['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '3']
episode: 0 training return: tensor(-628.1969, device='cuda:0')
episode: 1 training return: tensor(-635.2560, device='cuda:0')
episode: 2 training return: tensor(-683.3483, device='cuda:0')
episode: 3 training return: tensor(-641.3942, device='cuda:0')
epoch: 1 test_true_pfm: -91.32369470996521 sim_pfm: -675.019148071607
episode: 4 training return: tensor(-605.8599, device='cuda:0')
episode: 5 training return: tensor(-726.3041, device='cuda:0')
episode: 6 training return: tensor(-666.1434, device='cuda:0')
episode: 7 training return: tensor(-583.8454, device='cuda:0')
epoch: 2 test_true_pfm: 36.370012130415425 sim_pfm: -497.20478804417263
episode: 8 training return: tensor(-636.0237, device='cuda:0')
episode: 9 training return: tensor(-699.9133, device='cuda:0')
episode: 10 training return: tensor(-651.9714, device='cuda:0')
episode: 11 training return: tensor(-644.1349, device='cuda:0')
epoch: 3 test_true_pfm: 89.49092957250251 sim_pfm: -710.0411947748313
episode: 12 training return: tensor(-619.7957, device='cuda:0')
episode: 13 training return: tensor(-582.3257, device='cuda:0')
episode: 14 training return: tensor(-569.7712, device='cuda:0')
episode: 15 training return: tensor(-603.0869, device='cuda:0')
epoch: 4 test_true_pfm: 124.82719655651196 sim_pfm: -604.1923390752636
episode: 16 training return: tensor(-658.4673, device='cuda:0')
episode: 17 training return: tensor(-616.1136, device='cuda:0')
episode: 18 training return: tensor(-679.2241, device='cuda:0')
episode: 19 training return: tensor(-661.3121, device='cuda:0')
epoch: 5 test_true_pfm: -325.8657834290671 sim_pfm: -338.31313071063295
episode: 20 training return: tensor(-639.1140, device='cuda:0')
episode: 21 training return: tensor(-501.2264, device='cuda:0')
episode: 22 training return: tensor(-428.2669, device='cuda:0')
episode: 23 training return: tensor(-530.6734, device='cuda:0')
epoch: 6 test_true_pfm: 6.470242447241239 sim_pfm: -688.3955961217483
episode: 24 training return: tensor(-643.1524, device='cuda:0')
episode: 25 training return: tensor(-609.9457, device='cuda:0')
episode: 26 training return: tensor(-692.2685, device='cuda:0')
episode: 27 training return: tensor(-472.1375, device='cuda:0')
epoch: 7 test_true_pfm: 53.2957051021659 sim_pfm: -627.4091338713964
episode: 28 training return: tensor(-568.4126, device='cuda:0')
episode: 29 training return: tensor(-589.2264, device='cuda:0')
episode: 30 training return: tensor(-532.6334, device='cuda:0')
episode: 31 training return: tensor(-476.5648, device='cuda:0')
epoch: 8 test_true_pfm: 104.4393007881689 sim_pfm: -364.2442389804249
episode: 32 training return: tensor(-560.6356, device='cuda:0')
episode: 33 training return: tensor(-703.9047, device='cuda:0')
episode: 34 training return: tensor(-488.6682, device='cuda:0')
episode: 35 training return: tensor(-687.7664, device='cuda:0')
epoch: 9 test_true_pfm: 172.07055527425197 sim_pfm: -652.7206649182286
episode: 36 training return: tensor(-680.6907, device='cuda:0')
episode: 37 training return: tensor(-688.5816, device='cuda:0')
episode: 38 training return: tensor(-521.7061, device='cuda:0')
episode: 39 training return: tensor(-663.9738, device='cuda:0')
epoch: 10 test_true_pfm: 197.95245060531576 sim_pfm: -610.4329773500795
episode: 40 training return: tensor(-490.1949, device='cuda:0')
episode: 41 training return: tensor(-646.6736, device='cuda:0')
episode: 42 training return: tensor(-630.2800, device='cuda:0')
episode: 43 training return: tensor(-632.8596, device='cuda:0')
epoch: 11 test_true_pfm: 104.80640990003462 sim_pfm: -635.760477445942
episode: 44 training return: tensor(-654.9353, device='cuda:0')
episode: 45 training return: tensor(-699.3652, device='cuda:0')
episode: 46 training return: tensor(-680.6409, device='cuda:0')
episode: 47 training return: tensor(-630.3896, device='cuda:0')
epoch: 12 test_true_pfm: -9.810495666736236 sim_pfm: -428.7906661393742
episode: 48 training return: tensor(-634.8762, device='cuda:0')
episode: 49 training return: tensor(-523.0327, device='cuda:0')
episode: 50 training return: tensor(-618.2040, device='cuda:0')
episode: 51 training return: tensor(-536.3506, device='cuda:0')
epoch: 13 test_true_pfm: 229.1818300230534 sim_pfm: -504.38203035248443
episode: 52 training return: tensor(-540.5102, device='cuda:0')
episode: 53 training return: tensor(-552.2745, device='cuda:0')
episode: 54 training return: tensor(-515.9748, device='cuda:0')
episode: 55 training return: tensor(-565.0151, device='cuda:0')
epoch: 14 test_true_pfm: 131.07184601693731 sim_pfm: -642.0835983629028
episode: 56 training return: tensor(-542.4567, device='cuda:0')
episode: 57 training return: tensor(-544.7291, device='cuda:0')
episode: 58 training return: tensor(-561.7775, device='cuda:0')
episode: 59 training return: tensor(-492.9102, device='cuda:0')
epoch: 15 test_true_pfm: 235.55038598867654 sim_pfm: -618.1778602316821
episode: 60 training return: tensor(-521.3453, device='cuda:0')
episode: 61 training return: tensor(-528.6613, device='cuda:0')
episode: 62 training return: tensor(-486.3082, device='cuda:0')
episode: 63 training return: tensor(-545.2416, device='cuda:0')
epoch: 16 test_true_pfm: 146.5635958224855 sim_pfm: -507.9479060360075
episode: 64 training return: tensor(-551.9720, device='cuda:0')
episode: 65 training return: tensor(-528.2088, device='cuda:0')
episode: 66 training return: tensor(-475.1653, device='cuda:0')
episode: 67 training return: tensor(-450.7769, device='cuda:0')
epoch: 17 test_true_pfm: 347.8414627703268 sim_pfm: -468.5133413599494
episode: 68 training return: tensor(-442.0147, device='cuda:0')
episode: 69 training return: tensor(-466.8344, device='cuda:0')
episode: 70 training return: tensor(-476.8826, device='cuda:0')
episode: 71 training return: tensor(-502.5724, device='cuda:0')
epoch: 18 test_true_pfm: 159.8375951082849 sim_pfm: -510.25513270268374
episode: 72 training return: tensor(-438.9466, device='cuda:0')
episode: 73 training return: tensor(-426.2262, device='cuda:0')
episode: 74 training return: tensor(-469.6434, device='cuda:0')
episode: 75 training return: tensor(-496.2981, device='cuda:0')
epoch: 19 test_true_pfm: -34.93131810491936 sim_pfm: -496.1867404625712
episode: 76 training return: tensor(-429.4226, device='cuda:0')
episode: 77 training return: tensor(-465.5594, device='cuda:0')
episode: 78 training return: tensor(-460.4452, device='cuda:0')
episode: 79 training return: tensor(-424.1029, device='cuda:0')
epoch: 20 test_true_pfm: 239.4226572900341 sim_pfm: -420.9741368570637
episode: 80 training return: tensor(-446.0674, device='cuda:0')
episode: 81 training return: tensor(-403.9672, device='cuda:0')
episode: 82 training return: tensor(-589.6079, device='cuda:0')
episode: 83 training return: tensor(-454.0656, device='cuda:0')
epoch: 21 test_true_pfm: 500.44023496251384 sim_pfm: -399.25294096721336
episode: 84 training return: tensor(-458.8158, device='cuda:0')
episode: 85 training return: tensor(-473.1144, device='cuda:0')
episode: 86 training return: tensor(-428.3019, device='cuda:0')
episode: 87 training return: tensor(-428.9687, device='cuda:0')
epoch: 22 test_true_pfm: 227.65015080488442 sim_pfm: -503.7342075179331
episode: 88 training return: tensor(-429.1273, device='cuda:0')
episode: 89 training return: tensor(-453.5741, device='cuda:0')
episode: 90 training return: tensor(-474.8179, device='cuda:0')
episode: 91 training return: tensor(-439.8651, device='cuda:0')
epoch: 23 test_true_pfm: 460.537684276706 sim_pfm: -402.6037313392541
episode: 92 training return: tensor(-475.2120, device='cuda:0')
episode: 93 training return: tensor(-399.4919, device='cuda:0')
episode: 94 training return: tensor(-453.2975, device='cuda:0')
episode: 95 training return: tensor(-379.5638, device='cuda:0')
epoch: 24 test_true_pfm: 450.6816134032513 sim_pfm: -364.7996862921864
episode: 96 training return: tensor(-476.7858, device='cuda:0')
episode: 97 training return: tensor(-393.9173, device='cuda:0')
episode: 98 training return: tensor(-430.8101, device='cuda:0')
episode: 99 training return: tensor(-413.9997, device='cuda:0')
epoch: 25 test_true_pfm: 499.31601821916115 sim_pfm: -377.0912677294594
episode: 100 training return: tensor(-408.9926, device='cuda:0')
episode: 101 training return: tensor(-420.5061, device='cuda:0')
episode: 102 training return: tensor(-404.5436, device='cuda:0')
episode: 103 training return: tensor(-473.4767, device='cuda:0')
epoch: 26 test_true_pfm: 315.720229517578 sim_pfm: -402.97694605387125
episode: 104 training return: tensor(-439.6193, device='cuda:0')
episode: 105 training return: tensor(-431.4447, device='cuda:0')
episode: 106 training return: tensor(-414.8888, device='cuda:0')
episode: 107 training return: tensor(-431.3694, device='cuda:0')
epoch: 27 test_true_pfm: 721.5616257634579 sim_pfm: -356.1211771032249
episode: 108 training return: tensor(-448.4630, device='cuda:0')
episode: 109 training return: tensor(-402.6865, device='cuda:0')
episode: 110 training return: tensor(-472.7597, device='cuda:0')
episode: 111 training return: tensor(-404.3104, device='cuda:0')
epoch: 28 test_true_pfm: 561.1569834901832 sim_pfm: -379.68875114937936
episode: 112 training return: tensor(-445.1414, device='cuda:0')
episode: 113 training return: tensor(-441.5995, device='cuda:0')
episode: 114 training return: tensor(-401.4313, device='cuda:0')
episode: 115 training return: tensor(-434.9800, device='cuda:0')
epoch: 29 test_true_pfm: 334.44975098888335 sim_pfm: -374.19428013356327
episode: 116 training return: tensor(-427.7193, device='cuda:0')
episode: 117 training return: tensor(-434.6707, device='cuda:0')
episode: 118 training return: tensor(-461.4114, device='cuda:0')
episode: 119 training return: tensor(-379.4059, device='cuda:0')
epoch: 30 test_true_pfm: 675.4716685594872 sim_pfm: -300.074097738446
episode: 120 training return: tensor(-436.4263, device='cuda:0')
episode: 121 training return: tensor(-414.2845, device='cuda:0')
episode: 122 training return: tensor(-426.9268, device='cuda:0')
episode: 123 training return: tensor(-386.8142, device='cuda:0')
epoch: 31 test_true_pfm: 587.929685141214 sim_pfm: -345.9448390167672
episode: 124 training return: tensor(-441.3411, device='cuda:0')
episode: 125 training return: tensor(-470.1046, device='cuda:0')
episode: 126 training return: tensor(-455.9412, device='cuda:0')
episode: 127 training return: tensor(-411.3916, device='cuda:0')
epoch: 32 test_true_pfm: 619.7326328983651 sim_pfm: -338.71898565090186
episode: 128 training return: tensor(-421.5902, device='cuda:0')
episode: 129 training return: tensor(-420.4210, device='cuda:0')
episode: 130 training return: tensor(-450.0791, device='cuda:0')
episode: 131 training return: tensor(-449.7662, device='cuda:0')
epoch: 33 test_true_pfm: 412.36782125211647 sim_pfm: -408.2556560660596
episode: 132 training return: tensor(-412.5204, device='cuda:0')
episode: 133 training return: tensor(-452.7198, device='cuda:0')
episode: 134 training return: tensor(-416.3093, device='cuda:0')
episode: 135 training return: tensor(-467.1970, device='cuda:0')
epoch: 34 test_true_pfm: 820.4550596369703 sim_pfm: -307.97351360220154
episode: 136 training return: tensor(-743.4878, device='cuda:0')
episode: 137 training return: tensor(-438.1502, device='cuda:0')
episode: 138 training return: tensor(-407.5938, device='cuda:0')
episode: 139 training return: tensor(-423.0687, device='cuda:0')
epoch: 35 test_true_pfm: 594.5813032674569 sim_pfm: -376.8434103058341
episode: 140 training return: tensor(-450.3445, device='cuda:0')
episode: 141 training return: tensor(-387.0011, device='cuda:0')
episode: 142 training return: tensor(-453.6123, device='cuda:0')
episode: 143 training return: tensor(-418.0177, device='cuda:0')
epoch: 36 test_true_pfm: 532.5418012865715 sim_pfm: -362.40176720311865
episode: 144 training return: tensor(-418.5547, device='cuda:0')
episode: 145 training return: tensor(-401.2404, device='cuda:0')
episode: 146 training return: tensor(-409.1923, device='cuda:0')
episode: 147 training return: tensor(-425.4573, device='cuda:0')
epoch: 37 test_true_pfm: 526.1805130007211 sim_pfm: -359.5957636819997
episode: 148 training return: tensor(-414.2509, device='cuda:0')
episode: 149 training return: tensor(-449.0504, device='cuda:0')
episode: 150 training return: tensor(-372.1725, device='cuda:0')
episode: 151 training return: tensor(-404.5251, device='cuda:0')
epoch: 38 test_true_pfm: 392.691769049917 sim_pfm: -345.3774638582933
episode: 152 training return: tensor(-430.4026, device='cuda:0')
episode: 153 training return: tensor(-406.2112, device='cuda:0')
episode: 154 training return: tensor(-497.9978, device='cuda:0')
episode: 155 training return: tensor(-418.0405, device='cuda:0')
epoch: 39 test_true_pfm: 462.875146345927 sim_pfm: -363.0087504134378
episode: 156 training return: tensor(-410.7964, device='cuda:0')
episode: 157 training return: tensor(-458.2581, device='cuda:0')
episode: 158 training return: tensor(-422.4410, device='cuda:0')
episode: 159 training return: tensor(-426.0192, device='cuda:0')
epoch: 40 test_true_pfm: 437.86494752675867 sim_pfm: -360.3231045470845
episode: 160 training return: tensor(-376.4374, device='cuda:0')
episode: 161 training return: tensor(-450.6439, device='cuda:0')
episode: 162 training return: tensor(-380.1451, device='cuda:0')
episode: 163 training return: tensor(-421.6912, device='cuda:0')
epoch: 41 test_true_pfm: 521.9834999261316 sim_pfm: -344.6685291423928
episode: 164 training return: tensor(-410.9737, device='cuda:0')
episode: 165 training return: tensor(-383.1938, device='cuda:0')
episode: 166 training return: tensor(-393.0885, device='cuda:0')
episode: 167 training return: tensor(-420.5719, device='cuda:0')
epoch: 42 test_true_pfm: 542.3614268200023 sim_pfm: -351.068316517941
episode: 168 training return: tensor(-405.3445, device='cuda:0')
episode: 169 training return: tensor(-412.4308, device='cuda:0')
episode: 170 training return: tensor(-395.8760, device='cuda:0')
episode: 171 training return: tensor(-420.5460, device='cuda:0')
epoch: 43 test_true_pfm: 654.8378241148017 sim_pfm: -317.67162159015425
episode: 172 training return: tensor(-470.0043, device='cuda:0')
episode: 173 training return: tensor(-418.1844, device='cuda:0')
episode: 174 training return: tensor(-423.7688, device='cuda:0')
episode: 175 training return: tensor(-421.2950, device='cuda:0')
epoch: 44 test_true_pfm: 700.9590541752738 sim_pfm: -337.1715361196936
episode: 176 training return: tensor(-415.5657, device='cuda:0')
episode: 177 training return: tensor(-398.4648, device='cuda:0')
episode: 178 training return: tensor(-403.9761, device='cuda:0')
episode: 179 training return: tensor(-386.9082, device='cuda:0')
epoch: 45 test_true_pfm: 552.3805778175581 sim_pfm: -358.07369939393055
episode: 180 training return: tensor(-431.2883, device='cuda:0')
episode: 181 training return: tensor(-371.4656, device='cuda:0')
episode: 182 training return: tensor(-388.6503, device='cuda:0')
episode: 183 training return: tensor(-419.0882, device='cuda:0')
epoch: 46 test_true_pfm: 623.3495945425774 sim_pfm: -343.7768637575985
episode: 184 training return: tensor(-396.9545, device='cuda:0')
episode: 185 training return: tensor(-381.4318, device='cuda:0')
episode: 186 training return: tensor(-356.9362, device='cuda:0')
episode: 187 training return: tensor(-412.2671, device='cuda:0')
epoch: 47 test_true_pfm: 586.528939575962 sim_pfm: -308.6024768583787
episode: 188 training return: tensor(-406.0768, device='cuda:0')
episode: 189 training return: tensor(-372.6925, device='cuda:0')
episode: 190 training return: tensor(-431.9974, device='cuda:0')
episode: 191 training return: tensor(-418.7372, device='cuda:0')
epoch: 48 test_true_pfm: 598.7755793623388 sim_pfm: -339.2792354322252
episode: 192 training return: tensor(-405.4093, device='cuda:0')
episode: 193 training return: tensor(-361.6046, device='cuda:0')
episode: 194 training return: tensor(-423.6613, device='cuda:0')
episode: 195 training return: tensor(-405.5298, device='cuda:0')
epoch: 49 test_true_pfm: 548.0646417023027 sim_pfm: -361.76127798905753
episode: 196 training return: tensor(-411.8676, device='cuda:0')
episode: 197 training return: tensor(-410.9967, device='cuda:0')
episode: 198 training return: tensor(-376.7113, device='cuda:0')
episode: 199 training return: tensor(-428.3571, device='cuda:0')
epoch: 50 test_true_pfm: 524.4887057213756 sim_pfm: -343.7827474070946
episode: 200 training return: tensor(-363.6175, device='cuda:0')
episode: 201 training return: tensor(-363.2612, device='cuda:0')
episode: 202 training return: tensor(-384.3473, device='cuda:0')
episode: 203 training return: tensor(-401.7168, device='cuda:0')
epoch: 51 test_true_pfm: 620.9744038341519 sim_pfm: -313.2757327478903
episode: 204 training return: tensor(-399.8133, device='cuda:0')
episode: 205 training return: tensor(-397.9104, device='cuda:0')
episode: 206 training return: tensor(-421.8780, device='cuda:0')
episode: 207 training return: tensor(-430.4255, device='cuda:0')
epoch: 52 test_true_pfm: 678.2906689153297 sim_pfm: -355.95165081244585
episode: 208 training return: tensor(-387.0979, device='cuda:0')
episode: 209 training return: tensor(-427.2880, device='cuda:0')
episode: 210 training return: tensor(-415.7161, device='cuda:0')
episode: 211 training return: tensor(-385.6504, device='cuda:0')
epoch: 53 test_true_pfm: 599.3912815701128 sim_pfm: -353.17908009840176
episode: 212 training return: tensor(-419.5517, device='cuda:0')
episode: 213 training return: tensor(-394.0957, device='cuda:0')
episode: 214 training return: tensor(-389.4067, device='cuda:0')
episode: 215 training return: tensor(-412.3493, device='cuda:0')
epoch: 54 test_true_pfm: 726.460334388929 sim_pfm: -309.46842117083725
episode: 216 training return: tensor(-409.3622, device='cuda:0')
episode: 217 training return: tensor(-436.9836, device='cuda:0')
episode: 218 training return: tensor(-443.5214, device='cuda:0')
episode: 219 training return: tensor(-388.8155, device='cuda:0')
epoch: 55 test_true_pfm: 636.2062888298707 sim_pfm: -328.8897882674355
episode: 220 training return: tensor(-402.3841, device='cuda:0')
episode: 221 training return: tensor(-378.3816, device='cuda:0')
episode: 222 training return: tensor(-392.7872, device='cuda:0')
episode: 223 training return: tensor(-376.5924, device='cuda:0')
epoch: 56 test_true_pfm: 774.4662069108323 sim_pfm: -329.53032982938265
episode: 224 training return: tensor(-404.8723, device='cuda:0')
episode: 225 training return: tensor(-380.4927, device='cuda:0')
episode: 226 training return: tensor(-346.5825, device='cuda:0')
episode: 227 training return: tensor(-397.0563, device='cuda:0')
epoch: 57 test_true_pfm: 770.2646790867842 sim_pfm: -320.2294743618598
episode: 228 training return: tensor(-425.2061, device='cuda:0')
episode: 229 training return: tensor(-364.7394, device='cuda:0')
episode: 230 training return: tensor(-347.4623, device='cuda:0')
episode: 231 training return: tensor(-409.6551, device='cuda:0')
epoch: 58 test_true_pfm: 916.6143074389814 sim_pfm: -285.5609495595272
episode: 232 training return: tensor(-376.8794, device='cuda:0')
episode: 233 training return: tensor(-395.2071, device='cuda:0')
episode: 234 training return: tensor(-387.4983, device='cuda:0')
episode: 235 training return: tensor(-433.6143, device='cuda:0')
epoch: 59 test_true_pfm: 666.6411778389366 sim_pfm: -307.19079159899655
episode: 236 training return: tensor(-405.7805, device='cuda:0')
episode: 237 training return: tensor(-363.0091, device='cuda:0')
episode: 238 training return: tensor(-354.1806, device='cuda:0')
episode: 239 training return: tensor(-416.7086, device='cuda:0')
epoch: 60 test_true_pfm: 747.5821854988885 sim_pfm: -323.88681256736163
episode: 240 training return: tensor(-441.1588, device='cuda:0')
episode: 241 training return: tensor(-427.4881, device='cuda:0')
episode: 242 training return: tensor(-390.8745, device='cuda:0')
episode: 243 training return: tensor(-400.2695, device='cuda:0')
epoch: 61 test_true_pfm: 692.8545041564051 sim_pfm: -315.3880171069177
episode: 244 training return: tensor(-380.9129, device='cuda:0')
episode: 245 training return: tensor(-388.0256, device='cuda:0')
episode: 246 training return: tensor(-373.4859, device='cuda:0')
episode: 247 training return: tensor(-397.5666, device='cuda:0')
epoch: 62 test_true_pfm: 733.4344956956807 sim_pfm: -341.57324662743486
episode: 248 training return: tensor(-405.7961, device='cuda:0')
episode: 249 training return: tensor(-497.8992, device='cuda:0')
episode: 250 training return: tensor(-429.0585, device='cuda:0')
episode: 251 training return: tensor(-363.1851, device='cuda:0')
epoch: 63 test_true_pfm: 621.5729772744402 sim_pfm: -325.4156856653669
episode: 252 training return: tensor(-353.3047, device='cuda:0')
episode: 253 training return: tensor(-427.9434, device='cuda:0')
episode: 254 training return: tensor(-553.3174, device='cuda:0')
episode: 255 training return: tensor(-419.3939, device='cuda:0')
epoch: 64 test_true_pfm: 608.0829501480343 sim_pfm: -341.8102651421602
episode: 256 training return: tensor(-415.1300, device='cuda:0')
episode: 257 training return: tensor(-365.7096, device='cuda:0')
episode: 258 training return: tensor(-361.2878, device='cuda:0')
episode: 259 training return: tensor(-411.1984, device='cuda:0')
epoch: 65 test_true_pfm: 762.2158577886494 sim_pfm: -335.9031887568029
episode: 260 training return: tensor(-381.7122, device='cuda:0')
episode: 261 training return: tensor(-403.1468, device='cuda:0')
episode: 262 training return: tensor(-397.6193, device='cuda:0')
episode: 263 training return: tensor(-419.5720, device='cuda:0')
epoch: 66 test_true_pfm: 845.4613453356951 sim_pfm: -338.7923032111624
episode: 264 training return: tensor(-386.1192, device='cuda:0')
episode: 265 training return: tensor(-368.8986, device='cuda:0')
episode: 266 training return: tensor(-350.4862, device='cuda:0')
episode: 267 training return: tensor(-432.5262, device='cuda:0')
epoch: 67 test_true_pfm: 626.3783107534487 sim_pfm: -334.56545337083907
episode: 268 training return: tensor(-376.9933, device='cuda:0')
episode: 269 training return: tensor(-403.0087, device='cuda:0')
episode: 270 training return: tensor(-394.6177, device='cuda:0')
episode: 271 training return: tensor(-376.1252, device='cuda:0')
epoch: 68 test_true_pfm: 899.9954750258175 sim_pfm: -315.61563932383433
episode: 272 training return: tensor(-374.7043, device='cuda:0')
episode: 273 training return: tensor(-448.6578, device='cuda:0')
episode: 274 training return: tensor(-634.3851, device='cuda:0')
episode: 275 training return: tensor(-353.3743, device='cuda:0')
epoch: 69 test_true_pfm: 822.0619145742263 sim_pfm: -303.0762010437708
episode: 276 training return: tensor(-425.6697, device='cuda:0')
episode: 277 training return: tensor(-440.8441, device='cuda:0')
episode: 278 training return: tensor(-397.0458, device='cuda:0')
episode: 279 training return: tensor(-394.8017, device='cuda:0')
epoch: 70 test_true_pfm: 719.7356231570025 sim_pfm: -327.8369968906433
episode: 280 training return: tensor(-386.9617, device='cuda:0')
episode: 281 training return: tensor(-367.9659, device='cuda:0')
episode: 282 training return: tensor(-398.9079, device='cuda:0')
episode: 283 training return: tensor(-388.1579, device='cuda:0')
epoch: 71 test_true_pfm: 874.8751465941982 sim_pfm: -309.65717655342695
episode: 284 training return: tensor(-448.3917, device='cuda:0')
episode: 285 training return: tensor(-421.8611, device='cuda:0')
episode: 286 training return: tensor(-391.8769, device='cuda:0')
episode: 287 training return: tensor(-400.1420, device='cuda:0')
epoch: 72 test_true_pfm: 669.8273823914956 sim_pfm: -366.22725323121995
episode: 288 training return: tensor(-435.1609, device='cuda:0')
episode: 289 training return: tensor(-449.4479, device='cuda:0')
episode: 290 training return: tensor(-403.5585, device='cuda:0')
episode: 291 training return: tensor(-408.0912, device='cuda:0')
epoch: 73 test_true_pfm: 596.5383391669726 sim_pfm: -345.0866029385943
episode: 292 training return: tensor(-489.4074, device='cuda:0')
episode: 293 training return: tensor(-414.5867, device='cuda:0')
episode: 294 training return: tensor(-380.7609, device='cuda:0')
episode: 295 training return: tensor(-668.3508, device='cuda:0')
epoch: 74 test_true_pfm: 558.408109016075 sim_pfm: -374.9735536532632
episode: 296 training return: tensor(-600.6555, device='cuda:0')
episode: 297 training return: tensor(-388.9981, device='cuda:0')
episode: 298 training return: tensor(-425.4180, device='cuda:0')
episode: 299 training return: tensor(-371.2568, device='cuda:0')
epoch: 75 test_true_pfm: 712.3877921877851 sim_pfm: -342.84744094026
episode: 300 training return: tensor(-382.0105, device='cuda:0')
episode: 301 training return: tensor(-424.5616, device='cuda:0')
episode: 302 training return: tensor(-398.3025, device='cuda:0')
episode: 303 training return: tensor(-394.6350, device='cuda:0')
epoch: 76 test_true_pfm: 814.6499179291723 sim_pfm: -294.540097339234
episode: 304 training return: tensor(-411.5597, device='cuda:0')
episode: 305 training return: tensor(-388.4171, device='cuda:0')
episode: 306 training return: tensor(-372.8529, device='cuda:0')
episode: 307 training return: tensor(-380.5866, device='cuda:0')
epoch: 77 test_true_pfm: 740.2832154253083 sim_pfm: -309.7725667261984
episode: 308 training return: tensor(-395.1189, device='cuda:0')
episode: 309 training return: tensor(-403.2578, device='cuda:0')
episode: 310 training return: tensor(-406.8012, device='cuda:0')
episode: 311 training return: tensor(-381.1346, device='cuda:0')
epoch: 78 test_true_pfm: 589.1368019611166 sim_pfm: -371.02739478545845
episode: 312 training return: tensor(-405.7425, device='cuda:0')
episode: 313 training return: tensor(-372.3910, device='cuda:0')
episode: 314 training return: tensor(-389.2805, device='cuda:0')
episode: 315 training return: tensor(-365.7284, device='cuda:0')
epoch: 79 test_true_pfm: 868.0318781498544 sim_pfm: -324.17578767441836
episode: 316 training return: tensor(-370.1948, device='cuda:0')
episode: 317 training return: tensor(-399.3788, device='cuda:0')
episode: 318 training return: tensor(-370.3320, device='cuda:0')
episode: 319 training return: tensor(-640.5411, device='cuda:0')
epoch: 80 test_true_pfm: 521.7523586525929 sim_pfm: -341.2946736696952
episode: 320 training return: tensor(-378.5079, device='cuda:0')
episode: 321 training return: tensor(-432.3188, device='cuda:0')
episode: 322 training return: tensor(-406.0715, device='cuda:0')
episode: 323 training return: tensor(-410.0930, device='cuda:0')
epoch: 81 test_true_pfm: 643.5892370677972 sim_pfm: -342.92503109170747
episode: 324 training return: tensor(-379.9436, device='cuda:0')
episode: 325 training return: tensor(-387.1335, device='cuda:0')
episode: 326 training return: tensor(-412.9777, device='cuda:0')
episode: 327 training return: tensor(-409.9456, device='cuda:0')
epoch: 82 test_true_pfm: 913.1757291567109 sim_pfm: -320.72347617095994
episode: 328 training return: tensor(-344.1057, device='cuda:0')
episode: 329 training return: tensor(-431.3038, device='cuda:0')
episode: 330 training return: tensor(-421.3017, device='cuda:0')
episode: 331 training return: tensor(-357.9792, device='cuda:0')
epoch: 83 test_true_pfm: 793.6265435208766 sim_pfm: -311.9280678146558
episode: 332 training return: tensor(-364.3979, device='cuda:0')
episode: 333 training return: tensor(-405.5125, device='cuda:0')
episode: 334 training return: tensor(-358.8251, device='cuda:0')
episode: 335 training return: tensor(-397.5180, device='cuda:0')
epoch: 84 test_true_pfm: 802.8750321929074 sim_pfm: -305.1413371528906
episode: 336 training return: tensor(-453.6643, device='cuda:0')
episode: 337 training return: tensor(-396.2060, device='cuda:0')
episode: 338 training return: tensor(-391.6998, device='cuda:0')
episode: 339 training return: tensor(-406.2495, device='cuda:0')
epoch: 85 test_true_pfm: 493.9157375089447 sim_pfm: -329.1608181707173
episode: 340 training return: tensor(-385.2340, device='cuda:0')
episode: 341 training return: tensor(-400.0727, device='cuda:0')
episode: 342 training return: tensor(-383.7695, device='cuda:0')
episode: 343 training return: tensor(-403.6677, device='cuda:0')
epoch: 86 test_true_pfm: 627.2390202365655 sim_pfm: -413.8512344308353
episode: 344 training return: tensor(-416.3964, device='cuda:0')
episode: 345 training return: tensor(-356.9079, device='cuda:0')
episode: 346 training return: tensor(-419.8709, device='cuda:0')
episode: 347 training return: tensor(-394.9971, device='cuda:0')
epoch: 87 test_true_pfm: 692.8742990954696 sim_pfm: -433.2776420407463
episode: 348 training return: tensor(-385.8759, device='cuda:0')
episode: 349 training return: tensor(-459.0747, device='cuda:0')
episode: 350 training return: tensor(-371.8907, device='cuda:0')
episode: 351 training return: tensor(-421.3292, device='cuda:0')
epoch: 88 test_true_pfm: 787.2850539633347 sim_pfm: -322.9364380762757
episode: 352 training return: tensor(-359.6869, device='cuda:0')
episode: 353 training return: tensor(-413.5707, device='cuda:0')
episode: 354 training return: tensor(-384.5403, device='cuda:0')
episode: 355 training return: tensor(-386.1288, device='cuda:0')
epoch: 89 test_true_pfm: 811.1336766522453 sim_pfm: -283.07588879193645
episode: 356 training return: tensor(-366.8104, device='cuda:0')
episode: 357 training return: tensor(-382.8398, device='cuda:0')
episode: 358 training return: tensor(-352.6906, device='cuda:0')
episode: 359 training return: tensor(-388.3467, device='cuda:0')
epoch: 90 test_true_pfm: 743.3139074671435 sim_pfm: -349.7231836843421
episode: 360 training return: tensor(-394.7262, device='cuda:0')
episode: 361 training return: tensor(-376.9004, device='cuda:0')
episode: 362 training return: tensor(-372.3016, device='cuda:0')
episode: 363 training return: tensor(-401.5227, device='cuda:0')
epoch: 91 test_true_pfm: 591.7691165486921 sim_pfm: -333.71961409050465
episode: 364 training return: tensor(-373.4503, device='cuda:0')
episode: 365 training return: tensor(-421.6880, device='cuda:0')
episode: 366 training return: tensor(-422.9362, device='cuda:0')
episode: 367 training return: tensor(-417.1996, device='cuda:0')
epoch: 92 test_true_pfm: 643.3285201400055 sim_pfm: -408.98842218413483
episode: 368 training return: tensor(-341.9926, device='cuda:0')
episode: 369 training return: tensor(-394.2226, device='cuda:0')
episode: 370 training return: tensor(-398.7818, device='cuda:0')
episode: 371 training return: tensor(-398.4009, device='cuda:0')
epoch: 93 test_true_pfm: 638.2810830261317 sim_pfm: -350.96633010861115
episode: 372 training return: tensor(-330.9780, device='cuda:0')
episode: 373 training return: tensor(-397.7495, device='cuda:0')
episode: 374 training return: tensor(-379.0023, device='cuda:0')
episode: 375 training return: tensor(-393.7610, device='cuda:0')
epoch: 94 test_true_pfm: 489.3709437869275 sim_pfm: -342.784593055374
episode: 376 training return: tensor(-410.2744, device='cuda:0')
episode: 377 training return: tensor(-374.5190, device='cuda:0')
episode: 378 training return: tensor(-437.8499, device='cuda:0')
episode: 379 training return: tensor(-421.4120, device='cuda:0')
epoch: 95 test_true_pfm: 679.120366435426 sim_pfm: -350.8781910731923
episode: 380 training return: tensor(-377.3367, device='cuda:0')
episode: 381 training return: tensor(-395.2866, device='cuda:0')
episode: 382 training return: tensor(-393.1079, device='cuda:0')
episode: 383 training return: tensor(-377.1702, device='cuda:0')
epoch: 96 test_true_pfm: 870.342975007998 sim_pfm: -422.5913047218346
episode: 384 training return: tensor(-413.3042, device='cuda:0')
episode: 385 training return: tensor(-435.0593, device='cuda:0')
episode: 386 training return: tensor(-398.4469, device='cuda:0')
episode: 387 training return: tensor(-372.6476, device='cuda:0')
epoch: 97 test_true_pfm: 913.7968551293371 sim_pfm: -292.0174044157223
episode: 388 training return: tensor(-417.9096, device='cuda:0')
episode: 389 training return: tensor(-425.3513, device='cuda:0')
episode: 390 training return: tensor(-380.8131, device='cuda:0')
episode: 391 training return: tensor(-403.2769, device='cuda:0')
epoch: 98 test_true_pfm: 819.5668060999577 sim_pfm: -299.9254083302221
episode: 392 training return: tensor(-354.8286, device='cuda:0')
episode: 393 training return: tensor(-307.1260, device='cuda:0')
episode: 394 training return: tensor(-423.6352, device='cuda:0')
episode: 395 training return: tensor(-401.4199, device='cuda:0')
epoch: 99 test_true_pfm: 827.4175405554248 sim_pfm: -293.7390915337407
episode: 396 training return: tensor(-404.9108, device='cuda:0')
episode: 397 training return: tensor(-420.1403, device='cuda:0')
episode: 398 training return: tensor(-370.1222, device='cuda:0')
episode: 399 training return: tensor(-383.5743, device='cuda:0')
epoch: 100 test_true_pfm: 824.0168312025859 sim_pfm: -286.14330778853036
episode: 400 training return: tensor(-395.8611, device='cuda:0')
episode: 401 training return: tensor(-370.5177, device='cuda:0')
episode: 402 training return: tensor(-411.7632, device='cuda:0')
episode: 403 training return: tensor(-405.6663, device='cuda:0')
epoch: 101 test_true_pfm: 798.8833886308086 sim_pfm: -302.66240045655286
episode: 404 training return: tensor(-422.3246, device='cuda:0')
episode: 405 training return: tensor(-402.3641, device='cuda:0')
episode: 406 training return: tensor(-387.2133, device='cuda:0')
episode: 407 training return: tensor(-427.2374, device='cuda:0')
epoch: 102 test_true_pfm: 704.4617401065151 sim_pfm: -317.1388459527031
episode: 408 training return: tensor(-342.5129, device='cuda:0')
episode: 409 training return: tensor(-375.2837, device='cuda:0')
episode: 410 training return: tensor(-387.5551, device='cuda:0')
episode: 411 training return: tensor(-397.1077, device='cuda:0')
epoch: 103 test_true_pfm: 484.5914767811587 sim_pfm: -374.338386473828
episode: 412 training return: tensor(-385.8383, device='cuda:0')
episode: 413 training return: tensor(-367.1377, device='cuda:0')
episode: 414 training return: tensor(-404.0845, device='cuda:0')
episode: 415 training return: tensor(-382.3558, device='cuda:0')
epoch: 104 test_true_pfm: 841.2458080435041 sim_pfm: -288.7478552857453
episode: 416 training return: tensor(-377.0558, device='cuda:0')
episode: 417 training return: tensor(-401.7306, device='cuda:0')
episode: 418 training return: tensor(-361.0703, device='cuda:0')
episode: 419 training return: tensor(-381.7441, device='cuda:0')
epoch: 105 test_true_pfm: 807.2878066772679 sim_pfm: -267.58349331012386
episode: 420 training return: tensor(-374.7215, device='cuda:0')
episode: 421 training return: tensor(-397.9073, device='cuda:0')
episode: 422 training return: tensor(-401.9582, device='cuda:0')
episode: 423 training return: tensor(-414.4669, device='cuda:0')
epoch: 106 test_true_pfm: 808.97700657042 sim_pfm: -326.6140761569065
episode: 424 training return: tensor(-476.6270, device='cuda:0')
episode: 425 training return: tensor(-435.8397, device='cuda:0')
episode: 426 training return: tensor(-344.7290, device='cuda:0')
episode: 427 training return: tensor(-390.1760, device='cuda:0')
epoch: 107 test_true_pfm: 714.6937088686664 sim_pfm: -307.44331813941244
episode: 428 training return: tensor(-402.9230, device='cuda:0')
episode: 429 training return: tensor(-414.4894, device='cuda:0')
episode: 430 training return: tensor(-392.5592, device='cuda:0')
episode: 431 training return: tensor(-389.0055, device='cuda:0')
epoch: 108 test_true_pfm: 755.9022989306596 sim_pfm: -327.14376612387906
episode: 432 training return: tensor(-365.6790, device='cuda:0')
episode: 433 training return: tensor(-404.6361, device='cuda:0')
episode: 434 training return: tensor(-356.7726, device='cuda:0')
episode: 435 training return: tensor(-359.7927, device='cuda:0')
epoch: 109 test_true_pfm: 790.4764854580629 sim_pfm: -304.2395146290364
episode: 436 training return: tensor(-379.1689, device='cuda:0')
episode: 437 training return: tensor(-393.5268, device='cuda:0')
episode: 438 training return: tensor(-381.7993, device='cuda:0')
episode: 439 training return: tensor(-366.4325, device='cuda:0')
epoch: 110 test_true_pfm: 778.5978244415933 sim_pfm: -305.3565587290893
episode: 440 training return: tensor(-390.2739, device='cuda:0')
episode: 441 training return: tensor(-404.2809, device='cuda:0')
episode: 442 training return: tensor(-394.1577, device='cuda:0')
episode: 443 training return: tensor(-359.8163, device='cuda:0')
epoch: 111 test_true_pfm: 829.5332025933882 sim_pfm: -305.95267739348736
episode: 444 training return: tensor(-400.6245, device='cuda:0')
episode: 445 training return: tensor(-399.7521, device='cuda:0')
episode: 446 training return: tensor(-358.7323, device='cuda:0')
episode: 447 training return: tensor(-377.0340, device='cuda:0')
epoch: 112 test_true_pfm: 913.5132576615574 sim_pfm: -287.933766922215
episode: 448 training return: tensor(-355.6551, device='cuda:0')
episode: 449 training return: tensor(-420.2865, device='cuda:0')
episode: 450 training return: tensor(-384.6394, device='cuda:0')
episode: 451 training return: tensor(-354.6292, device='cuda:0')
epoch: 113 test_true_pfm: 799.8817607509063 sim_pfm: -284.3655745291908
episode: 452 training return: tensor(-382.0929, device='cuda:0')
episode: 453 training return: tensor(-367.0536, device='cuda:0')
episode: 454 training return: tensor(-389.8647, device='cuda:0')
episode: 455 training return: tensor(-368.0086, device='cuda:0')
epoch: 114 test_true_pfm: 687.6432321129881 sim_pfm: -312.7360000667007
episode: 456 training return: tensor(-366.4746, device='cuda:0')
episode: 457 training return: tensor(-402.7068, device='cuda:0')
episode: 458 training return: tensor(-386.6418, device='cuda:0')
episode: 459 training return: tensor(-358.3250, device='cuda:0')
epoch: 115 test_true_pfm: 884.7583941066387 sim_pfm: -307.65213597154553
episode: 460 training return: tensor(-403.8386, device='cuda:0')
episode: 461 training return: tensor(-404.7924, device='cuda:0')
episode: 462 training return: tensor(-377.4688, device='cuda:0')
episode: 463 training return: tensor(-334.1906, device='cuda:0')
epoch: 116 test_true_pfm: 821.1508321961683 sim_pfm: -307.4556032345669
episode: 464 training return: tensor(-369.4699, device='cuda:0')
episode: 465 training return: tensor(-347.4626, device='cuda:0')
episode: 466 training return: tensor(-400.6976, device='cuda:0')
episode: 467 training return: tensor(-384.0573, device='cuda:0')
epoch: 117 test_true_pfm: 872.66830566117 sim_pfm: -300.22514864243567
episode: 468 training return: tensor(-403.6541, device='cuda:0')
episode: 469 training return: tensor(-408.4853, device='cuda:0')
episode: 470 training return: tensor(-366.4725, device='cuda:0')
episode: 471 training return: tensor(-345.3069, device='cuda:0')
epoch: 118 test_true_pfm: 908.8914225608875 sim_pfm: -285.30275037510245
episode: 472 training return: tensor(-369.4708, device='cuda:0')
episode: 473 training return: tensor(-396.9049, device='cuda:0')
episode: 474 training return: tensor(-384.0239, device='cuda:0')
episode: 475 training return: tensor(-351.9745, device='cuda:0')
epoch: 119 test_true_pfm: 773.7181164463536 sim_pfm: -301.8605869916112
episode: 476 training return: tensor(-318.2144, device='cuda:0')
episode: 477 training return: tensor(-366.3014, device='cuda:0')
episode: 478 training return: tensor(-366.3564, device='cuda:0')
episode: 479 training return: tensor(-365.3811, device='cuda:0')
epoch: 120 test_true_pfm: 763.6821935735971 sim_pfm: -331.1384063162356
episode: 480 training return: tensor(-395.2456, device='cuda:0')
episode: 481 training return: tensor(-391.3446, device='cuda:0')
episode: 482 training return: tensor(-317.8730, device='cuda:0')
episode: 483 training return: tensor(-345.5796, device='cuda:0')
epoch: 121 test_true_pfm: 648.6108290108979 sim_pfm: -317.005556911851
episode: 484 training return: tensor(-390.7453, device='cuda:0')
episode: 485 training return: tensor(-391.2990, device='cuda:0')
episode: 486 training return: tensor(-359.2509, device='cuda:0')
episode: 487 training return: tensor(-384.8674, device='cuda:0')
epoch: 122 test_true_pfm: 874.3504869170574 sim_pfm: -305.5731991522286
episode: 488 training return: tensor(-390.0919, device='cuda:0')
episode: 489 training return: tensor(-380.2926, device='cuda:0')
episode: 490 training return: tensor(-370.4417, device='cuda:0')
episode: 491 training return: tensor(-389.8796, device='cuda:0')
epoch: 123 test_true_pfm: 831.4550237213925 sim_pfm: -298.0642480576644
episode: 492 training return: tensor(-372.9846, device='cuda:0')
episode: 493 training return: tensor(-418.0436, device='cuda:0')
episode: 494 training return: tensor(-354.4625, device='cuda:0')
episode: 495 training return: tensor(-372.8994, device='cuda:0')
epoch: 124 test_true_pfm: 820.0198214059261 sim_pfm: -332.92654544796096
episode: 496 training return: tensor(-422.1068, device='cuda:0')
episode: 497 training return: tensor(-360.9565, device='cuda:0')
episode: 498 training return: tensor(-368.6395, device='cuda:0')
episode: 499 training return: tensor(-365.6365, device='cuda:0')
epoch: 125 test_true_pfm: 779.141568390377 sim_pfm: -310.4392478129982
episode: 500 training return: tensor(-367.4991, device='cuda:0')
episode: 501 training return: tensor(-353.4948, device='cuda:0')
episode: 502 training return: tensor(-388.4610, device='cuda:0')
episode: 503 training return: tensor(-398.7836, device='cuda:0')
epoch: 126 test_true_pfm: 827.5087707276606 sim_pfm: -297.37106965482235
episode: 504 training return: tensor(-374.8477, device='cuda:0')
episode: 505 training return: tensor(-374.6827, device='cuda:0')
episode: 506 training return: tensor(-380.2133, device='cuda:0')
episode: 507 training return: tensor(-383.0252, device='cuda:0')
epoch: 127 test_true_pfm: 831.7855311912123 sim_pfm: -310.2239813385143
episode: 508 training return: tensor(-411.0228, device='cuda:0')
episode: 509 training return: tensor(-388.2912, device='cuda:0')
episode: 510 training return: tensor(-377.2492, device='cuda:0')
episode: 511 training return: tensor(-371.8386, device='cuda:0')
epoch: 128 test_true_pfm: 810.4736088711079 sim_pfm: -295.5658458479156
episode: 512 training return: tensor(-373.2256, device='cuda:0')
episode: 513 training return: tensor(-354.1900, device='cuda:0')
episode: 514 training return: tensor(-423.5971, device='cuda:0')
episode: 515 training return: tensor(-331.8402, device='cuda:0')
epoch: 129 test_true_pfm: 689.0677503580087 sim_pfm: -346.66295941519394
episode: 516 training return: tensor(-418.9225, device='cuda:0')
episode: 517 training return: tensor(-374.0015, device='cuda:0')
episode: 518 training return: tensor(-330.9775, device='cuda:0')
episode: 519 training return: tensor(-405.7443, device='cuda:0')
epoch: 130 test_true_pfm: 854.8193540027078 sim_pfm: -320.15613716638956
episode: 520 training return: tensor(-371.7046, device='cuda:0')
episode: 521 training return: tensor(-374.3491, device='cuda:0')
episode: 522 training return: tensor(-335.4131, device='cuda:0')
episode: 523 training return: tensor(-351.4330, device='cuda:0')
epoch: 131 test_true_pfm: 762.8646407044716 sim_pfm: -309.9262245214195
episode: 524 training return: tensor(-376.3159, device='cuda:0')
episode: 525 training return: tensor(-362.4059, device='cuda:0')
episode: 526 training return: tensor(-376.5431, device='cuda:0')
episode: 527 training return: tensor(-377.9987, device='cuda:0')
epoch: 132 test_true_pfm: 754.8091458570648 sim_pfm: -342.17892450179596
episode: 528 training return: tensor(-363.9499, device='cuda:0')
episode: 529 training return: tensor(-400.8085, device='cuda:0')
episode: 530 training return: tensor(-330.9274, device='cuda:0')
episode: 531 training return: tensor(-388.2852, device='cuda:0')
epoch: 133 test_true_pfm: 764.0793366231533 sim_pfm: -322.0410262950463
episode: 532 training return: tensor(-373.5308, device='cuda:0')
episode: 533 training return: tensor(-386.1307, device='cuda:0')
episode: 534 training return: tensor(-342.6031, device='cuda:0')
episode: 535 training return: tensor(-381.7935, device='cuda:0')
epoch: 134 test_true_pfm: 837.0746884495319 sim_pfm: -303.2295124169905
episode: 536 training return: tensor(-387.9864, device='cuda:0')
episode: 537 training return: tensor(-360.5683, device='cuda:0')
episode: 538 training return: tensor(-344.2556, device='cuda:0')
episode: 539 training return: tensor(-355.2928, device='cuda:0')
epoch: 135 test_true_pfm: 827.1481453826951 sim_pfm: -290.4045223617674
episode: 540 training return: tensor(-362.2023, device='cuda:0')
episode: 541 training return: tensor(-375.1528, device='cuda:0')
episode: 542 training return: tensor(-395.0463, device='cuda:0')
episode: 543 training return: tensor(-401.7117, device='cuda:0')
epoch: 136 test_true_pfm: 830.3948626276909 sim_pfm: -312.9844205287906
episode: 544 training return: tensor(-426.6532, device='cuda:0')
episode: 545 training return: tensor(-417.0082, device='cuda:0')
episode: 546 training return: tensor(-427.3893, device='cuda:0')
episode: 547 training return: tensor(-377.4210, device='cuda:0')
epoch: 137 test_true_pfm: 785.3658824284194 sim_pfm: -280.9636743896796
episode: 548 training return: tensor(-375.3252, device='cuda:0')
episode: 549 training return: tensor(-380.9188, device='cuda:0')
episode: 550 training return: tensor(-360.8521, device='cuda:0')
episode: 551 training return: tensor(-348.3946, device='cuda:0')
epoch: 138 test_true_pfm: 782.103598944902 sim_pfm: -321.20809689785045
episode: 552 training return: tensor(-381.3916, device='cuda:0')
episode: 553 training return: tensor(-388.9879, device='cuda:0')
episode: 554 training return: tensor(-423.4214, device='cuda:0')
episode: 555 training return: tensor(-418.0957, device='cuda:0')
epoch: 139 test_true_pfm: 696.987125177637 sim_pfm: -313.48823148520506
episode: 556 training return: tensor(-414.6815, device='cuda:0')
episode: 557 training return: tensor(-349.2356, device='cuda:0')
episode: 558 training return: tensor(-341.9883, device='cuda:0')
episode: 559 training return: tensor(-375.1053, device='cuda:0')
epoch: 140 test_true_pfm: 764.6615542110104 sim_pfm: -305.43443880150636
episode: 560 training return: tensor(-353.8050, device='cuda:0')
episode: 561 training return: tensor(-360.6460, device='cuda:0')
episode: 562 training return: tensor(-324.4058, device='cuda:0')
episode: 563 training return: tensor(-393.7569, device='cuda:0')
epoch: 141 test_true_pfm: 760.0244189575443 sim_pfm: -305.50166101883707
episode: 564 training return: tensor(-418.1884, device='cuda:0')
episode: 565 training return: tensor(-422.0856, device='cuda:0')
episode: 566 training return: tensor(-404.2169, device='cuda:0')
episode: 567 training return: tensor(-395.0954, device='cuda:0')
epoch: 142 test_true_pfm: 731.7845557730449 sim_pfm: -316.57474668770254
episode: 568 training return: tensor(-373.0824, device='cuda:0')
episode: 569 training return: tensor(-374.9225, device='cuda:0')
episode: 570 training return: tensor(-393.5173, device='cuda:0')
episode: 571 training return: tensor(-392.1423, device='cuda:0')
epoch: 143 test_true_pfm: 755.3185166103434 sim_pfm: -322.3811057897595
episode: 572 training return: tensor(-391.1254, device='cuda:0')
episode: 573 training return: tensor(-372.7946, device='cuda:0')
episode: 574 training return: tensor(-352.1087, device='cuda:0')
episode: 575 training return: tensor(-389.4438, device='cuda:0')
epoch: 144 test_true_pfm: 872.513319628661 sim_pfm: -292.3996424565169
episode: 576 training return: tensor(-380.1661, device='cuda:0')
episode: 577 training return: tensor(-406.9866, device='cuda:0')
episode: 578 training return: tensor(-408.9246, device='cuda:0')
episode: 579 training return: tensor(-370.3507, device='cuda:0')
epoch: 145 test_true_pfm: 786.5058542009474 sim_pfm: -309.8485834572057
episode: 580 training return: tensor(-378.9050, device='cuda:0')
episode: 581 training return: tensor(-389.3643, device='cuda:0')
episode: 582 training return: tensor(-385.4955, device='cuda:0')
episode: 583 training return: tensor(-359.0139, device='cuda:0')
epoch: 146 test_true_pfm: 757.5812388505501 sim_pfm: -275.81039642210817
episode: 584 training return: tensor(-370.4772, device='cuda:0')
episode: 585 training return: tensor(-335.9129, device='cuda:0')
episode: 586 training return: tensor(-397.8373, device='cuda:0')
episode: 587 training return: tensor(-395.5729, device='cuda:0')
epoch: 147 test_true_pfm: 734.5443967949471 sim_pfm: -305.53522883735906
episode: 588 training return: tensor(-371.9431, device='cuda:0')
episode: 589 training return: tensor(-416.1992, device='cuda:0')
episode: 590 training return: tensor(-401.2005, device='cuda:0')
episode: 591 training return: tensor(-380.5575, device='cuda:0')
epoch: 148 test_true_pfm: 889.904851452298 sim_pfm: -292.27574116010027
episode: 592 training return: tensor(-391.2647, device='cuda:0')
episode: 593 training return: tensor(-384.7310, device='cuda:0')
episode: 594 training return: tensor(-356.6166, device='cuda:0')
episode: 595 training return: tensor(-382.9290, device='cuda:0')
epoch: 149 test_true_pfm: 835.2583993169247 sim_pfm: -303.2749727266103
episode: 596 training return: tensor(-404.8247, device='cuda:0')
episode: 597 training return: tensor(-411.6052, device='cuda:0')
episode: 598 training return: tensor(-391.9000, device='cuda:0')
episode: 599 training return: tensor(-357.9849, device='cuda:0')
epoch: 150 test_true_pfm: 641.3840901010622 sim_pfm: -332.2399421746377
