['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'brac', '--traj', 'medium', '--seed', '4', '--data', '100000']
2555.155996785869
episode: 0 training return: tensor(-2522409.7500, device='cuda:0')
episode: 1 training return: tensor(-12799.0713, device='cuda:0')
episode: 2 training return: tensor(-64765500., device='cuda:0')
episode: 3 training return: tensor(-29729.3574, device='cuda:0')
epoch: 1 test_true_pfm: 24.487457469550478
episode: 4 training return: tensor(-10367372., device='cuda:0')
episode: 5 training return: tensor(-31614.8457, device='cuda:0')
episode: 6 training return: tensor(-42369.2383, device='cuda:0')
episode: 7 training return: tensor(-31649.2754, device='cuda:0')
epoch: 2 test_true_pfm: 350.65806961983486
episode: 8 training return: tensor(-7221670.5000, device='cuda:0')
episode: 9 training return: tensor(-933591.2500, device='cuda:0')
episode: 10 training return: tensor(-94847.7109, device='cuda:0')
episode: 11 training return: tensor(-93937.0469, device='cuda:0')
epoch: 3 test_true_pfm: 334.89611621466634
episode: 12 training return: tensor(-95595.7891, device='cuda:0')
episode: 13 training return: tensor(-97288.4609, device='cuda:0')
episode: 14 training return: tensor(-33627.9844, device='cuda:0')
episode: 15 training return: tensor(-97458.9297, device='cuda:0')
epoch: 4 test_true_pfm: -61.31916623343887
episode: 16 training return: tensor(-117483.2500, device='cuda:0')
episode: 17 training return: tensor(-147786.1406, device='cuda:0')
episode: 18 training return: tensor(-82040.5703, device='cuda:0')
episode: 19 training return: tensor(-87227.4531, device='cuda:0')
epoch: 5 test_true_pfm: 95.12053541647124
episode: 20 training return: tensor(-105396.9844, device='cuda:0')
episode: 21 training return: tensor(-104167.0078, device='cuda:0')
episode: 22 training return: tensor(-108635.6016, device='cuda:0')
episode: 23 training return: tensor(-38973.0820, device='cuda:0')
epoch: 6 test_true_pfm: -21.010012966820486
episode: 24 training return: tensor(-46759.8320, device='cuda:0')
episode: 25 training return: tensor(-25597.0840, device='cuda:0')
episode: 26 training return: tensor(-23990.3672, device='cuda:0')
episode: 27 training return: tensor(-1942787.1250, device='cuda:0')
epoch: 7 test_true_pfm: 161.5880158617456
episode: 28 training return: tensor(-2526275.2500, device='cuda:0')
episode: 29 training return: tensor(-20726.6406, device='cuda:0')
episode: 30 training return: tensor(-16103.2236, device='cuda:0')
episode: 31 training return: tensor(-15880.3701, device='cuda:0')
epoch: 8 test_true_pfm: 97.04332908445251
episode: 32 training return: tensor(-13856.6094, device='cuda:0')
episode: 33 training return: tensor(-22897.3535, device='cuda:0')
episode: 34 training return: tensor(-16849.0273, device='cuda:0')
episode: 35 training return: tensor(-18712.7832, device='cuda:0')
epoch: 9 test_true_pfm: 159.82416083786333
episode: 36 training return: tensor(-15935.3369, device='cuda:0')
episode: 37 training return: tensor(-14392.3818, device='cuda:0')
episode: 38 training return: tensor(-15132.8359, device='cuda:0')
episode: 39 training return: tensor(-17783.3828, device='cuda:0')
epoch: 10 test_true_pfm: 102.37427238794426
episode: 40 training return: tensor(-17934.8789, device='cuda:0')
episode: 41 training return: tensor(-16635.9336, device='cuda:0')
episode: 42 training return: tensor(-25004.1699, device='cuda:0')
episode: 43 training return: tensor(-17690.8027, device='cuda:0')
epoch: 11 test_true_pfm: -140.76901134756645
episode: 44 training return: tensor(-15044.7188, device='cuda:0')
episode: 45 training return: tensor(-68017.0469, device='cuda:0')
episode: 46 training return: tensor(-22279.8398, device='cuda:0')
episode: 47 training return: tensor(-118444.6719, device='cuda:0')
epoch: 12 test_true_pfm: 44.80282116014886
episode: 48 training return: tensor(-21863.9707, device='cuda:0')
episode: 49 training return: tensor(-14029.7891, device='cuda:0')
episode: 50 training return: tensor(-54822.3516, device='cuda:0')
episode: 51 training return: tensor(-1.6363e+09, device='cuda:0')
epoch: 13 test_true_pfm: -142.2347803818892
episode: 52 training return: tensor(-14880.2852, device='cuda:0')
episode: 53 training return: tensor(-329832.1875, device='cuda:0')
episode: 54 training return: tensor(-246232.7969, device='cuda:0')
episode: 55 training return: tensor(-198288.5938, device='cuda:0')
epoch: 14 test_true_pfm: 119.9269096875753
episode: 56 training return: tensor(-186371.5469, device='cuda:0')
episode: 57 training return: tensor(-214168.8750, device='cuda:0')
episode: 58 training return: tensor(-196652.1875, device='cuda:0')
episode: 59 training return: tensor(-185431.1094, device='cuda:0')
epoch: 15 test_true_pfm: 134.92947584264527
episode: 60 training return: tensor(-174197.0625, device='cuda:0')
episode: 61 training return: tensor(-12372.9404, device='cuda:0')
episode: 62 training return: tensor(-12219.2842, device='cuda:0')
episode: 63 training return: tensor(-10601.3057, device='cuda:0')
epoch: 16 test_true_pfm: 32.180719673875586
episode: 64 training return: tensor(-17348.0840, device='cuda:0')
episode: 65 training return: tensor(-14645.0869, device='cuda:0')
episode: 66 training return: tensor(-8863.8311, device='cuda:0')
episode: 67 training return: tensor(-8787.9160, device='cuda:0')
epoch: 17 test_true_pfm: 129.46651619041566
episode: 68 training return: tensor(-12518.2305, device='cuda:0')
episode: 69 training return: tensor(-12543.2705, device='cuda:0')
episode: 70 training return: tensor(-10741.9834, device='cuda:0')
episode: 71 training return: tensor(-111489.8750, device='cuda:0')
epoch: 18 test_true_pfm: 104.60478467143058
episode: 72 training return: tensor(-96380.8359, device='cuda:0')
episode: 73 training return: tensor(-35003.9375, device='cuda:0')
episode: 74 training return: tensor(-68356.1328, device='cuda:0')
episode: 75 training return: tensor(-64351.3047, device='cuda:0')
epoch: 19 test_true_pfm: -175.8817203890229
episode: 76 training return: tensor(-11213.4492, device='cuda:0')
episode: 77 training return: tensor(-26375.6367, device='cuda:0')
episode: 78 training return: tensor(-1084515.3750, device='cuda:0')
episode: 79 training return: tensor(-46439.0039, device='cuda:0')
epoch: 20 test_true_pfm: -575.3792666260955
episode: 80 training return: tensor(-24923.6328, device='cuda:0')
episode: 81 training return: tensor(-34822.0078, device='cuda:0')
episode: 82 training return: tensor(-26965.7266, device='cuda:0')
episode: 83 training return: tensor(-60206.6367, device='cuda:0')
epoch: 21 test_true_pfm: -161.71946198079294
episode: 84 training return: tensor(-24623.3984, device='cuda:0')
episode: 85 training return: tensor(-181535.2812, device='cuda:0')
episode: 86 training return: tensor(-20286.6348, device='cuda:0')
episode: 87 training return: tensor(-61191712., device='cuda:0')
epoch: 22 test_true_pfm: -317.82858235451914
episode: 88 training return: tensor(-51005384., device='cuda:0')
episode: 89 training return: tensor(-20874.5859, device='cuda:0')
episode: 90 training return: tensor(-21917.8750, device='cuda:0')
episode: 91 training return: tensor(-18305.5078, device='cuda:0')
epoch: 23 test_true_pfm: 123.5353200766332
episode: 92 training return: tensor(-10216.2139, device='cuda:0')
episode: 93 training return: tensor(-97502.6562, device='cuda:0')
episode: 94 training return: tensor(-31946.9570, device='cuda:0')
episode: 95 training return: tensor(-50309.3672, device='cuda:0')
epoch: 24 test_true_pfm: -334.35788998074685
episode: 96 training return: tensor(-31792.9355, device='cuda:0')
episode: 97 training return: tensor(-14730.1807, device='cuda:0')
episode: 98 training return: tensor(-16478.1680, device='cuda:0')
episode: 99 training return: tensor(-14356.5791, device='cuda:0')
epoch: 25 test_true_pfm: -419.74294301980126
episode: 100 training return: tensor(-44607.4219, device='cuda:0')
episode: 101 training return: tensor(-24817.4043, device='cuda:0')
episode: 102 training return: tensor(-10933.3418, device='cuda:0')
episode: 103 training return: tensor(-9564.6436, device='cuda:0')
epoch: 26 test_true_pfm: -67.0542194166758
episode: 104 training return: tensor(-58202.0156, device='cuda:0')
episode: 105 training return: tensor(-26125.6992, device='cuda:0')
episode: 106 training return: tensor(-40730.6016, device='cuda:0')
episode: 107 training return: tensor(-24576.0527, device='cuda:0')
epoch: 27 test_true_pfm: 96.86407574385936
episode: 108 training return: tensor(-11301.9023, device='cuda:0')
episode: 109 training return: tensor(-134779.9844, device='cuda:0')
episode: 110 training return: tensor(-15150.4307, device='cuda:0')
episode: 111 training return: tensor(-138327.7656, device='cuda:0')
epoch: 28 test_true_pfm: -113.45430426867362
episode: 112 training return: tensor(-171102.9375, device='cuda:0')
episode: 113 training return: tensor(-117005.9766, device='cuda:0')
episode: 114 training return: tensor(-34094.4219, device='cuda:0')
episode: 115 training return: tensor(-213040.0781, device='cuda:0')
epoch: 29 test_true_pfm: -63.421083735854985
episode: 116 training return: tensor(-85563., device='cuda:0')
episode: 117 training return: tensor(-65031.6133, device='cuda:0')
episode: 118 training return: tensor(-4.6251e+09, device='cuda:0')
episode: 119 training return: tensor(-169802.0469, device='cuda:0')
epoch: 30 test_true_pfm: -62.96165580112196
episode: 120 training return: tensor(-66891.5391, device='cuda:0')
episode: 121 training return: tensor(-16450625., device='cuda:0')
episode: 122 training return: tensor(-19928.7910, device='cuda:0')
episode: 123 training return: tensor(-144712.7500, device='cuda:0')
epoch: 31 test_true_pfm: -257.13622418774077
episode: 124 training return: tensor(-148388.3750, device='cuda:0')
episode: 125 training return: tensor(-161014.4375, device='cuda:0')
episode: 126 training return: tensor(-35601196., device='cuda:0')
episode: 127 training return: tensor(-138875.3281, device='cuda:0')
epoch: 32 test_true_pfm: 46.58231122213362
episode: 128 training return: tensor(-68293.0781, device='cuda:0')
episode: 129 training return: tensor(-5998560.5000, device='cuda:0')
episode: 130 training return: tensor(-68087.5547, device='cuda:0')
episode: 131 training return: tensor(-8445941., device='cuda:0')
epoch: 33 test_true_pfm: 58.799016193266645
episode: 132 training return: tensor(-18669.1895, device='cuda:0')
episode: 133 training return: tensor(-21958.4512, device='cuda:0')
episode: 134 training return: tensor(-44265.8164, device='cuda:0')
episode: 135 training return: tensor(-2515629.2500, device='cuda:0')
epoch: 34 test_true_pfm: -335.69036198178685
episode: 136 training return: tensor(-1.1037e+08, device='cuda:0')
episode: 137 training return: tensor(-51426404., device='cuda:0')
episode: 138 training return: tensor(-8729436., device='cuda:0')
episode: 139 training return: tensor(-75179.1094, device='cuda:0')
epoch: 35 test_true_pfm: 147.90631880573827
episode: 140 training return: tensor(-101249.7891, device='cuda:0')
episode: 141 training return: tensor(-440033.2500, device='cuda:0')
episode: 142 training return: tensor(-393545.5000, device='cuda:0')
episode: 143 training return: tensor(-7711336.5000, device='cuda:0')
epoch: 36 test_true_pfm: -115.97778132610897
episode: 144 training return: tensor(-7867885.5000, device='cuda:0')
episode: 145 training return: tensor(-64861.7109, device='cuda:0')
episode: 146 training return: tensor(-58084.1094, device='cuda:0')
episode: 147 training return: tensor(-862953., device='cuda:0')
epoch: 37 test_true_pfm: 25.559205468187088
episode: 148 training return: tensor(-505706.3750, device='cuda:0')
episode: 149 training return: tensor(-701895.3125, device='cuda:0')
episode: 150 training return: tensor(-42240480., device='cuda:0')
episode: 151 training return: tensor(-6.0353e+08, device='cuda:0')
epoch: 38 test_true_pfm: 81.64404398548498
episode: 152 training return: tensor(-5.2917e+08, device='cuda:0')
episode: 153 training return: tensor(-43611300., device='cuda:0')
episode: 154 training return: tensor(-6.7512e+08, device='cuda:0')
episode: 155 training return: tensor(-42400588., device='cuda:0')
epoch: 39 test_true_pfm: 46.878018201261455
episode: 156 training return: tensor(-9.7015e+09, device='cuda:0')
episode: 157 training return: tensor(-43162008., device='cuda:0')
episode: 158 training return: tensor(-495717.6875, device='cuda:0')
episode: 159 training return: tensor(-42206952., device='cuda:0')
epoch: 40 test_true_pfm: 31.62839334793217
episode: 160 training return: tensor(-462394.1250, device='cuda:0')
episode: 161 training return: tensor(-2.3078e+08, device='cuda:0')
episode: 162 training return: tensor(-49628.2891, device='cuda:0')
episode: 163 training return: tensor(-32454986., device='cuda:0')
epoch: 41 test_true_pfm: 106.21272532665557
episode: 164 training return: tensor(-3712357.5000, device='cuda:0')
episode: 165 training return: tensor(-1324693., device='cuda:0')
episode: 166 training return: tensor(-17603808., device='cuda:0')
episode: 167 training return: tensor(-1.8920e+13, device='cuda:0')
epoch: 42 test_true_pfm: 303.16665659138675
episode: 168 training return: tensor(-8685290., device='cuda:0')
episode: 169 training return: tensor(-7.6192e+08, device='cuda:0')
episode: 170 training return: tensor(-33831988., device='cuda:0')
episode: 171 training return: tensor(-259316.6719, device='cuda:0')
epoch: 43 test_true_pfm: 153.4857527850452
episode: 172 training return: tensor(-229800.0938, device='cuda:0')
episode: 173 training return: tensor(-40843.9141, device='cuda:0')
episode: 174 training return: tensor(-50230.3477, device='cuda:0')
episode: 175 training return: tensor(-46516.9688, device='cuda:0')
epoch: 44 test_true_pfm: -15.34689522877448
episode: 176 training return: tensor(-58027.2109, device='cuda:0')
episode: 177 training return: tensor(-45124.4648, device='cuda:0')
episode: 178 training return: tensor(-44821.8047, device='cuda:0')
episode: 179 training return: tensor(-44679.2383, device='cuda:0')
epoch: 45 test_true_pfm: 3.6236512845768147
episode: 180 training return: tensor(-44367.3984, device='cuda:0')
episode: 181 training return: tensor(-47770.6836, device='cuda:0')
episode: 182 training return: tensor(-47991.9531, device='cuda:0')
episode: 183 training return: tensor(-52340.3164, device='cuda:0')
epoch: 46 test_true_pfm: -79.24510097386019
episode: 184 training return: tensor(-10040.0889, device='cuda:0')
episode: 185 training return: tensor(-12193., device='cuda:0')
episode: 186 training return: tensor(-10304.5977, device='cuda:0')
episode: 187 training return: tensor(-192882.3594, device='cuda:0')
epoch: 47 test_true_pfm: -168.00189034071536
episode: 188 training return: tensor(-258138.8281, device='cuda:0')
episode: 189 training return: tensor(-10837.8447, device='cuda:0')
episode: 190 training return: tensor(-10002.7617, device='cuda:0')
episode: 191 training return: tensor(-26693.8125, device='cuda:0')
epoch: 48 test_true_pfm: -30.498892343046265
episode: 192 training return: tensor(-31637.0801, device='cuda:0')
episode: 193 training return: tensor(-9844.2588, device='cuda:0')
episode: 194 training return: tensor(-89888.3828, device='cuda:0')
episode: 195 training return: tensor(-45975.2734, device='cuda:0')
epoch: 49 test_true_pfm: -48.783678350074325
episode: 196 training return: tensor(-533270.6250, device='cuda:0')
episode: 197 training return: tensor(-10118.8672, device='cuda:0')
episode: 198 training return: tensor(-9579.8828, device='cuda:0')
episode: 199 training return: tensor(-21385.8887, device='cuda:0')
epoch: 50 test_true_pfm: -119.8629654908391
episode: 200 training return: tensor(-11159.7764, device='cuda:0')
episode: 201 training return: tensor(-9884.3408, device='cuda:0')
episode: 202 training return: tensor(-9771.6045, device='cuda:0')
episode: 203 training return: tensor(-39635.5352, device='cuda:0')
epoch: 51 test_true_pfm: -306.22879600145166
episode: 204 training return: tensor(-185141.2500, device='cuda:0')
episode: 205 training return: tensor(-413053.0625, device='cuda:0')
episode: 206 training return: tensor(-10727.0225, device='cuda:0')
episode: 207 training return: tensor(-145240.8906, device='cuda:0')
epoch: 52 test_true_pfm: 88.23742767146638
episode: 208 training return: tensor(-270834.9062, device='cuda:0')
episode: 209 training return: tensor(-292732.7500, device='cuda:0')
episode: 210 training return: tensor(-661179.7500, device='cuda:0')
episode: 211 training return: tensor(-91985.8516, device='cuda:0')
epoch: 53 test_true_pfm: 238.0712918685679
episode: 212 training return: tensor(-357568.5625, device='cuda:0')
episode: 213 training return: tensor(-692317.6875, device='cuda:0')
episode: 214 training return: tensor(-345422.7812, device='cuda:0')
episode: 215 training return: tensor(-32413.6270, device='cuda:0')
epoch: 54 test_true_pfm: 210.53467146839287
episode: 216 training return: tensor(-261215.8125, device='cuda:0')
episode: 217 training return: tensor(-460340.3438, device='cuda:0')
episode: 218 training return: tensor(-320811.9375, device='cuda:0')
episode: 219 training return: tensor(-127654.9922, device='cuda:0')
epoch: 55 test_true_pfm: 148.15189968931156
episode: 220 training return: tensor(-337872.9062, device='cuda:0')
episode: 221 training return: tensor(-393089.5312, device='cuda:0')
episode: 222 training return: tensor(-2879518., device='cuda:0')
episode: 223 training return: tensor(-22670882., device='cuda:0')
epoch: 56 test_true_pfm: 530.772921272836
episode: 224 training return: tensor(-137873.2656, device='cuda:0')
episode: 225 training return: tensor(-96169016., device='cuda:0')
episode: 226 training return: tensor(-1676419.3750, device='cuda:0')
episode: 227 training return: tensor(-5362427.5000, device='cuda:0')
epoch: 57 test_true_pfm: 119.22089802495532
episode: 228 training return: tensor(-531849.1875, device='cuda:0')
episode: 229 training return: tensor(-1198893.6250, device='cuda:0')
episode: 230 training return: tensor(-90998576., device='cuda:0')
episode: 231 training return: tensor(-342577.9375, device='cuda:0')
epoch: 58 test_true_pfm: -11.210922059675028
episode: 232 training return: tensor(-95162752., device='cuda:0')
episode: 233 training return: tensor(-2.5004e+08, device='cuda:0')
episode: 234 training return: tensor(-17878.9648, device='cuda:0')
episode: 235 training return: tensor(-12703.0996, device='cuda:0')
epoch: 59 test_true_pfm: -82.37860432484639
episode: 236 training return: tensor(-412898.7500, device='cuda:0')
episode: 237 training return: tensor(-5150.6323, device='cuda:0')
episode: 238 training return: tensor(-2522460.7500, device='cuda:0')
episode: 239 training return: tensor(-1.0376e+08, device='cuda:0')
epoch: 60 test_true_pfm: 26.012176013884016
episode: 240 training return: tensor(-939041.2500, device='cuda:0')
episode: 241 training return: tensor(-72783.2656, device='cuda:0')
episode: 242 training return: tensor(-98864.9375, device='cuda:0')
episode: 243 training return: tensor(-2844291., device='cuda:0')
epoch: 61 test_true_pfm: 424.23921775502663
episode: 244 training return: tensor(-46656932., device='cuda:0')
episode: 245 training return: tensor(-53572.1602, device='cuda:0')
episode: 246 training return: tensor(-90570.7031, device='cuda:0')
episode: 247 training return: tensor(-64185.0898, device='cuda:0')
epoch: 62 test_true_pfm: -95.40843373173408
episode: 248 training return: tensor(-40034.9609, device='cuda:0')
episode: 249 training return: tensor(-429289.8125, device='cuda:0')
episode: 250 training return: tensor(-1794682.2500, device='cuda:0')
episode: 251 training return: tensor(-764902.0625, device='cuda:0')
epoch: 63 test_true_pfm: -222.04504860105308
episode: 252 training return: tensor(-264636.6250, device='cuda:0')
episode: 253 training return: tensor(-345152.3750, device='cuda:0')
episode: 254 training return: tensor(-1001382.9375, device='cuda:0')
episode: 255 training return: tensor(-850113.1875, device='cuda:0')
epoch: 64 test_true_pfm: -111.69354731079251
episode: 256 training return: tensor(-94941.7500, device='cuda:0')
episode: 257 training return: tensor(-1794980.8750, device='cuda:0')
episode: 258 training return: tensor(-719702.7500, device='cuda:0')
episode: 259 training return: tensor(-490143.6250, device='cuda:0')
epoch: 65 test_true_pfm: 44.08938393610311
episode: 260 training return: tensor(-4539904.5000, device='cuda:0')
episode: 261 training return: tensor(-4246942.5000, device='cuda:0')
episode: 262 training return: tensor(-104874.9297, device='cuda:0')
episode: 263 training return: tensor(-143127.2969, device='cuda:0')
epoch: 66 test_true_pfm: -103.47832030306863
episode: 264 training return: tensor(-1875096.6250, device='cuda:0')
episode: 265 training return: tensor(-1828832.1250, device='cuda:0')
episode: 266 training return: tensor(-61494.4375, device='cuda:0')
episode: 267 training return: tensor(-19227.5078, device='cuda:0')
epoch: 67 test_true_pfm: -327.9058953315968
episode: 268 training return: tensor(-222450.3594, device='cuda:0')
episode: 269 training return: tensor(-43403.4414, device='cuda:0')
episode: 270 training return: tensor(-51114.3750, device='cuda:0')
episode: 271 training return: tensor(-60941.6055, device='cuda:0')
epoch: 68 test_true_pfm: 171.83715946187206
episode: 272 training return: tensor(-150509.2969, device='cuda:0')
episode: 273 training return: tensor(-282263.8125, device='cuda:0')
episode: 274 training return: tensor(-38594.2812, device='cuda:0')
episode: 275 training return: tensor(-96927848., device='cuda:0')
epoch: 69 test_true_pfm: 288.89872228450616
episode: 276 training return: tensor(-22737.9180, device='cuda:0')
episode: 277 training return: tensor(-23700.1934, device='cuda:0')
episode: 278 training return: tensor(-3071069.2500, device='cuda:0')
episode: 279 training return: tensor(-16593038., device='cuda:0')
epoch: 70 test_true_pfm: -84.69409935320422
episode: 280 training return: tensor(-29181.7793, device='cuda:0')
episode: 281 training return: tensor(-25772.9980, device='cuda:0')
episode: 282 training return: tensor(-26439.6133, device='cuda:0')
episode: 283 training return: tensor(-23515.2207, device='cuda:0')
epoch: 71 test_true_pfm: -739.6407983407977
episode: 284 training return: tensor(-24508.1270, device='cuda:0')
episode: 285 training return: tensor(-17724.6035, device='cuda:0')
episode: 286 training return: tensor(-16910.7598, device='cuda:0')
episode: 287 training return: tensor(-17229.5918, device='cuda:0')
epoch: 72 test_true_pfm: -345.80143254382875
episode: 288 training return: tensor(-28736.9160, device='cuda:0')
episode: 289 training return: tensor(-17272.1719, device='cuda:0')
episode: 290 training return: tensor(-24265.2305, device='cuda:0')
episode: 291 training return: tensor(-23392.9531, device='cuda:0')
epoch: 73 test_true_pfm: -348.50735598186225
episode: 292 training return: tensor(-27214.2656, device='cuda:0')
episode: 293 training return: tensor(-17007.1777, device='cuda:0')
episode: 294 training return: tensor(-17424.0977, device='cuda:0')
episode: 295 training return: tensor(-314925.9375, device='cuda:0')
epoch: 74 test_true_pfm: -372.59963764507046
episode: 296 training return: tensor(-357529.2500, device='cuda:0')
episode: 297 training return: tensor(-28142.9980, device='cuda:0')
episode: 298 training return: tensor(-34290.2578, device='cuda:0')
episode: 299 training return: tensor(-29771.8223, device='cuda:0')
epoch: 75 test_true_pfm: -256.1484483446921
episode: 300 training return: tensor(-26464.4531, device='cuda:0')
episode: 301 training return: tensor(-28477.9414, device='cuda:0')
episode: 302 training return: tensor(-13208.0928, device='cuda:0')
episode: 303 training return: tensor(-18074.1289, device='cuda:0')
epoch: 76 test_true_pfm: 138.27778834840555
episode: 304 training return: tensor(-21544.5742, device='cuda:0')
episode: 305 training return: tensor(-29133.6055, device='cuda:0')
episode: 306 training return: tensor(-26756.3047, device='cuda:0')
episode: 307 training return: tensor(-26581.5605, device='cuda:0')
epoch: 77 test_true_pfm: -183.1377656498174
episode: 308 training return: tensor(-132454.4062, device='cuda:0')
episode: 309 training return: tensor(-27254.9004, device='cuda:0')
episode: 310 training return: tensor(-16450.3672, device='cuda:0')
episode: 311 training return: tensor(-19915.1230, device='cuda:0')
epoch: 78 test_true_pfm: 88.93947430658902
episode: 312 training return: tensor(-18390.5820, device='cuda:0')
episode: 313 training return: tensor(-19786.7949, device='cuda:0')
episode: 314 training return: tensor(-14140.2744, device='cuda:0')
episode: 315 training return: tensor(-32892.7266, device='cuda:0')
epoch: 79 test_true_pfm: -282.96453169804755
episode: 316 training return: tensor(-30487.2051, device='cuda:0')
episode: 317 training return: tensor(-26200.9551, device='cuda:0')
episode: 318 training return: tensor(-21112.4238, device='cuda:0')
episode: 319 training return: tensor(-29872.4707, device='cuda:0')
epoch: 80 test_true_pfm: -283.7631649415683
episode: 320 training return: tensor(-23445.4395, device='cuda:0')
episode: 321 training return: tensor(-18761.0801, device='cuda:0')
episode: 322 training return: tensor(-18383.9492, device='cuda:0')
episode: 323 training return: tensor(-18707.7070, device='cuda:0')
epoch: 81 test_true_pfm: -130.23317263319242
episode: 324 training return: tensor(-25202.6660, device='cuda:0')
episode: 325 training return: tensor(-18174.8027, device='cuda:0')
episode: 326 training return: tensor(-20905.2188, device='cuda:0')
episode: 327 training return: tensor(-24279.4062, device='cuda:0')
epoch: 82 test_true_pfm: -45.66170505335159
episode: 328 training return: tensor(-24241.0215, device='cuda:0')
episode: 329 training return: tensor(-19720.1543, device='cuda:0')
episode: 330 training return: tensor(-17010.3965, device='cuda:0')
episode: 331 training return: tensor(-24060.9395, device='cuda:0')
epoch: 83 test_true_pfm: -129.52880493096015
episode: 332 training return: tensor(-18788.7793, device='cuda:0')
episode: 333 training return: tensor(-22619.4160, device='cuda:0')
episode: 334 training return: tensor(-20502.0215, device='cuda:0')
episode: 335 training return: tensor(-25240.4336, device='cuda:0')
epoch: 84 test_true_pfm: -132.58429964516952
episode: 336 training return: tensor(-22879.2266, device='cuda:0')
episode: 337 training return: tensor(-4689.0249, device='cuda:0')
episode: 338 training return: tensor(-6778.2437, device='cuda:0')
episode: 339 training return: tensor(-10187.0596, device='cuda:0')
epoch: 85 test_true_pfm: 16.23926374848529
episode: 340 training return: tensor(-23113.4375, device='cuda:0')
episode: 341 training return: tensor(-6709.0435, device='cuda:0')
episode: 342 training return: tensor(-23516.2402, device='cuda:0')
episode: 343 training return: tensor(-10689.7295, device='cuda:0')
epoch: 86 test_true_pfm: -24.98077570462566
episode: 344 training return: tensor(-6386.4580, device='cuda:0')
episode: 345 training return: tensor(-23232.1934, device='cuda:0')
episode: 346 training return: tensor(-20156.9688, device='cuda:0')
episode: 347 training return: tensor(-16279.1826, device='cuda:0')
epoch: 87 test_true_pfm: 152.3553839178652
episode: 348 training return: tensor(-20669.1855, device='cuda:0')
episode: 349 training return: tensor(-40682.1875, device='cuda:0')
episode: 350 training return: tensor(-20406.7227, device='cuda:0')
episode: 351 training return: tensor(-21174.4844, device='cuda:0')
epoch: 88 test_true_pfm: 182.2343940697535
episode: 352 training return: tensor(-16135.6191, device='cuda:0')
episode: 353 training return: tensor(-16063.4385, device='cuda:0')
episode: 354 training return: tensor(-16910.7520, device='cuda:0')
episode: 355 training return: tensor(-26024.1406, device='cuda:0')
epoch: 89 test_true_pfm: 208.11915485846302
episode: 356 training return: tensor(-25360.9395, device='cuda:0')
episode: 357 training return: tensor(-22235.4121, device='cuda:0')
episode: 358 training return: tensor(-23259.2461, device='cuda:0')
episode: 359 training return: tensor(-19986.7617, device='cuda:0')
epoch: 90 test_true_pfm: 48.676364721294014
episode: 360 training return: tensor(-20660.3887, device='cuda:0')
episode: 361 training return: tensor(-19963.7402, device='cuda:0')
episode: 362 training return: tensor(-26864.3281, device='cuda:0')
episode: 363 training return: tensor(-19899.2441, device='cuda:0')
epoch: 91 test_true_pfm: 125.89396126239586
episode: 364 training return: tensor(-19961.7578, device='cuda:0')
episode: 365 training return: tensor(-19863.2891, device='cuda:0')
episode: 366 training return: tensor(-18859.2598, device='cuda:0')
episode: 367 training return: tensor(-19433.5098, device='cuda:0')
epoch: 92 test_true_pfm: 235.5546599196888
episode: 368 training return: tensor(-19757.2734, device='cuda:0')
episode: 369 training return: tensor(-16661.2910, device='cuda:0')
episode: 370 training return: tensor(-16683.5059, device='cuda:0')
episode: 371 training return: tensor(-16651.0078, device='cuda:0')
epoch: 93 test_true_pfm: 116.23237565143386
episode: 372 training return: tensor(-16890.0312, device='cuda:0')
episode: 373 training return: tensor(-20528.7227, device='cuda:0')
episode: 374 training return: tensor(-20234.0293, device='cuda:0')
episode: 375 training return: tensor(-19779.8516, device='cuda:0')
epoch: 94 test_true_pfm: 159.4527950318144
episode: 376 training return: tensor(-19475.7109, device='cuda:0')
episode: 377 training return: tensor(-22369.7754, device='cuda:0')
episode: 378 training return: tensor(-17823.0488, device='cuda:0')
episode: 379 training return: tensor(-27376.4922, device='cuda:0')
epoch: 95 test_true_pfm: 52.169243400709746
episode: 380 training return: tensor(-4954.0576, device='cuda:0')
episode: 381 training return: tensor(-6823.0566, device='cuda:0')
episode: 382 training return: tensor(-20091.4062, device='cuda:0')
episode: 383 training return: tensor(-18474.6387, device='cuda:0')
epoch: 96 test_true_pfm: 211.65365247228883
episode: 384 training return: tensor(-28865.5566, device='cuda:0')
episode: 385 training return: tensor(-21320.5254, device='cuda:0')
episode: 386 training return: tensor(-24282.2168, device='cuda:0')
episode: 387 training return: tensor(-18597.2734, device='cuda:0')
epoch: 97 test_true_pfm: 274.8330388935447
episode: 388 training return: tensor(-17548.6699, device='cuda:0')
episode: 389 training return: tensor(-21807.4355, device='cuda:0')
episode: 390 training return: tensor(-21836.3594, device='cuda:0')
episode: 391 training return: tensor(-19461.4102, device='cuda:0')
epoch: 98 test_true_pfm: 230.7432372671818
episode: 392 training return: tensor(-18476., device='cuda:0')
episode: 393 training return: tensor(-19269.3008, device='cuda:0')
episode: 394 training return: tensor(-18707.9297, device='cuda:0')
episode: 395 training return: tensor(-19377.8945, device='cuda:0')
epoch: 99 test_true_pfm: 205.19200114172543
episode: 396 training return: tensor(-18441.7227, device='cuda:0')
episode: 397 training return: tensor(-19593.1797, device='cuda:0')
episode: 398 training return: tensor(-23123.7324, device='cuda:0')
episode: 399 training return: tensor(-21884.7441, device='cuda:0')
epoch: 100 test_true_pfm: 409.13001329217815
episode: 400 training return: tensor(-11744.9912, device='cuda:0')
episode: 401 training return: tensor(-11482.0312, device='cuda:0')
episode: 402 training return: tensor(-10275.9043, device='cuda:0')
episode: 403 training return: tensor(-24249.4844, device='cuda:0')
epoch: 101 test_true_pfm: -16.500542945404884
episode: 404 training return: tensor(-9684.3672, device='cuda:0')
episode: 405 training return: tensor(-24199.3887, device='cuda:0')
episode: 406 training return: tensor(-21823.4141, device='cuda:0')
episode: 407 training return: tensor(-17493.7188, device='cuda:0')
epoch: 102 test_true_pfm: 234.0047949614257
episode: 408 training return: tensor(-22540.6523, device='cuda:0')
episode: 409 training return: tensor(-10110.7324, device='cuda:0')
episode: 410 training return: tensor(-10140.0254, device='cuda:0')
episode: 411 training return: tensor(-11337.3135, device='cuda:0')
epoch: 103 test_true_pfm: 238.6575373280996
episode: 412 training return: tensor(-10401.8223, device='cuda:0')
episode: 413 training return: tensor(-18277.1621, device='cuda:0')
episode: 414 training return: tensor(-39774.5703, device='cuda:0')
episode: 415 training return: tensor(-18204.0586, device='cuda:0')
epoch: 104 test_true_pfm: 235.31797201153543
episode: 416 training return: tensor(-21095.4863, device='cuda:0')
episode: 417 training return: tensor(-18329.5293, device='cuda:0')
episode: 418 training return: tensor(-29198.2266, device='cuda:0')
episode: 419 training return: tensor(-23776.7090, device='cuda:0')
epoch: 105 test_true_pfm: 318.75911780446336
episode: 420 training return: tensor(-23109.7148, device='cuda:0')
episode: 421 training return: tensor(-15870.8926, device='cuda:0')
episode: 422 training return: tensor(-21177.7852, device='cuda:0')
episode: 423 training return: tensor(-22883.7441, device='cuda:0')
epoch: 106 test_true_pfm: 226.80587901124485
episode: 424 training return: tensor(-15424.9951, device='cuda:0')
episode: 425 training return: tensor(-23157.9023, device='cuda:0')
episode: 426 training return: tensor(-16102.6230, device='cuda:0')
episode: 427 training return: tensor(-13177.7168, device='cuda:0')
epoch: 107 test_true_pfm: -90.15734872190266
episode: 428 training return: tensor(-27479.7793, device='cuda:0')
episode: 429 training return: tensor(-10386.1885, device='cuda:0')
episode: 430 training return: tensor(-691686.9375, device='cuda:0')
episode: 431 training return: tensor(-3311793.7500, device='cuda:0')
epoch: 108 test_true_pfm: -7.709821554106902
episode: 432 training return: tensor(-9.4290e+09, device='cuda:0')
episode: 433 training return: tensor(-5.4697e+16, device='cuda:0')
episode: 434 training return: tensor(-9873638., device='cuda:0')
episode: 435 training return: tensor(-15697.2949, device='cuda:0')
epoch: 109 test_true_pfm: 25.63520659150633
episode: 436 training return: tensor(-15284.6523, device='cuda:0')
episode: 437 training return: tensor(-30416.6367, device='cuda:0')
episode: 438 training return: tensor(-86323608., device='cuda:0')
episode: 439 training return: tensor(-11740098., device='cuda:0')
epoch: 110 test_true_pfm: 181.15997851138192
episode: 440 training return: tensor(-9357.3389, device='cuda:0')
episode: 441 training return: tensor(-283798.5625, device='cuda:0')
episode: 442 training return: tensor(-18079.4082, device='cuda:0')
episode: 443 training return: tensor(-17237.8418, device='cuda:0')
epoch: 111 test_true_pfm: 110.48861618334945
episode: 444 training return: tensor(-145855.0469, device='cuda:0')
episode: 445 training return: tensor(-80994.5938, device='cuda:0')
episode: 446 training return: tensor(-40180.3477, device='cuda:0')
episode: 447 training return: tensor(-32174.7070, device='cuda:0')
epoch: 112 test_true_pfm: -232.4962110275769
episode: 448 training return: tensor(-14902.5156, device='cuda:0')
episode: 449 training return: tensor(-25212.3359, device='cuda:0')
episode: 450 training return: tensor(-10462.4248, device='cuda:0')
episode: 451 training return: tensor(-9243.0244, device='cuda:0')
epoch: 113 test_true_pfm: -92.21784295549158
episode: 452 training return: tensor(-9746.2822, device='cuda:0')
episode: 453 training return: tensor(-10879.9160, device='cuda:0')
episode: 454 training return: tensor(-11086.6182, device='cuda:0')
episode: 455 training return: tensor(-10219.9082, device='cuda:0')
epoch: 114 test_true_pfm: -132.45792953279704
episode: 456 training return: tensor(-10408.8174, device='cuda:0')
episode: 457 training return: tensor(-11028.9785, device='cuda:0')
episode: 458 training return: tensor(-10617.1279, device='cuda:0')
episode: 459 training return: tensor(-20522.4473, device='cuda:0')
epoch: 115 test_true_pfm: -350.39319280407204
episode: 460 training return: tensor(-37645.1016, device='cuda:0')
episode: 461 training return: tensor(-14752.8613, device='cuda:0')
episode: 462 training return: tensor(-10872.2803, device='cuda:0')
episode: 463 training return: tensor(-10609.1006, device='cuda:0')
epoch: 116 test_true_pfm: -79.57786766176305
episode: 464 training return: tensor(-10523.6016, device='cuda:0')
episode: 465 training return: tensor(-14823.2930, device='cuda:0')
episode: 466 training return: tensor(-10456.8320, device='cuda:0')
episode: 467 training return: tensor(-11149.0674, device='cuda:0')
epoch: 117 test_true_pfm: -88.63109436047917
episode: 468 training return: tensor(-10646.1025, device='cuda:0')
episode: 469 training return: tensor(-1532313.1250, device='cuda:0')
episode: 470 training return: tensor(-10594.9375, device='cuda:0')
episode: 471 training return: tensor(-10109.3379, device='cuda:0')
epoch: 118 test_true_pfm: -217.17154932257472
episode: 472 training return: tensor(-26157.2285, device='cuda:0')
episode: 473 training return: tensor(-10841.5801, device='cuda:0')
episode: 474 training return: tensor(-10753.2930, device='cuda:0')
episode: 475 training return: tensor(-11916.2070, device='cuda:0')
epoch: 119 test_true_pfm: -121.99042963934255
episode: 476 training return: tensor(-11198.9346, device='cuda:0')
episode: 477 training return: tensor(-11162.2666, device='cuda:0')
episode: 478 training return: tensor(-10947.7119, device='cuda:0')
episode: 479 training return: tensor(-10414.3281, device='cuda:0')
epoch: 120 test_true_pfm: -88.47711572574308
episode: 480 training return: tensor(-11244.9912, device='cuda:0')
episode: 481 training return: tensor(-9951.5068, device='cuda:0')
episode: 482 training return: tensor(-10817.9541, device='cuda:0')
episode: 483 training return: tensor(-11037.6768, device='cuda:0')
epoch: 121 test_true_pfm: -102.00850480977033
episode: 484 training return: tensor(-11772.5039, device='cuda:0')
episode: 485 training return: tensor(-10343.6865, device='cuda:0')
episode: 486 training return: tensor(-11427.3838, device='cuda:0')
episode: 487 training return: tensor(-8780.7393, device='cuda:0')
epoch: 122 test_true_pfm: -3.2984183672689533
episode: 488 training return: tensor(-13859.5146, device='cuda:0')
episode: 489 training return: tensor(-10793.6963, device='cuda:0')
episode: 490 training return: tensor(-12422.8008, device='cuda:0')
episode: 491 training return: tensor(-10155.3818, device='cuda:0')
epoch: 123 test_true_pfm: -6.949614301104883
episode: 492 training return: tensor(-10478.6699, device='cuda:0')
episode: 493 training return: tensor(-15475.4355, device='cuda:0')
episode: 494 training return: tensor(-10574.4111, device='cuda:0')
episode: 495 training return: tensor(-10089.1211, device='cuda:0')
epoch: 124 test_true_pfm: -111.73266516908552
episode: 496 training return: tensor(-10675.6924, device='cuda:0')
episode: 497 training return: tensor(-10318.6484, device='cuda:0')
episode: 498 training return: tensor(-10697.8613, device='cuda:0')
episode: 499 training return: tensor(-11778.9658, device='cuda:0')
epoch: 125 test_true_pfm: -89.8939767487318
episode: 500 training return: tensor(-10731.3916, device='cuda:0')
episode: 501 training return: tensor(-11207.0889, device='cuda:0')
episode: 502 training return: tensor(-10614.0029, device='cuda:0')
episode: 503 training return: tensor(-10508.5479, device='cuda:0')
epoch: 126 test_true_pfm: -145.1857573500058
episode: 504 training return: tensor(-10279.0889, device='cuda:0')
episode: 505 training return: tensor(-10179.2236, device='cuda:0')
episode: 506 training return: tensor(-10964.4785, device='cuda:0')
episode: 507 training return: tensor(-10796.9600, device='cuda:0')
epoch: 127 test_true_pfm: -118.84566093126314
episode: 508 training return: tensor(-9942.0186, device='cuda:0')
episode: 509 training return: tensor(-10715.4346, device='cuda:0')
episode: 510 training return: tensor(-10372.7148, device='cuda:0')
episode: 511 training return: tensor(-10614.6670, device='cuda:0')
epoch: 128 test_true_pfm: -99.1681861226823
episode: 512 training return: tensor(-10527.0811, device='cuda:0')
episode: 513 training return: tensor(-10486.1611, device='cuda:0')
episode: 514 training return: tensor(-11122.1836, device='cuda:0')
episode: 515 training return: tensor(-11074.5967, device='cuda:0')
epoch: 129 test_true_pfm: -129.605868627193
episode: 516 training return: tensor(-10690.8115, device='cuda:0')
episode: 517 training return: tensor(-7489.4590, device='cuda:0')
episode: 518 training return: tensor(-10425.1670, device='cuda:0')
episode: 519 training return: tensor(-10386.5762, device='cuda:0')
epoch: 130 test_true_pfm: -52.26588656193079
episode: 520 training return: tensor(-15966.0996, device='cuda:0')
episode: 521 training return: tensor(-220174.2500, device='cuda:0')
episode: 522 training return: tensor(-8805.1943, device='cuda:0')
episode: 523 training return: tensor(-10850.4814, device='cuda:0')
epoch: 131 test_true_pfm: 20.74160627074718
episode: 524 training return: tensor(-3747.1716, device='cuda:0')
episode: 525 training return: tensor(-12267.8145, device='cuda:0')
episode: 526 training return: tensor(-4920.3960, device='cuda:0')
episode: 527 training return: tensor(-4466.5371, device='cuda:0')
epoch: 132 test_true_pfm: -15.857356752996822
episode: 528 training return: tensor(-15223.8018, device='cuda:0')
episode: 529 training return: tensor(-13888.0850, device='cuda:0')
episode: 530 training return: tensor(-10277.3877, device='cuda:0')
episode: 531 training return: tensor(-9767.2305, device='cuda:0')
epoch: 133 test_true_pfm: -137.99906549504047
episode: 532 training return: tensor(-12914.8730, device='cuda:0')
episode: 533 training return: tensor(-9930.5879, device='cuda:0')
episode: 534 training return: tensor(-9874.8584, device='cuda:0')
episode: 535 training return: tensor(-11890.8418, device='cuda:0')
epoch: 134 test_true_pfm: -119.35162587832026
episode: 536 training return: tensor(-10116.6357, device='cuda:0')
episode: 537 training return: tensor(-10213.4082, device='cuda:0')
episode: 538 training return: tensor(-10622.2617, device='cuda:0')
episode: 539 training return: tensor(-10634.4707, device='cuda:0')
epoch: 135 test_true_pfm: -120.5708865793922
episode: 540 training return: tensor(-10545.6250, device='cuda:0')
episode: 541 training return: tensor(-17786.5723, device='cuda:0')
episode: 542 training return: tensor(-12171.9473, device='cuda:0')
episode: 543 training return: tensor(-11685.5977, device='cuda:0')
epoch: 136 test_true_pfm: -158.1738233935715
episode: 544 training return: tensor(-10220.1055, device='cuda:0')
episode: 545 training return: tensor(-11057.6465, device='cuda:0')
episode: 546 training return: tensor(-10030.2051, device='cuda:0')
episode: 547 training return: tensor(-10506.2168, device='cuda:0')
epoch: 137 test_true_pfm: -102.5702017127682
episode: 548 training return: tensor(-10678.0244, device='cuda:0')
episode: 549 training return: tensor(-10532.3975, device='cuda:0')
episode: 550 training return: tensor(-10683.6494, device='cuda:0')
episode: 551 training return: tensor(-10407.9297, device='cuda:0')
epoch: 138 test_true_pfm: -122.31183515376159
episode: 552 training return: tensor(-10765.7012, device='cuda:0')
episode: 553 training return: tensor(-10313.8115, device='cuda:0')
episode: 554 training return: tensor(-10131.3633, device='cuda:0')
episode: 555 training return: tensor(-10310.9971, device='cuda:0')
epoch: 139 test_true_pfm: -109.19624638440126
episode: 556 training return: tensor(-9967.8418, device='cuda:0')
episode: 557 training return: tensor(-10305.0977, device='cuda:0')
episode: 558 training return: tensor(-9792.2119, device='cuda:0')
episode: 559 training return: tensor(-10769.1465, device='cuda:0')
epoch: 140 test_true_pfm: -112.54542535011547
episode: 560 training return: tensor(-10133.7295, device='cuda:0')
episode: 561 training return: tensor(-10367.7441, device='cuda:0')
episode: 562 training return: tensor(-10629.1797, device='cuda:0')
episode: 563 training return: tensor(-9985.1289, device='cuda:0')
epoch: 141 test_true_pfm: -72.04331688273932
episode: 564 training return: tensor(-7992.6636, device='cuda:0')
episode: 565 training return: tensor(-9896.7832, device='cuda:0')
episode: 566 training return: tensor(-10576.1143, device='cuda:0')
episode: 567 training return: tensor(-9676.5879, device='cuda:0')
epoch: 142 test_true_pfm: -83.0159113496149
episode: 568 training return: tensor(-9684.7148, device='cuda:0')
episode: 569 training return: tensor(-10708.9531, device='cuda:0')
episode: 570 training return: tensor(-10252.8916, device='cuda:0')
episode: 571 training return: tensor(-9865.9307, device='cuda:0')
epoch: 143 test_true_pfm: -111.97580447168814
episode: 572 training return: tensor(-10726.7285, device='cuda:0')
episode: 573 training return: tensor(-10124.2920, device='cuda:0')
episode: 574 training return: tensor(-10512.3125, device='cuda:0')
episode: 575 training return: tensor(-10032.8545, device='cuda:0')
epoch: 144 test_true_pfm: -116.5383376832832
episode: 576 training return: tensor(-10808.1592, device='cuda:0')
episode: 577 training return: tensor(-9542.5928, device='cuda:0')
episode: 578 training return: tensor(-10871.4766, device='cuda:0')
episode: 579 training return: tensor(-10844.5674, device='cuda:0')
epoch: 145 test_true_pfm: -109.45489761417507
episode: 580 training return: tensor(-9931.1748, device='cuda:0')
episode: 581 training return: tensor(-10503.3633, device='cuda:0')
episode: 582 training return: tensor(-10423.0586, device='cuda:0')
episode: 583 training return: tensor(-11013.4873, device='cuda:0')
epoch: 146 test_true_pfm: -115.61192548783323
episode: 584 training return: tensor(-10628.4375, device='cuda:0')
episode: 585 training return: tensor(-13591.0352, device='cuda:0')
episode: 586 training return: tensor(-11134.8203, device='cuda:0')
episode: 587 training return: tensor(-12096.4043, device='cuda:0')
epoch: 147 test_true_pfm: -126.59412477119923
episode: 588 training return: tensor(-9577.0068, device='cuda:0')
episode: 589 training return: tensor(-11269.7520, device='cuda:0')
episode: 590 training return: tensor(-10704.4062, device='cuda:0')
episode: 591 training return: tensor(-13897.0898, device='cuda:0')
epoch: 148 test_true_pfm: -143.6096720229716
episode: 592 training return: tensor(-12978.1895, device='cuda:0')
episode: 593 training return: tensor(-13548.9932, device='cuda:0')
episode: 594 training return: tensor(-12589.6230, device='cuda:0')
episode: 595 training return: tensor(-11546.9629, device='cuda:0')
epoch: 149 test_true_pfm: -166.88736956776305
episode: 596 training return: tensor(-11779.3965, device='cuda:0')
episode: 597 training return: tensor(-4677.7202, device='cuda:0')
episode: 598 training return: tensor(-8978.3145, device='cuda:0')
episode: 599 training return: tensor(-10165.8018, device='cuda:0')
epoch: 150 test_true_pfm: -130.15514572782138
