['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'behavior', '--traj', 'medium', '--seed', '0', '--data', '100000', '--regu', '0.3']
5114.200022414097
episode: 0 training return: tensor(-191.2684, device='cuda:0')
episode: 1 training return: tensor(-201.3561, device='cuda:0')
episode: 2 training return: tensor(-244.6361, device='cuda:0')
episode: 3 training return: tensor(-250.0406, device='cuda:0')
epoch: 1 test_true_pfm: 3765.377231244085 sim_pfm: -543.2708166148708
episode: 4 training return: tensor(-236.1043, device='cuda:0')
episode: 5 training return: tensor(-170.0561, device='cuda:0')
episode: 6 training return: tensor(-339.6006, device='cuda:0')
episode: 7 training return: tensor(-191.1577, device='cuda:0')
epoch: 2 test_true_pfm: 4479.462116696188 sim_pfm: -336.79048441492097
episode: 8 training return: tensor(-298.3239, device='cuda:0')
episode: 9 training return: tensor(-175.1705, device='cuda:0')
episode: 10 training return: tensor(-245.6127, device='cuda:0')
episode: 11 training return: tensor(-160.1263, device='cuda:0')
epoch: 3 test_true_pfm: 4898.18313636244 sim_pfm: -117.17405101895565
episode: 12 training return: tensor(-139.9793, device='cuda:0')
episode: 13 training return: tensor(-262.9104, device='cuda:0')
episode: 14 training return: tensor(-343.1119, device='cuda:0')
episode: 15 training return: tensor(-217.7642, device='cuda:0')
epoch: 4 test_true_pfm: 4930.916983361407 sim_pfm: -61.10568541564862
episode: 16 training return: tensor(-126.5839, device='cuda:0')
episode: 17 training return: tensor(-264.1907, device='cuda:0')
episode: 18 training return: tensor(-191.3029, device='cuda:0')
episode: 19 training return: tensor(-143.6830, device='cuda:0')
epoch: 5 test_true_pfm: 4989.621371832161 sim_pfm: -12.345107257802738
episode: 20 training return: tensor(-219.9875, device='cuda:0')
episode: 21 training return: tensor(-65.0554, device='cuda:0')
episode: 22 training return: tensor(-116.0810, device='cuda:0')
episode: 23 training return: tensor(-70.8347, device='cuda:0')
epoch: 6 test_true_pfm: 5056.274361234286 sim_pfm: 125.88957406847233
episode: 24 training return: tensor(-54.3011, device='cuda:0')
episode: 25 training return: tensor(-110.9575, device='cuda:0')
episode: 26 training return: tensor(-43.2075, device='cuda:0')
episode: 27 training return: tensor(-113.9651, device='cuda:0')
epoch: 7 test_true_pfm: 5151.655353528785 sim_pfm: 110.74126742989756
episode: 28 training return: tensor(81.9541, device='cuda:0')
episode: 29 training return: tensor(-210.6374, device='cuda:0')
episode: 30 training return: tensor(-107.8168, device='cuda:0')
episode: 31 training return: tensor(-37.8698, device='cuda:0')
epoch: 8 test_true_pfm: 5165.185323896613 sim_pfm: 149.2068887350033
episode: 32 training return: tensor(-101.2232, device='cuda:0')
episode: 33 training return: tensor(-95.8101, device='cuda:0')
episode: 34 training return: tensor(22.4074, device='cuda:0')
episode: 35 training return: tensor(-33.7597, device='cuda:0')
epoch: 9 test_true_pfm: 5183.383332940232 sim_pfm: 210.07372874677336
episode: 36 training return: tensor(134.9949, device='cuda:0')
episode: 37 training return: tensor(100.6863, device='cuda:0')
episode: 38 training return: tensor(-134.3944, device='cuda:0')
episode: 39 training return: tensor(-36.8343, device='cuda:0')
epoch: 10 test_true_pfm: 5313.460789859392 sim_pfm: 39.90753275520789
episode: 40 training return: tensor(97.1244, device='cuda:0')
episode: 41 training return: tensor(5.1614, device='cuda:0')
episode: 42 training return: tensor(25.9506, device='cuda:0')
episode: 43 training return: tensor(9.9009, device='cuda:0')
epoch: 11 test_true_pfm: 5357.41151664235 sim_pfm: 300.59085765480995
episode: 44 training return: tensor(91.6092, device='cuda:0')
episode: 45 training return: tensor(94.6703, device='cuda:0')
episode: 46 training return: tensor(67.0570, device='cuda:0')
episode: 47 training return: tensor(169.3406, device='cuda:0')
epoch: 12 test_true_pfm: 5435.902653883834 sim_pfm: 233.99199429154396
episode: 48 training return: tensor(146.4494, device='cuda:0')
episode: 49 training return: tensor(30.1162, device='cuda:0')
episode: 50 training return: tensor(121.9013, device='cuda:0')
episode: 51 training return: tensor(55.3312, device='cuda:0')
epoch: 13 test_true_pfm: 5462.48743724794 sim_pfm: 374.1838712573711
episode: 52 training return: tensor(222.3619, device='cuda:0')
episode: 53 training return: tensor(191.6481, device='cuda:0')
episode: 54 training return: tensor(84.5356, device='cuda:0')
episode: 55 training return: tensor(-20.7903, device='cuda:0')
epoch: 14 test_true_pfm: 4490.267641894668 sim_pfm: 89.57743626085964
episode: 56 training return: tensor(48.6406, device='cuda:0')
episode: 57 training return: tensor(287.0845, device='cuda:0')
episode: 58 training return: tensor(186.2321, device='cuda:0')
episode: 59 training return: tensor(236.8851, device='cuda:0')
epoch: 15 test_true_pfm: 5546.969079050811 sim_pfm: 328.7106515248888
episode: 60 training return: tensor(144.5686, device='cuda:0')
episode: 61 training return: tensor(198.1717, device='cuda:0')
episode: 62 training return: tensor(105.9067, device='cuda:0')
episode: 63 training return: tensor(166.2328, device='cuda:0')
epoch: 16 test_true_pfm: 5548.742431759725 sim_pfm: 386.4908124333985
episode: 64 training return: tensor(137.6431, device='cuda:0')
episode: 65 training return: tensor(238.6424, device='cuda:0')
episode: 66 training return: tensor(190.7870, device='cuda:0')
episode: 67 training return: tensor(177.4491, device='cuda:0')
epoch: 17 test_true_pfm: 5662.80397993925 sim_pfm: 356.6956687466979
episode: 68 training return: tensor(134.0695, device='cuda:0')
episode: 69 training return: tensor(32.8803, device='cuda:0')
episode: 70 training return: tensor(304.7026, device='cuda:0')
episode: 71 training return: tensor(257.2310, device='cuda:0')
epoch: 18 test_true_pfm: 5631.218568656008 sim_pfm: 450.2626444392663
episode: 72 training return: tensor(214.4188, device='cuda:0')
episode: 73 training return: tensor(268.4029, device='cuda:0')
episode: 74 training return: tensor(237.7761, device='cuda:0')
episode: 75 training return: tensor(258.4081, device='cuda:0')
epoch: 19 test_true_pfm: 5725.546522591648 sim_pfm: 493.06814268041245
episode: 76 training return: tensor(169.7116, device='cuda:0')
episode: 77 training return: tensor(273.5263, device='cuda:0')
episode: 78 training return: tensor(251.2392, device='cuda:0')
episode: 79 training return: tensor(278.9654, device='cuda:0')
epoch: 20 test_true_pfm: 5601.759112230952 sim_pfm: 496.6688939963545
episode: 80 training return: tensor(192.2121, device='cuda:0')
episode: 81 training return: tensor(246.5101, device='cuda:0')
episode: 82 training return: tensor(237.3576, device='cuda:0')
episode: 83 training return: tensor(330.8598, device='cuda:0')
epoch: 21 test_true_pfm: 5750.20835646451 sim_pfm: 529.2028697033724
episode: 84 training return: tensor(275.8499, device='cuda:0')
episode: 85 training return: tensor(329.9682, device='cuda:0')
episode: 86 training return: tensor(288.9636, device='cuda:0')
episode: 87 training return: tensor(-79.5194, device='cuda:0')
epoch: 22 test_true_pfm: 5729.344813860188 sim_pfm: 525.522961845311
episode: 88 training return: tensor(313.5530, device='cuda:0')
episode: 89 training return: tensor(410.2146, device='cuda:0')
episode: 90 training return: tensor(369.2204, device='cuda:0')
episode: 91 training return: tensor(323.8264, device='cuda:0')
epoch: 23 test_true_pfm: 5811.412606118342 sim_pfm: 560.7236107668141
episode: 92 training return: tensor(255.9245, device='cuda:0')
episode: 93 training return: tensor(373.4626, device='cuda:0')
episode: 94 training return: tensor(381.7287, device='cuda:0')
episode: 95 training return: tensor(385.6411, device='cuda:0')
epoch: 24 test_true_pfm: 5693.463479703044 sim_pfm: 534.9516824064194
episode: 96 training return: tensor(342.1916, device='cuda:0')
episode: 97 training return: tensor(293.5777, device='cuda:0')
episode: 98 training return: tensor(314.9415, device='cuda:0')
episode: 99 training return: tensor(341.9837, device='cuda:0')
epoch: 25 test_true_pfm: 5825.717300923989 sim_pfm: 615.0182786171403
episode: 100 training return: tensor(344.0005, device='cuda:0')
episode: 101 training return: tensor(451.4620, device='cuda:0')
episode: 102 training return: tensor(336.8100, device='cuda:0')
episode: 103 training return: tensor(420.2520, device='cuda:0')
epoch: 26 test_true_pfm: 5844.08268622615 sim_pfm: 569.757203366491
episode: 104 training return: tensor(365.1798, device='cuda:0')
episode: 105 training return: tensor(350.0249, device='cuda:0')
episode: 106 training return: tensor(415.8091, device='cuda:0')
episode: 107 training return: tensor(260.2031, device='cuda:0')
epoch: 27 test_true_pfm: 5909.605331220665 sim_pfm: 591.5882314008583
episode: 108 training return: tensor(531.1277, device='cuda:0')
episode: 109 training return: tensor(363.6030, device='cuda:0')
episode: 110 training return: tensor(276.8222, device='cuda:0')
episode: 111 training return: tensor(412.6705, device='cuda:0')
epoch: 28 test_true_pfm: 5854.8333669118665 sim_pfm: 552.3466216993887
episode: 112 training return: tensor(356.1526, device='cuda:0')
episode: 113 training return: tensor(392.4508, device='cuda:0')
episode: 114 training return: tensor(415.0287, device='cuda:0')
episode: 115 training return: tensor(414.7604, device='cuda:0')
epoch: 29 test_true_pfm: 5963.465345867298 sim_pfm: 601.7879979877034
episode: 116 training return: tensor(403.9572, device='cuda:0')
episode: 117 training return: tensor(471.7657, device='cuda:0')
episode: 118 training return: tensor(376.3192, device='cuda:0')
episode: 119 training return: tensor(474.9709, device='cuda:0')
epoch: 30 test_true_pfm: 6001.449966415774 sim_pfm: 657.5105904182516
episode: 120 training return: tensor(468.2023, device='cuda:0')
episode: 121 training return: tensor(392.6919, device='cuda:0')
episode: 122 training return: tensor(498.9133, device='cuda:0')
episode: 123 training return: tensor(502.9597, device='cuda:0')
epoch: 31 test_true_pfm: 5872.936244713241 sim_pfm: 591.8133560139686
episode: 124 training return: tensor(483.2440, device='cuda:0')
episode: 125 training return: tensor(419.3184, device='cuda:0')
episode: 126 training return: tensor(437.9053, device='cuda:0')
episode: 127 training return: tensor(422.7202, device='cuda:0')
epoch: 32 test_true_pfm: 5924.027596130596 sim_pfm: 620.9758817778978
episode: 128 training return: tensor(481.1543, device='cuda:0')
episode: 129 training return: tensor(424.8503, device='cuda:0')
episode: 130 training return: tensor(445.0883, device='cuda:0')
episode: 131 training return: tensor(473.0372, device='cuda:0')
epoch: 33 test_true_pfm: 5990.070744479679 sim_pfm: 654.0384139319261
episode: 132 training return: tensor(446.3255, device='cuda:0')
episode: 133 training return: tensor(408.0112, device='cuda:0')
episode: 134 training return: tensor(487.2798, device='cuda:0')
episode: 135 training return: tensor(507.5876, device='cuda:0')
epoch: 34 test_true_pfm: 5961.59514309945 sim_pfm: 611.6649354487114
episode: 136 training return: tensor(404.0939, device='cuda:0')
episode: 137 training return: tensor(471.9603, device='cuda:0')
episode: 138 training return: tensor(530.9892, device='cuda:0')
episode: 139 training return: tensor(450.4283, device='cuda:0')
epoch: 35 test_true_pfm: 5961.74211064362 sim_pfm: 668.642010627004
episode: 140 training return: tensor(509.1759, device='cuda:0')
episode: 141 training return: tensor(517.8683, device='cuda:0')
episode: 142 training return: tensor(437.2220, device='cuda:0')
episode: 143 training return: tensor(475.0302, device='cuda:0')
epoch: 36 test_true_pfm: 5995.979036827325 sim_pfm: 702.8087290446274
episode: 144 training return: tensor(393.0175, device='cuda:0')
episode: 145 training return: tensor(551.9285, device='cuda:0')
episode: 146 training return: tensor(490.8481, device='cuda:0')
episode: 147 training return: tensor(565.9583, device='cuda:0')
epoch: 37 test_true_pfm: 6047.693315243076 sim_pfm: 655.899498809032
episode: 148 training return: tensor(538.8088, device='cuda:0')
episode: 149 training return: tensor(519.9979, device='cuda:0')
episode: 150 training return: tensor(466.6018, device='cuda:0')
episode: 151 training return: tensor(483.2910, device='cuda:0')
epoch: 38 test_true_pfm: 5992.669450565201 sim_pfm: 646.3313172433409
episode: 152 training return: tensor(456.1400, device='cuda:0')
episode: 153 training return: tensor(473.1509, device='cuda:0')
episode: 154 training return: tensor(434.9666, device='cuda:0')
episode: 155 training return: tensor(511.8974, device='cuda:0')
epoch: 39 test_true_pfm: 5970.981902745715 sim_pfm: 654.102748314462
episode: 156 training return: tensor(470.9651, device='cuda:0')
episode: 157 training return: tensor(473.6556, device='cuda:0')
episode: 158 training return: tensor(505.5125, device='cuda:0')
episode: 159 training return: tensor(533.2194, device='cuda:0')
epoch: 40 test_true_pfm: 5886.5753449146405 sim_pfm: 654.2748494723346
episode: 160 training return: tensor(491.1267, device='cuda:0')
episode: 161 training return: tensor(501.7794, device='cuda:0')
episode: 162 training return: tensor(532.0232, device='cuda:0')
episode: 163 training return: tensor(498.7044, device='cuda:0')
epoch: 41 test_true_pfm: 6105.863797618239 sim_pfm: 638.7604618734719
episode: 164 training return: tensor(519.5101, device='cuda:0')
episode: 165 training return: tensor(491.1246, device='cuda:0')
episode: 166 training return: tensor(534.1362, device='cuda:0')
episode: 167 training return: tensor(474.4269, device='cuda:0')
epoch: 42 test_true_pfm: 6083.168491118872 sim_pfm: 706.9429722066076
episode: 168 training return: tensor(570.1819, device='cuda:0')
episode: 169 training return: tensor(466.7239, device='cuda:0')
episode: 170 training return: tensor(588.6899, device='cuda:0')
episode: 171 training return: tensor(563.5072, device='cuda:0')
epoch: 43 test_true_pfm: 6021.62984975265 sim_pfm: 709.0683847363398
episode: 172 training return: tensor(472.3270, device='cuda:0')
episode: 173 training return: tensor(559.4139, device='cuda:0')
episode: 174 training return: tensor(547.4215, device='cuda:0')
episode: 175 training return: tensor(479.3582, device='cuda:0')
epoch: 44 test_true_pfm: 6037.033159198351 sim_pfm: 675.2885033502631
episode: 176 training return: tensor(576.3172, device='cuda:0')
episode: 177 training return: tensor(487.1314, device='cuda:0')
episode: 178 training return: tensor(535.3253, device='cuda:0')
episode: 179 training return: tensor(459.1018, device='cuda:0')
epoch: 45 test_true_pfm: 6053.713744827673 sim_pfm: 712.765574119015
episode: 180 training return: tensor(435.1436, device='cuda:0')
episode: 181 training return: tensor(502.2234, device='cuda:0')
episode: 182 training return: tensor(550.0995, device='cuda:0')
episode: 183 training return: tensor(548.0335, device='cuda:0')
epoch: 46 test_true_pfm: 6118.080160510832 sim_pfm: 708.1203280929476
episode: 184 training return: tensor(549.0845, device='cuda:0')
episode: 185 training return: tensor(481.4258, device='cuda:0')
episode: 186 training return: tensor(475.2665, device='cuda:0')
episode: 187 training return: tensor(469.9378, device='cuda:0')
epoch: 47 test_true_pfm: 5994.800606973336 sim_pfm: 687.2507309221741
episode: 188 training return: tensor(522.1142, device='cuda:0')
episode: 189 training return: tensor(468.5486, device='cuda:0')
episode: 190 training return: tensor(432.3344, device='cuda:0')
episode: 191 training return: tensor(404.7234, device='cuda:0')
epoch: 48 test_true_pfm: 6114.6659015868 sim_pfm: 687.4927460769735
episode: 192 training return: tensor(485.6178, device='cuda:0')
episode: 193 training return: tensor(472.8618, device='cuda:0')
episode: 194 training return: tensor(406.8417, device='cuda:0')
episode: 195 training return: tensor(481.1735, device='cuda:0')
epoch: 49 test_true_pfm: 6076.799999808415 sim_pfm: 690.523278886074
episode: 196 training return: tensor(571.6562, device='cuda:0')
episode: 197 training return: tensor(572.2872, device='cuda:0')
episode: 198 training return: tensor(545.1883, device='cuda:0')
episode: 199 training return: tensor(487.7068, device='cuda:0')
epoch: 50 test_true_pfm: 6094.175130804461 sim_pfm: 706.8549233569453
episode: 200 training return: tensor(588.9238, device='cuda:0')
episode: 201 training return: tensor(530.1432, device='cuda:0')
episode: 202 training return: tensor(543.0106, device='cuda:0')
episode: 203 training return: tensor(577.4536, device='cuda:0')
epoch: 51 test_true_pfm: 6046.367880154863 sim_pfm: 669.8454848083007
episode: 204 training return: tensor(558.6444, device='cuda:0')
episode: 205 training return: tensor(490.7619, device='cuda:0')
episode: 206 training return: tensor(525.6307, device='cuda:0')
episode: 207 training return: tensor(619.6738, device='cuda:0')
epoch: 52 test_true_pfm: 5978.443512150488 sim_pfm: 665.5635759685343
episode: 208 training return: tensor(572.4700, device='cuda:0')
episode: 209 training return: tensor(542.5834, device='cuda:0')
episode: 210 training return: tensor(500.6497, device='cuda:0')
episode: 211 training return: tensor(484.0972, device='cuda:0')
epoch: 53 test_true_pfm: 6033.758324841616 sim_pfm: 708.1308695769403
episode: 212 training return: tensor(579.8062, device='cuda:0')
episode: 213 training return: tensor(546.6764, device='cuda:0')
episode: 214 training return: tensor(528.6781, device='cuda:0')
episode: 215 training return: tensor(595.1922, device='cuda:0')
epoch: 54 test_true_pfm: 6065.241183133847 sim_pfm: 691.2187354258882
episode: 216 training return: tensor(537.4431, device='cuda:0')
episode: 217 training return: tensor(543.9299, device='cuda:0')
episode: 218 training return: tensor(512.5914, device='cuda:0')
episode: 219 training return: tensor(577.7241, device='cuda:0')
epoch: 55 test_true_pfm: 6079.566178641926 sim_pfm: 734.0716566421615
episode: 220 training return: tensor(553.7479, device='cuda:0')
episode: 221 training return: tensor(540.0492, device='cuda:0')
episode: 222 training return: tensor(540.9391, device='cuda:0')
episode: 223 training return: tensor(581.3400, device='cuda:0')
epoch: 56 test_true_pfm: 6107.265510087355 sim_pfm: 689.9062824625677
episode: 224 training return: tensor(610.3898, device='cuda:0')
episode: 225 training return: tensor(594.0573, device='cuda:0')
episode: 226 training return: tensor(499.1647, device='cuda:0')
episode: 227 training return: tensor(565.0591, device='cuda:0')
epoch: 57 test_true_pfm: 6057.75432516358 sim_pfm: 719.2346029262408
episode: 228 training return: tensor(625.1934, device='cuda:0')
episode: 229 training return: tensor(520.2653, device='cuda:0')
episode: 230 training return: tensor(518.5317, device='cuda:0')
episode: 231 training return: tensor(625.4509, device='cuda:0')
epoch: 58 test_true_pfm: 6154.177854661734 sim_pfm: 686.3151195575095
episode: 232 training return: tensor(554.6819, device='cuda:0')
episode: 233 training return: tensor(575.2084, device='cuda:0')
episode: 234 training return: tensor(587.0546, device='cuda:0')
episode: 235 training return: tensor(491.8381, device='cuda:0')
epoch: 59 test_true_pfm: 6096.602741437731 sim_pfm: 702.9780538159345
episode: 236 training return: tensor(594.1644, device='cuda:0')
episode: 237 training return: tensor(639.4420, device='cuda:0')
episode: 238 training return: tensor(523.0505, device='cuda:0')
episode: 239 training return: tensor(560.6414, device='cuda:0')
epoch: 60 test_true_pfm: 6094.678197077842 sim_pfm: 716.0192998310085
episode: 240 training return: tensor(609.5331, device='cuda:0')
episode: 241 training return: tensor(538.1932, device='cuda:0')
episode: 242 training return: tensor(542.0689, device='cuda:0')
episode: 243 training return: tensor(465.2584, device='cuda:0')
epoch: 61 test_true_pfm: 6108.176199923735 sim_pfm: 700.5966815814996
episode: 244 training return: tensor(514.2914, device='cuda:0')
episode: 245 training return: tensor(589.9655, device='cuda:0')
episode: 246 training return: tensor(542.1619, device='cuda:0')
episode: 247 training return: tensor(539.2289, device='cuda:0')
epoch: 62 test_true_pfm: 6118.000722054225 sim_pfm: 725.2145449252179
episode: 248 training return: tensor(576.5439, device='cuda:0')
episode: 249 training return: tensor(636.8493, device='cuda:0')
episode: 250 training return: tensor(503.3615, device='cuda:0')
episode: 251 training return: tensor(529.9380, device='cuda:0')
epoch: 63 test_true_pfm: 6077.893798800632 sim_pfm: 684.9085535433454
episode: 252 training return: tensor(528.6864, device='cuda:0')
episode: 253 training return: tensor(501.2237, device='cuda:0')
episode: 254 training return: tensor(525.5636, device='cuda:0')
episode: 255 training return: tensor(585.2352, device='cuda:0')
epoch: 64 test_true_pfm: 6093.9401849606 sim_pfm: 746.6093148672177
episode: 256 training return: tensor(585.4797, device='cuda:0')
episode: 257 training return: tensor(571.2763, device='cuda:0')
episode: 258 training return: tensor(594.9908, device='cuda:0')
episode: 259 training return: tensor(640.3160, device='cuda:0')
epoch: 65 test_true_pfm: 6043.810084794903 sim_pfm: 712.1914039926293
episode: 260 training return: tensor(583.1898, device='cuda:0')
episode: 261 training return: tensor(611.8576, device='cuda:0')
episode: 262 training return: tensor(528.5582, device='cuda:0')
episode: 263 training return: tensor(641.5803, device='cuda:0')
epoch: 66 test_true_pfm: 6138.200098388693 sim_pfm: 705.3775673504764
episode: 264 training return: tensor(580.9018, device='cuda:0')
episode: 265 training return: tensor(562.4639, device='cuda:0')
episode: 266 training return: tensor(509.8387, device='cuda:0')
episode: 267 training return: tensor(546.3342, device='cuda:0')
epoch: 67 test_true_pfm: 6171.806695952546 sim_pfm: 721.3929082443938
episode: 268 training return: tensor(541., device='cuda:0')
episode: 269 training return: tensor(574.8434, device='cuda:0')
episode: 270 training return: tensor(564.2238, device='cuda:0')
episode: 271 training return: tensor(596.5728, device='cuda:0')
epoch: 68 test_true_pfm: 6134.276170494978 sim_pfm: 721.767283563735
episode: 272 training return: tensor(613.9285, device='cuda:0')
episode: 273 training return: tensor(565.5089, device='cuda:0')
episode: 274 training return: tensor(591.7909, device='cuda:0')
episode: 275 training return: tensor(601.5057, device='cuda:0')
epoch: 69 test_true_pfm: 6192.886672345064 sim_pfm: 716.443335901325
episode: 276 training return: tensor(628.5399, device='cuda:0')
episode: 277 training return: tensor(591.2090, device='cuda:0')
episode: 278 training return: tensor(562.3770, device='cuda:0')
episode: 279 training return: tensor(505.8685, device='cuda:0')
epoch: 70 test_true_pfm: 6157.4704634724685 sim_pfm: 741.9429445543016
episode: 280 training return: tensor(578.0505, device='cuda:0')
episode: 281 training return: tensor(538.4856, device='cuda:0')
episode: 282 training return: tensor(600.5859, device='cuda:0')
episode: 283 training return: tensor(546.4743, device='cuda:0')
epoch: 71 test_true_pfm: 6110.912443943981 sim_pfm: 719.2642159294337
episode: 284 training return: tensor(586.1522, device='cuda:0')
episode: 285 training return: tensor(505.5792, device='cuda:0')
episode: 286 training return: tensor(636.0551, device='cuda:0')
episode: 287 training return: tensor(584.1241, device='cuda:0')
epoch: 72 test_true_pfm: 6219.16379968668 sim_pfm: 734.6802131914689
episode: 288 training return: tensor(577.3281, device='cuda:0')
episode: 289 training return: tensor(630.1267, device='cuda:0')
episode: 290 training return: tensor(546.2640, device='cuda:0')
episode: 291 training return: tensor(558.3891, device='cuda:0')
epoch: 73 test_true_pfm: 6205.32240650006 sim_pfm: 766.2495631907756
episode: 292 training return: tensor(585.4252, device='cuda:0')
episode: 293 training return: tensor(496.2884, device='cuda:0')
episode: 294 training return: tensor(609.6428, device='cuda:0')
episode: 295 training return: tensor(533.3497, device='cuda:0')
epoch: 74 test_true_pfm: 6158.720478158335 sim_pfm: 742.3819757462479
episode: 296 training return: tensor(563.2056, device='cuda:0')
episode: 297 training return: tensor(594.6670, device='cuda:0')
episode: 298 training return: tensor(655.2177, device='cuda:0')
episode: 299 training return: tensor(625.5653, device='cuda:0')
epoch: 75 test_true_pfm: 6191.885066682834 sim_pfm: 728.4617437990382
episode: 300 training return: tensor(580.8083, device='cuda:0')
episode: 301 training return: tensor(527.0267, device='cuda:0')
episode: 302 training return: tensor(612.4089, device='cuda:0')
episode: 303 training return: tensor(608.5692, device='cuda:0')
epoch: 76 test_true_pfm: 6169.966794456591 sim_pfm: 744.979529794616
episode: 304 training return: tensor(576.0491, device='cuda:0')
episode: 305 training return: tensor(628.0795, device='cuda:0')
episode: 306 training return: tensor(543.2891, device='cuda:0')
episode: 307 training return: tensor(587.2357, device='cuda:0')
epoch: 77 test_true_pfm: 6099.83440796233 sim_pfm: 687.8862022592026
episode: 308 training return: tensor(592.4878, device='cuda:0')
episode: 309 training return: tensor(548.6440, device='cuda:0')
episode: 310 training return: tensor(605.6931, device='cuda:0')
episode: 311 training return: tensor(614.7431, device='cuda:0')
epoch: 78 test_true_pfm: 6178.131701914089 sim_pfm: 739.2289859115845
episode: 312 training return: tensor(636.5846, device='cuda:0')
episode: 313 training return: tensor(667.8818, device='cuda:0')
episode: 314 training return: tensor(627.0402, device='cuda:0')
episode: 315 training return: tensor(585.4646, device='cuda:0')
epoch: 79 test_true_pfm: 6136.076010577407 sim_pfm: 740.700992159041
episode: 316 training return: tensor(562.0790, device='cuda:0')
episode: 317 training return: tensor(522.6569, device='cuda:0')
episode: 318 training return: tensor(613.5119, device='cuda:0')
episode: 319 training return: tensor(579.8293, device='cuda:0')
epoch: 80 test_true_pfm: 6188.0336967127 sim_pfm: 742.7710504385954
episode: 320 training return: tensor(584.8183, device='cuda:0')
episode: 321 training return: tensor(590.4636, device='cuda:0')
episode: 322 training return: tensor(570.1755, device='cuda:0')
episode: 323 training return: tensor(583.5958, device='cuda:0')
epoch: 81 test_true_pfm: 6193.3790073695745 sim_pfm: 726.5084227992533
episode: 324 training return: tensor(514.7465, device='cuda:0')
episode: 325 training return: tensor(597.7099, device='cuda:0')
episode: 326 training return: tensor(603.8289, device='cuda:0')
episode: 327 training return: tensor(600.0389, device='cuda:0')
epoch: 82 test_true_pfm: 6242.301651025227 sim_pfm: 742.6954854945652
episode: 328 training return: tensor(587.6772, device='cuda:0')
episode: 329 training return: tensor(551.0189, device='cuda:0')
episode: 330 training return: tensor(594.7485, device='cuda:0')
episode: 331 training return: tensor(596.1936, device='cuda:0')
epoch: 83 test_true_pfm: 6217.481440401968 sim_pfm: 733.1319661076801
episode: 332 training return: tensor(513.5232, device='cuda:0')
episode: 333 training return: tensor(573.3719, device='cuda:0')
episode: 334 training return: tensor(617.3879, device='cuda:0')
episode: 335 training return: tensor(585.8756, device='cuda:0')
epoch: 84 test_true_pfm: 6163.26623904526 sim_pfm: 757.1053905114532
episode: 336 training return: tensor(660.8155, device='cuda:0')
episode: 337 training return: tensor(584.7527, device='cuda:0')
episode: 338 training return: tensor(535.9661, device='cuda:0')
episode: 339 training return: tensor(587.6910, device='cuda:0')
epoch: 85 test_true_pfm: 6235.980874622044 sim_pfm: 766.9786498421648
episode: 340 training return: tensor(559.1969, device='cuda:0')
episode: 341 training return: tensor(556.7990, device='cuda:0')
episode: 342 training return: tensor(658.7617, device='cuda:0')
episode: 343 training return: tensor(537.1544, device='cuda:0')
epoch: 86 test_true_pfm: 6189.900288368593 sim_pfm: 749.7913787659878
episode: 344 training return: tensor(621.5867, device='cuda:0')
episode: 345 training return: tensor(598.1624, device='cuda:0')
episode: 346 training return: tensor(608.0862, device='cuda:0')
episode: 347 training return: tensor(633.6941, device='cuda:0')
epoch: 87 test_true_pfm: 6102.577467787061 sim_pfm: 731.0282483650759
episode: 348 training return: tensor(631.1356, device='cuda:0')
episode: 349 training return: tensor(593.1126, device='cuda:0')
episode: 350 training return: tensor(635.6237, device='cuda:0')
episode: 351 training return: tensor(601.3502, device='cuda:0')
epoch: 88 test_true_pfm: 6171.17970294848 sim_pfm: 752.6259761022715
episode: 352 training return: tensor(605.9148, device='cuda:0')
episode: 353 training return: tensor(616.6249, device='cuda:0')
episode: 354 training return: tensor(673.1406, device='cuda:0')
episode: 355 training return: tensor(616.0096, device='cuda:0')
epoch: 89 test_true_pfm: 6117.54894467083 sim_pfm: 732.9542061230168
episode: 356 training return: tensor(663.4361, device='cuda:0')
episode: 357 training return: tensor(564.7567, device='cuda:0')
episode: 358 training return: tensor(637.5352, device='cuda:0')
episode: 359 training return: tensor(655.8132, device='cuda:0')
epoch: 90 test_true_pfm: 6253.207937788217 sim_pfm: 760.8134999916268
episode: 360 training return: tensor(596.5347, device='cuda:0')
episode: 361 training return: tensor(606.4382, device='cuda:0')
episode: 362 training return: tensor(660.0754, device='cuda:0')
episode: 363 training return: tensor(649.7625, device='cuda:0')
epoch: 91 test_true_pfm: 6233.4840886765605 sim_pfm: 771.5261084175823
episode: 364 training return: tensor(644.4947, device='cuda:0')
episode: 365 training return: tensor(644.8516, device='cuda:0')
episode: 366 training return: tensor(618.8673, device='cuda:0')
episode: 367 training return: tensor(564.1931, device='cuda:0')
epoch: 92 test_true_pfm: 6151.929372763786 sim_pfm: 744.353215296811
episode: 368 training return: tensor(623.5859, device='cuda:0')
episode: 369 training return: tensor(575.9405, device='cuda:0')
episode: 370 training return: tensor(634.9018, device='cuda:0')
episode: 371 training return: tensor(673.1751, device='cuda:0')
epoch: 93 test_true_pfm: 6194.1319807014215 sim_pfm: 746.8171982067482
episode: 372 training return: tensor(584.4626, device='cuda:0')
episode: 373 training return: tensor(567.0779, device='cuda:0')
episode: 374 training return: tensor(608.0940, device='cuda:0')
episode: 375 training return: tensor(657.0738, device='cuda:0')
epoch: 94 test_true_pfm: 6150.255441163678 sim_pfm: 730.1507434852732
episode: 376 training return: tensor(664.6280, device='cuda:0')
episode: 377 training return: tensor(629.7012, device='cuda:0')
episode: 378 training return: tensor(674.7886, device='cuda:0')
episode: 379 training return: tensor(654.7249, device='cuda:0')
epoch: 95 test_true_pfm: 6168.476461602608 sim_pfm: 770.6319181943933
episode: 380 training return: tensor(537.4670, device='cuda:0')
episode: 381 training return: tensor(611.0175, device='cuda:0')
episode: 382 training return: tensor(645.5034, device='cuda:0')
episode: 383 training return: tensor(653.3037, device='cuda:0')
epoch: 96 test_true_pfm: 6168.927254462018 sim_pfm: 741.8081071598766
episode: 384 training return: tensor(538.6608, device='cuda:0')
episode: 385 training return: tensor(559.4155, device='cuda:0')
episode: 386 training return: tensor(613.0329, device='cuda:0')
episode: 387 training return: tensor(589.2114, device='cuda:0')
epoch: 97 test_true_pfm: 6188.214964402501 sim_pfm: 751.7670611209857
episode: 388 training return: tensor(648.4517, device='cuda:0')
episode: 389 training return: tensor(591.2466, device='cuda:0')
episode: 390 training return: tensor(635.8193, device='cuda:0')
episode: 391 training return: tensor(566.5430, device='cuda:0')
epoch: 98 test_true_pfm: 6159.720201142832 sim_pfm: 762.0108849112876
episode: 392 training return: tensor(620.1700, device='cuda:0')
episode: 393 training return: tensor(531.2915, device='cuda:0')
episode: 394 training return: tensor(591.4193, device='cuda:0')
episode: 395 training return: tensor(599.6121, device='cuda:0')
epoch: 99 test_true_pfm: 6170.142831805974 sim_pfm: 751.4401420287322
episode: 396 training return: tensor(588.9724, device='cuda:0')
episode: 397 training return: tensor(500.0828, device='cuda:0')
episode: 398 training return: tensor(652.4763, device='cuda:0')
episode: 399 training return: tensor(639.8057, device='cuda:0')
epoch: 100 test_true_pfm: 6105.421667782607 sim_pfm: 731.3840926200306
episode: 400 training return: tensor(632.2793, device='cuda:0')
episode: 401 training return: tensor(623.9448, device='cuda:0')
episode: 402 training return: tensor(621.8856, device='cuda:0')
episode: 403 training return: tensor(620.6228, device='cuda:0')
epoch: 101 test_true_pfm: 6205.61395464971 sim_pfm: 762.5293290910777
episode: 404 training return: tensor(602.8507, device='cuda:0')
episode: 405 training return: tensor(611.3926, device='cuda:0')
episode: 406 training return: tensor(628.1136, device='cuda:0')
episode: 407 training return: tensor(602.0977, device='cuda:0')
epoch: 102 test_true_pfm: 6288.22426962294 sim_pfm: 536.4892552101519
episode: 408 training return: tensor(615.8560, device='cuda:0')
episode: 409 training return: tensor(655.9889, device='cuda:0')
episode: 410 training return: tensor(615.8140, device='cuda:0')
episode: 411 training return: tensor(645.6002, device='cuda:0')
epoch: 103 test_true_pfm: 6137.968441225166 sim_pfm: 765.0045731645854
episode: 412 training return: tensor(597.1038, device='cuda:0')
episode: 413 training return: tensor(649.5947, device='cuda:0')
episode: 414 training return: tensor(574.6907, device='cuda:0')
episode: 415 training return: tensor(591.4233, device='cuda:0')
epoch: 104 test_true_pfm: 6214.283737848803 sim_pfm: 734.6624179468394
episode: 416 training return: tensor(629.7670, device='cuda:0')
episode: 417 training return: tensor(622.9607, device='cuda:0')
episode: 418 training return: tensor(657.2983, device='cuda:0')
episode: 419 training return: tensor(596.3897, device='cuda:0')
epoch: 105 test_true_pfm: 6254.914018019045 sim_pfm: 755.4405511297518
episode: 420 training return: tensor(586.7543, device='cuda:0')
episode: 421 training return: tensor(661.8054, device='cuda:0')
episode: 422 training return: tensor(663.4909, device='cuda:0')
episode: 423 training return: tensor(672.7853, device='cuda:0')
epoch: 106 test_true_pfm: 6195.61284610569 sim_pfm: 755.2176849291815
episode: 424 training return: tensor(676.3141, device='cuda:0')
episode: 425 training return: tensor(635.2349, device='cuda:0')
episode: 426 training return: tensor(672.9309, device='cuda:0')
episode: 427 training return: tensor(617.0268, device='cuda:0')
epoch: 107 test_true_pfm: 6224.658071338335 sim_pfm: 764.1329978608215
episode: 428 training return: tensor(628.8401, device='cuda:0')
episode: 429 training return: tensor(613.6771, device='cuda:0')
episode: 430 training return: tensor(598.9338, device='cuda:0')
episode: 431 training return: tensor(621.9551, device='cuda:0')
epoch: 108 test_true_pfm: 6100.894559856267 sim_pfm: 725.3478501811624
episode: 432 training return: tensor(639.5637, device='cuda:0')
episode: 433 training return: tensor(633.7374, device='cuda:0')
episode: 434 training return: tensor(611.6985, device='cuda:0')
episode: 435 training return: tensor(626.2763, device='cuda:0')
epoch: 109 test_true_pfm: 6226.953995256833 sim_pfm: 748.0165091934032
episode: 436 training return: tensor(599.9779, device='cuda:0')
episode: 437 training return: tensor(620.6965, device='cuda:0')
episode: 438 training return: tensor(600.4171, device='cuda:0')
episode: 439 training return: tensor(608.7122, device='cuda:0')
epoch: 110 test_true_pfm: 6168.544162032139 sim_pfm: 745.7894637507076
episode: 440 training return: tensor(608.7279, device='cuda:0')
episode: 441 training return: tensor(549.8602, device='cuda:0')
episode: 442 training return: tensor(678.8126, device='cuda:0')
episode: 443 training return: tensor(655.9263, device='cuda:0')
epoch: 111 test_true_pfm: 6217.294015180701 sim_pfm: 748.1580072209472
episode: 444 training return: tensor(639.9735, device='cuda:0')
episode: 445 training return: tensor(598.6885, device='cuda:0')
episode: 446 training return: tensor(546.1838, device='cuda:0')
episode: 447 training return: tensor(606.8779, device='cuda:0')
epoch: 112 test_true_pfm: 6196.563596634816 sim_pfm: 752.6470130366894
episode: 448 training return: tensor(623.1296, device='cuda:0')
episode: 449 training return: tensor(588.6793, device='cuda:0')
episode: 450 training return: tensor(598.3060, device='cuda:0')
episode: 451 training return: tensor(659.7578, device='cuda:0')
epoch: 113 test_true_pfm: 6238.072856431153 sim_pfm: 750.0988784710256
episode: 452 training return: tensor(641.5251, device='cuda:0')
episode: 453 training return: tensor(598.0986, device='cuda:0')
episode: 454 training return: tensor(657.7648, device='cuda:0')
episode: 455 training return: tensor(613.4605, device='cuda:0')
epoch: 114 test_true_pfm: 6237.5124143642715 sim_pfm: 762.576139335831
episode: 456 training return: tensor(668.1263, device='cuda:0')
episode: 457 training return: tensor(589.4396, device='cuda:0')
episode: 458 training return: tensor(647.9236, device='cuda:0')
episode: 459 training return: tensor(653.6605, device='cuda:0')
epoch: 115 test_true_pfm: 6234.607563792118 sim_pfm: 760.1721013986195
episode: 460 training return: tensor(640.1996, device='cuda:0')
episode: 461 training return: tensor(680.2891, device='cuda:0')
episode: 462 training return: tensor(582.3093, device='cuda:0')
episode: 463 training return: tensor(647.8066, device='cuda:0')
epoch: 116 test_true_pfm: 6220.144182314073 sim_pfm: 763.2049440127643
episode: 464 training return: tensor(671.7625, device='cuda:0')
episode: 465 training return: tensor(614.9970, device='cuda:0')
episode: 466 training return: tensor(637.4321, device='cuda:0')
episode: 467 training return: tensor(677.0569, device='cuda:0')
epoch: 117 test_true_pfm: 6206.968036352234 sim_pfm: 759.9096588593287
episode: 468 training return: tensor(621.9910, device='cuda:0')
episode: 469 training return: tensor(646.4793, device='cuda:0')
episode: 470 training return: tensor(657.9741, device='cuda:0')
episode: 471 training return: tensor(652.0557, device='cuda:0')
epoch: 118 test_true_pfm: 6192.408509542866 sim_pfm: 753.319992329935
episode: 472 training return: tensor(662.9678, device='cuda:0')
episode: 473 training return: tensor(655.9721, device='cuda:0')
episode: 474 training return: tensor(654.0214, device='cuda:0')
episode: 475 training return: tensor(643.4001, device='cuda:0')
epoch: 119 test_true_pfm: 6274.512140461094 sim_pfm: 771.3177073654564
episode: 476 training return: tensor(633.7393, device='cuda:0')
episode: 477 training return: tensor(673.3422, device='cuda:0')
episode: 478 training return: tensor(613.4753, device='cuda:0')
episode: 479 training return: tensor(594.8637, device='cuda:0')
epoch: 120 test_true_pfm: 6249.845707085049 sim_pfm: 778.789521873463
episode: 480 training return: tensor(631.0515, device='cuda:0')
episode: 481 training return: tensor(578.9271, device='cuda:0')
episode: 482 training return: tensor(669.0562, device='cuda:0')
episode: 483 training return: tensor(563.0863, device='cuda:0')
epoch: 121 test_true_pfm: 6217.473540554944 sim_pfm: 754.9675417230465
episode: 484 training return: tensor(616.4588, device='cuda:0')
episode: 485 training return: tensor(683.9844, device='cuda:0')
episode: 486 training return: tensor(677.6772, device='cuda:0')
episode: 487 training return: tensor(655.3942, device='cuda:0')
epoch: 122 test_true_pfm: 6261.536176736401 sim_pfm: 768.075088853327
episode: 488 training return: tensor(595.1218, device='cuda:0')
episode: 489 training return: tensor(614.7042, device='cuda:0')
episode: 490 training return: tensor(665.0311, device='cuda:0')
episode: 491 training return: tensor(635.7509, device='cuda:0')
epoch: 123 test_true_pfm: 6225.568199291626 sim_pfm: 771.7199545445231
episode: 492 training return: tensor(668.9239, device='cuda:0')
episode: 493 training return: tensor(669.3945, device='cuda:0')
episode: 494 training return: tensor(642.0480, device='cuda:0')
episode: 495 training return: tensor(685.8668, device='cuda:0')
epoch: 124 test_true_pfm: 6301.164147129602 sim_pfm: 755.8535978494523
episode: 496 training return: tensor(610.7429, device='cuda:0')
episode: 497 training return: tensor(610.8356, device='cuda:0')
episode: 498 training return: tensor(625.6087, device='cuda:0')
episode: 499 training return: tensor(644.4888, device='cuda:0')
epoch: 125 test_true_pfm: 6251.321640859934 sim_pfm: 763.397445961833
episode: 500 training return: tensor(616.9072, device='cuda:0')
episode: 501 training return: tensor(632.9340, device='cuda:0')
episode: 502 training return: tensor(612.2731, device='cuda:0')
episode: 503 training return: tensor(670.7529, device='cuda:0')
epoch: 126 test_true_pfm: 6304.8934807745245 sim_pfm: 759.0187476977395
episode: 504 training return: tensor(612.4207, device='cuda:0')
episode: 505 training return: tensor(557.6105, device='cuda:0')
episode: 506 training return: tensor(606.9343, device='cuda:0')
episode: 507 training return: tensor(649.5840, device='cuda:0')
epoch: 127 test_true_pfm: 6225.321454052903 sim_pfm: 773.2110907832781
episode: 508 training return: tensor(652.1227, device='cuda:0')
episode: 509 training return: tensor(630.2783, device='cuda:0')
episode: 510 training return: tensor(659.3759, device='cuda:0')
episode: 511 training return: tensor(682.7375, device='cuda:0')
epoch: 128 test_true_pfm: 6221.993001902534 sim_pfm: 767.1859884605414
episode: 512 training return: tensor(642.3019, device='cuda:0')
episode: 513 training return: tensor(606.5576, device='cuda:0')
episode: 514 training return: tensor(658.3851, device='cuda:0')
episode: 515 training return: tensor(608.6033, device='cuda:0')
epoch: 129 test_true_pfm: 6287.669365542383 sim_pfm: 780.887313564308
episode: 516 training return: tensor(657.5233, device='cuda:0')
episode: 517 training return: tensor(593.1522, device='cuda:0')
episode: 518 training return: tensor(586.1733, device='cuda:0')
episode: 519 training return: tensor(614.1627, device='cuda:0')
epoch: 130 test_true_pfm: 6273.160207192667 sim_pfm: 776.2225459888577
episode: 520 training return: tensor(607.4159, device='cuda:0')
episode: 521 training return: tensor(664.8862, device='cuda:0')
episode: 522 training return: tensor(647.7797, device='cuda:0')
episode: 523 training return: tensor(625.2322, device='cuda:0')
epoch: 131 test_true_pfm: 6274.167756319726 sim_pfm: 755.1270544907699
episode: 524 training return: tensor(643.0275, device='cuda:0')
episode: 525 training return: tensor(638.6892, device='cuda:0')
episode: 526 training return: tensor(680.6791, device='cuda:0')
episode: 527 training return: tensor(628.6810, device='cuda:0')
epoch: 132 test_true_pfm: 6285.499578730244 sim_pfm: 773.7351960695038
episode: 528 training return: tensor(630.7707, device='cuda:0')
episode: 529 training return: tensor(612.8877, device='cuda:0')
episode: 530 training return: tensor(618.1620, device='cuda:0')
episode: 531 training return: tensor(556.1639, device='cuda:0')
epoch: 133 test_true_pfm: 6289.881703185784 sim_pfm: 773.6085991975851
episode: 532 training return: tensor(682.3140, device='cuda:0')
episode: 533 training return: tensor(637.7643, device='cuda:0')
episode: 534 training return: tensor(648.6704, device='cuda:0')
episode: 535 training return: tensor(630.2651, device='cuda:0')
epoch: 134 test_true_pfm: 6273.255158623339 sim_pfm: 769.6083568558097
episode: 536 training return: tensor(630.1555, device='cuda:0')
episode: 537 training return: tensor(579.8267, device='cuda:0')
episode: 538 training return: tensor(637.5661, device='cuda:0')
episode: 539 training return: tensor(643.6795, device='cuda:0')
epoch: 135 test_true_pfm: 6282.915619591604 sim_pfm: 759.4600374697087
episode: 540 training return: tensor(645.8964, device='cuda:0')
episode: 541 training return: tensor(584.8855, device='cuda:0')
episode: 542 training return: tensor(627.9753, device='cuda:0')
episode: 543 training return: tensor(642.6528, device='cuda:0')
epoch: 136 test_true_pfm: 6269.324995036045 sim_pfm: 789.5271702227183
episode: 544 training return: tensor(597.4865, device='cuda:0')
episode: 545 training return: tensor(678.1544, device='cuda:0')
episode: 546 training return: tensor(543.4238, device='cuda:0')
episode: 547 training return: tensor(612.2150, device='cuda:0')
epoch: 137 test_true_pfm: 6199.128082633396 sim_pfm: 756.3118365571523
episode: 548 training return: tensor(661.5101, device='cuda:0')
episode: 549 training return: tensor(667.4839, device='cuda:0')
episode: 550 training return: tensor(667.8520, device='cuda:0')
episode: 551 training return: tensor(654.5026, device='cuda:0')
epoch: 138 test_true_pfm: 6197.061441329407 sim_pfm: 779.5671380391965
episode: 552 training return: tensor(686.1911, device='cuda:0')
episode: 553 training return: tensor(669.6417, device='cuda:0')
episode: 554 training return: tensor(655.1867, device='cuda:0')
episode: 555 training return: tensor(645.6155, device='cuda:0')
epoch: 139 test_true_pfm: 6256.305526879371 sim_pfm: 784.0084259922927
episode: 556 training return: tensor(617.1883, device='cuda:0')
episode: 557 training return: tensor(623.0036, device='cuda:0')
episode: 558 training return: tensor(664.6561, device='cuda:0')
episode: 559 training return: tensor(601.0355, device='cuda:0')
epoch: 140 test_true_pfm: 6267.439120462183 sim_pfm: 756.291300554915
episode: 560 training return: tensor(694.0509, device='cuda:0')
episode: 561 training return: tensor(606.4136, device='cuda:0')
episode: 562 training return: tensor(675.2188, device='cuda:0')
episode: 563 training return: tensor(686.4071, device='cuda:0')
epoch: 141 test_true_pfm: 6352.444683267732 sim_pfm: 790.8400557147494
episode: 564 training return: tensor(615.9863, device='cuda:0')
episode: 565 training return: tensor(673.5831, device='cuda:0')
episode: 566 training return: tensor(592.3427, device='cuda:0')
episode: 567 training return: tensor(626.2798, device='cuda:0')
epoch: 142 test_true_pfm: 6125.124507531644 sim_pfm: 718.5665957788005
episode: 568 training return: tensor(673.7542, device='cuda:0')
episode: 569 training return: tensor(631.0178, device='cuda:0')
episode: 570 training return: tensor(658.1024, device='cuda:0')
episode: 571 training return: tensor(656.1252, device='cuda:0')
epoch: 143 test_true_pfm: 6319.941930736616 sim_pfm: 763.8101715132749
episode: 572 training return: tensor(679.2819, device='cuda:0')
episode: 573 training return: tensor(648.3091, device='cuda:0')
episode: 574 training return: tensor(721.9214, device='cuda:0')
episode: 575 training return: tensor(672.0133, device='cuda:0')
epoch: 144 test_true_pfm: 6238.265170480252 sim_pfm: 763.1503877388701
episode: 576 training return: tensor(643.1642, device='cuda:0')
episode: 577 training return: tensor(673.8491, device='cuda:0')
episode: 578 training return: tensor(679.8171, device='cuda:0')
episode: 579 training return: tensor(578.9005, device='cuda:0')
epoch: 145 test_true_pfm: 6324.660730489919 sim_pfm: 788.0364790388849
episode: 580 training return: tensor(666.0622, device='cuda:0')
episode: 581 training return: tensor(568.1490, device='cuda:0')
episode: 582 training return: tensor(695.9975, device='cuda:0')
episode: 583 training return: tensor(626.7627, device='cuda:0')
epoch: 146 test_true_pfm: 6257.5064352541785 sim_pfm: 792.8634175661331
episode: 584 training return: tensor(641.8121, device='cuda:0')
episode: 585 training return: tensor(665.6944, device='cuda:0')
episode: 586 training return: tensor(629.1169, device='cuda:0')
episode: 587 training return: tensor(659.7554, device='cuda:0')
epoch: 147 test_true_pfm: 6281.130176174212 sim_pfm: 764.4171019257628
episode: 588 training return: tensor(616.6196, device='cuda:0')
episode: 589 training return: tensor(643.6141, device='cuda:0')
episode: 590 training return: tensor(682.6608, device='cuda:0')
episode: 591 training return: tensor(571.2435, device='cuda:0')
epoch: 148 test_true_pfm: 6318.8044966812595 sim_pfm: 785.0531100557806
episode: 592 training return: tensor(660.6245, device='cuda:0')
episode: 593 training return: tensor(665.6921, device='cuda:0')
episode: 594 training return: tensor(648.1674, device='cuda:0')
episode: 595 training return: tensor(627.4980, device='cuda:0')
epoch: 149 test_true_pfm: 6273.933547545713 sim_pfm: 774.6867349526534
episode: 596 training return: tensor(635.0788, device='cuda:0')
episode: 597 training return: tensor(646.7469, device='cuda:0')
episode: 598 training return: tensor(672.5184, device='cuda:0')
episode: 599 training return: tensor(674.1390, device='cuda:0')
epoch: 150 test_true_pfm: 6387.081869864461 sim_pfm: 792.4736929520537
