['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '1', '--data', '100000', '--regu', '0.3']
2582.8039920726646
episode: 0 training return: tensor(284.3498, device='cuda:0')
episode: 1 training return: tensor(340.7113, device='cuda:0')
episode: 2 training return: tensor(266.8530, device='cuda:0')
episode: 3 training return: tensor(273.8017, device='cuda:0')
epoch: 1 test_true_pfm: 1825.4218500085747 sim_pfm: 152.52122771312133
episode: 4 training return: tensor(303.2271, device='cuda:0')
episode: 5 training return: tensor(376.3232, device='cuda:0')
episode: 6 training return: tensor(2.5474, device='cuda:0')
episode: 7 training return: tensor(325.3959, device='cuda:0')
epoch: 2 test_true_pfm: 1963.5157256632012 sim_pfm: 238.0584267199738
episode: 8 training return: tensor(322.3927, device='cuda:0')
episode: 9 training return: tensor(284.6101, device='cuda:0')
episode: 10 training return: tensor(156.5571, device='cuda:0')
episode: 11 training return: tensor(376.6505, device='cuda:0')
epoch: 3 test_true_pfm: 2056.9644159288246 sim_pfm: -51.63748828224683
episode: 12 training return: tensor(157.8234, device='cuda:0')
episode: 13 training return: tensor(57.6605, device='cuda:0')
episode: 14 training return: tensor(425.9554, device='cuda:0')
episode: 15 training return: tensor(-510.6771, device='cuda:0')
epoch: 4 test_true_pfm: 3168.9177243602667 sim_pfm: 414.80587709340034
episode: 16 training return: tensor(183.4693, device='cuda:0')
episode: 17 training return: tensor(323.9205, device='cuda:0')
episode: 18 training return: tensor(237.1300, device='cuda:0')
episode: 19 training return: tensor(314.1025, device='cuda:0')
epoch: 5 test_true_pfm: 3226.020087906789 sim_pfm: 368.10311630116
episode: 20 training return: tensor(348.7132, device='cuda:0')
episode: 21 training return: tensor(477.1182, device='cuda:0')
episode: 22 training return: tensor(323.8579, device='cuda:0')
episode: 23 training return: tensor(385.7687, device='cuda:0')
epoch: 6 test_true_pfm: 3227.915025412129 sim_pfm: 365.39080737760133
episode: 24 training return: tensor(397.9991, device='cuda:0')
episode: 25 training return: tensor(419.0483, device='cuda:0')
episode: 26 training return: tensor(415.9012, device='cuda:0')
episode: 27 training return: tensor(375.1021, device='cuda:0')
epoch: 7 test_true_pfm: 2539.5910482668896 sim_pfm: 450.64945253450423
episode: 28 training return: tensor(393.6733, device='cuda:0')
episode: 29 training return: tensor(487.6771, device='cuda:0')
episode: 30 training return: tensor(446.6872, device='cuda:0')
episode: 31 training return: tensor(-28.1628, device='cuda:0')
epoch: 8 test_true_pfm: 3451.437223974131 sim_pfm: 344.91379260279547
episode: 32 training return: tensor(378.2295, device='cuda:0')
episode: 33 training return: tensor(473.7549, device='cuda:0')
episode: 34 training return: tensor(440.9706, device='cuda:0')
episode: 35 training return: tensor(391.1697, device='cuda:0')
epoch: 9 test_true_pfm: 3525.8430989502776 sim_pfm: 465.5131707706411
episode: 36 training return: tensor(502.7400, device='cuda:0')
episode: 37 training return: tensor(-8.7219, device='cuda:0')
episode: 38 training return: tensor(524.6455, device='cuda:0')
episode: 39 training return: tensor(477.4442, device='cuda:0')
epoch: 10 test_true_pfm: 3380.9167232557597 sim_pfm: 156.51821720228568
episode: 40 training return: tensor(466.9080, device='cuda:0')
episode: 41 training return: tensor(352.8975, device='cuda:0')
episode: 42 training return: tensor(407.9906, device='cuda:0')
episode: 43 training return: tensor(-173.3920, device='cuda:0')
epoch: 11 test_true_pfm: 3045.3123445680944 sim_pfm: 116.5101244323693
episode: 44 training return: tensor(386.6805, device='cuda:0')
episode: 45 training return: tensor(444.6255, device='cuda:0')
episode: 46 training return: tensor(439.1949, device='cuda:0')
episode: 47 training return: tensor(-509.2242, device='cuda:0')
epoch: 12 test_true_pfm: 3237.6998049910926 sim_pfm: 406.47640802144696
episode: 48 training return: tensor(86.5663, device='cuda:0')
episode: 49 training return: tensor(485.9399, device='cuda:0')
episode: 50 training return: tensor(442.4385, device='cuda:0')
episode: 51 training return: tensor(10.8932, device='cuda:0')
epoch: 13 test_true_pfm: 3472.1029430791605 sim_pfm: 340.1984928446861
episode: 52 training return: tensor(295.0233, device='cuda:0')
episode: 53 training return: tensor(343.7599, device='cuda:0')
episode: 54 training return: tensor(333.2616, device='cuda:0')
episode: 55 training return: tensor(341.5717, device='cuda:0')
epoch: 14 test_true_pfm: 2790.1620756481957 sim_pfm: 329.04615461120073
episode: 56 training return: tensor(357.0219, device='cuda:0')
episode: 57 training return: tensor(479.6012, device='cuda:0')
episode: 58 training return: tensor(415.2610, device='cuda:0')
episode: 59 training return: tensor(406.0258, device='cuda:0')
epoch: 15 test_true_pfm: 3616.2395177266067 sim_pfm: 487.6079246364534
episode: 60 training return: tensor(428.4301, device='cuda:0')
episode: 61 training return: tensor(268.3246, device='cuda:0')
episode: 62 training return: tensor(18.9591, device='cuda:0')
episode: 63 training return: tensor(459.8932, device='cuda:0')
epoch: 16 test_true_pfm: 3071.142587177162 sim_pfm: 94.92723740714912
episode: 64 training return: tensor(469.9743, device='cuda:0')
episode: 65 training return: tensor(197.0541, device='cuda:0')
episode: 66 training return: tensor(489.3436, device='cuda:0')
episode: 67 training return: tensor(464.2975, device='cuda:0')
epoch: 17 test_true_pfm: 3183.8133832320186 sim_pfm: 429.9373562679587
episode: 68 training return: tensor(444.0135, device='cuda:0')
episode: 69 training return: tensor(327.7542, device='cuda:0')
episode: 70 training return: tensor(-268.1021, device='cuda:0')
episode: 71 training return: tensor(-243.8419, device='cuda:0')
epoch: 18 test_true_pfm: 3480.4884057048725 sim_pfm: 413.2941805791731
episode: 72 training return: tensor(366.8344, device='cuda:0')
episode: 73 training return: tensor(-328.0047, device='cuda:0')
episode: 74 training return: tensor(-188.2419, device='cuda:0')
episode: 75 training return: tensor(-234.1378, device='cuda:0')
epoch: 19 test_true_pfm: 3362.2293791002935 sim_pfm: -88.37835456323228
episode: 76 training return: tensor(24.5104, device='cuda:0')
episode: 77 training return: tensor(318.7479, device='cuda:0')
episode: 78 training return: tensor(424.2051, device='cuda:0')
episode: 79 training return: tensor(289.2942, device='cuda:0')
epoch: 20 test_true_pfm: 2626.5899953158796 sim_pfm: 327.080804910666
episode: 80 training return: tensor(368.9187, device='cuda:0')
episode: 81 training return: tensor(441.9016, device='cuda:0')
episode: 82 training return: tensor(-58.2035, device='cuda:0')
episode: 83 training return: tensor(351.5931, device='cuda:0')
epoch: 21 test_true_pfm: 3422.3412136408333 sim_pfm: 108.6095445882723
episode: 84 training return: tensor(383.8784, device='cuda:0')
episode: 85 training return: tensor(329.6406, device='cuda:0')
episode: 86 training return: tensor(416.2506, device='cuda:0')
episode: 87 training return: tensor(468.6618, device='cuda:0')
epoch: 22 test_true_pfm: 3371.0385370082017 sim_pfm: 371.13634985177004
episode: 88 training return: tensor(486.3001, device='cuda:0')
episode: 89 training return: tensor(442.0402, device='cuda:0')
episode: 90 training return: tensor(441.4631, device='cuda:0')
episode: 91 training return: tensor(394.0881, device='cuda:0')
epoch: 23 test_true_pfm: 3204.0001440468563 sim_pfm: 254.26083064478976
episode: 92 training return: tensor(404.7010, device='cuda:0')
episode: 93 training return: tensor(440.7616, device='cuda:0')
episode: 94 training return: tensor(159.0823, device='cuda:0')
episode: 95 training return: tensor(-255.6402, device='cuda:0')
epoch: 24 test_true_pfm: 1709.4298422077054 sim_pfm: 379.97963558216
episode: 96 training return: tensor(400.8613, device='cuda:0')
episode: 97 training return: tensor(501.1082, device='cuda:0')
episode: 98 training return: tensor(416.8850, device='cuda:0')
episode: 99 training return: tensor(414.6085, device='cuda:0')
epoch: 25 test_true_pfm: 3450.2386949012744 sim_pfm: 366.19555914467975
episode: 100 training return: tensor(226.1916, device='cuda:0')
episode: 101 training return: tensor(307.1325, device='cuda:0')
episode: 102 training return: tensor(258.1294, device='cuda:0')
episode: 103 training return: tensor(340.7161, device='cuda:0')
epoch: 26 test_true_pfm: 3311.6503082989275 sim_pfm: 397.4892952617568
episode: 104 training return: tensor(76.2218, device='cuda:0')
episode: 105 training return: tensor(549.4476, device='cuda:0')
episode: 106 training return: tensor(399.1885, device='cuda:0')
episode: 107 training return: tensor(-386.5503, device='cuda:0')
epoch: 27 test_true_pfm: 3576.583226310467 sim_pfm: 456.2571350184541
episode: 108 training return: tensor(445.0596, device='cuda:0')
episode: 109 training return: tensor(349.4541, device='cuda:0')
episode: 110 training return: tensor(-191.1627, device='cuda:0')
episode: 111 training return: tensor(313.9353, device='cuda:0')
epoch: 28 test_true_pfm: 3537.005060878939 sim_pfm: 523.1237494858409
episode: 112 training return: tensor(383.0887, device='cuda:0')
episode: 113 training return: tensor(422.2396, device='cuda:0')
episode: 114 training return: tensor(452.9512, device='cuda:0')
episode: 115 training return: tensor(323.8755, device='cuda:0')
epoch: 29 test_true_pfm: 3418.438877798168 sim_pfm: 392.45167192191974
episode: 116 training return: tensor(412.4224, device='cuda:0')
episode: 117 training return: tensor(484.6162, device='cuda:0')
episode: 118 training return: tensor(427.1216, device='cuda:0')
episode: 119 training return: tensor(471.8764, device='cuda:0')
epoch: 30 test_true_pfm: 3428.5718130969017 sim_pfm: 270.33443315828725
episode: 120 training return: tensor(281.3557, device='cuda:0')
episode: 121 training return: tensor(364.9449, device='cuda:0')
episode: 122 training return: tensor(408.7426, device='cuda:0')
episode: 123 training return: tensor(448.3083, device='cuda:0')
epoch: 31 test_true_pfm: 3487.6993037904035 sim_pfm: 445.9625862732064
episode: 124 training return: tensor(417.8045, device='cuda:0')
episode: 125 training return: tensor(481.4430, device='cuda:0')
episode: 126 training return: tensor(415.2909, device='cuda:0')
episode: 127 training return: tensor(492.3958, device='cuda:0')
epoch: 32 test_true_pfm: 3587.9591905044986 sim_pfm: 536.6333339722672
episode: 128 training return: tensor(426.2033, device='cuda:0')
episode: 129 training return: tensor(398.9993, device='cuda:0')
episode: 130 training return: tensor(457.9915, device='cuda:0')
episode: 131 training return: tensor(388.5584, device='cuda:0')
epoch: 33 test_true_pfm: 3558.515506511569 sim_pfm: 486.6886516675974
episode: 132 training return: tensor(445.5443, device='cuda:0')
episode: 133 training return: tensor(426.7883, device='cuda:0')
episode: 134 training return: tensor(-146.8972, device='cuda:0')
episode: 135 training return: tensor(-216.7068, device='cuda:0')
epoch: 34 test_true_pfm: 3185.3718214205905 sim_pfm: 450.109415711835
episode: 136 training return: tensor(421.8980, device='cuda:0')
episode: 137 training return: tensor(347.3944, device='cuda:0')
episode: 138 training return: tensor(418.7004, device='cuda:0')
episode: 139 training return: tensor(523.6109, device='cuda:0')
epoch: 35 test_true_pfm: 2960.7296717765494 sim_pfm: 576.0291164031756
episode: 140 training return: tensor(20.6261, device='cuda:0')
episode: 141 training return: tensor(433.6659, device='cuda:0')
episode: 142 training return: tensor(439.2287, device='cuda:0')
episode: 143 training return: tensor(451.2317, device='cuda:0')
epoch: 36 test_true_pfm: 3519.5972187590924 sim_pfm: 421.8741101802637
episode: 144 training return: tensor(460.8936, device='cuda:0')
episode: 145 training return: tensor(521.9274, device='cuda:0')
episode: 146 training return: tensor(424.0282, device='cuda:0')
episode: 147 training return: tensor(427.7004, device='cuda:0')
epoch: 37 test_true_pfm: 3331.861393554092 sim_pfm: 520.6794670514452
episode: 148 training return: tensor(458.6812, device='cuda:0')
episode: 149 training return: tensor(428.6500, device='cuda:0')
episode: 150 training return: tensor(436.8829, device='cuda:0')
episode: 151 training return: tensor(370.3415, device='cuda:0')
epoch: 38 test_true_pfm: 3633.294544727651 sim_pfm: 511.1301091905722
episode: 152 training return: tensor(479.2841, device='cuda:0')
episode: 153 training return: tensor(371.1077, device='cuda:0')
episode: 154 training return: tensor(404.4670, device='cuda:0')
episode: 155 training return: tensor(427.6130, device='cuda:0')
epoch: 39 test_true_pfm: 3661.76927527397 sim_pfm: 534.8368407098266
episode: 156 training return: tensor(460.6104, device='cuda:0')
episode: 157 training return: tensor(449.3854, device='cuda:0')
episode: 158 training return: tensor(451.2578, device='cuda:0')
episode: 159 training return: tensor(437.1236, device='cuda:0')
epoch: 40 test_true_pfm: 3641.452859067169 sim_pfm: 533.561319165087
episode: 160 training return: tensor(422.8767, device='cuda:0')
episode: 161 training return: tensor(472.7993, device='cuda:0')
episode: 162 training return: tensor(368.2130, device='cuda:0')
episode: 163 training return: tensor(423.2292, device='cuda:0')
epoch: 41 test_true_pfm: 3636.7146379381797 sim_pfm: 543.5890466899922
episode: 164 training return: tensor(499.0546, device='cuda:0')
episode: 165 training return: tensor(361.9340, device='cuda:0')
episode: 166 training return: tensor(471.8662, device='cuda:0')
episode: 167 training return: tensor(438.4676, device='cuda:0')
epoch: 42 test_true_pfm: 3657.5097474036334 sim_pfm: 487.12445929731865
episode: 168 training return: tensor(359.2459, device='cuda:0')
episode: 169 training return: tensor(486.8130, device='cuda:0')
episode: 170 training return: tensor(491.5938, device='cuda:0')
episode: 171 training return: tensor(479.4674, device='cuda:0')
epoch: 43 test_true_pfm: 3619.005232721689 sim_pfm: 531.6086138539637
episode: 172 training return: tensor(499.8535, device='cuda:0')
episode: 173 training return: tensor(453.7156, device='cuda:0')
episode: 174 training return: tensor(385.3132, device='cuda:0')
episode: 175 training return: tensor(-113.8118, device='cuda:0')
epoch: 44 test_true_pfm: 3462.8467171411435 sim_pfm: 535.2539873908585
episode: 176 training return: tensor(434.7639, device='cuda:0')
episode: 177 training return: tensor(518.0574, device='cuda:0')
episode: 178 training return: tensor(575.4779, device='cuda:0')
episode: 179 training return: tensor(443.3323, device='cuda:0')
epoch: 45 test_true_pfm: 3633.733580378352 sim_pfm: 527.280438517521
episode: 180 training return: tensor(522.2147, device='cuda:0')
episode: 181 training return: tensor(481.9019, device='cuda:0')
episode: 182 training return: tensor(520.5308, device='cuda:0')
episode: 183 training return: tensor(-60.9045, device='cuda:0')
epoch: 46 test_true_pfm: 3654.246342643705 sim_pfm: 527.7856972461256
episode: 184 training return: tensor(446.3768, device='cuda:0')
episode: 185 training return: tensor(484.3177, device='cuda:0')
episode: 186 training return: tensor(490.1960, device='cuda:0')
episode: 187 training return: tensor(454.8391, device='cuda:0')
epoch: 47 test_true_pfm: 3764.5216361327257 sim_pfm: 488.07306277317304
episode: 188 training return: tensor(520.6814, device='cuda:0')
episode: 189 training return: tensor(487.9914, device='cuda:0')
episode: 190 training return: tensor(506.3418, device='cuda:0')
episode: 191 training return: tensor(220.4065, device='cuda:0')
epoch: 48 test_true_pfm: 3671.6515715223773 sim_pfm: 580.1719636261696
episode: 192 training return: tensor(483.5627, device='cuda:0')
episode: 193 training return: tensor(486.2286, device='cuda:0')
episode: 194 training return: tensor(550.3661, device='cuda:0')
episode: 195 training return: tensor(378.7396, device='cuda:0')
epoch: 49 test_true_pfm: 3692.9982164229436 sim_pfm: 598.9524603247022
episode: 196 training return: tensor(458.7027, device='cuda:0')
episode: 197 training return: tensor(572.5673, device='cuda:0')
episode: 198 training return: tensor(451.6725, device='cuda:0')
episode: 199 training return: tensor(487.2585, device='cuda:0')
epoch: 50 test_true_pfm: 3644.775487058622 sim_pfm: 612.1298985183239
episode: 200 training return: tensor(486.0718, device='cuda:0')
episode: 201 training return: tensor(476.9988, device='cuda:0')
episode: 202 training return: tensor(502.3182, device='cuda:0')
episode: 203 training return: tensor(535.7466, device='cuda:0')
epoch: 51 test_true_pfm: 3677.1592091726375 sim_pfm: 582.9083832971131
episode: 204 training return: tensor(35.4902, device='cuda:0')
episode: 205 training return: tensor(509.1543, device='cuda:0')
episode: 206 training return: tensor(532.4489, device='cuda:0')
episode: 207 training return: tensor(386.7183, device='cuda:0')
epoch: 52 test_true_pfm: 3770.375007500057 sim_pfm: 578.7663304197098
episode: 208 training return: tensor(474.9200, device='cuda:0')
episode: 209 training return: tensor(449.0935, device='cuda:0')
episode: 210 training return: tensor(543.7703, device='cuda:0')
episode: 211 training return: tensor(553.2992, device='cuda:0')
epoch: 53 test_true_pfm: 3715.0511501955702 sim_pfm: 594.8375217203671
episode: 212 training return: tensor(499.0364, device='cuda:0')
episode: 213 training return: tensor(560.7153, device='cuda:0')
episode: 214 training return: tensor(470.7007, device='cuda:0')
episode: 215 training return: tensor(516.2496, device='cuda:0')
epoch: 54 test_true_pfm: 3517.6172420520793 sim_pfm: 537.0068380138837
episode: 216 training return: tensor(504.3177, device='cuda:0')
episode: 217 training return: tensor(567.5659, device='cuda:0')
episode: 218 training return: tensor(460.9856, device='cuda:0')
episode: 219 training return: tensor(441.9734, device='cuda:0')
epoch: 55 test_true_pfm: 3641.7772864465255 sim_pfm: 538.3965555454294
episode: 220 training return: tensor(473.7409, device='cuda:0')
episode: 221 training return: tensor(496.1306, device='cuda:0')
episode: 222 training return: tensor(559.6323, device='cuda:0')
episode: 223 training return: tensor(515.5405, device='cuda:0')
epoch: 56 test_true_pfm: 3635.0827622032216 sim_pfm: 551.4860803247429
episode: 224 training return: tensor(522.6912, device='cuda:0')
episode: 225 training return: tensor(453.8315, device='cuda:0')
episode: 226 training return: tensor(459.1113, device='cuda:0')
episode: 227 training return: tensor(-133.3378, device='cuda:0')
epoch: 57 test_true_pfm: 3153.5162436323244 sim_pfm: 508.9718006433298
episode: 228 training return: tensor(450.4626, device='cuda:0')
episode: 229 training return: tensor(540.6475, device='cuda:0')
episode: 230 training return: tensor(325.6750, device='cuda:0')
episode: 231 training return: tensor(386.4467, device='cuda:0')
epoch: 58 test_true_pfm: 3604.4652645597707 sim_pfm: 505.2507329670868
episode: 232 training return: tensor(470.0904, device='cuda:0')
episode: 233 training return: tensor(481.6148, device='cuda:0')
episode: 234 training return: tensor(-61.8877, device='cuda:0')
episode: 235 training return: tensor(450.9575, device='cuda:0')
epoch: 59 test_true_pfm: 3741.20529030602 sim_pfm: 595.1673737289384
episode: 236 training return: tensor(543.9982, device='cuda:0')
episode: 237 training return: tensor(519.0535, device='cuda:0')
episode: 238 training return: tensor(515.3217, device='cuda:0')
episode: 239 training return: tensor(-60.2492, device='cuda:0')
epoch: 60 test_true_pfm: 3614.671148200205 sim_pfm: 537.5883138071125
episode: 240 training return: tensor(216.9405, device='cuda:0')
episode: 241 training return: tensor(493.5941, device='cuda:0')
episode: 242 training return: tensor(486.8694, device='cuda:0')
episode: 243 training return: tensor(435.4112, device='cuda:0')
epoch: 61 test_true_pfm: 3728.6296965111796 sim_pfm: 492.2322315266356
episode: 244 training return: tensor(512.7293, device='cuda:0')
episode: 245 training return: tensor(488.2334, device='cuda:0')
episode: 246 training return: tensor(458.1440, device='cuda:0')
episode: 247 training return: tensor(497.4699, device='cuda:0')
epoch: 62 test_true_pfm: 3587.9580153832544 sim_pfm: 536.9768782065657
episode: 248 training return: tensor(500.4116, device='cuda:0')
episode: 249 training return: tensor(507.1081, device='cuda:0')
episode: 250 training return: tensor(447.1890, device='cuda:0')
episode: 251 training return: tensor(57.7951, device='cuda:0')
epoch: 63 test_true_pfm: 3613.0687126779994 sim_pfm: 552.133658261116
episode: 252 training return: tensor(504.1990, device='cuda:0')
episode: 253 training return: tensor(462.6087, device='cuda:0')
episode: 254 training return: tensor(495.7998, device='cuda:0')
episode: 255 training return: tensor(524.5832, device='cuda:0')
epoch: 64 test_true_pfm: 3551.639015652745 sim_pfm: 513.895886290508
episode: 256 training return: tensor(-45.9553, device='cuda:0')
episode: 257 training return: tensor(443.1109, device='cuda:0')
episode: 258 training return: tensor(490.5873, device='cuda:0')
episode: 259 training return: tensor(576.0690, device='cuda:0')
epoch: 65 test_true_pfm: 3720.530962775372 sim_pfm: 599.8858634408485
episode: 260 training return: tensor(567.9429, device='cuda:0')
episode: 261 training return: tensor(512.7743, device='cuda:0')
episode: 262 training return: tensor(-86.8102, device='cuda:0')
episode: 263 training return: tensor(490.2214, device='cuda:0')
epoch: 66 test_true_pfm: 3688.9524569152672 sim_pfm: 555.4413011936316
episode: 264 training return: tensor(482.3465, device='cuda:0')
episode: 265 training return: tensor(435.5250, device='cuda:0')
episode: 266 training return: tensor(441.8945, device='cuda:0')
episode: 267 training return: tensor(499.3389, device='cuda:0')
epoch: 67 test_true_pfm: 3472.303154059125 sim_pfm: 292.25171618311043
episode: 268 training return: tensor(473.6779, device='cuda:0')
episode: 269 training return: tensor(502.2620, device='cuda:0')
episode: 270 training return: tensor(475.4385, device='cuda:0')
episode: 271 training return: tensor(500.8170, device='cuda:0')
epoch: 68 test_true_pfm: 3580.48070885881 sim_pfm: 514.1427081755052
episode: 272 training return: tensor(503.3115, device='cuda:0')
episode: 273 training return: tensor(456.5563, device='cuda:0')
episode: 274 training return: tensor(459.2493, device='cuda:0')
episode: 275 training return: tensor(540.6940, device='cuda:0')
epoch: 69 test_true_pfm: 3626.6262721978687 sim_pfm: 549.5915549161533
episode: 276 training return: tensor(450.7165, device='cuda:0')
episode: 277 training return: tensor(449.1000, device='cuda:0')
episode: 278 training return: tensor(487.0464, device='cuda:0')
episode: 279 training return: tensor(473.1736, device='cuda:0')
epoch: 70 test_true_pfm: 3636.2038619886466 sim_pfm: 588.0688187920023
episode: 280 training return: tensor(426.6476, device='cuda:0')
episode: 281 training return: tensor(461.9137, device='cuda:0')
episode: 282 training return: tensor(465.9554, device='cuda:0')
episode: 283 training return: tensor(496.4380, device='cuda:0')
epoch: 71 test_true_pfm: 3690.039352025904 sim_pfm: 599.1306961625038
episode: 284 training return: tensor(495.3591, device='cuda:0')
episode: 285 training return: tensor(-156.8417, device='cuda:0')
episode: 286 training return: tensor(510.0702, device='cuda:0')
episode: 287 training return: tensor(567.0413, device='cuda:0')
epoch: 72 test_true_pfm: 3584.276427795308 sim_pfm: 539.044022209108
episode: 288 training return: tensor(489.1618, device='cuda:0')
episode: 289 training return: tensor(468.7852, device='cuda:0')
episode: 290 training return: tensor(529.0850, device='cuda:0')
episode: 291 training return: tensor(451.2029, device='cuda:0')
epoch: 73 test_true_pfm: 3646.955708663738 sim_pfm: 542.518784463619
episode: 292 training return: tensor(474.9215, device='cuda:0')
episode: 293 training return: tensor(407.2311, device='cuda:0')
episode: 294 training return: tensor(497.4019, device='cuda:0')
episode: 295 training return: tensor(496.1841, device='cuda:0')
epoch: 74 test_true_pfm: 2667.493145662387 sim_pfm: 391.4198841949401
episode: 296 training return: tensor(386.3405, device='cuda:0')
episode: 297 training return: tensor(479.6850, device='cuda:0')
episode: 298 training return: tensor(489.8844, device='cuda:0')
episode: 299 training return: tensor(531.7142, device='cuda:0')
epoch: 75 test_true_pfm: 3575.6220277406005 sim_pfm: 549.6419732520977
episode: 300 training return: tensor(439.3396, device='cuda:0')
episode: 301 training return: tensor(520.6448, device='cuda:0')
episode: 302 training return: tensor(502.8065, device='cuda:0')
episode: 303 training return: tensor(511.4015, device='cuda:0')
epoch: 76 test_true_pfm: 3632.3530732988033 sim_pfm: 488.14695077668875
episode: 304 training return: tensor(-135.4949, device='cuda:0')
episode: 305 training return: tensor(513.9295, device='cuda:0')
episode: 306 training return: tensor(569.1596, device='cuda:0')
episode: 307 training return: tensor(492.5811, device='cuda:0')
epoch: 77 test_true_pfm: 3610.9784891276863 sim_pfm: 493.9621292386437
episode: 308 training return: tensor(517.2772, device='cuda:0')
episode: 309 training return: tensor(509.2585, device='cuda:0')
episode: 310 training return: tensor(134.0155, device='cuda:0')
episode: 311 training return: tensor(487.5271, device='cuda:0')
epoch: 78 test_true_pfm: 3673.778628089802 sim_pfm: 554.3914508461021
episode: 312 training return: tensor(512.1813, device='cuda:0')
episode: 313 training return: tensor(599.7709, device='cuda:0')
episode: 314 training return: tensor(-37.1636, device='cuda:0')
episode: 315 training return: tensor(-97.2889, device='cuda:0')
epoch: 79 test_true_pfm: 3762.9801182094548 sim_pfm: 600.0724488673732
episode: 316 training return: tensor(566.6685, device='cuda:0')
episode: 317 training return: tensor(493.9268, device='cuda:0')
episode: 318 training return: tensor(613.5261, device='cuda:0')
episode: 319 training return: tensor(537.8588, device='cuda:0')
epoch: 80 test_true_pfm: 3754.4612622486416 sim_pfm: 598.1779897250235
episode: 320 training return: tensor(502.4000, device='cuda:0')
episode: 321 training return: tensor(518.9720, device='cuda:0')
episode: 322 training return: tensor(498.7528, device='cuda:0')
episode: 323 training return: tensor(-36.1454, device='cuda:0')
epoch: 81 test_true_pfm: 3638.3174250177963 sim_pfm: 528.5580446679378
episode: 324 training return: tensor(528.8408, device='cuda:0')
episode: 325 training return: tensor(-168.3088, device='cuda:0')
episode: 326 training return: tensor(546.0729, device='cuda:0')
episode: 327 training return: tensor(451.1355, device='cuda:0')
epoch: 82 test_true_pfm: 3216.6500594450804 sim_pfm: 518.3072590254791
episode: 328 training return: tensor(510.1161, device='cuda:0')
episode: 329 training return: tensor(143.6802, device='cuda:0')
episode: 330 training return: tensor(-231.0694, device='cuda:0')
episode: 331 training return: tensor(529.1066, device='cuda:0')
epoch: 83 test_true_pfm: 3638.5466316404268 sim_pfm: 535.0660812230781
episode: 332 training return: tensor(474.5786, device='cuda:0')
episode: 333 training return: tensor(229.9893, device='cuda:0')
episode: 334 training return: tensor(499.2345, device='cuda:0')
episode: 335 training return: tensor(486.3699, device='cuda:0')
epoch: 84 test_true_pfm: 3707.431772702584 sim_pfm: 623.7782479387824
episode: 336 training return: tensor(534.3240, device='cuda:0')
episode: 337 training return: tensor(427.0242, device='cuda:0')
episode: 338 training return: tensor(483.2857, device='cuda:0')
episode: 339 training return: tensor(532.3184, device='cuda:0')
epoch: 85 test_true_pfm: 3625.673342211316 sim_pfm: 567.134245383398
episode: 340 training return: tensor(534.3514, device='cuda:0')
episode: 341 training return: tensor(438.5218, device='cuda:0')
episode: 342 training return: tensor(409.4149, device='cuda:0')
episode: 343 training return: tensor(485.5746, device='cuda:0')
epoch: 86 test_true_pfm: 3305.3335716269776 sim_pfm: 506.75723585882224
episode: 344 training return: tensor(478.0137, device='cuda:0')
episode: 345 training return: tensor(426.9915, device='cuda:0')
episode: 346 training return: tensor(-25.2672, device='cuda:0')
episode: 347 training return: tensor(488.5086, device='cuda:0')
epoch: 87 test_true_pfm: 3655.759338295358 sim_pfm: 496.00924560870044
episode: 348 training return: tensor(520.4248, device='cuda:0')
episode: 349 training return: tensor(421.6838, device='cuda:0')
episode: 350 training return: tensor(467.2737, device='cuda:0')
episode: 351 training return: tensor(473.5681, device='cuda:0')
epoch: 88 test_true_pfm: 3580.7878414550555 sim_pfm: 544.4644569906717
episode: 352 training return: tensor(460.2554, device='cuda:0')
episode: 353 training return: tensor(474.4187, device='cuda:0')
episode: 354 training return: tensor(531.5354, device='cuda:0')
episode: 355 training return: tensor(467.5089, device='cuda:0')
epoch: 89 test_true_pfm: 3662.8706012497387 sim_pfm: 551.043302929184
episode: 356 training return: tensor(442.0307, device='cuda:0')
episode: 357 training return: tensor(452.4563, device='cuda:0')
episode: 358 training return: tensor(482.0433, device='cuda:0')
episode: 359 training return: tensor(474.0560, device='cuda:0')
epoch: 90 test_true_pfm: 3505.69661674891 sim_pfm: 558.860336893859
episode: 360 training return: tensor(488.4475, device='cuda:0')
episode: 361 training return: tensor(222.9361, device='cuda:0')
episode: 362 training return: tensor(452.6037, device='cuda:0')
episode: 363 training return: tensor(502.1982, device='cuda:0')
epoch: 91 test_true_pfm: 3581.1027815378516 sim_pfm: 509.14222325795953
episode: 364 training return: tensor(505.0442, device='cuda:0')
episode: 365 training return: tensor(505.0063, device='cuda:0')
episode: 366 training return: tensor(463.0063, device='cuda:0')
episode: 367 training return: tensor(384.4323, device='cuda:0')
epoch: 92 test_true_pfm: 2912.506422218426 sim_pfm: 416.87650642567314
episode: 368 training return: tensor(510.1864, device='cuda:0')
episode: 369 training return: tensor(450.7376, device='cuda:0')
episode: 370 training return: tensor(448.4863, device='cuda:0')
episode: 371 training return: tensor(361.5901, device='cuda:0')
epoch: 93 test_true_pfm: 3534.457000014252 sim_pfm: 480.73008091771044
episode: 372 training return: tensor(431.9445, device='cuda:0')
episode: 373 training return: tensor(462.2382, device='cuda:0')
episode: 374 training return: tensor(490.1413, device='cuda:0')
episode: 375 training return: tensor(527.7065, device='cuda:0')
epoch: 94 test_true_pfm: 3624.738487322172 sim_pfm: 546.7802671387714
episode: 376 training return: tensor(440.7977, device='cuda:0')
episode: 377 training return: tensor(569.5154, device='cuda:0')
episode: 378 training return: tensor(527.5624, device='cuda:0')
episode: 379 training return: tensor(504.4681, device='cuda:0')
epoch: 95 test_true_pfm: 3675.262057654699 sim_pfm: 569.8125500002255
episode: 380 training return: tensor(523.3638, device='cuda:0')
episode: 381 training return: tensor(473.2751, device='cuda:0')
episode: 382 training return: tensor(525.2947, device='cuda:0')
episode: 383 training return: tensor(560.6915, device='cuda:0')
epoch: 96 test_true_pfm: 3572.419269423826 sim_pfm: 545.8187551343193
episode: 384 training return: tensor(482.7556, device='cuda:0')
episode: 385 training return: tensor(518.6556, device='cuda:0')
episode: 386 training return: tensor(466.9358, device='cuda:0')
episode: 387 training return: tensor(500.0206, device='cuda:0')
epoch: 97 test_true_pfm: 3687.717180677915 sim_pfm: 562.3227827290539
episode: 388 training return: tensor(420.2339, device='cuda:0')
episode: 389 training return: tensor(469.9943, device='cuda:0')
episode: 390 training return: tensor(490.7523, device='cuda:0')
episode: 391 training return: tensor(535.9822, device='cuda:0')
epoch: 98 test_true_pfm: 3766.215444354759 sim_pfm: 610.7520711594261
episode: 392 training return: tensor(482.0905, device='cuda:0')
episode: 393 training return: tensor(487.1282, device='cuda:0')
episode: 394 training return: tensor(503.0772, device='cuda:0')
episode: 395 training return: tensor(437.6147, device='cuda:0')
epoch: 99 test_true_pfm: 3731.764401056391 sim_pfm: 590.4079840147557
episode: 396 training return: tensor(515.8126, device='cuda:0')
episode: 397 training return: tensor(544.1117, device='cuda:0')
episode: 398 training return: tensor(471.1819, device='cuda:0')
episode: 399 training return: tensor(510.6440, device='cuda:0')
epoch: 100 test_true_pfm: 3656.4355361630733 sim_pfm: 526.9655306315593
episode: 400 training return: tensor(493.1873, device='cuda:0')
episode: 401 training return: tensor(497.5550, device='cuda:0')
episode: 402 training return: tensor(523.6063, device='cuda:0')
episode: 403 training return: tensor(546.7753, device='cuda:0')
epoch: 101 test_true_pfm: 3661.465866306929 sim_pfm: 576.1574936786977
episode: 404 training return: tensor(127.4784, device='cuda:0')
episode: 405 training return: tensor(48.9317, device='cuda:0')
episode: 406 training return: tensor(477.8722, device='cuda:0')
episode: 407 training return: tensor(456.7285, device='cuda:0')
epoch: 102 test_true_pfm: 3648.5038987798857 sim_pfm: 531.9634127776759
episode: 408 training return: tensor(487.1194, device='cuda:0')
episode: 409 training return: tensor(418.1656, device='cuda:0')
episode: 410 training return: tensor(447.1088, device='cuda:0')
episode: 411 training return: tensor(502.5206, device='cuda:0')
epoch: 103 test_true_pfm: 3690.337412631008 sim_pfm: 561.5051421149789
episode: 412 training return: tensor(498.2241, device='cuda:0')
episode: 413 training return: tensor(556.5211, device='cuda:0')
episode: 414 training return: tensor(488.9166, device='cuda:0')
episode: 415 training return: tensor(488.3401, device='cuda:0')
epoch: 104 test_true_pfm: 3744.9059397785973 sim_pfm: 580.334810382997
episode: 416 training return: tensor(473.9613, device='cuda:0')
episode: 417 training return: tensor(511.8516, device='cuda:0')
episode: 418 training return: tensor(478.3185, device='cuda:0')
episode: 419 training return: tensor(478.2428, device='cuda:0')
epoch: 105 test_true_pfm: 3739.3001957498714 sim_pfm: 618.4951456154231
episode: 420 training return: tensor(498.5219, device='cuda:0')
episode: 421 training return: tensor(517.7600, device='cuda:0')
episode: 422 training return: tensor(520.0257, device='cuda:0')
episode: 423 training return: tensor(515.1053, device='cuda:0')
epoch: 106 test_true_pfm: 3739.609485518123 sim_pfm: 625.1139024496078
episode: 424 training return: tensor(540.1980, device='cuda:0')
episode: 425 training return: tensor(555.3451, device='cuda:0')
episode: 426 training return: tensor(507.2364, device='cuda:0')
episode: 427 training return: tensor(513.0215, device='cuda:0')
epoch: 107 test_true_pfm: 3613.3043977817492 sim_pfm: 512.7033260238823
episode: 428 training return: tensor(509.6766, device='cuda:0')
episode: 429 training return: tensor(515.1226, device='cuda:0')
episode: 430 training return: tensor(571.1185, device='cuda:0')
episode: 431 training return: tensor(555.1725, device='cuda:0')
epoch: 108 test_true_pfm: 3690.6180991380884 sim_pfm: 578.9217054260274
episode: 432 training return: tensor(511.3918, device='cuda:0')
episode: 433 training return: tensor(487.2432, device='cuda:0')
episode: 434 training return: tensor(489.3400, device='cuda:0')
episode: 435 training return: tensor(479.1488, device='cuda:0')
epoch: 109 test_true_pfm: 3762.7153582946726 sim_pfm: 625.3366760433031
episode: 436 training return: tensor(442.6369, device='cuda:0')
episode: 437 training return: tensor(485.4438, device='cuda:0')
episode: 438 training return: tensor(467.2364, device='cuda:0')
episode: 439 training return: tensor(525.2767, device='cuda:0')
epoch: 110 test_true_pfm: 3717.591692659142 sim_pfm: 603.8436668951375
episode: 440 training return: tensor(599.4500, device='cuda:0')
episode: 441 training return: tensor(489.1678, device='cuda:0')
episode: 442 training return: tensor(645.3254, device='cuda:0')
episode: 443 training return: tensor(557.0038, device='cuda:0')
epoch: 111 test_true_pfm: 3747.8181032102293 sim_pfm: 615.0917006377131
episode: 444 training return: tensor(529.1862, device='cuda:0')
episode: 445 training return: tensor(587.4677, device='cuda:0')
episode: 446 training return: tensor(467.2182, device='cuda:0')
episode: 447 training return: tensor(527.8577, device='cuda:0')
epoch: 112 test_true_pfm: 3717.2202343195713 sim_pfm: 594.8042693079333
episode: 448 training return: tensor(482.7095, device='cuda:0')
episode: 449 training return: tensor(522.2422, device='cuda:0')
episode: 450 training return: tensor(352.9711, device='cuda:0')
episode: 451 training return: tensor(549.1407, device='cuda:0')
epoch: 113 test_true_pfm: 3734.1450509809324 sim_pfm: 579.077858332758
episode: 452 training return: tensor(450.7280, device='cuda:0')
episode: 453 training return: tensor(508.2447, device='cuda:0')
episode: 454 training return: tensor(593.6570, device='cuda:0')
episode: 455 training return: tensor(452.1357, device='cuda:0')
epoch: 114 test_true_pfm: 3696.4312523213266 sim_pfm: 572.3571118020142
episode: 456 training return: tensor(502.5587, device='cuda:0')
episode: 457 training return: tensor(511.9573, device='cuda:0')
episode: 458 training return: tensor(492.8398, device='cuda:0')
episode: 459 training return: tensor(525.7175, device='cuda:0')
epoch: 115 test_true_pfm: 3697.5318623549524 sim_pfm: 581.1885116915606
episode: 460 training return: tensor(483.6382, device='cuda:0')
episode: 461 training return: tensor(540.9277, device='cuda:0')
episode: 462 training return: tensor(520.3275, device='cuda:0')
episode: 463 training return: tensor(510.0716, device='cuda:0')
epoch: 116 test_true_pfm: 3702.8811185870177 sim_pfm: 583.1850882597888
episode: 464 training return: tensor(452.9754, device='cuda:0')
episode: 465 training return: tensor(498.9849, device='cuda:0')
episode: 466 training return: tensor(491.8346, device='cuda:0')
episode: 467 training return: tensor(519.3307, device='cuda:0')
epoch: 117 test_true_pfm: 3641.348226310072 sim_pfm: 560.2025220502788
episode: 468 training return: tensor(434.7743, device='cuda:0')
episode: 469 training return: tensor(458.6786, device='cuda:0')
episode: 470 training return: tensor(478.9549, device='cuda:0')
episode: 471 training return: tensor(505.1762, device='cuda:0')
epoch: 118 test_true_pfm: 3801.911848373677 sim_pfm: 625.4139131012683
episode: 472 training return: tensor(570.5032, device='cuda:0')
episode: 473 training return: tensor(476.7959, device='cuda:0')
episode: 474 training return: tensor(503.2464, device='cuda:0')
episode: 475 training return: tensor(529.2798, device='cuda:0')
epoch: 119 test_true_pfm: 3772.5841341982755 sim_pfm: 594.6177590287989
episode: 476 training return: tensor(591.3682, device='cuda:0')
episode: 477 training return: tensor(507.8275, device='cuda:0')
episode: 478 training return: tensor(473.1213, device='cuda:0')
episode: 479 training return: tensor(496.7505, device='cuda:0')
epoch: 120 test_true_pfm: 3761.952858262681 sim_pfm: 617.4328828804815
episode: 480 training return: tensor(509.9178, device='cuda:0')
episode: 481 training return: tensor(503.1143, device='cuda:0')
episode: 482 training return: tensor(505.5081, device='cuda:0')
episode: 483 training return: tensor(522.1777, device='cuda:0')
epoch: 121 test_true_pfm: 3703.600457034024 sim_pfm: 597.2235706390251
episode: 484 training return: tensor(524.9601, device='cuda:0')
episode: 485 training return: tensor(507.8823, device='cuda:0')
episode: 486 training return: tensor(498.4850, device='cuda:0')
episode: 487 training return: tensor(502.8187, device='cuda:0')
epoch: 122 test_true_pfm: 3738.68513652786 sim_pfm: 609.5973347766945
episode: 488 training return: tensor(497.3564, device='cuda:0')
episode: 489 training return: tensor(519.9090, device='cuda:0')
episode: 490 training return: tensor(542.5762, device='cuda:0')
episode: 491 training return: tensor(486.7052, device='cuda:0')
epoch: 123 test_true_pfm: 3613.3087872901997 sim_pfm: 562.1175090521574
episode: 492 training return: tensor(488.3865, device='cuda:0')
episode: 493 training return: tensor(336.9181, device='cuda:0')
episode: 494 training return: tensor(523.4286, device='cuda:0')
episode: 495 training return: tensor(559.8667, device='cuda:0')
epoch: 124 test_true_pfm: 3789.647005537184 sim_pfm: 623.9011403543409
episode: 496 training return: tensor(521.0231, device='cuda:0')
episode: 497 training return: tensor(580.5616, device='cuda:0')
episode: 498 training return: tensor(580.6855, device='cuda:0')
episode: 499 training return: tensor(484.3084, device='cuda:0')
epoch: 125 test_true_pfm: 3676.5446797755735 sim_pfm: 582.8326022713445
episode: 500 training return: tensor(535.8389, device='cuda:0')
episode: 501 training return: tensor(487.4720, device='cuda:0')
episode: 502 training return: tensor(491.7766, device='cuda:0')
episode: 503 training return: tensor(496.5085, device='cuda:0')
epoch: 126 test_true_pfm: 3626.624867250597 sim_pfm: 552.7452229276241
episode: 504 training return: tensor(545.5242, device='cuda:0')
episode: 505 training return: tensor(477.9610, device='cuda:0')
episode: 506 training return: tensor(553.2977, device='cuda:0')
episode: 507 training return: tensor(537.0007, device='cuda:0')
epoch: 127 test_true_pfm: 3705.373531462652 sim_pfm: 630.8040212450238
episode: 508 training return: tensor(470.1433, device='cuda:0')
episode: 509 training return: tensor(514.2155, device='cuda:0')
episode: 510 training return: tensor(505.1605, device='cuda:0')
episode: 511 training return: tensor(498.1996, device='cuda:0')
epoch: 128 test_true_pfm: 3736.2801842135523 sim_pfm: 583.9656553656483
episode: 512 training return: tensor(563.4887, device='cuda:0')
episode: 513 training return: tensor(530.0174, device='cuda:0')
episode: 514 training return: tensor(434.4384, device='cuda:0')
episode: 515 training return: tensor(522.9149, device='cuda:0')
epoch: 129 test_true_pfm: 3744.7043487214482 sim_pfm: 595.7179930070415
episode: 516 training return: tensor(551.6390, device='cuda:0')
episode: 517 training return: tensor(471.9722, device='cuda:0')
episode: 518 training return: tensor(523.3372, device='cuda:0')
episode: 519 training return: tensor(590.4104, device='cuda:0')
epoch: 130 test_true_pfm: 3678.717831384793 sim_pfm: 576.5284167956561
episode: 520 training return: tensor(537.9589, device='cuda:0')
episode: 521 training return: tensor(472.6169, device='cuda:0')
episode: 522 training return: tensor(545.5150, device='cuda:0')
episode: 523 training return: tensor(534.1902, device='cuda:0')
epoch: 131 test_true_pfm: 3766.8472377031853 sim_pfm: 630.4560250899134
episode: 524 training return: tensor(535.2031, device='cuda:0')
episode: 525 training return: tensor(544.1008, device='cuda:0')
episode: 526 training return: tensor(522.7123, device='cuda:0')
episode: 527 training return: tensor(514.5426, device='cuda:0')
epoch: 132 test_true_pfm: 3741.293816516117 sim_pfm: 640.2296749129891
episode: 528 training return: tensor(582.5132, device='cuda:0')
episode: 529 training return: tensor(540.2184, device='cuda:0')
episode: 530 training return: tensor(551.1727, device='cuda:0')
episode: 531 training return: tensor(531.9816, device='cuda:0')
epoch: 133 test_true_pfm: 3767.542777832974 sim_pfm: 599.2524713753179
episode: 532 training return: tensor(473.3189, device='cuda:0')
episode: 533 training return: tensor(495.0708, device='cuda:0')
episode: 534 training return: tensor(458.0255, device='cuda:0')
episode: 535 training return: tensor(499.4839, device='cuda:0')
epoch: 134 test_true_pfm: 3622.1218198633146 sim_pfm: 571.5879646120593
episode: 536 training return: tensor(560.8507, device='cuda:0')
episode: 537 training return: tensor(472.2198, device='cuda:0')
episode: 538 training return: tensor(528.4697, device='cuda:0')
episode: 539 training return: tensor(544.6112, device='cuda:0')
epoch: 135 test_true_pfm: 3700.5524032611415 sim_pfm: 575.698922503662
episode: 540 training return: tensor(485.1719, device='cuda:0')
episode: 541 training return: tensor(578.4565, device='cuda:0')
episode: 542 training return: tensor(466.4060, device='cuda:0')
episode: 543 training return: tensor(505.4987, device='cuda:0')
epoch: 136 test_true_pfm: 3675.48409821832 sim_pfm: 538.6306130701172
episode: 544 training return: tensor(577.2460, device='cuda:0')
episode: 545 training return: tensor(518.9535, device='cuda:0')
episode: 546 training return: tensor(514.2129, device='cuda:0')
episode: 547 training return: tensor(501.8514, device='cuda:0')
epoch: 137 test_true_pfm: 3743.2913339674365 sim_pfm: 602.561521824527
episode: 548 training return: tensor(508.4440, device='cuda:0')
episode: 549 training return: tensor(401.6324, device='cuda:0')
episode: 550 training return: tensor(475.9424, device='cuda:0')
episode: 551 training return: tensor(504.5777, device='cuda:0')
epoch: 138 test_true_pfm: 3687.7129744480894 sim_pfm: 532.5918990476833
episode: 552 training return: tensor(468.8618, device='cuda:0')
episode: 553 training return: tensor(532.4183, device='cuda:0')
episode: 554 training return: tensor(515.8257, device='cuda:0')
episode: 555 training return: tensor(506.3201, device='cuda:0')
epoch: 139 test_true_pfm: 3742.7154998711508 sim_pfm: 608.7316241467294
episode: 556 training return: tensor(537.2231, device='cuda:0')
episode: 557 training return: tensor(549.1138, device='cuda:0')
episode: 558 training return: tensor(545.0543, device='cuda:0')
episode: 559 training return: tensor(512.9164, device='cuda:0')
epoch: 140 test_true_pfm: 3760.347567529186 sim_pfm: 627.5631625448974
episode: 560 training return: tensor(516.3912, device='cuda:0')
episode: 561 training return: tensor(499.1125, device='cuda:0')
episode: 562 training return: tensor(552.8967, device='cuda:0')
episode: 563 training return: tensor(500.4845, device='cuda:0')
epoch: 141 test_true_pfm: 3663.617216099787 sim_pfm: 554.9223304361027
episode: 564 training return: tensor(527.9038, device='cuda:0')
episode: 565 training return: tensor(586.7935, device='cuda:0')
episode: 566 training return: tensor(544.4073, device='cuda:0')
episode: 567 training return: tensor(576.6000, device='cuda:0')
epoch: 142 test_true_pfm: 3742.457240604966 sim_pfm: 608.875359630833
episode: 568 training return: tensor(537.3134, device='cuda:0')
episode: 569 training return: tensor(505.7559, device='cuda:0')
episode: 570 training return: tensor(507.4994, device='cuda:0')
episode: 571 training return: tensor(519.5980, device='cuda:0')
epoch: 143 test_true_pfm: 3724.492892494707 sim_pfm: 579.6991496297996
episode: 572 training return: tensor(468.6249, device='cuda:0')
episode: 573 training return: tensor(483.0858, device='cuda:0')
episode: 574 training return: tensor(520.6028, device='cuda:0')
episode: 575 training return: tensor(592.1180, device='cuda:0')
epoch: 144 test_true_pfm: 3696.637957185901 sim_pfm: 580.9713873810446
episode: 576 training return: tensor(532.6558, device='cuda:0')
episode: 577 training return: tensor(500.4574, device='cuda:0')
episode: 578 training return: tensor(541.6010, device='cuda:0')
episode: 579 training return: tensor(532.6143, device='cuda:0')
epoch: 145 test_true_pfm: 3637.192618349811 sim_pfm: 561.2204108453589
episode: 580 training return: tensor(552.6780, device='cuda:0')
episode: 581 training return: tensor(493.7964, device='cuda:0')
episode: 582 training return: tensor(528.9292, device='cuda:0')
episode: 583 training return: tensor(506.5386, device='cuda:0')
epoch: 146 test_true_pfm: 3766.1779884596194 sim_pfm: 621.191269584621
episode: 584 training return: tensor(521.0695, device='cuda:0')
episode: 585 training return: tensor(569.7467, device='cuda:0')
episode: 586 training return: tensor(536.5011, device='cuda:0')
episode: 587 training return: tensor(540.0002, device='cuda:0')
epoch: 147 test_true_pfm: 3638.450134499462 sim_pfm: 542.9347667732121
episode: 588 training return: tensor(591.9565, device='cuda:0')
episode: 589 training return: tensor(601.2264, device='cuda:0')
episode: 590 training return: tensor(512.8968, device='cuda:0')
episode: 591 training return: tensor(468.8463, device='cuda:0')
epoch: 148 test_true_pfm: 3763.7395167193613 sim_pfm: 612.0982393527714
episode: 592 training return: tensor(540.5240, device='cuda:0')
episode: 593 training return: tensor(526.5124, device='cuda:0')
episode: 594 training return: tensor(446.7312, device='cuda:0')
episode: 595 training return: tensor(470.9296, device='cuda:0')
epoch: 149 test_true_pfm: 3718.067234039189 sim_pfm: 595.7526701319342
episode: 596 training return: tensor(562.0057, device='cuda:0')
episode: 597 training return: tensor(495.2334, device='cuda:0')
episode: 598 training return: tensor(490.6363, device='cuda:0')
episode: 599 training return: tensor(501.9538, device='cuda:0')
epoch: 150 test_true_pfm: 3797.3504677411233 sim_pfm: 647.7478385535069
