['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'brac', '--traj', 'medium', '--seed', '2', '--data', '100000']
1882.618213621298
episode: 0 training return: tensor(-1.4955e+19, device='cuda:0')
episode: 1 training return: tensor(-2.8661e+15, device='cuda:0')
episode: 2 training return: tensor(-1.8916e+14, device='cuda:0')
episode: 3 training return: tensor(-3.6213e+14, device='cuda:0')
epoch: 1 test_true_pfm: -98.26605818298951
episode: 4 training return: tensor(-2.4013e+11, device='cuda:0')
episode: 5 training return: tensor(-6.4308e+14, device='cuda:0')
episode: 6 training return: tensor(-3.1256e+15, device='cuda:0')
episode: 7 training return: tensor(-1.5796e+16, device='cuda:0')
epoch: 2 test_true_pfm: -98.82350179488537
episode: 8 training return: tensor(-1.9056e+15, device='cuda:0')
episode: 9 training return: tensor(-1.1251e+16, device='cuda:0')
episode: 10 training return: tensor(-22545808., device='cuda:0')
episode: 11 training return: tensor(-36092228., device='cuda:0')
epoch: 3 test_true_pfm: -97.82529528208214
episode: 12 training return: tensor(-33088682., device='cuda:0')
episode: 13 training return: tensor(-34389124., device='cuda:0')
episode: 14 training return: tensor(-33477106., device='cuda:0')
episode: 15 training return: tensor(-34946384., device='cuda:0')
epoch: 4 test_true_pfm: -97.44158988672724
episode: 16 training return: tensor(-36324760., device='cuda:0')
episode: 17 training return: tensor(-34188268., device='cuda:0')
episode: 18 training return: tensor(-35161664., device='cuda:0')
episode: 19 training return: tensor(-32149748., device='cuda:0')
epoch: 5 test_true_pfm: -97.30889203487551
episode: 20 training return: tensor(-38658444., device='cuda:0')
episode: 21 training return: tensor(-39271964., device='cuda:0')
episode: 22 training return: tensor(-34307148., device='cuda:0')
episode: 23 training return: tensor(-37668804., device='cuda:0')
epoch: 6 test_true_pfm: -97.40118188037574
episode: 24 training return: tensor(-35495836., device='cuda:0')
episode: 25 training return: tensor(-38692388., device='cuda:0')
episode: 26 training return: tensor(-33422506., device='cuda:0')
episode: 27 training return: tensor(-35648888., device='cuda:0')
epoch: 7 test_true_pfm: -97.42870184841918
episode: 28 training return: tensor(-33870700., device='cuda:0')
episode: 29 training return: tensor(-28407744., device='cuda:0')
episode: 30 training return: tensor(-35229588., device='cuda:0')
episode: 31 training return: tensor(-38842936., device='cuda:0')
epoch: 8 test_true_pfm: -97.12846598317111
episode: 32 training return: tensor(-39823692., device='cuda:0')
episode: 33 training return: tensor(-29334654., device='cuda:0')
episode: 34 training return: tensor(-39715300., device='cuda:0')
episode: 35 training return: tensor(-34349564., device='cuda:0')
epoch: 9 test_true_pfm: -97.27732784473976
episode: 36 training return: tensor(-33902416., device='cuda:0')
episode: 37 training return: tensor(-33422760., device='cuda:0')
episode: 38 training return: tensor(-32488574., device='cuda:0')
episode: 39 training return: tensor(-38034036., device='cuda:0')
epoch: 10 test_true_pfm: -98.77220049059649
episode: 40 training return: tensor(-36869224., device='cuda:0')
episode: 41 training return: tensor(-38584104., device='cuda:0')
episode: 42 training return: tensor(-34047012., device='cuda:0')
episode: 43 training return: tensor(-37331616., device='cuda:0')
epoch: 11 test_true_pfm: -97.64724147288052
episode: 44 training return: tensor(-34151492., device='cuda:0')
episode: 45 training return: tensor(-35555456., device='cuda:0')
episode: 46 training return: tensor(-37823256., device='cuda:0')
episode: 47 training return: tensor(-34151200., device='cuda:0')
epoch: 12 test_true_pfm: -97.47563050861736
episode: 48 training return: tensor(-36901500., device='cuda:0')
episode: 49 training return: tensor(-36241008., device='cuda:0')
episode: 50 training return: tensor(-36455896., device='cuda:0')
episode: 51 training return: tensor(-36178332., device='cuda:0')
epoch: 13 test_true_pfm: -97.63091514679054
episode: 52 training return: tensor(-33066454., device='cuda:0')
episode: 53 training return: tensor(-38305812., device='cuda:0')
episode: 54 training return: tensor(-39256604., device='cuda:0')
episode: 55 training return: tensor(-33818088., device='cuda:0')
epoch: 14 test_true_pfm: -97.62075716113911
episode: 56 training return: tensor(-34627820., device='cuda:0')
episode: 57 training return: tensor(-36543224., device='cuda:0')
episode: 58 training return: tensor(-29865454., device='cuda:0')
episode: 59 training return: tensor(-34657960., device='cuda:0')
epoch: 15 test_true_pfm: -98.51728575730617
episode: 60 training return: tensor(-34798596., device='cuda:0')
episode: 61 training return: tensor(-37687780., device='cuda:0')
episode: 62 training return: tensor(-38523264., device='cuda:0')
episode: 63 training return: tensor(-34173548., device='cuda:0')
epoch: 16 test_true_pfm: -97.7658884980534
episode: 64 training return: tensor(-36999072., device='cuda:0')
episode: 65 training return: tensor(-36771048., device='cuda:0')
episode: 66 training return: tensor(-34466724., device='cuda:0')
episode: 67 training return: tensor(-36889380., device='cuda:0')
epoch: 17 test_true_pfm: -97.99128598587619
episode: 68 training return: tensor(-37597972., device='cuda:0')
episode: 69 training return: tensor(-35375972., device='cuda:0')
episode: 70 training return: tensor(-34912416., device='cuda:0')
episode: 71 training return: tensor(-35633980., device='cuda:0')
epoch: 18 test_true_pfm: -97.53366114122137
episode: 72 training return: tensor(-34731684., device='cuda:0')
episode: 73 training return: tensor(-34336348., device='cuda:0')
episode: 74 training return: tensor(-33633944., device='cuda:0')
episode: 75 training return: tensor(-33918300., device='cuda:0')
epoch: 19 test_true_pfm: -97.47345715613638
episode: 76 training return: tensor(-34633420., device='cuda:0')
episode: 77 training return: tensor(-34568244., device='cuda:0')
episode: 78 training return: tensor(-35706556., device='cuda:0')
episode: 79 training return: tensor(-30151660., device='cuda:0')
epoch: 20 test_true_pfm: -98.19832585387958
episode: 80 training return: tensor(-41102328., device='cuda:0')
episode: 81 training return: tensor(-36595644., device='cuda:0')
episode: 82 training return: tensor(-33840344., device='cuda:0')
episode: 83 training return: tensor(-38439868., device='cuda:0')
epoch: 21 test_true_pfm: -98.00815937271089
episode: 84 training return: tensor(-36081972., device='cuda:0')
episode: 85 training return: tensor(-28696174., device='cuda:0')
episode: 86 training return: tensor(-33605376., device='cuda:0')
episode: 87 training return: tensor(-42468812., device='cuda:0')
epoch: 22 test_true_pfm: -98.28892879945828
episode: 88 training return: tensor(-38728424., device='cuda:0')
episode: 89 training return: tensor(-33902448., device='cuda:0')
episode: 90 training return: tensor(-28298386., device='cuda:0')
episode: 91 training return: tensor(-35753100., device='cuda:0')
epoch: 23 test_true_pfm: -97.24297013377561
episode: 92 training return: tensor(-35851676., device='cuda:0')
episode: 93 training return: tensor(-33424704., device='cuda:0')
episode: 94 training return: tensor(-35213996., device='cuda:0')
episode: 95 training return: tensor(-39210172., device='cuda:0')
epoch: 24 test_true_pfm: -97.91558184752728
episode: 96 training return: tensor(-36145104., device='cuda:0')
episode: 97 training return: tensor(-34315924., device='cuda:0')
episode: 98 training return: tensor(-34111508., device='cuda:0')
episode: 99 training return: tensor(-40014348., device='cuda:0')
epoch: 25 test_true_pfm: -98.49280127165633
episode: 100 training return: tensor(-41051956., device='cuda:0')
episode: 101 training return: tensor(-32774068., device='cuda:0')
episode: 102 training return: tensor(-34255436., device='cuda:0')
episode: 103 training return: tensor(-38505760., device='cuda:0')
epoch: 26 test_true_pfm: -97.16285193750427
episode: 104 training return: tensor(-33698756., device='cuda:0')
episode: 105 training return: tensor(-34830408., device='cuda:0')
episode: 106 training return: tensor(-32946358., device='cuda:0')
episode: 107 training return: tensor(-30869392., device='cuda:0')
epoch: 27 test_true_pfm: -98.1184648996827
episode: 108 training return: tensor(-33289526., device='cuda:0')
episode: 109 training return: tensor(-28496446., device='cuda:0')
episode: 110 training return: tensor(-36954196., device='cuda:0')
episode: 111 training return: tensor(-34195080., device='cuda:0')
epoch: 28 test_true_pfm: -97.9463802242666
episode: 112 training return: tensor(-33964940., device='cuda:0')
episode: 113 training return: tensor(-32643216., device='cuda:0')
episode: 114 training return: tensor(-34764864., device='cuda:0')
episode: 115 training return: tensor(-32986906., device='cuda:0')
epoch: 29 test_true_pfm: -97.51671710287064
episode: 116 training return: tensor(-34130868., device='cuda:0')
episode: 117 training return: tensor(-32387224., device='cuda:0')
episode: 118 training return: tensor(-35030532., device='cuda:0')
episode: 119 training return: tensor(-36871136., device='cuda:0')
epoch: 30 test_true_pfm: -98.21338960352148
episode: 120 training return: tensor(-33995452., device='cuda:0')
episode: 121 training return: tensor(-35222600., device='cuda:0')
episode: 122 training return: tensor(-34311620., device='cuda:0')
episode: 123 training return: tensor(-34715440., device='cuda:0')
epoch: 31 test_true_pfm: -97.83804103775475
episode: 124 training return: tensor(-35913088., device='cuda:0')
episode: 125 training return: tensor(-35981416., device='cuda:0')
episode: 126 training return: tensor(-38776108., device='cuda:0')
episode: 127 training return: tensor(-33913380., device='cuda:0')
epoch: 32 test_true_pfm: -98.23390313625542
episode: 128 training return: tensor(-29716168., device='cuda:0')
episode: 129 training return: tensor(-39582132., device='cuda:0')
episode: 130 training return: tensor(-36607952., device='cuda:0')
episode: 131 training return: tensor(-36547692., device='cuda:0')
epoch: 33 test_true_pfm: -98.08867014994725
episode: 132 training return: tensor(-39095900., device='cuda:0')
episode: 133 training return: tensor(-35558636., device='cuda:0')
episode: 134 training return: tensor(-30414112., device='cuda:0')
episode: 135 training return: tensor(-34340972., device='cuda:0')
epoch: 34 test_true_pfm: -98.42364533993602
episode: 136 training return: tensor(-35075756., device='cuda:0')
episode: 137 training return: tensor(-34422816., device='cuda:0')
episode: 138 training return: tensor(-35288532., device='cuda:0')
episode: 139 training return: tensor(-35231160., device='cuda:0')
epoch: 35 test_true_pfm: -97.72400625754511
episode: 140 training return: tensor(-34193164., device='cuda:0')
episode: 141 training return: tensor(-34750460., device='cuda:0')
episode: 142 training return: tensor(-35246992., device='cuda:0')
episode: 143 training return: tensor(-36552544., device='cuda:0')
epoch: 36 test_true_pfm: -98.19307764036182
episode: 144 training return: tensor(-35297536., device='cuda:0')
episode: 145 training return: tensor(-36329724., device='cuda:0')
episode: 146 training return: tensor(-35895412., device='cuda:0')
episode: 147 training return: tensor(-38123624., device='cuda:0')
epoch: 37 test_true_pfm: -97.95199759759316
episode: 148 training return: tensor(-34593612., device='cuda:0')
episode: 149 training return: tensor(-38055800., device='cuda:0')
episode: 150 training return: tensor(-33311680., device='cuda:0')
episode: 151 training return: tensor(-34891540., device='cuda:0')
epoch: 38 test_true_pfm: -98.38230855076388
episode: 152 training return: tensor(-35851052., device='cuda:0')
episode: 153 training return: tensor(-35907456., device='cuda:0')
episode: 154 training return: tensor(-33004376., device='cuda:0')
episode: 155 training return: tensor(-33934356., device='cuda:0')
epoch: 39 test_true_pfm: -98.137833252356
episode: 156 training return: tensor(-36084756., device='cuda:0')
episode: 157 training return: tensor(-36195168., device='cuda:0')
episode: 158 training return: tensor(-34033964., device='cuda:0')
episode: 159 training return: tensor(-34156592., device='cuda:0')
epoch: 40 test_true_pfm: -97.87433441242581
episode: 160 training return: tensor(-35228960., device='cuda:0')
episode: 161 training return: tensor(-33742400., device='cuda:0')
episode: 162 training return: tensor(-34238060., device='cuda:0')
episode: 163 training return: tensor(-34329120., device='cuda:0')
epoch: 41 test_true_pfm: -98.06662154067288
episode: 164 training return: tensor(-33751948., device='cuda:0')
episode: 165 training return: tensor(-8574197., device='cuda:0')
episode: 166 training return: tensor(-34788552., device='cuda:0')
episode: 167 training return: tensor(-33696780., device='cuda:0')
epoch: 42 test_true_pfm: -97.45014815365158
episode: 168 training return: tensor(-34678060., device='cuda:0')
episode: 169 training return: tensor(-35390636., device='cuda:0')
episode: 170 training return: tensor(-34209792., device='cuda:0')
episode: 171 training return: tensor(-28854740., device='cuda:0')
epoch: 43 test_true_pfm: -98.19745940748949
episode: 172 training return: tensor(-35124324., device='cuda:0')
episode: 173 training return: tensor(-33011958., device='cuda:0')
episode: 174 training return: tensor(-29156886., device='cuda:0')
episode: 175 training return: tensor(-33471690., device='cuda:0')
epoch: 44 test_true_pfm: -98.57110701124832
episode: 176 training return: tensor(-36332148., device='cuda:0')
episode: 177 training return: tensor(-38036332., device='cuda:0')
episode: 178 training return: tensor(-37488808., device='cuda:0')
episode: 179 training return: tensor(-37625372., device='cuda:0')
epoch: 45 test_true_pfm: -98.04663924965253
episode: 180 training return: tensor(-34118740., device='cuda:0')
episode: 181 training return: tensor(-32296126., device='cuda:0')
episode: 182 training return: tensor(-33714392., device='cuda:0')
episode: 183 training return: tensor(-34604508., device='cuda:0')
epoch: 46 test_true_pfm: -97.93972318736239
episode: 184 training return: tensor(-38572932., device='cuda:0')
episode: 185 training return: tensor(-34390764., device='cuda:0')
episode: 186 training return: tensor(-33291610., device='cuda:0')
episode: 187 training return: tensor(-33692124., device='cuda:0')
epoch: 47 test_true_pfm: -98.11025894268403
episode: 188 training return: tensor(-32941796., device='cuda:0')
episode: 189 training return: tensor(-9.8842e+09, device='cuda:0')
episode: 190 training return: tensor(-32346810., device='cuda:0')
episode: 191 training return: tensor(-34510208., device='cuda:0')
epoch: 48 test_true_pfm: -98.00276809634492
episode: 192 training return: tensor(-32672712., device='cuda:0')
episode: 193 training return: tensor(-34372688., device='cuda:0')
episode: 194 training return: tensor(-35246116., device='cuda:0')
episode: 195 training return: tensor(-38481768., device='cuda:0')
epoch: 49 test_true_pfm: -97.98432543361037
episode: 196 training return: tensor(-35870980., device='cuda:0')
episode: 197 training return: tensor(-36342140., device='cuda:0')
episode: 198 training return: tensor(-20537168., device='cuda:0')
episode: 199 training return: tensor(-36887752., device='cuda:0')
epoch: 50 test_true_pfm: -98.31210015356231
episode: 200 training return: tensor(-32857696., device='cuda:0')
episode: 201 training return: tensor(-34656664., device='cuda:0')
episode: 202 training return: tensor(-35489380., device='cuda:0')
episode: 203 training return: tensor(-40487096., device='cuda:0')
epoch: 51 test_true_pfm: -98.12380037349116
episode: 204 training return: tensor(-39480336., device='cuda:0')
episode: 205 training return: tensor(-32895192., device='cuda:0')
episode: 206 training return: tensor(-36403088., device='cuda:0')
episode: 207 training return: tensor(-15018741., device='cuda:0')
epoch: 52 test_true_pfm: -97.9319703658801
episode: 208 training return: tensor(-34829724., device='cuda:0')
episode: 209 training return: tensor(-37823184., device='cuda:0')
episode: 210 training return: tensor(-33513104., device='cuda:0')
episode: 211 training return: tensor(-34110788., device='cuda:0')
epoch: 53 test_true_pfm: -97.58133042777497
episode: 212 training return: tensor(-33019714., device='cuda:0')
episode: 213 training return: tensor(-35049768., device='cuda:0')
episode: 214 training return: tensor(-36789260., device='cuda:0')
episode: 215 training return: tensor(-35828004., device='cuda:0')
epoch: 54 test_true_pfm: -97.45453174876745
episode: 216 training return: tensor(-35809020., device='cuda:0')
episode: 217 training return: tensor(-38829280., device='cuda:0')
episode: 218 training return: tensor(-32895094., device='cuda:0')
episode: 219 training return: tensor(-29286706., device='cuda:0')
epoch: 55 test_true_pfm: -97.92749850042567
episode: 220 training return: tensor(-30631916., device='cuda:0')
episode: 221 training return: tensor(-34201328., device='cuda:0')
episode: 222 training return: tensor(-34550008., device='cuda:0')
episode: 223 training return: tensor(-39132344., device='cuda:0')
epoch: 56 test_true_pfm: -98.2309606821175
episode: 224 training return: tensor(-37522724., device='cuda:0')
episode: 225 training return: tensor(-39162988., device='cuda:0')
episode: 226 training return: tensor(-37637020., device='cuda:0')
episode: 227 training return: tensor(-37829912., device='cuda:0')
epoch: 57 test_true_pfm: -97.8170182158292
episode: 228 training return: tensor(-35809360., device='cuda:0')
episode: 229 training return: tensor(-34466548., device='cuda:0')
episode: 230 training return: tensor(-35260704., device='cuda:0')
episode: 231 training return: tensor(-36675040., device='cuda:0')
epoch: 58 test_true_pfm: -97.83747147285054
episode: 232 training return: tensor(-34369988., device='cuda:0')
episode: 233 training return: tensor(-37517652., device='cuda:0')
episode: 234 training return: tensor(-36566392., device='cuda:0')
episode: 235 training return: tensor(-33089766., device='cuda:0')
epoch: 59 test_true_pfm: -97.84364266564499
episode: 236 training return: tensor(-32918080., device='cuda:0')
episode: 237 training return: tensor(-37219252., device='cuda:0')
episode: 238 training return: tensor(-36604524., device='cuda:0')
episode: 239 training return: tensor(-32524922., device='cuda:0')
epoch: 60 test_true_pfm: -97.90870671260491
episode: 240 training return: tensor(-33363664., device='cuda:0')
episode: 241 training return: tensor(-33405376., device='cuda:0')
episode: 242 training return: tensor(-38789540., device='cuda:0')
episode: 243 training return: tensor(-35905240., device='cuda:0')
epoch: 61 test_true_pfm: -98.12064156886174
episode: 244 training return: tensor(-40805112., device='cuda:0')
episode: 245 training return: tensor(-33535430., device='cuda:0')
episode: 246 training return: tensor(-2.9374e+10, device='cuda:0')
episode: 247 training return: tensor(-36016412., device='cuda:0')
epoch: 62 test_true_pfm: -97.88772099763294
episode: 248 training return: tensor(-33029572., device='cuda:0')
episode: 249 training return: tensor(-34219240., device='cuda:0')
episode: 250 training return: tensor(-36781008., device='cuda:0')
episode: 251 training return: tensor(-33574504., device='cuda:0')
epoch: 63 test_true_pfm: -97.55195061224839
episode: 252 training return: tensor(-35464992., device='cuda:0')
episode: 253 training return: tensor(-36812060., device='cuda:0')
episode: 254 training return: tensor(-36727380., device='cuda:0')
episode: 255 training return: tensor(-41708128., device='cuda:0')
epoch: 64 test_true_pfm: -97.95033228280842
episode: 256 training return: tensor(-34160312., device='cuda:0')
episode: 257 training return: tensor(-25932960., device='cuda:0')
episode: 258 training return: tensor(-35872560., device='cuda:0')
episode: 259 training return: tensor(-33321328., device='cuda:0')
epoch: 65 test_true_pfm: -98.26816870145579
episode: 260 training return: tensor(-35574240., device='cuda:0')
episode: 261 training return: tensor(-35855812., device='cuda:0')
episode: 262 training return: tensor(-1.2391e+10, device='cuda:0')
episode: 263 training return: tensor(-35286508., device='cuda:0')
epoch: 66 test_true_pfm: -97.83093402634681
episode: 264 training return: tensor(-34689468., device='cuda:0')
episode: 265 training return: tensor(-34066808., device='cuda:0')
episode: 266 training return: tensor(-33815768., device='cuda:0')
episode: 267 training return: tensor(-35166272., device='cuda:0')
epoch: 67 test_true_pfm: -97.89751295055828
episode: 268 training return: tensor(-33805236., device='cuda:0')
episode: 269 training return: tensor(-35097352., device='cuda:0')
episode: 270 training return: tensor(-34274680., device='cuda:0')
episode: 271 training return: tensor(-38525296., device='cuda:0')
epoch: 68 test_true_pfm: -98.20323473945916
episode: 272 training return: tensor(-33912012., device='cuda:0')
episode: 273 training return: tensor(-37147416., device='cuda:0')
episode: 274 training return: tensor(-36140280., device='cuda:0')
episode: 275 training return: tensor(-32684258., device='cuda:0')
epoch: 69 test_true_pfm: -97.99338175918575
episode: 276 training return: tensor(-32416136., device='cuda:0')
episode: 277 training return: tensor(-34410328., device='cuda:0')
episode: 278 training return: tensor(-36780088., device='cuda:0')
episode: 279 training return: tensor(-33516204., device='cuda:0')
epoch: 70 test_true_pfm: -98.24049306222709
episode: 280 training return: tensor(-39343596., device='cuda:0')
episode: 281 training return: tensor(-29128268., device='cuda:0')
episode: 282 training return: tensor(-34827560., device='cuda:0')
episode: 283 training return: tensor(-35105028., device='cuda:0')
epoch: 71 test_true_pfm: -97.96904543132253
episode: 284 training return: tensor(-32252508., device='cuda:0')
episode: 285 training return: tensor(-32233084., device='cuda:0')
episode: 286 training return: tensor(-7.6975e+15, device='cuda:0')
episode: 287 training return: tensor(-33658752., device='cuda:0')
epoch: 72 test_true_pfm: -98.51700604341589
episode: 288 training return: tensor(-33559224., device='cuda:0')
episode: 289 training return: tensor(-36435644., device='cuda:0')
episode: 290 training return: tensor(-34464788., device='cuda:0')
episode: 291 training return: tensor(-34854108., device='cuda:0')
epoch: 73 test_true_pfm: -97.41561377130847
episode: 292 training return: tensor(-33735620., device='cuda:0')
episode: 293 training return: tensor(-36594916., device='cuda:0')
episode: 294 training return: tensor(-37590692., device='cuda:0')
episode: 295 training return: tensor(-40689336., device='cuda:0')
epoch: 74 test_true_pfm: -97.6098932929062
episode: 296 training return: tensor(-37083064., device='cuda:0')
episode: 297 training return: tensor(-32554158., device='cuda:0')
episode: 298 training return: tensor(-36700244., device='cuda:0')
episode: 299 training return: tensor(-35018060., device='cuda:0')
epoch: 75 test_true_pfm: -97.48289162018041
episode: 300 training return: tensor(-32675878., device='cuda:0')
episode: 301 training return: tensor(-36108872., device='cuda:0')
episode: 302 training return: tensor(-32563188., device='cuda:0')
episode: 303 training return: tensor(-34107844., device='cuda:0')
epoch: 76 test_true_pfm: -97.73953462274817
episode: 304 training return: tensor(-33875220., device='cuda:0')
episode: 305 training return: tensor(-35901928., device='cuda:0')
episode: 306 training return: tensor(-33281646., device='cuda:0')
episode: 307 training return: tensor(-34335188., device='cuda:0')
epoch: 77 test_true_pfm: -98.31528335001053
episode: 308 training return: tensor(-36891636., device='cuda:0')
episode: 309 training return: tensor(-33717512., device='cuda:0')
episode: 310 training return: tensor(-35388256., device='cuda:0')
episode: 311 training return: tensor(-33004676., device='cuda:0')
epoch: 78 test_true_pfm: -97.78482225036775
episode: 312 training return: tensor(-32971320., device='cuda:0')
episode: 313 training return: tensor(-33956168., device='cuda:0')
episode: 314 training return: tensor(-36466692., device='cuda:0')
episode: 315 training return: tensor(-41097332., device='cuda:0')
epoch: 79 test_true_pfm: -98.47878243685079
episode: 316 training return: tensor(-38503680., device='cuda:0')
episode: 317 training return: tensor(-35850208., device='cuda:0')
episode: 318 training return: tensor(-36894208., device='cuda:0')
episode: 319 training return: tensor(-38137880., device='cuda:0')
epoch: 80 test_true_pfm: -98.22482736310633
episode: 320 training return: tensor(-37125300., device='cuda:0')
episode: 321 training return: tensor(-34440628., device='cuda:0')
episode: 322 training return: tensor(-35176804., device='cuda:0')
episode: 323 training return: tensor(-39460472., device='cuda:0')
epoch: 81 test_true_pfm: -97.97131810895219
episode: 324 training return: tensor(-35452056., device='cuda:0')
episode: 325 training return: tensor(-36417476., device='cuda:0')
episode: 326 training return: tensor(-36692760., device='cuda:0')
episode: 327 training return: tensor(-34938340., device='cuda:0')
epoch: 82 test_true_pfm: -98.01975596860689
episode: 328 training return: tensor(-34971260., device='cuda:0')
episode: 329 training return: tensor(-38139560., device='cuda:0')
episode: 330 training return: tensor(-34441292., device='cuda:0')
episode: 331 training return: tensor(-38275252., device='cuda:0')
epoch: 83 test_true_pfm: -97.98768175761559
episode: 332 training return: tensor(-35855388., device='cuda:0')
episode: 333 training return: tensor(-39503760., device='cuda:0')
episode: 334 training return: tensor(-33617320., device='cuda:0')
episode: 335 training return: tensor(-33924568., device='cuda:0')
epoch: 84 test_true_pfm: -98.66503548666401
episode: 336 training return: tensor(-36468348., device='cuda:0')
episode: 337 training return: tensor(-33190348., device='cuda:0')
episode: 338 training return: tensor(-35656672., device='cuda:0')
episode: 339 training return: tensor(-35762168., device='cuda:0')
epoch: 85 test_true_pfm: -97.97640472376197
episode: 340 training return: tensor(-35878320., device='cuda:0')
episode: 341 training return: tensor(-34843600., device='cuda:0')
episode: 342 training return: tensor(-36335944., device='cuda:0')
episode: 343 training return: tensor(-2.7865e+12, device='cuda:0')
epoch: 86 test_true_pfm: -97.67565623575985
episode: 344 training return: tensor(-34038720., device='cuda:0')
episode: 345 training return: tensor(-34585704., device='cuda:0')
episode: 346 training return: tensor(-33497162., device='cuda:0')
episode: 347 training return: tensor(-35681592., device='cuda:0')
epoch: 87 test_true_pfm: -97.99738388845964
episode: 348 training return: tensor(-35577004., device='cuda:0')
episode: 349 training return: tensor(-33785724., device='cuda:0')
episode: 350 training return: tensor(-15396872., device='cuda:0')
episode: 351 training return: tensor(-41887900., device='cuda:0')
epoch: 88 test_true_pfm: -97.57890756650768
episode: 352 training return: tensor(-33402716., device='cuda:0')
episode: 353 training return: tensor(-36691616., device='cuda:0')
episode: 354 training return: tensor(-36441544., device='cuda:0')
episode: 355 training return: tensor(-41059124., device='cuda:0')
epoch: 89 test_true_pfm: -98.29058232532604
episode: 356 training return: tensor(-35194808., device='cuda:0')
episode: 357 training return: tensor(-35800352., device='cuda:0')
episode: 358 training return: tensor(-37018132., device='cuda:0')
episode: 359 training return: tensor(-38298968., device='cuda:0')
epoch: 90 test_true_pfm: -97.34331102103555
episode: 360 training return: tensor(-35738232., device='cuda:0')
episode: 361 training return: tensor(-41111116., device='cuda:0')
episode: 362 training return: tensor(-37363692., device='cuda:0')
episode: 363 training return: tensor(-33454658., device='cuda:0')
epoch: 91 test_true_pfm: -97.98111655511951
episode: 364 training return: tensor(-38033504., device='cuda:0')
episode: 365 training return: tensor(-35804584., device='cuda:0')
episode: 366 training return: tensor(-33167142., device='cuda:0')
episode: 367 training return: tensor(-38313468., device='cuda:0')
epoch: 92 test_true_pfm: -98.13154936786769
episode: 368 training return: tensor(-34470880., device='cuda:0')
episode: 369 training return: tensor(-35109140., device='cuda:0')
episode: 370 training return: tensor(-33002774., device='cuda:0')
episode: 371 training return: tensor(-33131276., device='cuda:0')
epoch: 93 test_true_pfm: -97.90530063396649
episode: 372 training return: tensor(-40026912., device='cuda:0')
episode: 373 training return: tensor(-38385488., device='cuda:0')
episode: 374 training return: tensor(-34003592., device='cuda:0')
episode: 375 training return: tensor(-33787964., device='cuda:0')
epoch: 94 test_true_pfm: -97.9482529714168
episode: 376 training return: tensor(-34191112., device='cuda:0')
episode: 377 training return: tensor(-37904364., device='cuda:0')
episode: 378 training return: tensor(-35440948., device='cuda:0')
episode: 379 training return: tensor(-35896976., device='cuda:0')
epoch: 95 test_true_pfm: -98.01021744012333
episode: 380 training return: tensor(-29320926., device='cuda:0')
episode: 381 training return: tensor(-32300286., device='cuda:0')
episode: 382 training return: tensor(-35173084., device='cuda:0')
episode: 383 training return: tensor(-36124308., device='cuda:0')
epoch: 96 test_true_pfm: -98.1954326284774
episode: 384 training return: tensor(-37837296., device='cuda:0')
episode: 385 training return: tensor(-38912480., device='cuda:0')
episode: 386 training return: tensor(-38790204., device='cuda:0')
episode: 387 training return: tensor(-33277322., device='cuda:0')
epoch: 97 test_true_pfm: -98.23055948371695
episode: 388 training return: tensor(-34634184., device='cuda:0')
episode: 389 training return: tensor(-33951944., device='cuda:0')
episode: 390 training return: tensor(-34951288., device='cuda:0')
episode: 391 training return: tensor(-37692428., device='cuda:0')
epoch: 98 test_true_pfm: -97.58811885796274
episode: 392 training return: tensor(-38147824., device='cuda:0')
episode: 393 training return: tensor(-33449170., device='cuda:0')
episode: 394 training return: tensor(-33910772., device='cuda:0')
episode: 395 training return: tensor(-37043556., device='cuda:0')
epoch: 99 test_true_pfm: -97.71841059550479
episode: 396 training return: tensor(-34122640., device='cuda:0')
episode: 397 training return: tensor(-38975812., device='cuda:0')
episode: 398 training return: tensor(-33706960., device='cuda:0')
episode: 399 training return: tensor(-28107672., device='cuda:0')
epoch: 100 test_true_pfm: -98.03643186978684
episode: 400 training return: tensor(-32771286., device='cuda:0')
episode: 401 training return: tensor(-39522388., device='cuda:0')
episode: 402 training return: tensor(-30171890., device='cuda:0')
episode: 403 training return: tensor(-32957870., device='cuda:0')
epoch: 101 test_true_pfm: -97.52174856259369
episode: 404 training return: tensor(-34415884., device='cuda:0')
episode: 405 training return: tensor(-36589548., device='cuda:0')
episode: 406 training return: tensor(-31085806., device='cuda:0')
episode: 407 training return: tensor(-33697932., device='cuda:0')
epoch: 102 test_true_pfm: -98.06748971278235
episode: 408 training return: tensor(-39098536., device='cuda:0')
episode: 409 training return: tensor(-37301924., device='cuda:0')
episode: 410 training return: tensor(-9112752., device='cuda:0')
episode: 411 training return: tensor(-32897378., device='cuda:0')
epoch: 103 test_true_pfm: -97.41459652780071
episode: 412 training return: tensor(-33296556., device='cuda:0')
episode: 413 training return: tensor(-33917340., device='cuda:0')
episode: 414 training return: tensor(-40975012., device='cuda:0')
episode: 415 training return: tensor(-34705592., device='cuda:0')
epoch: 104 test_true_pfm: -97.53849496000883
episode: 416 training return: tensor(-36144836., device='cuda:0')
episode: 417 training return: tensor(-38648428., device='cuda:0')
episode: 418 training return: tensor(-37667960., device='cuda:0')
episode: 419 training return: tensor(-34515004., device='cuda:0')
epoch: 105 test_true_pfm: -98.35084035195167
episode: 420 training return: tensor(-34817884., device='cuda:0')
episode: 421 training return: tensor(-30493640., device='cuda:0')
episode: 422 training return: tensor(-35311488., device='cuda:0')
episode: 423 training return: tensor(-34794120., device='cuda:0')
epoch: 106 test_true_pfm: -98.05318738678754
episode: 424 training return: tensor(-38393336., device='cuda:0')
episode: 425 training return: tensor(-35279824., device='cuda:0')
episode: 426 training return: tensor(-33578832., device='cuda:0')
episode: 427 training return: tensor(-35733120., device='cuda:0')
epoch: 107 test_true_pfm: -97.62338820707804
episode: 428 training return: tensor(-33392390., device='cuda:0')
episode: 429 training return: tensor(-37053664., device='cuda:0')
episode: 430 training return: tensor(-33922232., device='cuda:0')
episode: 431 training return: tensor(-35519584., device='cuda:0')
epoch: 108 test_true_pfm: -97.66200270709868
episode: 432 training return: tensor(-34655644., device='cuda:0')
episode: 433 training return: tensor(-38924056., device='cuda:0')
episode: 434 training return: tensor(-35312816., device='cuda:0')
episode: 435 training return: tensor(-38144948., device='cuda:0')
epoch: 109 test_true_pfm: -98.51454029822992
episode: 436 training return: tensor(-30392332., device='cuda:0')
episode: 437 training return: tensor(-33965680., device='cuda:0')
episode: 438 training return: tensor(-34818288., device='cuda:0')
episode: 439 training return: tensor(-33729048., device='cuda:0')
epoch: 110 test_true_pfm: -97.97759843923143
episode: 440 training return: tensor(-34431352., device='cuda:0')
episode: 441 training return: tensor(-35083872., device='cuda:0')
episode: 442 training return: tensor(-35036828., device='cuda:0')
episode: 443 training return: tensor(-38577168., device='cuda:0')
epoch: 111 test_true_pfm: -98.64173673464798
episode: 444 training return: tensor(-35166648., device='cuda:0')
episode: 445 training return: tensor(-32941196., device='cuda:0')
episode: 446 training return: tensor(-34518316., device='cuda:0')
episode: 447 training return: tensor(-38669720., device='cuda:0')
epoch: 112 test_true_pfm: -98.1702667303341
episode: 448 training return: tensor(-38033944., device='cuda:0')
episode: 449 training return: tensor(-33744004., device='cuda:0')
episode: 450 training return: tensor(-28066234., device='cuda:0')
episode: 451 training return: tensor(-33001246., device='cuda:0')
epoch: 113 test_true_pfm: -98.47984150813757
episode: 452 training return: tensor(-37791532., device='cuda:0')
episode: 453 training return: tensor(-33703188., device='cuda:0')
episode: 454 training return: tensor(-39942848., device='cuda:0')
episode: 455 training return: tensor(-36910492., device='cuda:0')
epoch: 114 test_true_pfm: -97.50506466954916
episode: 456 training return: tensor(-36589444., device='cuda:0')
episode: 457 training return: tensor(-35660352., device='cuda:0')
episode: 458 training return: tensor(-6.8885e+12, device='cuda:0')
episode: 459 training return: tensor(-34035728., device='cuda:0')
epoch: 115 test_true_pfm: -97.99420150905358
episode: 460 training return: tensor(-39334668., device='cuda:0')
episode: 461 training return: tensor(-33878748., device='cuda:0')
episode: 462 training return: tensor(-36021784., device='cuda:0')
episode: 463 training return: tensor(-34184036., device='cuda:0')
epoch: 116 test_true_pfm: -98.43124845632447
episode: 464 training return: tensor(-34414888., device='cuda:0')
episode: 465 training return: tensor(-34611004., device='cuda:0')
episode: 466 training return: tensor(-37255084., device='cuda:0')
episode: 467 training return: tensor(-36105728., device='cuda:0')
epoch: 117 test_true_pfm: -97.70955602190445
episode: 468 training return: tensor(-36039504., device='cuda:0')
episode: 469 training return: tensor(-29597470., device='cuda:0')
episode: 470 training return: tensor(-38871036., device='cuda:0')
episode: 471 training return: tensor(-37341588., device='cuda:0')
epoch: 118 test_true_pfm: -97.82722394104921
episode: 472 training return: tensor(-33093438., device='cuda:0')
episode: 473 training return: tensor(-37189912., device='cuda:0')
episode: 474 training return: tensor(-36324272., device='cuda:0')
episode: 475 training return: tensor(-39081132., device='cuda:0')
epoch: 119 test_true_pfm: -98.00750986192611
episode: 476 training return: tensor(-34040272., device='cuda:0')
episode: 477 training return: tensor(-34562060., device='cuda:0')
episode: 478 training return: tensor(-37630144., device='cuda:0')
episode: 479 training return: tensor(-33035454., device='cuda:0')
epoch: 120 test_true_pfm: -97.96082782565769
episode: 480 training return: tensor(-35033640., device='cuda:0')
episode: 481 training return: tensor(-37730888., device='cuda:0')
episode: 482 training return: tensor(-40291416., device='cuda:0')
episode: 483 training return: tensor(-32757266., device='cuda:0')
epoch: 121 test_true_pfm: -97.66455016332652
episode: 484 training return: tensor(-33738804., device='cuda:0')
episode: 485 training return: tensor(-36833092., device='cuda:0')
episode: 486 training return: tensor(-35925048., device='cuda:0')
episode: 487 training return: tensor(-1.4948e+11, device='cuda:0')
epoch: 122 test_true_pfm: -98.10875324368897
episode: 488 training return: tensor(-34568180., device='cuda:0')
episode: 489 training return: tensor(-31545906., device='cuda:0')
episode: 490 training return: tensor(-33918016., device='cuda:0')
episode: 491 training return: tensor(-33571084., device='cuda:0')
epoch: 123 test_true_pfm: -97.79009421785696
episode: 492 training return: tensor(-38767480., device='cuda:0')
episode: 493 training return: tensor(-4.6594e+15, device='cuda:0')
episode: 494 training return: tensor(-36886868., device='cuda:0')
episode: 495 training return: tensor(-33801668., device='cuda:0')
epoch: 124 test_true_pfm: -97.95282566687189
episode: 496 training return: tensor(-34015932., device='cuda:0')
episode: 497 training return: tensor(-2.4621e+11, device='cuda:0')
episode: 498 training return: tensor(-37116312., device='cuda:0')
episode: 499 training return: tensor(-30454932., device='cuda:0')
epoch: 125 test_true_pfm: -98.53436292107214
episode: 500 training return: tensor(-32166848., device='cuda:0')
episode: 501 training return: tensor(-36376840., device='cuda:0')
episode: 502 training return: tensor(-33057976., device='cuda:0')
episode: 503 training return: tensor(-33993696., device='cuda:0')
epoch: 126 test_true_pfm: -97.83108594396504
episode: 504 training return: tensor(-33805248., device='cuda:0')
episode: 505 training return: tensor(-34378628., device='cuda:0')
episode: 506 training return: tensor(-33182676., device='cuda:0')
episode: 507 training return: tensor(-33855452., device='cuda:0')
epoch: 127 test_true_pfm: -98.39985621097095
episode: 508 training return: tensor(-37803484., device='cuda:0')
episode: 509 training return: tensor(-34371932., device='cuda:0')
episode: 510 training return: tensor(-34308404., device='cuda:0')
episode: 511 training return: tensor(-36209424., device='cuda:0')
epoch: 128 test_true_pfm: -97.81678642587929
episode: 512 training return: tensor(-36108100., device='cuda:0')
episode: 513 training return: tensor(-37498636., device='cuda:0')
episode: 514 training return: tensor(-28568694., device='cuda:0')
episode: 515 training return: tensor(-39605712., device='cuda:0')
epoch: 129 test_true_pfm: -98.24428585948529
episode: 516 training return: tensor(-41816300., device='cuda:0')
episode: 517 training return: tensor(-34030592., device='cuda:0')
episode: 518 training return: tensor(-33181984., device='cuda:0')
episode: 519 training return: tensor(-38254108., device='cuda:0')
epoch: 130 test_true_pfm: -98.03991046306032
episode: 520 training return: tensor(-36358884., device='cuda:0')
episode: 521 training return: tensor(-35611024., device='cuda:0')
episode: 522 training return: tensor(-34219176., device='cuda:0')
episode: 523 training return: tensor(-28508224., device='cuda:0')
epoch: 131 test_true_pfm: -98.09851198062438
episode: 524 training return: tensor(-35331608., device='cuda:0')
episode: 525 training return: tensor(-33752752., device='cuda:0')
episode: 526 training return: tensor(-35204956., device='cuda:0')
episode: 527 training return: tensor(-33852304., device='cuda:0')
epoch: 132 test_true_pfm: -97.84765666131732
episode: 528 training return: tensor(-34445640., device='cuda:0')
episode: 529 training return: tensor(-37199648., device='cuda:0')
episode: 530 training return: tensor(-33638480., device='cuda:0')
episode: 531 training return: tensor(-34408500., device='cuda:0')
epoch: 133 test_true_pfm: -97.77445680002664
episode: 532 training return: tensor(-36690280., device='cuda:0')
episode: 533 training return: tensor(-32715618., device='cuda:0')
episode: 534 training return: tensor(-35053396., device='cuda:0')
episode: 535 training return: tensor(-38291496., device='cuda:0')
epoch: 134 test_true_pfm: -98.31222017997321
episode: 536 training return: tensor(-41394240., device='cuda:0')
episode: 537 training return: tensor(-35864472., device='cuda:0')
episode: 538 training return: tensor(-34195968., device='cuda:0')
episode: 539 training return: tensor(-32679440., device='cuda:0')
epoch: 135 test_true_pfm: -98.00112850310518
episode: 540 training return: tensor(-34335060., device='cuda:0')
episode: 541 training return: tensor(-35665280., device='cuda:0')
episode: 542 training return: tensor(-32852076., device='cuda:0')
episode: 543 training return: tensor(-37736708., device='cuda:0')
epoch: 136 test_true_pfm: -98.3577554348319
episode: 544 training return: tensor(-33818888., device='cuda:0')
episode: 545 training return: tensor(-34210884., device='cuda:0')
episode: 546 training return: tensor(-34355112., device='cuda:0')
episode: 547 training return: tensor(-35656896., device='cuda:0')
epoch: 137 test_true_pfm: -98.02401245212606
episode: 548 training return: tensor(-34697872., device='cuda:0')
episode: 549 training return: tensor(-34238988., device='cuda:0')
episode: 550 training return: tensor(-38861460., device='cuda:0')
episode: 551 training return: tensor(-35493472., device='cuda:0')
epoch: 138 test_true_pfm: -98.10154847814958
episode: 552 training return: tensor(-34167280., device='cuda:0')
episode: 553 training return: tensor(-28642562., device='cuda:0')
episode: 554 training return: tensor(-37042996., device='cuda:0')
episode: 555 training return: tensor(-32926628., device='cuda:0')
epoch: 139 test_true_pfm: -97.9531544916804
episode: 556 training return: tensor(-35839320., device='cuda:0')
episode: 557 training return: tensor(-33215722., device='cuda:0')
episode: 558 training return: tensor(-41487200., device='cuda:0')
episode: 559 training return: tensor(-34470752., device='cuda:0')
epoch: 140 test_true_pfm: -97.71403741343612
episode: 560 training return: tensor(-37721972., device='cuda:0')
episode: 561 training return: tensor(-33762100., device='cuda:0')
episode: 562 training return: tensor(-33526704., device='cuda:0')
episode: 563 training return: tensor(-41478436., device='cuda:0')
epoch: 141 test_true_pfm: -98.13204822915166
episode: 564 training return: tensor(-35472924., device='cuda:0')
episode: 565 training return: tensor(-33309284., device='cuda:0')
episode: 566 training return: tensor(-36686376., device='cuda:0')
episode: 567 training return: tensor(-34321540., device='cuda:0')
epoch: 142 test_true_pfm: -97.60900638697723
episode: 568 training return: tensor(-40852720., device='cuda:0')
episode: 569 training return: tensor(-33755428., device='cuda:0')
episode: 570 training return: tensor(-37946012., device='cuda:0')
episode: 571 training return: tensor(-35104772., device='cuda:0')
epoch: 143 test_true_pfm: -97.7316095284454
episode: 572 training return: tensor(-35211448., device='cuda:0')
episode: 573 training return: tensor(-35993140., device='cuda:0')
episode: 574 training return: tensor(-33203054., device='cuda:0')
episode: 575 training return: tensor(-32872990., device='cuda:0')
epoch: 144 test_true_pfm: -98.32761727983423
episode: 576 training return: tensor(-36219204., device='cuda:0')
episode: 577 training return: tensor(-32372972., device='cuda:0')
episode: 578 training return: tensor(-33025576., device='cuda:0')
episode: 579 training return: tensor(-34573088., device='cuda:0')
epoch: 145 test_true_pfm: -98.02124868298283
episode: 580 training return: tensor(-39343864., device='cuda:0')
episode: 581 training return: tensor(-34995448., device='cuda:0')
episode: 582 training return: tensor(-33156244., device='cuda:0')
episode: 583 training return: tensor(-33495708., device='cuda:0')
epoch: 146 test_true_pfm: -98.13420447149257
episode: 584 training return: tensor(-34961716., device='cuda:0')
episode: 585 training return: tensor(-34525348., device='cuda:0')
episode: 586 training return: tensor(-25413520., device='cuda:0')
episode: 587 training return: tensor(-34624564., device='cuda:0')
epoch: 147 test_true_pfm: -98.0490784632683
episode: 588 training return: tensor(-38094440., device='cuda:0')
episode: 589 training return: tensor(-36877072., device='cuda:0')
episode: 590 training return: tensor(-36025424., device='cuda:0')
episode: 591 training return: tensor(-38115836., device='cuda:0')
epoch: 148 test_true_pfm: -97.93771687077839
episode: 592 training return: tensor(-34264376., device='cuda:0')
episode: 593 training return: tensor(-35166060., device='cuda:0')
episode: 594 training return: tensor(-35218804., device='cuda:0')
episode: 595 training return: tensor(-35970636., device='cuda:0')
epoch: 149 test_true_pfm: -98.16667501715004
episode: 596 training return: tensor(-29153982., device='cuda:0')
episode: 597 training return: tensor(-32481160., device='cuda:0')
episode: 598 training return: tensor(-28412648., device='cuda:0')
episode: 599 training return: tensor(-36498768., device='cuda:0')
epoch: 150 test_true_pfm: -97.60314249003557
