['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '1']
episode: 0 training return: tensor(-161.0864, device='cuda:0')
episode: 1 training return: tensor(-210.8101, device='cuda:0')
episode: 2 training return: tensor(-334.4704, device='cuda:0')
episode: 3 training return: tensor(-311.4525, device='cuda:0')
epoch: 1 test_true_pfm: 25.52551992536714 sim_pfm: 241.76123123657308
episode: 4 training return: tensor(-323.9843, device='cuda:0')
episode: 5 training return: tensor(-197.5956, device='cuda:0')
episode: 6 training return: tensor(-195.6141, device='cuda:0')
episode: 7 training return: tensor(-179.7135, device='cuda:0')
epoch: 2 test_true_pfm: 18.537736668848776 sim_pfm: -265.1221913713962
episode: 8 training return: tensor(-300.4943, device='cuda:0')
episode: 9 training return: tensor(-291.3571, device='cuda:0')
episode: 10 training return: tensor(-481.5721, device='cuda:0')
episode: 11 training return: tensor(-16.2630, device='cuda:0')
epoch: 3 test_true_pfm: 24.76994340624151 sim_pfm: -94.4249920804461
episode: 12 training return: tensor(-50.5425, device='cuda:0')
episode: 13 training return: tensor(146.4908, device='cuda:0')
episode: 14 training return: tensor(164.7000, device='cuda:0')
episode: 15 training return: tensor(-39.4837, device='cuda:0')
epoch: 4 test_true_pfm: 19.382337980759036 sim_pfm: -53.97592689255252
episode: 16 training return: tensor(223.1378, device='cuda:0')
episode: 17 training return: tensor(268.0732, device='cuda:0')
episode: 18 training return: tensor(147.0362, device='cuda:0')
episode: 19 training return: tensor(282.1293, device='cuda:0')
epoch: 5 test_true_pfm: 30.40850676245359 sim_pfm: 308.30220684005764
episode: 20 training return: tensor(286.9958, device='cuda:0')
episode: 21 training return: tensor(281.9911, device='cuda:0')
episode: 22 training return: tensor(252.7671, device='cuda:0')
episode: 23 training return: tensor(255.2810, device='cuda:0')
epoch: 6 test_true_pfm: 22.582706140467955 sim_pfm: -32.68939167721546
episode: 24 training return: tensor(285.1121, device='cuda:0')
episode: 25 training return: tensor(304.1770, device='cuda:0')
episode: 26 training return: tensor(328.1100, device='cuda:0')
episode: 27 training return: tensor(316.9975, device='cuda:0')
epoch: 7 test_true_pfm: 31.546639500450574 sim_pfm: 357.0717744661553
episode: 28 training return: tensor(345.8786, device='cuda:0')
episode: 29 training return: tensor(226.1122, device='cuda:0')
episode: 30 training return: tensor(366.0755, device='cuda:0')
episode: 31 training return: tensor(380.5273, device='cuda:0')
epoch: 8 test_true_pfm: 31.852073363475665 sim_pfm: 390.9246764240728
episode: 32 training return: tensor(351.8316, device='cuda:0')
episode: 33 training return: tensor(338.7879, device='cuda:0')
episode: 34 training return: tensor(325.0284, device='cuda:0')
episode: 35 training return: tensor(333.3558, device='cuda:0')
epoch: 9 test_true_pfm: 27.46776554101192 sim_pfm: 196.9177546123974
episode: 36 training return: tensor(345.1366, device='cuda:0')
episode: 37 training return: tensor(-182.9214, device='cuda:0')
episode: 38 training return: tensor(-214.7996, device='cuda:0')
episode: 39 training return: tensor(382.2702, device='cuda:0')
epoch: 10 test_true_pfm: 31.769795560284745 sim_pfm: 420.4710178539506
episode: 40 training return: tensor(392.3471, device='cuda:0')
episode: 41 training return: tensor(372.6276, device='cuda:0')
episode: 42 training return: tensor(385.5599, device='cuda:0')
episode: 43 training return: tensor(357.4721, device='cuda:0')
epoch: 11 test_true_pfm: 33.266226171779465 sim_pfm: 373.7322149084415
episode: 44 training return: tensor(359.1337, device='cuda:0')
episode: 45 training return: tensor(34.8042, device='cuda:0')
episode: 46 training return: tensor(264.5183, device='cuda:0')
episode: 47 training return: tensor(154.3929, device='cuda:0')
epoch: 12 test_true_pfm: 35.11109744586277 sim_pfm: 242.7675744020904
episode: 48 training return: tensor(119.8814, device='cuda:0')
episode: 49 training return: tensor(215.2543, device='cuda:0')
episode: 50 training return: tensor(330.7371, device='cuda:0')
episode: 51 training return: tensor(309.6658, device='cuda:0')
epoch: 13 test_true_pfm: 25.602444364127308 sim_pfm: -334.94100488811966
episode: 52 training return: tensor(22.4261, device='cuda:0')
episode: 53 training return: tensor(287.7047, device='cuda:0')
episode: 54 training return: tensor(268.4061, device='cuda:0')
episode: 55 training return: tensor(406.5244, device='cuda:0')
epoch: 14 test_true_pfm: 29.686701433247435 sim_pfm: 290.91360603859647
episode: 56 training return: tensor(301.6268, device='cuda:0')
episode: 57 training return: tensor(370.2598, device='cuda:0')
episode: 58 training return: tensor(152.7895, device='cuda:0')
episode: 59 training return: tensor(407.6627, device='cuda:0')
epoch: 15 test_true_pfm: 34.40186526561639 sim_pfm: 369.14807836037363
episode: 60 training return: tensor(350.2034, device='cuda:0')
episode: 61 training return: tensor(392.9333, device='cuda:0')
episode: 62 training return: tensor(380.4456, device='cuda:0')
episode: 63 training return: tensor(374.1916, device='cuda:0')
epoch: 16 test_true_pfm: 37.123856080656694 sim_pfm: 395.4710478413035
episode: 64 training return: tensor(379.5075, device='cuda:0')
episode: 65 training return: tensor(387.8100, device='cuda:0')
episode: 66 training return: tensor(356.2815, device='cuda:0')
episode: 67 training return: tensor(320.5188, device='cuda:0')
epoch: 17 test_true_pfm: 45.37628853125588 sim_pfm: 341.7286879419291
episode: 68 training return: tensor(323.2325, device='cuda:0')
episode: 69 training return: tensor(316.6153, device='cuda:0')
episode: 70 training return: tensor(462.1765, device='cuda:0')
episode: 71 training return: tensor(374.3136, device='cuda:0')
epoch: 18 test_true_pfm: 38.62857623815843 sim_pfm: 273.8591355498182
episode: 72 training return: tensor(292.8563, device='cuda:0')
episode: 73 training return: tensor(346.4651, device='cuda:0')
episode: 74 training return: tensor(485.1414, device='cuda:0')
episode: 75 training return: tensor(349.5753, device='cuda:0')
epoch: 19 test_true_pfm: 34.420703360265506 sim_pfm: 394.0526798683568
episode: 76 training return: tensor(354.3321, device='cuda:0')
episode: 77 training return: tensor(501.2351, device='cuda:0')
episode: 78 training return: tensor(557.4373, device='cuda:0')
episode: 79 training return: tensor(-105.8801, device='cuda:0')
epoch: 20 test_true_pfm: 19.142738188594148 sim_pfm: 181.78222381483064
episode: 80 training return: tensor(450.0815, device='cuda:0')
episode: 81 training return: tensor(290.7474, device='cuda:0')
episode: 82 training return: tensor(510.1281, device='cuda:0')
episode: 83 training return: tensor(480.4860, device='cuda:0')
epoch: 21 test_true_pfm: 33.06821956015769 sim_pfm: 598.5202167460695
episode: 84 training return: tensor(507.2355, device='cuda:0')
episode: 85 training return: tensor(565.1449, device='cuda:0')
episode: 86 training return: tensor(605.5852, device='cuda:0')
episode: 87 training return: tensor(596.0723, device='cuda:0')
epoch: 22 test_true_pfm: 39.173581564436844 sim_pfm: 590.3577908497303
episode: 88 training return: tensor(603.9612, device='cuda:0')
episode: 89 training return: tensor(669.9346, device='cuda:0')
episode: 90 training return: tensor(679.5964, device='cuda:0')
episode: 91 training return: tensor(641.9956, device='cuda:0')
epoch: 23 test_true_pfm: 48.993517628284586 sim_pfm: 721.1255130557344
episode: 92 training return: tensor(697.7610, device='cuda:0')
episode: 93 training return: tensor(642.4453, device='cuda:0')
episode: 94 training return: tensor(532.6906, device='cuda:0')
episode: 95 training return: tensor(681.0854, device='cuda:0')
epoch: 24 test_true_pfm: 36.20705482144109 sim_pfm: 215.90158986615717
episode: 96 training return: tensor(687.8181, device='cuda:0')
episode: 97 training return: tensor(-164.0842, device='cuda:0')
episode: 98 training return: tensor(-94.0524, device='cuda:0')
episode: 99 training return: tensor(-100.8760, device='cuda:0')
epoch: 25 test_true_pfm: 22.154502379525333 sim_pfm: 121.39711982959416
episode: 100 training return: tensor(-180.3531, device='cuda:0')
episode: 101 training return: tensor(627.9923, device='cuda:0')
episode: 102 training return: tensor(684.9703, device='cuda:0')
episode: 103 training return: tensor(726.5043, device='cuda:0')
epoch: 26 test_true_pfm: 44.319215860025544 sim_pfm: 572.1614600242581
episode: 104 training return: tensor(707.6024, device='cuda:0')
episode: 105 training return: tensor(721.8004, device='cuda:0')
episode: 106 training return: tensor(605.4867, device='cuda:0')
episode: 107 training return: tensor(750.7639, device='cuda:0')
epoch: 27 test_true_pfm: 46.832381649150875 sim_pfm: 722.8761994249187
episode: 108 training return: tensor(728.6245, device='cuda:0')
episode: 109 training return: tensor(715.5570, device='cuda:0')
episode: 110 training return: tensor(737.5543, device='cuda:0')
episode: 111 training return: tensor(731.8078, device='cuda:0')
epoch: 28 test_true_pfm: 36.82762980466042 sim_pfm: 752.4875058398466
episode: 112 training return: tensor(661.7053, device='cuda:0')
episode: 113 training return: tensor(678.2090, device='cuda:0')
episode: 114 training return: tensor(651.7541, device='cuda:0')
episode: 115 training return: tensor(708.3306, device='cuda:0')
epoch: 29 test_true_pfm: 44.23208640801908 sim_pfm: 760.0002830043435
episode: 116 training return: tensor(687.1094, device='cuda:0')
episode: 117 training return: tensor(660.5847, device='cuda:0')
episode: 118 training return: tensor(720.5908, device='cuda:0')
episode: 119 training return: tensor(711.2388, device='cuda:0')
epoch: 30 test_true_pfm: 40.01675355133513 sim_pfm: 697.6160640687682
episode: 120 training return: tensor(694.3160, device='cuda:0')
episode: 121 training return: tensor(713.5898, device='cuda:0')
episode: 122 training return: tensor(720.0157, device='cuda:0')
episode: 123 training return: tensor(723.1351, device='cuda:0')
epoch: 31 test_true_pfm: 43.01418334708571 sim_pfm: 760.8753207501024
episode: 124 training return: tensor(729.9264, device='cuda:0')
episode: 125 training return: tensor(724.7559, device='cuda:0')
episode: 126 training return: tensor(741.2538, device='cuda:0')
episode: 127 training return: tensor(710.7263, device='cuda:0')
epoch: 32 test_true_pfm: 48.57815614068608 sim_pfm: 741.659498531418
episode: 128 training return: tensor(713.5955, device='cuda:0')
episode: 129 training return: tensor(731.0024, device='cuda:0')
episode: 130 training return: tensor(706.3214, device='cuda:0')
episode: 131 training return: tensor(702.7323, device='cuda:0')
epoch: 33 test_true_pfm: 47.671129810312934 sim_pfm: 743.337835121993
episode: 132 training return: tensor(730.3765, device='cuda:0')
episode: 133 training return: tensor(737.0533, device='cuda:0')
episode: 134 training return: tensor(729.5541, device='cuda:0')
episode: 135 training return: tensor(712.6745, device='cuda:0')
epoch: 34 test_true_pfm: 39.23216143405293 sim_pfm: 760.7217628606129
episode: 136 training return: tensor(742.6570, device='cuda:0')
episode: 137 training return: tensor(728.4139, device='cuda:0')
episode: 138 training return: tensor(736.7339, device='cuda:0')
episode: 139 training return: tensor(739.9592, device='cuda:0')
epoch: 35 test_true_pfm: 36.6582583447406 sim_pfm: 772.6518267791253
episode: 140 training return: tensor(755.2502, device='cuda:0')
episode: 141 training return: tensor(729.6829, device='cuda:0')
episode: 142 training return: tensor(737.1888, device='cuda:0')
episode: 143 training return: tensor(731.4727, device='cuda:0')
epoch: 36 test_true_pfm: 52.01489806003367 sim_pfm: 763.6498297079931
episode: 144 training return: tensor(706.3906, device='cuda:0')
episode: 145 training return: tensor(720.6773, device='cuda:0')
episode: 146 training return: tensor(739.1613, device='cuda:0')
episode: 147 training return: tensor(746.8866, device='cuda:0')
epoch: 37 test_true_pfm: 49.33990081182738 sim_pfm: 756.8343990314752
episode: 148 training return: tensor(735.7286, device='cuda:0')
episode: 149 training return: tensor(733.4328, device='cuda:0')
episode: 150 training return: tensor(734.3926, device='cuda:0')
episode: 151 training return: tensor(755.1277, device='cuda:0')
epoch: 38 test_true_pfm: 57.878552008879886 sim_pfm: 755.7085619687102
episode: 152 training return: tensor(741.3820, device='cuda:0')
episode: 153 training return: tensor(758.1265, device='cuda:0')
episode: 154 training return: tensor(745.9274, device='cuda:0')
episode: 155 training return: tensor(719.9099, device='cuda:0')
epoch: 39 test_true_pfm: 51.93376669570789 sim_pfm: 782.824109840393
episode: 156 training return: tensor(768.5686, device='cuda:0')
episode: 157 training return: tensor(731.3572, device='cuda:0')
episode: 158 training return: tensor(746.9478, device='cuda:0')
episode: 159 training return: tensor(735.7635, device='cuda:0')
epoch: 40 test_true_pfm: 47.87113864203377 sim_pfm: 760.8934778875671
episode: 160 training return: tensor(733.5470, device='cuda:0')
episode: 161 training return: tensor(743.2639, device='cuda:0')
episode: 162 training return: tensor(743.8137, device='cuda:0')
episode: 163 training return: tensor(757.4513, device='cuda:0')
epoch: 41 test_true_pfm: 45.964883088552334 sim_pfm: 759.0367309479974
episode: 164 training return: tensor(763.1331, device='cuda:0')
episode: 165 training return: tensor(696.3959, device='cuda:0')
episode: 166 training return: tensor(738.2882, device='cuda:0')
episode: 167 training return: tensor(747.0193, device='cuda:0')
epoch: 42 test_true_pfm: 47.70576403371528 sim_pfm: 771.7903611843474
episode: 168 training return: tensor(719.4519, device='cuda:0')
episode: 169 training return: tensor(732.1641, device='cuda:0')
episode: 170 training return: tensor(746.9940, device='cuda:0')
episode: 171 training return: tensor(754.3954, device='cuda:0')
epoch: 43 test_true_pfm: 52.53395264282295 sim_pfm: 770.4949734985828
episode: 172 training return: tensor(741.1779, device='cuda:0')
episode: 173 training return: tensor(738.0902, device='cuda:0')
episode: 174 training return: tensor(736.4910, device='cuda:0')
episode: 175 training return: tensor(741.6633, device='cuda:0')
epoch: 44 test_true_pfm: 44.90018661659316 sim_pfm: 781.728910657391
episode: 176 training return: tensor(764.3505, device='cuda:0')
episode: 177 training return: tensor(741.4371, device='cuda:0')
episode: 178 training return: tensor(744.4417, device='cuda:0')
episode: 179 training return: tensor(738.9008, device='cuda:0')
epoch: 45 test_true_pfm: 31.336732257354036 sim_pfm: 666.7931315511581
episode: 180 training return: tensor(736.5953, device='cuda:0')
episode: 181 training return: tensor(741.6508, device='cuda:0')
episode: 182 training return: tensor(722.6502, device='cuda:0')
episode: 183 training return: tensor(730.5104, device='cuda:0')
epoch: 46 test_true_pfm: 50.75145674567515 sim_pfm: 776.7702893624082
episode: 184 training return: tensor(756.0410, device='cuda:0')
episode: 185 training return: tensor(761.9144, device='cuda:0')
episode: 186 training return: tensor(753.3252, device='cuda:0')
episode: 187 training return: tensor(751.8387, device='cuda:0')
epoch: 47 test_true_pfm: 58.20505655730941 sim_pfm: 794.371345538646
episode: 188 training return: tensor(745.9182, device='cuda:0')
episode: 189 training return: tensor(743.2144, device='cuda:0')
episode: 190 training return: tensor(728.2167, device='cuda:0')
episode: 191 training return: tensor(740.1953, device='cuda:0')
epoch: 48 test_true_pfm: 48.43342173614654 sim_pfm: 712.6875471917447
episode: 192 training return: tensor(747.0619, device='cuda:0')
episode: 193 training return: tensor(727.4796, device='cuda:0')
episode: 194 training return: tensor(687.9562, device='cuda:0')
episode: 195 training return: tensor(723.9532, device='cuda:0')
epoch: 49 test_true_pfm: 46.12023791296482 sim_pfm: 769.7663646451198
episode: 196 training return: tensor(687.3640, device='cuda:0')
episode: 197 training return: tensor(744.4156, device='cuda:0')
episode: 198 training return: tensor(723.5894, device='cuda:0')
episode: 199 training return: tensor(756.3576, device='cuda:0')
epoch: 50 test_true_pfm: 52.47197156077375 sim_pfm: 755.951302996464
episode: 200 training return: tensor(719.9990, device='cuda:0')
episode: 201 training return: tensor(747.0629, device='cuda:0')
episode: 202 training return: tensor(747.1428, device='cuda:0')
episode: 203 training return: tensor(759.4763, device='cuda:0')
epoch: 51 test_true_pfm: 42.45348178801022 sim_pfm: 793.3394901251653
episode: 204 training return: tensor(761.8745, device='cuda:0')
episode: 205 training return: tensor(705.8617, device='cuda:0')
episode: 206 training return: tensor(715.3845, device='cuda:0')
episode: 207 training return: tensor(767.7200, device='cuda:0')
epoch: 52 test_true_pfm: 46.9659672182784 sim_pfm: 743.2831691174302
episode: 208 training return: tensor(711.5163, device='cuda:0')
episode: 209 training return: tensor(698.9734, device='cuda:0')
episode: 210 training return: tensor(741.0602, device='cuda:0')
episode: 211 training return: tensor(752.8460, device='cuda:0')
epoch: 53 test_true_pfm: 49.34416250294756 sim_pfm: 763.1463929120916
episode: 212 training return: tensor(730.4564, device='cuda:0')
episode: 213 training return: tensor(762.6044, device='cuda:0')
episode: 214 training return: tensor(757.7081, device='cuda:0')
episode: 215 training return: tensor(731.9816, device='cuda:0')
epoch: 54 test_true_pfm: 47.94101800184095 sim_pfm: 780.3922315269825
episode: 216 training return: tensor(743.7581, device='cuda:0')
episode: 217 training return: tensor(767.5602, device='cuda:0')
episode: 218 training return: tensor(701.6349, device='cuda:0')
episode: 219 training return: tensor(671.9991, device='cuda:0')
epoch: 55 test_true_pfm: 37.96195498388691 sim_pfm: 778.1872703146189
episode: 220 training return: tensor(723.0117, device='cuda:0')
episode: 221 training return: tensor(762.1808, device='cuda:0')
episode: 222 training return: tensor(741.6443, device='cuda:0')
episode: 223 training return: tensor(713.9922, device='cuda:0')
epoch: 56 test_true_pfm: 49.69842447100798 sim_pfm: 770.3703309603036
episode: 224 training return: tensor(747.1347, device='cuda:0')
episode: 225 training return: tensor(723.7343, device='cuda:0')
episode: 226 training return: tensor(757.7604, device='cuda:0')
episode: 227 training return: tensor(764.5316, device='cuda:0')
epoch: 57 test_true_pfm: 41.623948690955196 sim_pfm: 754.5067026282661
episode: 228 training return: tensor(748.8360, device='cuda:0')
episode: 229 training return: tensor(733.9946, device='cuda:0')
episode: 230 training return: tensor(739.0468, device='cuda:0')
episode: 231 training return: tensor(739.8786, device='cuda:0')
epoch: 58 test_true_pfm: 46.79280850837101 sim_pfm: 765.2110379456542
episode: 232 training return: tensor(760.0402, device='cuda:0')
episode: 233 training return: tensor(759.0215, device='cuda:0')
episode: 234 training return: tensor(765.3394, device='cuda:0')
episode: 235 training return: tensor(735.9088, device='cuda:0')
epoch: 59 test_true_pfm: 47.68036717776498 sim_pfm: 763.2977160179755
episode: 236 training return: tensor(724.1240, device='cuda:0')
episode: 237 training return: tensor(737.1813, device='cuda:0')
episode: 238 training return: tensor(716.0187, device='cuda:0')
episode: 239 training return: tensor(727.6665, device='cuda:0')
epoch: 60 test_true_pfm: 41.148012849855135 sim_pfm: 726.3348259091377
episode: 240 training return: tensor(710.7968, device='cuda:0')
episode: 241 training return: tensor(737.8589, device='cuda:0')
episode: 242 training return: tensor(748.7516, device='cuda:0')
episode: 243 training return: tensor(726.9653, device='cuda:0')
epoch: 61 test_true_pfm: 38.43858220340537 sim_pfm: 753.6619764948497
episode: 244 training return: tensor(728.4282, device='cuda:0')
episode: 245 training return: tensor(751.8059, device='cuda:0')
episode: 246 training return: tensor(729.0029, device='cuda:0')
episode: 247 training return: tensor(719.3307, device='cuda:0')
epoch: 62 test_true_pfm: 36.837281883953345 sim_pfm: 763.6364238044247
episode: 248 training return: tensor(757.2722, device='cuda:0')
episode: 249 training return: tensor(785.6083, device='cuda:0')
episode: 250 training return: tensor(738.6393, device='cuda:0')
episode: 251 training return: tensor(714.0943, device='cuda:0')
epoch: 63 test_true_pfm: 48.3133946504536 sim_pfm: 721.5635359979235
episode: 252 training return: tensor(719.3546, device='cuda:0')
episode: 253 training return: tensor(749.0377, device='cuda:0')
episode: 254 training return: tensor(729.6307, device='cuda:0')
episode: 255 training return: tensor(722.8434, device='cuda:0')
epoch: 64 test_true_pfm: 48.31139785133656 sim_pfm: 709.9294395996258
episode: 256 training return: tensor(746.1227, device='cuda:0')
episode: 257 training return: tensor(750.7404, device='cuda:0')
episode: 258 training return: tensor(721.1801, device='cuda:0')
episode: 259 training return: tensor(732.5223, device='cuda:0')
epoch: 65 test_true_pfm: 48.45609568653758 sim_pfm: 752.277795117721
episode: 260 training return: tensor(746.4600, device='cuda:0')
episode: 261 training return: tensor(733.9238, device='cuda:0')
episode: 262 training return: tensor(715.1003, device='cuda:0')
episode: 263 training return: tensor(716.4487, device='cuda:0')
epoch: 66 test_true_pfm: 48.2246277268916 sim_pfm: 785.9747700442094
episode: 264 training return: tensor(713.7137, device='cuda:0')
episode: 265 training return: tensor(740.0903, device='cuda:0')
episode: 266 training return: tensor(726.2127, device='cuda:0')
episode: 267 training return: tensor(712.8675, device='cuda:0')
epoch: 67 test_true_pfm: 50.353967707519665 sim_pfm: 776.1304493502015
episode: 268 training return: tensor(768.4250, device='cuda:0')
episode: 269 training return: tensor(730.8986, device='cuda:0')
episode: 270 training return: tensor(734.1342, device='cuda:0')
episode: 271 training return: tensor(748.6086, device='cuda:0')
epoch: 68 test_true_pfm: 50.99290296517413 sim_pfm: 767.5981687614694
episode: 272 training return: tensor(749.2133, device='cuda:0')
episode: 273 training return: tensor(746.1071, device='cuda:0')
episode: 274 training return: tensor(762.3145, device='cuda:0')
episode: 275 training return: tensor(752.2157, device='cuda:0')
epoch: 69 test_true_pfm: 49.46939337191206 sim_pfm: 774.2832401280291
episode: 276 training return: tensor(764.5645, device='cuda:0')
episode: 277 training return: tensor(774.9313, device='cuda:0')
episode: 278 training return: tensor(740.2525, device='cuda:0')
episode: 279 training return: tensor(777.3228, device='cuda:0')
epoch: 70 test_true_pfm: 49.21810065838862 sim_pfm: 783.3041287254542
episode: 280 training return: tensor(738.3292, device='cuda:0')
episode: 281 training return: tensor(752.2344, device='cuda:0')
episode: 282 training return: tensor(767.7953, device='cuda:0')
episode: 283 training return: tensor(761.4641, device='cuda:0')
epoch: 71 test_true_pfm: 47.684946102629105 sim_pfm: 778.1151671588304
episode: 284 training return: tensor(768.4397, device='cuda:0')
episode: 285 training return: tensor(774.5802, device='cuda:0')
episode: 286 training return: tensor(765.7604, device='cuda:0')
episode: 287 training return: tensor(775.4500, device='cuda:0')
epoch: 72 test_true_pfm: 43.53138670926851 sim_pfm: 790.7804299704264
episode: 288 training return: tensor(756.6312, device='cuda:0')
episode: 289 training return: tensor(750.3359, device='cuda:0')
episode: 290 training return: tensor(751.2775, device='cuda:0')
episode: 291 training return: tensor(782.7727, device='cuda:0')
epoch: 73 test_true_pfm: 52.648797800522104 sim_pfm: 789.2672179116868
episode: 292 training return: tensor(743.1154, device='cuda:0')
episode: 293 training return: tensor(741.4345, device='cuda:0')
episode: 294 training return: tensor(726.6669, device='cuda:0')
episode: 295 training return: tensor(762.4940, device='cuda:0')
epoch: 74 test_true_pfm: 51.023184604843635 sim_pfm: 773.9364319067448
episode: 296 training return: tensor(734.1323, device='cuda:0')
episode: 297 training return: tensor(744.6295, device='cuda:0')
episode: 298 training return: tensor(747.2985, device='cuda:0')
episode: 299 training return: tensor(754.6099, device='cuda:0')
epoch: 75 test_true_pfm: 51.03297838703533 sim_pfm: 771.403318436438
episode: 300 training return: tensor(740.7982, device='cuda:0')
episode: 301 training return: tensor(770.9298, device='cuda:0')
episode: 302 training return: tensor(755.4401, device='cuda:0')
episode: 303 training return: tensor(752.7533, device='cuda:0')
epoch: 76 test_true_pfm: 46.63644800535277 sim_pfm: 741.1997598864139
episode: 304 training return: tensor(756.8030, device='cuda:0')
episode: 305 training return: tensor(743.9415, device='cuda:0')
episode: 306 training return: tensor(749.4086, device='cuda:0')
episode: 307 training return: tensor(740.4410, device='cuda:0')
epoch: 77 test_true_pfm: 46.71202906427512 sim_pfm: 754.9358926281333
episode: 308 training return: tensor(691.7202, device='cuda:0')
episode: 309 training return: tensor(655.4941, device='cuda:0')
episode: 310 training return: tensor(602.1837, device='cuda:0')
episode: 311 training return: tensor(753.1734, device='cuda:0')
epoch: 78 test_true_pfm: 30.75826614521275 sim_pfm: 739.3836964185582
episode: 312 training return: tensor(733.7932, device='cuda:0')
episode: 313 training return: tensor(750.4675, device='cuda:0')
episode: 314 training return: tensor(748.6941, device='cuda:0')
episode: 315 training return: tensor(740.2676, device='cuda:0')
epoch: 79 test_true_pfm: 37.62578516700617 sim_pfm: 772.2819033680483
episode: 316 training return: tensor(760.1874, device='cuda:0')
episode: 317 training return: tensor(754.7337, device='cuda:0')
episode: 318 training return: tensor(762.9156, device='cuda:0')
episode: 319 training return: tensor(729.7994, device='cuda:0')
epoch: 80 test_true_pfm: 46.745872919233264 sim_pfm: 773.109627384413
episode: 320 training return: tensor(780.0846, device='cuda:0')
episode: 321 training return: tensor(692.2615, device='cuda:0')
episode: 322 training return: tensor(705.9631, device='cuda:0')
episode: 323 training return: tensor(741.1382, device='cuda:0')
epoch: 81 test_true_pfm: 53.503549975211435 sim_pfm: 775.4022944284603
episode: 324 training return: tensor(762.7222, device='cuda:0')
episode: 325 training return: tensor(733.5358, device='cuda:0')
episode: 326 training return: tensor(745.0839, device='cuda:0')
episode: 327 training return: tensor(737.1805, device='cuda:0')
epoch: 82 test_true_pfm: 40.80441059410752 sim_pfm: 754.2192877711728
episode: 328 training return: tensor(738.4575, device='cuda:0')
episode: 329 training return: tensor(718.5948, device='cuda:0')
episode: 330 training return: tensor(768.9404, device='cuda:0')
episode: 331 training return: tensor(687.4808, device='cuda:0')
epoch: 83 test_true_pfm: 39.83328250824357 sim_pfm: 739.5036301638931
episode: 332 training return: tensor(757.5434, device='cuda:0')
episode: 333 training return: tensor(743.6830, device='cuda:0')
episode: 334 training return: tensor(758.8751, device='cuda:0')
episode: 335 training return: tensor(762.4412, device='cuda:0')
epoch: 84 test_true_pfm: 43.45357580040607 sim_pfm: 776.9524644367397
episode: 336 training return: tensor(749.8192, device='cuda:0')
episode: 337 training return: tensor(745.2668, device='cuda:0')
episode: 338 training return: tensor(748.0455, device='cuda:0')
episode: 339 training return: tensor(755.1718, device='cuda:0')
epoch: 85 test_true_pfm: 50.18754487639148 sim_pfm: 776.3915605608374
episode: 340 training return: tensor(767.3011, device='cuda:0')
episode: 341 training return: tensor(755.0538, device='cuda:0')
episode: 342 training return: tensor(737.3460, device='cuda:0')
episode: 343 training return: tensor(722.7569, device='cuda:0')
epoch: 86 test_true_pfm: 44.84899712440166 sim_pfm: 779.8466118822805
episode: 344 training return: tensor(743.6946, device='cuda:0')
episode: 345 training return: tensor(706.6550, device='cuda:0')
episode: 346 training return: tensor(739.7036, device='cuda:0')
episode: 347 training return: tensor(741.5443, device='cuda:0')
epoch: 87 test_true_pfm: 48.58065018871146 sim_pfm: 770.1244624659419
episode: 348 training return: tensor(753.1859, device='cuda:0')
episode: 349 training return: tensor(748.1096, device='cuda:0')
episode: 350 training return: tensor(763.7933, device='cuda:0')
episode: 351 training return: tensor(764.6100, device='cuda:0')
epoch: 88 test_true_pfm: 52.9863832479086 sim_pfm: 768.6594186268746
episode: 352 training return: tensor(752.8672, device='cuda:0')
episode: 353 training return: tensor(749.4436, device='cuda:0')
episode: 354 training return: tensor(762.0962, device='cuda:0')
episode: 355 training return: tensor(745.2341, device='cuda:0')
epoch: 89 test_true_pfm: 50.52258715573268 sim_pfm: 762.847831043601
episode: 356 training return: tensor(717.1018, device='cuda:0')
episode: 357 training return: tensor(719.1927, device='cuda:0')
episode: 358 training return: tensor(749.3772, device='cuda:0')
episode: 359 training return: tensor(747.1217, device='cuda:0')
epoch: 90 test_true_pfm: 48.43347522886594 sim_pfm: 764.576261756057
episode: 360 training return: tensor(769.2787, device='cuda:0')
episode: 361 training return: tensor(728.1664, device='cuda:0')
episode: 362 training return: tensor(755.4943, device='cuda:0')
episode: 363 training return: tensor(729.5979, device='cuda:0')
epoch: 91 test_true_pfm: 38.21869080429504 sim_pfm: 766.6251982368528
episode: 364 training return: tensor(756.3424, device='cuda:0')
episode: 365 training return: tensor(731.1318, device='cuda:0')
episode: 366 training return: tensor(716.6903, device='cuda:0')
episode: 367 training return: tensor(745.6165, device='cuda:0')
epoch: 92 test_true_pfm: 47.92082100105051 sim_pfm: 775.3815951291472
episode: 368 training return: tensor(738.9137, device='cuda:0')
episode: 369 training return: tensor(730.9930, device='cuda:0')
episode: 370 training return: tensor(736.9865, device='cuda:0')
episode: 371 training return: tensor(745.1156, device='cuda:0')
epoch: 93 test_true_pfm: 51.00429163083328 sim_pfm: 775.6772271442227
episode: 372 training return: tensor(759.8524, device='cuda:0')
episode: 373 training return: tensor(757.7886, device='cuda:0')
episode: 374 training return: tensor(741.9818, device='cuda:0')
episode: 375 training return: tensor(741.9720, device='cuda:0')
epoch: 94 test_true_pfm: 55.092507243051124 sim_pfm: 789.3991535201669
episode: 376 training return: tensor(754.2415, device='cuda:0')
episode: 377 training return: tensor(745.0156, device='cuda:0')
episode: 378 training return: tensor(724.8813, device='cuda:0')
episode: 379 training return: tensor(762.8376, device='cuda:0')
epoch: 95 test_true_pfm: 51.003705464484796 sim_pfm: 784.1213072892045
episode: 380 training return: tensor(708.6121, device='cuda:0')
episode: 381 training return: tensor(779.5575, device='cuda:0')
episode: 382 training return: tensor(757.8491, device='cuda:0')
episode: 383 training return: tensor(703.7468, device='cuda:0')
epoch: 96 test_true_pfm: 43.89002868259128 sim_pfm: 758.3922932426678
episode: 384 training return: tensor(738.9083, device='cuda:0')
episode: 385 training return: tensor(725.8915, device='cuda:0')
episode: 386 training return: tensor(730.0360, device='cuda:0')
episode: 387 training return: tensor(738.6867, device='cuda:0')
epoch: 97 test_true_pfm: 41.21560734625365 sim_pfm: 633.7955821941607
episode: 388 training return: tensor(697.3098, device='cuda:0')
episode: 389 training return: tensor(746.3279, device='cuda:0')
episode: 390 training return: tensor(739.1209, device='cuda:0')
episode: 391 training return: tensor(736.3807, device='cuda:0')
epoch: 98 test_true_pfm: 44.316810045985406 sim_pfm: 797.1088491730392
episode: 392 training return: tensor(746.9138, device='cuda:0')
episode: 393 training return: tensor(742.1910, device='cuda:0')
episode: 394 training return: tensor(756.8652, device='cuda:0')
episode: 395 training return: tensor(706.4501, device='cuda:0')
epoch: 99 test_true_pfm: 40.30663744002086 sim_pfm: 761.5593707957305
episode: 396 training return: tensor(764.4454, device='cuda:0')
episode: 397 training return: tensor(751.1815, device='cuda:0')
episode: 398 training return: tensor(787.8180, device='cuda:0')
episode: 399 training return: tensor(738.5229, device='cuda:0')
epoch: 100 test_true_pfm: 43.730934151498865 sim_pfm: 743.9898570149205
episode: 400 training return: tensor(731.4318, device='cuda:0')
episode: 401 training return: tensor(762.4111, device='cuda:0')
episode: 402 training return: tensor(753.0477, device='cuda:0')
episode: 403 training return: tensor(749.7644, device='cuda:0')
epoch: 101 test_true_pfm: 35.5930177954805 sim_pfm: -86.79307245101081
episode: 404 training return: tensor(-130.5836, device='cuda:0')
episode: 405 training return: tensor(-75.7176, device='cuda:0')
episode: 406 training return: tensor(-67.9506, device='cuda:0')
episode: 407 training return: tensor(-45.1679, device='cuda:0')
epoch: 102 test_true_pfm: 36.95825605181853 sim_pfm: -65.471292159101
episode: 408 training return: tensor(36.2404, device='cuda:0')
episode: 409 training return: tensor(-121.3306, device='cuda:0')
episode: 410 training return: tensor(-90.9100, device='cuda:0')
episode: 411 training return: tensor(-122.4319, device='cuda:0')
epoch: 103 test_true_pfm: 34.21013242089842 sim_pfm: 176.0268352846033
episode: 412 training return: tensor(-94.8148, device='cuda:0')
episode: 413 training return: tensor(98.7575, device='cuda:0')
episode: 414 training return: tensor(751.4563, device='cuda:0')
episode: 415 training return: tensor(733.5295, device='cuda:0')
epoch: 104 test_true_pfm: 51.777588108505974 sim_pfm: 745.8661052430282
episode: 416 training return: tensor(743.9691, device='cuda:0')
episode: 417 training return: tensor(725.8934, device='cuda:0')
episode: 418 training return: tensor(754.7264, device='cuda:0')
episode: 419 training return: tensor(730.1296, device='cuda:0')
epoch: 105 test_true_pfm: 50.9147490191272 sim_pfm: 751.0869961876422
episode: 420 training return: tensor(730.7882, device='cuda:0')
episode: 421 training return: tensor(754.9214, device='cuda:0')
episode: 422 training return: tensor(739.2872, device='cuda:0')
episode: 423 training return: tensor(751.5433, device='cuda:0')
epoch: 106 test_true_pfm: 45.811072026418586 sim_pfm: 751.4584532301408
episode: 424 training return: tensor(733.4592, device='cuda:0')
episode: 425 training return: tensor(762.9407, device='cuda:0')
episode: 426 training return: tensor(763.2335, device='cuda:0')
episode: 427 training return: tensor(773.1977, device='cuda:0')
epoch: 107 test_true_pfm: 55.00593633677043 sim_pfm: 781.0941247409094
episode: 428 training return: tensor(766.8591, device='cuda:0')
episode: 429 training return: tensor(767.1343, device='cuda:0')
episode: 430 training return: tensor(752.3185, device='cuda:0')
episode: 431 training return: tensor(765.8782, device='cuda:0')
epoch: 108 test_true_pfm: 55.708575920268274 sim_pfm: 781.0576536965789
episode: 432 training return: tensor(766.6182, device='cuda:0')
episode: 433 training return: tensor(770.5599, device='cuda:0')
episode: 434 training return: tensor(769.4069, device='cuda:0')
episode: 435 training return: tensor(751.5735, device='cuda:0')
epoch: 109 test_true_pfm: 49.712472785667515 sim_pfm: 773.3031338591594
episode: 436 training return: tensor(738.0294, device='cuda:0')
episode: 437 training return: tensor(726.8325, device='cuda:0')
episode: 438 training return: tensor(770.9905, device='cuda:0')
episode: 439 training return: tensor(770.0901, device='cuda:0')
epoch: 110 test_true_pfm: 52.45665933884389 sim_pfm: 761.5545334143098
episode: 440 training return: tensor(735.5710, device='cuda:0')
episode: 441 training return: tensor(744.8745, device='cuda:0')
episode: 442 training return: tensor(755.3542, device='cuda:0')
episode: 443 training return: tensor(736.3438, device='cuda:0')
epoch: 111 test_true_pfm: 51.0110888929929 sim_pfm: 788.2919587735087
episode: 444 training return: tensor(772.3981, device='cuda:0')
episode: 445 training return: tensor(755.0784, device='cuda:0')
episode: 446 training return: tensor(744.8286, device='cuda:0')
episode: 447 training return: tensor(714.2272, device='cuda:0')
epoch: 112 test_true_pfm: 25.327964309925274 sim_pfm: 743.6935072927736
episode: 448 training return: tensor(720.3912, device='cuda:0')
episode: 449 training return: tensor(717.6360, device='cuda:0')
episode: 450 training return: tensor(-190.0117, device='cuda:0')
episode: 451 training return: tensor(740.9351, device='cuda:0')
epoch: 113 test_true_pfm: 36.11439351977694 sim_pfm: -86.83287660667557
episode: 452 training return: tensor(-115.9082, device='cuda:0')
episode: 453 training return: tensor(-93.1430, device='cuda:0')
episode: 454 training return: tensor(-98.9577, device='cuda:0')
episode: 455 training return: tensor(726.8371, device='cuda:0')
epoch: 114 test_true_pfm: 45.56089323441419 sim_pfm: 772.8279829843435
episode: 456 training return: tensor(687.9884, device='cuda:0')
episode: 457 training return: tensor(730.6081, device='cuda:0')
episode: 458 training return: tensor(649.2271, device='cuda:0')
episode: 459 training return: tensor(706.0710, device='cuda:0')
epoch: 115 test_true_pfm: 46.44263461824584 sim_pfm: 754.4423019688577
episode: 460 training return: tensor(706.1178, device='cuda:0')
episode: 461 training return: tensor(717.7767, device='cuda:0')
episode: 462 training return: tensor(730.6422, device='cuda:0')
episode: 463 training return: tensor(751.1843, device='cuda:0')
epoch: 116 test_true_pfm: 47.96053310278294 sim_pfm: 789.2726796256378
episode: 464 training return: tensor(757.5023, device='cuda:0')
episode: 465 training return: tensor(703.7731, device='cuda:0')
episode: 466 training return: tensor(707.6775, device='cuda:0')
episode: 467 training return: tensor(729.7344, device='cuda:0')
epoch: 117 test_true_pfm: 28.835795349334195 sim_pfm: 710.9804097136832
episode: 468 training return: tensor(721.0377, device='cuda:0')
episode: 469 training return: tensor(670.2524, device='cuda:0')
episode: 470 training return: tensor(744.3165, device='cuda:0')
episode: 471 training return: tensor(741.1957, device='cuda:0')
epoch: 118 test_true_pfm: 41.16068115362161 sim_pfm: 750.691166083049
episode: 472 training return: tensor(717.3696, device='cuda:0')
episode: 473 training return: tensor(714.4355, device='cuda:0')
episode: 474 training return: tensor(699.6018, device='cuda:0')
episode: 475 training return: tensor(692.5340, device='cuda:0')
epoch: 119 test_true_pfm: 48.9808882832516 sim_pfm: 757.2425633023493
episode: 476 training return: tensor(742.4926, device='cuda:0')
episode: 477 training return: tensor(740.6122, device='cuda:0')
episode: 478 training return: tensor(746.8076, device='cuda:0')
episode: 479 training return: tensor(763.1329, device='cuda:0')
epoch: 120 test_true_pfm: 40.73745499991875 sim_pfm: 775.7417592842132
episode: 480 training return: tensor(735.0679, device='cuda:0')
episode: 481 training return: tensor(770.6853, device='cuda:0')
episode: 482 training return: tensor(744.1226, device='cuda:0')
episode: 483 training return: tensor(763.8421, device='cuda:0')
epoch: 121 test_true_pfm: 48.72403434961476 sim_pfm: 781.1986014951719
episode: 484 training return: tensor(759.5025, device='cuda:0')
episode: 485 training return: tensor(768.9486, device='cuda:0')
episode: 486 training return: tensor(782.1472, device='cuda:0')
episode: 487 training return: tensor(749.3840, device='cuda:0')
epoch: 122 test_true_pfm: 47.37927028872359 sim_pfm: 781.5208217123524
episode: 488 training return: tensor(712.5260, device='cuda:0')
episode: 489 training return: tensor(694.9806, device='cuda:0')
episode: 490 training return: tensor(768.0862, device='cuda:0')
episode: 491 training return: tensor(699.0904, device='cuda:0')
epoch: 123 test_true_pfm: 37.9132407689435 sim_pfm: 719.3321681380272
episode: 492 training return: tensor(669.8242, device='cuda:0')
episode: 493 training return: tensor(756.0477, device='cuda:0')
episode: 494 training return: tensor(753.7552, device='cuda:0')
episode: 495 training return: tensor(753.6531, device='cuda:0')
epoch: 124 test_true_pfm: 46.91332882670939 sim_pfm: 754.5524945912882
episode: 496 training return: tensor(747.3445, device='cuda:0')
episode: 497 training return: tensor(768.0499, device='cuda:0')
episode: 498 training return: tensor(732.5707, device='cuda:0')
episode: 499 training return: tensor(725.6125, device='cuda:0')
epoch: 125 test_true_pfm: 40.880295156468016 sim_pfm: 767.4106304448098
episode: 500 training return: tensor(754.1771, device='cuda:0')
episode: 501 training return: tensor(747.5417, device='cuda:0')
episode: 502 training return: tensor(754.5372, device='cuda:0')
episode: 503 training return: tensor(768.4665, device='cuda:0')
epoch: 126 test_true_pfm: 51.510621433992334 sim_pfm: 763.2437364662067
episode: 504 training return: tensor(754.5089, device='cuda:0')
episode: 505 training return: tensor(757.8082, device='cuda:0')
episode: 506 training return: tensor(741.1350, device='cuda:0')
episode: 507 training return: tensor(755.8121, device='cuda:0')
epoch: 127 test_true_pfm: 53.27395161780693 sim_pfm: 784.7095149254194
episode: 508 training return: tensor(788.5394, device='cuda:0')
episode: 509 training return: tensor(730.2421, device='cuda:0')
episode: 510 training return: tensor(742.8378, device='cuda:0')
episode: 511 training return: tensor(700.2284, device='cuda:0')
epoch: 128 test_true_pfm: 46.07947830926484 sim_pfm: 769.8001491602511
episode: 512 training return: tensor(732.9693, device='cuda:0')
episode: 513 training return: tensor(773.2873, device='cuda:0')
episode: 514 training return: tensor(762.7903, device='cuda:0')
episode: 515 training return: tensor(748.9989, device='cuda:0')
epoch: 129 test_true_pfm: 47.832431294769336 sim_pfm: 782.5580998688936
episode: 516 training return: tensor(783.3122, device='cuda:0')
episode: 517 training return: tensor(757.2390, device='cuda:0')
episode: 518 training return: tensor(773.1965, device='cuda:0')
episode: 519 training return: tensor(758.2375, device='cuda:0')
epoch: 130 test_true_pfm: 46.56079897184652 sim_pfm: 766.3544348232448
episode: 520 training return: tensor(738.3325, device='cuda:0')
episode: 521 training return: tensor(767.8672, device='cuda:0')
episode: 522 training return: tensor(769.9341, device='cuda:0')
episode: 523 training return: tensor(781.3184, device='cuda:0')
epoch: 131 test_true_pfm: 48.461919491678096 sim_pfm: 782.8838182888052
episode: 524 training return: tensor(755.9808, device='cuda:0')
episode: 525 training return: tensor(765.5158, device='cuda:0')
episode: 526 training return: tensor(721.5797, device='cuda:0')
episode: 527 training return: tensor(743.8535, device='cuda:0')
epoch: 132 test_true_pfm: 50.6551369927495 sim_pfm: 775.40147144316
episode: 528 training return: tensor(758.9753, device='cuda:0')
episode: 529 training return: tensor(784.1179, device='cuda:0')
episode: 530 training return: tensor(756.6568, device='cuda:0')
episode: 531 training return: tensor(761.3884, device='cuda:0')
epoch: 133 test_true_pfm: 53.31701493502227 sim_pfm: 791.0719020338729
episode: 532 training return: tensor(758.4672, device='cuda:0')
episode: 533 training return: tensor(729.0698, device='cuda:0')
episode: 534 training return: tensor(753.3754, device='cuda:0')
episode: 535 training return: tensor(716.8723, device='cuda:0')
epoch: 134 test_true_pfm: 40.73113067421177 sim_pfm: 773.6114824008197
episode: 536 training return: tensor(774.9822, device='cuda:0')
episode: 537 training return: tensor(765.3300, device='cuda:0')
episode: 538 training return: tensor(780.4927, device='cuda:0')
episode: 539 training return: tensor(756.2147, device='cuda:0')
epoch: 135 test_true_pfm: 42.81747575246867 sim_pfm: 739.3150157666765
episode: 540 training return: tensor(740.4721, device='cuda:0')
episode: 541 training return: tensor(755.4000, device='cuda:0')
episode: 542 training return: tensor(753.0892, device='cuda:0')
episode: 543 training return: tensor(775.1938, device='cuda:0')
epoch: 136 test_true_pfm: 50.01444490917358 sim_pfm: 789.0208964135963
episode: 544 training return: tensor(792.8955, device='cuda:0')
episode: 545 training return: tensor(760.1052, device='cuda:0')
episode: 546 training return: tensor(681.2480, device='cuda:0')
episode: 547 training return: tensor(759.9889, device='cuda:0')
epoch: 137 test_true_pfm: 44.426505716676196 sim_pfm: 780.6991357844788
episode: 548 training return: tensor(695.6544, device='cuda:0')
episode: 549 training return: tensor(741.1762, device='cuda:0')
episode: 550 training return: tensor(790.8889, device='cuda:0')
episode: 551 training return: tensor(727.6306, device='cuda:0')
epoch: 138 test_true_pfm: 41.92678633977791 sim_pfm: 725.4451637169404
episode: 552 training return: tensor(759.3698, device='cuda:0')
episode: 553 training return: tensor(759.4596, device='cuda:0')
episode: 554 training return: tensor(775.5073, device='cuda:0')
episode: 555 training return: tensor(746.6578, device='cuda:0')
epoch: 139 test_true_pfm: 48.22485629318483 sim_pfm: 762.4251757434453
episode: 556 training return: tensor(741.8400, device='cuda:0')
episode: 557 training return: tensor(728.1089, device='cuda:0')
episode: 558 training return: tensor(763.1971, device='cuda:0')
episode: 559 training return: tensor(724.0044, device='cuda:0')
epoch: 140 test_true_pfm: 43.78499737172994 sim_pfm: 744.6382447250187
episode: 560 training return: tensor(724.2346, device='cuda:0')
episode: 561 training return: tensor(708.0417, device='cuda:0')
episode: 562 training return: tensor(782.4907, device='cuda:0')
episode: 563 training return: tensor(772.7388, device='cuda:0')
epoch: 141 test_true_pfm: 45.07252256363577 sim_pfm: 770.8803047813475
episode: 564 training return: tensor(759.6835, device='cuda:0')
episode: 565 training return: tensor(771.4552, device='cuda:0')
episode: 566 training return: tensor(751.5799, device='cuda:0')
episode: 567 training return: tensor(729.6089, device='cuda:0')
epoch: 142 test_true_pfm: 45.82971977494321 sim_pfm: 776.5091867887647
episode: 568 training return: tensor(766.3724, device='cuda:0')
episode: 569 training return: tensor(771.3881, device='cuda:0')
episode: 570 training return: tensor(783.5948, device='cuda:0')
episode: 571 training return: tensor(763.7729, device='cuda:0')
epoch: 143 test_true_pfm: 46.09359706210013 sim_pfm: 792.0960688204971
episode: 572 training return: tensor(756.8251, device='cuda:0')
episode: 573 training return: tensor(754.2238, device='cuda:0')
episode: 574 training return: tensor(725.9536, device='cuda:0')
episode: 575 training return: tensor(725.6089, device='cuda:0')
epoch: 144 test_true_pfm: 32.74449844697906 sim_pfm: 745.4798597354442
episode: 576 training return: tensor(715.7148, device='cuda:0')
episode: 577 training return: tensor(734.1626, device='cuda:0')
episode: 578 training return: tensor(709.5635, device='cuda:0')
episode: 579 training return: tensor(744.9157, device='cuda:0')
epoch: 145 test_true_pfm: 45.62225538284082 sim_pfm: 754.0775517127477
episode: 580 training return: tensor(750.3029, device='cuda:0')
episode: 581 training return: tensor(760.6180, device='cuda:0')
episode: 582 training return: tensor(733.8126, device='cuda:0')
episode: 583 training return: tensor(753.3762, device='cuda:0')
epoch: 146 test_true_pfm: 48.799575457355175 sim_pfm: 745.0883093228098
episode: 584 training return: tensor(691.2352, device='cuda:0')
episode: 585 training return: tensor(737.7781, device='cuda:0')
episode: 586 training return: tensor(710.9284, device='cuda:0')
episode: 587 training return: tensor(619.5253, device='cuda:0')
epoch: 147 test_true_pfm: 35.90343485261205 sim_pfm: 525.1115086321254
episode: 588 training return: tensor(493.7776, device='cuda:0')
episode: 589 training return: tensor(539.8373, device='cuda:0')
episode: 590 training return: tensor(746.3383, device='cuda:0')
episode: 591 training return: tensor(736.9594, device='cuda:0')
epoch: 148 test_true_pfm: 42.58824067088692 sim_pfm: 772.522463324666
episode: 592 training return: tensor(758.8491, device='cuda:0')
episode: 593 training return: tensor(762.5101, device='cuda:0')
episode: 594 training return: tensor(771.7776, device='cuda:0')
episode: 595 training return: tensor(756.3743, device='cuda:0')
epoch: 149 test_true_pfm: 52.307366061825725 sim_pfm: 780.8378047801555
episode: 596 training return: tensor(758.0170, device='cuda:0')
episode: 597 training return: tensor(759.5522, device='cuda:0')
episode: 598 training return: tensor(759.2775, device='cuda:0')
episode: 599 training return: tensor(746.2089, device='cuda:0')
epoch: 150 test_true_pfm: 53.24658122347912 sim_pfm: 778.3317989632487
