['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'baseline', '--traj', 'expert', '--seed', '2']
episode: 0 training return: tensor(-998.7810, device='cuda:0')
episode: 1 training return: tensor(-999.6696, device='cuda:0')
episode: 2 training return: tensor(-986.6452, device='cuda:0')
episode: 3 training return: tensor(-989.2715, device='cuda:0')
epoch: 1 test_true_pfm: 279.43012496008595 sim_pfm: -987.1870208382607
episode: 4 training return: tensor(-997.5252, device='cuda:0')
episode: 5 training return: tensor(-991.2622, device='cuda:0')
episode: 6 training return: tensor(-993.0625, device='cuda:0')
episode: 7 training return: tensor(-956.8945, device='cuda:0')
epoch: 2 test_true_pfm: 209.80729898875083 sim_pfm: -957.7103577529391
episode: 8 training return: tensor(-999.6648, device='cuda:0')
episode: 9 training return: tensor(-996.4521, device='cuda:0')
episode: 10 training return: tensor(-999.8036, device='cuda:0')
episode: 11 training return: tensor(-987.7779, device='cuda:0')
epoch: 3 test_true_pfm: 211.94972803438873 sim_pfm: -955.4584533534944
episode: 12 training return: tensor(-974.7838, device='cuda:0')
episode: 13 training return: tensor(-969.6244, device='cuda:0')
episode: 14 training return: tensor(-950.1487, device='cuda:0')
episode: 15 training return: tensor(-959.1432, device='cuda:0')
epoch: 4 test_true_pfm: 189.62496242072817 sim_pfm: -950.119277610754
episode: 16 training return: tensor(-952.7110, device='cuda:0')
episode: 17 training return: tensor(-944.4770, device='cuda:0')
episode: 18 training return: tensor(-956.5085, device='cuda:0')
episode: 19 training return: tensor(-950.4842, device='cuda:0')
epoch: 5 test_true_pfm: 202.711319364524 sim_pfm: -947.59533698949
episode: 20 training return: tensor(-950.1988, device='cuda:0')
episode: 21 training return: tensor(-954.6282, device='cuda:0')
episode: 22 training return: tensor(-947.0563, device='cuda:0')
episode: 23 training return: tensor(-935.1759, device='cuda:0')
epoch: 6 test_true_pfm: 240.92004189979312 sim_pfm: -927.8368080881968
episode: 24 training return: tensor(-931.2740, device='cuda:0')
episode: 25 training return: tensor(-927.5278, device='cuda:0')
episode: 26 training return: tensor(-931.8156, device='cuda:0')
episode: 27 training return: tensor(-927.3270, device='cuda:0')
epoch: 7 test_true_pfm: 243.35907116160914 sim_pfm: -920.6754027721084
episode: 28 training return: tensor(-923.9857, device='cuda:0')
episode: 29 training return: tensor(-916.7494, device='cuda:0')
episode: 30 training return: tensor(-913.8118, device='cuda:0')
episode: 31 training return: tensor(-933.9485, device='cuda:0')
epoch: 8 test_true_pfm: 261.655255657565 sim_pfm: -904.0738446937563
episode: 32 training return: tensor(-929.9919, device='cuda:0')
episode: 33 training return: tensor(-885.1016, device='cuda:0')
episode: 34 training return: tensor(-906.1008, device='cuda:0')
episode: 35 training return: tensor(-889.5504, device='cuda:0')
epoch: 9 test_true_pfm: 248.8790757552738 sim_pfm: -884.0562346687851
episode: 36 training return: tensor(-872.8847, device='cuda:0')
episode: 37 training return: tensor(-884.4600, device='cuda:0')
episode: 38 training return: tensor(-872.8223, device='cuda:0')
episode: 39 training return: tensor(-892.7650, device='cuda:0')
epoch: 10 test_true_pfm: 301.6483249526159 sim_pfm: -884.8641091278599
episode: 40 training return: tensor(-859.9067, device='cuda:0')
episode: 41 training return: tensor(-893.7234, device='cuda:0')
episode: 42 training return: tensor(-901.7660, device='cuda:0')
episode: 43 training return: tensor(-875.8940, device='cuda:0')
epoch: 11 test_true_pfm: 315.77659561795105 sim_pfm: -869.2927137260946
episode: 44 training return: tensor(-877.2625, device='cuda:0')
episode: 45 training return: tensor(-867.5837, device='cuda:0')
episode: 46 training return: tensor(-882.6659, device='cuda:0')
episode: 47 training return: tensor(-877.3526, device='cuda:0')
epoch: 12 test_true_pfm: 291.79734896978215 sim_pfm: -877.6848576230308
episode: 48 training return: tensor(-900.0272, device='cuda:0')
episode: 49 training return: tensor(-903.6111, device='cuda:0')
episode: 50 training return: tensor(-859.5865, device='cuda:0')
episode: 51 training return: tensor(-894.3763, device='cuda:0')
epoch: 13 test_true_pfm: 248.9941966967913 sim_pfm: -891.4671042207628
episode: 52 training return: tensor(-889.7287, device='cuda:0')
episode: 53 training return: tensor(-896.5056, device='cuda:0')
episode: 54 training return: tensor(-808.9429, device='cuda:0')
episode: 55 training return: tensor(-765.4031, device='cuda:0')
epoch: 14 test_true_pfm: 281.4810047467124 sim_pfm: -884.836990082685
episode: 56 training return: tensor(-708.6010, device='cuda:0')
episode: 57 training return: tensor(-724.8603, device='cuda:0')
episode: 58 training return: tensor(-772.5090, device='cuda:0')
episode: 59 training return: tensor(-840.8346, device='cuda:0')
epoch: 15 test_true_pfm: 134.45553692478447 sim_pfm: -895.8312284074879
episode: 60 training return: tensor(-753.3771, device='cuda:0')
episode: 61 training return: tensor(-843.0270, device='cuda:0')
episode: 62 training return: tensor(-818.4729, device='cuda:0')
episode: 63 training return: tensor(-839.5226, device='cuda:0')
epoch: 16 test_true_pfm: 254.3438469496015 sim_pfm: -833.4726225556806
episode: 64 training return: tensor(-856.0660, device='cuda:0')
episode: 65 training return: tensor(-867.0663, device='cuda:0')
episode: 66 training return: tensor(-878.6950, device='cuda:0')
episode: 67 training return: tensor(-875.6583, device='cuda:0')
epoch: 17 test_true_pfm: 283.7495235511437 sim_pfm: -862.6499335847329
episode: 68 training return: tensor(-851.1881, device='cuda:0')
episode: 69 training return: tensor(-858.6969, device='cuda:0')
episode: 70 training return: tensor(-811.9008, device='cuda:0')
episode: 71 training return: tensor(-886.0171, device='cuda:0')
epoch: 18 test_true_pfm: 284.8252427198554 sim_pfm: -862.5148067571378
episode: 72 training return: tensor(-871.1998, device='cuda:0')
episode: 73 training return: tensor(-879.1829, device='cuda:0')
episode: 74 training return: tensor(-864.2487, device='cuda:0')
episode: 75 training return: tensor(-887.5856, device='cuda:0')
epoch: 19 test_true_pfm: 296.1464276462793 sim_pfm: -865.0340834133871
episode: 76 training return: tensor(-863.0662, device='cuda:0')
episode: 77 training return: tensor(-870.8616, device='cuda:0')
episode: 78 training return: tensor(-892.7703, device='cuda:0')
episode: 79 training return: tensor(-888.5232, device='cuda:0')
epoch: 20 test_true_pfm: 288.76453009183837 sim_pfm: -862.419603969281
episode: 80 training return: tensor(-867.0662, device='cuda:0')
episode: 81 training return: tensor(-859.1228, device='cuda:0')
episode: 82 training return: tensor(-870.7928, device='cuda:0')
episode: 83 training return: tensor(-861.5590, device='cuda:0')
epoch: 21 test_true_pfm: 257.88793227903716 sim_pfm: -855.5923145606648
episode: 84 training return: tensor(-852.8913, device='cuda:0')
episode: 85 training return: tensor(-869.7374, device='cuda:0')
episode: 86 training return: tensor(-797.6317, device='cuda:0')
episode: 87 training return: tensor(-836.2180, device='cuda:0')
epoch: 22 test_true_pfm: 296.6006337913207 sim_pfm: -839.549869351089
episode: 88 training return: tensor(-837.2769, device='cuda:0')
episode: 89 training return: tensor(-854.8523, device='cuda:0')
episode: 90 training return: tensor(-858.0838, device='cuda:0')
episode: 91 training return: tensor(-724.9323, device='cuda:0')
epoch: 23 test_true_pfm: 322.49206648129916 sim_pfm: -835.2450515975555
episode: 92 training return: tensor(-852.6047, device='cuda:0')
episode: 93 training return: tensor(-758.9462, device='cuda:0')
episode: 94 training return: tensor(-793.6599, device='cuda:0')
episode: 95 training return: tensor(-777.5723, device='cuda:0')
epoch: 24 test_true_pfm: 302.5971651928971 sim_pfm: -847.6031219277356
episode: 96 training return: tensor(-860.0956, device='cuda:0')
episode: 97 training return: tensor(-858.0471, device='cuda:0')
episode: 98 training return: tensor(-712.6309, device='cuda:0')
episode: 99 training return: tensor(-822.3320, device='cuda:0')
epoch: 25 test_true_pfm: 308.5736817161373 sim_pfm: -837.5047141983329
episode: 100 training return: tensor(-779.8936, device='cuda:0')
episode: 101 training return: tensor(-796.8016, device='cuda:0')
episode: 102 training return: tensor(-849.6758, device='cuda:0')
episode: 103 training return: tensor(-664.5239, device='cuda:0')
epoch: 26 test_true_pfm: 286.5339853657977 sim_pfm: -847.1626589881101
episode: 104 training return: tensor(-836.5540, device='cuda:0')
episode: 105 training return: tensor(-795.3248, device='cuda:0')
episode: 106 training return: tensor(-843.5218, device='cuda:0')
episode: 107 training return: tensor(-855.4586, device='cuda:0')
epoch: 27 test_true_pfm: 310.2037984341645 sim_pfm: -844.9778681109892
episode: 108 training return: tensor(-849.5688, device='cuda:0')
episode: 109 training return: tensor(-806.0232, device='cuda:0')
episode: 110 training return: tensor(-848.8724, device='cuda:0')
episode: 111 training return: tensor(-785.6115, device='cuda:0')
epoch: 28 test_true_pfm: 313.762289960963 sim_pfm: -840.0646567992711
episode: 112 training return: tensor(-847.0327, device='cuda:0')
episode: 113 training return: tensor(-842.1532, device='cuda:0')
episode: 114 training return: tensor(-836.0397, device='cuda:0')
episode: 115 training return: tensor(-592.7872, device='cuda:0')
epoch: 29 test_true_pfm: 270.41298035994674 sim_pfm: -521.3581021021431
episode: 116 training return: tensor(-655.5368, device='cuda:0')
episode: 117 training return: tensor(-840.2415, device='cuda:0')
episode: 118 training return: tensor(-523.2074, device='cuda:0')
episode: 119 training return: tensor(-538.7117, device='cuda:0')
epoch: 30 test_true_pfm: 314.0595806805971 sim_pfm: -506.22850812824134
episode: 120 training return: tensor(-582.9795, device='cuda:0')
episode: 121 training return: tensor(-501.8988, device='cuda:0')
episode: 122 training return: tensor(-523.4707, device='cuda:0')
episode: 123 training return: tensor(-527.6959, device='cuda:0')
epoch: 31 test_true_pfm: 274.0372517855247 sim_pfm: -498.96982881783816
episode: 124 training return: tensor(-548.6931, device='cuda:0')
episode: 125 training return: tensor(-523.1886, device='cuda:0')
episode: 126 training return: tensor(-525.6764, device='cuda:0')
episode: 127 training return: tensor(-500.1167, device='cuda:0')
epoch: 32 test_true_pfm: 323.7078362820077 sim_pfm: -441.3350853347608
episode: 128 training return: tensor(-516.5815, device='cuda:0')
episode: 129 training return: tensor(-507.5988, device='cuda:0')
episode: 130 training return: tensor(-537.5916, device='cuda:0')
episode: 131 training return: tensor(-542.2825, device='cuda:0')
epoch: 33 test_true_pfm: 338.13025417056105 sim_pfm: -490.8614169636664
episode: 132 training return: tensor(-520.0258, device='cuda:0')
episode: 133 training return: tensor(-512.4916, device='cuda:0')
episode: 134 training return: tensor(-472.6923, device='cuda:0')
episode: 135 training return: tensor(-504.6672, device='cuda:0')
epoch: 34 test_true_pfm: 368.4126560895567 sim_pfm: -479.0606169877574
episode: 136 training return: tensor(-488.1516, device='cuda:0')
episode: 137 training return: tensor(-493.0003, device='cuda:0')
episode: 138 training return: tensor(-433.6630, device='cuda:0')
episode: 139 training return: tensor(-498.0121, device='cuda:0')
epoch: 35 test_true_pfm: 506.54201936792515 sim_pfm: -420.5757481470161
episode: 140 training return: tensor(-497.4937, device='cuda:0')
episode: 141 training return: tensor(-493.3042, device='cuda:0')
episode: 142 training return: tensor(-501.1368, device='cuda:0')
episode: 143 training return: tensor(-431.4666, device='cuda:0')
epoch: 36 test_true_pfm: 497.91197253175807 sim_pfm: -412.33543039074476
episode: 144 training return: tensor(-494.3226, device='cuda:0')
episode: 145 training return: tensor(-478.4969, device='cuda:0')
episode: 146 training return: tensor(-522.1789, device='cuda:0')
episode: 147 training return: tensor(-483.1508, device='cuda:0')
epoch: 37 test_true_pfm: 459.124344207466 sim_pfm: -422.68303538594046
episode: 148 training return: tensor(-524.5321, device='cuda:0')
episode: 149 training return: tensor(-455.0501, device='cuda:0')
episode: 150 training return: tensor(-487.6919, device='cuda:0')
episode: 151 training return: tensor(-501.8686, device='cuda:0')
epoch: 38 test_true_pfm: 446.95053722348547 sim_pfm: -422.1920977600773
episode: 152 training return: tensor(-447.4845, device='cuda:0')
episode: 153 training return: tensor(-446.8698, device='cuda:0')
episode: 154 training return: tensor(-437.1926, device='cuda:0')
episode: 155 training return: tensor(-444.5693, device='cuda:0')
epoch: 39 test_true_pfm: 397.5920343878235 sim_pfm: -416.06806350887445
episode: 156 training return: tensor(-424.0979, device='cuda:0')
episode: 157 training return: tensor(-439.6045, device='cuda:0')
episode: 158 training return: tensor(-430.7067, device='cuda:0')
episode: 159 training return: tensor(-449.3893, device='cuda:0')
epoch: 40 test_true_pfm: 369.15705948332646 sim_pfm: -426.2888825882498
episode: 160 training return: tensor(-438.4205, device='cuda:0')
episode: 161 training return: tensor(-434.7066, device='cuda:0')
episode: 162 training return: tensor(-442.5585, device='cuda:0')
episode: 163 training return: tensor(-443.3579, device='cuda:0')
epoch: 41 test_true_pfm: 421.03888277636844 sim_pfm: -440.1366204796359
episode: 164 training return: tensor(-453.7903, device='cuda:0')
episode: 165 training return: tensor(-451.2227, device='cuda:0')
episode: 166 training return: tensor(-429.3566, device='cuda:0')
episode: 167 training return: tensor(-434.3788, device='cuda:0')
epoch: 42 test_true_pfm: 328.91876461719886 sim_pfm: -424.9592670899001
episode: 168 training return: tensor(-434.8330, device='cuda:0')
episode: 169 training return: tensor(-445.0669, device='cuda:0')
episode: 170 training return: tensor(-436.9060, device='cuda:0')
episode: 171 training return: tensor(-572.1048, device='cuda:0')
epoch: 43 test_true_pfm: 318.5461088760158 sim_pfm: -431.06051538255997
episode: 172 training return: tensor(-437.9944, device='cuda:0')
episode: 173 training return: tensor(-433.9375, device='cuda:0')
episode: 174 training return: tensor(-431.1130, device='cuda:0')
episode: 175 training return: tensor(-418.2413, device='cuda:0')
epoch: 44 test_true_pfm: 364.9134802030847 sim_pfm: -418.76736730973545
episode: 176 training return: tensor(-457.7910, device='cuda:0')
episode: 177 training return: tensor(-446.5978, device='cuda:0')
episode: 178 training return: tensor(-424.8364, device='cuda:0')
episode: 179 training return: tensor(-478.0237, device='cuda:0')
epoch: 45 test_true_pfm: 378.1423540727517 sim_pfm: -411.43537962002057
episode: 180 training return: tensor(-450.1838, device='cuda:0')
episode: 181 training return: tensor(-411.1524, device='cuda:0')
episode: 182 training return: tensor(-428.9305, device='cuda:0')
episode: 183 training return: tensor(-434.5947, device='cuda:0')
epoch: 46 test_true_pfm: 329.39170332804196 sim_pfm: -423.0160732394822
episode: 184 training return: tensor(-424.3062, device='cuda:0')
episode: 185 training return: tensor(-423.9850, device='cuda:0')
episode: 186 training return: tensor(-424.6024, device='cuda:0')
episode: 187 training return: tensor(-403.9658, device='cuda:0')
epoch: 47 test_true_pfm: 356.1784281258328 sim_pfm: -403.72417493828107
episode: 188 training return: tensor(-433.9804, device='cuda:0')
episode: 189 training return: tensor(-419.2725, device='cuda:0')
episode: 190 training return: tensor(-437.3821, device='cuda:0')
episode: 191 training return: tensor(-436.7619, device='cuda:0')
epoch: 48 test_true_pfm: 467.7427518196818 sim_pfm: -349.04299816334
episode: 192 training return: tensor(-434.2432, device='cuda:0')
episode: 193 training return: tensor(-417.3482, device='cuda:0')
episode: 194 training return: tensor(-427.1270, device='cuda:0')
episode: 195 training return: tensor(-476.3726, device='cuda:0')
epoch: 49 test_true_pfm: 528.2289373764546 sim_pfm: -356.9147329555514
episode: 196 training return: tensor(-428.0508, device='cuda:0')
episode: 197 training return: tensor(-421.1129, device='cuda:0')
episode: 198 training return: tensor(-419.4224, device='cuda:0')
episode: 199 training return: tensor(-423.8223, device='cuda:0')
epoch: 50 test_true_pfm: 360.48529371701306 sim_pfm: -419.3729038795961
episode: 200 training return: tensor(-440.2577, device='cuda:0')
episode: 201 training return: tensor(-442.3520, device='cuda:0')
episode: 202 training return: tensor(-444.1686, device='cuda:0')
episode: 203 training return: tensor(-444.2961, device='cuda:0')
epoch: 51 test_true_pfm: 438.31526808796997 sim_pfm: -402.6454862291769
episode: 204 training return: tensor(-427.0561, device='cuda:0')
episode: 205 training return: tensor(-397.5840, device='cuda:0')
episode: 206 training return: tensor(-426.2231, device='cuda:0')
episode: 207 training return: tensor(-439.1225, device='cuda:0')
epoch: 52 test_true_pfm: 362.8465893522966 sim_pfm: -409.3636802728288
episode: 208 training return: tensor(-432.3456, device='cuda:0')
episode: 209 training return: tensor(-419.3304, device='cuda:0')
episode: 210 training return: tensor(-458.7861, device='cuda:0')
episode: 211 training return: tensor(-431.3549, device='cuda:0')
epoch: 53 test_true_pfm: 454.36213785424593 sim_pfm: -379.516647132424
episode: 212 training return: tensor(-432.4190, device='cuda:0')
episode: 213 training return: tensor(-426.8010, device='cuda:0')
episode: 214 training return: tensor(-416.1280, device='cuda:0')
episode: 215 training return: tensor(-427.9533, device='cuda:0')
epoch: 54 test_true_pfm: 495.31658783431766 sim_pfm: -362.8110246085562
episode: 216 training return: tensor(-418.2931, device='cuda:0')
episode: 217 training return: tensor(-441.6962, device='cuda:0')
episode: 218 training return: tensor(-427.5797, device='cuda:0')
episode: 219 training return: tensor(-433.2359, device='cuda:0')
epoch: 55 test_true_pfm: 536.8962499270899 sim_pfm: -331.34482584689977
episode: 220 training return: tensor(-446.2523, device='cuda:0')
episode: 221 training return: tensor(-436.9056, device='cuda:0')
episode: 222 training return: tensor(-378.8591, device='cuda:0')
episode: 223 training return: tensor(-425.1903, device='cuda:0')
epoch: 56 test_true_pfm: 536.7930575182268 sim_pfm: -350.9861172138092
episode: 224 training return: tensor(-418.3111, device='cuda:0')
episode: 225 training return: tensor(-424.1963, device='cuda:0')
episode: 226 training return: tensor(-418.2185, device='cuda:0')
episode: 227 training return: tensor(-405.5102, device='cuda:0')
epoch: 57 test_true_pfm: 532.3011208245059 sim_pfm: -339.33267207536846
episode: 228 training return: tensor(-428.1315, device='cuda:0')
episode: 229 training return: tensor(-409.6445, device='cuda:0')
episode: 230 training return: tensor(-427.6993, device='cuda:0')
episode: 231 training return: tensor(-416.2915, device='cuda:0')
epoch: 58 test_true_pfm: 500.64275607217434 sim_pfm: -346.74039538530633
episode: 232 training return: tensor(-431.4914, device='cuda:0')
episode: 233 training return: tensor(-434.6154, device='cuda:0')
episode: 234 training return: tensor(-405.3806, device='cuda:0')
episode: 235 training return: tensor(-407.9703, device='cuda:0')
epoch: 59 test_true_pfm: 484.77404645270775 sim_pfm: -341.371798732318
episode: 236 training return: tensor(-419.0009, device='cuda:0')
episode: 237 training return: tensor(-423.3564, device='cuda:0')
episode: 238 training return: tensor(-416.1012, device='cuda:0')
episode: 239 training return: tensor(-415.6379, device='cuda:0')
epoch: 60 test_true_pfm: 508.0995061503709 sim_pfm: -335.011905390614
episode: 240 training return: tensor(-434.0886, device='cuda:0')
episode: 241 training return: tensor(-417.7297, device='cuda:0')
episode: 242 training return: tensor(-423.6481, device='cuda:0')
episode: 243 training return: tensor(-414.9946, device='cuda:0')
epoch: 61 test_true_pfm: 517.7626235754881 sim_pfm: -361.53450397045043
episode: 244 training return: tensor(-400.6996, device='cuda:0')
episode: 245 training return: tensor(-403.3405, device='cuda:0')
episode: 246 training return: tensor(-429.0913, device='cuda:0')
episode: 247 training return: tensor(-409.2095, device='cuda:0')
epoch: 62 test_true_pfm: 514.7858088246301 sim_pfm: -344.894943461443
episode: 248 training return: tensor(-388.1107, device='cuda:0')
episode: 249 training return: tensor(-408.8109, device='cuda:0')
episode: 250 training return: tensor(-442.1434, device='cuda:0')
episode: 251 training return: tensor(-410.1121, device='cuda:0')
epoch: 63 test_true_pfm: 455.6485656919302 sim_pfm: -358.42217957837664
episode: 252 training return: tensor(-421.4136, device='cuda:0')
episode: 253 training return: tensor(-384.2127, device='cuda:0')
episode: 254 training return: tensor(-416.1386, device='cuda:0')
episode: 255 training return: tensor(-433.9815, device='cuda:0')
epoch: 64 test_true_pfm: 457.10978454596017 sim_pfm: -345.75377757420455
episode: 256 training return: tensor(-414.2767, device='cuda:0')
episode: 257 training return: tensor(-421.8156, device='cuda:0')
episode: 258 training return: tensor(-374.8806, device='cuda:0')
episode: 259 training return: tensor(-384.7114, device='cuda:0')
epoch: 65 test_true_pfm: 457.83263616172275 sim_pfm: -339.4767394400357
episode: 260 training return: tensor(-408.6028, device='cuda:0')
episode: 261 training return: tensor(-410.2258, device='cuda:0')
episode: 262 training return: tensor(-402.8310, device='cuda:0')
episode: 263 training return: tensor(-414.0414, device='cuda:0')
epoch: 66 test_true_pfm: 485.9735895473084 sim_pfm: -330.9902647278116
episode: 264 training return: tensor(-415.9797, device='cuda:0')
episode: 265 training return: tensor(-429.6431, device='cuda:0')
episode: 266 training return: tensor(-406.3509, device='cuda:0')
episode: 267 training return: tensor(-379.1053, device='cuda:0')
epoch: 67 test_true_pfm: 467.02061878115455 sim_pfm: -331.31661334571737
episode: 268 training return: tensor(-405.6767, device='cuda:0')
episode: 269 training return: tensor(-426.6971, device='cuda:0')
episode: 270 training return: tensor(-439.0024, device='cuda:0')
episode: 271 training return: tensor(-370.8035, device='cuda:0')
epoch: 68 test_true_pfm: 429.42694850334664 sim_pfm: -365.9195904474861
episode: 272 training return: tensor(-440.6989, device='cuda:0')
episode: 273 training return: tensor(-379.2082, device='cuda:0')
episode: 274 training return: tensor(-416.5922, device='cuda:0')
episode: 275 training return: tensor(-409.7446, device='cuda:0')
epoch: 69 test_true_pfm: 501.4244498314406 sim_pfm: -328.50683733727783
episode: 276 training return: tensor(-389.5799, device='cuda:0')
episode: 277 training return: tensor(-421.4490, device='cuda:0')
episode: 278 training return: tensor(-382.7881, device='cuda:0')
episode: 279 training return: tensor(-421.9723, device='cuda:0')
epoch: 70 test_true_pfm: 509.9136307500466 sim_pfm: -330.090001825088
episode: 280 training return: tensor(-388.3721, device='cuda:0')
episode: 281 training return: tensor(-406.8786, device='cuda:0')
episode: 282 training return: tensor(-410.0133, device='cuda:0')
episode: 283 training return: tensor(-418.3951, device='cuda:0')
epoch: 71 test_true_pfm: 424.2822656164337 sim_pfm: -336.5255332646581
episode: 284 training return: tensor(-415.8977, device='cuda:0')
episode: 285 training return: tensor(-419.7983, device='cuda:0')
episode: 286 training return: tensor(-402.1647, device='cuda:0')
episode: 287 training return: tensor(-416.2857, device='cuda:0')
epoch: 72 test_true_pfm: 460.0766063061658 sim_pfm: -340.3699188423343
episode: 288 training return: tensor(-378.1580, device='cuda:0')
episode: 289 training return: tensor(-387.1813, device='cuda:0')
episode: 290 training return: tensor(-394.9731, device='cuda:0')
episode: 291 training return: tensor(-405.7456, device='cuda:0')
epoch: 73 test_true_pfm: 502.8068190893785 sim_pfm: -321.10902916962124
episode: 292 training return: tensor(-425.1146, device='cuda:0')
episode: 293 training return: tensor(-414.9233, device='cuda:0')
episode: 294 training return: tensor(-393.7872, device='cuda:0')
episode: 295 training return: tensor(-414.5316, device='cuda:0')
epoch: 74 test_true_pfm: 372.34983190053816 sim_pfm: -362.25166960879386
episode: 296 training return: tensor(-427.3379, device='cuda:0')
episode: 297 training return: tensor(-409.8597, device='cuda:0')
episode: 298 training return: tensor(-412.7969, device='cuda:0')
episode: 299 training return: tensor(-411.4024, device='cuda:0')
epoch: 75 test_true_pfm: 449.7288236410712 sim_pfm: -344.909776700583
episode: 300 training return: tensor(-416.1423, device='cuda:0')
episode: 301 training return: tensor(-367.0734, device='cuda:0')
episode: 302 training return: tensor(-399.6730, device='cuda:0')
episode: 303 training return: tensor(-385.6253, device='cuda:0')
epoch: 76 test_true_pfm: 498.6311910297718 sim_pfm: -320.7560482445794
episode: 304 training return: tensor(-389.0963, device='cuda:0')
episode: 305 training return: tensor(-379.8549, device='cuda:0')
episode: 306 training return: tensor(-408.5725, device='cuda:0')
episode: 307 training return: tensor(-398.2094, device='cuda:0')
epoch: 77 test_true_pfm: 401.9917224491484 sim_pfm: -364.54651777407463
episode: 308 training return: tensor(-417.9925, device='cuda:0')
episode: 309 training return: tensor(-415.4807, device='cuda:0')
episode: 310 training return: tensor(-382.3009, device='cuda:0')
episode: 311 training return: tensor(-426.0434, device='cuda:0')
epoch: 78 test_true_pfm: 451.78272692538343 sim_pfm: -327.460987880826
episode: 312 training return: tensor(-418.6870, device='cuda:0')
episode: 313 training return: tensor(-408.1016, device='cuda:0')
episode: 314 training return: tensor(-385.2112, device='cuda:0')
episode: 315 training return: tensor(-432.3846, device='cuda:0')
epoch: 79 test_true_pfm: 520.5352431758705 sim_pfm: -318.39967228396563
episode: 316 training return: tensor(-371.1991, device='cuda:0')
episode: 317 training return: tensor(-374.9325, device='cuda:0')
episode: 318 training return: tensor(-375.3616, device='cuda:0')
episode: 319 training return: tensor(-400.9344, device='cuda:0')
epoch: 80 test_true_pfm: 520.0692735589338 sim_pfm: -310.41745640252094
episode: 320 training return: tensor(-351.6845, device='cuda:0')
episode: 321 training return: tensor(-404.9909, device='cuda:0')
episode: 322 training return: tensor(-373.0850, device='cuda:0')
episode: 323 training return: tensor(-377.2245, device='cuda:0')
epoch: 81 test_true_pfm: 447.81945276355424 sim_pfm: -326.5567133303266
episode: 324 training return: tensor(-403.9579, device='cuda:0')
episode: 325 training return: tensor(-368.9791, device='cuda:0')
episode: 326 training return: tensor(-398.5554, device='cuda:0')
episode: 327 training return: tensor(-415.3283, device='cuda:0')
epoch: 82 test_true_pfm: 507.482029045856 sim_pfm: -312.64798017940484
episode: 328 training return: tensor(-409.6463, device='cuda:0')
episode: 329 training return: tensor(-417.8901, device='cuda:0')
episode: 330 training return: tensor(-356.1628, device='cuda:0')
episode: 331 training return: tensor(-409.3239, device='cuda:0')
epoch: 83 test_true_pfm: 504.32779724496004 sim_pfm: -337.536150505223
episode: 332 training return: tensor(-434.1423, device='cuda:0')
episode: 333 training return: tensor(-364.8733, device='cuda:0')
episode: 334 training return: tensor(-376.8195, device='cuda:0')
episode: 335 training return: tensor(-377.6286, device='cuda:0')
epoch: 84 test_true_pfm: 453.9559950388212 sim_pfm: -340.52062685372465
episode: 336 training return: tensor(-383.6661, device='cuda:0')
episode: 337 training return: tensor(-321.4551, device='cuda:0')
episode: 338 training return: tensor(-381.8803, device='cuda:0')
episode: 339 training return: tensor(-351.3686, device='cuda:0')
epoch: 85 test_true_pfm: 522.2495437201059 sim_pfm: -320.1343160532415
episode: 340 training return: tensor(-416.7081, device='cuda:0')
episode: 341 training return: tensor(-356.8115, device='cuda:0')
episode: 342 training return: tensor(-411.8235, device='cuda:0')
episode: 343 training return: tensor(-405.9296, device='cuda:0')
epoch: 86 test_true_pfm: 511.14585066250646 sim_pfm: -303.2905989353312
episode: 344 training return: tensor(-384.8291, device='cuda:0')
episode: 345 training return: tensor(-396.5948, device='cuda:0')
episode: 346 training return: tensor(-406.8811, device='cuda:0')
episode: 347 training return: tensor(-366.1833, device='cuda:0')
epoch: 87 test_true_pfm: 541.7569237073772 sim_pfm: -287.69073227373883
episode: 348 training return: tensor(-405.5161, device='cuda:0')
episode: 349 training return: tensor(-373.3874, device='cuda:0')
episode: 350 training return: tensor(-393.2520, device='cuda:0')
episode: 351 training return: tensor(-396.4533, device='cuda:0')
epoch: 88 test_true_pfm: 432.5515684727461 sim_pfm: -330.5989819877238
episode: 352 training return: tensor(-377.1101, device='cuda:0')
episode: 353 training return: tensor(-391.0400, device='cuda:0')
episode: 354 training return: tensor(-403.6628, device='cuda:0')
episode: 355 training return: tensor(-363.5630, device='cuda:0')
epoch: 89 test_true_pfm: 529.20749752893 sim_pfm: -299.05769343666424
episode: 356 training return: tensor(-395.4564, device='cuda:0')
episode: 357 training return: tensor(-375.9585, device='cuda:0')
episode: 358 training return: tensor(-387.7668, device='cuda:0')
episode: 359 training return: tensor(-365.7327, device='cuda:0')
epoch: 90 test_true_pfm: 494.7199552354814 sim_pfm: -316.14106427982915
episode: 360 training return: tensor(-399.8061, device='cuda:0')
episode: 361 training return: tensor(-377.2764, device='cuda:0')
episode: 362 training return: tensor(-382.3377, device='cuda:0')
episode: 363 training return: tensor(-375.3076, device='cuda:0')
epoch: 91 test_true_pfm: 456.8841889984014 sim_pfm: -317.0389831309828
episode: 364 training return: tensor(-396.7309, device='cuda:0')
episode: 365 training return: tensor(-366.7294, device='cuda:0')
episode: 366 training return: tensor(-350.9534, device='cuda:0')
episode: 367 training return: tensor(-377.2765, device='cuda:0')
epoch: 92 test_true_pfm: 538.9226095576063 sim_pfm: -285.9927277400663
episode: 368 training return: tensor(-372.2991, device='cuda:0')
episode: 369 training return: tensor(-375.5818, device='cuda:0')
episode: 370 training return: tensor(-379.4702, device='cuda:0')
episode: 371 training return: tensor(-408.7951, device='cuda:0')
epoch: 93 test_true_pfm: 394.7110040051585 sim_pfm: -312.52074865375954
episode: 372 training return: tensor(-401.5645, device='cuda:0')
episode: 373 training return: tensor(-378.1841, device='cuda:0')
episode: 374 training return: tensor(-382.7260, device='cuda:0')
episode: 375 training return: tensor(-406.2299, device='cuda:0')
epoch: 94 test_true_pfm: 555.1122235312922 sim_pfm: -456.68548703193665
episode: 376 training return: tensor(-357.3489, device='cuda:0')
episode: 377 training return: tensor(-345.8400, device='cuda:0')
episode: 378 training return: tensor(-377.9421, device='cuda:0')
episode: 379 training return: tensor(-409.9217, device='cuda:0')
epoch: 95 test_true_pfm: 504.74951684640996 sim_pfm: -296.3237410688307
episode: 380 training return: tensor(-403.9955, device='cuda:0')
episode: 381 training return: tensor(-390.7306, device='cuda:0')
episode: 382 training return: tensor(-392.5482, device='cuda:0')
episode: 383 training return: tensor(-406.6335, device='cuda:0')
epoch: 96 test_true_pfm: 453.32329045417765 sim_pfm: -307.09746527475846
episode: 384 training return: tensor(-369.7064, device='cuda:0')
episode: 385 training return: tensor(-390.5138, device='cuda:0')
episode: 386 training return: tensor(-383.2742, device='cuda:0')
episode: 387 training return: tensor(-358.8619, device='cuda:0')
epoch: 97 test_true_pfm: 482.83068677596043 sim_pfm: -320.6499810634414
episode: 388 training return: tensor(-391.2473, device='cuda:0')
episode: 389 training return: tensor(-372.9426, device='cuda:0')
episode: 390 training return: tensor(-384.5255, device='cuda:0')
episode: 391 training return: tensor(-371.6281, device='cuda:0')
epoch: 98 test_true_pfm: 479.6879570045074 sim_pfm: -314.1089003308055
episode: 392 training return: tensor(-332.4560, device='cuda:0')
episode: 393 training return: tensor(-382.3332, device='cuda:0')
episode: 394 training return: tensor(-405.3095, device='cuda:0')
episode: 395 training return: tensor(-395.8604, device='cuda:0')
epoch: 99 test_true_pfm: 483.7928982730136 sim_pfm: -308.25183044653386
episode: 396 training return: tensor(-365.9995, device='cuda:0')
episode: 397 training return: tensor(-343.7927, device='cuda:0')
episode: 398 training return: tensor(-382.6556, device='cuda:0')
episode: 399 training return: tensor(-340.8695, device='cuda:0')
epoch: 100 test_true_pfm: 529.8753892400023 sim_pfm: -301.65202220669016
episode: 400 training return: tensor(-362.5049, device='cuda:0')
episode: 401 training return: tensor(-368.9302, device='cuda:0')
episode: 402 training return: tensor(-371.1696, device='cuda:0')
episode: 403 training return: tensor(-356.2804, device='cuda:0')
epoch: 101 test_true_pfm: 454.741575126473 sim_pfm: -310.0530969876175
episode: 404 training return: tensor(-336.5156, device='cuda:0')
episode: 405 training return: tensor(-366.0898, device='cuda:0')
episode: 406 training return: tensor(-330.4153, device='cuda:0')
episode: 407 training return: tensor(-413.1988, device='cuda:0')
epoch: 102 test_true_pfm: 463.26905147772044 sim_pfm: -288.28900162318797
episode: 408 training return: tensor(-318.3129, device='cuda:0')
episode: 409 training return: tensor(-368.0013, device='cuda:0')
episode: 410 training return: tensor(-329.1906, device='cuda:0')
episode: 411 training return: tensor(-324.0559, device='cuda:0')
epoch: 103 test_true_pfm: 510.1802780249712 sim_pfm: -296.89311426342465
episode: 412 training return: tensor(-323.3464, device='cuda:0')
episode: 413 training return: tensor(-342.8391, device='cuda:0')
episode: 414 training return: tensor(-377.6554, device='cuda:0')
episode: 415 training return: tensor(-338.6505, device='cuda:0')
epoch: 104 test_true_pfm: 401.3833154442819 sim_pfm: -328.4018213755141
episode: 416 training return: tensor(-401.4370, device='cuda:0')
episode: 417 training return: tensor(-365.7617, device='cuda:0')
episode: 418 training return: tensor(-349.1248, device='cuda:0')
episode: 419 training return: tensor(-331.2208, device='cuda:0')
epoch: 105 test_true_pfm: 449.2250628040445 sim_pfm: -299.3282912148473
episode: 420 training return: tensor(-337.8906, device='cuda:0')
episode: 421 training return: tensor(-396.3000, device='cuda:0')
episode: 422 training return: tensor(-343.8735, device='cuda:0')
episode: 423 training return: tensor(-375.8624, device='cuda:0')
epoch: 106 test_true_pfm: 486.55896084842425 sim_pfm: -303.7051864678894
episode: 424 training return: tensor(-336.8966, device='cuda:0')
episode: 425 training return: tensor(-369.2537, device='cuda:0')
episode: 426 training return: tensor(-323.0440, device='cuda:0')
episode: 427 training return: tensor(-367.2451, device='cuda:0')
epoch: 107 test_true_pfm: 482.2413774895774 sim_pfm: -308.07591177693877
episode: 428 training return: tensor(-394.8722, device='cuda:0')
episode: 429 training return: tensor(-343.0327, device='cuda:0')
episode: 430 training return: tensor(-353.1716, device='cuda:0')
episode: 431 training return: tensor(-363.9330, device='cuda:0')
epoch: 108 test_true_pfm: 462.92637119132877 sim_pfm: -305.37473482017714
episode: 432 training return: tensor(-340.2371, device='cuda:0')
episode: 433 training return: tensor(-331.2648, device='cuda:0')
episode: 434 training return: tensor(-346.2492, device='cuda:0')
episode: 435 training return: tensor(-382.5300, device='cuda:0')
epoch: 109 test_true_pfm: 455.01522169532853 sim_pfm: -298.00962618086487
episode: 436 training return: tensor(-350.7524, device='cuda:0')
episode: 437 training return: tensor(-385.4919, device='cuda:0')
episode: 438 training return: tensor(-392.6163, device='cuda:0')
episode: 439 training return: tensor(-343.8058, device='cuda:0')
epoch: 110 test_true_pfm: 517.4734716183821 sim_pfm: -303.3275361407238
episode: 440 training return: tensor(-330.9550, device='cuda:0')
episode: 441 training return: tensor(-392.8582, device='cuda:0')
episode: 442 training return: tensor(-348.1081, device='cuda:0')
episode: 443 training return: tensor(-355.6141, device='cuda:0')
epoch: 111 test_true_pfm: 466.86168363882683 sim_pfm: -294.79207245035406
episode: 444 training return: tensor(-342.3938, device='cuda:0')
episode: 445 training return: tensor(-328.6065, device='cuda:0')
episode: 446 training return: tensor(-314.5260, device='cuda:0')
episode: 447 training return: tensor(-325.9437, device='cuda:0')
epoch: 112 test_true_pfm: 492.5780397165913 sim_pfm: -303.5967392028542
episode: 448 training return: tensor(-325.9456, device='cuda:0')
episode: 449 training return: tensor(-369.1428, device='cuda:0')
episode: 450 training return: tensor(-391.1353, device='cuda:0')
episode: 451 training return: tensor(-336.4324, device='cuda:0')
epoch: 113 test_true_pfm: 444.84412954974323 sim_pfm: -308.9534071283027
episode: 452 training return: tensor(-389.1887, device='cuda:0')
episode: 453 training return: tensor(-353.3564, device='cuda:0')
episode: 454 training return: tensor(-371.0727, device='cuda:0')
episode: 455 training return: tensor(-336.4318, device='cuda:0')
epoch: 114 test_true_pfm: 428.5113283813933 sim_pfm: -322.78288971981965
episode: 456 training return: tensor(-384.5995, device='cuda:0')
episode: 457 training return: tensor(-337.4755, device='cuda:0')
episode: 458 training return: tensor(-384.9496, device='cuda:0')
episode: 459 training return: tensor(-344.0157, device='cuda:0')
epoch: 115 test_true_pfm: 401.1876136789663 sim_pfm: -308.15479882216704
episode: 460 training return: tensor(-353.1703, device='cuda:0')
episode: 461 training return: tensor(-357.3024, device='cuda:0')
episode: 462 training return: tensor(-330.3103, device='cuda:0')
episode: 463 training return: tensor(-346.8104, device='cuda:0')
epoch: 116 test_true_pfm: 539.1873310612217 sim_pfm: -300.9294829140417
episode: 464 training return: tensor(-343.5016, device='cuda:0')
episode: 465 training return: tensor(-326.5512, device='cuda:0')
episode: 466 training return: tensor(-348.5038, device='cuda:0')
episode: 467 training return: tensor(-337.2069, device='cuda:0')
epoch: 117 test_true_pfm: 446.6234784904232 sim_pfm: -301.4902825049746
episode: 468 training return: tensor(-347.5775, device='cuda:0')
episode: 469 training return: tensor(-343.0630, device='cuda:0')
episode: 470 training return: tensor(-357.5809, device='cuda:0')
episode: 471 training return: tensor(-333.9427, device='cuda:0')
epoch: 118 test_true_pfm: 453.16429337629353 sim_pfm: -309.101233570138
episode: 472 training return: tensor(-396.8607, device='cuda:0')
episode: 473 training return: tensor(-328.9269, device='cuda:0')
episode: 474 training return: tensor(-329.3434, device='cuda:0')
episode: 475 training return: tensor(-333.6674, device='cuda:0')
epoch: 119 test_true_pfm: 412.1341683851654 sim_pfm: -313.3230465691304
episode: 476 training return: tensor(-359.6340, device='cuda:0')
episode: 477 training return: tensor(-355.5343, device='cuda:0')
episode: 478 training return: tensor(-361.1480, device='cuda:0')
episode: 479 training return: tensor(-339.2911, device='cuda:0')
epoch: 120 test_true_pfm: 467.9361039490232 sim_pfm: -296.8304606744011
episode: 480 training return: tensor(-335.5273, device='cuda:0')
episode: 481 training return: tensor(-396.8837, device='cuda:0')
episode: 482 training return: tensor(-343.2368, device='cuda:0')
episode: 483 training return: tensor(-327.6210, device='cuda:0')
epoch: 121 test_true_pfm: 434.0734337124563 sim_pfm: -304.9137429110706
episode: 484 training return: tensor(-381.3292, device='cuda:0')
episode: 485 training return: tensor(-370.2749, device='cuda:0')
episode: 486 training return: tensor(-358.7893, device='cuda:0')
episode: 487 training return: tensor(-357.4299, device='cuda:0')
epoch: 122 test_true_pfm: 487.4335369824689 sim_pfm: -290.46308425472427
episode: 488 training return: tensor(-338.1903, device='cuda:0')
episode: 489 training return: tensor(-356.7340, device='cuda:0')
episode: 490 training return: tensor(-343.1537, device='cuda:0')
episode: 491 training return: tensor(-360.1093, device='cuda:0')
epoch: 123 test_true_pfm: 438.2647351441192 sim_pfm: -306.2340217816333
episode: 492 training return: tensor(-372.1972, device='cuda:0')
episode: 493 training return: tensor(-396.0844, device='cuda:0')
episode: 494 training return: tensor(-367.4298, device='cuda:0')
episode: 495 training return: tensor(-394.8915, device='cuda:0')
epoch: 124 test_true_pfm: 423.07927937886166 sim_pfm: -317.67838519796106
episode: 496 training return: tensor(-358.0874, device='cuda:0')
episode: 497 training return: tensor(-350.6490, device='cuda:0')
episode: 498 training return: tensor(-319.0596, device='cuda:0')
episode: 499 training return: tensor(-352.8890, device='cuda:0')
epoch: 125 test_true_pfm: 449.827623270145 sim_pfm: -313.64133833907545
episode: 500 training return: tensor(-323.0674, device='cuda:0')
episode: 501 training return: tensor(-322.4541, device='cuda:0')
episode: 502 training return: tensor(-334.3251, device='cuda:0')
episode: 503 training return: tensor(-341.8026, device='cuda:0')
epoch: 126 test_true_pfm: 459.42904819154023 sim_pfm: -303.3974953755581
episode: 504 training return: tensor(-366.9715, device='cuda:0')
episode: 505 training return: tensor(-339.1188, device='cuda:0')
episode: 506 training return: tensor(-341.9995, device='cuda:0')
episode: 507 training return: tensor(-338.2037, device='cuda:0')
epoch: 127 test_true_pfm: 422.5816919838068 sim_pfm: -316.7900463133119
episode: 508 training return: tensor(-358.9426, device='cuda:0')
episode: 509 training return: tensor(-339.6863, device='cuda:0')
episode: 510 training return: tensor(-339.0981, device='cuda:0')
episode: 511 training return: tensor(-374.4975, device='cuda:0')
epoch: 128 test_true_pfm: 366.56529403415084 sim_pfm: -317.0856323425348
episode: 512 training return: tensor(-348.4830, device='cuda:0')
episode: 513 training return: tensor(-340.4615, device='cuda:0')
episode: 514 training return: tensor(-354.7550, device='cuda:0')
episode: 515 training return: tensor(-343.1637, device='cuda:0')
epoch: 129 test_true_pfm: 459.5855760657023 sim_pfm: -287.9616226019959
episode: 516 training return: tensor(-341.8378, device='cuda:0')
episode: 517 training return: tensor(-337.4310, device='cuda:0')
episode: 518 training return: tensor(-328.0595, device='cuda:0')
episode: 519 training return: tensor(-322.6217, device='cuda:0')
epoch: 130 test_true_pfm: 478.61486132902263 sim_pfm: -288.6641082424515
episode: 520 training return: tensor(-378.8810, device='cuda:0')
episode: 521 training return: tensor(-372.4748, device='cuda:0')
episode: 522 training return: tensor(-333.3902, device='cuda:0')
episode: 523 training return: tensor(-354.7174, device='cuda:0')
epoch: 131 test_true_pfm: 444.42309504237704 sim_pfm: -312.9454369667898
episode: 524 training return: tensor(-334.7999, device='cuda:0')
episode: 525 training return: tensor(-356.9342, device='cuda:0')
episode: 526 training return: tensor(-331.8116, device='cuda:0')
episode: 527 training return: tensor(-352.7776, device='cuda:0')
epoch: 132 test_true_pfm: 440.5393540926684 sim_pfm: -305.23981040986837
episode: 528 training return: tensor(-358.2652, device='cuda:0')
episode: 529 training return: tensor(-342.3310, device='cuda:0')
episode: 530 training return: tensor(-357.5363, device='cuda:0')
episode: 531 training return: tensor(-350.4815, device='cuda:0')
epoch: 133 test_true_pfm: 476.5651239795707 sim_pfm: -302.85991798108444
episode: 532 training return: tensor(-328.4873, device='cuda:0')
episode: 533 training return: tensor(-366.7197, device='cuda:0')
episode: 534 training return: tensor(-330.0997, device='cuda:0')
episode: 535 training return: tensor(-374.6473, device='cuda:0')
epoch: 134 test_true_pfm: 482.2693534650884 sim_pfm: -296.0672559477389
episode: 536 training return: tensor(-345.1523, device='cuda:0')
episode: 537 training return: tensor(-325.4972, device='cuda:0')
episode: 538 training return: tensor(-339.9295, device='cuda:0')
episode: 539 training return: tensor(-381.4576, device='cuda:0')
epoch: 135 test_true_pfm: 460.3967544909283 sim_pfm: -291.9755605329992
episode: 540 training return: tensor(-384.6261, device='cuda:0')
episode: 541 training return: tensor(-374.3588, device='cuda:0')
episode: 542 training return: tensor(-384.4861, device='cuda:0')
episode: 543 training return: tensor(-375.6516, device='cuda:0')
epoch: 136 test_true_pfm: 405.64613040000995 sim_pfm: -304.05869058977504
episode: 544 training return: tensor(-368.4573, device='cuda:0')
episode: 545 training return: tensor(-311.8791, device='cuda:0')
episode: 546 training return: tensor(-365.8452, device='cuda:0')
episode: 547 training return: tensor(-330.2854, device='cuda:0')
epoch: 137 test_true_pfm: 470.81185557586645 sim_pfm: -296.00073636385304
episode: 548 training return: tensor(-302.4698, device='cuda:0')
episode: 549 training return: tensor(-322.5005, device='cuda:0')
episode: 550 training return: tensor(-327.8004, device='cuda:0')
episode: 551 training return: tensor(-313.8052, device='cuda:0')
epoch: 138 test_true_pfm: 383.13086199941404 sim_pfm: -314.2553431758036
episode: 552 training return: tensor(-340.3938, device='cuda:0')
episode: 553 training return: tensor(-349.8427, device='cuda:0')
episode: 554 training return: tensor(-338.6817, device='cuda:0')
episode: 555 training return: tensor(-326.6629, device='cuda:0')
epoch: 139 test_true_pfm: 438.5412954059068 sim_pfm: -297.5425979439169
episode: 556 training return: tensor(-318.4758, device='cuda:0')
episode: 557 training return: tensor(-365.5060, device='cuda:0')
episode: 558 training return: tensor(-318.0773, device='cuda:0')
episode: 559 training return: tensor(-357.2377, device='cuda:0')
epoch: 140 test_true_pfm: 480.88111335308867 sim_pfm: -301.86761724436656
episode: 560 training return: tensor(-325.1294, device='cuda:0')
episode: 561 training return: tensor(-325.5507, device='cuda:0')
episode: 562 training return: tensor(-326.9307, device='cuda:0')
episode: 563 training return: tensor(-366.8745, device='cuda:0')
epoch: 141 test_true_pfm: 462.57346337824873 sim_pfm: -302.0538468948798
episode: 564 training return: tensor(-338.5401, device='cuda:0')
episode: 565 training return: tensor(-332.6293, device='cuda:0')
episode: 566 training return: tensor(-344.5903, device='cuda:0')
episode: 567 training return: tensor(-351.4361, device='cuda:0')
epoch: 142 test_true_pfm: 386.0325865820048 sim_pfm: -299.5328117449147
episode: 568 training return: tensor(-335.3049, device='cuda:0')
episode: 569 training return: tensor(-340.3964, device='cuda:0')
episode: 570 training return: tensor(-326.0348, device='cuda:0')
episode: 571 training return: tensor(-333.3696, device='cuda:0')
epoch: 143 test_true_pfm: 445.03206208272945 sim_pfm: -304.2850226129328
episode: 572 training return: tensor(-324.1468, device='cuda:0')
episode: 573 training return: tensor(-349.7188, device='cuda:0')
episode: 574 training return: tensor(-337.4866, device='cuda:0')
episode: 575 training return: tensor(-318.9675, device='cuda:0')
epoch: 144 test_true_pfm: 447.9033500755072 sim_pfm: -299.57624748628587
episode: 576 training return: tensor(-318.3596, device='cuda:0')
episode: 577 training return: tensor(-345.4646, device='cuda:0')
episode: 578 training return: tensor(-332.5862, device='cuda:0')
episode: 579 training return: tensor(-361.0640, device='cuda:0')
epoch: 145 test_true_pfm: 373.84398837738604 sim_pfm: -302.978332523761
episode: 580 training return: tensor(-375.7923, device='cuda:0')
episode: 581 training return: tensor(-314.3723, device='cuda:0')
episode: 582 training return: tensor(-356.7196, device='cuda:0')
episode: 583 training return: tensor(-322.7231, device='cuda:0')
epoch: 146 test_true_pfm: 462.1573077674181 sim_pfm: -295.2947728680544
episode: 584 training return: tensor(-329.5383, device='cuda:0')
episode: 585 training return: tensor(-348.4298, device='cuda:0')
episode: 586 training return: tensor(-312.1167, device='cuda:0')
episode: 587 training return: tensor(-385.7383, device='cuda:0')
epoch: 147 test_true_pfm: 433.35366220530005 sim_pfm: -300.5744603748123
episode: 588 training return: tensor(-338.0974, device='cuda:0')
episode: 589 training return: tensor(-345.3652, device='cuda:0')
episode: 590 training return: tensor(-405.9239, device='cuda:0')
episode: 591 training return: tensor(-323.8800, device='cuda:0')
epoch: 148 test_true_pfm: 393.6348668799137 sim_pfm: -313.79373793513514
episode: 592 training return: tensor(-340.1709, device='cuda:0')
episode: 593 training return: tensor(-333.3253, device='cuda:0')
episode: 594 training return: tensor(-354.7838, device='cuda:0')
episode: 595 training return: tensor(-349.2323, device='cuda:0')
epoch: 149 test_true_pfm: 425.25749514397563 sim_pfm: -310.32441589950275
episode: 596 training return: tensor(-335.3370, device='cuda:0')
episode: 597 training return: tensor(-340.9633, device='cuda:0')
episode: 598 training return: tensor(-337.2559, device='cuda:0')
episode: 599 training return: tensor(-318.7936, device='cuda:0')
epoch: 150 test_true_pfm: 447.19881261668934 sim_pfm: -304.06377496911836
