['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '1', '--data', '10000']
epoch: 0 training_loss 0.24015189439058304 test_loss: 0.19227356910705568
epoch: 1 training_loss 0.20330643333494663 test_loss: 0.19213831424713135
epoch: 2 training_loss 0.19887215107679368 test_loss: 0.20608174800872803
epoch: 3 training_loss 0.19428315542638303 test_loss: 0.17958931922912597
epoch: 4 training_loss 0.18564304396510123 test_loss: 0.20529437065124512
epoch: 5 training_loss 0.18316402174532415 test_loss: 0.19090430736541747
epoch: 6 training_loss 0.18483418695628642 test_loss: 0.20075137615203859
epoch: 7 training_loss 0.18570543885231017 test_loss: 0.18947465419769288
epoch: 8 training_loss 0.17643153645098208 test_loss: 0.18366681337356566
epoch: 9 training_loss 0.18803514294326307 test_loss: 0.18052135705947875
epoch: 10 training_loss 0.1770624155551195 test_loss: 0.19064009189605713
epoch: 11 training_loss 0.18846443191170692 test_loss: 0.19437868595123292
epoch: 12 training_loss 0.179702702537179 test_loss: 0.19015402793884278
epoch: 13 training_loss 0.18480777099728585 test_loss: 0.18722364902496338
epoch: 14 training_loss 0.17436768300831318 test_loss: 0.17691022157669067
epoch: 15 training_loss 0.1834923364967108 test_loss: 0.1907646656036377
epoch: 16 training_loss 0.18177844472229482 test_loss: 0.20368618965148927
epoch: 17 training_loss 0.18236726202070713 test_loss: 0.18242826461791992
epoch: 18 training_loss 0.1827171529084444 test_loss: 0.1873279929161072
epoch: 19 training_loss 0.17352203153073786 test_loss: 0.1996143341064453
epoch: 20 training_loss 0.1845080018788576 test_loss: 0.17515037059783936
epoch: 21 training_loss 0.17747538533061744 test_loss: 0.17981737852096558
epoch: 22 training_loss 0.18063301663845777 test_loss: 0.17376151084899902
epoch: 23 training_loss 0.17925707779824734 test_loss: 0.19199317693710327
epoch: 24 training_loss 0.17262212209403516 test_loss: 0.1805071473121643
epoch: 25 training_loss 0.17362018495798112 test_loss: 0.1863610029220581
epoch: 26 training_loss 0.17210938423871994 test_loss: 0.18901827335357665
epoch: 27 training_loss 0.17589094042778014 test_loss: 0.16643401384353637
epoch: 28 training_loss 0.17897032998502255 test_loss: 0.18759782314300538
epoch: 29 training_loss 0.17897700905799865 test_loss: 0.17967303991317748
epoch: 30 training_loss 0.17413852319121362 test_loss: 0.17184717655181886
epoch: 31 training_loss 0.17866823554039002 test_loss: 0.18446176052093505
epoch: 32 training_loss 0.17786481410264968 test_loss: 0.18177132606506347
epoch: 33 training_loss 0.17654381766915322 test_loss: 0.17521549463272096
epoch: 34 training_loss 0.17850609920918942 test_loss: 0.18899205923080445
epoch: 35 training_loss 0.1833191467821598 test_loss: 0.1844615340232849
epoch: 36 training_loss 0.17517335519194602 test_loss: 0.19851901531219482
epoch: 37 training_loss 0.17390650004148483 test_loss: 0.19269448518753052
epoch: 38 training_loss 0.17953828684985637 test_loss: 0.17814295291900634
epoch: 39 training_loss 0.1766317694634199 test_loss: 0.18029356002807617
epoch: 40 training_loss 0.1779890099912882 test_loss: 0.18395255804061889
epoch: 41 training_loss 0.17848421670496464 test_loss: 0.18269187211990356
epoch: 42 training_loss 0.17942363627254962 test_loss: 0.18021047115325928
epoch: 43 training_loss 0.16907585911452772 test_loss: 0.18617091178894044
epoch: 44 training_loss 0.17658937931060792 test_loss: 0.19104673862457275
epoch: 45 training_loss 0.1700788262486458 test_loss: 0.18267771005630493
epoch: 46 training_loss 0.17405642688274384 test_loss: 0.18366072177886963
epoch: 47 training_loss 0.17482016824185848 test_loss: 0.18262088298797607
epoch: 48 training_loss 0.1708800369501114 test_loss: 0.18236792087554932
epoch: 49 training_loss 0.185232882425189 test_loss: 0.17639635801315307
epoch: 50 training_loss 0.17789694972336292 test_loss: 0.18428189754486085
epoch: 51 training_loss 0.17716672383248805 test_loss: 0.19371304512023926
epoch: 52 training_loss 0.17151069723069667 test_loss: 0.19056622982025145
epoch: 53 training_loss 0.17826499104499816 test_loss: 0.18968429565429687
epoch: 54 training_loss 0.1838136538863182 test_loss: 0.16975338459014894
epoch: 55 training_loss 0.17390329115092754 test_loss: 0.1901400327682495
epoch: 56 training_loss 0.1687153599411249 test_loss: 0.1926484227180481
epoch: 57 training_loss 0.17121850222349166 test_loss: 0.1803281784057617
epoch: 58 training_loss 0.17659272588789462 test_loss: 0.17855539321899414
epoch: 59 training_loss 0.17107752293348313 test_loss: 0.17558540105819703
epoch: 60 training_loss 0.17311061408370734 test_loss: 0.17352604866027832
epoch: 61 training_loss 0.18015965085476637 test_loss: 0.1848215103149414
epoch: 62 training_loss 0.1703471839427948 test_loss: 0.18718734979629517
epoch: 63 training_loss 0.16917416781187058 test_loss: 0.19158382415771485
epoch: 64 training_loss 0.178036777600646 test_loss: 0.17202693223953247
epoch: 65 training_loss 0.16924536034464835 test_loss: 0.17729781866073607
epoch: 66 training_loss 0.17067680165171623 test_loss: 0.17248973846435547
epoch: 67 training_loss 0.1818913718312979 test_loss: 0.18415093421936035
epoch: 68 training_loss 0.1752741526812315 test_loss: 0.18345975875854492
epoch: 69 training_loss 0.17122724249958993 test_loss: 0.1773219347000122
epoch: 70 training_loss 0.17113921403884888 test_loss: 0.18151155710220337
epoch: 71 training_loss 0.18077190406620502 test_loss: 0.1722806930541992
epoch: 72 training_loss 0.16663603067398072 test_loss: 0.18730155229568482
epoch: 73 training_loss 0.17643853358924388 test_loss: 0.18119217157363893
epoch: 74 training_loss 0.17641748383641243 test_loss: 0.18088749647140503
epoch: 75 training_loss 0.16895196326076983 test_loss: 0.1824541926383972
epoch: 76 training_loss 0.17520695455372334 test_loss: 0.1749057650566101
epoch: 77 training_loss 0.1749329373985529 test_loss: 0.18492614030838012
epoch: 78 training_loss 0.16874567061662674 test_loss: 0.19139375686645507
epoch: 79 training_loss 0.1719950971007347 test_loss: 0.17187795639038086
epoch: 80 training_loss 0.16783332966268064 test_loss: 0.18942395448684693
epoch: 81 training_loss 0.1806784376502037 test_loss: 0.1816360116004944
epoch: 82 training_loss 0.1771789776533842 test_loss: 0.17795897722244264
epoch: 83 training_loss 0.17319148927927017 test_loss: 0.18286205530166627
epoch: 84 training_loss 0.17673682242631913 test_loss: 0.18595858812332153
epoch: 85 training_loss 0.17429750047624112 test_loss: 0.19215885400772095
epoch: 86 training_loss 0.17676999263465404 test_loss: 0.19339675903320314
epoch: 87 training_loss 0.17136511869728566 test_loss: 0.18653019666671752
epoch: 88 training_loss 0.17334539607167243 test_loss: 0.19237474203109742
epoch: 89 training_loss 0.16846367791295053 test_loss: 0.1761294722557068
epoch: 90 training_loss 0.16907794829457998 test_loss: 0.17891643047332764
epoch: 91 training_loss 0.17488012790679933 test_loss: 0.17607241868972778
epoch: 92 training_loss 0.17374160766601562 test_loss: 0.17499383687973022
epoch: 93 training_loss 0.1759621788561344 test_loss: 0.1800239086151123
epoch: 94 training_loss 0.1700855375826359 test_loss: 0.18572474718093873
epoch: 95 training_loss 0.17059395492076873 test_loss: 0.17686463594436647
epoch: 96 training_loss 0.16674165569245816 test_loss: 0.18954832553863527
epoch: 97 training_loss 0.17657449401915074 test_loss: 0.18665355443954468
epoch: 98 training_loss 0.16884104914963247 test_loss: 0.17005144357681273
epoch: 99 training_loss 0.16252825394272805 test_loss: 0.18229326009750366
epoch: 100 training_loss 0.16765607960522175 test_loss: 0.191147518157959
epoch: 101 training_loss 0.16770989894866944 test_loss: 0.17857544422149657
epoch: 102 training_loss 0.17102980948984622 test_loss: 0.17821207046508789
epoch: 103 training_loss 0.1684652814269066 test_loss: 0.17350232601165771
epoch: 104 training_loss 0.16533621422946454 test_loss: 0.18577200174331665
epoch: 105 training_loss 0.17383186854422092 test_loss: 0.19038621187210084
epoch: 106 training_loss 0.16634716488420964 test_loss: 0.20266547203063964
epoch: 107 training_loss 0.17776912853121757 test_loss: 0.1868954300880432
epoch: 108 training_loss 0.168682811409235 test_loss: 0.17546221017837524
epoch: 109 training_loss 0.16286435306072236 test_loss: 0.19138107299804688
epoch: 110 training_loss 0.16780065789818763 test_loss: 0.18661229610443114
epoch: 111 training_loss 0.1643431568145752 test_loss: 0.19100608825683593
epoch: 112 training_loss 0.16772094272077084 test_loss: 0.19011837244033813
epoch: 113 training_loss 0.16900878183543683 test_loss: 0.18107503652572632
epoch: 114 training_loss 0.15231525227427484 test_loss: 0.1727290153503418
epoch: 115 training_loss 0.17224491402506828 test_loss: 0.18105934858322142
epoch: 116 training_loss 0.16435152374207973 test_loss: 0.18545328378677367
epoch: 117 training_loss 0.16136976499110461 test_loss: 0.18646935224533082
epoch: 118 training_loss 0.165515151694417 test_loss: 0.18004450798034669
epoch: 119 training_loss 0.16400652982294558 test_loss: 0.19340887069702148
epoch: 120 training_loss 0.17052892059087754 test_loss: 0.18266485929489135
epoch: 121 training_loss 0.17245693512260915 test_loss: 0.19057004451751708
epoch: 122 training_loss 0.1624568072333932 test_loss: 0.1887418508529663
epoch: 123 training_loss 0.16945223845541477 test_loss: 0.19655752182006836
epoch: 124 training_loss 0.16755449533462524 test_loss: 0.19094942808151244
epoch: 125 training_loss 0.1657925171405077 test_loss: 0.18602292537689208
epoch: 126 training_loss 0.16395341709256173 test_loss: 0.17977871894836425
epoch: 127 training_loss 0.16665815845131873 test_loss: 0.18122419118881225
epoch: 128 training_loss 0.1701677019894123 test_loss: 0.18466438055038453
epoch: 129 training_loss 0.16543326959013938 test_loss: 0.18966660499572754
epoch: 130 training_loss 0.16878975570201873 test_loss: 0.20751194953918456
epoch: 131 training_loss 0.16112349547445773 test_loss: 0.18687043190002442
epoch: 132 training_loss 0.16830677509307862 test_loss: 0.17488518953323365
epoch: 133 training_loss 0.16399567514657976 test_loss: 0.17320080995559692
epoch: 134 training_loss 0.16629001773893834 test_loss: 0.18174526691436768
epoch: 135 training_loss 0.1701665423810482 test_loss: 0.1997525215148926
epoch: 136 training_loss 0.16280828177928924 test_loss: 0.2020256996154785
epoch: 137 training_loss 0.1634246800094843 test_loss: 0.18325897455215454
epoch: 138 training_loss 0.16747918747365476 test_loss: 0.18271089792251588
epoch: 139 training_loss 0.1677961377054453 test_loss: 0.19638642072677612
epoch: 140 training_loss 0.1679967463761568 test_loss: 0.17691416740417482
epoch: 141 training_loss 0.16203724838793276 test_loss: 0.18491313457489014
epoch: 142 training_loss 0.17167139269411563 test_loss: 0.1805220365524292
epoch: 143 training_loss 0.17243799299001694 test_loss: 0.1875823736190796
epoch: 144 training_loss 0.1654070533812046 test_loss: 0.16948463916778564
epoch: 145 training_loss 0.16531757421791554 test_loss: 0.18330886363983154
epoch: 146 training_loss 0.16974038384854795 test_loss: 0.17574328184127808
epoch: 147 training_loss 0.16786399699747562 test_loss: 0.18086178302764894
epoch: 148 training_loss 0.1625178388878703 test_loss: 0.1865495562553406
epoch: 149 training_loss 0.16757943272590636 test_loss: 0.18373287916183473
epoch: 0 training_loss 8.310594449043274 test_loss: 4.675133895874024
epoch: 1 training_loss 3.70901371717453 test_loss: 3.0153057098388674
epoch: 2 training_loss 2.579388929605484 test_loss: 2.1825927734375
epoch: 3 training_loss 1.9971877062320709 test_loss: 1.781918716430664
epoch: 4 training_loss 1.6933417963981627 test_loss: 1.5919454574584961
epoch: 5 training_loss 1.526150358915329 test_loss: 1.5185112953186035
epoch: 6 training_loss 1.457188230752945 test_loss: 1.3703933715820313
epoch: 7 training_loss 1.3646019351482392 test_loss: 1.3249821662902832
epoch: 8 training_loss 1.29052703499794 test_loss: 1.2430249214172364
epoch: 9 training_loss 1.227860417366028 test_loss: 1.196673583984375
epoch: 10 training_loss 1.1757624047994613 test_loss: 1.1460315704345703
epoch: 11 training_loss 1.1439498168230058 test_loss: 1.1289878845214845
epoch: 12 training_loss 1.1061074036359786 test_loss: 1.0985663414001465
epoch: 13 training_loss 1.0752932542562486 test_loss: 1.0533863067626954
epoch: 14 training_loss 1.0244555389881134 test_loss: 1.0197147369384765
epoch: 15 training_loss 0.9925650411844253 test_loss: 0.9939330101013184
epoch: 16 training_loss 0.9801699596643448 test_loss: 0.9741533279418946
epoch: 17 training_loss 0.9453945791721344 test_loss: 0.971377182006836
epoch: 18 training_loss 0.9439239299297333 test_loss: 0.9311419486999511
epoch: 19 training_loss 0.9118399560451508 test_loss: 0.9467552185058594
epoch: 20 training_loss 0.9041150242090226 test_loss: 0.9552187919616699
epoch: 21 training_loss 0.8793488943576813 test_loss: 0.8742938041687012
epoch: 22 training_loss 0.8669474983215332 test_loss: 0.8503396034240722
epoch: 23 training_loss 0.8484371376037597 test_loss: 0.8334344863891602
epoch: 24 training_loss 0.8254503577947616 test_loss: 0.8216222763061524
epoch: 25 training_loss 0.8185404133796692 test_loss: 0.8267199516296386
epoch: 26 training_loss 0.8124678438901901 test_loss: 0.792652702331543
epoch: 27 training_loss 0.7971784913539887 test_loss: 0.7999771118164063
epoch: 28 training_loss 0.7964642632007599 test_loss: 0.8004376411437988
epoch: 29 training_loss 0.7720033174753189 test_loss: 0.7846662998199463
epoch: 30 training_loss 0.7763120710849762 test_loss: 0.7807312488555909
epoch: 31 training_loss 0.7670002436637878 test_loss: 0.7913204669952393
epoch: 32 training_loss 0.7572433429956437 test_loss: 0.7414558887481689
epoch: 33 training_loss 0.7499409478902817 test_loss: 0.7635478973388672
epoch: 34 training_loss 0.7447005993127823 test_loss: 0.7511173248291015
epoch: 35 training_loss 0.7160593628883362 test_loss: 0.7049868106842041
epoch: 36 training_loss 0.7204702460765838 test_loss: 0.718084716796875
epoch: 37 training_loss 0.7197630745172501 test_loss: 0.7103632926940918
epoch: 38 training_loss 0.7037730890512467 test_loss: 0.7215816497802734
epoch: 39 training_loss 0.700951236486435 test_loss: 0.7173966407775879
epoch: 40 training_loss 0.6984916174411774 test_loss: 0.6991336345672607
epoch: 41 training_loss 0.6918503314256668 test_loss: 0.6965702533721924
epoch: 42 training_loss 0.6749623972177505 test_loss: 0.7015354633331299
epoch: 43 training_loss 0.6782652115821839 test_loss: 0.690205717086792
epoch: 44 training_loss 0.6958947962522507 test_loss: 0.6695031642913818
epoch: 45 training_loss 0.667528510093689 test_loss: 0.6566685199737549
epoch: 46 training_loss 0.6735356086492539 test_loss: 0.6622540473937988
epoch: 47 training_loss 0.6565757882595062 test_loss: 0.6525153636932373
epoch: 48 training_loss 0.655935006737709 test_loss: 0.6703451156616211
epoch: 49 training_loss 0.6536081820726395 test_loss: 0.6562833786010742
epoch: 50 training_loss 0.6559960103034973 test_loss: 0.6494837760925293
epoch: 51 training_loss 0.6509926432371139 test_loss: 0.6550835132598877
epoch: 52 training_loss 0.6379256963729858 test_loss: 0.6670524120330811
epoch: 53 training_loss 0.6397558510303497 test_loss: 0.6532624244689942
epoch: 54 training_loss 0.6366220951080322 test_loss: 0.6587321758270264
epoch: 55 training_loss 0.657135415673256 test_loss: 0.6364687442779541
epoch: 56 training_loss 0.6281879043579102 test_loss: 0.6157540321350098
epoch: 57 training_loss 0.6277886128425598 test_loss: 0.6262555122375488
epoch: 58 training_loss 0.6216584020853042 test_loss: 0.6238152503967285
epoch: 59 training_loss 0.6153670233488083 test_loss: 0.6402204513549805
epoch: 60 training_loss 0.6231049764156341 test_loss: 0.6198878288269043
epoch: 61 training_loss 0.6098560661077499 test_loss: 0.6063000679016113
epoch: 62 training_loss 0.6129141965508461 test_loss: 0.6034491062164307
epoch: 63 training_loss 0.6210050517320633 test_loss: 0.6056385993957519
epoch: 64 training_loss 0.6031587848067284 test_loss: 0.6056017398834228
epoch: 65 training_loss 0.6041215318441391 test_loss: 0.6053431510925293
epoch: 66 training_loss 0.6021835750341415 test_loss: 0.6589498519897461
epoch: 67 training_loss 0.6133887445926667 test_loss: 0.6040884494781494
epoch: 68 training_loss 0.6037513512372971 test_loss: 0.6240799427032471
epoch: 69 training_loss 0.5997463911771774 test_loss: 0.5936507225036621
epoch: 70 training_loss 0.5849628281593323 test_loss: 0.5958950042724609
epoch: 71 training_loss 0.576293323636055 test_loss: 0.6015039443969726
epoch: 72 training_loss 0.581944335103035 test_loss: 0.5774662494659424
epoch: 73 training_loss 0.5871778666973114 test_loss: 0.6051250457763672
epoch: 74 training_loss 0.5807118970155716 test_loss: 0.6013050556182862
epoch: 75 training_loss 0.5767678248882294 test_loss: 0.5676824569702148
epoch: 76 training_loss 0.5794509696960449 test_loss: 0.5824171543121338
epoch: 77 training_loss 0.5827555102109909 test_loss: 0.6115305900573731
epoch: 78 training_loss 0.5746288049221039 test_loss: 0.6017630577087403
epoch: 79 training_loss 0.56830262362957 test_loss: 0.5674585342407227
epoch: 80 training_loss 0.5764795595407486 test_loss: 0.5713064193725585
epoch: 81 training_loss 0.5654133692383766 test_loss: 0.5923675537109375
epoch: 82 training_loss 0.5730272740125656 test_loss: 0.5653872489929199
epoch: 83 training_loss 0.5667203521728515 test_loss: 0.5780234813690186
epoch: 84 training_loss 0.5709741908311844 test_loss: 0.5787904262542725
epoch: 85 training_loss 0.5656762862205506 test_loss: 0.5542638778686524
epoch: 86 training_loss 0.5542888388037681 test_loss: 0.5593355655670166
epoch: 87 training_loss 0.5702530160546303 test_loss: 0.58761568069458
epoch: 88 training_loss 0.55621886074543 test_loss: 0.5562516689300537
epoch: 89 training_loss 0.5556132701039315 test_loss: 0.5575961112976074
epoch: 90 training_loss 0.565861132144928 test_loss: 0.5645686626434326
epoch: 91 training_loss 0.5534405621886254 test_loss: 0.5629218101501465
epoch: 92 training_loss 0.5531693881750107 test_loss: 0.5569732189178467
epoch: 93 training_loss 0.5519005039334297 test_loss: 0.5440866470336914
epoch: 94 training_loss 0.5392454621195794 test_loss: 0.5599137783050537
epoch: 95 training_loss 0.552662828862667 test_loss: 0.5401578903198242
epoch: 96 training_loss 0.5479043984413147 test_loss: 0.552355146408081
epoch: 97 training_loss 0.5457782557606697 test_loss: 0.5434120655059814
epoch: 98 training_loss 0.5353982642292976 test_loss: 0.5518470287322998
epoch: 99 training_loss 0.5382923007011413 test_loss: 0.5418723583221435
epoch: 100 training_loss 0.5402646198868751 test_loss: 0.5714582920074462
epoch: 101 training_loss 0.5335634341835975 test_loss: 0.5503180503845215
epoch: 102 training_loss 0.5302205699682235 test_loss: 0.5386153221130371
epoch: 103 training_loss 0.5416951808333397 test_loss: 0.5403181076049804
epoch: 104 training_loss 0.5362597835063935 test_loss: 0.5470376014709473
epoch: 105 training_loss 0.5301393514871597 test_loss: 0.5540757179260254
epoch: 106 training_loss 0.5391583099961281 test_loss: 0.5729817867279052
epoch: 107 training_loss 0.5406492477655411 test_loss: 0.5515549659729004
epoch: 108 training_loss 0.53348637342453 test_loss: 0.5827137947082519
epoch: 109 training_loss 0.536505110859871 test_loss: 0.5256202220916748
epoch: 110 training_loss 0.528199335038662 test_loss: 0.5739600181579589
epoch: 111 training_loss 0.5343157869577407 test_loss: 0.5304963111877441
epoch: 112 training_loss 0.5319407749176025 test_loss: 0.5836972713470459
epoch: 113 training_loss 0.5337389194965363 test_loss: 0.5422947883605957
epoch: 114 training_loss 0.532823168039322 test_loss: 0.5211202144622803
epoch: 115 training_loss 0.5221999901533126 test_loss: 0.5287856101989746
epoch: 116 training_loss 0.5178510719537734 test_loss: 0.5173366069793701
epoch: 117 training_loss 0.5151928639411927 test_loss: 0.5403340816497803
epoch: 118 training_loss 0.5216373160481453 test_loss: 0.5397253513336182
epoch: 119 training_loss 0.5237163653969765 test_loss: 0.5299445629119873
epoch: 120 training_loss 0.5235430800914764 test_loss: 0.5196902751922607
epoch: 121 training_loss 0.5229519975185394 test_loss: 0.544599199295044
epoch: 122 training_loss 0.528758747279644 test_loss: 0.5378671646118164
epoch: 123 training_loss 0.5264556863904 test_loss: 0.5655328273773194
epoch: 124 training_loss 0.5204770344495774 test_loss: 0.5266600131988526
epoch: 125 training_loss 0.5158162549138069 test_loss: 0.5451250076293945
epoch: 126 training_loss 0.5193429452180862 test_loss: 0.5263919353485107
epoch: 127 training_loss 0.5050092822313309 test_loss: 0.5061285972595215
epoch: 128 training_loss 0.5087105092406273 test_loss: 0.5364576816558838
epoch: 129 training_loss 0.5134954300522804 test_loss: 0.518863296508789
epoch: 130 training_loss 0.514815809726715 test_loss: 0.5321389198303222
epoch: 131 training_loss 0.5056455466151237 test_loss: 0.5127663135528564
epoch: 132 training_loss 0.5059879153966904 test_loss: 0.508933162689209
epoch: 133 training_loss 0.5096112722158432 test_loss: 0.5094892024993897
epoch: 134 training_loss 0.513648234307766 test_loss: 0.5251261234283447
epoch: 135 training_loss 0.5084343275427818 test_loss: 0.5151673793792725
epoch: 136 training_loss 0.5017068272829056 test_loss: 0.5145708560943604
epoch: 137 training_loss 0.5042378106713294 test_loss: 0.5056002140045166
epoch: 138 training_loss 0.5048972851037979 test_loss: 0.5465147972106934
epoch: 139 training_loss 0.5044264551997185 test_loss: 0.506540584564209
epoch: 140 training_loss 0.4995227339863777 test_loss: 0.4912742614746094
epoch: 141 training_loss 0.49753880679607393 test_loss: 0.5141269207000733
epoch: 142 training_loss 0.5035487186908721 test_loss: 0.5194740772247315
epoch: 143 training_loss 0.507460643351078 test_loss: 0.4966104030609131
epoch: 144 training_loss 0.5031324711441993 test_loss: 0.5171294689178467
epoch: 145 training_loss 0.5052934268116951 test_loss: 0.5114728450775147
epoch: 146 training_loss 0.5065884667634964 test_loss: 0.5102514743804931
epoch: 147 training_loss 0.512885517179966 test_loss: 0.515331506729126
epoch: 148 training_loss 0.5037437707185746 test_loss: 0.49550790786743165
epoch: 149 training_loss 0.5020043155550957 test_loss: 0.4997703075408936
1458.40297182815
episode: 0 training return: tensor(-384.3788, device='cuda:0')
episode: 1 training return: tensor(-127.4717, device='cuda:0')
episode: 2 training return: tensor(294.9377, device='cuda:0')
episode: 3 training return: tensor(-27.6702, device='cuda:0')
epoch: 1 test_true_pfm: 1616.96146678734 sim_pfm: -348.201370428423
episode: 4 training return: tensor(-314.8482, device='cuda:0')
episode: 5 training return: tensor(-407.0763, device='cuda:0')
episode: 6 training return: tensor(-302.6494, device='cuda:0')
episode: 7 training return: tensor(160.0462, device='cuda:0')
epoch: 2 test_true_pfm: 1550.4713385892937 sim_pfm: -394.48343433237943
episode: 8 training return: tensor(-339.2769, device='cuda:0')
episode: 9 training return: tensor(-180.2587, device='cuda:0')
episode: 10 training return: tensor(-275.5638, device='cuda:0')
episode: 11 training return: tensor(90.8049, device='cuda:0')
epoch: 3 test_true_pfm: 1287.9674849082248 sim_pfm: -411.7799924541614
episode: 12 training return: tensor(-104.6770, device='cuda:0')
episode: 13 training return: tensor(-353.4346, device='cuda:0')
episode: 14 training return: tensor(-4.7960, device='cuda:0')
episode: 15 training return: tensor(-443.3345, device='cuda:0')
epoch: 4 test_true_pfm: 1217.3528225223024 sim_pfm: -418.91668753280345
episode: 16 training return: tensor(-390.2252, device='cuda:0')
episode: 17 training return: tensor(-422.4998, device='cuda:0')
episode: 18 training return: tensor(-406.0901, device='cuda:0')
episode: 19 training return: tensor(-150.4819, device='cuda:0')
epoch: 5 test_true_pfm: 1199.9110943518288 sim_pfm: -435.1141910981581
episode: 20 training return: tensor(-363.0783, device='cuda:0')
episode: 21 training return: tensor(-404.3293, device='cuda:0')
episode: 22 training return: tensor(-380.3575, device='cuda:0')
episode: 23 training return: tensor(-340.8894, device='cuda:0')
epoch: 6 test_true_pfm: 1298.4579857686606 sim_pfm: -418.4686072262314
episode: 24 training return: tensor(-406.0207, device='cuda:0')
episode: 25 training return: tensor(-154.3039, device='cuda:0')
episode: 26 training return: tensor(-332.9009, device='cuda:0')
episode: 27 training return: tensor(-269.3366, device='cuda:0')
epoch: 7 test_true_pfm: 1275.3614590796224 sim_pfm: -413.57721031146747
episode: 28 training return: tensor(-161.5452, device='cuda:0')
episode: 29 training return: tensor(187.5116, device='cuda:0')
episode: 30 training return: tensor(-120.9010, device='cuda:0')
episode: 31 training return: tensor(241.4915, device='cuda:0')
epoch: 8 test_true_pfm: 1327.2940834524686 sim_pfm: -397.0484013464302
episode: 32 training return: tensor(-255.5252, device='cuda:0')
episode: 33 training return: tensor(-347.6109, device='cuda:0')
episode: 34 training return: tensor(-421.0191, device='cuda:0')
episode: 35 training return: tensor(-227.4575, device='cuda:0')
epoch: 9 test_true_pfm: 1315.296475716981 sim_pfm: -410.0891380602843
episode: 36 training return: tensor(-254.9071, device='cuda:0')
episode: 37 training return: tensor(-134.1162, device='cuda:0')
episode: 38 training return: tensor(-363.8655, device='cuda:0')
episode: 39 training return: tensor(-293.9081, device='cuda:0')
epoch: 10 test_true_pfm: 1333.432301780366 sim_pfm: -364.4888023820822
episode: 40 training return: tensor(-412.6613, device='cuda:0')
episode: 41 training return: tensor(-143.9720, device='cuda:0')
episode: 42 training return: tensor(-402.0493, device='cuda:0')
episode: 43 training return: tensor(-321.8181, device='cuda:0')
epoch: 11 test_true_pfm: 1297.891979184876 sim_pfm: -409.64611399369704
episode: 44 training return: tensor(-88.1768, device='cuda:0')
episode: 45 training return: tensor(75.8099, device='cuda:0')
episode: 46 training return: tensor(-374.3085, device='cuda:0')
episode: 47 training return: tensor(-178.3116, device='cuda:0')
epoch: 12 test_true_pfm: 1403.6197726783246 sim_pfm: -380.69666181784123
episode: 48 training return: tensor(-250.4394, device='cuda:0')
episode: 49 training return: tensor(-54.2271, device='cuda:0')
episode: 50 training return: tensor(-396.0662, device='cuda:0')
episode: 51 training return: tensor(-292.1252, device='cuda:0')
epoch: 13 test_true_pfm: 1413.9019393167412 sim_pfm: -362.70259569190483
episode: 52 training return: tensor(-417.6755, device='cuda:0')
episode: 53 training return: tensor(-185.5123, device='cuda:0')
episode: 54 training return: tensor(-345.6879, device='cuda:0')
episode: 55 training return: tensor(-296.4350, device='cuda:0')
epoch: 14 test_true_pfm: 1489.3761734805942 sim_pfm: -371.9387042670763
episode: 56 training return: tensor(-177.8240, device='cuda:0')
episode: 57 training return: tensor(-188.9344, device='cuda:0')
episode: 58 training return: tensor(-281.4595, device='cuda:0')
episode: 59 training return: tensor(-403.0012, device='cuda:0')
epoch: 15 test_true_pfm: 1530.8814877043608 sim_pfm: -172.59613755371538
episode: 60 training return: tensor(233.7852, device='cuda:0')
episode: 61 training return: tensor(-350.0916, device='cuda:0')
episode: 62 training return: tensor(-347.6268, device='cuda:0')
episode: 63 training return: tensor(-410.4412, device='cuda:0')
epoch: 16 test_true_pfm: 2133.441197603514 sim_pfm: -278.2811669623188
episode: 64 training return: tensor(254.1768, device='cuda:0')
episode: 65 training return: tensor(-401.8654, device='cuda:0')
episode: 66 training return: tensor(178.7610, device='cuda:0')
episode: 67 training return: tensor(-348.3789, device='cuda:0')
epoch: 17 test_true_pfm: 2216.3310493967833 sim_pfm: -218.54216061113402
episode: 68 training return: tensor(-67.1529, device='cuda:0')
episode: 69 training return: tensor(-352.3409, device='cuda:0')
episode: 70 training return: tensor(-400.3358, device='cuda:0')
episode: 71 training return: tensor(-337.4135, device='cuda:0')
epoch: 18 test_true_pfm: 2333.105360928483 sim_pfm: -177.06425828603096
episode: 72 training return: tensor(-402.5184, device='cuda:0')
episode: 73 training return: tensor(-175.0428, device='cuda:0')
episode: 74 training return: tensor(-319.9520, device='cuda:0')
episode: 75 training return: tensor(-398.0414, device='cuda:0')
epoch: 19 test_true_pfm: 2478.385452955127 sim_pfm: -270.0939151782077
episode: 76 training return: tensor(-392.1461, device='cuda:0')
episode: 77 training return: tensor(73.1816, device='cuda:0')
episode: 78 training return: tensor(-395.6945, device='cuda:0')
episode: 79 training return: tensor(-373.7436, device='cuda:0')
epoch: 20 test_true_pfm: 2959.4023444605155 sim_pfm: -161.42734712014013
episode: 80 training return: tensor(-398.1782, device='cuda:0')
episode: 81 training return: tensor(-70.0113, device='cuda:0')
episode: 82 training return: tensor(-321.6056, device='cuda:0')
episode: 83 training return: tensor(-326.2613, device='cuda:0')
epoch: 21 test_true_pfm: 2406.359724091105 sim_pfm: 129.95104524867688
episode: 84 training return: tensor(-349.1477, device='cuda:0')
episode: 85 training return: tensor(-248.0209, device='cuda:0')
episode: 86 training return: tensor(-351.9592, device='cuda:0')
episode: 87 training return: tensor(-393.3004, device='cuda:0')
epoch: 22 test_true_pfm: 2124.053591397236 sim_pfm: -273.8062141812795
episode: 88 training return: tensor(-398.4885, device='cuda:0')
episode: 89 training return: tensor(-411.4071, device='cuda:0')
episode: 90 training return: tensor(-407.2880, device='cuda:0')
episode: 91 training return: tensor(-144.5871, device='cuda:0')
epoch: 23 test_true_pfm: 2349.7844019993977 sim_pfm: -182.56036651861118
episode: 92 training return: tensor(-397.8778, device='cuda:0')
episode: 93 training return: tensor(-400.6163, device='cuda:0')
episode: 94 training return: tensor(-270.2140, device='cuda:0')
episode: 95 training return: tensor(-345.2573, device='cuda:0')
epoch: 24 test_true_pfm: 1681.1818400627901 sim_pfm: -234.66856202066023
episode: 96 training return: tensor(-415.1545, device='cuda:0')
episode: 97 training return: tensor(151.7000, device='cuda:0')
episode: 98 training return: tensor(22.7391, device='cuda:0')
episode: 99 training return: tensor(-396.9285, device='cuda:0')
epoch: 25 test_true_pfm: 2582.2357246404185 sim_pfm: -51.96869319285421
episode: 100 training return: tensor(-403.9294, device='cuda:0')
episode: 101 training return: tensor(-322.9298, device='cuda:0')
episode: 102 training return: tensor(-410.8185, device='cuda:0')
episode: 103 training return: tensor(-362.0841, device='cuda:0')
epoch: 26 test_true_pfm: 2855.276721684227 sim_pfm: -138.3471024747705
episode: 104 training return: tensor(-311.0087, device='cuda:0')
episode: 105 training return: tensor(-413.9549, device='cuda:0')
episode: 106 training return: tensor(-394.5233, device='cuda:0')
episode: 107 training return: tensor(-404.1240, device='cuda:0')
epoch: 27 test_true_pfm: 2340.003224755837 sim_pfm: -203.63294643718595
episode: 108 training return: tensor(-273.8144, device='cuda:0')
episode: 109 training return: tensor(-353.0543, device='cuda:0')
episode: 110 training return: tensor(-353.5089, device='cuda:0')
episode: 111 training return: tensor(201.9421, device='cuda:0')
epoch: 28 test_true_pfm: 2063.302758602634 sim_pfm: -62.55872637751357
episode: 112 training return: tensor(-317.1700, device='cuda:0')
episode: 113 training return: tensor(-423.5346, device='cuda:0')
episode: 114 training return: tensor(-296.7425, device='cuda:0')
episode: 115 training return: tensor(-380.4757, device='cuda:0')
epoch: 29 test_true_pfm: 2518.128520225073 sim_pfm: 84.4701249563368
episode: 116 training return: tensor(-401.1747, device='cuda:0')
episode: 117 training return: tensor(-266.8783, device='cuda:0')
episode: 118 training return: tensor(-368.1056, device='cuda:0')
episode: 119 training return: tensor(23.4975, device='cuda:0')
epoch: 30 test_true_pfm: 2076.2709890298656 sim_pfm: -10.92494059460781
episode: 120 training return: tensor(-369.5707, device='cuda:0')
episode: 121 training return: tensor(-395.7911, device='cuda:0')
episode: 122 training return: tensor(-252.4797, device='cuda:0')
episode: 123 training return: tensor(-150.1935, device='cuda:0')
epoch: 31 test_true_pfm: 2621.988088773604 sim_pfm: -209.92264652857557
episode: 124 training return: tensor(-397.5136, device='cuda:0')
episode: 125 training return: tensor(-389.6549, device='cuda:0')
episode: 126 training return: tensor(-166.3292, device='cuda:0')
episode: 127 training return: tensor(-348.6778, device='cuda:0')
epoch: 32 test_true_pfm: 2257.3991674318195 sim_pfm: 63.157511695705274
episode: 128 training return: tensor(-394.3516, device='cuda:0')
episode: 129 training return: tensor(-14.7398, device='cuda:0')
episode: 130 training return: tensor(-342.7647, device='cuda:0')
episode: 131 training return: tensor(-155.5043, device='cuda:0')
epoch: 33 test_true_pfm: 2535.1536687989083 sim_pfm: -45.71182096543877
episode: 132 training return: tensor(-376.7999, device='cuda:0')
episode: 133 training return: tensor(-334.4965, device='cuda:0')
episode: 134 training return: tensor(-423.7197, device='cuda:0')
episode: 135 training return: tensor(254.1791, device='cuda:0')
epoch: 34 test_true_pfm: 3040.811507689313 sim_pfm: -86.88165385040338
episode: 136 training return: tensor(-403.9248, device='cuda:0')
episode: 137 training return: tensor(-371.6281, device='cuda:0')
episode: 138 training return: tensor(-278.1233, device='cuda:0')
episode: 139 training return: tensor(-401.1188, device='cuda:0')
epoch: 35 test_true_pfm: 2360.122039166304 sim_pfm: -233.1428606477566
episode: 140 training return: tensor(-356.8740, device='cuda:0')
episode: 141 training return: tensor(-314.5694, device='cuda:0')
episode: 142 training return: tensor(141.9363, device='cuda:0')
episode: 143 training return: tensor(-368.1002, device='cuda:0')
epoch: 36 test_true_pfm: 2614.7449566478317 sim_pfm: -137.59700656012865
episode: 144 training return: tensor(-413.7420, device='cuda:0')
episode: 145 training return: tensor(-151.3336, device='cuda:0')
episode: 146 training return: tensor(-325.1603, device='cuda:0')
episode: 147 training return: tensor(-409.3965, device='cuda:0')
epoch: 37 test_true_pfm: 2107.408221589958 sim_pfm: -215.45417951773075
episode: 148 training return: tensor(-207.9606, device='cuda:0')
episode: 149 training return: tensor(-288.2510, device='cuda:0')
episode: 150 training return: tensor(-392.0498, device='cuda:0')
episode: 151 training return: tensor(-402.0615, device='cuda:0')
epoch: 38 test_true_pfm: 1949.373923607669 sim_pfm: 27.775984677127173
episode: 152 training return: tensor(-387.4458, device='cuda:0')
episode: 153 training return: tensor(-428.5533, device='cuda:0')
episode: 154 training return: tensor(-401.8179, device='cuda:0')
episode: 155 training return: tensor(-394.8920, device='cuda:0')
epoch: 39 test_true_pfm: 2933.570433221324 sim_pfm: 77.72064986751259
episode: 156 training return: tensor(202.8341, device='cuda:0')
episode: 157 training return: tensor(-398.4129, device='cuda:0')
episode: 158 training return: tensor(-357.4228, device='cuda:0')
episode: 159 training return: tensor(-342.2903, device='cuda:0')
epoch: 40 test_true_pfm: 2330.131848571711 sim_pfm: 32.74790117193091
episode: 160 training return: tensor(-322.8489, device='cuda:0')
episode: 161 training return: tensor(-306.2324, device='cuda:0')
episode: 162 training return: tensor(-343.8658, device='cuda:0')
episode: 163 training return: tensor(-396.6944, device='cuda:0')
epoch: 41 test_true_pfm: 2086.9491969633727 sim_pfm: -56.80142152511204
episode: 164 training return: tensor(-163.5331, device='cuda:0')
episode: 165 training return: tensor(-55.0949, device='cuda:0')
episode: 166 training return: tensor(-399.3068, device='cuda:0')
episode: 167 training return: tensor(-345.0039, device='cuda:0')
epoch: 42 test_true_pfm: 2591.474195977277 sim_pfm: 135.04870307529927
episode: 168 training return: tensor(247.2862, device='cuda:0')
episode: 169 training return: tensor(-301.6787, device='cuda:0')
episode: 170 training return: tensor(-295.2924, device='cuda:0')
episode: 171 training return: tensor(-249.8259, device='cuda:0')
epoch: 43 test_true_pfm: 2601.243014228075 sim_pfm: -6.025981744479698
episode: 172 training return: tensor(-403.0005, device='cuda:0')
episode: 173 training return: tensor(-181.0955, device='cuda:0')
episode: 174 training return: tensor(-251.3484, device='cuda:0')
episode: 175 training return: tensor(-316.3342, device='cuda:0')
epoch: 44 test_true_pfm: 2663.1420835317026 sim_pfm: -64.8875941397079
episode: 176 training return: tensor(-399.8486, device='cuda:0')
episode: 177 training return: tensor(200.5965, device='cuda:0')
episode: 178 training return: tensor(-63.7400, device='cuda:0')
episode: 179 training return: tensor(-398.3141, device='cuda:0')
epoch: 45 test_true_pfm: 2593.6818063940377 sim_pfm: 75.1405067971403
episode: 180 training return: tensor(-326.5584, device='cuda:0')
episode: 181 training return: tensor(-305.4153, device='cuda:0')
episode: 182 training return: tensor(-221.5411, device='cuda:0')
episode: 183 training return: tensor(248.7555, device='cuda:0')
epoch: 46 test_true_pfm: 2622.0161136507872 sim_pfm: 68.51472316476672
episode: 184 training return: tensor(-395.0536, device='cuda:0')
episode: 185 training return: tensor(-223.4990, device='cuda:0')
episode: 186 training return: tensor(-79.3075, device='cuda:0')
episode: 187 training return: tensor(-405.4234, device='cuda:0')
epoch: 47 test_true_pfm: 2785.5208463214003 sim_pfm: 150.91358369243486
episode: 188 training return: tensor(-385.0543, device='cuda:0')
episode: 189 training return: tensor(-396.5034, device='cuda:0')
episode: 190 training return: tensor(-414.1997, device='cuda:0')
episode: 191 training return: tensor(-412.5603, device='cuda:0')
epoch: 48 test_true_pfm: 1996.549185050402 sim_pfm: -163.77124917297624
episode: 192 training return: tensor(84.6092, device='cuda:0')
episode: 193 training return: tensor(-71.4404, device='cuda:0')
episode: 194 training return: tensor(-341.4176, device='cuda:0')
episode: 195 training return: tensor(-369.0175, device='cuda:0')
epoch: 49 test_true_pfm: 2729.588109166801 sim_pfm: 79.8609624732441
episode: 196 training return: tensor(-403.0386, device='cuda:0')
episode: 197 training return: tensor(-277.0067, device='cuda:0')
episode: 198 training return: tensor(-397.8393, device='cuda:0')
episode: 199 training return: tensor(-398.6580, device='cuda:0')
epoch: 50 test_true_pfm: 3258.1806473022793 sim_pfm: -84.40226137427574
episode: 200 training return: tensor(-364.6393, device='cuda:0')
episode: 201 training return: tensor(-395.7665, device='cuda:0')
episode: 202 training return: tensor(-397.0339, device='cuda:0')
episode: 203 training return: tensor(285.9381, device='cuda:0')
epoch: 51 test_true_pfm: 2858.8712065947343 sim_pfm: 186.22125757320705
episode: 204 training return: tensor(-391.1817, device='cuda:0')
episode: 205 training return: tensor(-132.0235, device='cuda:0')
episode: 206 training return: tensor(-316.8882, device='cuda:0')
episode: 207 training return: tensor(-402.3246, device='cuda:0')
epoch: 52 test_true_pfm: 1934.624005691813 sim_pfm: -71.28911530656235
episode: 208 training return: tensor(-318.0554, device='cuda:0')
episode: 209 training return: tensor(-401.6323, device='cuda:0')
episode: 210 training return: tensor(-319.1070, device='cuda:0')
episode: 211 training return: tensor(206.3639, device='cuda:0')
epoch: 53 test_true_pfm: 2271.5365744323167 sim_pfm: 116.69191550599255
episode: 212 training return: tensor(-395.8075, device='cuda:0')
episode: 213 training return: tensor(-169.9240, device='cuda:0')
episode: 214 training return: tensor(-374.5528, device='cuda:0')
episode: 215 training return: tensor(-395.2029, device='cuda:0')
epoch: 54 test_true_pfm: 2877.68226202715 sim_pfm: 36.24724021942044
episode: 216 training return: tensor(-352.8966, device='cuda:0')
episode: 217 training return: tensor(-279.6353, device='cuda:0')
episode: 218 training return: tensor(-48.3984, device='cuda:0')
episode: 219 training return: tensor(-298.5691, device='cuda:0')
epoch: 55 test_true_pfm: 2989.553009442667 sim_pfm: -9.459016198205063
episode: 220 training return: tensor(-375.1706, device='cuda:0')
episode: 221 training return: tensor(-406.6648, device='cuda:0')
episode: 222 training return: tensor(-364.0832, device='cuda:0')
episode: 223 training return: tensor(-399.7288, device='cuda:0')
epoch: 56 test_true_pfm: 2334.903959900835 sim_pfm: 72.89809685536117
episode: 224 training return: tensor(-391.9386, device='cuda:0')
episode: 225 training return: tensor(-400.8856, device='cuda:0')
episode: 226 training return: tensor(-320.2173, device='cuda:0')
episode: 227 training return: tensor(-143.7579, device='cuda:0')
epoch: 57 test_true_pfm: 1944.9499905868404 sim_pfm: -130.25517009516867
episode: 228 training return: tensor(-178.6656, device='cuda:0')
episode: 229 training return: tensor(291.7807, device='cuda:0')
episode: 230 training return: tensor(281.4606, device='cuda:0')
episode: 231 training return: tensor(-329.0753, device='cuda:0')
epoch: 58 test_true_pfm: 2261.1300796824758 sim_pfm: -101.87220677826554
episode: 232 training return: tensor(-41.9292, device='cuda:0')
episode: 233 training return: tensor(-406.2141, device='cuda:0')
episode: 234 training return: tensor(-400.1307, device='cuda:0')
episode: 235 training return: tensor(-415.9479, device='cuda:0')
epoch: 59 test_true_pfm: 3180.4032777715242 sim_pfm: 15.103596799114408
episode: 236 training return: tensor(-314.8292, device='cuda:0')
episode: 237 training return: tensor(-398.7688, device='cuda:0')
episode: 238 training return: tensor(-399.5377, device='cuda:0')
episode: 239 training return: tensor(-395.9608, device='cuda:0')
epoch: 60 test_true_pfm: 2495.478534338202 sim_pfm: 96.03385523605782
episode: 240 training return: tensor(-399.0836, device='cuda:0')
episode: 241 training return: tensor(-392.4517, device='cuda:0')
episode: 242 training return: tensor(-402.2174, device='cuda:0')
episode: 243 training return: tensor(-301.5667, device='cuda:0')
epoch: 61 test_true_pfm: 2764.6367843892567 sim_pfm: 88.05736867293793
episode: 244 training return: tensor(-393.5965, device='cuda:0')
episode: 245 training return: tensor(-370.8458, device='cuda:0')
episode: 246 training return: tensor(-379.7091, device='cuda:0')
episode: 247 training return: tensor(-416.8761, device='cuda:0')
epoch: 62 test_true_pfm: 2437.8510647203534 sim_pfm: -12.477374961037034
episode: 248 training return: tensor(164.5749, device='cuda:0')
episode: 249 training return: tensor(-364.1001, device='cuda:0')
episode: 250 training return: tensor(-389.8507, device='cuda:0')
episode: 251 training return: tensor(-402.3272, device='cuda:0')
epoch: 63 test_true_pfm: 2140.8404138749606 sim_pfm: -52.913165282225236
episode: 252 training return: tensor(-409.0999, device='cuda:0')
episode: 253 training return: tensor(-392.6089, device='cuda:0')
episode: 254 training return: tensor(-401.7509, device='cuda:0')
episode: 255 training return: tensor(19.3666, device='cuda:0')
epoch: 64 test_true_pfm: 2128.8990656149704 sim_pfm: 20.377890446048696
episode: 256 training return: tensor(-352.8967, device='cuda:0')
episode: 257 training return: tensor(-403.4569, device='cuda:0')
episode: 258 training return: tensor(-403.3816, device='cuda:0')
episode: 259 training return: tensor(-344.5129, device='cuda:0')
epoch: 65 test_true_pfm: 3248.67509614284 sim_pfm: 199.95422198603046
episode: 260 training return: tensor(-328.8039, device='cuda:0')
episode: 261 training return: tensor(-79.4117, device='cuda:0')
episode: 262 training return: tensor(-404.5535, device='cuda:0')
episode: 263 training return: tensor(-387.9409, device='cuda:0')
epoch: 66 test_true_pfm: 2322.2247689303763 sim_pfm: -161.85036552647944
episode: 264 training return: tensor(-335.6831, device='cuda:0')
episode: 265 training return: tensor(-402.3867, device='cuda:0')
episode: 266 training return: tensor(-415.3167, device='cuda:0')
episode: 267 training return: tensor(-56.8990, device='cuda:0')
epoch: 67 test_true_pfm: 3229.260364173977 sim_pfm: 36.39671269156194
episode: 268 training return: tensor(-309.0406, device='cuda:0')
episode: 269 training return: tensor(-227.1431, device='cuda:0')
episode: 270 training return: tensor(-180.6801, device='cuda:0')
episode: 271 training return: tensor(-371.1940, device='cuda:0')
epoch: 68 test_true_pfm: 2878.488460893654 sim_pfm: 102.65112183607805
episode: 272 training return: tensor(-319.5247, device='cuda:0')
episode: 273 training return: tensor(-351.4229, device='cuda:0')
episode: 274 training return: tensor(-218.7557, device='cuda:0')
episode: 275 training return: tensor(0.4301, device='cuda:0')
epoch: 69 test_true_pfm: 2946.150055949222 sim_pfm: 82.01847665776343
episode: 276 training return: tensor(194.0902, device='cuda:0')
episode: 277 training return: tensor(-370.8027, device='cuda:0')
episode: 278 training return: tensor(-325.1637, device='cuda:0')
episode: 279 training return: tensor(-144.0591, device='cuda:0')
epoch: 70 test_true_pfm: 2659.8375472486578 sim_pfm: 33.001838075821674
episode: 280 training return: tensor(-386.6516, device='cuda:0')
episode: 281 training return: tensor(-395.6505, device='cuda:0')
episode: 282 training return: tensor(-343.4593, device='cuda:0')
episode: 283 training return: tensor(-189.4837, device='cuda:0')
epoch: 71 test_true_pfm: 2503.205504970798 sim_pfm: 75.48034730216993
episode: 284 training return: tensor(-366.4418, device='cuda:0')
episode: 285 training return: tensor(-84.7932, device='cuda:0')
episode: 286 training return: tensor(-366.0616, device='cuda:0')
episode: 287 training return: tensor(-296.3815, device='cuda:0')
epoch: 72 test_true_pfm: 2675.1889206962787 sim_pfm: 100.85839640534444
episode: 288 training return: tensor(-398.4015, device='cuda:0')
episode: 289 training return: tensor(-403.8547, device='cuda:0')
episode: 290 training return: tensor(-350.1322, device='cuda:0')
episode: 291 training return: tensor(-397.1496, device='cuda:0')
epoch: 73 test_true_pfm: 2903.2411152175805 sim_pfm: -21.36627545780114
episode: 292 training return: tensor(-343.5640, device='cuda:0')
episode: 293 training return: tensor(-329.3809, device='cuda:0')
episode: 294 training return: tensor(-398.3677, device='cuda:0')
episode: 295 training return: tensor(-409.3325, device='cuda:0')
epoch: 74 test_true_pfm: 2732.0771348223884 sim_pfm: 93.09148705405339
episode: 296 training return: tensor(-399.1746, device='cuda:0')
episode: 297 training return: tensor(-408.3457, device='cuda:0')
episode: 298 training return: tensor(-364.5166, device='cuda:0')
episode: 299 training return: tensor(-370.7845, device='cuda:0')
epoch: 75 test_true_pfm: 2313.248649571526 sim_pfm: -18.733609148679534
episode: 300 training return: tensor(-338.3765, device='cuda:0')
episode: 301 training return: tensor(-390.0899, device='cuda:0')
episode: 302 training return: tensor(-389.5466, device='cuda:0')
episode: 303 training return: tensor(-396.5542, device='cuda:0')
epoch: 76 test_true_pfm: 2484.0054616930443 sim_pfm: -4.0113568436936475
episode: 304 training return: tensor(-400.6011, device='cuda:0')
episode: 305 training return: tensor(-287.0434, device='cuda:0')
episode: 306 training return: tensor(-398.7270, device='cuda:0')
episode: 307 training return: tensor(-306.1463, device='cuda:0')
epoch: 77 test_true_pfm: 2318.4369815242717 sim_pfm: -141.41494334785966
episode: 308 training return: tensor(-400.0746, device='cuda:0')
episode: 309 training return: tensor(-375.9574, device='cuda:0')
episode: 310 training return: tensor(-358.0937, device='cuda:0')
episode: 311 training return: tensor(-343.6285, device='cuda:0')
epoch: 78 test_true_pfm: 2214.636216621179 sim_pfm: -87.14311719233713
episode: 312 training return: tensor(-327.3288, device='cuda:0')
episode: 313 training return: tensor(-409.7950, device='cuda:0')
episode: 314 training return: tensor(-394.1541, device='cuda:0')
episode: 315 training return: tensor(-144.8215, device='cuda:0')
epoch: 79 test_true_pfm: 2053.584143947323 sim_pfm: 60.851582952949684
episode: 316 training return: tensor(-307.4549, device='cuda:0')
episode: 317 training return: tensor(-358.9346, device='cuda:0')
episode: 318 training return: tensor(-228.5842, device='cuda:0')
episode: 319 training return: tensor(-400.9534, device='cuda:0')
epoch: 80 test_true_pfm: 2199.892924087901 sim_pfm: -24.848376649208756
episode: 320 training return: tensor(-399.4121, device='cuda:0')
episode: 321 training return: tensor(-260.6226, device='cuda:0')
episode: 322 training return: tensor(-397.9832, device='cuda:0')
episode: 323 training return: tensor(235.3706, device='cuda:0')
epoch: 81 test_true_pfm: 2468.5239724006133 sim_pfm: 15.777146701778596
episode: 324 training return: tensor(-116.3498, device='cuda:0')
episode: 325 training return: tensor(222.0735, device='cuda:0')
episode: 326 training return: tensor(-316.9554, device='cuda:0')
episode: 327 training return: tensor(-268.2744, device='cuda:0')
epoch: 82 test_true_pfm: 2450.867217339916 sim_pfm: 59.49683313504405
episode: 328 training return: tensor(-399.2173, device='cuda:0')
episode: 329 training return: tensor(-393.5006, device='cuda:0')
episode: 330 training return: tensor(-362.9151, device='cuda:0')
episode: 331 training return: tensor(-134.3548, device='cuda:0')
epoch: 83 test_true_pfm: 3010.027904795597 sim_pfm: 119.3710190767403
episode: 332 training return: tensor(-320.3977, device='cuda:0')
episode: 333 training return: tensor(-398.1093, device='cuda:0')
episode: 334 training return: tensor(-383.6607, device='cuda:0')
episode: 335 training return: tensor(4.3514, device='cuda:0')
epoch: 84 test_true_pfm: 2556.411170548989 sim_pfm: 17.05201937421225
episode: 336 training return: tensor(-403.4489, device='cuda:0')
episode: 337 training return: tensor(-414.1799, device='cuda:0')
episode: 338 training return: tensor(-399.7885, device='cuda:0')
episode: 339 training return: tensor(-339.1841, device='cuda:0')
epoch: 85 test_true_pfm: 2352.143721913659 sim_pfm: -87.01475574609746
episode: 340 training return: tensor(-324.2734, device='cuda:0')
episode: 341 training return: tensor(-384.5184, device='cuda:0')
episode: 342 training return: tensor(-403.9165, device='cuda:0')
episode: 343 training return: tensor(-425.1190, device='cuda:0')
epoch: 86 test_true_pfm: 2672.310002668671 sim_pfm: -23.594822541538935
episode: 344 training return: tensor(171.4510, device='cuda:0')
episode: 345 training return: tensor(-394.3587, device='cuda:0')
episode: 346 training return: tensor(-379.2594, device='cuda:0')
episode: 347 training return: tensor(-407.4532, device='cuda:0')
epoch: 87 test_true_pfm: 2010.1429869416952 sim_pfm: -110.41448284865085
episode: 348 training return: tensor(-313.1923, device='cuda:0')
episode: 349 training return: tensor(-171.1315, device='cuda:0')
episode: 350 training return: tensor(-396.4063, device='cuda:0')
episode: 351 training return: tensor(-301.6943, device='cuda:0')
epoch: 88 test_true_pfm: 2350.5388421403654 sim_pfm: 52.00269854462628
episode: 352 training return: tensor(-295.1338, device='cuda:0')
episode: 353 training return: tensor(-329.0710, device='cuda:0')
episode: 354 training return: tensor(-403.8292, device='cuda:0')
episode: 355 training return: tensor(-271.6033, device='cuda:0')
epoch: 89 test_true_pfm: 3103.5790998150246 sim_pfm: 52.498195138400966
episode: 356 training return: tensor(-47.5718, device='cuda:0')
episode: 357 training return: tensor(-337.8752, device='cuda:0')
episode: 358 training return: tensor(-351.9236, device='cuda:0')
episode: 359 training return: tensor(-402.1634, device='cuda:0')
epoch: 90 test_true_pfm: 2721.33219930263 sim_pfm: 111.03659722146888
episode: 360 training return: tensor(-408.0961, device='cuda:0')
episode: 361 training return: tensor(-101.7867, device='cuda:0')
episode: 362 training return: tensor(-398.1973, device='cuda:0')
episode: 363 training return: tensor(-407.0847, device='cuda:0')
epoch: 91 test_true_pfm: 2834.377219380902 sim_pfm: -51.099741500152355
episode: 364 training return: tensor(-371.0339, device='cuda:0')
episode: 365 training return: tensor(-392.8704, device='cuda:0')
episode: 366 training return: tensor(-394.8254, device='cuda:0')
episode: 367 training return: tensor(-141.4833, device='cuda:0')
epoch: 92 test_true_pfm: 2546.483573301822 sim_pfm: 0.9773836325039156
episode: 368 training return: tensor(-444.1870, device='cuda:0')
episode: 369 training return: tensor(-338.9469, device='cuda:0')
episode: 370 training return: tensor(234.1385, device='cuda:0')
episode: 371 training return: tensor(-375.0212, device='cuda:0')
epoch: 93 test_true_pfm: 2163.4319991760426 sim_pfm: -34.81323679772322
episode: 372 training return: tensor(-409.3568, device='cuda:0')
episode: 373 training return: tensor(-331.3235, device='cuda:0')
episode: 374 training return: tensor(-397.6816, device='cuda:0')
episode: 375 training return: tensor(-401.1523, device='cuda:0')
epoch: 94 test_true_pfm: 2109.647934794338 sim_pfm: 62.6115547583419
episode: 376 training return: tensor(-330.4589, device='cuda:0')
episode: 377 training return: tensor(-319.0970, device='cuda:0')
episode: 378 training return: tensor(-343.9370, device='cuda:0')
episode: 379 training return: tensor(-345.5977, device='cuda:0')
epoch: 95 test_true_pfm: 2371.7827535181536 sim_pfm: 256.2571220113411
episode: 380 training return: tensor(-249.8676, device='cuda:0')
episode: 381 training return: tensor(-323.0767, device='cuda:0')
episode: 382 training return: tensor(178.7323, device='cuda:0')
episode: 383 training return: tensor(-408.9417, device='cuda:0')
epoch: 96 test_true_pfm: 2006.421543640324 sim_pfm: -98.35262789443368
episode: 384 training return: tensor(-395.2902, device='cuda:0')
episode: 385 training return: tensor(-395.1794, device='cuda:0')
episode: 386 training return: tensor(34.9482, device='cuda:0')
episode: 387 training return: tensor(5.7289, device='cuda:0')
epoch: 97 test_true_pfm: 2488.136240699699 sim_pfm: -217.96767828282705
episode: 388 training return: tensor(-204.1824, device='cuda:0')
episode: 389 training return: tensor(190.0862, device='cuda:0')
episode: 390 training return: tensor(-342.9800, device='cuda:0')
episode: 391 training return: tensor(-362.4926, device='cuda:0')
epoch: 98 test_true_pfm: 3136.4108930007583 sim_pfm: 85.33636826897661
episode: 392 training return: tensor(-256.5006, device='cuda:0')
episode: 393 training return: tensor(-352.7617, device='cuda:0')
episode: 394 training return: tensor(185.3212, device='cuda:0')
episode: 395 training return: tensor(-44.9484, device='cuda:0')
epoch: 99 test_true_pfm: 2731.2604550590863 sim_pfm: 70.12846231334454
episode: 396 training return: tensor(-114.3771, device='cuda:0')
episode: 397 training return: tensor(218.7968, device='cuda:0')
episode: 398 training return: tensor(-362.0244, device='cuda:0')
episode: 399 training return: tensor(-402.3053, device='cuda:0')
epoch: 100 test_true_pfm: 2922.640717951715 sim_pfm: -135.32820658385754
episode: 400 training return: tensor(-401.2440, device='cuda:0')
episode: 401 training return: tensor(-358.8136, device='cuda:0')
episode: 402 training return: tensor(-79.7338, device='cuda:0')
episode: 403 training return: tensor(-395.2936, device='cuda:0')
epoch: 101 test_true_pfm: 2880.0250773520042 sim_pfm: 183.37491313906503
episode: 404 training return: tensor(-358.8015, device='cuda:0')
episode: 405 training return: tensor(-410.4792, device='cuda:0')
episode: 406 training return: tensor(-265.1172, device='cuda:0')
episode: 407 training return: tensor(-385.5508, device='cuda:0')
epoch: 102 test_true_pfm: 2531.9160940495276 sim_pfm: -90.28714051605978
episode: 408 training return: tensor(-318.0636, device='cuda:0')
episode: 409 training return: tensor(-336.6866, device='cuda:0')
episode: 410 training return: tensor(-331.9993, device='cuda:0')
episode: 411 training return: tensor(227.0708, device='cuda:0')
epoch: 103 test_true_pfm: 2488.6024957865216 sim_pfm: 187.86417469557878
episode: 412 training return: tensor(-272.8809, device='cuda:0')
episode: 413 training return: tensor(240.7213, device='cuda:0')
episode: 414 training return: tensor(-368.5986, device='cuda:0')
episode: 415 training return: tensor(-49.5060, device='cuda:0')
epoch: 104 test_true_pfm: 2637.2683809535215 sim_pfm: -53.97175573578958
episode: 416 training return: tensor(-405.8001, device='cuda:0')
episode: 417 training return: tensor(-322.6482, device='cuda:0')
episode: 418 training return: tensor(-395.4053, device='cuda:0')
episode: 419 training return: tensor(-333.0627, device='cuda:0')
epoch: 105 test_true_pfm: 2483.6552972389495 sim_pfm: 81.270437192133
episode: 420 training return: tensor(-413.7414, device='cuda:0')
episode: 421 training return: tensor(-229.9160, device='cuda:0')
episode: 422 training return: tensor(-398.8800, device='cuda:0')
episode: 423 training return: tensor(-145.7820, device='cuda:0')
epoch: 106 test_true_pfm: 2782.8604402163965 sim_pfm: -3.1813742417434696
episode: 424 training return: tensor(-71.2678, device='cuda:0')
episode: 425 training return: tensor(-321.0964, device='cuda:0')
episode: 426 training return: tensor(-310.7564, device='cuda:0')
episode: 427 training return: tensor(-396.6313, device='cuda:0')
epoch: 107 test_true_pfm: 3173.873403560367 sim_pfm: 7.999592784316822
episode: 428 training return: tensor(-310.5178, device='cuda:0')
episode: 429 training return: tensor(-115.0364, device='cuda:0')
episode: 430 training return: tensor(-368.7334, device='cuda:0')
episode: 431 training return: tensor(-396.4371, device='cuda:0')
epoch: 108 test_true_pfm: 2750.3074849041222 sim_pfm: -33.60191920044599
episode: 432 training return: tensor(-392.2237, device='cuda:0')
episode: 433 training return: tensor(-355.5401, device='cuda:0')
episode: 434 training return: tensor(-230.2452, device='cuda:0')
episode: 435 training return: tensor(-128.9505, device='cuda:0')
epoch: 109 test_true_pfm: 2531.4941369604217 sim_pfm: 64.43729715769102
episode: 436 training return: tensor(-362.4090, device='cuda:0')
episode: 437 training return: tensor(-345.9587, device='cuda:0')
episode: 438 training return: tensor(-410.0977, device='cuda:0')
episode: 439 training return: tensor(-280.6871, device='cuda:0')
epoch: 110 test_true_pfm: 2843.9845016456443 sim_pfm: 73.967508966889
episode: 440 training return: tensor(-401.8539, device='cuda:0')
episode: 441 training return: tensor(-89.9749, device='cuda:0')
episode: 442 training return: tensor(-237.0214, device='cuda:0')
episode: 443 training return: tensor(-314.4609, device='cuda:0')
epoch: 111 test_true_pfm: 2012.1856413405037 sim_pfm: -118.12485700901016
episode: 444 training return: tensor(-351.4599, device='cuda:0')
episode: 445 training return: tensor(-53.4501, device='cuda:0')
episode: 446 training return: tensor(-293.7639, device='cuda:0')
episode: 447 training return: tensor(-410.7235, device='cuda:0')
epoch: 112 test_true_pfm: 2467.5165756745814 sim_pfm: -70.11056529108707
episode: 448 training return: tensor(-357.1090, device='cuda:0')
episode: 449 training return: tensor(-415.3723, device='cuda:0')
episode: 450 training return: tensor(-330.5345, device='cuda:0')
episode: 451 training return: tensor(-350.3535, device='cuda:0')
epoch: 113 test_true_pfm: 2526.1937712590757 sim_pfm: -83.19584299822843
episode: 452 training return: tensor(-62.7287, device='cuda:0')
episode: 453 training return: tensor(-126.3294, device='cuda:0')
episode: 454 training return: tensor(-348.6980, device='cuda:0')
episode: 455 training return: tensor(-397.8811, device='cuda:0')
epoch: 114 test_true_pfm: 2968.94733769386 sim_pfm: 248.25408568175044
episode: 456 training return: tensor(-306.2726, device='cuda:0')
episode: 457 training return: tensor(-145.2662, device='cuda:0')
episode: 458 training return: tensor(-350.3553, device='cuda:0')
episode: 459 training return: tensor(-311.3695, device='cuda:0')
epoch: 115 test_true_pfm: 2805.391253274805 sim_pfm: 58.30349674126288
episode: 460 training return: tensor(-411.7688, device='cuda:0')
episode: 461 training return: tensor(-388.6686, device='cuda:0')
episode: 462 training return: tensor(203.3398, device='cuda:0')
episode: 463 training return: tensor(-244.5535, device='cuda:0')
epoch: 116 test_true_pfm: 2579.083820186372 sim_pfm: 198.97182264099442
episode: 464 training return: tensor(171.7108, device='cuda:0')
episode: 465 training return: tensor(-292.2771, device='cuda:0')
episode: 466 training return: tensor(-350.0359, device='cuda:0')
episode: 467 training return: tensor(-178.4658, device='cuda:0')
epoch: 117 test_true_pfm: 2592.2319877682567 sim_pfm: 69.25827916848357
episode: 468 training return: tensor(-126.8892, device='cuda:0')
episode: 469 training return: tensor(-148.6590, device='cuda:0')
episode: 470 training return: tensor(-276.8476, device='cuda:0')
episode: 471 training return: tensor(-400.3049, device='cuda:0')
epoch: 118 test_true_pfm: 3315.907934718863 sim_pfm: 126.39033295879683
episode: 472 training return: tensor(-7.6329, device='cuda:0')
episode: 473 training return: tensor(-418.2672, device='cuda:0')
episode: 474 training return: tensor(9.9847, device='cuda:0')
episode: 475 training return: tensor(-276.3996, device='cuda:0')
epoch: 119 test_true_pfm: 2414.04080604489 sim_pfm: 66.596350671869
episode: 476 training return: tensor(-345.4950, device='cuda:0')
episode: 477 training return: tensor(126.1940, device='cuda:0')
episode: 478 training return: tensor(-400.4891, device='cuda:0')
episode: 479 training return: tensor(-192.7354, device='cuda:0')
epoch: 120 test_true_pfm: 3240.58947608947 sim_pfm: -45.98608361223402
episode: 480 training return: tensor(-391.7485, device='cuda:0')
episode: 481 training return: tensor(-310.9436, device='cuda:0')
episode: 482 training return: tensor(-393.4476, device='cuda:0')
episode: 483 training return: tensor(-354.6318, device='cuda:0')
epoch: 121 test_true_pfm: 2317.0808503756675 sim_pfm: -44.66321631519046
episode: 484 training return: tensor(-366.4413, device='cuda:0')
episode: 485 training return: tensor(-356.6584, device='cuda:0')
episode: 486 training return: tensor(-393.8795, device='cuda:0')
episode: 487 training return: tensor(-408.9790, device='cuda:0')
epoch: 122 test_true_pfm: 2983.6150687218146 sim_pfm: 27.60569466976449
episode: 488 training return: tensor(-55.7905, device='cuda:0')
episode: 489 training return: tensor(-335.2658, device='cuda:0')
episode: 490 training return: tensor(-267.1294, device='cuda:0')
episode: 491 training return: tensor(-305.7390, device='cuda:0')
epoch: 123 test_true_pfm: 1980.1992771219666 sim_pfm: 49.00469872484488
episode: 492 training return: tensor(-312.2269, device='cuda:0')
episode: 493 training return: tensor(-177.8535, device='cuda:0')
episode: 494 training return: tensor(-363.6406, device='cuda:0')
episode: 495 training return: tensor(205.1216, device='cuda:0')
epoch: 124 test_true_pfm: 2638.8826134692113 sim_pfm: 20.70609869933105
episode: 496 training return: tensor(-372.2623, device='cuda:0')
episode: 497 training return: tensor(-402.5461, device='cuda:0')
episode: 498 training return: tensor(-375.2113, device='cuda:0')
episode: 499 training return: tensor(-347.6576, device='cuda:0')
epoch: 125 test_true_pfm: 2240.8564656914045 sim_pfm: 54.57792778254952
episode: 500 training return: tensor(-396.1245, device='cuda:0')
episode: 501 training return: tensor(152.0019, device='cuda:0')
episode: 502 training return: tensor(-367.7779, device='cuda:0')
episode: 503 training return: tensor(-394.3640, device='cuda:0')
epoch: 126 test_true_pfm: 3165.28189878498 sim_pfm: -7.086520385132947
episode: 504 training return: tensor(-338.1706, device='cuda:0')
episode: 505 training return: tensor(-400.5453, device='cuda:0')
episode: 506 training return: tensor(-353.4792, device='cuda:0')
episode: 507 training return: tensor(-394.1063, device='cuda:0')
epoch: 127 test_true_pfm: 3180.6518936528787 sim_pfm: -209.95753747933
episode: 508 training return: tensor(-331.7397, device='cuda:0')
episode: 509 training return: tensor(-397.5319, device='cuda:0')
episode: 510 training return: tensor(-415.1076, device='cuda:0')
episode: 511 training return: tensor(-367.8504, device='cuda:0')
epoch: 128 test_true_pfm: 3250.6944899790183 sim_pfm: 105.55784992813521
episode: 512 training return: tensor(-401.2025, device='cuda:0')
episode: 513 training return: tensor(-322.6028, device='cuda:0')
episode: 514 training return: tensor(-354.8737, device='cuda:0')
episode: 515 training return: tensor(-330.4267, device='cuda:0')
epoch: 129 test_true_pfm: 2740.562653023099 sim_pfm: 21.980728312172385
episode: 516 training return: tensor(-395.8727, device='cuda:0')
episode: 517 training return: tensor(-338.5919, device='cuda:0')
episode: 518 training return: tensor(-294.1127, device='cuda:0')
episode: 519 training return: tensor(69.4387, device='cuda:0')
epoch: 130 test_true_pfm: 2776.236598601609 sim_pfm: 82.58314052283338
episode: 520 training return: tensor(-320.9065, device='cuda:0')
episode: 521 training return: tensor(-314.9461, device='cuda:0')
episode: 522 training return: tensor(-345.8398, device='cuda:0')
episode: 523 training return: tensor(-393.8258, device='cuda:0')
epoch: 131 test_true_pfm: 2263.964521275037 sim_pfm: -9.376901899833078
episode: 524 training return: tensor(-346.8252, device='cuda:0')
episode: 525 training return: tensor(-239.3586, device='cuda:0')
episode: 526 training return: tensor(-350.6424, device='cuda:0')
episode: 527 training return: tensor(-403.4696, device='cuda:0')
epoch: 132 test_true_pfm: 2290.70611094073 sim_pfm: 139.9776991036682
episode: 528 training return: tensor(-364.1895, device='cuda:0')
episode: 529 training return: tensor(-334.4130, device='cuda:0')
episode: 530 training return: tensor(-337.8652, device='cuda:0')
episode: 531 training return: tensor(-388.1851, device='cuda:0')
epoch: 133 test_true_pfm: 1931.605112060149 sim_pfm: -41.20000165386591
episode: 532 training return: tensor(-314.5452, device='cuda:0')
episode: 533 training return: tensor(242.1836, device='cuda:0')
episode: 534 training return: tensor(26.5813, device='cuda:0')
episode: 535 training return: tensor(-409.3459, device='cuda:0')
epoch: 134 test_true_pfm: 2449.0463977848776 sim_pfm: 104.7134255093503
episode: 536 training return: tensor(227.7542, device='cuda:0')
episode: 537 training return: tensor(-338.0072, device='cuda:0')
episode: 538 training return: tensor(-306.6722, device='cuda:0')
episode: 539 training return: tensor(-394.8332, device='cuda:0')
epoch: 135 test_true_pfm: 2038.3863844923526 sim_pfm: -165.66920709056043
episode: 540 training return: tensor(-327.8095, device='cuda:0')
episode: 541 training return: tensor(122.5939, device='cuda:0')
episode: 542 training return: tensor(-395.7372, device='cuda:0')
episode: 543 training return: tensor(-223.9493, device='cuda:0')
epoch: 136 test_true_pfm: 2544.2622195300605 sim_pfm: 159.874603389481
episode: 544 training return: tensor(19.9694, device='cuda:0')
episode: 545 training return: tensor(-408.9244, device='cuda:0')
episode: 546 training return: tensor(-179.5178, device='cuda:0')
episode: 547 training return: tensor(-396.6190, device='cuda:0')
epoch: 137 test_true_pfm: 2815.467299035434 sim_pfm: 137.19238123608133
episode: 548 training return: tensor(-269.7910, device='cuda:0')
episode: 549 training return: tensor(-360.9811, device='cuda:0')
episode: 550 training return: tensor(-394.7963, device='cuda:0')
episode: 551 training return: tensor(-408.6571, device='cuda:0')
epoch: 138 test_true_pfm: 2144.429149859063 sim_pfm: 57.372515130603766
episode: 552 training return: tensor(-325.7375, device='cuda:0')
episode: 553 training return: tensor(-178.5552, device='cuda:0')
episode: 554 training return: tensor(-409.9501, device='cuda:0')
episode: 555 training return: tensor(-373.4750, device='cuda:0')
epoch: 139 test_true_pfm: 2473.121230932428 sim_pfm: 87.66588531899227
episode: 556 training return: tensor(-377.7639, device='cuda:0')
episode: 557 training return: tensor(-374.5757, device='cuda:0')
episode: 558 training return: tensor(-395.3512, device='cuda:0')
episode: 559 training return: tensor(-95.2768, device='cuda:0')
epoch: 140 test_true_pfm: 2228.161502488631 sim_pfm: 5.435192166284348
episode: 560 training return: tensor(-189.3911, device='cuda:0')
episode: 561 training return: tensor(-374.0656, device='cuda:0')
episode: 562 training return: tensor(-401.5477, device='cuda:0')
episode: 563 training return: tensor(-59.9562, device='cuda:0')
epoch: 141 test_true_pfm: 2097.882042543724 sim_pfm: -59.35500459946343
episode: 564 training return: tensor(-179.3315, device='cuda:0')
episode: 565 training return: tensor(-256.7531, device='cuda:0')
episode: 566 training return: tensor(182.5532, device='cuda:0')
episode: 567 training return: tensor(-306.2946, device='cuda:0')
epoch: 142 test_true_pfm: 2139.141864939543 sim_pfm: -17.34908073876674
episode: 568 training return: tensor(-311.3619, device='cuda:0')
episode: 569 training return: tensor(-257.1488, device='cuda:0')
episode: 570 training return: tensor(-354.5786, device='cuda:0')
episode: 571 training return: tensor(-263.2464, device='cuda:0')
epoch: 143 test_true_pfm: 2277.7352479779615 sim_pfm: -109.28646353581765
episode: 572 training return: tensor(-361.5024, device='cuda:0')
episode: 573 training return: tensor(-365.7848, device='cuda:0')
episode: 574 training return: tensor(-416.8349, device='cuda:0')
episode: 575 training return: tensor(-244.0160, device='cuda:0')
epoch: 144 test_true_pfm: 2725.770091610549 sim_pfm: -131.83986372476406
episode: 576 training return: tensor(-414.4785, device='cuda:0')
episode: 577 training return: tensor(-399.6856, device='cuda:0')
episode: 578 training return: tensor(-403.0036, device='cuda:0')
episode: 579 training return: tensor(-406.4286, device='cuda:0')
epoch: 145 test_true_pfm: 2612.317217944967 sim_pfm: 104.96330779309694
episode: 580 training return: tensor(-375.9639, device='cuda:0')
episode: 581 training return: tensor(-396.0579, device='cuda:0')
episode: 582 training return: tensor(-345.8086, device='cuda:0')
episode: 583 training return: tensor(126.5253, device='cuda:0')
epoch: 146 test_true_pfm: 2489.8152318182424 sim_pfm: 67.78826230168731
episode: 584 training return: tensor(-308.0561, device='cuda:0')
episode: 585 training return: tensor(-368.3513, device='cuda:0')
episode: 586 training return: tensor(-263.5182, device='cuda:0')
episode: 587 training return: tensor(-271.5360, device='cuda:0')
epoch: 147 test_true_pfm: 2922.6547708574685 sim_pfm: 121.78824845826603
episode: 588 training return: tensor(210.4063, device='cuda:0')
episode: 589 training return: tensor(-396.7943, device='cuda:0')
episode: 590 training return: tensor(-332.5984, device='cuda:0')
episode: 591 training return: tensor(-398.9884, device='cuda:0')
epoch: 148 test_true_pfm: 2996.4345136917404 sim_pfm: -127.73189532298905
episode: 592 training return: tensor(-84.2957, device='cuda:0')
episode: 593 training return: tensor(-416.8033, device='cuda:0')
episode: 594 training return: tensor(-337.0597, device='cuda:0')
episode: 595 training return: tensor(-261.3036, device='cuda:0')
epoch: 149 test_true_pfm: 2810.6086807869965 sim_pfm: 88.0865576105037
episode: 596 training return: tensor(227.0284, device='cuda:0')
episode: 597 training return: tensor(-405.2830, device='cuda:0')
episode: 598 training return: tensor(-350.8140, device='cuda:0')
episode: 599 training return: tensor(-396.4838, device='cuda:0')
epoch: 150 test_true_pfm: 2262.9985702731187 sim_pfm: 78.0698386829851
