['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'behavior', '--traj', 'medium', '--seed', '1', '--data', '100000', '--regu', '0.3']
5096.169552640438
episode: 0 training return: tensor(-189.3767, device='cuda:0')
episode: 1 training return: tensor(-393.3957, device='cuda:0')
episode: 2 training return: tensor(-273.5012, device='cuda:0')
episode: 3 training return: tensor(-217.2173, device='cuda:0')
epoch: 1 test_true_pfm: 4898.59740665862 sim_pfm: -25.27428129274631
episode: 4 training return: tensor(-285.8525, device='cuda:0')
episode: 5 training return: tensor(-398.8512, device='cuda:0')
episode: 6 training return: tensor(-350.1517, device='cuda:0')
episode: 7 training return: tensor(-233.0419, device='cuda:0')
epoch: 2 test_true_pfm: 3912.761775725083 sim_pfm: -392.8343602132324
episode: 8 training return: tensor(-234.7576, device='cuda:0')
episode: 9 training return: tensor(-346.1467, device='cuda:0')
episode: 10 training return: tensor(-226.9333, device='cuda:0')
episode: 11 training return: tensor(-106.4292, device='cuda:0')
epoch: 3 test_true_pfm: 4896.7527702428815 sim_pfm: -80.04394321818836
episode: 12 training return: tensor(-218.0206, device='cuda:0')
episode: 13 training return: tensor(-202.8552, device='cuda:0')
episode: 14 training return: tensor(-294.4322, device='cuda:0')
episode: 15 training return: tensor(-221.3794, device='cuda:0')
epoch: 4 test_true_pfm: 4260.688128727549 sim_pfm: -70.05846891509525
episode: 16 training return: tensor(-127.4009, device='cuda:0')
episode: 17 training return: tensor(-28.4525, device='cuda:0')
episode: 18 training return: tensor(-152.0461, device='cuda:0')
episode: 19 training return: tensor(-175.0759, device='cuda:0')
epoch: 5 test_true_pfm: 4970.360053723553 sim_pfm: 19.489151171330985
episode: 20 training return: tensor(-528.4236, device='cuda:0')
episode: 21 training return: tensor(-109.3723, device='cuda:0')
episode: 22 training return: tensor(-254.9736, device='cuda:0')
episode: 23 training return: tensor(-70.2935, device='cuda:0')
epoch: 6 test_true_pfm: 5160.602032943406 sim_pfm: 133.37603147572372
episode: 24 training return: tensor(-109.5479, device='cuda:0')
episode: 25 training return: tensor(-60.0616, device='cuda:0')
episode: 26 training return: tensor(-178.3598, device='cuda:0')
episode: 27 training return: tensor(-140.4576, device='cuda:0')
epoch: 7 test_true_pfm: 5294.432953154469 sim_pfm: 77.05250965148055
episode: 28 training return: tensor(-8.2126, device='cuda:0')
episode: 29 training return: tensor(-79.5287, device='cuda:0')
episode: 30 training return: tensor(-218.5000, device='cuda:0')
episode: 31 training return: tensor(4.0051, device='cuda:0')
epoch: 8 test_true_pfm: 5385.353125844832 sim_pfm: 255.58762676608362
episode: 32 training return: tensor(-116.4613, device='cuda:0')
episode: 33 training return: tensor(112.7274, device='cuda:0')
episode: 34 training return: tensor(-16.6740, device='cuda:0')
episode: 35 training return: tensor(-139.7732, device='cuda:0')
epoch: 9 test_true_pfm: 5301.691237720347 sim_pfm: 131.97979065952435
episode: 36 training return: tensor(-6.6535, device='cuda:0')
episode: 37 training return: tensor(4.3694, device='cuda:0')
episode: 38 training return: tensor(40.2470, device='cuda:0')
episode: 39 training return: tensor(65.5108, device='cuda:0')
epoch: 10 test_true_pfm: 5201.15399196464 sim_pfm: 213.69019662455926
episode: 40 training return: tensor(9.8416, device='cuda:0')
episode: 41 training return: tensor(-52.2536, device='cuda:0')
episode: 42 training return: tensor(-62.6488, device='cuda:0')
episode: 43 training return: tensor(-4.0163, device='cuda:0')
epoch: 11 test_true_pfm: 5447.846384042913 sim_pfm: -88.5365058502454
episode: 44 training return: tensor(49.3881, device='cuda:0')
episode: 45 training return: tensor(-85.2473, device='cuda:0')
episode: 46 training return: tensor(59.5545, device='cuda:0')
episode: 47 training return: tensor(97.0306, device='cuda:0')
epoch: 12 test_true_pfm: 5360.258759534314 sim_pfm: 295.5702505986167
episode: 48 training return: tensor(84.1135, device='cuda:0')
episode: 49 training return: tensor(65.8006, device='cuda:0')
episode: 50 training return: tensor(44.8334, device='cuda:0')
episode: 51 training return: tensor(26.5389, device='cuda:0')
epoch: 13 test_true_pfm: 5379.6587032813795 sim_pfm: 270.7336027651327
episode: 52 training return: tensor(145.5246, device='cuda:0')
episode: 53 training return: tensor(160.9573, device='cuda:0')
episode: 54 training return: tensor(-39.8158, device='cuda:0')
episode: 55 training return: tensor(34.1043, device='cuda:0')
epoch: 14 test_true_pfm: 5367.9218594981 sim_pfm: 266.37646341882646
episode: 56 training return: tensor(161.1055, device='cuda:0')
episode: 57 training return: tensor(-59.3453, device='cuda:0')
episode: 58 training return: tensor(117.1951, device='cuda:0')
episode: 59 training return: tensor(-0.3576, device='cuda:0')
epoch: 15 test_true_pfm: 5454.11661519605 sim_pfm: 350.20005610759836
episode: 60 training return: tensor(194.4774, device='cuda:0')
episode: 61 training return: tensor(81.2742, device='cuda:0')
episode: 62 training return: tensor(121.1767, device='cuda:0')
episode: 63 training return: tensor(283.2644, device='cuda:0')
epoch: 16 test_true_pfm: 5420.9840470069985 sim_pfm: 402.56246737673064
episode: 64 training return: tensor(113.1115, device='cuda:0')
episode: 65 training return: tensor(65.7591, device='cuda:0')
episode: 66 training return: tensor(97.0742, device='cuda:0')
episode: 67 training return: tensor(142.6459, device='cuda:0')
epoch: 17 test_true_pfm: 5477.691008737395 sim_pfm: 298.3186254175186
episode: 68 training return: tensor(212.2067, device='cuda:0')
episode: 69 training return: tensor(147.4650, device='cuda:0')
episode: 70 training return: tensor(176.3662, device='cuda:0')
episode: 71 training return: tensor(128.6475, device='cuda:0')
epoch: 18 test_true_pfm: 5573.867276374965 sim_pfm: 395.80762807193486
episode: 72 training return: tensor(-712.1366, device='cuda:0')
episode: 73 training return: tensor(131.9434, device='cuda:0')
episode: 74 training return: tensor(186.8001, device='cuda:0')
episode: 75 training return: tensor(69.1494, device='cuda:0')
epoch: 19 test_true_pfm: 5545.17269816434 sim_pfm: 387.76843942143023
episode: 76 training return: tensor(91.2825, device='cuda:0')
episode: 77 training return: tensor(255.4160, device='cuda:0')
episode: 78 training return: tensor(170.6244, device='cuda:0')
episode: 79 training return: tensor(160.9417, device='cuda:0')
epoch: 20 test_true_pfm: 5581.675819829373 sim_pfm: 441.6032749549486
episode: 80 training return: tensor(150.2185, device='cuda:0')
episode: 81 training return: tensor(221.5952, device='cuda:0')
episode: 82 training return: tensor(285.3596, device='cuda:0')
episode: 83 training return: tensor(268.5592, device='cuda:0')
epoch: 21 test_true_pfm: 5519.774397018089 sim_pfm: 389.6880114498296
episode: 84 training return: tensor(205.4559, device='cuda:0')
episode: 85 training return: tensor(221.7966, device='cuda:0')
episode: 86 training return: tensor(210.8954, device='cuda:0')
episode: 87 training return: tensor(247.5089, device='cuda:0')
epoch: 22 test_true_pfm: 5632.43415427546 sim_pfm: 455.865271739749
episode: 88 training return: tensor(224.8870, device='cuda:0')
episode: 89 training return: tensor(207.0999, device='cuda:0')
episode: 90 training return: tensor(219.2488, device='cuda:0')
episode: 91 training return: tensor(285.2179, device='cuda:0')
epoch: 23 test_true_pfm: 5769.416217626897 sim_pfm: 506.2947950566886
episode: 92 training return: tensor(235.9345, device='cuda:0')
episode: 93 training return: tensor(273.0464, device='cuda:0')
episode: 94 training return: tensor(293.4159, device='cuda:0')
episode: 95 training return: tensor(163.3146, device='cuda:0')
epoch: 24 test_true_pfm: 5808.524805084881 sim_pfm: 501.05341005007114
episode: 96 training return: tensor(324.1802, device='cuda:0')
episode: 97 training return: tensor(336.8817, device='cuda:0')
episode: 98 training return: tensor(312.6863, device='cuda:0')
episode: 99 training return: tensor(231.9152, device='cuda:0')
epoch: 25 test_true_pfm: 5774.708644773241 sim_pfm: 492.20029247534694
episode: 100 training return: tensor(311.4746, device='cuda:0')
episode: 101 training return: tensor(299.2445, device='cuda:0')
episode: 102 training return: tensor(140.8488, device='cuda:0')
episode: 103 training return: tensor(331.4601, device='cuda:0')
epoch: 26 test_true_pfm: 5818.622752910075 sim_pfm: 562.6036482326066
episode: 104 training return: tensor(215.6659, device='cuda:0')
episode: 105 training return: tensor(265.0548, device='cuda:0')
episode: 106 training return: tensor(348.7763, device='cuda:0')
episode: 107 training return: tensor(280.3242, device='cuda:0')
epoch: 27 test_true_pfm: 5774.8307277226495 sim_pfm: 525.8305747676641
episode: 108 training return: tensor(325.8886, device='cuda:0')
episode: 109 training return: tensor(351.7034, device='cuda:0')
episode: 110 training return: tensor(310.3823, device='cuda:0')
episode: 111 training return: tensor(304.2559, device='cuda:0')
epoch: 28 test_true_pfm: 5773.914797442667 sim_pfm: 536.3684275601214
episode: 112 training return: tensor(304.1190, device='cuda:0')
episode: 113 training return: tensor(318.6061, device='cuda:0')
episode: 114 training return: tensor(257.4410, device='cuda:0')
episode: 115 training return: tensor(402.5092, device='cuda:0')
epoch: 29 test_true_pfm: 5845.523087479708 sim_pfm: 574.4178517333348
episode: 116 training return: tensor(317.2816, device='cuda:0')
episode: 117 training return: tensor(361.9600, device='cuda:0')
episode: 118 training return: tensor(262.4125, device='cuda:0')
episode: 119 training return: tensor(373.4764, device='cuda:0')
epoch: 30 test_true_pfm: 5867.354851532508 sim_pfm: 561.9799853896257
episode: 120 training return: tensor(329.2577, device='cuda:0')
episode: 121 training return: tensor(434.6796, device='cuda:0')
episode: 122 training return: tensor(362.8648, device='cuda:0')
episode: 123 training return: tensor(352.9094, device='cuda:0')
epoch: 31 test_true_pfm: 5790.295645772949 sim_pfm: 555.1369959184085
episode: 124 training return: tensor(438.0910, device='cuda:0')
episode: 125 training return: tensor(307.5501, device='cuda:0')
episode: 126 training return: tensor(362.6250, device='cuda:0')
episode: 127 training return: tensor(323.8414, device='cuda:0')
epoch: 32 test_true_pfm: 5822.602465110854 sim_pfm: 385.08627211292816
episode: 128 training return: tensor(285.8545, device='cuda:0')
episode: 129 training return: tensor(374.3383, device='cuda:0')
episode: 130 training return: tensor(315.0725, device='cuda:0')
episode: 131 training return: tensor(303.6987, device='cuda:0')
epoch: 33 test_true_pfm: 5833.879414101892 sim_pfm: 565.5264703534
episode: 132 training return: tensor(418.2731, device='cuda:0')
episode: 133 training return: tensor(286.7112, device='cuda:0')
episode: 134 training return: tensor(391.4456, device='cuda:0')
episode: 135 training return: tensor(264.2151, device='cuda:0')
epoch: 34 test_true_pfm: 5859.7773684462545 sim_pfm: 530.0861994783821
episode: 136 training return: tensor(303.3966, device='cuda:0')
episode: 137 training return: tensor(425.7596, device='cuda:0')
episode: 138 training return: tensor(275.4812, device='cuda:0')
episode: 139 training return: tensor(343.4665, device='cuda:0')
epoch: 35 test_true_pfm: 5857.377414957241 sim_pfm: 581.5079862305817
episode: 140 training return: tensor(453.0399, device='cuda:0')
episode: 141 training return: tensor(331.7599, device='cuda:0')
episode: 142 training return: tensor(460.5202, device='cuda:0')
episode: 143 training return: tensor(405.5992, device='cuda:0')
epoch: 36 test_true_pfm: 5896.301080178229 sim_pfm: 626.9181382071305
episode: 144 training return: tensor(364.8045, device='cuda:0')
episode: 145 training return: tensor(400.5086, device='cuda:0')
episode: 146 training return: tensor(517.7244, device='cuda:0')
episode: 147 training return: tensor(382.3775, device='cuda:0')
epoch: 37 test_true_pfm: 5836.299244232073 sim_pfm: 580.4979389624592
episode: 148 training return: tensor(366.0771, device='cuda:0')
episode: 149 training return: tensor(437.8698, device='cuda:0')
episode: 150 training return: tensor(392.3130, device='cuda:0')
episode: 151 training return: tensor(410.1355, device='cuda:0')
epoch: 38 test_true_pfm: 5899.940601054921 sim_pfm: 636.323416338632
episode: 152 training return: tensor(404.1655, device='cuda:0')
episode: 153 training return: tensor(400.0611, device='cuda:0')
episode: 154 training return: tensor(390.6822, device='cuda:0')
episode: 155 training return: tensor(445.7342, device='cuda:0')
epoch: 39 test_true_pfm: 5921.101383079095 sim_pfm: 629.4431546346071
episode: 156 training return: tensor(498.7757, device='cuda:0')
episode: 157 training return: tensor(386.1739, device='cuda:0')
episode: 158 training return: tensor(451.4743, device='cuda:0')
episode: 159 training return: tensor(428.0669, device='cuda:0')
epoch: 40 test_true_pfm: 5867.916106575995 sim_pfm: 634.0920168486579
episode: 160 training return: tensor(476.6969, device='cuda:0')
episode: 161 training return: tensor(440.6479, device='cuda:0')
episode: 162 training return: tensor(369.3034, device='cuda:0')
episode: 163 training return: tensor(525.0136, device='cuda:0')
epoch: 41 test_true_pfm: 6023.767619674607 sim_pfm: 639.7926541588191
episode: 164 training return: tensor(433.0933, device='cuda:0')
episode: 165 training return: tensor(451.3837, device='cuda:0')
episode: 166 training return: tensor(402.7983, device='cuda:0')
episode: 167 training return: tensor(418.4627, device='cuda:0')
epoch: 42 test_true_pfm: 5990.356939471417 sim_pfm: 601.1703760680393
episode: 168 training return: tensor(413.1216, device='cuda:0')
episode: 169 training return: tensor(430.9709, device='cuda:0')
episode: 170 training return: tensor(428.6966, device='cuda:0')
episode: 171 training return: tensor(434.1170, device='cuda:0')
epoch: 43 test_true_pfm: 5996.081782574386 sim_pfm: 607.8559607465673
episode: 172 training return: tensor(435.4762, device='cuda:0')
episode: 173 training return: tensor(424.4027, device='cuda:0')
episode: 174 training return: tensor(482.5938, device='cuda:0')
episode: 175 training return: tensor(445.0909, device='cuda:0')
epoch: 44 test_true_pfm: 5988.943104392496 sim_pfm: 587.231951584341
episode: 176 training return: tensor(482.7463, device='cuda:0')
episode: 177 training return: tensor(405.5526, device='cuda:0')
episode: 178 training return: tensor(447.3615, device='cuda:0')
episode: 179 training return: tensor(457.2649, device='cuda:0')
epoch: 45 test_true_pfm: 5969.801892505316 sim_pfm: 630.3602180933036
episode: 180 training return: tensor(380.7959, device='cuda:0')
episode: 181 training return: tensor(487.5612, device='cuda:0')
episode: 182 training return: tensor(475.6676, device='cuda:0')
episode: 183 training return: tensor(492.7370, device='cuda:0')
epoch: 46 test_true_pfm: 6003.148919735839 sim_pfm: 612.4239025303395
episode: 184 training return: tensor(549.7455, device='cuda:0')
episode: 185 training return: tensor(321.5103, device='cuda:0')
episode: 186 training return: tensor(468.9850, device='cuda:0')
episode: 187 training return: tensor(463.4372, device='cuda:0')
epoch: 47 test_true_pfm: 6065.634323378246 sim_pfm: 658.2626644851019
episode: 188 training return: tensor(497.7279, device='cuda:0')
episode: 189 training return: tensor(446.8572, device='cuda:0')
episode: 190 training return: tensor(432.3327, device='cuda:0')
episode: 191 training return: tensor(401.8477, device='cuda:0')
epoch: 48 test_true_pfm: 6109.002355350574 sim_pfm: 647.3777639422138
episode: 192 training return: tensor(476.3043, device='cuda:0')
episode: 193 training return: tensor(449.2841, device='cuda:0')
episode: 194 training return: tensor(477.9405, device='cuda:0')
episode: 195 training return: tensor(540.4065, device='cuda:0')
epoch: 49 test_true_pfm: 5910.832701152988 sim_pfm: 605.3926048878153
episode: 196 training return: tensor(428.7458, device='cuda:0')
episode: 197 training return: tensor(424.1177, device='cuda:0')
episode: 198 training return: tensor(450.4287, device='cuda:0')
episode: 199 training return: tensor(460.1956, device='cuda:0')
epoch: 50 test_true_pfm: 6021.950241394889 sim_pfm: 648.2699976660855
episode: 200 training return: tensor(533.2619, device='cuda:0')
episode: 201 training return: tensor(519.6374, device='cuda:0')
episode: 202 training return: tensor(498.9152, device='cuda:0')
episode: 203 training return: tensor(392.3463, device='cuda:0')
epoch: 51 test_true_pfm: 6059.325625642082 sim_pfm: 657.8556280361954
episode: 204 training return: tensor(563.2170, device='cuda:0')
episode: 205 training return: tensor(504.3064, device='cuda:0')
episode: 206 training return: tensor(534.7758, device='cuda:0')
episode: 207 training return: tensor(436.7094, device='cuda:0')
epoch: 52 test_true_pfm: 6121.779120373608 sim_pfm: 665.8358302939838
episode: 208 training return: tensor(491.5390, device='cuda:0')
episode: 209 training return: tensor(409.9632, device='cuda:0')
episode: 210 training return: tensor(480.2132, device='cuda:0')
episode: 211 training return: tensor(436.8988, device='cuda:0')
epoch: 53 test_true_pfm: 6080.6850172911645 sim_pfm: 687.1580392995966
episode: 212 training return: tensor(501.3644, device='cuda:0')
episode: 213 training return: tensor(527.5139, device='cuda:0')
episode: 214 training return: tensor(468.4596, device='cuda:0')
episode: 215 training return: tensor(436.1637, device='cuda:0')
epoch: 54 test_true_pfm: 6032.390943323097 sim_pfm: 647.6619880610184
episode: 216 training return: tensor(429.0852, device='cuda:0')
episode: 217 training return: tensor(479.7780, device='cuda:0')
episode: 218 training return: tensor(490.1726, device='cuda:0')
episode: 219 training return: tensor(507.7112, device='cuda:0')
epoch: 55 test_true_pfm: 6108.132384244999 sim_pfm: 668.6765859806522
episode: 220 training return: tensor(559.3130, device='cuda:0')
episode: 221 training return: tensor(498.7438, device='cuda:0')
episode: 222 training return: tensor(531.2322, device='cuda:0')
episode: 223 training return: tensor(492.8513, device='cuda:0')
epoch: 56 test_true_pfm: 6001.962506512871 sim_pfm: 617.0719289334957
episode: 224 training return: tensor(510.0703, device='cuda:0')
episode: 225 training return: tensor(525.7128, device='cuda:0')
episode: 226 training return: tensor(487.2180, device='cuda:0')
episode: 227 training return: tensor(549.5106, device='cuda:0')
epoch: 57 test_true_pfm: 6104.164863194847 sim_pfm: 677.2649787540237
episode: 228 training return: tensor(516.5565, device='cuda:0')
episode: 229 training return: tensor(415.4573, device='cuda:0')
episode: 230 training return: tensor(557.0877, device='cuda:0')
episode: 231 training return: tensor(504.0482, device='cuda:0')
epoch: 58 test_true_pfm: 6030.963341912616 sim_pfm: 673.9373302489306
episode: 232 training return: tensor(502.6534, device='cuda:0')
episode: 233 training return: tensor(469.8765, device='cuda:0')
episode: 234 training return: tensor(541.0613, device='cuda:0')
episode: 235 training return: tensor(538.4603, device='cuda:0')
epoch: 59 test_true_pfm: 6126.142759228668 sim_pfm: 651.7939123575148
episode: 236 training return: tensor(472.7289, device='cuda:0')
episode: 237 training return: tensor(501.9293, device='cuda:0')
episode: 238 training return: tensor(580.3563, device='cuda:0')
episode: 239 training return: tensor(553.1077, device='cuda:0')
epoch: 60 test_true_pfm: 6127.604144257406 sim_pfm: 660.7886118146902
episode: 240 training return: tensor(474.4263, device='cuda:0')
episode: 241 training return: tensor(484.4380, device='cuda:0')
episode: 242 training return: tensor(491.0742, device='cuda:0')
episode: 243 training return: tensor(436.9731, device='cuda:0')
epoch: 61 test_true_pfm: 6106.066554948348 sim_pfm: 685.0378415705054
episode: 244 training return: tensor(458.6167, device='cuda:0')
episode: 245 training return: tensor(472.6304, device='cuda:0')
episode: 246 training return: tensor(520.9419, device='cuda:0')
episode: 247 training return: tensor(532.1396, device='cuda:0')
epoch: 62 test_true_pfm: 6098.809473387891 sim_pfm: 680.0499510605974
episode: 248 training return: tensor(523.3795, device='cuda:0')
episode: 249 training return: tensor(461.1712, device='cuda:0')
episode: 250 training return: tensor(561.9681, device='cuda:0')
episode: 251 training return: tensor(502.4473, device='cuda:0')
epoch: 63 test_true_pfm: 6143.032161875573 sim_pfm: 666.4286523927003
episode: 252 training return: tensor(542.9902, device='cuda:0')
episode: 253 training return: tensor(476.6260, device='cuda:0')
episode: 254 training return: tensor(453.6370, device='cuda:0')
episode: 255 training return: tensor(485.9511, device='cuda:0')
epoch: 64 test_true_pfm: 6040.957379475437 sim_pfm: 666.831477130414
episode: 256 training return: tensor(497.0076, device='cuda:0')
episode: 257 training return: tensor(456.8096, device='cuda:0')
episode: 258 training return: tensor(485.4443, device='cuda:0')
episode: 259 training return: tensor(557.3842, device='cuda:0')
epoch: 65 test_true_pfm: 6150.793468421386 sim_pfm: 688.2650681334004
episode: 260 training return: tensor(507.9375, device='cuda:0')
episode: 261 training return: tensor(510.5454, device='cuda:0')
episode: 262 training return: tensor(568.0334, device='cuda:0')
episode: 263 training return: tensor(575.2489, device='cuda:0')
epoch: 66 test_true_pfm: 6061.896260075805 sim_pfm: 671.0541238364143
episode: 264 training return: tensor(538.0056, device='cuda:0')
episode: 265 training return: tensor(574.6679, device='cuda:0')
episode: 266 training return: tensor(532.6140, device='cuda:0')
episode: 267 training return: tensor(480.9425, device='cuda:0')
epoch: 67 test_true_pfm: 6183.921454443621 sim_pfm: 702.7625899705259
episode: 268 training return: tensor(459.5892, device='cuda:0')
episode: 269 training return: tensor(519.7276, device='cuda:0')
episode: 270 training return: tensor(562.6094, device='cuda:0')
episode: 271 training return: tensor(555.8665, device='cuda:0')
epoch: 68 test_true_pfm: 6141.186126691336 sim_pfm: 699.2549737181204
episode: 272 training return: tensor(485.9577, device='cuda:0')
episode: 273 training return: tensor(472.7233, device='cuda:0')
episode: 274 training return: tensor(482.6438, device='cuda:0')
episode: 275 training return: tensor(486.4597, device='cuda:0')
epoch: 69 test_true_pfm: 6148.859594562106 sim_pfm: 692.1676411650454
episode: 276 training return: tensor(545.3311, device='cuda:0')
episode: 277 training return: tensor(492.5742, device='cuda:0')
episode: 278 training return: tensor(526.9916, device='cuda:0')
episode: 279 training return: tensor(488.4877, device='cuda:0')
epoch: 70 test_true_pfm: 6096.000458237632 sim_pfm: 678.6363765748683
episode: 280 training return: tensor(557.3829, device='cuda:0')
episode: 281 training return: tensor(548.8182, device='cuda:0')
episode: 282 training return: tensor(471.7919, device='cuda:0')
episode: 283 training return: tensor(606.1246, device='cuda:0')
epoch: 71 test_true_pfm: 6084.560259276722 sim_pfm: 687.4737221091927
episode: 284 training return: tensor(548.2347, device='cuda:0')
episode: 285 training return: tensor(574.3716, device='cuda:0')
episode: 286 training return: tensor(530.9547, device='cuda:0')
episode: 287 training return: tensor(537.8722, device='cuda:0')
epoch: 72 test_true_pfm: 6150.363997583125 sim_pfm: 443.8490422406855
episode: 288 training return: tensor(537.3275, device='cuda:0')
episode: 289 training return: tensor(514.2410, device='cuda:0')
episode: 290 training return: tensor(588.0034, device='cuda:0')
episode: 291 training return: tensor(504.8080, device='cuda:0')
epoch: 73 test_true_pfm: 6103.683615283088 sim_pfm: 678.9618967979526
episode: 292 training return: tensor(514.2445, device='cuda:0')
episode: 293 training return: tensor(508.4634, device='cuda:0')
episode: 294 training return: tensor(613.6605, device='cuda:0')
episode: 295 training return: tensor(498.0488, device='cuda:0')
epoch: 74 test_true_pfm: 6162.118870940707 sim_pfm: 703.9886851541232
episode: 296 training return: tensor(548.4100, device='cuda:0')
episode: 297 training return: tensor(572.1445, device='cuda:0')
episode: 298 training return: tensor(529.9935, device='cuda:0')
episode: 299 training return: tensor(569.7612, device='cuda:0')
epoch: 75 test_true_pfm: 6121.928764854713 sim_pfm: 683.9492511598897
episode: 300 training return: tensor(479.0162, device='cuda:0')
episode: 301 training return: tensor(547.7724, device='cuda:0')
episode: 302 training return: tensor(537.4291, device='cuda:0')
episode: 303 training return: tensor(506.1864, device='cuda:0')
epoch: 76 test_true_pfm: 6141.839154043082 sim_pfm: 687.2428363198027
episode: 304 training return: tensor(544.5325, device='cuda:0')
episode: 305 training return: tensor(466.6464, device='cuda:0')
episode: 306 training return: tensor(579.9288, device='cuda:0')
episode: 307 training return: tensor(507.6258, device='cuda:0')
epoch: 77 test_true_pfm: 6112.2519485203475 sim_pfm: 684.1025756010009
episode: 308 training return: tensor(553.3899, device='cuda:0')
episode: 309 training return: tensor(612.4649, device='cuda:0')
episode: 310 training return: tensor(602.3675, device='cuda:0')
episode: 311 training return: tensor(568.9660, device='cuda:0')
epoch: 78 test_true_pfm: 6144.637664112913 sim_pfm: 707.1140252644351
episode: 312 training return: tensor(549.1948, device='cuda:0')
episode: 313 training return: tensor(534.4127, device='cuda:0')
episode: 314 training return: tensor(594.6681, device='cuda:0')
episode: 315 training return: tensor(520.3552, device='cuda:0')
epoch: 79 test_true_pfm: 6159.626085575664 sim_pfm: 705.408728518174
episode: 316 training return: tensor(579.6322, device='cuda:0')
episode: 317 training return: tensor(462.3702, device='cuda:0')
episode: 318 training return: tensor(549.9662, device='cuda:0')
episode: 319 training return: tensor(579.1978, device='cuda:0')
epoch: 80 test_true_pfm: 6211.967868975681 sim_pfm: 728.8319761185752
episode: 320 training return: tensor(580.7784, device='cuda:0')
episode: 321 training return: tensor(538.5142, device='cuda:0')
episode: 322 training return: tensor(565.2365, device='cuda:0')
episode: 323 training return: tensor(547.4282, device='cuda:0')
epoch: 81 test_true_pfm: 6206.91725664774 sim_pfm: 729.1560725987656
episode: 324 training return: tensor(541.3920, device='cuda:0')
episode: 325 training return: tensor(582.4512, device='cuda:0')
episode: 326 training return: tensor(582.6558, device='cuda:0')
episode: 327 training return: tensor(560.8288, device='cuda:0')
epoch: 82 test_true_pfm: 6191.600520687774 sim_pfm: 699.9222759928865
episode: 328 training return: tensor(433.1934, device='cuda:0')
episode: 329 training return: tensor(583.3204, device='cuda:0')
episode: 330 training return: tensor(538.2289, device='cuda:0')
episode: 331 training return: tensor(516.7070, device='cuda:0')
epoch: 83 test_true_pfm: 6139.115128569614 sim_pfm: 705.5159659273146
episode: 332 training return: tensor(514.4123, device='cuda:0')
episode: 333 training return: tensor(574.7641, device='cuda:0')
episode: 334 training return: tensor(575.8237, device='cuda:0')
episode: 335 training return: tensor(572.5866, device='cuda:0')
epoch: 84 test_true_pfm: 6164.713262572317 sim_pfm: 703.1089741480149
episode: 336 training return: tensor(502.7117, device='cuda:0')
episode: 337 training return: tensor(560.4819, device='cuda:0')
episode: 338 training return: tensor(565.5341, device='cuda:0')
episode: 339 training return: tensor(579.1204, device='cuda:0')
epoch: 85 test_true_pfm: 6170.477466905329 sim_pfm: 706.5974067489539
episode: 340 training return: tensor(538.9028, device='cuda:0')
episode: 341 training return: tensor(594.0639, device='cuda:0')
episode: 342 training return: tensor(578.4825, device='cuda:0')
episode: 343 training return: tensor(569.3274, device='cuda:0')
epoch: 86 test_true_pfm: 6176.281158213274 sim_pfm: 720.5870365734445
episode: 344 training return: tensor(607.7372, device='cuda:0')
episode: 345 training return: tensor(522.3177, device='cuda:0')
episode: 346 training return: tensor(552.9991, device='cuda:0')
episode: 347 training return: tensor(583.0676, device='cuda:0')
epoch: 87 test_true_pfm: 6258.369988543808 sim_pfm: 734.3930389914118
episode: 348 training return: tensor(597.0693, device='cuda:0')
episode: 349 training return: tensor(594.0542, device='cuda:0')
episode: 350 training return: tensor(569.2438, device='cuda:0')
episode: 351 training return: tensor(491.3057, device='cuda:0')
epoch: 88 test_true_pfm: 6198.249507560608 sim_pfm: 732.0877878939112
episode: 352 training return: tensor(544.1075, device='cuda:0')
episode: 353 training return: tensor(523.4663, device='cuda:0')
episode: 354 training return: tensor(527.0126, device='cuda:0')
episode: 355 training return: tensor(573.6348, device='cuda:0')
epoch: 89 test_true_pfm: 6151.163450468703 sim_pfm: 725.6976530903485
episode: 356 training return: tensor(518.4164, device='cuda:0')
episode: 357 training return: tensor(568.9178, device='cuda:0')
episode: 358 training return: tensor(631.2733, device='cuda:0')
episode: 359 training return: tensor(497.4418, device='cuda:0')
epoch: 90 test_true_pfm: 6145.5973142829 sim_pfm: 689.7921532740196
episode: 360 training return: tensor(494.5792, device='cuda:0')
episode: 361 training return: tensor(554.6255, device='cuda:0')
episode: 362 training return: tensor(585.5431, device='cuda:0')
episode: 363 training return: tensor(511.5336, device='cuda:0')
epoch: 91 test_true_pfm: 6278.138212731072 sim_pfm: 712.0769209867188
episode: 364 training return: tensor(501.8071, device='cuda:0')
episode: 365 training return: tensor(630.9183, device='cuda:0')
episode: 366 training return: tensor(590.0629, device='cuda:0')
episode: 367 training return: tensor(575.0870, device='cuda:0')
epoch: 92 test_true_pfm: 6203.75641429967 sim_pfm: 727.9308746050423
episode: 368 training return: tensor(569.9247, device='cuda:0')
episode: 369 training return: tensor(620.2537, device='cuda:0')
episode: 370 training return: tensor(554.6177, device='cuda:0')
episode: 371 training return: tensor(616.0701, device='cuda:0')
epoch: 93 test_true_pfm: 6184.961769222081 sim_pfm: 728.4514041307071
episode: 372 training return: tensor(602.4657, device='cuda:0')
episode: 373 training return: tensor(586.7428, device='cuda:0')
episode: 374 training return: tensor(570.8569, device='cuda:0')
episode: 375 training return: tensor(622.3352, device='cuda:0')
epoch: 94 test_true_pfm: 6170.31558022972 sim_pfm: 704.2186221708544
episode: 376 training return: tensor(571.2549, device='cuda:0')
episode: 377 training return: tensor(623.1168, device='cuda:0')
episode: 378 training return: tensor(546.0611, device='cuda:0')
episode: 379 training return: tensor(527.8875, device='cuda:0')
epoch: 95 test_true_pfm: 6232.3453577845785 sim_pfm: 735.8083356354813
episode: 380 training return: tensor(572.9307, device='cuda:0')
episode: 381 training return: tensor(583.5869, device='cuda:0')
episode: 382 training return: tensor(577.9425, device='cuda:0')
episode: 383 training return: tensor(540.2004, device='cuda:0')
epoch: 96 test_true_pfm: 6071.656694030477 sim_pfm: 634.8919023755006
episode: 384 training return: tensor(526.8226, device='cuda:0')
episode: 385 training return: tensor(561.3378, device='cuda:0')
episode: 386 training return: tensor(522.0906, device='cuda:0')
episode: 387 training return: tensor(594.8489, device='cuda:0')
epoch: 97 test_true_pfm: 6235.529501230667 sim_pfm: 746.460117905032
episode: 388 training return: tensor(568.7114, device='cuda:0')
episode: 389 training return: tensor(602.7532, device='cuda:0')
episode: 390 training return: tensor(599.6555, device='cuda:0')
episode: 391 training return: tensor(545.9398, device='cuda:0')
epoch: 98 test_true_pfm: 6135.536885584632 sim_pfm: 714.5407900747377
episode: 392 training return: tensor(545.6390, device='cuda:0')
episode: 393 training return: tensor(616.2060, device='cuda:0')
episode: 394 training return: tensor(588.2622, device='cuda:0')
episode: 395 training return: tensor(547.3799, device='cuda:0')
epoch: 99 test_true_pfm: 6260.678368755866 sim_pfm: 709.4236702062577
episode: 396 training return: tensor(615.0142, device='cuda:0')
episode: 397 training return: tensor(465.9560, device='cuda:0')
episode: 398 training return: tensor(522.7728, device='cuda:0')
episode: 399 training return: tensor(528.1835, device='cuda:0')
epoch: 100 test_true_pfm: 6137.33393479321 sim_pfm: 736.7820004355939
episode: 400 training return: tensor(601.0643, device='cuda:0')
episode: 401 training return: tensor(517.5806, device='cuda:0')
episode: 402 training return: tensor(510.6015, device='cuda:0')
episode: 403 training return: tensor(578.8724, device='cuda:0')
epoch: 101 test_true_pfm: 6217.1809587801545 sim_pfm: 714.7311084626126
episode: 404 training return: tensor(476.3295, device='cuda:0')
episode: 405 training return: tensor(587.3065, device='cuda:0')
episode: 406 training return: tensor(566.3956, device='cuda:0')
episode: 407 training return: tensor(568.3834, device='cuda:0')
epoch: 102 test_true_pfm: 6165.774860975533 sim_pfm: 722.3594281694968
episode: 408 training return: tensor(546.9653, device='cuda:0')
episode: 409 training return: tensor(548.9296, device='cuda:0')
episode: 410 training return: tensor(589.9052, device='cuda:0')
episode: 411 training return: tensor(549.6484, device='cuda:0')
epoch: 103 test_true_pfm: 6203.404583956674 sim_pfm: 697.3216818977768
episode: 412 training return: tensor(549.6003, device='cuda:0')
episode: 413 training return: tensor(522.9775, device='cuda:0')
episode: 414 training return: tensor(608.7007, device='cuda:0')
episode: 415 training return: tensor(588.7698, device='cuda:0')
epoch: 104 test_true_pfm: 6276.901753672565 sim_pfm: 734.1213369281808
episode: 416 training return: tensor(549.7750, device='cuda:0')
episode: 417 training return: tensor(574.9875, device='cuda:0')
episode: 418 training return: tensor(566.8185, device='cuda:0')
episode: 419 training return: tensor(588.6714, device='cuda:0')
epoch: 105 test_true_pfm: 6161.539829262095 sim_pfm: 710.67144708056
episode: 420 training return: tensor(523.0149, device='cuda:0')
episode: 421 training return: tensor(577.9275, device='cuda:0')
episode: 422 training return: tensor(574.8895, device='cuda:0')
episode: 423 training return: tensor(594.8171, device='cuda:0')
epoch: 106 test_true_pfm: 6140.385950415065 sim_pfm: 712.3189453597103
episode: 424 training return: tensor(578.8463, device='cuda:0')
episode: 425 training return: tensor(598.5529, device='cuda:0')
episode: 426 training return: tensor(614.1934, device='cuda:0')
episode: 427 training return: tensor(574.3892, device='cuda:0')
epoch: 107 test_true_pfm: 6173.905374619749 sim_pfm: 721.1863561497497
episode: 428 training return: tensor(571.9976, device='cuda:0')
episode: 429 training return: tensor(588.2325, device='cuda:0')
episode: 430 training return: tensor(600.8967, device='cuda:0')
episode: 431 training return: tensor(598.0579, device='cuda:0')
epoch: 108 test_true_pfm: 6183.764252940925 sim_pfm: 725.5883706005601
episode: 432 training return: tensor(580.7994, device='cuda:0')
episode: 433 training return: tensor(607.5491, device='cuda:0')
episode: 434 training return: tensor(530.2943, device='cuda:0')
episode: 435 training return: tensor(529.0483, device='cuda:0')
epoch: 109 test_true_pfm: 6205.931763969912 sim_pfm: 730.9658154632392
episode: 436 training return: tensor(596.0858, device='cuda:0')
episode: 437 training return: tensor(589.6096, device='cuda:0')
episode: 438 training return: tensor(595.0971, device='cuda:0')
episode: 439 training return: tensor(606.6118, device='cuda:0')
epoch: 110 test_true_pfm: 6189.412610202941 sim_pfm: 719.3270355519684
episode: 440 training return: tensor(530.5868, device='cuda:0')
episode: 441 training return: tensor(634.5244, device='cuda:0')
episode: 442 training return: tensor(608.0164, device='cuda:0')
episode: 443 training return: tensor(577.9785, device='cuda:0')
epoch: 111 test_true_pfm: 6170.71916402172 sim_pfm: 687.0069803750957
episode: 444 training return: tensor(620.4636, device='cuda:0')
episode: 445 training return: tensor(541.5455, device='cuda:0')
episode: 446 training return: tensor(611.9221, device='cuda:0')
episode: 447 training return: tensor(554.9470, device='cuda:0')
epoch: 112 test_true_pfm: 6255.175560941712 sim_pfm: 724.8055822848304
episode: 448 training return: tensor(580.6024, device='cuda:0')
episode: 449 training return: tensor(589.6292, device='cuda:0')
episode: 450 training return: tensor(534.7911, device='cuda:0')
episode: 451 training return: tensor(527.4496, device='cuda:0')
epoch: 113 test_true_pfm: 6286.2765796151 sim_pfm: 731.1728825520646
episode: 452 training return: tensor(625.9758, device='cuda:0')
episode: 453 training return: tensor(580.2383, device='cuda:0')
episode: 454 training return: tensor(583.2773, device='cuda:0')
episode: 455 training return: tensor(585.1472, device='cuda:0')
epoch: 114 test_true_pfm: 6245.0936840932545 sim_pfm: 743.2511108222728
episode: 456 training return: tensor(565.1630, device='cuda:0')
episode: 457 training return: tensor(632.7426, device='cuda:0')
episode: 458 training return: tensor(531.1770, device='cuda:0')
episode: 459 training return: tensor(565.3703, device='cuda:0')
epoch: 115 test_true_pfm: 6212.206029748594 sim_pfm: 697.9270060334044
episode: 460 training return: tensor(598.2520, device='cuda:0')
episode: 461 training return: tensor(603.1409, device='cuda:0')
episode: 462 training return: tensor(614.4479, device='cuda:0')
episode: 463 training return: tensor(589.7443, device='cuda:0')
epoch: 116 test_true_pfm: 6335.435916432675 sim_pfm: 750.295482504492
episode: 464 training return: tensor(639.6022, device='cuda:0')
episode: 465 training return: tensor(601.9621, device='cuda:0')
episode: 466 training return: tensor(624.1824, device='cuda:0')
episode: 467 training return: tensor(568.7459, device='cuda:0')
epoch: 117 test_true_pfm: 6258.0154237276265 sim_pfm: 760.7143100480704
episode: 468 training return: tensor(595.1514, device='cuda:0')
episode: 469 training return: tensor(659.6053, device='cuda:0')
episode: 470 training return: tensor(625.3101, device='cuda:0')
episode: 471 training return: tensor(585.7413, device='cuda:0')
epoch: 118 test_true_pfm: 6266.736731947077 sim_pfm: 738.8237333168896
episode: 472 training return: tensor(628.6204, device='cuda:0')
episode: 473 training return: tensor(575.6236, device='cuda:0')
episode: 474 training return: tensor(529.0283, device='cuda:0')
episode: 475 training return: tensor(553.6248, device='cuda:0')
epoch: 119 test_true_pfm: 6236.37995745806 sim_pfm: 742.750096261967
episode: 476 training return: tensor(608.6014, device='cuda:0')
episode: 477 training return: tensor(586.5694, device='cuda:0')
episode: 478 training return: tensor(560.1818, device='cuda:0')
episode: 479 training return: tensor(613.6165, device='cuda:0')
epoch: 120 test_true_pfm: 6271.378653003267 sim_pfm: 722.7702778172679
episode: 480 training return: tensor(596.6877, device='cuda:0')
episode: 481 training return: tensor(599.3715, device='cuda:0')
episode: 482 training return: tensor(592.4421, device='cuda:0')
episode: 483 training return: tensor(566.4791, device='cuda:0')
epoch: 121 test_true_pfm: 6074.693879346009 sim_pfm: 686.0028730708096
episode: 484 training return: tensor(531.5329, device='cuda:0')
episode: 485 training return: tensor(608.2535, device='cuda:0')
episode: 486 training return: tensor(567.9966, device='cuda:0')
episode: 487 training return: tensor(580.6407, device='cuda:0')
epoch: 122 test_true_pfm: 6270.3714968327995 sim_pfm: 750.3166072690316
episode: 488 training return: tensor(605.5015, device='cuda:0')
episode: 489 training return: tensor(585.9420, device='cuda:0')
episode: 490 training return: tensor(550.9004, device='cuda:0')
episode: 491 training return: tensor(579.2386, device='cuda:0')
epoch: 123 test_true_pfm: 6258.445419911898 sim_pfm: 751.0057076785791
episode: 492 training return: tensor(560.5280, device='cuda:0')
episode: 493 training return: tensor(584.8639, device='cuda:0')
episode: 494 training return: tensor(630.8397, device='cuda:0')
episode: 495 training return: tensor(565.1050, device='cuda:0')
epoch: 124 test_true_pfm: 6253.3940810687345 sim_pfm: 763.1432904201598
episode: 496 training return: tensor(612.1566, device='cuda:0')
episode: 497 training return: tensor(586.3324, device='cuda:0')
episode: 498 training return: tensor(575.7640, device='cuda:0')
episode: 499 training return: tensor(567.4478, device='cuda:0')
epoch: 125 test_true_pfm: 6191.002342722095 sim_pfm: 730.3354489821553
episode: 500 training return: tensor(615.3470, device='cuda:0')
episode: 501 training return: tensor(652.4709, device='cuda:0')
episode: 502 training return: tensor(608.0493, device='cuda:0')
episode: 503 training return: tensor(563.5046, device='cuda:0')
epoch: 126 test_true_pfm: 6325.296516347633 sim_pfm: 753.2837617011586
episode: 504 training return: tensor(606.1920, device='cuda:0')
episode: 505 training return: tensor(625.4366, device='cuda:0')
episode: 506 training return: tensor(589.9557, device='cuda:0')
episode: 507 training return: tensor(649.2328, device='cuda:0')
epoch: 127 test_true_pfm: 6271.8250955626545 sim_pfm: 763.0436658652421
episode: 508 training return: tensor(602.0503, device='cuda:0')
episode: 509 training return: tensor(542.9089, device='cuda:0')
episode: 510 training return: tensor(607.0131, device='cuda:0')
episode: 511 training return: tensor(577.1678, device='cuda:0')
epoch: 128 test_true_pfm: 6259.008977977236 sim_pfm: 721.8075728537515
episode: 512 training return: tensor(637.7687, device='cuda:0')
episode: 513 training return: tensor(645.6711, device='cuda:0')
episode: 514 training return: tensor(664.5281, device='cuda:0')
episode: 515 training return: tensor(596.1792, device='cuda:0')
epoch: 129 test_true_pfm: 6300.540107156642 sim_pfm: 743.813072810648
episode: 516 training return: tensor(667.9605, device='cuda:0')
episode: 517 training return: tensor(617.3190, device='cuda:0')
episode: 518 training return: tensor(590.9249, device='cuda:0')
episode: 519 training return: tensor(563.3450, device='cuda:0')
epoch: 130 test_true_pfm: 6198.565945836898 sim_pfm: 692.9027618331214
episode: 520 training return: tensor(571.3876, device='cuda:0')
episode: 521 training return: tensor(599.2606, device='cuda:0')
episode: 522 training return: tensor(619.9592, device='cuda:0')
episode: 523 training return: tensor(613.8035, device='cuda:0')
epoch: 131 test_true_pfm: 6353.029631962225 sim_pfm: 756.1799609546337
episode: 524 training return: tensor(589.1014, device='cuda:0')
episode: 525 training return: tensor(605.6522, device='cuda:0')
episode: 526 training return: tensor(656.1594, device='cuda:0')
episode: 527 training return: tensor(554.5645, device='cuda:0')
epoch: 132 test_true_pfm: 6377.757918743801 sim_pfm: 759.7407339036776
episode: 528 training return: tensor(606.1328, device='cuda:0')
episode: 529 training return: tensor(588.8954, device='cuda:0')
episode: 530 training return: tensor(602.2860, device='cuda:0')
episode: 531 training return: tensor(631.5926, device='cuda:0')
epoch: 133 test_true_pfm: 6237.842798066685 sim_pfm: 731.1792079190878
episode: 532 training return: tensor(600.7123, device='cuda:0')
episode: 533 training return: tensor(608.2041, device='cuda:0')
episode: 534 training return: tensor(629.0756, device='cuda:0')
episode: 535 training return: tensor(605.0267, device='cuda:0')
epoch: 134 test_true_pfm: 6206.064137670226 sim_pfm: 734.0457101456899
episode: 536 training return: tensor(564.4303, device='cuda:0')
episode: 537 training return: tensor(544.8069, device='cuda:0')
episode: 538 training return: tensor(613.8314, device='cuda:0')
episode: 539 training return: tensor(593.9460, device='cuda:0')
epoch: 135 test_true_pfm: 6302.490032251018 sim_pfm: 763.3653307862793
episode: 540 training return: tensor(600.6157, device='cuda:0')
episode: 541 training return: tensor(602.0604, device='cuda:0')
episode: 542 training return: tensor(629.2317, device='cuda:0')
episode: 543 training return: tensor(604.2209, device='cuda:0')
epoch: 136 test_true_pfm: 6120.7934535393315 sim_pfm: 696.6728668853951
episode: 544 training return: tensor(575.3417, device='cuda:0')
episode: 545 training return: tensor(615.9146, device='cuda:0')
episode: 546 training return: tensor(593.0814, device='cuda:0')
episode: 547 training return: tensor(604.9415, device='cuda:0')
epoch: 137 test_true_pfm: 6244.934401250197 sim_pfm: 736.6903029085757
episode: 548 training return: tensor(627.8969, device='cuda:0')
episode: 549 training return: tensor(615.5928, device='cuda:0')
episode: 550 training return: tensor(570.0334, device='cuda:0')
episode: 551 training return: tensor(584.3763, device='cuda:0')
epoch: 138 test_true_pfm: 6265.4464930979875 sim_pfm: 722.1417593142638
episode: 552 training return: tensor(621.9080, device='cuda:0')
episode: 553 training return: tensor(614.6849, device='cuda:0')
episode: 554 training return: tensor(570.0892, device='cuda:0')
episode: 555 training return: tensor(605.9973, device='cuda:0')
epoch: 139 test_true_pfm: 6257.932566618245 sim_pfm: 741.4686188132813
episode: 556 training return: tensor(644.3415, device='cuda:0')
episode: 557 training return: tensor(627.2996, device='cuda:0')
episode: 558 training return: tensor(591.5849, device='cuda:0')
episode: 559 training return: tensor(613.6649, device='cuda:0')
epoch: 140 test_true_pfm: 6249.153094070151 sim_pfm: 741.3954663957702
episode: 560 training return: tensor(610.0338, device='cuda:0')
episode: 561 training return: tensor(561.9002, device='cuda:0')
episode: 562 training return: tensor(606.5546, device='cuda:0')
episode: 563 training return: tensor(670.0032, device='cuda:0')
epoch: 141 test_true_pfm: 6295.575763170543 sim_pfm: 735.5868478921087
episode: 564 training return: tensor(576.7922, device='cuda:0')
episode: 565 training return: tensor(638.9951, device='cuda:0')
episode: 566 training return: tensor(586.7442, device='cuda:0')
episode: 567 training return: tensor(661.0815, device='cuda:0')
epoch: 142 test_true_pfm: 6308.337539041798 sim_pfm: 716.7966178834516
episode: 568 training return: tensor(583.7892, device='cuda:0')
episode: 569 training return: tensor(592.2266, device='cuda:0')
episode: 570 training return: tensor(581.2714, device='cuda:0')
episode: 571 training return: tensor(538.9363, device='cuda:0')
epoch: 143 test_true_pfm: 6370.6573925657685 sim_pfm: 796.6882910546847
episode: 572 training return: tensor(612.1020, device='cuda:0')
episode: 573 training return: tensor(574.3342, device='cuda:0')
episode: 574 training return: tensor(543.5711, device='cuda:0')
episode: 575 training return: tensor(600.4218, device='cuda:0')
epoch: 144 test_true_pfm: 6219.452720155235 sim_pfm: 703.5571526323911
episode: 576 training return: tensor(600.2616, device='cuda:0')
episode: 577 training return: tensor(600.1028, device='cuda:0')
episode: 578 training return: tensor(548.6464, device='cuda:0')
episode: 579 training return: tensor(644.4238, device='cuda:0')
epoch: 145 test_true_pfm: 6322.762593086569 sim_pfm: 726.1192505757596
episode: 580 training return: tensor(675.3354, device='cuda:0')
episode: 581 training return: tensor(646.8908, device='cuda:0')
episode: 582 training return: tensor(577.9121, device='cuda:0')
episode: 583 training return: tensor(632.5671, device='cuda:0')
epoch: 146 test_true_pfm: 6315.9912586260225 sim_pfm: 772.2858129098701
episode: 584 training return: tensor(609.7247, device='cuda:0')
episode: 585 training return: tensor(579.2082, device='cuda:0')
episode: 586 training return: tensor(604.1830, device='cuda:0')
episode: 587 training return: tensor(603.9038, device='cuda:0')
epoch: 147 test_true_pfm: 6300.257505330671 sim_pfm: 751.7205998968178
episode: 588 training return: tensor(594.7111, device='cuda:0')
episode: 589 training return: tensor(561.5756, device='cuda:0')
episode: 590 training return: tensor(627.6263, device='cuda:0')
episode: 591 training return: tensor(603.8601, device='cuda:0')
epoch: 148 test_true_pfm: 6298.308660113519 sim_pfm: 748.5123321790015
episode: 592 training return: tensor(641.1078, device='cuda:0')
episode: 593 training return: tensor(602.0264, device='cuda:0')
episode: 594 training return: tensor(632.4000, device='cuda:0')
episode: 595 training return: tensor(612.7263, device='cuda:0')
epoch: 149 test_true_pfm: 6415.576353402797 sim_pfm: 769.0187831946338
episode: 596 training return: tensor(635.4793, device='cuda:0')
episode: 597 training return: tensor(653.8633, device='cuda:0')
episode: 598 training return: tensor(630.7253, device='cuda:0')
episode: 599 training return: tensor(598.6401, device='cuda:0')
epoch: 150 test_true_pfm: 6261.176168960864 sim_pfm: 709.5344668778125
