch: 20 test_true_pfm: 2705.0501964788396 sim_pfm: -18.879169655857066
episode: 80 training return: tensor(169.9052, device='cuda:0')
episode: 81 training return: tensor(-40.8507, device='cuda:0')
episode: 82 training return: tensor(269.2694, device='cuda:0')
episode: 83 training return: tensor(-4.3977, device='cuda:0')
epoch: 21 test_true_pfm: 2543.2414404389356 sim_pfm: 66.2482921530415
episode: 84 training return: tensor(-309.6375, device='cuda:0')
episode: 85 training return: tensor(233.4149, device='cuda:0')
episode: 86 training return: tensor(-145.5507, device='cuda:0')
episode: 87 training return: tensor(-57.1835, device='cuda:0')
epoch: 22 test_true_pfm: 3190.2139763830387 sim_pfm: 58.06940933249037
episode: 88 training return: tensor(-330.8452, device='cuda:0')
episode: 89 training return: tensor(-408.3080, device='cuda:0')
episode: 90 training return: tensor(-334.9737, device='cuda:0')
episode: 91 training return: tensor(-351.5144, device='cuda:0')
epoch: 23 test_true_pfm: 2944.1078154004613 sim_pfm: 30.383605498063844
episode: 92 training return: tensor(4.9634, device='cuda:0')
episode: 93 training return: tensor(341.8677, device='cuda:0')
episode: 94 training return: tensor(1.8927, device='cuda:0')
episode: 95 training return: tensor(-93.5076, device='cuda:0')
epoch: 24 test_true_pfm: 2809.453759353672 sim_pfm: -12.396387182292528
episode: 96 training return: tensor(-55.0882, device='cuda:0')
episode: 97 training return: tensor(287.1132, device='cuda:0')
episode: 98 training return: tensor(267.4009, device='cuda:0')
episode: 99 training return: tensor(-200.3341, device='cuda:0')
epoch: 25 test_true_pfm: 2478.0945323958745 sim_pfm: -59.119903478693836
episode: 100 training return: tensor(-68.1569, device='cuda:0')
episode: 101 training return: tensor(285.0150, device='cuda:0')
episode: 102 training return: tensor(292.0935, device='cuda:0')
episode: 103 training return: tensor(139.1093, device='cuda:0')
epoch: 26 test_true_pfm: 2774.7469046118495 sim_pfm: 29.840838809575263
episode: 104 training return: tensor(-144.9947, device='cuda:0')
episode: 105 training return: tensor(-33.8287, device='cuda:0')
episode: 106 training return: tensor(39.3184, device='cuda:0')
episode: 107 training return: tensor(222.7901, device='cuda:0')
epoch: 27 test_true_pfm: 2990.3071781638027 sim_pfm: -18.471280208730604
episode: 108 training return: tensor(231.9025, device='cuda:0')
episode: 109 training return: tensor(-311.6898, device='cuda:0')
episode: 110 training return: tensor(182.9653, device='cuda:0')
episode: 111 training return: tensor(242.6914, device='cuda:0')
epoch: 28 test_true_pfm: 2296.500865882434 sim_pfm: -63.48515773601442
episode: 112 training return: tensor(272.1407, device='cuda:0')
episode: 113 training return: tensor(-193.7902, device='cuda:0')
episode: 114 training return: tensor(90.5222, device='cuda:0')
episode: 115 training return: tensor(-122.7904, device='cuda:0')
epoch: 29 test_true_pfm: 3244.9994989311076 sim_pfm: 25.24639596856044
episode: 116 training return: tensor(-141.5328, device='cuda:0')
episode: 117 training return: tensor(246.1703, device='cuda:0')
episode: 118 training return: tensor(-186.5529, device='cuda:0')
episode: 119 training return: tensor(-304.3213, device='cuda:0')
epoch: 30 test_true_pfm: 2935.8295193227036 sim_pfm: 15.070569989271462
episode: 120 training return: tensor(-321.8396, device='cuda:0')
episode: 121 training return: tensor(213.1040, device='cuda:0')
episode: 122 training return: tensor(138.8772, device='cuda:0')
episode: 123 training return: tensor(-175.4026, device='cuda:0')
epoch: 31 test_true_pfm: 2760.2397649453346 sim_pfm: 107.88922657773946
episode: 124 training return: tensor(-351.0599, device='cuda:0')
episode: 125 training return: tensor(-303.7833, device='cuda:0')
episode: 126 training return: tensor(-184.7399, device='cuda:0')
episode: 127 training return: tensor(115.3853, device='cuda:0')
epoch: 32 test_true_pfm: 2754.196517287089 sim_pfm: 6.893930893827928
episode: 128 training return: tensor(-108.9483, device='cuda:0')
episode: 129 training return: tensor(242.3779, device='cuda:0')
episode: 130 training return: tensor(-230.2344, device='cuda:0')
episode: 131 training return: tensor(250.6090, device='cuda:0')
epoch: 33 test_true_pfm: 2253.4498766091942 sim_pfm: 73.51844378216386
episode: 132 training return: tensor(-76.6109, device='cuda:0')
episode: 133 training return: tensor(183.4893, device='cuda:0')
episode: 134 training return: tensor(-94.3870, device='cuda:0')
episode: 135 training return: tensor(-236.1478, device='cuda:0')
epoch: 34 test_true_pfm: 3016.872838461484 sim_pfm: 74.14401806149787
episode: 136 training return: tensor(139.6704, device='cuda:0')
episode: 137 training return: tensor(319.4118, device='cuda:0')
episode: 138 training return: tensor(-303.0029, device='cuda:0')
episode: 139 training return: tensor(-42.0473, device='cuda:0')
epoch: 35 test_true_pfm: 2588.972847166275 sim_pfm: 163.78191197975926
episode: 140 training return: tensor(257.1590, device='cuda:0')
episode: 141 training return: tensor(98.3451, device='cuda:0')
episode: 142 training return: tensor(261.8389, device='cuda:0')
episode: 143 training return: tensor(-86.3578, device='cuda:0')
epoch: 36 test_true_pfm: 2228.2196142004323 sim_pfm: -17.788708234157337
episode: 144 training return: tensor(-372.2431, device='cuda:0')
episode: 145 training return: tensor(-166.0103, device='cuda:0')
episode: 146 training return: tensor(-12.1188, device='cuda:0')
episode: 147 training return: tensor(-2.2925, device='cuda:0')
epoch: 37 test_true_pfm: 2641.9183075557967 sim_pfm: 205.55342762886235
episode: 148 training return: tensor(-65.4958, device='cuda:0')
episode: 149 training return: tensor(-311.7271, device='cuda:0')
episode: 150 training return: tensor(-356.0532, device='cuda:0')
episode: 151 training return: tensor(-127.7620, device='cuda:0')
epoch: 38 test_true_pfm: 2872.353740928602 sim_pfm: 91.5634413077302
episode: 152 training return: tensor(-103.8603, device='cuda:0')
episode: 153 training return: tensor(271.3527, device='cuda:0')
episode: 154 training return: tensor(104.9341, device='cuda:0')
episode: 155 training return: tensor(284.6149, device='cuda:0')
epoch: 39 test_true_pfm: 2852.4457458230386 sim_pfm: 217.27024711727668
episode: 156 training return: tensor(-362.6833, device='cuda:0')
episode: 157 training return: tensor(114.8630, device='cuda:0')
episode: 158 training return: tensor(-185.1028, device='cuda:0')
episode: 159 training return: tensor(-163.3958, device='cuda:0')
epoch: 40 test_true_pfm: 2506.0526813648253 sim_pfm: 134.07978727383306
episode: 160 training return: tensor(-109.5235, device='cuda:0')
episode: 161 training return: tensor(233.8354, device='cuda:0')
episode: 162 training return: tensor(-34.1589, device='cuda:0')
episode: 163 training return: tensor(265.2553, device='cuda:0')
epoch: 41 test_true_pfm: 2933.3031066558815 sim_pfm: 80.87103221046466
episode: 164 training return: tensor(-33.7906, device='cuda:0')
episode: 165 training return: tensor(-338.5206, device='cuda:0')
episode: 166 training return: tensor(166.3071, device='cuda:0')
episode: 167 training return: tensor(200.1381, device='cuda:0')
epoch: 42 test_true_pfm: 2699.1353210254547 sim_pfm: 114.87438651290722
episode: 168 training return: tensor(244.6932, device='cuda:0')
episode: 169 training return: tensor(-324.5725, device='cuda:0')
episode: 170 training return: tensor(-322.6035, device='cuda:0')
episode: 171 training return: tensor(-129.9659, device='cuda:0')
epoch: 43 test_true_pfm: 2759.407410349511 sim_pfm: 40.43164158040114
episode: 172 training return: tensor(-405.3091, device='cuda:0')
episode: 173 training return: tensor(99.2258, device='cuda:0')
episode: 174 training return: tensor(-256.4336, device='cuda:0')
episode: 175 training return: tensor(-91.2671, device='cuda:0')
epoch: 44 test_true_pfm: 2670.2790472861325 sim_pfm: -27.924541161279194
episode: 176 training return: tensor(-234.1288, device='cuda:0')
episode: 177 training return: tensor(-252.1809, device='cuda:0')
episode: 178 training return: tensor(-297.4483, device='cuda:0')
episode: 179 training return: tensor(-405.3257, device='cuda:0')
epoch: 45 test_true_pfm: 3261.1148972538845 sim_pfm: 3.194490167690674
episode: 180 training return: tensor(-408.2101, device='cuda:0')
episode: 181 training return: tensor(-96.1861, device='cuda:0')
episode: 182 training return: tensor(-270.4567, device='cuda:0')
episode: 183 training return: tensor(-66.6571, device='cuda:0')
epoch: 46 test_true_pfm: 3231.27594239817 sim_pfm: 44.60719322833271
episode: 184 training return: tensor(-368.0009, device='cuda:0')
episode: 185 training return: tensor(236.2035, device='cuda:0')
episode: 186 training return: tensor(249.9313, device='cuda:0')
episode: 187 training return: tensor(-50.9890, device='cuda:0')
epoch: 47 test_true_pfm: 2516.9252230063043 sim_pfm: -12.334424638189375
episode: 188 training return: tensor(78.9815, device='cuda:0')
episode: 189 training return: tensor(-302.9530, device='cuda:0')
episode: 190 training return: tensor(247.3252, device='cuda:0')
episode: 191 training return: tensor(-270.4211, device='cuda:0')
epoch: 48 test_true_pfm: 2711.878386454475 sim_pfm: -77.13333927907904
episode: 192 training return: tensor(-71.8880, device='cuda:0')
episode: 193 training return: tensor(-305.9930, device='cuda:0')
episode: 194 training return: tensor(123.4104, device='cuda:0')
episode: 195 training return: tensor(-180.7913, device='cuda:0')
epoch: 49 test_true_pfm: 2882.312020237276 sim_pfm: 250.60069889528677
episode: 196 training return: tensor(-313.8205, device='cuda:0')
episode: 197 training return: tensor(-394.8658, device='cuda:0')
episode: 198 training return: tensor(167.4698, device='cuda:0')
episode: 199 training return: tensor(-102.5204, device='cuda:0')
epoch: 50 test_true_pfm: 2396.624078380433 sim_pfm: 161.6052563492267
episode: 200 training return: tensor(-154.3191, device='cuda:0')
episode: 201 training return: tensor(-117.4710, device='cuda:0')
episode: 202 training return: tensor(91.3400, device='cuda:0')
episode: 203 training return: tensor(280.9297, device='cuda:0')
epoch: 51 test_true_pfm: 2547.7646485531154 sim_pfm: 7.119949397398159
episode: 204 training return: tensor(-97.2239, device='cuda:0')
episode: 205 training return: tensor(-309.6403, device='cuda:0')
episode: 206 training return: tensor(-287.9993, device='cuda:0')
episode: 207 training return: tensor(272.3342, device='cuda:0')
epoch: 52 test_true_pfm: 2300.1210582811195 sim_pfm: 207.75420290633338
episode: 208 training return: tensor(-393.2724, device='cuda:0')
episode: 209 training return: tensor(-388.6926, device='cuda:0')
episode: 210 training return: tensor(129.6255, device='cuda:0')
episode: 211 training return: tensor(-170.5891, device='cuda:0')
epoch: 53 test_true_pfm: 3013.9596606694377 sim_pfm: 38.05683483187264
episode: 212 training return: tensor(-250.6252, device='cuda:0')
episode: 213 training return: tensor(-113.0793, device='cuda:0')
episode: 214 training return: tensor(159.2935, device='cuda:0')
episode: 215 training return: tensor(-303.9738, device='cuda:0')
epoch: 54 test_true_pfm: 2879.4899680313943 sim_pfm: 127.3939988987986
episode: 216 training return: tensor(-314.3373, device='cuda:0')
episode: 217 training return: tensor(268.2437, device='cuda:0')
episode: 218 training return: tensor(-82.4276, device='cuda:0')
episode: 219 training return: tensor(263.9518, device='cuda:0')
epoch: 55 test_true_pfm: 2997.5428969514505 sim_pfm: 152.47599881210286
episode: 220 training return: tensor(-156.9088, device='cuda:0')
episode: 221 training return: tensor(-308.3877, device='cuda:0')
episode: 222 training return: tensor(117.4837, device='cuda:0')
episode: 223 training return: tensor(-260.5131, device='cuda:0')
epoch: 56 test_true_pfm: 3238.0949172970268 sim_pfm: 50.86007948064556
episode: 224 training return: tensor(-273.1565, device='cuda:0')
episode: 225 training return: tensor(-374.9910, device='cuda:0')
episode: 226 training return: tensor(-131.4334, device='cuda:0')
episode: 227 training return: tensor(142.9198, device='cuda:0')
epoch: 57 test_true_pfm: 2478.4066360036813 sim_pfm: -102.79908263941373
episode: 228 training return: tensor(-361.1703, device='cuda:0')
episode: 229 training return: tensor(274.4187, device='cuda:0')
episode: 230 training return: tensor(-320.3347, device='cuda:0')
episode: 231 training return: tensor(-354.0563, device='cuda:0')
epoch: 58 test_true_pfm: 2264.6263266669384 sim_pfm: 80.8770966201555
episode: 232 training return: tensor(-324.2975, device='cuda:0')
episode: 233 training return: tensor(-137.6398, device='cuda:0')
episode: 234 training return: tensor(-100.2889, device='cuda:0')
episode: 235 training return: tensor(-88.7215, device='cuda:0')
epoch: 59 test_true_pfm: 2225.683859580104 sim_pfm: -77.20713340506579
episode: 236 training return: tensor(-309.9669, device='cuda:0')
episode: 237 training return: tensor(-11.4078, device='cuda:0')
episode: 238 training return: tensor(-308.3572, device='cuda:0')
episode: 239 training return: tensor(305.4040, device='cuda:0')
epoch: 60 test_true_pfm: 2636.34903363312 sim_pfm: 31.905623960405745
episode: 240 training return: tensor(-95.7416, device='cuda:0')
episode: 241 training return: tensor(-15.8780, device='cuda:0')
episode: 242 training return: tensor(14.4489, device='cuda:0')
episode: 243 training return: tensor(-313.8871, device='cuda:0')
epoch: 61 test_true_pfm: 3003.664018861638 sim_pfm: 0.8495705313980579
episode: 244 training return: tensor(-80.7044, device='cuda:0')
episode: 245 training return: tensor(-125.4210, device='cuda:0')
episode: 246 training return: tensor(255.6053, device='cuda:0')
episode: 247 training return: tensor(-75.8872, device='cuda:0')
epoch: 62 test_true_pfm: 2636.932179461664 sim_pfm: -22.387513721594587
episode: 248 training return: tensor(-117.8616, device='cuda:0')
episode: 249 training return: tensor(-71.7163, device='cuda:0')
episode: 250 training return: tensor(-110.0087, device='cuda:0')
episode: 251 training return: tensor(223.8486, device='cuda:0')
epoch: 63 test_true_pfm: 3178.8598864329992 sim_pfm: 27.726260070844244
episode: 252 training return: tensor(-118.8885, device='cuda:0')
episode: 253 training return: tensor(23.9089, device='cuda:0')
episode: 254 training return: tensor(321.5290, device='cuda:0')
episode: 255 training return: tensor(-273.2143, device='cuda:0')
epoch: 64 test_true_pfm: 2659.2800913737265 sim_pfm: 149.49519110581605
episode: 256 training return: tensor(313.0280, device='cuda:0')
episode: 257 training return: tensor(126.5998, device='cuda:0')
episode: 258 training return: tensor(265.7244, device='cuda:0')
episode: 259 training return: tensor(-59.2759, device='cuda:0')
epoch: 65 test_true_pfm: 2894.9396160756514 sim_pfm: 19.30821644272267
episode: 260 training return: tensor(-66.4524, device='cuda:0')
episode: 261 training return: tensor(302.7875, device='cuda:0')
episode: 262 training return: tensor(-154.4124, device='cuda:0')
episode: 263 training return: tensor(-197.1117, device='cuda:0')
epoch: 66 test_true_pfm: 2858.9764340879206 sim_pfm: 130.5213644519002
episode: 264 training return: tensor(-164.0744, device='cuda:0')
episode: 265 training return: tensor(-207.1878, device='cuda:0')
episode: 266 training return: tensor(-133.9592, device='cuda:0')
episode: 267 training return: tensor(261.8030, device='cuda:0')
epoch: 67 test_true_pfm: 2842.8237701641447 sim_pfm: 219.28197371299999
episode: 268 training return: tensor(-399.0391, device='cuda:0')
episode: 269 training return: tensor(320.6738, device='cuda:0')
episode: 270 training return: tensor(-270.8427, device='cuda:0')
episode: 271 training return: tensor(255.3678, device='cuda:0')
epoch: 68 test_true_pfm: 2836.868435858137 sim_pfm: 48.254075130214915
episode: 272 training return: tensor(-87.4432, device='cuda:0')
episode: 273 training return: tensor(120.7733, device='cuda:0')
episode: 274 training return: tensor(270.8197, device='cuda:0')
episode: 275 training return: tensor(-95.0238, device='cuda:0')
epoch: 69 test_true_pfm: 2238.911832967758 sim_pfm: 202.66562362040472
episode: 276 training return: tensor(-68.0870, device='cuda:0')
episode: 277 training return: tensor(-60.8583, device='cuda:0')
episode: 278 training return: tensor(-9.1409, device='cuda:0')
episode: 279 training return: tensor(-37.3640, device='cuda:0')
epoch: 70 test_true_pfm: 2640.496972824751 sim_pfm: -58.78013343602652
episode: 280 training return: tensor(116.1864, device='cuda:0')
episode: 281 training return: tensor(73.0697, device='cuda:0')
episode: 282 training return: tensor(-86.4037, device='cuda:0')
episode: 283 training return: tensor(269.4083, device='cuda:0')
epoch: 71 test_true_pfm: 2581.9993979139617 sim_pfm: -20.999377573801514
episode: 284 training return: tensor(-194.5612, device='cuda:0')
episode: 285 training return: tensor(-96.0306, device='cuda:0')
episode: 286 training return: tensor(-57.6614, device='cuda:0')
episode: 287 training return: tensor(-107.4026, device='cuda:0')
epoch: 72 test_true_pfm: 2929.4203094492823 sim_pfm: 260.6486819608447
episode: 288 training return: tensor(-388.6380, device='cuda:0')
episode: 289 training return: tensor(-129.5380, device='cuda:0')
episode: 290 training return: tensor(-277.5885, device='cuda:0')
episode: 291 training return: tensor(115.0560, device='cuda:0')
epoch: 73 test_true_pfm: 2827.968073698652 sim_pfm: 41.46275547122544
episode: 292 training return: tensor(-280.8598, device='cuda:0')
episode: 293 training return: tensor(-310.5369, device='cuda:0')
episode: 294 training return: tensor(-160.9240, device='cuda:0')
episode: 295 training return: tensor(289.5395, device='cuda:0')
epoch: 74 test_true_pfm: 2476.3937420217103 sim_pfm: 84.72473064126098
episode: 296 training return: tensor(237.7925, device='cuda:0')
episode: 297 training return: tensor(104.2032, device='cuda:0')
episode: 298 training return: tensor(-78.5542, device='cuda:0')
episode: 299 training return: tensor(-321.4991, device='cuda:0')
epoch: 75 test_true_pfm: 2860.1289015920065 sim_pfm: 117.79517668448777
episode: 300 training return: tensor(-364.5562, device='cuda:0')
episode: 301 training return: tensor(-7.7288, device='cuda:0')
episode: 302 training return: tensor(-350.2411, device='cuda:0')
episode: 303 training return: tensor(-114.6191, device='cuda:0')
epoch: 76 test_true_pfm: 2495.47355596818 sim_pfm: -100.0903697887261
episode: 304 training return: tensor(-240.6287, device='cuda:0')
episode: 305 training return: tensor(-169.6049, device='cuda:0')
episode: 306 training return: tensor(-161.2935, device='cuda:0')
episode: 307 training return: tensor(-70.3525, device='cuda:0')
epoch: 77 test_true_pfm: 2715.136241972216 sim_pfm: -14.678446011074508
episode: 308 training return: tensor(270.7824, device='cuda:0')
episode: 309 training return: tensor(98.2289, device='cuda:0')
episode: 310 training return: tensor(-85.3045, device='cuda:0')
episode: 311 training return: tensor(-228.1397, device='cuda:0')
epoch: 78 test_true_pfm: 2365.624743296348 sim_pfm: -15.567427234200295
episode: 312 training return: tensor(-276.0060, device='cuda:0')
episode: 313 training return: tensor(298.2685, device='cuda:0')
episode: 314 training return: tensor(-88.6402, device='cuda:0')
episode: 315 training return: tensor(-166.4172, device='cuda:0')
epoch: 79 test_true_pfm: 3157.600247201215 sim_pfm: -20.910489732574206
episode: 316 training return: tensor(-355.5907, device='cuda:0')
episode: 317 training return: tensor(112.6565, device='cuda:0')
episode: 318 training return: tensor(338.2667, device='cuda:0')
episode: 319 training return: tensor(164.2857, device='cuda:0')
epoch: 80 test_true_pfm: 2354.779247393195 sim_pfm: -168.40965890389634
episode: 320 training return: tensor(-98.1164, device='cuda:0')
episode: 321 training return: tensor(-29.6762, device='cuda:0')
episode: 322 training return: tensor(84.0064, device='cuda:0')
episode: 323 training return: tensor(-94.7386, device='cuda:0')
epoch: 81 test_true_pfm: 2232.0567628099357 sim_pfm: 36.43964472568283
episode: 324 training return: tensor(268.4229, device='cuda:0')
episode: 325 training return: tensor(-53.7609, device='cuda:0')
episode: 326 training return: tensor(-154.4036, device='cuda:0')
episode: 327 training return: tensor(233.9183, device='cuda:0')
epoch: 82 test_true_pfm: 2807.151560748243 sim_pfm: 69.75142486203306
episode: 328 training return: tensor(-397.7863, device='cuda:0')
episode: 329 training return: tensor(-331.5062, device='cuda:0')
episode: 330 training return: tensor(121.0447, device='cuda:0')
episode: 331 training return: tensor(-93.1374, device='cuda:0')
epoch: 83 test_true_pfm: 2850.118560121093 sim_pfm: 29.822724133215768
episode: 332 training return: tensor(-71.3428, device='cuda:0')
episode: 333 training return: tensor(-398.3298, device='cuda:0')
episode: 334 training return: tensor(309.0960, device='cuda:0')
episode: 335 training return: tensor(153.9316, device='cuda:0')
epoch: 84 test_true_pfm: 2360.5106968883933 sim_pfm: 60.63917834196278
episode: 336 training return: tensor(-200.3812, device='cuda:0')
episode: 337 training return: tensor(93.4378, device='cuda:0')
episode: 338 training return: tensor(118.8438, device='cuda:0')
episode: 339 training return: tensor(-325.0440, device='cuda:0')
epoch: 85 test_true_pfm: 2507.545522707274 sim_pfm: 25.74240748762774
episode: 340 training return: tensor(168.9363, device='cuda:0')
episode: 341 training return: tensor(-194.1330, device='cuda:0')
episode: 342 training return: tensor(-166.8447, device='cuda:0')
episode: 343 training return: tensor(-89.2440, device='cuda:0')
epoch: 86 test_true_pfm: 3019.533526172973 sim_pfm: 103.80075594701339
episode: 344 training return: tensor(-105.9903, device='cuda:0')
episode: 345 training return: tensor(-148.2947, device='cuda:0')
episode: 346 training return: tensor(-232.2964, device='cuda:0')
episode: 347 training return: tensor(21.9089, device='cuda:0')
epoch: 87 test_true_pfm: 2552.9196628128116 sim_pfm: 20.43455364710341
episode: 348 training return: tensor(-337.6553, device='cuda:0')
episode: 349 training return: tensor(-99.8222, device='cuda:0')
episode: 350 training return: tensor(-288.9801, device='cuda:0')
episode: 351 training return: tensor(306.0764, device='cuda:0')
epoch: 88 test_true_pfm: 2871.082627937734 sim_pfm: 264.62438787526725
episode: 352 training return: tensor(-379.4186, device='cuda:0')
episode: 353 training return: tensor(-402.7991, device='cuda:0')
episode: 354 training return: tensor(-23.8180, device='cuda:0')
episode: 355 training return: tensor(240.5419, device='cuda:0')
epoch: 89 test_true_pfm: 2717.759439105963 sim_pfm: 214.3885568943612
episode: 356 training return: tensor(16.4132, device='cuda:0')
episode: 357 training return: tensor(-392.3047, device='cuda:0')
episode: 358 training return: tensor(-399.2178, device='cuda:0')
episode: 359 training return: tensor(252.2574, device='cuda:0')
epoch: 90 test_true_pfm: 2541.7128644928166 sim_pfm: 100.65143218521068
episode: 360 training return: tensor(-365.5784, device='cuda:0')
episode: 361 training return: tensor(295.2784, device='cuda:0')
episode: 362 training return: tensor(-313.9835, device='cuda:0')
episode: 363 training return: tensor(-313.5332, device='cuda:0')
epoch: 91 test_true_pfm: 2200.565495165272 sim_pfm: 200.48457000359
episode: 364 training return: tensor(266.6150, device='cuda:0')
episode: 365 training return: tensor(-127.2164, device='cuda:0')
episode: 366 training return: tensor(280.6038, device='cuda:0')
episode: 367 training return: tensor(-398.2450, device='cuda:0')
epoch: 92 test_true_pfm: 2603.7842810216953 sim_pfm: 133.13794817677504
episode: 368 training return: tensor(223.5350, device='cuda:0')
episode: 369 training return: tensor(-309.0092, device='cuda:0')
episode: 370 training return: tensor(257.4610, device='cuda:0')
episode: 371 training return: tensor(-324.2840, device='cuda:0')
epoch: 93 test_true_pfm: 2943.8926062101054 sim_pfm: -3.434002878687655
episode: 372 training return: tensor(-208.5885, device='cuda:0')
episode: 373 training return: tensor(-0.1899, device='cuda:0')
episode: 374 training return: tensor(-69.3215, device='cuda:0')
episode: 375 training return: tensor(-309.9320, device='cuda:0')
epoch: 94 test_true_pfm: 3068.217061150741 sim_pfm: 127.57188129458034
episode: 376 training return: tensor(319.9633, device='cuda:0')
episode: 377 training return: tensor(-279.6670, device='cuda:0')
episode: 378 training return: tensor(200.9192, device='cuda:0')
episode: 379 training return: tensor(88.2861, device='cuda:0')
epoch: 95 test_true_pfm: 2615.9760804986713 sim_pfm: -12.173469797882717
episode: 380 training return: tensor(246.5198, device='cuda:0')
episode: 381 training return: tensor(-359.2366, device='cuda:0')
episode: 382 training return: tensor(315.2635, device='cuda:0')
episode: 383 training return: tensor(97.7765, device='cuda:0')
epoch: 96 test_true_pfm: 3051.473606779919 sim_pfm: 40.642525106280424
episode: 384 training return: tensor(239.3988, device='cuda:0')
episode: 385 training return: tensor(13.7331, device='cuda:0')
episode: 386 training return: tensor(188.5462, device='cuda:0')
episode: 387 training return: tensor(198.5451, device='cuda:0')
epoch: 97 test_true_pfm: 2724.9424146440647 sim_pfm: 16.943577286903746
episode: 388 training return: tensor(-308.3472, device='cuda:0')
episode: 389 training return: tensor(-312.2786, device='cuda:0')
episode: 390 training return: tensor(-165.4912, device='cuda:0')
episode: 391 training return: tensor(-138.2433, device='cuda:0')
epoch: 98 test_true_pfm: 2534.5366990286825 sim_pfm: 0.18738396217425665
episode: 392 training return: tensor(-345.4345, device='cuda:0')
episode: 393 training return: tensor(-165.3936, device='cuda:0')
episode: 394 training return: tensor(-341.7088, device='cuda:0')
episode: 395 training return: tensor(263.6124, device='cuda:0')
epoch: 99 test_true_pfm: 3011.0106415980536 sim_pfm: -96.71050408916199
episode: 396 training return: tensor(-79.7139, device='cuda:0')
episode: 397 training return: tensor(-338.3755, device='cuda:0')
episode: 398 training return: tensor(-199.8806, device='cuda:0')
episode: 399 training return: tensor(-250.8995, device='cuda:0')
epoch: 100 test_true_pfm: 2870.864130559103 sim_pfm: 181.3941564943428
episode: 400 training return: tensor(0.0689, device='cuda:0')
episode: 401 training return: tensor(-196.2003, device='cuda:0')
episode: 402 training return: tensor(29.8043, device='cuda:0')
episode: 403 training return: tensor(-321.7890, device='cuda:0')
epoch: 101 test_true_pfm: 2954.2723618306063 sim_pfm: 173.71826999409436
episode: 404 training return: tensor(-128.4918, device='cuda:0')
episode: 405 training return: tensor(-286.1086, device='cuda:0')
episode: 406 training return: tensor(-288.2921, device='cuda:0')
episode: 407 training return: tensor(77.3959, device='cuda:0')
epoch: 102 test_true_pfm: 3133.58110327631 sim_pfm: 81.02117755059346
episode: 408 training return: tensor(-353.7584, device='cuda:0')
episode: 409 training return: tensor(-386.4095, device='cuda:0')
episode: 410 training return: tensor(-391.3523, device='cuda:0')
episode: 411 training return: tensor(-311.3120, device='cuda:0')
epoch: 103 test_true_pfm: 2456.1667468839573 sim_pfm: 102.42343681363855
episode: 412 training return: tensor(-117.8400, device='cuda:0')
episode: 413 training return: tensor(-121.9751, device='cuda:0')
episode: 414 training return: tensor(18.2145, device='cuda:0')
episode: 415 training return: tensor(-354.9456, device='cuda:0')
epoch: 104 test_true_pfm: 2568.979355378623 sim_pfm: 242.9637829271572
episode: 416 training return: tensor(-400.8294, device='cuda:0')
episode: 417 training return: tensor(-14.6184, device='cuda:0')
episode: 418 training return: tensor(-362.2542, device='cuda:0')
episode: 419 training return: tensor(-303.0439, device='cuda:0')
epoch: 105 test_true_pfm: 3142.3503531373153 sim_pfm: 195.8005052522834
episode: 420 training return: tensor(-163.4044, device='cuda:0')
episode: 421 training return: tensor(284.7350, device='cuda:0')
episode: 422 training return: tensor(-405.7240, device='cuda:0')
episode: 423 training return: tensor(-341.8772, device='cuda:0')
epoch: 106 test_true_pfm: 2658.128665402545 sim_pfm: 73.9168552509218
episode: 424 training return: tensor(-342.2639, device='cuda:0')
episode: 425 training return: tensor(-158.6449, device='cuda:0')
episode: 426 training return: tensor(-261.8586, device='cuda:0')
episode: 427 training return: tensor(-77.5189, device='cuda:0')
epoch: 107 test_true_pfm: 2672.3224346196857 sim_pfm: 17.650752270652447
episode: 428 training return: tensor(-217.5849, device='cuda:0')
episode: 429 training return: tensor(-118.8904, device='cuda:0')
episode: 430 training return: tensor(253.4738, device='cuda:0')
episode: 431 training return: tensor(-284.8750, device='cuda:0')
epoch: 108 test_true_pfm: 2594.859561996041 sim_pfm: 10.728410783689469
episode: 432 training return: tensor(13.5883, device='cuda:0')
episode: 433 training return: tensor(-398.2831, device='cuda:0')
episode: 434 training return: tensor(-319.5885, device='cuda:0')
episode: 435 training return: tensor(262.7116, device='cuda:0')
epoch: 109 test_true_pfm: 2959.3874022382092 sim_pfm: -111.42902441629364
episode: 436 training return: tensor(299.4815, device='cuda:0')
episode: 437 training return: tensor(-112.1219, device='cuda:0')
episode: 438 training return: tensor(-53.3596, device='cuda:0')
episode: 439 training return: tensor(-28.3654, device='cuda:0')
epoch: 110 test_true_pfm: 2857.7714484056637 sim_pfm: 39.70295066711454
episode: 440 training return: tensor(-355.2700, device='cuda:0')
episode: 441 training return: tensor(-5.7624, device='cuda:0')
episode: 442 training return: tensor(-359.9306, device='cuda:0')
episode: 443 training return: tensor(242.9596, device='cuda:0')
epoch: 111 test_true_pfm: 2776.9462820625617 sim_pfm: 31.853132228522252
episode: 444 training return: tensor(247.2843, device='cuda:0')
episode: 445 training return: tensor(-115.4276, device='cuda:0')
episode: 446 training return: tensor(20.7373, device='cuda:0')
episode: 447 training return: tensor(264.9122, device='cuda:0')
epoch: 112 test_true_pfm: 2965.417265775584 sim_pfm: 134.45056064108698
episode: 448 training return: tensor(60.3937, device='cuda:0')
episode: 449 training return: tensor(-163.7238, device='cuda:0')
episode: 450 training return: tensor(-132.2962, device='cuda:0')
episode: 451 training return: tensor(-237.5743, device='cuda:0')
epoch: 113 test_true_pfm: 2152.8633621619406 sim_pfm: 30.527674535755068
episode: 452 training return: tensor(235.6411, device='cuda:0')
episode: 453 training return: tensor(-6.3922, device='cuda:0')
episode: 454 training return: tensor(-375.8767, device='cuda:0')
episode: 455 training return: tensor(-358.1690, device='cuda:0')
epoch: 114 test_true_pfm: 2552.04943323366 sim_pfm: 21.522178530615445
episode: 456 training return: tensor(-78.3520, device='cuda:0')
episode: 457 training return: tensor(255.3450, device='cuda:0')
episode: 458 training return: tensor(-368.1945, device='cuda:0')
episode: 459 training return: tensor(-239.1570, device='cuda:0')
epoch: 115 test_true_pfm: 2767.3356166877857 sim_pfm: 69.76208890678633
episode: 460 training return: tensor(-296.1924, device='cuda:0')
episode: 461 training return: tensor(-309.5819, device='cuda:0')
episode: 462 training return: tensor(60.9946, device='cuda:0')
episode: 463 training return: tensor(150.6295, device='cuda:0')
epoch: 116 test_true_pfm: 2433.16853864782 sim_pfm: 151.4172947941115
episode: 464 training return: tensor(78.1842, device='cuda:0')
episode: 465 training return: tensor(149.2867, device='cuda:0')
episode: 466 training return: tensor(-269.6707, device='cuda:0')
episode: 467 training return: tensor(-287.1811, device='cuda:0')
epoch: 117 test_true_pfm: 2373.9473463517957 sim_pfm: 20.523949727765284
episode: 468 training return: tensor(-354.2233, device='cuda:0')
episode: 469 training return: tensor(-332.5006, device='cuda:0')
episode: 470 training return: tensor(-118.4185, device='cuda:0')
episode: 471 training return: tensor(-368.0776, device='cuda:0')
epoch: 118 test_true_pfm: 2516.4646620166463 sim_pfm: 143.18595726860804
episode: 472 training return: tensor(-307.6294, device='cuda:0')
episode: 473 training return: tensor(140.9748, device='cuda:0')
episode: 474 training return: tensor(-403.5154, device='cuda:0')
episode: 475 training return: tensor(-246.8161, device='cuda:0')
epoch: 119 test_true_pfm: 2086.963610901017 sim_pfm: 147.26432002690854
episode: 476 training return: tensor(86.5467, device='cuda:0')
episode: 477 training return: tensor(-360.4800, device='cuda:0')
episode: 478 training return: tensor(-355.3445, device='cuda:0')
episode: 479 training return: tensor(-353.2610, device='cuda:0')
epoch: 120 test_true_pfm: 2418.877788293906 sim_pfm: -20.78150851877096
episode: 480 training return: tensor(-265.3368, device='cuda:0')
episode: 481 training return: tensor(-248.4754, device='cuda:0')
episode: 482 training return: tensor(-299.9031, device='cuda:0')
episode: 483 training return: tensor(250.3403, device='cuda:0')
epoch: 121 test_true_pfm: 2891.7950114574655 sim_pfm: 22.54961250181077
episode: 484 training return: tensor(-220.5731, device='cuda:0')
episode: 485 training return: tensor(135.3412, device='cuda:0')
episode: 486 training return: tensor(133.4932, device='cuda:0')
episode: 487 training return: tensor(256.1751, device='cuda:0')
epoch: 122 test_true_pfm: 2764.729045858152 sim_pfm: 110.89757557314199
episode: 488 training return: tensor(265.5196, device='cuda:0')
episode: 489 training return: tensor(-257.2686, device='cuda:0')
episode: 490 training return: tensor(67.5206, device='cuda:0')
episode: 491 training return: tensor(-404.4579, device='cuda:0')
epoch: 123 test_true_pfm: 2987.6284847409247 sim_pfm: 138.03687700400283
episode: 492 training return: tensor(-402.1751, device='cuda:0')
episode: 493 training return: tensor(-403.1827, device='cuda:0')
episode: 494 training return: tensor(-356.5754, device='cuda:0')
episode: 495 training return: tensor(-32.4432, device='cuda:0')
epoch: 124 test_true_pfm: 2783.5162829412566 sim_pfm: -34.16219155395326
episode: 496 training return: tensor(-377.2401, device='cuda:0')
episode: 497 training return: tensor(-267.0674, device='cuda:0')
episode: 498 training return: tensor(-154.9681, device='cuda:0')
episode: 499 training return: tensor(-381.5650, device='cuda:0')
epoch: 125 test_true_pfm: 3136.4626433884173 sim_pfm: 75.52309590634347
episode: 500 training return: tensor(238.2334, device='cuda:0')
episode: 501 training return: tensor(-10.5157, device='cuda:0')
episode: 502 training return: tensor(312.9053, device='cuda:0')
episode: 503 training return: tensor(-130.6967, device='cuda:0')
epoch: 126 test_true_pfm: 2867.3390294610267 sim_pfm: 92.1248049272884
episode: 504 training return: tensor(259.8914, device='cuda:0')
episode: 505 training return: tensor(-346.8960, device='cuda:0')
episode: 506 training return: tensor(-226.9763, device='cuda:0')
episode: 507 training return: tensor(-78.4288, device='cuda:0')
epoch: 127 test_true_pfm: 2821.23281086834 sim_pfm: -67.83510027746281
episode: 508 training return: tensor(-282.0489, device='cuda:0')
episode: 509 training return: tensor(-308.1375, device='cuda:0')
episode: 510 training return: tensor(-402.1769, device='cuda:0')
episode: 511 training return: tensor(-380.2465, device='cuda:0')
epoch: 128 test_true_pfm: 2598.032337061792 sim_pfm: -124.94197376724333
episode: 512 training return: tensor(-94.0548, device='cuda:0')
episode: 513 training return: tensor(-265.2925, device='cuda:0')
episode: 514 training return: tensor(263.8221, device='cuda:0')
episode: 515 training return: tensor(295.6621, device='cuda:0')
epoch: 129 test_true_pfm: 2870.680866372795 sim_pfm: -46.364412219341226
episode: 516 training return: tensor(110.6513, device='cuda:0')
episode: 517 training return: tensor(-138.5090, device='cuda:0')
episode: 518 training return: tensor(-365.1762, device='cuda:0')
episode: 519 training return: tensor(156.3443, device='cuda:0')
epoch: 130 test_true_pfm: 2427.976301569983 sim_pfm: 31.968877258244902
episode: 520 training return: tensor(52.5730, device='cuda:0')
episode: 521 training return: tensor(252.9322, device='cuda:0')
episode: 522 training return: tensor(-49.9284, device='cuda:0')
episode: 523 training return: tensor(284.1933, device='cuda:0')
epoch: 131 test_true_pfm: 2536.612139374843 sim_pfm: -94.03432443470228
episode: 524 training return: tensor(90.9934, device='cuda:0')
episode: 525 training return: tensor(-260.3593, device='cuda:0')
episode: 526 training return: tensor(288.4157, device='cuda:0')
episode: 527 training return: tensor(278.5366, device='cuda:0')
epoch: 132 test_true_pfm: 2733.238267847013 sim_pfm: -50.60376627999358
episode: 528 training return: tensor(-306.3989, device='cuda:0')
episode: 529 training return: tensor(-404.3650, device='cuda:0')
episode: 530 training return: tensor(-120.8545, device='cuda:0')
episode: 531 training return: tensor(67.9768, device='cuda:0')
epoch: 133 test_true_pfm: 2674.80722117901 sim_pfm: 34.74345668586708
episode: 532 training return: tensor(-383.3233, device='cuda:0')
episode: 533 training return: tensor(-70.1378, device='cuda:0')
episode: 534 training return: tensor(283.3320, device='cuda:0')
episode: 535 training return: tensor(-115.3539, device='cuda:0')
epoch: 134 test_true_pfm: 2812.411023587754 sim_pfm: 73.733322866261
episode: 536 training return: tensor(-80.2337, device='cuda:0')
episode: 537 training return: tensor(-384.9217, device='cuda:0')
episode: 538 training return: tensor(-328.2391, device='cuda:0')
episode: 539 training return: tensor(-35.9576, device='cuda:0')
epoch: 135 test_true_pfm: 2753.490903617288 sim_pfm: -67.52267367828365
episode: 540 training return: tensor(-24.6145, device='cuda:0')
episode: 541 training return: tensor(-300.7227, device='cuda:0')
episode: 542 training return: tensor(-325.0736, device='cuda:0')
episode: 543 training return: tensor(-374.1213, device='cuda:0')
epoch: 136 test_true_pfm: 2872.6325972955005 sim_pfm: -134.56690611181935
episode: 544 training return: tensor(-284.0863, device='cuda:0')
episode: 545 training return: tensor(249.0116, device='cuda:0')
episode: 546 training return: tensor(-175.9778, device='cuda:0')
episode: 547 training return: tensor(-47.5295, device='cuda:0')
epoch: 137 test_true_pfm: 2915.4894478583374 sim_pfm: 13.429668511962518
episode: 548 training return: tensor(-364.5856, device='cuda:0')
episode: 549 training return: tensor(-381.7769, device='cuda:0')
episode: 550 training return: tensor(-317.9308, device='cuda:0')
episode: 551 training return: tensor(-352.5949, device='cuda:0')
epoch: 138 test_true_pfm: 2185.219319539174 sim_pfm: 223.22762219414776
episode: 552 training return: tensor(61.8171, device='cuda:0')
episode: 553 training return: tensor(-94.9221, device='cuda:0')
episode: 554 training return: tensor(71.8498, device='cuda:0')
episode: 555 training return: tensor(275.9076, device='cuda:0')
epoch: 139 test_true_pfm: 2456.665479974677 sim_pfm: 59.27425934613954
episode: 556 training return: tensor(198.0065, device='cuda:0')
episode: 557 training return: tensor(-76.4769, device='cuda:0')
episode: 558 training return: tensor(-357.2911, device='cuda:0')
episode: 559 training return: tensor(244.1420, device='cuda:0')
epoch: 140 test_true_pfm: 2600.0406658026386 sim_pfm: 43.455151447483026
episode: 560 training return: tensor(-358.5205, device='cuda:0')
episode: 561 training return: tensor(-79.4758, device='cuda:0')
episode: 562 training return: tensor(-261.9575, device='cuda:0')
episode: 563 training return: tensor(-379.5038, device='cuda:0')
epoch: 141 test_true_pfm: 2512.923270454583 sim_pfm: 118.35445738064784
episode: 564 training return: tensor(262.1499, device='cuda:0')
episode: 565 training return: tensor(-406.4293, device='cuda:0')
episode: 566 training return: tensor(162.5398, device='cuda:0')
episode: 567 training return: tensor(-228.1602, device='cuda:0')
epoch: 142 test_true_pfm: 2905.5733830016325 sim_pfm: 39.43448965241745
episode: 568 training return: tensor(-334.0981, device='cuda:0')
episode: 569 training return: tensor(255.5147, device='cuda:0')
episode: 570 training return: tensor(-369.9734, device='cuda:0')
episode: 571 training return: tensor(-366.4661, device='cuda:0')
epoch: 143 test_true_pfm: 2936.9403344655498 sim_pfm: 150.20198093005456
episode: 572 training return: tensor(109.0753, device='cuda:0')
episode: 573 training return: tensor(-22.5895, device='cuda:0')
episode: 574 training return: tensor(241.9875, device='cuda:0')
episode: 575 training return: tensor(-244.4491, device='cuda:0')
epoch: 144 test_true_pfm: 3034.246538719046 sim_pfm: -14.214524289709516
episode: 576 training return: tensor(279.6716, device='cuda:0')
episode: 577 training return: tensor(299.8535, device='cuda:0')
episode: 578 training return: tensor(-394.8875, device='cuda:0')
episode: 579 training return: tensor(20.1750, device='cuda:0')
epoch: 145 test_true_pfm: 3049.016690698314 sim_pfm: 115.22991463161695
episode: 580 training return: tensor(-59.8605, device='cuda:0')
episode: 581 training return: tensor(-123.9045, device='cuda:0')
episode: 582 training return: tensor(-161.3167, device='cuda:0')
episode: 583 training return: tensor(-15.9264, device='cuda:0')
epoch: 146 test_true_pfm: 2581.699370472464 sim_pfm: 58.63045503861698
episode: 584 training return: tensor(-333.9973, device='cuda:0')
episode: 585 training return: tensor(-201.8111, device='cuda:0')
episode: 586 training return: tensor(-106.2118, device='cuda:0')
episode: 587 training return: tensor(-267.8849, device='cuda:0')
epoch: 147 test_true_pfm: 2473.4757761393707 sim_pfm: 66.02055995756139
episode: 588 training return: tensor(122.9050, device='cuda:0')
episode: 589 training return: tensor(-378.4768, device='cuda:0')
episode: 590 training return: tensor(-113.9952, device='cuda:0')
episode: 591 training return: tensor(-170.1342, device='cuda:0')
epoch: 148 test_true_pfm: 2752.705277307079 sim_pfm: 95.71739998065944
episode: 592 training return: tensor(255.8859, device='cuda:0')
episode: 593 training return: tensor(39.7450, device='cuda:0')
episode: 594 training return: tensor(-268.9979, device='cuda:0')
episode: 595 training return: tensor(96.9457, device='cuda:0')
epoch: 149 test_true_pfm: 2855.819868128862 sim_pfm: 82.05207321192331
episode: 596 training return: tensor(319.6174, device='cuda:0')
episode: 597 training return: tensor(-311.2486, device='cuda:0')
episode: 598 training return: tensor(-302.1095, device='cuda:0')
episode: 599 training return: tensor(-383.7897, device='cuda:0')
epoch: 150 test_true_pfm: 3028.01320577062 sim_pfm: 59.97830330400029
