['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'uncertainty', '--traj', 'medium', '--seed', '0', '--data', '100000']
episode: 0 training return: -1101.5552829741848
episode: 1 training return: -974.7930760753991
episode: 2 training return: -972.1446071446583
episode: 3 training return: -1207.8502376850286
epoch: 1 test_true_pfm: 205.18135806255657 sim_pfm: -858.2626693787728
episode: 4 training return: -1022.4279092805259
episode: 5 training return: -1006.9674380379569
episode: 6 training return: -994.6479144426527
episode: 7 training return: -943.4101415428142
epoch: 2 test_true_pfm: 233.66298867922274 sim_pfm: -840.0475215687674
episode: 8 training return: -952.9927307968336
episode: 9 training return: -1069.611501865848
episode: 10 training return: -834.978968313413
episode: 11 training return: -841.8222206798264
epoch: 3 test_true_pfm: 210.16843355904953 sim_pfm: -861.0048762106484
episode: 12 training return: -853.266481562913
episode: 13 training return: -875.5367167805771
episode: 14 training return: -847.8152594230078
episode: 15 training return: -857.3113777454947
epoch: 4 test_true_pfm: 228.98457492782805 sim_pfm: -823.8616848069506
episode: 16 training return: -789.1034481215158
episode: 17 training return: -843.398856579337
episode: 18 training return: -823.2285961476773
episode: 19 training return: -840.0745650118429
epoch: 5 test_true_pfm: 259.478073468354 sim_pfm: -827.9635710127986
episode: 20 training return: -854.6442832555125
episode: 21 training return: -834.2407943950532
episode: 22 training return: -825.0100392002723
episode: 23 training return: -771.8275739671486
epoch: 6 test_true_pfm: 265.3881130613588 sim_pfm: -841.0601581174768
episode: 24 training return: -748.9232582818917
episode: 25 training return: -742.3101154073356
episode: 26 training return: -740.2181741675503
episode: 27 training return: -718.8694724956736
epoch: 7 test_true_pfm: 315.9279917030845 sim_pfm: -700.4928554672707
episode: 28 training return: -678.1327144063454
episode: 29 training return: -661.2001361800747
episode: 30 training return: -679.1398089247565
episode: 31 training return: -660.6237638345134
epoch: 8 test_true_pfm: 497.86742288945584 sim_pfm: -577.9748998617195
episode: 32 training return: -633.5637372916507
episode: 33 training return: -628.2334114198148
episode: 34 training return: -615.0758235709502
episode: 35 training return: -578.1303336462796
epoch: 9 test_true_pfm: 429.1095572372492 sim_pfm: -537.8092340342433
episode: 36 training return: -590.2054875643407
episode: 37 training return: -591.2164274390913
episode: 38 training return: -586.0477868210102
episode: 39 training return: -596.8734666935411
epoch: 10 test_true_pfm: 296.3412064218068 sim_pfm: -731.5270295656182
episode: 40 training return: -626.0033680238733
episode: 41 training return: -560.6033154422867
episode: 42 training return: -575.52243319725
episode: 43 training return: -568.5767136112499
epoch: 11 test_true_pfm: 542.7341916729866 sim_pfm: -518.3556226447705
episode: 44 training return: -553.4066773753768
episode: 45 training return: -569.6345868365305
episode: 46 training return: -545.4280292785508
episode: 47 training return: -530.0034004148624
epoch: 12 test_true_pfm: 557.6344594607737 sim_pfm: -486.7403512328092
episode: 48 training return: -560.5684867367662
episode: 49 training return: -525.0251445535354
episode: 50 training return: -523.787955904155
episode: 51 training return: -529.5419708914715
epoch: 13 test_true_pfm: 544.2704777234418 sim_pfm: -486.13997866812997
episode: 52 training return: -527.3884592269314
episode: 53 training return: -537.5647672256739
episode: 54 training return: -528.3161608601986
episode: 55 training return: -540.4639420261125
epoch: 14 test_true_pfm: 654.2462826659327 sim_pfm: -467.0800185940111
episode: 56 training return: -551.9797634554436
episode: 57 training return: -528.721457445938
episode: 58 training return: -526.3387814089546
episode: 59 training return: -548.8796651663185
epoch: 15 test_true_pfm: 607.0467881981627 sim_pfm: -462.22849276379384
episode: 60 training return: -531.5998542137586
episode: 61 training return: -517.4388704967264
episode: 62 training return: -524.7098914382203
episode: 63 training return: -520.9945354495632
epoch: 16 test_true_pfm: 619.7181397624805 sim_pfm: -465.2111509468205
episode: 64 training return: -531.7674205919245
episode: 65 training return: -526.411595831696
episode: 66 training return: -507.1345474007704
episode: 67 training return: -530.0140917693045
epoch: 17 test_true_pfm: 694.6561378386904 sim_pfm: -468.8092141724901
episode: 68 training return: -514.608530657236
episode: 69 training return: -514.4949363097638
episode: 70 training return: -499.2715761831223
episode: 71 training return: -513.582202067054
epoch: 18 test_true_pfm: 628.9812904247586 sim_pfm: -451.19353046590703
episode: 72 training return: -511.07302771489043
episode: 73 training return: -502.5413011075983
episode: 74 training return: -501.9698155649255
episode: 75 training return: -502.9638674704419
epoch: 19 test_true_pfm: 656.4524146378741 sim_pfm: -464.12313146526793
episode: 76 training return: -518.5038669851347
episode: 77 training return: -510.11896745624836
episode: 78 training return: -514.4413609655603
episode: 79 training return: -502.86545317790785
epoch: 20 test_true_pfm: 637.1625031497956 sim_pfm: -463.39151383662016
episode: 80 training return: -493.44479707101533
episode: 81 training return: -485.9244801751045
episode: 82 training return: -523.4267067105835
episode: 83 training return: -519.9397893350855
epoch: 21 test_true_pfm: 647.9124410478545 sim_pfm: -457.3587000824159
episode: 84 training return: -511.66253119098417
episode: 85 training return: -490.0260692305692
episode: 86 training return: -494.8540043415203
episode: 87 training return: -515.9270103924033
epoch: 22 test_true_pfm: 648.0982928779016 sim_pfm: -453.41949289467385
episode: 88 training return: -508.21333365561486
episode: 89 training return: -515.4157686989333
episode: 90 training return: -497.2387565013571
episode: 91 training return: -518.491690232171
epoch: 23 test_true_pfm: 646.2581164430445 sim_pfm: -455.29069677804654
episode: 92 training return: -525.7325228685884
episode: 93 training return: -518.1747249048285
episode: 94 training return: -510.5871374119398
episode: 95 training return: -499.23291515150635
epoch: 24 test_true_pfm: 631.9177968204355 sim_pfm: -449.5216916630847
episode: 96 training return: -509.90016381734176
episode: 97 training return: -504.86297984427233
episode: 98 training return: -520.1525550428621
episode: 99 training return: -502.6179341689126
epoch: 25 test_true_pfm: 607.8424380415573 sim_pfm: -451.7194081636153
episode: 100 training return: -501.9115268176514
episode: 101 training return: -502.2970469048284
episode: 102 training return: -502.3076468793993
episode: 103 training return: -508.3551253348112
epoch: 26 test_true_pfm: 635.203728952264 sim_pfm: -457.37645028202525
episode: 104 training return: -514.9380932537849
episode: 105 training return: -494.65288697442764
episode: 106 training return: -514.8024799170544
episode: 107 training return: -513.1120636114466
epoch: 27 test_true_pfm: 635.4409442428033 sim_pfm: -462.0946294999837
episode: 108 training return: -509.7270557481775
episode: 109 training return: -503.04175732854617
episode: 110 training return: -507.8975280286716
episode: 111 training return: -514.8183809655244
epoch: 28 test_true_pfm: 713.4534271443907 sim_pfm: -436.9328171009235
episode: 112 training return: -496.95891695177903
episode: 113 training return: -505.573516717786
episode: 114 training return: -493.07670477404895
episode: 115 training return: -494.34692528146894
epoch: 29 test_true_pfm: 708.5931536490807 sim_pfm: -452.29049307012957
episode: 116 training return: -518.5424197827024
episode: 117 training return: -507.30343919900247
episode: 118 training return: -511.303985981354
episode: 119 training return: -497.22388132099684
epoch: 30 test_true_pfm: 647.5721132217942 sim_pfm: -441.41409933750083
episode: 120 training return: -483.3183694054398
episode: 121 training return: -506.75795416846836
episode: 122 training return: -513.6892343031058
episode: 123 training return: -488.73081156299656
epoch: 31 test_true_pfm: 630.5062221275449 sim_pfm: -454.05306280394706
episode: 124 training return: -499.45079625105956
episode: 125 training return: -487.78940890586824
episode: 126 training return: -492.2411632671287
episode: 127 training return: -489.4071183284573
epoch: 32 test_true_pfm: 703.852956619096 sim_pfm: -441.518559045993
episode: 128 training return: -506.7843265469922
episode: 129 training return: -527.2909702510015
episode: 130 training return: -487.2430247344802
episode: 131 training return: -488.8827787118291
epoch: 33 test_true_pfm: 654.860043597747 sim_pfm: -442.6887741907345
episode: 132 training return: -500.4585541205901
episode: 133 training return: -492.2511516124713
episode: 134 training return: -522.135185688103
episode: 135 training return: -488.88557944182116
epoch: 34 test_true_pfm: 663.1555565826762 sim_pfm: -440.1764644563023
episode: 136 training return: -497.6232644936566
episode: 137 training return: -499.4805080242844
episode: 138 training return: -503.49063536200373
episode: 139 training return: -512.4300981492706
epoch: 35 test_true_pfm: 651.159195180178 sim_pfm: -447.7401847162423
episode: 140 training return: -504.604923884896
episode: 141 training return: -498.5042972289787
episode: 142 training return: -492.119004585973
episode: 143 training return: -512.81748393799
epoch: 36 test_true_pfm: 656.9385122561081 sim_pfm: -441.84150627047535
episode: 144 training return: -502.03729722933576
episode: 145 training return: -503.21438980717875
episode: 146 training return: -475.6380746650373
episode: 147 training return: -482.0733822081168
epoch: 37 test_true_pfm: 642.7239186321734 sim_pfm: -447.7881780317038
episode: 148 training return: -502.1067145962788
episode: 149 training return: -507.325717504013
episode: 150 training return: -484.5741490789942
episode: 151 training return: -493.2965354963725
epoch: 38 test_true_pfm: 721.9547680358737 sim_pfm: -431.1706252598151
episode: 152 training return: -478.18627126896786
episode: 153 training return: -488.689997929643
episode: 154 training return: -503.39435541727113
episode: 155 training return: -499.5816704737375
epoch: 39 test_true_pfm: 664.4161588925039 sim_pfm: -448.2629487357412
episode: 156 training return: -485.0929000413651
episode: 157 training return: -485.50960452806225
episode: 158 training return: -483.9226886489262
episode: 159 training return: -495.8391736925539
epoch: 40 test_true_pfm: 716.7688918731984 sim_pfm: -442.10085475441156
episode: 160 training return: -485.0885288665124
episode: 161 training return: -499.0235059540808
episode: 162 training return: -481.6994383945352
episode: 163 training return: -458.1648031957928
epoch: 41 test_true_pfm: 689.7945551867443 sim_pfm: -437.70397864781324
episode: 164 training return: -480.7064154035003
episode: 165 training return: -506.12453721173387
episode: 166 training return: -473.97048589917546
episode: 167 training return: -487.8851511046986
epoch: 42 test_true_pfm: 674.764774346342 sim_pfm: -447.6405658809408
episode: 168 training return: -490.8736397029443
episode: 169 training return: -499.33839643940956
episode: 170 training return: -516.550772546687
episode: 171 training return: -489.30481806690034
epoch: 43 test_true_pfm: 721.8292306026378 sim_pfm: -427.207131732895
episode: 172 training return: -491.4922242172287
episode: 173 training return: -499.4740230046469
episode: 174 training return: -493.28574190354016
episode: 175 training return: -499.1182033273903
epoch: 44 test_true_pfm: 677.7642895029318 sim_pfm: -444.5928158205357
episode: 176 training return: -481.3668128139595
episode: 177 training return: -503.03202585931695
episode: 178 training return: -493.4957737392793
episode: 179 training return: -504.20117614491573
epoch: 45 test_true_pfm: 654.4283977801357 sim_pfm: -452.0605476208373
episode: 180 training return: -488.5354237898067
episode: 181 training return: -501.31152575997
episode: 182 training return: -484.8273045103868
episode: 183 training return: -500.7335598219736
epoch: 46 test_true_pfm: 691.3413988194249 sim_pfm: -446.0364846241069
episode: 184 training return: -488.90426329876976
episode: 185 training return: -481.87623793144706
episode: 186 training return: -492.95548365178814
episode: 187 training return: -488.02993591975195
epoch: 47 test_true_pfm: 657.2624159296445 sim_pfm: -439.74432799845704
episode: 188 training return: -483.5362058493124
episode: 189 training return: -485.64751485907186
episode: 190 training return: -507.45790097045324
episode: 191 training return: -492.42067193797703
epoch: 48 test_true_pfm: 660.0167618719671 sim_pfm: -445.89978189297034
episode: 192 training return: -487.67013043084694
episode: 193 training return: -482.3675438437486
episode: 194 training return: -499.7592299025852
episode: 195 training return: -475.11769183745315
epoch: 49 test_true_pfm: 644.3036671224405 sim_pfm: -452.92456617899774
episode: 196 training return: -508.49560885516405
episode: 197 training return: -505.9837492907999
episode: 198 training return: -494.73934587600235
episode: 199 training return: -503.17785512451377
epoch: 50 test_true_pfm: 688.7294122641388 sim_pfm: -436.9130917437553
episode: 200 training return: -508.26634217773244
episode: 201 training return: -508.0353922061903
episode: 202 training return: -488.6875087274383
episode: 203 training return: -490.3803086155716
epoch: 51 test_true_pfm: 710.5771125842795 sim_pfm: -445.81617076296146
episode: 204 training return: -498.642920507691
episode: 205 training return: -491.5258366836771
episode: 206 training return: -497.07689230338065
episode: 207 training return: -465.8905713235023
epoch: 52 test_true_pfm: 640.5767863457849 sim_pfm: -447.72618897581395
episode: 208 training return: -471.05390429466337
episode: 209 training return: -488.8091197796506
episode: 210 training return: -493.20789842955816
episode: 211 training return: -476.9335033701085
epoch: 53 test_true_pfm: 642.8392207928125 sim_pfm: -453.1938148678203
episode: 212 training return: -490.24153853423456
episode: 213 training return: -478.5302623383434
episode: 214 training return: -481.58708165385315
episode: 215 training return: -496.5045709982282
epoch: 54 test_true_pfm: 663.2705298709703 sim_pfm: -445.46699260842524
episode: 216 training return: -475.8757107086985
episode: 217 training return: -481.46469386982557
episode: 218 training return: -484.96601465589873
episode: 219 training return: -479.5924552125347
epoch: 55 test_true_pfm: 660.7293783960946 sim_pfm: -445.3811669454498
episode: 220 training return: -494.2363164393669
episode: 221 training return: -477.19020838584436
episode: 222 training return: -489.8360304888431
episode: 223 training return: -497.3170985873806
epoch: 56 test_true_pfm: 691.5406761384944 sim_pfm: -437.83322560368373
episode: 224 training return: -485.12041486562805
episode: 225 training return: -486.58038143065073
episode: 226 training return: -493.69630047797625
episode: 227 training return: -482.706458439652
epoch: 57 test_true_pfm: 671.612869859683 sim_pfm: -441.00635236754835
episode: 228 training return: -487.02644302106097
episode: 229 training return: -481.30066358310097
episode: 230 training return: -474.1603380494939
episode: 231 training return: -481.76963797020187
epoch: 58 test_true_pfm: 694.990655645965 sim_pfm: -435.2842231296924
episode: 232 training return: -467.58134231084426
episode: 233 training return: -496.72031684632975
episode: 234 training return: -478.5428285600967
episode: 235 training return: -504.3591760986324
epoch: 59 test_true_pfm: 674.0816913122268 sim_pfm: -436.1462852283609
episode: 236 training return: -506.13731617530505
episode: 237 training return: -480.4471617870952
episode: 238 training return: -501.97676276544206
episode: 239 training return: -494.94688521413195
epoch: 60 test_true_pfm: 674.9513027727455 sim_pfm: -432.9093100796983
episode: 240 training return: -476.4847571073111
episode: 241 training return: -486.678186950629
episode: 242 training return: -503.3275631868826
episode: 243 training return: -496.7427653458217
epoch: 61 test_true_pfm: 714.024970516691 sim_pfm: -441.31091691389383
episode: 244 training return: -467.4148279245211
episode: 245 training return: -474.3865231744765
episode: 246 training return: -489.792139347703
episode: 247 training return: -489.4724816920942
epoch: 62 test_true_pfm: 666.0492600059762 sim_pfm: -443.67837762974995
episode: 248 training return: -494.8059285336222
episode: 249 training return: -475.7160477609355
episode: 250 training return: -495.9862859932851
episode: 251 training return: -493.5935810974742
epoch: 63 test_true_pfm: 755.1700389649526 sim_pfm: -423.6277496648006
episode: 252 training return: -470.3527308720326
episode: 253 training return: -470.060918881821
episode: 254 training return: -478.6083412246778
episode: 255 training return: -479.38918867305284
epoch: 64 test_true_pfm: 690.7220499116111 sim_pfm: -444.2418878888156
episode: 256 training return: -483.7254787258013
episode: 257 training return: -476.17635287601274
episode: 258 training return: -489.2543696988876
episode: 259 training return: -506.42392149545964
epoch: 65 test_true_pfm: 752.1516559181324 sim_pfm: -431.26552645282845
episode: 260 training return: -475.60263705124856
episode: 261 training return: -474.1191110943802
episode: 262 training return: -486.5351331019748
episode: 263 training return: -480.30972671678376
epoch: 66 test_true_pfm: 672.8647078927647 sim_pfm: -447.0579740618767
episode: 264 training return: -488.60266048381243
episode: 265 training return: -481.739326795586
episode: 266 training return: -491.7767954766406
episode: 267 training return: -471.3244021946205
epoch: 67 test_true_pfm: 741.3370877187366 sim_pfm: -439.10293256655405
episode: 268 training return: -475.78400796420664
episode: 269 training return: -500.18146800757626
episode: 270 training return: -472.7286584920378
episode: 271 training return: -469.6738935241944
epoch: 68 test_true_pfm: 748.0148473581138 sim_pfm: -422.37973830796733
episode: 272 training return: -474.5111506767596
episode: 273 training return: -474.26077637886283
episode: 274 training return: -499.01725715699797
episode: 275 training return: -486.0499212232712
epoch: 69 test_true_pfm: 754.8454901830704 sim_pfm: -415.0244392447391
episode: 276 training return: -473.4933245331877
episode: 277 training return: -482.7102516523675
episode: 278 training return: -468.4678731414177
episode: 279 training return: -477.3544403791865
epoch: 70 test_true_pfm: 747.261541238597 sim_pfm: -431.3618644870985
episode: 280 training return: -477.66631017905945
episode: 281 training return: -490.35152835319724
episode: 282 training return: -478.04400000498066
episode: 283 training return: -484.6687619950791
epoch: 71 test_true_pfm: 687.7380127175875 sim_pfm: -426.1837413333951
episode: 284 training return: -488.5970793135327
episode: 285 training return: -484.3473039996789
episode: 286 training return: -501.79491582371423
episode: 287 training return: -469.7835456165513
epoch: 72 test_true_pfm: 719.8113119788244 sim_pfm: -430.36437244363634
episode: 288 training return: -476.7198598918074
episode: 289 training return: -475.7743789642133
episode: 290 training return: -480.3800404993428
episode: 291 training return: -479.949930315715
epoch: 73 test_true_pfm: 755.3866691660396 sim_pfm: -424.47877645740783
episode: 292 training return: -474.31368796438204
episode: 293 training return: -482.76290966515364
episode: 294 training return: -485.9031314773451
episode: 295 training return: -470.81445369675004
epoch: 74 test_true_pfm: 738.7401695935614 sim_pfm: -425.38135092933413
episode: 296 training return: -479.06683078407315
episode: 297 training return: -477.2446568325126
episode: 298 training return: -482.4312838399234
episode: 299 training return: -491.2343438959648
epoch: 75 test_true_pfm: 708.8782839220507 sim_pfm: -431.78050716729166
episode: 300 training return: -468.3435158373925
episode: 301 training return: -490.98664479097795
episode: 302 training return: -498.4615849606265
episode: 303 training return: -465.80424732789913
epoch: 76 test_true_pfm: 759.6234801724319 sim_pfm: -416.89578082368445
episode: 304 training return: -480.783755818753
episode: 305 training return: -475.50996962234836
episode: 306 training return: -474.939636708611
episode: 307 training return: -483.6314111355474
epoch: 77 test_true_pfm: 676.2856391872004 sim_pfm: -425.3269523291083
episode: 308 training return: -474.4167313816441
episode: 309 training return: -490.19687024459495
episode: 310 training return: -494.1875252775525
episode: 311 training return: -481.528271165107
epoch: 78 test_true_pfm: 680.6292065532404 sim_pfm: -442.4730528791362
episode: 312 training return: -475.1504100483551
episode: 313 training return: -470.66306724503016
episode: 314 training return: -484.2730393244615
episode: 315 training return: -475.6593222320441
epoch: 79 test_true_pfm: 736.1305664825617 sim_pfm: -418.3933414019497
episode: 316 training return: -470.06280367731824
episode: 317 training return: -469.0733594044051
episode: 318 training return: -486.236520945591
episode: 319 training return: -480.2851149385078
epoch: 80 test_true_pfm: 746.9535517076978 sim_pfm: -415.78844596713685
episode: 320 training return: -478.787797068157
episode: 321 training return: -465.23497518111964
episode: 322 training return: -480.84152425459473
episode: 323 training return: -463.88290674647453
epoch: 81 test_true_pfm: 741.7026515023163 sim_pfm: -406.44829323606456
episode: 324 training return: -457.62460036477034
episode: 325 training return: -475.6862609587551
episode: 326 training return: -483.14460060757887
episode: 327 training return: -480.88928929497695
epoch: 82 test_true_pfm: 717.1650229534956 sim_pfm: -423.70221893509233
episode: 328 training return: -483.927887964778
episode: 329 training return: -492.5855681036284
episode: 330 training return: -477.8244681059675
episode: 331 training return: -477.76309916487475
epoch: 83 test_true_pfm: 765.3397233826108 sim_pfm: -429.45418464353196
episode: 332 training return: -498.54535034261795
episode: 333 training return: -487.1577075098195
episode: 334 training return: -472.50780162493334
episode: 335 training return: -460.24226019272396
epoch: 84 test_true_pfm: 712.3053330878269 sim_pfm: -436.7623857344843
episode: 336 training return: -482.6738614726368
episode: 337 training return: -475.5419865613008
episode: 338 training return: -475.3672298811288
episode: 339 training return: -468.8441057112693
epoch: 85 test_true_pfm: 774.3438157718971 sim_pfm: -390.8169748701573
episode: 340 training return: -476.08923278153594
episode: 341 training return: -467.61695295568995
episode: 342 training return: -452.6095645903589
episode: 343 training return: -468.0059190246672
epoch: 86 test_true_pfm: 749.6461039897571 sim_pfm: -412.2274164424198
episode: 344 training return: -476.71255959432904
episode: 345 training return: -482.3907786966927
episode: 346 training return: -480.3700680678464
episode: 347 training return: -461.55361187451507
epoch: 87 test_true_pfm: 728.2667963396988 sim_pfm: -431.2289745507929
episode: 348 training return: -475.5011984534425
episode: 349 training return: -474.0194296143508
episode: 350 training return: -468.4583985938811
episode: 351 training return: -484.5463209690964
epoch: 88 test_true_pfm: 682.5148402181343 sim_pfm: -440.2289564648939
episode: 352 training return: -460.7553836560316
episode: 353 training return: -475.0345782107179
episode: 354 training return: -492.364748869357
episode: 355 training return: -469.9986427326482
epoch: 89 test_true_pfm: 734.3455473536648 sim_pfm: -417.570588737626
episode: 356 training return: -457.4293137013052
episode: 357 training return: -458.81428362421144
episode: 358 training return: -456.63605072337714
episode: 359 training return: -463.42448104214367
epoch: 90 test_true_pfm: 678.3569292038123 sim_pfm: -426.44170840044916
episode: 360 training return: -465.618019434264
episode: 361 training return: -462.6980378652481
episode: 362 training return: -482.57954586480435
episode: 363 training return: -455.5701254009546
epoch: 91 test_true_pfm: 716.7188466109207 sim_pfm: -424.5177865882251
episode: 364 training return: -456.29973649484407
episode: 365 training return: -441.1768434025171
episode: 366 training return: -483.15293435522307
episode: 367 training return: -449.6576659604647
epoch: 92 test_true_pfm: 687.6188972457481 sim_pfm: -415.48063013605883
episode: 368 training return: -450.84940642484736
episode: 369 training return: -464.6451764541847
episode: 370 training return: -460.0203262283157
episode: 371 training return: -443.0199539877076
epoch: 93 test_true_pfm: 704.4754145020219 sim_pfm: -422.8664055275065
episode: 372 training return: -479.8402424811472
episode: 373 training return: -481.4999473947066
episode: 374 training return: -478.46285100155177
episode: 375 training return: -451.812017169514
epoch: 94 test_true_pfm: 776.3114451701698 sim_pfm: -403.33483979571594
episode: 376 training return: -470.265944458821
episode: 377 training return: -449.1167626997408
episode: 378 training return: -459.72413535309477
episode: 379 training return: -481.1061431956571
epoch: 95 test_true_pfm: 696.3960769968259 sim_pfm: -426.4533132176946
episode: 380 training return: -462.2741468899612
episode: 381 training return: -459.11870134996065
episode: 382 training return: -447.50956552545745
episode: 383 training return: -458.0585363391312
epoch: 96 test_true_pfm: 761.5835492862634 sim_pfm: -397.12408647606975
episode: 384 training return: -469.34272282494055
episode: 385 training return: -451.4457074381969
episode: 386 training return: -463.175915352779
episode: 387 training return: -468.4813961780318
epoch: 97 test_true_pfm: 709.6848366705066 sim_pfm: -425.27365355184514
episode: 388 training return: -487.42044587928456
episode: 389 training return: -473.14126935079935
episode: 390 training return: -460.45265383994087
episode: 391 training return: -451.2749206689278
epoch: 98 test_true_pfm: 793.6146532179681 sim_pfm: -374.8456748840211
episode: 392 training return: -436.15373318832644
episode: 393 training return: -473.30986157889316
episode: 394 training return: -453.9707919616365
episode: 395 training return: -456.24392594765635
epoch: 99 test_true_pfm: 701.4256031041796 sim_pfm: -413.9213839252152
episode: 396 training return: -460.00692600643447
episode: 397 training return: -456.63951100808
episode: 398 training return: -461.6622474236083
episode: 399 training return: -448.390993385804
epoch: 100 test_true_pfm: 724.931449031927 sim_pfm: -397.47798820378716
episode: 400 training return: -462.69241849824357
episode: 401 training return: -452.7565129808055
episode: 402 training return: -459.415985242041
episode: 403 training return: -474.8228186796444
epoch: 101 test_true_pfm: 729.088472099596 sim_pfm: -390.29768332025577
episode: 404 training return: -440.6776943219933
episode: 405 training return: -451.63939026991983
episode: 406 training return: -454.44095453210764
episode: 407 training return: -452.5414722908919
epoch: 102 test_true_pfm: 760.6979058978135 sim_pfm: -393.7727953152871
episode: 408 training return: -445.8137131277523
episode: 409 training return: -462.5503409336492
episode: 410 training return: -443.6477961049002
episode: 411 training return: -446.6562500543654
epoch: 103 test_true_pfm: 713.2313551267968 sim_pfm: -410.9872457612043
episode: 412 training return: -479.0172299895223
episode: 413 training return: -432.4315323035455
episode: 414 training return: -426.94653395136254
episode: 415 training return: -426.40168928873595
epoch: 104 test_true_pfm: 788.3273291395848 sim_pfm: -374.6453692383557
episode: 416 training return: -438.4357445490522
episode: 417 training return: -455.9420316877288
episode: 418 training return: -428.91743684234143
episode: 419 training return: -453.7368156357322
epoch: 105 test_true_pfm: 779.682358528256 sim_pfm: -360.6769347755265
episode: 420 training return: -435.92848242198863
episode: 421 training return: -431.06766401162014
episode: 422 training return: -411.0507387728501
episode: 423 training return: -435.41501249725
epoch: 106 test_true_pfm: 769.5514327127548 sim_pfm: -361.29617677476614
episode: 424 training return: -456.1416271228464
episode: 425 training return: -457.43277024583756
episode: 426 training return: -395.3054685609009
episode: 427 training return: -423.8564620176062
epoch: 107 test_true_pfm: 835.9051545352795 sim_pfm: -341.34857619860617
episode: 428 training return: -426.43760215288125
episode: 429 training return: -441.61099039005956
episode: 430 training return: -406.979937027198
episode: 431 training return: -457.17979866697544
epoch: 108 test_true_pfm: 906.7397704318613 sim_pfm: -307.113832867788
episode: 432 training return: -400.87472948278185
episode: 433 training return: -406.41563232473294
episode: 434 training return: -416.2151457575976
episode: 435 training return: -459.1620134149351
epoch: 109 test_true_pfm: 893.1535345231019 sim_pfm: -318.52376341695646
episode: 436 training return: -398.5361273317797
episode: 437 training return: -392.9915628011657
episode: 438 training return: -429.87875020210237
episode: 439 training return: -434.1050123430271
epoch: 110 test_true_pfm: 808.7779949461375 sim_pfm: -350.32218716363985
episode: 440 training return: -394.2110135316034
episode: 441 training return: -412.3176474172587
episode: 442 training return: -437.7489303271187
episode: 443 training return: -415.0884041075014
epoch: 111 test_true_pfm: 872.4677907843007 sim_pfm: -323.8066362728241
episode: 444 training return: -404.98570110731316
episode: 445 training return: -419.91642036721345
episode: 446 training return: -375.5292314199007
episode: 447 training return: -387.43754663824274
epoch: 112 test_true_pfm: 985.6467830865523 sim_pfm: -266.3905750652205
episode: 448 training return: -393.7581585251561
episode: 449 training return: -450.61579124560905
episode: 450 training return: -396.8308514019397
episode: 451 training return: -388.2347369097391
epoch: 113 test_true_pfm: 922.1795815059312 sim_pfm: -282.73917628368343
episode: 452 training return: -378.76781864173313
episode: 453 training return: -408.8536043938059
episode: 454 training return: -364.03384447249016
episode: 455 training return: -329.7864693753649
epoch: 114 test_true_pfm: 910.1935107173921 sim_pfm: -294.100293986985
episode: 456 training return: -400.88399682526295
episode: 457 training return: -379.49132172486145
episode: 458 training return: -407.81144438882797
episode: 459 training return: -370.87065869333213
epoch: 115 test_true_pfm: 985.6535096328188 sim_pfm: -256.2425173511874
episode: 460 training return: -382.4149297368004
episode: 461 training return: -372.6944025566879
episode: 462 training return: -384.0816662034008
episode: 463 training return: -330.9805781793607
epoch: 116 test_true_pfm: 978.4311246949537 sim_pfm: -255.0844587870878
episode: 464 training return: -421.58250322807373
episode: 465 training return: -365.6606938664594
episode: 466 training return: -328.0965608380436
episode: 467 training return: -342.9217475477961
epoch: 117 test_true_pfm: 954.5356983087812 sim_pfm: -276.9990173951387
episode: 468 training return: -328.2197212119686
episode: 469 training return: -351.4150280616974
episode: 470 training return: -357.50777403312696
episode: 471 training return: -314.1497863005958
epoch: 118 test_true_pfm: 1066.5173686289252 sim_pfm: -226.2191016661984
episode: 472 training return: -320.0300190949749
episode: 473 training return: -330.1523834105802
episode: 474 training return: -343.2616755616514
episode: 475 training return: -323.6362633818592
epoch: 119 test_true_pfm: 1041.5288687811324 sim_pfm: -231.7084591552674
episode: 476 training return: -339.3441557073147
episode: 477 training return: -383.30211583290856
episode: 478 training return: -361.4233379612617
episode: 479 training return: -334.6348714123349
epoch: 120 test_true_pfm: 1032.6838133860726 sim_pfm: -232.98797614562395
episode: 480 training return: -299.9467641226889
episode: 481 training return: -336.07714000096297
episode: 482 training return: -350.51608611718586
episode: 483 training return: -333.2987065163523
epoch: 121 test_true_pfm: 1021.0938098256116 sim_pfm: -228.81877765298495
episode: 484 training return: -325.2522550209071
episode: 485 training return: -332.66437030066027
episode: 486 training return: -317.56894387537494
episode: 487 training return: -318.53107027447425
epoch: 122 test_true_pfm: 1017.3638855686818 sim_pfm: -227.78964770605128
episode: 488 training return: -352.54600717557446
episode: 489 training return: -313.43222318117574
episode: 490 training return: -330.6180877167409
episode: 491 training return: -311.8808445631654
epoch: 123 test_true_pfm: 980.6667222458263 sim_pfm: -243.36782167243086
episode: 492 training return: -306.3891569882146
episode: 493 training return: -355.3195765074403
episode: 494 training return: -304.95515290470644
episode: 495 training return: -309.945926200342
epoch: 124 test_true_pfm: 1059.1473069035035 sim_pfm: -218.7809296810348
episode: 496 training return: -338.79046169685165
episode: 497 training return: -364.33811956599646
episode: 498 training return: -336.17476652844647
episode: 499 training return: -353.4994539512279
epoch: 125 test_true_pfm: 1073.681512104277 sim_pfm: -228.22021944177826
episode: 500 training return: -292.35233082353585
episode: 501 training return: -316.28800830909984
episode: 502 training return: -282.409629275171
episode: 503 training return: -321.9106193055584
epoch: 126 test_true_pfm: 1149.259691401465 sim_pfm: -178.9265845136321
episode: 504 training return: -327.8815627768069
episode: 505 training return: -340.5956392071957
episode: 506 training return: -252.47798373816912
episode: 507 training return: -335.36423664098373
epoch: 127 test_true_pfm: 1058.7427746173378 sim_pfm: -196.60143567532245
episode: 508 training return: -318.4596126664134
episode: 509 training return: -313.3003986023865
episode: 510 training return: -329.6312893104822
episode: 511 training return: -305.9621643968999
epoch: 128 test_true_pfm: 1106.6165022050543 sim_pfm: -192.10023387612156
episode: 512 training return: -302.7183629017226
episode: 513 training return: -282.0661597032423
episode: 514 training return: -331.0059311503248
episode: 515 training return: -279.7529434969126
epoch: 129 test_true_pfm: 1101.901680026271 sim_pfm: -202.1507308305688
episode: 516 training return: -311.28229362644186
episode: 517 training return: -273.49725212779947
episode: 518 training return: -281.52135656059266
episode: 519 training return: -346.60860041808496
epoch: 130 test_true_pfm: 1083.4719536611087 sim_pfm: -206.49073147572744
episode: 520 training return: -280.3123921787162
episode: 521 training return: -253.05788361289774
episode: 522 training return: -322.8600945190637
episode: 523 training return: -320.85681143976456
epoch: 131 test_true_pfm: 1071.4549966833674 sim_pfm: -203.89939995298346
episode: 524 training return: -277.9342872061211
episode: 525 training return: -295.5658636544873
episode: 526 training return: -285.0531477802424
episode: 527 training return: -268.2715614790255
epoch: 132 test_true_pfm: 1109.1949130000362 sim_pfm: -188.57931394021637
episode: 528 training return: -288.7449429038947
episode: 529 training return: -253.42756851722987
episode: 530 training return: -314.4918250867309
episode: 531 training return: -259.9309053327415
epoch: 133 test_true_pfm: 1123.5694918123158 sim_pfm: -186.7769269488498
episode: 532 training return: -296.58697054942246
episode: 533 training return: -276.9023837379331
episode: 534 training return: -272.41166098961986
episode: 535 training return: -274.1886008714519
epoch: 134 test_true_pfm: 1134.8639237175546 sim_pfm: -183.88619086840063
episode: 536 training return: -290.6224645741283
episode: 537 training return: -266.7459751603524
episode: 538 training return: -282.15831683928457
episode: 539 training return: -275.27228566537923
epoch: 135 test_true_pfm: 1132.2412795696591 sim_pfm: -165.1674847502007
episode: 540 training return: -296.5386290334271
episode: 541 training return: -295.3395453434903
episode: 542 training return: -256.33181086398093
episode: 543 training return: -286.0375853962415
epoch: 136 test_true_pfm: 1133.4936586849 sim_pfm: -197.56028727127196
episode: 544 training return: -288.30577035136207
episode: 545 training return: -247.5646442597522
episode: 546 training return: -267.04450338214195
episode: 547 training return: -269.35644454089544
epoch: 137 test_true_pfm: 1088.3749937834702 sim_pfm: -178.21298034344136
episode: 548 training return: -287.4458963798653
episode: 549 training return: -280.9980927208546
episode: 550 training return: -257.82045743223455
episode: 551 training return: -279.24501062782724
epoch: 138 test_true_pfm: 1091.4131855560142 sim_pfm: -172.4822985932603
episode: 552 training return: -275.70624087107666
episode: 553 training return: -261.7125803014353
episode: 554 training return: -254.6594618246995
episode: 555 training return: -294.13989728670174
epoch: 139 test_true_pfm: 1143.118671671133 sim_pfm: -172.1999566820116
episode: 556 training return: -269.2032791860846
episode: 557 training return: -256.4656726336577
episode: 558 training return: -296.2477609728496
episode: 559 training return: -284.06241340551463
epoch: 140 test_true_pfm: 1159.829949593277 sim_pfm: -162.17714858777347
episode: 560 training return: -257.1468914971843
episode: 561 training return: -252.34529075981524
episode: 562 training return: -222.26336706208906
episode: 563 training return: -249.41635312501117
epoch: 141 test_true_pfm: 1075.985633320582 sim_pfm: -176.61819023590388
episode: 564 training return: -245.1536138277164
episode: 565 training return: -280.4252073811645
episode: 566 training return: -258.77107689799954
episode: 567 training return: -222.7458930270946
epoch: 142 test_true_pfm: 1160.6865837089701 sim_pfm: -158.89829824629976
episode: 568 training return: -303.9345321262766
episode: 569 training return: -254.83660870949367
episode: 570 training return: -271.70238240968393
episode: 571 training return: -282.4389164353277
epoch: 143 test_true_pfm: 1163.029698757084 sim_pfm: -162.39731035687817
episode: 572 training return: -250.68550366858048
episode: 573 training return: -229.38490960161312
episode: 574 training return: -255.5888368591223
episode: 575 training return: -263.5414757365458
epoch: 144 test_true_pfm: 1121.94174589546 sim_pfm: -172.6514105257551
episode: 576 training return: -276.703821672971
episode: 577 training return: -266.09637923881155
episode: 578 training return: -256.4185367522126
episode: 579 training return: -251.3516386670989
epoch: 145 test_true_pfm: 1149.3593938926385 sim_pfm: -165.5627803165616
episode: 580 training return: -249.47237838153214
episode: 581 training return: -242.77519378526964
episode: 582 training return: -245.32481458888267
episode: 583 training return: -264.81461290892344
epoch: 146 test_true_pfm: 1167.3460604138536 sim_pfm: -152.94293300322923
episode: 584 training return: -243.66874438881132
episode: 585 training return: -261.75046100344844
episode: 586 training return: -248.77398424624926
episode: 587 training return: -282.30775195370717
epoch: 147 test_true_pfm: 1178.6547256621425 sim_pfm: -143.8467998431166
episode: 588 training return: -242.69910505672613
episode: 589 training return: -238.50029587541806
episode: 590 training return: -268.2700583836449
episode: 591 training return: -221.97120742790523
epoch: 148 test_true_pfm: 1187.0103248257321 sim_pfm: -153.55439619104345
episode: 592 training return: -252.8498601102565
episode: 593 training return: -256.3591317516882
episode: 594 training return: -205.51925317165762
episode: 595 training return: -233.78933386857145
epoch: 149 test_true_pfm: 1181.1109832181946 sim_pfm: -153.24235310483903
episode: 596 training return: -265.4686256331647
episode: 597 training return: -235.39419665125928
episode: 598 training return: -239.0775318398738
episode: 599 training return: -220.5789434684434
epoch: 150 test_true_pfm: 1146.7036848914072 sim_pfm: -168.35466621033788
