['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '4', '--data', '100000', '--regu', '0.3']
2716.5043881305164
episode: 0 training return: tensor(313.6656, device='cuda:0')
episode: 1 training return: tensor(270.7975, device='cuda:0')
episode: 2 training return: tensor(361.3936, device='cuda:0')
episode: 3 training return: tensor(167.7632, device='cuda:0')
epoch: 1 test_true_pfm: 3341.1973380110758 sim_pfm: 202.83400588513663
episode: 4 training return: tensor(200.2422, device='cuda:0')
episode: 5 training return: tensor(246.2578, device='cuda:0')
episode: 6 training return: tensor(35.5858, device='cuda:0')
episode: 7 training return: tensor(221.7621, device='cuda:0')
epoch: 2 test_true_pfm: 2051.1014931055834 sim_pfm: -116.88108944530056
episode: 8 training return: tensor(289.2866, device='cuda:0')
episode: 9 training return: tensor(-13.0569, device='cuda:0')
episode: 10 training return: tensor(310.7846, device='cuda:0')
episode: 11 training return: tensor(329.2910, device='cuda:0')
epoch: 3 test_true_pfm: 3470.603429894231 sim_pfm: 371.30561049449415
episode: 12 training return: tensor(-70.6845, device='cuda:0')
episode: 13 training return: tensor(65.2996, device='cuda:0')
episode: 14 training return: tensor(383.2826, device='cuda:0')
episode: 15 training return: tensor(394.8569, device='cuda:0')
epoch: 4 test_true_pfm: 3528.7170169346914 sim_pfm: 119.55514840610947
episode: 16 training return: tensor(273.6913, device='cuda:0')
episode: 17 training return: tensor(358.4199, device='cuda:0')
episode: 18 training return: tensor(316.5655, device='cuda:0')
episode: 19 training return: tensor(-181.5467, device='cuda:0')
epoch: 5 test_true_pfm: 3474.741801329297 sim_pfm: 378.4837243799896
episode: 20 training return: tensor(296.6699, device='cuda:0')
episode: 21 training return: tensor(351.5685, device='cuda:0')
episode: 22 training return: tensor(317.1024, device='cuda:0')
episode: 23 training return: tensor(378.6481, device='cuda:0')
epoch: 6 test_true_pfm: 3565.1821179522744 sim_pfm: 233.461466502146
episode: 24 training return: tensor(390.7310, device='cuda:0')
episode: 25 training return: tensor(396.9656, device='cuda:0')
episode: 26 training return: tensor(364.3664, device='cuda:0')
episode: 27 training return: tensor(-243.9161, device='cuda:0')
epoch: 7 test_true_pfm: 2054.953743563793 sim_pfm: 101.26639536683797
episode: 28 training return: tensor(311.8160, device='cuda:0')
episode: 29 training return: tensor(440.1006, device='cuda:0')
episode: 30 training return: tensor(-43.3781, device='cuda:0')
episode: 31 training return: tensor(271.0234, device='cuda:0')
epoch: 8 test_true_pfm: 3596.804021030331 sim_pfm: 221.17306513740914
episode: 32 training return: tensor(282.8392, device='cuda:0')
episode: 33 training return: tensor(307.8554, device='cuda:0')
episode: 34 training return: tensor(350.4871, device='cuda:0')
episode: 35 training return: tensor(292.4511, device='cuda:0')
epoch: 9 test_true_pfm: 3428.4895136473096 sim_pfm: 159.77316847418356
episode: 36 training return: tensor(364.0560, device='cuda:0')
episode: 37 training return: tensor(372.6440, device='cuda:0')
episode: 38 training return: tensor(355.2242, device='cuda:0')
episode: 39 training return: tensor(354.1065, device='cuda:0')
epoch: 10 test_true_pfm: 2721.816470491958 sim_pfm: 309.3821706120313
episode: 40 training return: tensor(369.8423, device='cuda:0')
episode: 41 training return: tensor(409.2321, device='cuda:0')
episode: 42 training return: tensor(402.0879, device='cuda:0')
episode: 43 training return: tensor(345.0589, device='cuda:0')
epoch: 11 test_true_pfm: 3433.919411501003 sim_pfm: -184.1064280536181
episode: 44 training return: tensor(-212.0660, device='cuda:0')
episode: 45 training return: tensor(360.1061, device='cuda:0')
episode: 46 training return: tensor(416.8351, device='cuda:0')
episode: 47 training return: tensor(414.2941, device='cuda:0')
epoch: 12 test_true_pfm: 2396.472680662688 sim_pfm: -231.01035654816465
episode: 48 training return: tensor(353.2498, device='cuda:0')
episode: 49 training return: tensor(236.1107, device='cuda:0')
episode: 50 training return: tensor(-382.6312, device='cuda:0')
episode: 51 training return: tensor(422.2811, device='cuda:0')
epoch: 13 test_true_pfm: 3157.699742477363 sim_pfm: 300.06300401264645
episode: 52 training return: tensor(296.5522, device='cuda:0')
episode: 53 training return: tensor(145.4084, device='cuda:0')
episode: 54 training return: tensor(-365.6070, device='cuda:0')
episode: 55 training return: tensor(-412.8816, device='cuda:0')
epoch: 14 test_true_pfm: 2971.291482775551 sim_pfm: 163.22796111988524
episode: 56 training return: tensor(-270.4694, device='cuda:0')
episode: 57 training return: tensor(395.8801, device='cuda:0')
episode: 58 training return: tensor(291.6064, device='cuda:0')
episode: 59 training return: tensor(365.9149, device='cuda:0')
epoch: 15 test_true_pfm: 3494.3026784667873 sim_pfm: -105.91351914514478
episode: 60 training return: tensor(-334.2012, device='cuda:0')
episode: 61 training return: tensor(409.7140, device='cuda:0')
episode: 62 training return: tensor(307.1218, device='cuda:0')
episode: 63 training return: tensor(290.8615, device='cuda:0')
epoch: 16 test_true_pfm: 3190.699576450139 sim_pfm: 355.83800381899346
episode: 64 training return: tensor(130.4964, device='cuda:0')
episode: 65 training return: tensor(19.4903, device='cuda:0')
episode: 66 training return: tensor(364.8989, device='cuda:0')
episode: 67 training return: tensor(432.4999, device='cuda:0')
epoch: 17 test_true_pfm: 3470.2799527596435 sim_pfm: 226.4793501323244
episode: 68 training return: tensor(407.9557, device='cuda:0')
episode: 69 training return: tensor(321.7578, device='cuda:0')
episode: 70 training return: tensor(325.3075, device='cuda:0')
episode: 71 training return: tensor(347.1382, device='cuda:0')
epoch: 18 test_true_pfm: 3472.128741191186 sim_pfm: 412.435340047911
episode: 72 training return: tensor(366.6281, device='cuda:0')
episode: 73 training return: tensor(349.5566, device='cuda:0')
episode: 74 training return: tensor(349.9320, device='cuda:0')
episode: 75 training return: tensor(254.9658, device='cuda:0')
epoch: 19 test_true_pfm: 3524.0993008350524 sim_pfm: 301.1699006068132
episode: 76 training return: tensor(398.5481, device='cuda:0')
episode: 77 training return: tensor(290.5225, device='cuda:0')
episode: 78 training return: tensor(366.5265, device='cuda:0')
episode: 79 training return: tensor(334.9114, device='cuda:0')
epoch: 20 test_true_pfm: 3430.3386635060665 sim_pfm: 209.92628926132844
episode: 80 training return: tensor(401.1717, device='cuda:0')
episode: 81 training return: tensor(371.4557, device='cuda:0')
episode: 82 training return: tensor(-306.4048, device='cuda:0')
episode: 83 training return: tensor(364.2621, device='cuda:0')
epoch: 21 test_true_pfm: 2825.0568758140666 sim_pfm: 271.1525221798026
episode: 84 training return: tensor(426.2286, device='cuda:0')
episode: 85 training return: tensor(356.6962, device='cuda:0')
episode: 86 training return: tensor(-10.7499, device='cuda:0')
episode: 87 training return: tensor(423.6086, device='cuda:0')
epoch: 22 test_true_pfm: 3470.928989455482 sim_pfm: 439.55663126154104
episode: 88 training return: tensor(367.2874, device='cuda:0')
episode: 89 training return: tensor(419.4078, device='cuda:0')
episode: 90 training return: tensor(226.3300, device='cuda:0')
episode: 91 training return: tensor(392.1560, device='cuda:0')
epoch: 23 test_true_pfm: 3706.683603995272 sim_pfm: 346.32758739350055
episode: 92 training return: tensor(351.7144, device='cuda:0')
episode: 93 training return: tensor(338.1548, device='cuda:0')
episode: 94 training return: tensor(428.6143, device='cuda:0')
episode: 95 training return: tensor(359.6192, device='cuda:0')
epoch: 24 test_true_pfm: 3652.9771661134587 sim_pfm: 456.53534525446594
episode: 96 training return: tensor(-36.7056, device='cuda:0')
episode: 97 training return: tensor(338.9355, device='cuda:0')
episode: 98 training return: tensor(373.2137, device='cuda:0')
episode: 99 training return: tensor(405.1336, device='cuda:0')
epoch: 25 test_true_pfm: 3643.442055514286 sim_pfm: 475.2143376080009
episode: 100 training return: tensor(-224.2272, device='cuda:0')
episode: 101 training return: tensor(387.6413, device='cuda:0')
episode: 102 training return: tensor(425.1641, device='cuda:0')
episode: 103 training return: tensor(434.5376, device='cuda:0')
epoch: 26 test_true_pfm: 3564.8285542908047 sim_pfm: 427.30872615384095
episode: 104 training return: tensor(429.1349, device='cuda:0')
episode: 105 training return: tensor(-123.0347, device='cuda:0')
episode: 106 training return: tensor(362.7709, device='cuda:0')
episode: 107 training return: tensor(-169.9785, device='cuda:0')
epoch: 27 test_true_pfm: 3583.1389835570367 sim_pfm: 460.61803919969435
episode: 108 training return: tensor(456.2410, device='cuda:0')
episode: 109 training return: tensor(445.3808, device='cuda:0')
episode: 110 training return: tensor(58.6596, device='cuda:0')
episode: 111 training return: tensor(452.5121, device='cuda:0')
epoch: 28 test_true_pfm: 3539.6300802251008 sim_pfm: 357.4433225133107
episode: 112 training return: tensor(383.8227, device='cuda:0')
episode: 113 training return: tensor(486.5107, device='cuda:0')
episode: 114 training return: tensor(406.7559, device='cuda:0')
episode: 115 training return: tensor(387.5503, device='cuda:0')
epoch: 29 test_true_pfm: 3535.925635030678 sim_pfm: 364.1630830465195
episode: 116 training return: tensor(391.1624, device='cuda:0')
episode: 117 training return: tensor(384.8959, device='cuda:0')
episode: 118 training return: tensor(296.9392, device='cuda:0')
episode: 119 training return: tensor(303.1339, device='cuda:0')
epoch: 30 test_true_pfm: 2941.4850234080036 sim_pfm: 333.84676252588787
episode: 120 training return: tensor(423.6347, device='cuda:0')
episode: 121 training return: tensor(-91.5910, device='cuda:0')
episode: 122 training return: tensor(407.9286, device='cuda:0')
episode: 123 training return: tensor(327.7014, device='cuda:0')
epoch: 31 test_true_pfm: 2709.6606774515744 sim_pfm: 308.4517390252731
episode: 124 training return: tensor(-43.1432, device='cuda:0')
episode: 125 training return: tensor(324.9490, device='cuda:0')
episode: 126 training return: tensor(467.7198, device='cuda:0')
episode: 127 training return: tensor(358.3889, device='cuda:0')
epoch: 32 test_true_pfm: 3526.632390934496 sim_pfm: 375.44129380211234
episode: 128 training return: tensor(319.5602, device='cuda:0')
episode: 129 training return: tensor(313.9514, device='cuda:0')
episode: 130 training return: tensor(455.8912, device='cuda:0')
episode: 131 training return: tensor(413.7648, device='cuda:0')
epoch: 33 test_true_pfm: 3400.308136639914 sim_pfm: 318.8577778761489
episode: 132 training return: tensor(417.9892, device='cuda:0')
episode: 133 training return: tensor(304.5462, device='cuda:0')
episode: 134 training return: tensor(276.8366, device='cuda:0')
episode: 135 training return: tensor(403.0309, device='cuda:0')
epoch: 34 test_true_pfm: 3548.8038639503775 sim_pfm: 442.7011283285877
episode: 136 training return: tensor(470.6687, device='cuda:0')
episode: 137 training return: tensor(414.4817, device='cuda:0')
episode: 138 training return: tensor(356.5661, device='cuda:0')
episode: 139 training return: tensor(344.4027, device='cuda:0')
epoch: 35 test_true_pfm: 3566.5859503583797 sim_pfm: 436.1405005103831
episode: 140 training return: tensor(319.3953, device='cuda:0')
episode: 141 training return: tensor(428.6055, device='cuda:0')
episode: 142 training return: tensor(386.3581, device='cuda:0')
episode: 143 training return: tensor(349.2007, device='cuda:0')
epoch: 36 test_true_pfm: 3553.0312232265715 sim_pfm: 420.38220752765966
episode: 144 training return: tensor(455.7706, device='cuda:0')
episode: 145 training return: tensor(375.7245, device='cuda:0')
episode: 146 training return: tensor(358.6423, device='cuda:0')
episode: 147 training return: tensor(365.4635, device='cuda:0')
epoch: 37 test_true_pfm: 3582.1503212699768 sim_pfm: 423.3568635334571
episode: 148 training return: tensor(412.5856, device='cuda:0')
episode: 149 training return: tensor(336.1059, device='cuda:0')
episode: 150 training return: tensor(391.8208, device='cuda:0')
episode: 151 training return: tensor(365.3488, device='cuda:0')
epoch: 38 test_true_pfm: 3515.305156814793 sim_pfm: 405.28782540195
episode: 152 training return: tensor(362.2532, device='cuda:0')
episode: 153 training return: tensor(458.6456, device='cuda:0')
episode: 154 training return: tensor(10.3202, device='cuda:0')
episode: 155 training return: tensor(413.6174, device='cuda:0')
epoch: 39 test_true_pfm: 3592.9479515773214 sim_pfm: 402.05968725364073
episode: 156 training return: tensor(374.7458, device='cuda:0')
episode: 157 training return: tensor(363.7116, device='cuda:0')
episode: 158 training return: tensor(364.4830, device='cuda:0')
episode: 159 training return: tensor(410.7132, device='cuda:0')
epoch: 40 test_true_pfm: 3590.6872428574147 sim_pfm: 454.08547448037035
episode: 160 training return: tensor(350.9342, device='cuda:0')
episode: 161 training return: tensor(367.5512, device='cuda:0')
episode: 162 training return: tensor(383.6935, device='cuda:0')
episode: 163 training return: tensor(409.2661, device='cuda:0')
epoch: 41 test_true_pfm: 3599.774990917895 sim_pfm: 404.0468955853333
episode: 164 training return: tensor(357.2264, device='cuda:0')
episode: 165 training return: tensor(408.6589, device='cuda:0')
episode: 166 training return: tensor(356.6339, device='cuda:0')
episode: 167 training return: tensor(385.5502, device='cuda:0')
epoch: 42 test_true_pfm: 3477.8866782048494 sim_pfm: 360.7935109252964
episode: 168 training return: tensor(419.4774, device='cuda:0')
episode: 169 training return: tensor(-193.2320, device='cuda:0')
episode: 170 training return: tensor(338.4428, device='cuda:0')
episode: 171 training return: tensor(431.2272, device='cuda:0')
epoch: 43 test_true_pfm: 3496.3033409752866 sim_pfm: 398.4582929355868
episode: 172 training return: tensor(342.6585, device='cuda:0')
episode: 173 training return: tensor(426.6328, device='cuda:0')
episode: 174 training return: tensor(159.1473, device='cuda:0')
episode: 175 training return: tensor(398.4129, device='cuda:0')
epoch: 44 test_true_pfm: 3145.7841867928455 sim_pfm: 439.83159205833607
episode: 176 training return: tensor(446.4196, device='cuda:0')
episode: 177 training return: tensor(417.5122, device='cuda:0')
episode: 178 training return: tensor(410.6589, device='cuda:0')
episode: 179 training return: tensor(389.1118, device='cuda:0')
epoch: 45 test_true_pfm: 3509.573463442643 sim_pfm: 406.03875817129546
episode: 180 training return: tensor(363.6916, device='cuda:0')
episode: 181 training return: tensor(370.5503, device='cuda:0')
episode: 182 training return: tensor(303.1807, device='cuda:0')
episode: 183 training return: tensor(394.1853, device='cuda:0')
epoch: 46 test_true_pfm: 3560.2765315445145 sim_pfm: 418.97622053468757
episode: 184 training return: tensor(399.0162, device='cuda:0')
episode: 185 training return: tensor(417.4322, device='cuda:0')
episode: 186 training return: tensor(427.7162, device='cuda:0')
episode: 187 training return: tensor(414.7277, device='cuda:0')
epoch: 47 test_true_pfm: 3508.2805604337796 sim_pfm: 381.2531564531382
episode: 188 training return: tensor(356.2460, device='cuda:0')
episode: 189 training return: tensor(399.4294, device='cuda:0')
episode: 190 training return: tensor(392.1776, device='cuda:0')
episode: 191 training return: tensor(319.9237, device='cuda:0')
epoch: 48 test_true_pfm: 3646.573537310456 sim_pfm: 363.9776864405333
episode: 192 training return: tensor(394.4228, device='cuda:0')
episode: 193 training return: tensor(330.4208, device='cuda:0')
episode: 194 training return: tensor(191.0891, device='cuda:0')
episode: 195 training return: tensor(128.1814, device='cuda:0')
epoch: 49 test_true_pfm: 3520.231314107612 sim_pfm: 381.1209358604004
episode: 196 training return: tensor(399.7025, device='cuda:0')
episode: 197 training return: tensor(357.8950, device='cuda:0')
episode: 198 training return: tensor(491.2697, device='cuda:0')
episode: 199 training return: tensor(375.7703, device='cuda:0')
epoch: 50 test_true_pfm: 3498.695864222022 sim_pfm: 386.7649143942787
episode: 200 training return: tensor(364.9622, device='cuda:0')
episode: 201 training return: tensor(362.9603, device='cuda:0')
episode: 202 training return: tensor(370.5362, device='cuda:0')
episode: 203 training return: tensor(361.0577, device='cuda:0')
epoch: 51 test_true_pfm: 3548.9693690411946 sim_pfm: 419.4840567141461
episode: 204 training return: tensor(436.1406, device='cuda:0')
episode: 205 training return: tensor(374.9020, device='cuda:0')
episode: 206 training return: tensor(411.5446, device='cuda:0')
episode: 207 training return: tensor(290.8425, device='cuda:0')
epoch: 52 test_true_pfm: 3555.5133927026413 sim_pfm: 342.96930168652517
episode: 208 training return: tensor(418.5367, device='cuda:0')
episode: 209 training return: tensor(338.2886, device='cuda:0')
episode: 210 training return: tensor(434.2533, device='cuda:0')
episode: 211 training return: tensor(353.5768, device='cuda:0')
epoch: 53 test_true_pfm: 3539.8239665472806 sim_pfm: 400.70173904206604
episode: 212 training return: tensor(353.2985, device='cuda:0')
episode: 213 training return: tensor(384.3208, device='cuda:0')
episode: 214 training return: tensor(334.0325, device='cuda:0')
episode: 215 training return: tensor(393.2734, device='cuda:0')
epoch: 54 test_true_pfm: 3603.0639430961805 sim_pfm: 402.9693048385282
episode: 216 training return: tensor(388.6588, device='cuda:0')
episode: 217 training return: tensor(333.5048, device='cuda:0')
episode: 218 training return: tensor(429.2402, device='cuda:0')
episode: 219 training return: tensor(395.5058, device='cuda:0')
epoch: 55 test_true_pfm: 3576.602337782149 sim_pfm: 412.6147993929432
episode: 220 training return: tensor(343.0603, device='cuda:0')
episode: 221 training return: tensor(395.6852, device='cuda:0')
episode: 222 training return: tensor(435.8873, device='cuda:0')
episode: 223 training return: tensor(444.2091, device='cuda:0')
epoch: 56 test_true_pfm: 3564.542228270235 sim_pfm: 362.4541055757242
episode: 224 training return: tensor(342.9987, device='cuda:0')
episode: 225 training return: tensor(390.1819, device='cuda:0')
episode: 226 training return: tensor(386.4661, device='cuda:0')
episode: 227 training return: tensor(484.1443, device='cuda:0')
epoch: 57 test_true_pfm: 3089.006229054292 sim_pfm: 282.01074462787557
episode: 228 training return: tensor(359.0023, device='cuda:0')
episode: 229 training return: tensor(419.3705, device='cuda:0')
episode: 230 training return: tensor(439.0301, device='cuda:0')
episode: 231 training return: tensor(390.0346, device='cuda:0')
epoch: 58 test_true_pfm: 3540.028303495617 sim_pfm: 416.287174336748
episode: 232 training return: tensor(395.5094, device='cuda:0')
episode: 233 training return: tensor(437.5103, device='cuda:0')
episode: 234 training return: tensor(380.8147, device='cuda:0')
episode: 235 training return: tensor(457.8015, device='cuda:0')
epoch: 59 test_true_pfm: 3555.5827946536506 sim_pfm: 434.5550702921755
episode: 236 training return: tensor(416.4253, device='cuda:0')
episode: 237 training return: tensor(400.1242, device='cuda:0')
episode: 238 training return: tensor(389.6675, device='cuda:0')
episode: 239 training return: tensor(446.8354, device='cuda:0')
epoch: 60 test_true_pfm: 3629.252578612175 sim_pfm: 447.1429668383498
episode: 240 training return: tensor(441.7044, device='cuda:0')
episode: 241 training return: tensor(424.5337, device='cuda:0')
episode: 242 training return: tensor(73.4848, device='cuda:0')
episode: 243 training return: tensor(-76.3729, device='cuda:0')
epoch: 61 test_true_pfm: 3597.8508535516908 sim_pfm: 432.5594837310685
episode: 244 training return: tensor(447.2140, device='cuda:0')
episode: 245 training return: tensor(470.0771, device='cuda:0')
episode: 246 training return: tensor(400.7984, device='cuda:0')
episode: 247 training return: tensor(411.0851, device='cuda:0')
epoch: 62 test_true_pfm: 3539.0476350431977 sim_pfm: 407.6546944554818
episode: 248 training return: tensor(424.0976, device='cuda:0')
episode: 249 training return: tensor(390.8117, device='cuda:0')
episode: 250 training return: tensor(348.0428, device='cuda:0')
episode: 251 training return: tensor(369.2949, device='cuda:0')
epoch: 63 test_true_pfm: 3476.3757919351533 sim_pfm: 417.6193644491432
episode: 252 training return: tensor(351.0096, device='cuda:0')
episode: 253 training return: tensor(358.6213, device='cuda:0')
episode: 254 training return: tensor(-605.1285, device='cuda:0')
episode: 255 training return: tensor(376.5684, device='cuda:0')
epoch: 64 test_true_pfm: 3557.621153757768 sim_pfm: 442.8326319265664
episode: 256 training return: tensor(460.6266, device='cuda:0')
episode: 257 training return: tensor(373.2517, device='cuda:0')
episode: 258 training return: tensor(405.5860, device='cuda:0')
episode: 259 training return: tensor(394.4419, device='cuda:0')
epoch: 65 test_true_pfm: 3596.0711094533617 sim_pfm: 443.5441149273732
episode: 260 training return: tensor(414.6653, device='cuda:0')
episode: 261 training return: tensor(414.7843, device='cuda:0')
episode: 262 training return: tensor(457.1282, device='cuda:0')
episode: 263 training return: tensor(391.1006, device='cuda:0')
epoch: 66 test_true_pfm: 3520.3471944388134 sim_pfm: 419.455822413244
episode: 264 training return: tensor(397.8637, device='cuda:0')
episode: 265 training return: tensor(400.7867, device='cuda:0')
episode: 266 training return: tensor(348.2432, device='cuda:0')
episode: 267 training return: tensor(372.7994, device='cuda:0')
epoch: 67 test_true_pfm: 3550.0421949461265 sim_pfm: 423.46913865643245
episode: 268 training return: tensor(356.2619, device='cuda:0')
episode: 269 training return: tensor(-155.7300, device='cuda:0')
episode: 270 training return: tensor(384.8440, device='cuda:0')
episode: 271 training return: tensor(453.6310, device='cuda:0')
epoch: 68 test_true_pfm: 3570.678381224973 sim_pfm: 413.65299930465216
episode: 272 training return: tensor(404.0038, device='cuda:0')
episode: 273 training return: tensor(417.6440, device='cuda:0')
episode: 274 training return: tensor(415.7740, device='cuda:0')
episode: 275 training return: tensor(119.1749, device='cuda:0')
epoch: 69 test_true_pfm: 3570.782895835484 sim_pfm: 450.0431687311987
episode: 276 training return: tensor(376.5338, device='cuda:0')
episode: 277 training return: tensor(437.5470, device='cuda:0')
episode: 278 training return: tensor(372.7723, device='cuda:0')
episode: 279 training return: tensor(388.0864, device='cuda:0')
epoch: 70 test_true_pfm: 3475.0167094779536 sim_pfm: 419.2044675774717
episode: 280 training return: tensor(371.4553, device='cuda:0')
episode: 281 training return: tensor(406.7050, device='cuda:0')
episode: 282 training return: tensor(349.4388, device='cuda:0')
episode: 283 training return: tensor(366.4487, device='cuda:0')
epoch: 71 test_true_pfm: 3563.54430887568 sim_pfm: 428.3525026485052
episode: 284 training return: tensor(382.4947, device='cuda:0')
episode: 285 training return: tensor(360.6837, device='cuda:0')
episode: 286 training return: tensor(325.5377, device='cuda:0')
episode: 287 training return: tensor(114.2101, device='cuda:0')
epoch: 72 test_true_pfm: 3568.246617818801 sim_pfm: 437.5280398466275
episode: 288 training return: tensor(413.4613, device='cuda:0')
episode: 289 training return: tensor(351.5825, device='cuda:0')
episode: 290 training return: tensor(383.3815, device='cuda:0')
episode: 291 training return: tensor(366.9496, device='cuda:0')
epoch: 73 test_true_pfm: 3576.248573148718 sim_pfm: 459.90884862545255
episode: 292 training return: tensor(436.6711, device='cuda:0')
episode: 293 training return: tensor(351.4949, device='cuda:0')
episode: 294 training return: tensor(351.7339, device='cuda:0')
episode: 295 training return: tensor(329.9452, device='cuda:0')
epoch: 74 test_true_pfm: 3541.524307087068 sim_pfm: 416.9418614145446
episode: 296 training return: tensor(374.4484, device='cuda:0')
episode: 297 training return: tensor(348.2339, device='cuda:0')
episode: 298 training return: tensor(402.4693, device='cuda:0')
episode: 299 training return: tensor(435.7917, device='cuda:0')
epoch: 75 test_true_pfm: 3608.0916330904183 sim_pfm: 457.88040474031976
episode: 300 training return: tensor(422.3742, device='cuda:0')
episode: 301 training return: tensor(429.4704, device='cuda:0')
episode: 302 training return: tensor(313.2731, device='cuda:0')
episode: 303 training return: tensor(427.9073, device='cuda:0')
epoch: 76 test_true_pfm: 3482.6302907763475 sim_pfm: 374.15592678888544
episode: 304 training return: tensor(358.4097, device='cuda:0')
episode: 305 training return: tensor(345.1428, device='cuda:0')
episode: 306 training return: tensor(369.9185, device='cuda:0')
episode: 307 training return: tensor(342.7900, device='cuda:0')
epoch: 77 test_true_pfm: 3579.471689382625 sim_pfm: 412.1337146317819
episode: 308 training return: tensor(397.4652, device='cuda:0')
episode: 309 training return: tensor(390.2737, device='cuda:0')
episode: 310 training return: tensor(393.8966, device='cuda:0')
episode: 311 training return: tensor(353.3485, device='cuda:0')
epoch: 78 test_true_pfm: 3555.6557497853014 sim_pfm: 406.54657304721576
episode: 312 training return: tensor(418.4016, device='cuda:0')
episode: 313 training return: tensor(428.6229, device='cuda:0')
episode: 314 training return: tensor(377.2036, device='cuda:0')
episode: 315 training return: tensor(433.0900, device='cuda:0')
epoch: 79 test_true_pfm: 3601.2582754696273 sim_pfm: 434.2726144895035
episode: 316 training return: tensor(384.2067, device='cuda:0')
episode: 317 training return: tensor(375.1259, device='cuda:0')
episode: 318 training return: tensor(408.6159, device='cuda:0')
episode: 319 training return: tensor(463.3089, device='cuda:0')
epoch: 80 test_true_pfm: 3299.7928522168127 sim_pfm: 482.4835128788448
episode: 320 training return: tensor(406.7926, device='cuda:0')
episode: 321 training return: tensor(458.0605, device='cuda:0')
episode: 322 training return: tensor(499.0273, device='cuda:0')
episode: 323 training return: tensor(355.8252, device='cuda:0')
epoch: 81 test_true_pfm: 3604.3676077225077 sim_pfm: 434.22827933804365
episode: 324 training return: tensor(419.8467, device='cuda:0')
episode: 325 training return: tensor(382.5858, device='cuda:0')
episode: 326 training return: tensor(426.7086, device='cuda:0')
episode: 327 training return: tensor(361.0048, device='cuda:0')
epoch: 82 test_true_pfm: 3612.6384350361272 sim_pfm: 446.2645653821528
episode: 328 training return: tensor(394.1556, device='cuda:0')
episode: 329 training return: tensor(420.7780, device='cuda:0')
episode: 330 training return: tensor(395.9749, device='cuda:0')
episode: 331 training return: tensor(393.8137, device='cuda:0')
epoch: 83 test_true_pfm: 3579.290686407339 sim_pfm: 441.59659866422106
episode: 332 training return: tensor(391.0818, device='cuda:0')
episode: 333 training return: tensor(430.9077, device='cuda:0')
episode: 334 training return: tensor(443.7269, device='cuda:0')
episode: 335 training return: tensor(436.6974, device='cuda:0')
epoch: 84 test_true_pfm: 3668.5951728175114 sim_pfm: 473.69827775020775
episode: 336 training return: tensor(400.9333, device='cuda:0')
episode: 337 training return: tensor(419.6571, device='cuda:0')
episode: 338 training return: tensor(452.2637, device='cuda:0')
episode: 339 training return: tensor(364.3465, device='cuda:0')
epoch: 85 test_true_pfm: 3579.9312003871487 sim_pfm: 459.2223533150973
episode: 340 training return: tensor(383.4274, device='cuda:0')
episode: 341 training return: tensor(370.4146, device='cuda:0')
episode: 342 training return: tensor(408.2761, device='cuda:0')
episode: 343 training return: tensor(440.5107, device='cuda:0')
epoch: 86 test_true_pfm: 3518.7457356483064 sim_pfm: 389.2119151215302
episode: 344 training return: tensor(378.4096, device='cuda:0')
episode: 345 training return: tensor(402.1448, device='cuda:0')
episode: 346 training return: tensor(426.1588, device='cuda:0')
episode: 347 training return: tensor(389.2776, device='cuda:0')
epoch: 87 test_true_pfm: 3488.0139508821685 sim_pfm: 376.3458403297312
episode: 348 training return: tensor(441.8771, device='cuda:0')
episode: 349 training return: tensor(470.0168, device='cuda:0')
episode: 350 training return: tensor(447.2167, device='cuda:0')
episode: 351 training return: tensor(391.0962, device='cuda:0')
epoch: 88 test_true_pfm: 3642.7523413918348 sim_pfm: 449.5075239878109
episode: 352 training return: tensor(373.0385, device='cuda:0')
episode: 353 training return: tensor(408.3233, device='cuda:0')
episode: 354 training return: tensor(475.3190, device='cuda:0')
episode: 355 training return: tensor(452.7495, device='cuda:0')
epoch: 89 test_true_pfm: 3614.400606250633 sim_pfm: 446.04800535272807
episode: 356 training return: tensor(432.6912, device='cuda:0')
episode: 357 training return: tensor(420.0350, device='cuda:0')
episode: 358 training return: tensor(372.4008, device='cuda:0')
episode: 359 training return: tensor(373.3392, device='cuda:0')
epoch: 90 test_true_pfm: 3588.322891598895 sim_pfm: 463.6127642414358
episode: 360 training return: tensor(404.0059, device='cuda:0')
episode: 361 training return: tensor(458.1032, device='cuda:0')
episode: 362 training return: tensor(417.8070, device='cuda:0')
episode: 363 training return: tensor(411.8202, device='cuda:0')
epoch: 91 test_true_pfm: 3635.4011014896682 sim_pfm: 476.66468277127325
episode: 364 training return: tensor(435.0699, device='cuda:0')
episode: 365 training return: tensor(383.5795, device='cuda:0')
episode: 366 training return: tensor(401.3780, device='cuda:0')
episode: 367 training return: tensor(390.5642, device='cuda:0')
epoch: 92 test_true_pfm: 3638.4108786803577 sim_pfm: 445.0892020930769
episode: 368 training return: tensor(391.5741, device='cuda:0')
episode: 369 training return: tensor(369.9157, device='cuda:0')
episode: 370 training return: tensor(441.0990, device='cuda:0')
episode: 371 training return: tensor(418.9157, device='cuda:0')
epoch: 93 test_true_pfm: 3606.991782750285 sim_pfm: 436.4839341886497
episode: 372 training return: tensor(417.1693, device='cuda:0')
episode: 373 training return: tensor(468.2896, device='cuda:0')
episode: 374 training return: tensor(446.6151, device='cuda:0')
episode: 375 training return: tensor(450.1209, device='cuda:0')
epoch: 94 test_true_pfm: 3589.9755421707873 sim_pfm: 444.0676226294211
episode: 376 training return: tensor(391.9787, device='cuda:0')
episode: 377 training return: tensor(388.3758, device='cuda:0')
episode: 378 training return: tensor(357.3858, device='cuda:0')
episode: 379 training return: tensor(417.6029, device='cuda:0')
epoch: 95 test_true_pfm: 3604.4655454440835 sim_pfm: 442.35462575855973
episode: 380 training return: tensor(423.8804, device='cuda:0')
episode: 381 training return: tensor(471.5860, device='cuda:0')
episode: 382 training return: tensor(389.3306, device='cuda:0')
episode: 383 training return: tensor(451.4693, device='cuda:0')
epoch: 96 test_true_pfm: 3559.2778334015416 sim_pfm: 431.9112766977244
episode: 384 training return: tensor(428.1753, device='cuda:0')
episode: 385 training return: tensor(452.2003, device='cuda:0')
episode: 386 training return: tensor(447.3008, device='cuda:0')
episode: 387 training return: tensor(403.9463, device='cuda:0')
epoch: 97 test_true_pfm: 3584.1931619264483 sim_pfm: 422.51131610161
episode: 388 training return: tensor(427.0564, device='cuda:0')
episode: 389 training return: tensor(416.6338, device='cuda:0')
episode: 390 training return: tensor(422.8839, device='cuda:0')
episode: 391 training return: tensor(390.5786, device='cuda:0')
epoch: 98 test_true_pfm: 3643.1711099790214 sim_pfm: 460.6879915546936
episode: 392 training return: tensor(464.7151, device='cuda:0')
episode: 393 training return: tensor(441.5370, device='cuda:0')
episode: 394 training return: tensor(494.0649, device='cuda:0')
episode: 395 training return: tensor(374.6820, device='cuda:0')
epoch: 99 test_true_pfm: 3624.6491239147003 sim_pfm: 465.92311759580235
episode: 396 training return: tensor(417.0823, device='cuda:0')
episode: 397 training return: tensor(430.6505, device='cuda:0')
episode: 398 training return: tensor(387.9368, device='cuda:0')
episode: 399 training return: tensor(441.9198, device='cuda:0')
epoch: 100 test_true_pfm: 3242.2202171446684 sim_pfm: 394.48213587604306
episode: 400 training return: tensor(442.8932, device='cuda:0')
episode: 401 training return: tensor(465.6796, device='cuda:0')
episode: 402 training return: tensor(262.3426, device='cuda:0')
episode: 403 training return: tensor(412.0497, device='cuda:0')
epoch: 101 test_true_pfm: 3584.071878210581 sim_pfm: 438.9681417039149
episode: 404 training return: tensor(462.6659, device='cuda:0')
episode: 405 training return: tensor(430.7610, device='cuda:0')
episode: 406 training return: tensor(401.1708, device='cuda:0')
episode: 407 training return: tensor(388.7715, device='cuda:0')
epoch: 102 test_true_pfm: 3645.27506329523 sim_pfm: 477.52158934110776
episode: 408 training return: tensor(459.0341, device='cuda:0')
episode: 409 training return: tensor(372.3380, device='cuda:0')
episode: 410 training return: tensor(422.5758, device='cuda:0')
episode: 411 training return: tensor(466.1437, device='cuda:0')
epoch: 103 test_true_pfm: 3577.437925464686 sim_pfm: 455.86339171909884
episode: 412 training return: tensor(416.8209, device='cuda:0')
episode: 413 training return: tensor(387.5620, device='cuda:0')
episode: 414 training return: tensor(467.7609, device='cuda:0')
episode: 415 training return: tensor(430.4658, device='cuda:0')
epoch: 104 test_true_pfm: 3601.8828745162523 sim_pfm: 445.7391766074773
episode: 416 training return: tensor(503.9919, device='cuda:0')
episode: 417 training return: tensor(396.6869, device='cuda:0')
episode: 418 training return: tensor(378.6569, device='cuda:0')
episode: 419 training return: tensor(447.1582, device='cuda:0')
epoch: 105 test_true_pfm: 3634.9300204730075 sim_pfm: 400.4705953039229
episode: 420 training return: tensor(404.4644, device='cuda:0')
episode: 421 training return: tensor(375.7899, device='cuda:0')
episode: 422 training return: tensor(418.5927, device='cuda:0')
episode: 423 training return: tensor(135.3595, device='cuda:0')
epoch: 106 test_true_pfm: 3602.7397177963217 sim_pfm: 453.2678249878809
episode: 424 training return: tensor(392.8329, device='cuda:0')
episode: 425 training return: tensor(443.5064, device='cuda:0')
episode: 426 training return: tensor(427.7791, device='cuda:0')
episode: 427 training return: tensor(439.8232, device='cuda:0')
epoch: 107 test_true_pfm: 3560.332118481429 sim_pfm: 435.685935031157
episode: 428 training return: tensor(418.6720, device='cuda:0')
episode: 429 training return: tensor(484.4791, device='cuda:0')
episode: 430 training return: tensor(427.4532, device='cuda:0')
episode: 431 training return: tensor(411.8521, device='cuda:0')
epoch: 108 test_true_pfm: 3603.484479503337 sim_pfm: 437.55841421561007
episode: 432 training return: tensor(422.1812, device='cuda:0')
episode: 433 training return: tensor(421.5758, device='cuda:0')
episode: 434 training return: tensor(444.4922, device='cuda:0')
episode: 435 training return: tensor(478.4170, device='cuda:0')
epoch: 109 test_true_pfm: 3632.80952377917 sim_pfm: 468.73881388824276
episode: 436 training return: tensor(411.1430, device='cuda:0')
episode: 437 training return: tensor(390.6805, device='cuda:0')
episode: 438 training return: tensor(451.3511, device='cuda:0')
episode: 439 training return: tensor(458.2391, device='cuda:0')
epoch: 110 test_true_pfm: 3618.9944513709 sim_pfm: 447.5803845063395
episode: 440 training return: tensor(426.2014, device='cuda:0')
episode: 441 training return: tensor(473.6623, device='cuda:0')
episode: 442 training return: tensor(472.5997, device='cuda:0')
episode: 443 training return: tensor(436.8747, device='cuda:0')
epoch: 111 test_true_pfm: 3553.2622788912836 sim_pfm: 424.5596657146428
episode: 444 training return: tensor(440.2695, device='cuda:0')
episode: 445 training return: tensor(420.8986, device='cuda:0')
episode: 446 training return: tensor(420.9235, device='cuda:0')
episode: 447 training return: tensor(440.3115, device='cuda:0')
epoch: 112 test_true_pfm: 3596.748102202102 sim_pfm: 469.1765583805779
episode: 448 training return: tensor(451.9901, device='cuda:0')
episode: 449 training return: tensor(428.5493, device='cuda:0')
episode: 450 training return: tensor(345.1475, device='cuda:0')
episode: 451 training return: tensor(409.3235, device='cuda:0')
epoch: 113 test_true_pfm: 3620.0280834806476 sim_pfm: 473.5242669146198
episode: 452 training return: tensor(461.1237, device='cuda:0')
episode: 453 training return: tensor(472.0943, device='cuda:0')
episode: 454 training return: tensor(456.2662, device='cuda:0')
episode: 455 training return: tensor(429.4074, device='cuda:0')
epoch: 114 test_true_pfm: 3665.7358694853738 sim_pfm: 476.5284121343866
episode: 456 training return: tensor(428.3065, device='cuda:0')
episode: 457 training return: tensor(403.2880, device='cuda:0')
episode: 458 training return: tensor(439.9658, device='cuda:0')
episode: 459 training return: tensor(379.5392, device='cuda:0')
epoch: 115 test_true_pfm: 3688.8194449483763 sim_pfm: 510.0373450159871
episode: 460 training return: tensor(457.4199, device='cuda:0')
episode: 461 training return: tensor(366.8343, device='cuda:0')
episode: 462 training return: tensor(458.0640, device='cuda:0')
episode: 463 training return: tensor(437.4921, device='cuda:0')
epoch: 116 test_true_pfm: 3650.849206570276 sim_pfm: 449.569180641789
episode: 464 training return: tensor(499.6990, device='cuda:0')
episode: 465 training return: tensor(380.0250, device='cuda:0')
episode: 466 training return: tensor(414.9412, device='cuda:0')
episode: 467 training return: tensor(68.2210, device='cuda:0')
epoch: 117 test_true_pfm: 3648.595604170021 sim_pfm: 463.307215288068
episode: 468 training return: tensor(484.4321, device='cuda:0')
episode: 469 training return: tensor(405.5988, device='cuda:0')
episode: 470 training return: tensor(409.1785, device='cuda:0')
episode: 471 training return: tensor(386.5657, device='cuda:0')
epoch: 118 test_true_pfm: 3605.9504396983925 sim_pfm: 453.02408229606226
episode: 472 training return: tensor(422.0995, device='cuda:0')
episode: 473 training return: tensor(457.5441, device='cuda:0')
episode: 474 training return: tensor(486.5425, device='cuda:0')
episode: 475 training return: tensor(434.8120, device='cuda:0')
epoch: 119 test_true_pfm: 3614.32659162866 sim_pfm: 450.91612255638273
episode: 476 training return: tensor(399.2462, device='cuda:0')
episode: 477 training return: tensor(321.9493, device='cuda:0')
episode: 478 training return: tensor(459.9678, device='cuda:0')
episode: 479 training return: tensor(442.7332, device='cuda:0')
epoch: 120 test_true_pfm: 3691.67672080281 sim_pfm: 505.94156632440473
episode: 480 training return: tensor(445.3835, device='cuda:0')
episode: 481 training return: tensor(417.5207, device='cuda:0')
episode: 482 training return: tensor(442.1288, device='cuda:0')
episode: 483 training return: tensor(409.3980, device='cuda:0')
epoch: 121 test_true_pfm: 3599.7415730951247 sim_pfm: 464.36259902004775
episode: 484 training return: tensor(420.2527, device='cuda:0')
episode: 485 training return: tensor(439.2880, device='cuda:0')
episode: 486 training return: tensor(466.5453, device='cuda:0')
episode: 487 training return: tensor(415.0605, device='cuda:0')
epoch: 122 test_true_pfm: 3576.146875079515 sim_pfm: 435.2834278617326
episode: 488 training return: tensor(492.9242, device='cuda:0')
episode: 489 training return: tensor(400.7914, device='cuda:0')
episode: 490 training return: tensor(319.1868, device='cuda:0')
episode: 491 training return: tensor(472.5449, device='cuda:0')
epoch: 123 test_true_pfm: 3612.7366819256645 sim_pfm: 439.9596478554886
episode: 492 training return: tensor(424.9697, device='cuda:0')
episode: 493 training return: tensor(418.2056, device='cuda:0')
episode: 494 training return: tensor(429.0866, device='cuda:0')
episode: 495 training return: tensor(410.2545, device='cuda:0')
epoch: 124 test_true_pfm: 3641.1776425059325 sim_pfm: 477.39271971288446
episode: 496 training return: tensor(413.7704, device='cuda:0')
episode: 497 training return: tensor(370.3303, device='cuda:0')
episode: 498 training return: tensor(430.8907, device='cuda:0')
episode: 499 training return: tensor(432.3785, device='cuda:0')
epoch: 125 test_true_pfm: 3563.365215116157 sim_pfm: 430.985655225794
episode: 500 training return: tensor(398.7277, device='cuda:0')
episode: 501 training return: tensor(467.6169, device='cuda:0')
episode: 502 training return: tensor(421.5438, device='cuda:0')
episode: 503 training return: tensor(378.5029, device='cuda:0')
epoch: 126 test_true_pfm: 3612.451878499562 sim_pfm: 463.9349212474578
episode: 504 training return: tensor(402.9529, device='cuda:0')
episode: 505 training return: tensor(415.0197, device='cuda:0')
episode: 506 training return: tensor(435.4097, device='cuda:0')
episode: 507 training return: tensor(395.0535, device='cuda:0')
epoch: 127 test_true_pfm: 3532.7303090141963 sim_pfm: 419.8850888760256
episode: 508 training return: tensor(414.0587, device='cuda:0')
episode: 509 training return: tensor(482.9209, device='cuda:0')
episode: 510 training return: tensor(472.1799, device='cuda:0')
episode: 511 training return: tensor(464.2189, device='cuda:0')
epoch: 128 test_true_pfm: 3668.91724021891 sim_pfm: 484.3865486995007
episode: 512 training return: tensor(422.8210, device='cuda:0')
episode: 513 training return: tensor(433.2600, device='cuda:0')
episode: 514 training return: tensor(434.7159, device='cuda:0')
episode: 515 training return: tensor(503.4475, device='cuda:0')
epoch: 129 test_true_pfm: 3593.0050251019106 sim_pfm: 428.9326434539592
episode: 516 training return: tensor(435.6509, device='cuda:0')
episode: 517 training return: tensor(468.6373, device='cuda:0')
episode: 518 training return: tensor(423.3911, device='cuda:0')
episode: 519 training return: tensor(466.8053, device='cuda:0')
epoch: 130 test_true_pfm: 3578.678337030933 sim_pfm: 437.67069843380403
episode: 520 training return: tensor(459.8760, device='cuda:0')
episode: 521 training return: tensor(408.3563, device='cuda:0')
episode: 522 training return: tensor(445.9142, device='cuda:0')
episode: 523 training return: tensor(455.1818, device='cuda:0')
epoch: 131 test_true_pfm: 3667.4711993686046 sim_pfm: 481.73173801472876
episode: 524 training return: tensor(431.5235, device='cuda:0')
episode: 525 training return: tensor(418.2171, device='cuda:0')
episode: 526 training return: tensor(440.4935, device='cuda:0')
episode: 527 training return: tensor(405.4091, device='cuda:0')
epoch: 132 test_true_pfm: 3581.3817845446265 sim_pfm: 448.0164360443596
episode: 528 training return: tensor(393.7328, device='cuda:0')
episode: 529 training return: tensor(444.1165, device='cuda:0')
episode: 530 training return: tensor(437.9474, device='cuda:0')
episode: 531 training return: tensor(414.8842, device='cuda:0')
epoch: 133 test_true_pfm: 3587.184926658641 sim_pfm: 454.68862283679
episode: 532 training return: tensor(455.3617, device='cuda:0')
episode: 533 training return: tensor(429.1368, device='cuda:0')
episode: 534 training return: tensor(466.4230, device='cuda:0')
episode: 535 training return: tensor(426.3075, device='cuda:0')
epoch: 134 test_true_pfm: 3559.585511308603 sim_pfm: 423.84680923066725
episode: 536 training return: tensor(428.8342, device='cuda:0')
episode: 537 training return: tensor(503.9267, device='cuda:0')
episode: 538 training return: tensor(473.9364, device='cuda:0')
episode: 539 training return: tensor(403.6225, device='cuda:0')
epoch: 135 test_true_pfm: 3597.374377430044 sim_pfm: 455.5285171942475
episode: 540 training return: tensor(416.4524, device='cuda:0')
episode: 541 training return: tensor(424.1552, device='cuda:0')
episode: 542 training return: tensor(482.7631, device='cuda:0')
episode: 543 training return: tensor(444.5427, device='cuda:0')
epoch: 136 test_true_pfm: 3689.7609083734255 sim_pfm: 505.5806472861441
episode: 544 training return: tensor(410.8741, device='cuda:0')
episode: 545 training return: tensor(407.6252, device='cuda:0')
episode: 546 training return: tensor(461.2918, device='cuda:0')
episode: 547 training return: tensor(421.7994, device='cuda:0')
epoch: 137 test_true_pfm: 3622.1650390213267 sim_pfm: 484.702157787707
episode: 548 training return: tensor(464.6490, device='cuda:0')
episode: 549 training return: tensor(477.7188, device='cuda:0')
episode: 550 training return: tensor(437.1962, device='cuda:0')
episode: 551 training return: tensor(446.3911, device='cuda:0')
epoch: 138 test_true_pfm: 3596.651496238222 sim_pfm: 464.87046050749876
episode: 552 training return: tensor(432.2596, device='cuda:0')
episode: 553 training return: tensor(444.3030, device='cuda:0')
episode: 554 training return: tensor(450.6337, device='cuda:0')
episode: 555 training return: tensor(421.6293, device='cuda:0')
epoch: 139 test_true_pfm: 3608.948305507485 sim_pfm: 487.30737192781334
episode: 556 training return: tensor(426.3683, device='cuda:0')
episode: 557 training return: tensor(407.6106, device='cuda:0')
episode: 558 training return: tensor(481.5507, device='cuda:0')
episode: 559 training return: tensor(439.9550, device='cuda:0')
epoch: 140 test_true_pfm: 3613.8080141801365 sim_pfm: 448.7974254398917
episode: 560 training return: tensor(440.6279, device='cuda:0')
episode: 561 training return: tensor(414.2985, device='cuda:0')
episode: 562 training return: tensor(436.5150, device='cuda:0')
episode: 563 training return: tensor(424.8013, device='cuda:0')
epoch: 141 test_true_pfm: 3631.51694546675 sim_pfm: 472.7576890196069
episode: 564 training return: tensor(353.8839, device='cuda:0')
episode: 565 training return: tensor(406.2211, device='cuda:0')
episode: 566 training return: tensor(486.7932, device='cuda:0')
episode: 567 training return: tensor(475.4775, device='cuda:0')
epoch: 142 test_true_pfm: 3636.9584955708146 sim_pfm: 462.841525676117
episode: 568 training return: tensor(456.7926, device='cuda:0')
episode: 569 training return: tensor(458.3304, device='cuda:0')
episode: 570 training return: tensor(464.1164, device='cuda:0')
episode: 571 training return: tensor(423.8210, device='cuda:0')
epoch: 143 test_true_pfm: 3602.664267433647 sim_pfm: 465.6408910708851
episode: 572 training return: tensor(384.4044, device='cuda:0')
episode: 573 training return: tensor(456.9148, device='cuda:0')
episode: 574 training return: tensor(439.7051, device='cuda:0')
episode: 575 training return: tensor(482.5899, device='cuda:0')
epoch: 144 test_true_pfm: 3614.101588802354 sim_pfm: 446.2755995982249
episode: 576 training return: tensor(432.5591, device='cuda:0')
episode: 577 training return: tensor(434.5439, device='cuda:0')
episode: 578 training return: tensor(462.1111, device='cuda:0')
episode: 579 training return: tensor(458.1745, device='cuda:0')
epoch: 145 test_true_pfm: 3612.4094855237636 sim_pfm: 454.29077947962406
episode: 580 training return: tensor(444.0730, device='cuda:0')
episode: 581 training return: tensor(418.8362, device='cuda:0')
episode: 582 training return: tensor(418.0929, device='cuda:0')
episode: 583 training return: tensor(436.0720, device='cuda:0')
epoch: 146 test_true_pfm: 3561.4691617499325 sim_pfm: 432.0659630896989
episode: 584 training return: tensor(432.6584, device='cuda:0')
episode: 585 training return: tensor(420.2603, device='cuda:0')
episode: 586 training return: tensor(450.1112, device='cuda:0')
episode: 587 training return: tensor(429.3850, device='cuda:0')
epoch: 147 test_true_pfm: 3628.509398705371 sim_pfm: 476.5600057127497
episode: 588 training return: tensor(424.6482, device='cuda:0')
episode: 589 training return: tensor(428.0737, device='cuda:0')
episode: 590 training return: tensor(450.3693, device='cuda:0')
episode: 591 training return: tensor(452.1823, device='cuda:0')
epoch: 148 test_true_pfm: 3675.9763956503666 sim_pfm: 476.45581107295584
episode: 592 training return: tensor(433.5882, device='cuda:0')
episode: 593 training return: tensor(482.0826, device='cuda:0')
episode: 594 training return: tensor(449.7532, device='cuda:0')
episode: 595 training return: tensor(472.8182, device='cuda:0')
epoch: 149 test_true_pfm: 3602.2105131159774 sim_pfm: 450.3939391253516
episode: 596 training return: tensor(446.9095, device='cuda:0')
episode: 597 training return: tensor(443.2833, device='cuda:0')
episode: 598 training return: tensor(429.9073, device='cuda:0')
episode: 599 training return: tensor(424.5445, device='cuda:0')
epoch: 150 test_true_pfm: 3567.7927016550316 sim_pfm: 429.8529329742305
