['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '2', '--data', '100000', '--regu', '0.3']
2720.658832205013
episode: 0 training return: tensor(133.6646, device='cuda:0')
episode: 1 training return: tensor(-471.8011, device='cuda:0')
episode: 2 training return: tensor(-141.9148, device='cuda:0')
episode: 3 training return: tensor(230.3761, device='cuda:0')
epoch: 1 test_true_pfm: 3162.0394623694697 sim_pfm: 128.61235885721786
episode: 4 training return: tensor(242.1934, device='cuda:0')
episode: 5 training return: tensor(244.4070, device='cuda:0')
episode: 6 training return: tensor(179.3180, device='cuda:0')
episode: 7 training return: tensor(-148.2946, device='cuda:0')
epoch: 2 test_true_pfm: 2780.024282495342 sim_pfm: 248.4658709926783
episode: 8 training return: tensor(-282.9064, device='cuda:0')
episode: 9 training return: tensor(262.8217, device='cuda:0')
episode: 10 training return: tensor(276.8653, device='cuda:0')
episode: 11 training return: tensor(214.2057, device='cuda:0')
epoch: 3 test_true_pfm: 3005.908533577746 sim_pfm: 121.25581555243116
episode: 12 training return: tensor(245.2118, device='cuda:0')
episode: 13 training return: tensor(134.9877, device='cuda:0')
episode: 14 training return: tensor(265.0151, device='cuda:0')
episode: 15 training return: tensor(288.2900, device='cuda:0')
epoch: 4 test_true_pfm: 3395.1474114833286 sim_pfm: 303.1402844120166
episode: 16 training return: tensor(314.1720, device='cuda:0')
episode: 17 training return: tensor(305.8061, device='cuda:0')
episode: 18 training return: tensor(228.3834, device='cuda:0')
episode: 19 training return: tensor(325.1097, device='cuda:0')
epoch: 5 test_true_pfm: 2620.1736031706314 sim_pfm: 119.59226091547559
episode: 20 training return: tensor(291.1086, device='cuda:0')
episode: 21 training return: tensor(330.4938, device='cuda:0')
episode: 22 training return: tensor(291.1045, device='cuda:0')
episode: 23 training return: tensor(269.8989, device='cuda:0')
epoch: 6 test_true_pfm: 3499.4049202807037 sim_pfm: 177.85501609905623
episode: 24 training return: tensor(319.9995, device='cuda:0')
episode: 25 training return: tensor(-234.6909, device='cuda:0')
episode: 26 training return: tensor(361.9338, device='cuda:0')
episode: 27 training return: tensor(337.9199, device='cuda:0')
epoch: 7 test_true_pfm: 2952.356657353778 sim_pfm: -94.20725902997462
episode: 28 training return: tensor(19.7773, device='cuda:0')
episode: 29 training return: tensor(350.0246, device='cuda:0')
episode: 30 training return: tensor(149.1988, device='cuda:0')
episode: 31 training return: tensor(320.3088, device='cuda:0')
epoch: 8 test_true_pfm: 2985.363149768593 sim_pfm: 370.2613664921567
episode: 32 training return: tensor(316.0522, device='cuda:0')
episode: 33 training return: tensor(315.0876, device='cuda:0')
episode: 34 training return: tensor(-311.1560, device='cuda:0')
episode: 35 training return: tensor(-162.8297, device='cuda:0')
epoch: 9 test_true_pfm: 3213.615146950313 sim_pfm: 305.9185364927398
episode: 36 training return: tensor(189.6326, device='cuda:0')
episode: 37 training return: tensor(50.0331, device='cuda:0')
episode: 38 training return: tensor(370.4905, device='cuda:0')
episode: 39 training return: tensor(138.5469, device='cuda:0')
epoch: 10 test_true_pfm: 3128.2570838836946 sim_pfm: 361.33302852654987
episode: 40 training return: tensor(330.0017, device='cuda:0')
episode: 41 training return: tensor(310.3425, device='cuda:0')
episode: 42 training return: tensor(281.1674, device='cuda:0')
episode: 43 training return: tensor(226.8562, device='cuda:0')
epoch: 11 test_true_pfm: 3483.271592548777 sim_pfm: 350.1549574439802
episode: 44 training return: tensor(277.7285, device='cuda:0')
episode: 45 training return: tensor(338.0179, device='cuda:0')
episode: 46 training return: tensor(-174.5340, device='cuda:0')
episode: 47 training return: tensor(362.6949, device='cuda:0')
epoch: 12 test_true_pfm: 3340.9078203942895 sim_pfm: 325.41715405514697
episode: 48 training return: tensor(432.9783, device='cuda:0')
episode: 49 training return: tensor(309.7872, device='cuda:0')
episode: 50 training return: tensor(378.5646, device='cuda:0')
episode: 51 training return: tensor(243.6975, device='cuda:0')
epoch: 13 test_true_pfm: 3555.350584282934 sim_pfm: 302.28826228606823
episode: 52 training return: tensor(360.5731, device='cuda:0')
episode: 53 training return: tensor(-130.0670, device='cuda:0')
episode: 54 training return: tensor(-204.8653, device='cuda:0')
episode: 55 training return: tensor(-287.7817, device='cuda:0')
epoch: 14 test_true_pfm: 3034.260096959188 sim_pfm: 342.5793433415917
episode: 56 training return: tensor(298.3380, device='cuda:0')
episode: 57 training return: tensor(374.9982, device='cuda:0')
episode: 58 training return: tensor(316.3643, device='cuda:0')
episode: 59 training return: tensor(-214.1595, device='cuda:0')
epoch: 15 test_true_pfm: 2374.0136406183865 sim_pfm: 318.37256848684046
episode: 60 training return: tensor(280.8358, device='cuda:0')
episode: 61 training return: tensor(299.3936, device='cuda:0')
episode: 62 training return: tensor(243.1155, device='cuda:0')
episode: 63 training return: tensor(312.8761, device='cuda:0')
epoch: 16 test_true_pfm: 3477.1108897244376 sim_pfm: 301.3707491917982
episode: 64 training return: tensor(360.4185, device='cuda:0')
episode: 65 training return: tensor(440.6780, device='cuda:0')
episode: 66 training return: tensor(-209.2705, device='cuda:0')
episode: 67 training return: tensor(284.0172, device='cuda:0')
epoch: 17 test_true_pfm: 3550.895237549676 sim_pfm: 438.7870944024762
episode: 68 training return: tensor(331.2031, device='cuda:0')
episode: 69 training return: tensor(-136.2737, device='cuda:0')
episode: 70 training return: tensor(403.4419, device='cuda:0')
episode: 71 training return: tensor(269.0750, device='cuda:0')
epoch: 18 test_true_pfm: 2758.244165553368 sim_pfm: 132.26408536899058
episode: 72 training return: tensor(302.7689, device='cuda:0')
episode: 73 training return: tensor(168.1338, device='cuda:0')
episode: 74 training return: tensor(368.8495, device='cuda:0')
episode: 75 training return: tensor(-245.8229, device='cuda:0')
epoch: 19 test_true_pfm: 3562.945240827949 sim_pfm: 407.2865741849916
episode: 76 training return: tensor(412.7697, device='cuda:0')
episode: 77 training return: tensor(341.6168, device='cuda:0')
episode: 78 training return: tensor(240.7642, device='cuda:0')
episode: 79 training return: tensor(333.9283, device='cuda:0')
epoch: 20 test_true_pfm: 2583.2300910486133 sim_pfm: 387.2821772035483
episode: 80 training return: tensor(-21.3718, device='cuda:0')
episode: 81 training return: tensor(301.0868, device='cuda:0')
episode: 82 training return: tensor(349.0656, device='cuda:0')
episode: 83 training return: tensor(294.5653, device='cuda:0')
epoch: 21 test_true_pfm: 3603.4234665177482 sim_pfm: 367.86086929403245
episode: 84 training return: tensor(366.9053, device='cuda:0')
episode: 85 training return: tensor(287.6750, device='cuda:0')
episode: 86 training return: tensor(-241.5355, device='cuda:0')
episode: 87 training return: tensor(343.6265, device='cuda:0')
epoch: 22 test_true_pfm: 3498.2466279374476 sim_pfm: 397.7315310688767
episode: 88 training return: tensor(364.4639, device='cuda:0')
episode: 89 training return: tensor(419.0663, device='cuda:0')
episode: 90 training return: tensor(369.2098, device='cuda:0')
episode: 91 training return: tensor(66.6778, device='cuda:0')
epoch: 23 test_true_pfm: 3528.459355167577 sim_pfm: 386.2836344955722
episode: 92 training return: tensor(39.0073, device='cuda:0')
episode: 93 training return: tensor(288.0563, device='cuda:0')
episode: 94 training return: tensor(286.5208, device='cuda:0')
episode: 95 training return: tensor(391.5090, device='cuda:0')
epoch: 24 test_true_pfm: 3553.752645899112 sim_pfm: 420.85650502090965
episode: 96 training return: tensor(64.9087, device='cuda:0')
episode: 97 training return: tensor(327.0973, device='cuda:0')
episode: 98 training return: tensor(353.3827, device='cuda:0')
episode: 99 training return: tensor(296.8159, device='cuda:0')
epoch: 25 test_true_pfm: 3655.4906244825183 sim_pfm: 299.9590897222127
episode: 100 training return: tensor(-18.1185, device='cuda:0')
episode: 101 training return: tensor(332.5250, device='cuda:0')
episode: 102 training return: tensor(353.5791, device='cuda:0')
episode: 103 training return: tensor(278.1386, device='cuda:0')
epoch: 26 test_true_pfm: 3270.9725226952064 sim_pfm: 390.5755842629199
episode: 104 training return: tensor(291.1227, device='cuda:0')
episode: 105 training return: tensor(214.6938, device='cuda:0')
episode: 106 training return: tensor(193.8366, device='cuda:0')
episode: 107 training return: tensor(430.2998, device='cuda:0')
epoch: 27 test_true_pfm: 3577.8549508413694 sim_pfm: 416.3658026534443
episode: 108 training return: tensor(287.8289, device='cuda:0')
episode: 109 training return: tensor(389.3542, device='cuda:0')
episode: 110 training return: tensor(373.0599, device='cuda:0')
episode: 111 training return: tensor(340.6856, device='cuda:0')
epoch: 28 test_true_pfm: 3482.7204986759134 sim_pfm: 381.0355811106565
episode: 112 training return: tensor(79.8049, device='cuda:0')
episode: 113 training return: tensor(61.0729, device='cuda:0')
episode: 114 training return: tensor(387.3411, device='cuda:0')
episode: 115 training return: tensor(321.9461, device='cuda:0')
epoch: 29 test_true_pfm: 3587.759974602295 sim_pfm: 424.68629447826726
episode: 116 training return: tensor(343.8065, device='cuda:0')
episode: 117 training return: tensor(386.8698, device='cuda:0')
episode: 118 training return: tensor(338.1061, device='cuda:0')
episode: 119 training return: tensor(80.8847, device='cuda:0')
epoch: 30 test_true_pfm: 3559.929871616818 sim_pfm: 413.52335578969604
episode: 120 training return: tensor(329.6091, device='cuda:0')
episode: 121 training return: tensor(479.6266, device='cuda:0')
episode: 122 training return: tensor(294.6541, device='cuda:0')
episode: 123 training return: tensor(252.5122, device='cuda:0')
epoch: 31 test_true_pfm: 3557.4302503732724 sim_pfm: 374.9066768216435
episode: 124 training return: tensor(338.9290, device='cuda:0')
episode: 125 training return: tensor(305.8376, device='cuda:0')
episode: 126 training return: tensor(351.2359, device='cuda:0')
episode: 127 training return: tensor(194.5182, device='cuda:0')
epoch: 32 test_true_pfm: 3458.4555612894133 sim_pfm: 410.12319440448965
episode: 128 training return: tensor(368.4128, device='cuda:0')
episode: 129 training return: tensor(331.4188, device='cuda:0')
episode: 130 training return: tensor(407.2838, device='cuda:0')
episode: 131 training return: tensor(363.7351, device='cuda:0')
epoch: 33 test_true_pfm: 3439.2590053143435 sim_pfm: 348.0742845624918
episode: 132 training return: tensor(427.1448, device='cuda:0')
episode: 133 training return: tensor(400.7215, device='cuda:0')
episode: 134 training return: tensor(349.0377, device='cuda:0')
episode: 135 training return: tensor(341.1208, device='cuda:0')
epoch: 34 test_true_pfm: 3356.606409677415 sim_pfm: 460.96441021433566
episode: 136 training return: tensor(363.4969, device='cuda:0')
episode: 137 training return: tensor(379.7152, device='cuda:0')
episode: 138 training return: tensor(338.3110, device='cuda:0')
episode: 139 training return: tensor(433.6301, device='cuda:0')
epoch: 35 test_true_pfm: 3546.0963637497675 sim_pfm: 320.7640657665809
episode: 140 training return: tensor(413.5112, device='cuda:0')
episode: 141 training return: tensor(424.7422, device='cuda:0')
episode: 142 training return: tensor(447.1223, device='cuda:0')
episode: 143 training return: tensor(336.1318, device='cuda:0')
epoch: 36 test_true_pfm: 3646.63495817005 sim_pfm: 444.9363912602421
episode: 144 training return: tensor(402.9883, device='cuda:0')
episode: 145 training return: tensor(353.7346, device='cuda:0')
episode: 146 training return: tensor(231.7648, device='cuda:0')
episode: 147 training return: tensor(416.5642, device='cuda:0')
epoch: 37 test_true_pfm: 3590.3734194870326 sim_pfm: 428.4195921559585
episode: 148 training return: tensor(435.2602, device='cuda:0')
episode: 149 training return: tensor(472.5139, device='cuda:0')
episode: 150 training return: tensor(481.2744, device='cuda:0')
episode: 151 training return: tensor(524.0717, device='cuda:0')
epoch: 38 test_true_pfm: 3755.4200102349882 sim_pfm: 456.7588963031497
episode: 152 training return: tensor(412.4149, device='cuda:0')
episode: 153 training return: tensor(420.8552, device='cuda:0')
episode: 154 training return: tensor(395.7320, device='cuda:0')
episode: 155 training return: tensor(391.1273, device='cuda:0')
epoch: 39 test_true_pfm: 3652.7648125055457 sim_pfm: 459.3568519821274
episode: 156 training return: tensor(367.1880, device='cuda:0')
episode: 157 training return: tensor(138.1219, device='cuda:0')
episode: 158 training return: tensor(430.9586, device='cuda:0')
episode: 159 training return: tensor(371.0533, device='cuda:0')
epoch: 40 test_true_pfm: 3604.247752572674 sim_pfm: 432.03197872739594
episode: 160 training return: tensor(412.6081, device='cuda:0')
episode: 161 training return: tensor(387.9865, device='cuda:0')
episode: 162 training return: tensor(462.7550, device='cuda:0')
episode: 163 training return: tensor(342.3509, device='cuda:0')
epoch: 41 test_true_pfm: 3608.518750205152 sim_pfm: 439.55075609326985
episode: 164 training return: tensor(443.8695, device='cuda:0')
episode: 165 training return: tensor(385.6216, device='cuda:0')
episode: 166 training return: tensor(336.4449, device='cuda:0')
episode: 167 training return: tensor(405.5805, device='cuda:0')
epoch: 42 test_true_pfm: 3775.86028962483 sim_pfm: 477.41489691117505
episode: 168 training return: tensor(405.1933, device='cuda:0')
episode: 169 training return: tensor(412.4802, device='cuda:0')
episode: 170 training return: tensor(400.6865, device='cuda:0')
episode: 171 training return: tensor(395.2972, device='cuda:0')
epoch: 43 test_true_pfm: 3656.8400789710836 sim_pfm: 476.23854556435253
episode: 172 training return: tensor(388.4730, device='cuda:0')
episode: 173 training return: tensor(428.1283, device='cuda:0')
episode: 174 training return: tensor(-136.2729, device='cuda:0')
episode: 175 training return: tensor(442.0959, device='cuda:0')
epoch: 44 test_true_pfm: 3678.446137692337 sim_pfm: 524.2998817520565
episode: 176 training return: tensor(362.0721, device='cuda:0')
episode: 177 training return: tensor(393.0660, device='cuda:0')
episode: 178 training return: tensor(420.6444, device='cuda:0')
episode: 179 training return: tensor(407.3968, device='cuda:0')
epoch: 45 test_true_pfm: 3694.2407125002005 sim_pfm: 508.2599114981713
episode: 180 training return: tensor(424.5279, device='cuda:0')
episode: 181 training return: tensor(401.3748, device='cuda:0')
episode: 182 training return: tensor(-178.0814, device='cuda:0')
episode: 183 training return: tensor(406.7494, device='cuda:0')
epoch: 46 test_true_pfm: 3630.4841740577817 sim_pfm: 482.7669180625041
episode: 184 training return: tensor(115.5529, device='cuda:0')
episode: 185 training return: tensor(385.1727, device='cuda:0')
episode: 186 training return: tensor(440.4844, device='cuda:0')
episode: 187 training return: tensor(405.6850, device='cuda:0')
epoch: 47 test_true_pfm: 3534.8563633396475 sim_pfm: 437.5881881203192
episode: 188 training return: tensor(432.3042, device='cuda:0')
episode: 189 training return: tensor(-397.5479, device='cuda:0')
episode: 190 training return: tensor(478.4322, device='cuda:0')
episode: 191 training return: tensor(392.3891, device='cuda:0')
epoch: 48 test_true_pfm: 3719.6230409487252 sim_pfm: 274.12428725050023
episode: 192 training return: tensor(371.2754, device='cuda:0')
episode: 193 training return: tensor(491.8702, device='cuda:0')
episode: 194 training return: tensor(425.8959, device='cuda:0')
episode: 195 training return: tensor(449.0451, device='cuda:0')
epoch: 49 test_true_pfm: 3689.9025287292084 sim_pfm: 479.25858094527695
episode: 196 training return: tensor(344.8269, device='cuda:0')
episode: 197 training return: tensor(347.7127, device='cuda:0')
episode: 198 training return: tensor(466.0879, device='cuda:0')
episode: 199 training return: tensor(452.1712, device='cuda:0')
epoch: 50 test_true_pfm: 3509.503224587999 sim_pfm: 411.1873837199528
episode: 200 training return: tensor(366.8223, device='cuda:0')
episode: 201 training return: tensor(443.4855, device='cuda:0')
episode: 202 training return: tensor(322.2695, device='cuda:0')
episode: 203 training return: tensor(397.4195, device='cuda:0')
epoch: 51 test_true_pfm: 3689.516428676117 sim_pfm: 507.6567511326866
episode: 204 training return: tensor(360.0959, device='cuda:0')
episode: 205 training return: tensor(414.4745, device='cuda:0')
episode: 206 training return: tensor(399.4601, device='cuda:0')
episode: 207 training return: tensor(385.5305, device='cuda:0')
epoch: 52 test_true_pfm: 3642.272861880009 sim_pfm: 423.7953991642765
episode: 208 training return: tensor(444.7520, device='cuda:0')
episode: 209 training return: tensor(375.5821, device='cuda:0')
episode: 210 training return: tensor(414.3415, device='cuda:0')
episode: 211 training return: tensor(409.0291, device='cuda:0')
epoch: 53 test_true_pfm: 3319.122454587299 sim_pfm: 458.83889097658295
episode: 212 training return: tensor(410.8141, device='cuda:0')
episode: 213 training return: tensor(409.0439, device='cuda:0')
episode: 214 training return: tensor(365.8872, device='cuda:0')
episode: 215 training return: tensor(398.1579, device='cuda:0')
epoch: 54 test_true_pfm: 3184.584613405373 sim_pfm: 423.3435248300666
episode: 216 training return: tensor(379.7773, device='cuda:0')
episode: 217 training return: tensor(344.0700, device='cuda:0')
episode: 218 training return: tensor(398.6491, device='cuda:0')
episode: 219 training return: tensor(428.2285, device='cuda:0')
epoch: 55 test_true_pfm: 3463.364027662064 sim_pfm: 479.91153995413333
episode: 220 training return: tensor(404.5515, device='cuda:0')
episode: 221 training return: tensor(408.6530, device='cuda:0')
episode: 222 training return: tensor(391.1570, device='cuda:0')
episode: 223 training return: tensor(307.1871, device='cuda:0')
epoch: 56 test_true_pfm: 3756.6833638113008 sim_pfm: 494.58098685225315
episode: 224 training return: tensor(443.4933, device='cuda:0')
episode: 225 training return: tensor(345.6570, device='cuda:0')
episode: 226 training return: tensor(472.6386, device='cuda:0')
episode: 227 training return: tensor(462.4924, device='cuda:0')
epoch: 57 test_true_pfm: 3651.431001701411 sim_pfm: 461.1266194815592
episode: 228 training return: tensor(472.1936, device='cuda:0')
episode: 229 training return: tensor(440.4801, device='cuda:0')
episode: 230 training return: tensor(502.9196, device='cuda:0')
episode: 231 training return: tensor(497.1674, device='cuda:0')
epoch: 58 test_true_pfm: 3686.766141633437 sim_pfm: 508.9148960089854
episode: 232 training return: tensor(429.7112, device='cuda:0')
episode: 233 training return: tensor(444.6849, device='cuda:0')
episode: 234 training return: tensor(367.1053, device='cuda:0')
episode: 235 training return: tensor(444.0217, device='cuda:0')
epoch: 59 test_true_pfm: 3778.3909013188036 sim_pfm: 525.7972866499719
episode: 236 training return: tensor(419.3866, device='cuda:0')
episode: 237 training return: tensor(-206.8370, device='cuda:0')
episode: 238 training return: tensor(452.2426, device='cuda:0')
episode: 239 training return: tensor(429.6332, device='cuda:0')
epoch: 60 test_true_pfm: 3730.3532241583093 sim_pfm: 514.4607067395312
episode: 240 training return: tensor(395.6877, device='cuda:0')
episode: 241 training return: tensor(467.4642, device='cuda:0')
episode: 242 training return: tensor(470.6076, device='cuda:0')
episode: 243 training return: tensor(497.0467, device='cuda:0')
epoch: 61 test_true_pfm: 3682.849931751938 sim_pfm: 499.8395216395923
episode: 244 training return: tensor(390.6233, device='cuda:0')
episode: 245 training return: tensor(410.2545, device='cuda:0')
episode: 246 training return: tensor(375.3447, device='cuda:0')
episode: 247 training return: tensor(410.5392, device='cuda:0')
epoch: 62 test_true_pfm: 3738.2440542242166 sim_pfm: 528.5448283015867
episode: 248 training return: tensor(400.8633, device='cuda:0')
episode: 249 training return: tensor(452.5523, device='cuda:0')
episode: 250 training return: tensor(461.1285, device='cuda:0')
episode: 251 training return: tensor(474.6805, device='cuda:0')
epoch: 63 test_true_pfm: 3747.9699649468234 sim_pfm: 548.6629451090994
episode: 252 training return: tensor(414.7745, device='cuda:0')
episode: 253 training return: tensor(381.4267, device='cuda:0')
episode: 254 training return: tensor(415.2853, device='cuda:0')
episode: 255 training return: tensor(514.3341, device='cuda:0')
epoch: 64 test_true_pfm: 3735.995918617014 sim_pfm: 508.40741157124285
episode: 256 training return: tensor(566.8480, device='cuda:0')
episode: 257 training return: tensor(91.7469, device='cuda:0')
episode: 258 training return: tensor(450.5592, device='cuda:0')
episode: 259 training return: tensor(443.2148, device='cuda:0')
epoch: 65 test_true_pfm: 3694.7790999404992 sim_pfm: 508.56421919795685
episode: 260 training return: tensor(486.2436, device='cuda:0')
episode: 261 training return: tensor(344.2440, device='cuda:0')
episode: 262 training return: tensor(449.8889, device='cuda:0')
episode: 263 training return: tensor(456.3988, device='cuda:0')
epoch: 66 test_true_pfm: 3701.0134473666963 sim_pfm: 475.8848129002533
episode: 264 training return: tensor(445.3037, device='cuda:0')
episode: 265 training return: tensor(432.0352, device='cuda:0')
episode: 266 training return: tensor(452.4797, device='cuda:0')
episode: 267 training return: tensor(395.4565, device='cuda:0')
epoch: 67 test_true_pfm: 3667.601324870066 sim_pfm: 464.56424801493995
episode: 268 training return: tensor(461.1219, device='cuda:0')
episode: 269 training return: tensor(281.6851, device='cuda:0')
episode: 270 training return: tensor(444.4287, device='cuda:0')
episode: 271 training return: tensor(447.9685, device='cuda:0')
epoch: 68 test_true_pfm: 3744.143745209765 sim_pfm: 428.2047450381797
episode: 272 training return: tensor(444.6835, device='cuda:0')
episode: 273 training return: tensor(473.0160, device='cuda:0')
episode: 274 training return: tensor(-616.4709, device='cuda:0')
episode: 275 training return: tensor(424.6544, device='cuda:0')
epoch: 69 test_true_pfm: 3783.2638030681096 sim_pfm: 531.3870711643152
episode: 276 training return: tensor(468.6456, device='cuda:0')
episode: 277 training return: tensor(414.8923, device='cuda:0')
episode: 278 training return: tensor(400.6665, device='cuda:0')
episode: 279 training return: tensor(490.8145, device='cuda:0')
epoch: 70 test_true_pfm: 3778.7573753635183 sim_pfm: 511.4877246651643
episode: 280 training return: tensor(488.9923, device='cuda:0')
episode: 281 training return: tensor(463.1362, device='cuda:0')
episode: 282 training return: tensor(450.8646, device='cuda:0')
episode: 283 training return: tensor(419.4844, device='cuda:0')
epoch: 71 test_true_pfm: 3658.84316302777 sim_pfm: 460.4717700746066
episode: 284 training return: tensor(-364.8184, device='cuda:0')
episode: 285 training return: tensor(400.5008, device='cuda:0')
episode: 286 training return: tensor(486.1158, device='cuda:0')
episode: 287 training return: tensor(237.1766, device='cuda:0')
epoch: 72 test_true_pfm: 3713.033336074282 sim_pfm: 527.0525122413237
episode: 288 training return: tensor(469.5897, device='cuda:0')
episode: 289 training return: tensor(415.8288, device='cuda:0')
episode: 290 training return: tensor(439.5282, device='cuda:0')
episode: 291 training return: tensor(491.0782, device='cuda:0')
epoch: 73 test_true_pfm: 3691.0757035792926 sim_pfm: 555.5165965113168
episode: 292 training return: tensor(429.1208, device='cuda:0')
episode: 293 training return: tensor(463.3822, device='cuda:0')
episode: 294 training return: tensor(506.9413, device='cuda:0')
episode: 295 training return: tensor(434.2907, device='cuda:0')
epoch: 74 test_true_pfm: 2653.5661460258566 sim_pfm: 505.2555161919833
episode: 296 training return: tensor(442.5300, device='cuda:0')
episode: 297 training return: tensor(419.0905, device='cuda:0')
episode: 298 training return: tensor(411.5177, device='cuda:0')
episode: 299 training return: tensor(431.0587, device='cuda:0')
epoch: 75 test_true_pfm: 3736.3433102609256 sim_pfm: 494.2880752623799
episode: 300 training return: tensor(473.8929, device='cuda:0')
episode: 301 training return: tensor(361.0930, device='cuda:0')
episode: 302 training return: tensor(399.9753, device='cuda:0')
episode: 303 training return: tensor(466.7596, device='cuda:0')
epoch: 76 test_true_pfm: 3727.4515164173367 sim_pfm: 488.63924876839155
episode: 304 training return: tensor(436.9473, device='cuda:0')
episode: 305 training return: tensor(503.5389, device='cuda:0')
episode: 306 training return: tensor(433.9373, device='cuda:0')
episode: 307 training return: tensor(445.1365, device='cuda:0')
epoch: 77 test_true_pfm: 3778.8832525797084 sim_pfm: 527.9406230572689
episode: 308 training return: tensor(465.5325, device='cuda:0')
episode: 309 training return: tensor(-552.7911, device='cuda:0')
episode: 310 training return: tensor(407.8515, device='cuda:0')
episode: 311 training return: tensor(459.0946, device='cuda:0')
epoch: 78 test_true_pfm: 3688.8802873131676 sim_pfm: 495.7102877714594
episode: 312 training return: tensor(460.6351, device='cuda:0')
episode: 313 training return: tensor(476.8358, device='cuda:0')
episode: 314 training return: tensor(382.0027, device='cuda:0')
episode: 315 training return: tensor(403.2247, device='cuda:0')
epoch: 79 test_true_pfm: 3768.781421250464 sim_pfm: 510.3674057895939
episode: 316 training return: tensor(457.7063, device='cuda:0')
episode: 317 training return: tensor(424.5246, device='cuda:0')
episode: 318 training return: tensor(462.8344, device='cuda:0')
episode: 319 training return: tensor(451.0875, device='cuda:0')
epoch: 80 test_true_pfm: 3766.7149713935755 sim_pfm: 538.7755458740672
episode: 320 training return: tensor(486.0646, device='cuda:0')
episode: 321 training return: tensor(406.1360, device='cuda:0')
episode: 322 training return: tensor(396.1163, device='cuda:0')
episode: 323 training return: tensor(502.3881, device='cuda:0')
epoch: 81 test_true_pfm: 3689.3258859903776 sim_pfm: 504.1957404134543
episode: 324 training return: tensor(475.4105, device='cuda:0')
episode: 325 training return: tensor(456.9881, device='cuda:0')
episode: 326 training return: tensor(434.4267, device='cuda:0')
episode: 327 training return: tensor(483.6898, device='cuda:0')
epoch: 82 test_true_pfm: 3725.4532204541597 sim_pfm: 516.2932106963708
episode: 328 training return: tensor(483.7604, device='cuda:0')
episode: 329 training return: tensor(444.0567, device='cuda:0')
episode: 330 training return: tensor(460.7389, device='cuda:0')
episode: 331 training return: tensor(457.9892, device='cuda:0')
epoch: 83 test_true_pfm: 3722.3759914594993 sim_pfm: 513.8531588373395
episode: 332 training return: tensor(472.3558, device='cuda:0')
episode: 333 training return: tensor(401.8335, device='cuda:0')
episode: 334 training return: tensor(472.5825, device='cuda:0')
episode: 335 training return: tensor(13.5199, device='cuda:0')
epoch: 84 test_true_pfm: 3789.5218087388334 sim_pfm: 530.7390165847804
episode: 336 training return: tensor(-227.0034, device='cuda:0')
episode: 337 training return: tensor(456.2578, device='cuda:0')
episode: 338 training return: tensor(456.5574, device='cuda:0')
episode: 339 training return: tensor(444.4972, device='cuda:0')
epoch: 85 test_true_pfm: 3713.8043114690845 sim_pfm: 516.1218960712819
episode: 340 training return: tensor(436.9088, device='cuda:0')
episode: 341 training return: tensor(484.4563, device='cuda:0')
episode: 342 training return: tensor(456.9525, device='cuda:0')
episode: 343 training return: tensor(432.0721, device='cuda:0')
epoch: 86 test_true_pfm: 3736.308007285341 sim_pfm: 512.0920045810053
episode: 344 training return: tensor(461.3165, device='cuda:0')
episode: 345 training return: tensor(463.3365, device='cuda:0')
episode: 346 training return: tensor(447.2968, device='cuda:0')
episode: 347 training return: tensor(453.1689, device='cuda:0')
epoch: 87 test_true_pfm: 3770.3204745336316 sim_pfm: 497.2433945168741
episode: 348 training return: tensor(500.2710, device='cuda:0')
episode: 349 training return: tensor(397.5617, device='cuda:0')
episode: 350 training return: tensor(402.1517, device='cuda:0')
episode: 351 training return: tensor(419.4742, device='cuda:0')
epoch: 88 test_true_pfm: 3788.5564408872706 sim_pfm: 530.6585437847922
episode: 352 training return: tensor(437.4927, device='cuda:0')
episode: 353 training return: tensor(450.2277, device='cuda:0')
episode: 354 training return: tensor(472.3268, device='cuda:0')
episode: 355 training return: tensor(459.8024, device='cuda:0')
epoch: 89 test_true_pfm: 3710.5453349848353 sim_pfm: 513.8870993005112
episode: 356 training return: tensor(505.2828, device='cuda:0')
episode: 357 training return: tensor(487.9703, device='cuda:0')
episode: 358 training return: tensor(484.7173, device='cuda:0')
episode: 359 training return: tensor(416.4691, device='cuda:0')
epoch: 90 test_true_pfm: 3784.9532943962295 sim_pfm: 529.5084071159168
episode: 360 training return: tensor(513.1849, device='cuda:0')
episode: 361 training return: tensor(475.1061, device='cuda:0')
episode: 362 training return: tensor(438.6215, device='cuda:0')
episode: 363 training return: tensor(475.2912, device='cuda:0')
epoch: 91 test_true_pfm: 3763.0329558844496 sim_pfm: 556.694183958151
episode: 364 training return: tensor(483.3839, device='cuda:0')
episode: 365 training return: tensor(459.7369, device='cuda:0')
episode: 366 training return: tensor(474.0368, device='cuda:0')
episode: 367 training return: tensor(489.8651, device='cuda:0')
epoch: 92 test_true_pfm: 3701.37579223381 sim_pfm: 447.61150915920734
episode: 368 training return: tensor(439.3996, device='cuda:0')
episode: 369 training return: tensor(395.5332, device='cuda:0')
episode: 370 training return: tensor(476.7869, device='cuda:0')
episode: 371 training return: tensor(388.2074, device='cuda:0')
epoch: 93 test_true_pfm: 3746.732812695626 sim_pfm: 504.78710506575106
episode: 372 training return: tensor(437.3714, device='cuda:0')
episode: 373 training return: tensor(486.3592, device='cuda:0')
episode: 374 training return: tensor(473.6937, device='cuda:0')
episode: 375 training return: tensor(463.2007, device='cuda:0')
epoch: 94 test_true_pfm: 3732.4011167319836 sim_pfm: 526.4262742262023
episode: 376 training return: tensor(486.6059, device='cuda:0')
episode: 377 training return: tensor(465.4077, device='cuda:0')
episode: 378 training return: tensor(481.0992, device='cuda:0')
episode: 379 training return: tensor(481.3514, device='cuda:0')
epoch: 95 test_true_pfm: 3740.8094448717634 sim_pfm: 517.9615011694065
episode: 380 training return: tensor(446.7940, device='cuda:0')
episode: 381 training return: tensor(395.0261, device='cuda:0')
episode: 382 training return: tensor(499.6479, device='cuda:0')
episode: 383 training return: tensor(464.8656, device='cuda:0')
epoch: 96 test_true_pfm: 3771.532783683051 sim_pfm: 537.0147096034876
episode: 384 training return: tensor(453.5773, device='cuda:0')
episode: 385 training return: tensor(458.3642, device='cuda:0')
episode: 386 training return: tensor(441.0396, device='cuda:0')
episode: 387 training return: tensor(454.2760, device='cuda:0')
epoch: 97 test_true_pfm: 3725.4963847616104 sim_pfm: 517.8207634995537
episode: 388 training return: tensor(448.9122, device='cuda:0')
episode: 389 training return: tensor(506.5939, device='cuda:0')
episode: 390 training return: tensor(445.0455, device='cuda:0')
episode: 391 training return: tensor(467.0816, device='cuda:0')
epoch: 98 test_true_pfm: 3722.161876169724 sim_pfm: 535.7950274594672
episode: 392 training return: tensor(-240.2757, device='cuda:0')
episode: 393 training return: tensor(448.2249, device='cuda:0')
episode: 394 training return: tensor(470.8058, device='cuda:0')
episode: 395 training return: tensor(447.0012, device='cuda:0')
epoch: 99 test_true_pfm: 3826.6052448357436 sim_pfm: 546.1387153138057
episode: 396 training return: tensor(280.0852, device='cuda:0')
episode: 397 training return: tensor(65.1335, device='cuda:0')
episode: 398 training return: tensor(451.0002, device='cuda:0')
episode: 399 training return: tensor(451.3073, device='cuda:0')
epoch: 100 test_true_pfm: 3465.223982751286 sim_pfm: 539.498244137348
episode: 400 training return: tensor(508.1110, device='cuda:0')
episode: 401 training return: tensor(441.8762, device='cuda:0')
episode: 402 training return: tensor(468.7895, device='cuda:0')
episode: 403 training return: tensor(453.8676, device='cuda:0')
epoch: 101 test_true_pfm: 3770.9389261589754 sim_pfm: 539.7781132675397
episode: 404 training return: tensor(453.4001, device='cuda:0')
episode: 405 training return: tensor(460.3878, device='cuda:0')
episode: 406 training return: tensor(483.7288, device='cuda:0')
episode: 407 training return: tensor(464.6744, device='cuda:0')
epoch: 102 test_true_pfm: 3735.1441834056823 sim_pfm: 518.5146490598563
episode: 408 training return: tensor(504.0912, device='cuda:0')
episode: 409 training return: tensor(448.1554, device='cuda:0')
episode: 410 training return: tensor(415.8346, device='cuda:0')
episode: 411 training return: tensor(492.6072, device='cuda:0')
epoch: 103 test_true_pfm: 3643.043428784474 sim_pfm: 444.16151069417054
episode: 412 training return: tensor(494.9675, device='cuda:0')
episode: 413 training return: tensor(428.1085, device='cuda:0')
episode: 414 training return: tensor(491.5646, device='cuda:0')
episode: 415 training return: tensor(111.5848, device='cuda:0')
epoch: 104 test_true_pfm: 3810.1767747161953 sim_pfm: 550.4090438274046
episode: 416 training return: tensor(365.6217, device='cuda:0')
episode: 417 training return: tensor(441.1851, device='cuda:0')
episode: 418 training return: tensor(431.0509, device='cuda:0')
episode: 419 training return: tensor(478.4883, device='cuda:0')
epoch: 105 test_true_pfm: 3764.160274736754 sim_pfm: 541.8058484958892
episode: 420 training return: tensor(402.0923, device='cuda:0')
episode: 421 training return: tensor(478.3315, device='cuda:0')
episode: 422 training return: tensor(398.1131, device='cuda:0')
episode: 423 training return: tensor(439.7745, device='cuda:0')
epoch: 106 test_true_pfm: 3702.083714278016 sim_pfm: 491.49771204862435
episode: 424 training return: tensor(484.2798, device='cuda:0')
episode: 425 training return: tensor(470.4059, device='cuda:0')
episode: 426 training return: tensor(436.9850, device='cuda:0')
episode: 427 training return: tensor(456.2718, device='cuda:0')
epoch: 107 test_true_pfm: 3761.739154050026 sim_pfm: 525.7391191744246
episode: 428 training return: tensor(465.6326, device='cuda:0')
episode: 429 training return: tensor(466.2922, device='cuda:0')
episode: 430 training return: tensor(445.3622, device='cuda:0')
episode: 431 training return: tensor(431.3260, device='cuda:0')
epoch: 108 test_true_pfm: 3767.6296690123786 sim_pfm: 517.4814881307539
episode: 432 training return: tensor(509.1270, device='cuda:0')
episode: 433 training return: tensor(467.6737, device='cuda:0')
episode: 434 training return: tensor(423.7167, device='cuda:0')
episode: 435 training return: tensor(466.5362, device='cuda:0')
epoch: 109 test_true_pfm: 3688.9166912240657 sim_pfm: 480.55301110850996
episode: 436 training return: tensor(481.6105, device='cuda:0')
episode: 437 training return: tensor(464.0663, device='cuda:0')
episode: 438 training return: tensor(442.8676, device='cuda:0')
episode: 439 training return: tensor(486.3963, device='cuda:0')
epoch: 110 test_true_pfm: 3738.154746484816 sim_pfm: 500.807594695827
episode: 440 training return: tensor(442.0297, device='cuda:0')
episode: 441 training return: tensor(411.6000, device='cuda:0')
episode: 442 training return: tensor(483.2494, device='cuda:0')
episode: 443 training return: tensor(448.3695, device='cuda:0')
epoch: 111 test_true_pfm: 3719.589309763976 sim_pfm: 532.9789702732427
episode: 444 training return: tensor(405.9563, device='cuda:0')
episode: 445 training return: tensor(452.4226, device='cuda:0')
episode: 446 training return: tensor(436.9852, device='cuda:0')
episode: 447 training return: tensor(496.8260, device='cuda:0')
epoch: 112 test_true_pfm: 3725.2494109854283 sim_pfm: 515.2126595724063
episode: 448 training return: tensor(456.1109, device='cuda:0')
episode: 449 training return: tensor(472.7387, device='cuda:0')
episode: 450 training return: tensor(467.0865, device='cuda:0')
episode: 451 training return: tensor(495.1155, device='cuda:0')
epoch: 113 test_true_pfm: 3739.4672118026124 sim_pfm: 492.27116288722027
episode: 452 training return: tensor(494.5049, device='cuda:0')
episode: 453 training return: tensor(453.2724, device='cuda:0')
episode: 454 training return: tensor(443.7090, device='cuda:0')
episode: 455 training return: tensor(467.3752, device='cuda:0')
epoch: 114 test_true_pfm: 3708.929836389914 sim_pfm: 522.3718931080463
episode: 456 training return: tensor(484.6148, device='cuda:0')
episode: 457 training return: tensor(442.6986, device='cuda:0')
episode: 458 training return: tensor(443.6564, device='cuda:0')
episode: 459 training return: tensor(493.0256, device='cuda:0')
epoch: 115 test_true_pfm: 3755.107024745074 sim_pfm: 506.18974552788615
episode: 460 training return: tensor(473.7890, device='cuda:0')
episode: 461 training return: tensor(529.9503, device='cuda:0')
episode: 462 training return: tensor(497.1833, device='cuda:0')
episode: 463 training return: tensor(444.6078, device='cuda:0')
epoch: 116 test_true_pfm: 3717.0688471240114 sim_pfm: 498.58544581007055
episode: 464 training return: tensor(455.7520, device='cuda:0')
episode: 465 training return: tensor(443.0740, device='cuda:0')
episode: 466 training return: tensor(451.5576, device='cuda:0')
episode: 467 training return: tensor(405.5056, device='cuda:0')
epoch: 117 test_true_pfm: 3816.77158632931 sim_pfm: 542.0684979637541
episode: 468 training return: tensor(375.0477, device='cuda:0')
episode: 469 training return: tensor(440.5973, device='cuda:0')
episode: 470 training return: tensor(513.0388, device='cuda:0')
episode: 471 training return: tensor(456.8935, device='cuda:0')
epoch: 118 test_true_pfm: 3791.734576685057 sim_pfm: 544.7001644336851
episode: 472 training return: tensor(496.7470, device='cuda:0')
episode: 473 training return: tensor(480.9241, device='cuda:0')
episode: 474 training return: tensor(495.6461, device='cuda:0')
episode: 475 training return: tensor(469.4914, device='cuda:0')
epoch: 119 test_true_pfm: 3740.334125449322 sim_pfm: 507.68201865865075
episode: 476 training return: tensor(437.2188, device='cuda:0')
episode: 477 training return: tensor(423.8446, device='cuda:0')
episode: 478 training return: tensor(471.4825, device='cuda:0')
episode: 479 training return: tensor(513.8828, device='cuda:0')
epoch: 120 test_true_pfm: 3760.8820065154687 sim_pfm: 546.0732405876819
episode: 480 training return: tensor(466.4469, device='cuda:0')
episode: 481 training return: tensor(486.2202, device='cuda:0')
episode: 482 training return: tensor(514.7169, device='cuda:0')
episode: 483 training return: tensor(452.6505, device='cuda:0')
epoch: 121 test_true_pfm: 3824.494504683807 sim_pfm: 549.9908315124727
episode: 484 training return: tensor(479.7843, device='cuda:0')
episode: 485 training return: tensor(484.9410, device='cuda:0')
episode: 486 training return: tensor(467.9406, device='cuda:0')
episode: 487 training return: tensor(418.1555, device='cuda:0')
epoch: 122 test_true_pfm: 3772.1290037346866 sim_pfm: 547.8204169361852
episode: 488 training return: tensor(454.5337, device='cuda:0')
episode: 489 training return: tensor(402.5233, device='cuda:0')
episode: 490 training return: tensor(439.1190, device='cuda:0')
episode: 491 training return: tensor(482.8968, device='cuda:0')
epoch: 123 test_true_pfm: 3772.0842443033403 sim_pfm: 548.2684580195152
episode: 492 training return: tensor(488.5310, device='cuda:0')
episode: 493 training return: tensor(425.6931, device='cuda:0')
episode: 494 training return: tensor(478.8761, device='cuda:0')
episode: 495 training return: tensor(394.1267, device='cuda:0')
epoch: 124 test_true_pfm: 3727.9062958925447 sim_pfm: 516.5518603027255
episode: 496 training return: tensor(423.7765, device='cuda:0')
episode: 497 training return: tensor(459.1693, device='cuda:0')
episode: 498 training return: tensor(513.1223, device='cuda:0')
episode: 499 training return: tensor(413.7860, device='cuda:0')
epoch: 125 test_true_pfm: 3787.410933021678 sim_pfm: 527.7331968470244
episode: 500 training return: tensor(479.4104, device='cuda:0')
episode: 501 training return: tensor(498.3425, device='cuda:0')
episode: 502 training return: tensor(458.8633, device='cuda:0')
episode: 503 training return: tensor(441.3119, device='cuda:0')
epoch: 126 test_true_pfm: 3773.74022404388 sim_pfm: 537.3002974675813
episode: 504 training return: tensor(458.2894, device='cuda:0')
episode: 505 training return: tensor(469.4843, device='cuda:0')
episode: 506 training return: tensor(471.2330, device='cuda:0')
episode: 507 training return: tensor(501.0452, device='cuda:0')
epoch: 127 test_true_pfm: 3824.2822647433436 sim_pfm: 534.8134164846269
episode: 508 training return: tensor(492.9204, device='cuda:0')
episode: 509 training return: tensor(472.0503, device='cuda:0')
episode: 510 training return: tensor(489.4557, device='cuda:0')
episode: 511 training return: tensor(452.9404, device='cuda:0')
epoch: 128 test_true_pfm: 3758.4221491828544 sim_pfm: 520.6750818326642
episode: 512 training return: tensor(456.7304, device='cuda:0')
episode: 513 training return: tensor(516.0945, device='cuda:0')
episode: 514 training return: tensor(484.3892, device='cuda:0')
episode: 515 training return: tensor(529.4523, device='cuda:0')
epoch: 129 test_true_pfm: 3799.6063975629863 sim_pfm: 569.9017470846107
episode: 516 training return: tensor(458.3620, device='cuda:0')
episode: 517 training return: tensor(465.0430, device='cuda:0')
episode: 518 training return: tensor(451.9211, device='cuda:0')
episode: 519 training return: tensor(473.0967, device='cuda:0')
epoch: 130 test_true_pfm: 3790.1397886092504 sim_pfm: 537.3381818112199
episode: 520 training return: tensor(466.6935, device='cuda:0')
episode: 521 training return: tensor(485.8404, device='cuda:0')
episode: 522 training return: tensor(510.5156, device='cuda:0')
episode: 523 training return: tensor(425.7489, device='cuda:0')
epoch: 131 test_true_pfm: 3807.7386079231815 sim_pfm: 529.9375742424163
episode: 524 training return: tensor(501.0984, device='cuda:0')
episode: 525 training return: tensor(480.9305, device='cuda:0')
episode: 526 training return: tensor(490.9564, device='cuda:0')
episode: 527 training return: tensor(505.1688, device='cuda:0')
epoch: 132 test_true_pfm: 3759.586679037516 sim_pfm: 523.9346043822201
episode: 528 training return: tensor(501.4185, device='cuda:0')
episode: 529 training return: tensor(485.8932, device='cuda:0')
episode: 530 training return: tensor(471.9588, device='cuda:0')
episode: 531 training return: tensor(480.4984, device='cuda:0')
epoch: 133 test_true_pfm: 3788.251389035926 sim_pfm: 559.8020447768116
episode: 532 training return: tensor(499.3919, device='cuda:0')
episode: 533 training return: tensor(449.6018, device='cuda:0')
episode: 534 training return: tensor(491.1305, device='cuda:0')
episode: 535 training return: tensor(462.4973, device='cuda:0')
epoch: 134 test_true_pfm: 3798.894786443147 sim_pfm: 492.82733902222634
episode: 536 training return: tensor(475.5112, device='cuda:0')
episode: 537 training return: tensor(485.9333, device='cuda:0')
episode: 538 training return: tensor(492.7437, device='cuda:0')
episode: 539 training return: tensor(497.7054, device='cuda:0')
epoch: 135 test_true_pfm: 3783.143803565188 sim_pfm: 533.9003189890645
episode: 540 training return: tensor(517.1317, device='cuda:0')
episode: 541 training return: tensor(444.7411, device='cuda:0')
episode: 542 training return: tensor(510.8510, device='cuda:0')
episode: 543 training return: tensor(551.6552, device='cuda:0')
epoch: 136 test_true_pfm: 3827.214367759328 sim_pfm: 536.9590697940827
episode: 544 training return: tensor(541.9299, device='cuda:0')
episode: 545 training return: tensor(459.1268, device='cuda:0')
episode: 546 training return: tensor(472.6435, device='cuda:0')
episode: 547 training return: tensor(500.2131, device='cuda:0')
epoch: 137 test_true_pfm: 3792.027841411144 sim_pfm: 562.7319145378036
episode: 548 training return: tensor(488.6297, device='cuda:0')
episode: 549 training return: tensor(387.7457, device='cuda:0')
episode: 550 training return: tensor(475.5369, device='cuda:0')
episode: 551 training return: tensor(529.2205, device='cuda:0')
epoch: 138 test_true_pfm: 3813.8346533346144 sim_pfm: 549.0593040770231
episode: 552 training return: tensor(485.1829, device='cuda:0')
episode: 553 training return: tensor(458.6616, device='cuda:0')
episode: 554 training return: tensor(506.1168, device='cuda:0')
episode: 555 training return: tensor(504.2673, device='cuda:0')
epoch: 139 test_true_pfm: 3796.9117412074265 sim_pfm: 558.081104733205
episode: 556 training return: tensor(478.3813, device='cuda:0')
episode: 557 training return: tensor(474.4716, device='cuda:0')
episode: 558 training return: tensor(449.7327, device='cuda:0')
episode: 559 training return: tensor(518.6811, device='cuda:0')
epoch: 140 test_true_pfm: 3789.0156160317997 sim_pfm: 543.8946735036249
episode: 560 training return: tensor(493.8911, device='cuda:0')
episode: 561 training return: tensor(487.5056, device='cuda:0')
episode: 562 training return: tensor(505.3150, device='cuda:0')
episode: 563 training return: tensor(475.8651, device='cuda:0')
epoch: 141 test_true_pfm: 3832.880537671503 sim_pfm: 565.9383653104305
episode: 564 training return: tensor(486.6475, device='cuda:0')
episode: 565 training return: tensor(-254.4176, device='cuda:0')
episode: 566 training return: tensor(541.7353, device='cuda:0')
episode: 567 training return: tensor(498.3629, device='cuda:0')
epoch: 142 test_true_pfm: 3811.2766741018972 sim_pfm: 524.3807260571824
episode: 568 training return: tensor(499.9638, device='cuda:0')
episode: 569 training return: tensor(477.1758, device='cuda:0')
episode: 570 training return: tensor(459.7937, device='cuda:0')
episode: 571 training return: tensor(498.9567, device='cuda:0')
epoch: 143 test_true_pfm: 3861.636713710226 sim_pfm: 586.3532988250566
episode: 572 training return: tensor(471.2673, device='cuda:0')
episode: 573 training return: tensor(472.5414, device='cuda:0')
episode: 574 training return: tensor(487.8121, device='cuda:0')
episode: 575 training return: tensor(425.2391, device='cuda:0')
epoch: 144 test_true_pfm: 3786.1654532656435 sim_pfm: 558.582159534058
episode: 576 training return: tensor(488.8579, device='cuda:0')
episode: 577 training return: tensor(499.6332, device='cuda:0')
episode: 578 training return: tensor(490.2824, device='cuda:0')
episode: 579 training return: tensor(494.6583, device='cuda:0')
epoch: 145 test_true_pfm: 3783.6702755783517 sim_pfm: 550.6991123102683
episode: 580 training return: tensor(460.7360, device='cuda:0')
episode: 581 training return: tensor(476.1250, device='cuda:0')
episode: 582 training return: tensor(485.6271, device='cuda:0')
episode: 583 training return: tensor(487.7212, device='cuda:0')
epoch: 146 test_true_pfm: 3858.234474345887 sim_pfm: 566.9273238302072
episode: 584 training return: tensor(490.3589, device='cuda:0')
episode: 585 training return: tensor(454.7735, device='cuda:0')
episode: 586 training return: tensor(512.0338, device='cuda:0')
episode: 587 training return: tensor(508.3383, device='cuda:0')
epoch: 147 test_true_pfm: 3822.9087845440263 sim_pfm: 549.7593710468888
episode: 588 training return: tensor(515.8118, device='cuda:0')
episode: 589 training return: tensor(476.5848, device='cuda:0')
episode: 590 training return: tensor(506.6760, device='cuda:0')
episode: 591 training return: tensor(519.8661, device='cuda:0')
epoch: 148 test_true_pfm: 3107.1149454572483 sim_pfm: 372.6369947633163
episode: 592 training return: tensor(505.2162, device='cuda:0')
episode: 593 training return: tensor(533.5616, device='cuda:0')
episode: 594 training return: tensor(528.0069, device='cuda:0')
episode: 595 training return: tensor(513.0980, device='cuda:0')
epoch: 149 test_true_pfm: 3923.4620012105274 sim_pfm: 600.6386626267534
episode: 596 training return: tensor(438.6942, device='cuda:0')
episode: 597 training return: tensor(525.7366, device='cuda:0')
episode: 598 training return: tensor(475.4609, device='cuda:0')
episode: 599 training return: tensor(473.0431, device='cuda:0')
epoch: 150 test_true_pfm: 3803.5507634019377 sim_pfm: 558.9318435250316
