['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'behavior', '--traj', 'medium', '--seed', '1', '--data', '100000', '--regu', '0.3']
5135.460775783178
episode: 0 training return: tensor(-467.8752, device='cuda:0')
episode: 1 training return: tensor(-370.4119, device='cuda:0')
episode: 2 training return: tensor(-328.1346, device='cuda:0')
episode: 3 training return: tensor(-424.6840, device='cuda:0')
epoch: 1 test_true_pfm: 3664.656264779434 sim_pfm: -110.17179385113802
episode: 4 training return: tensor(-292.0044, device='cuda:0')
episode: 5 training return: tensor(-417.3035, device='cuda:0')
episode: 6 training return: tensor(-437.7296, device='cuda:0')
episode: 7 training return: tensor(-387.9224, device='cuda:0')
epoch: 2 test_true_pfm: 4841.541995095755 sim_pfm: -72.1788405487702
episode: 8 training return: tensor(-319.5011, device='cuda:0')
episode: 9 training return: tensor(-221.0616, device='cuda:0')
episode: 10 training return: tensor(-230.3306, device='cuda:0')
episode: 11 training return: tensor(-207.7192, device='cuda:0')
epoch: 3 test_true_pfm: 4829.505947209329 sim_pfm: -299.02373456332134
episode: 12 training return: tensor(-162.2793, device='cuda:0')
episode: 13 training return: tensor(-237.0089, device='cuda:0')
episode: 14 training return: tensor(-143.0396, device='cuda:0')
episode: 15 training return: tensor(-281.8249, device='cuda:0')
epoch: 4 test_true_pfm: 5008.262431549896 sim_pfm: 36.88264567596101
episode: 16 training return: tensor(-301.0648, device='cuda:0')
episode: 17 training return: tensor(-330.8442, device='cuda:0')
episode: 18 training return: tensor(-130.0046, device='cuda:0')
episode: 19 training return: tensor(-935.5255, device='cuda:0')
epoch: 5 test_true_pfm: 5052.328390895896 sim_pfm: 14.079719507368281
episode: 20 training return: tensor(-148.5920, device='cuda:0')
episode: 21 training return: tensor(-34.7280, device='cuda:0')
episode: 22 training return: tensor(-154.5313, device='cuda:0')
episode: 23 training return: tensor(0.8024, device='cuda:0')
epoch: 6 test_true_pfm: 5016.381759825283 sim_pfm: 193.01359724856835
episode: 24 training return: tensor(-99.7346, device='cuda:0')
episode: 25 training return: tensor(-176.6097, device='cuda:0')
episode: 26 training return: tensor(-247.6026, device='cuda:0')
episode: 27 training return: tensor(-36.0110, device='cuda:0')
epoch: 7 test_true_pfm: 5088.5952042339695 sim_pfm: 127.09564093127847
episode: 28 training return: tensor(-34.9099, device='cuda:0')
episode: 29 training return: tensor(-57.5778, device='cuda:0')
episode: 30 training return: tensor(-50.9395, device='cuda:0')
episode: 31 training return: tensor(-63.4679, device='cuda:0')
epoch: 8 test_true_pfm: 5291.972242171558 sim_pfm: 157.5367652021038
episode: 32 training return: tensor(-131.4744, device='cuda:0')
episode: 33 training return: tensor(-14.6101, device='cuda:0')
episode: 34 training return: tensor(31.2435, device='cuda:0')
episode: 35 training return: tensor(-126.3805, device='cuda:0')
epoch: 9 test_true_pfm: 5290.204662110631 sim_pfm: 47.45252426511919
episode: 36 training return: tensor(-101.9979, device='cuda:0')
episode: 37 training return: tensor(-130.0208, device='cuda:0')
episode: 38 training return: tensor(-111.2422, device='cuda:0')
episode: 39 training return: tensor(-24.6579, device='cuda:0')
epoch: 10 test_true_pfm: 5263.2200529472875 sim_pfm: 238.61775986799816
episode: 40 training return: tensor(-82.2296, device='cuda:0')
episode: 41 training return: tensor(6.2151, device='cuda:0')
episode: 42 training return: tensor(51.6460, device='cuda:0')
episode: 43 training return: tensor(-135.3098, device='cuda:0')
epoch: 11 test_true_pfm: 5340.425572395983 sim_pfm: 265.81399518911104
episode: 44 training return: tensor(61.2602, device='cuda:0')
episode: 45 training return: tensor(-73.5279, device='cuda:0')
episode: 46 training return: tensor(98.2562, device='cuda:0')
episode: 47 training return: tensor(0.9732, device='cuda:0')
epoch: 12 test_true_pfm: 5334.513042876085 sim_pfm: 302.75211566178285
episode: 48 training return: tensor(210.7530, device='cuda:0')
episode: 49 training return: tensor(91.4138, device='cuda:0')
episode: 50 training return: tensor(-564.5222, device='cuda:0')
episode: 51 training return: tensor(-726.2941, device='cuda:0')
epoch: 13 test_true_pfm: 5402.742098669272 sim_pfm: 305.0534469045039
episode: 52 training return: tensor(23.5411, device='cuda:0')
episode: 53 training return: tensor(90.6017, device='cuda:0')
episode: 54 training return: tensor(141.7461, device='cuda:0')
episode: 55 training return: tensor(82.5647, device='cuda:0')
epoch: 14 test_true_pfm: 5415.836193148965 sim_pfm: 338.4666329292231
episode: 56 training return: tensor(-6.7649, device='cuda:0')
episode: 57 training return: tensor(52.0041, device='cuda:0')
episode: 58 training return: tensor(109.9216, device='cuda:0')
episode: 59 training return: tensor(99.7954, device='cuda:0')
epoch: 15 test_true_pfm: 5410.635569421338 sim_pfm: 295.5544407707251
episode: 60 training return: tensor(125.3066, device='cuda:0')
episode: 61 training return: tensor(214.1387, device='cuda:0')
episode: 62 training return: tensor(128.2991, device='cuda:0')
episode: 63 training return: tensor(172.3813, device='cuda:0')
epoch: 16 test_true_pfm: 5576.333040442997 sim_pfm: 376.7678881132936
episode: 64 training return: tensor(172.5806, device='cuda:0')
episode: 65 training return: tensor(51.7227, device='cuda:0')
episode: 66 training return: tensor(109.5967, device='cuda:0')
episode: 67 training return: tensor(121.4879, device='cuda:0')
epoch: 17 test_true_pfm: 5599.037387465079 sim_pfm: 386.42041100747883
episode: 68 training return: tensor(170.0960, device='cuda:0')
episode: 69 training return: tensor(124.5968, device='cuda:0')
episode: 70 training return: tensor(117.7823, device='cuda:0')
episode: 71 training return: tensor(221.2939, device='cuda:0')
epoch: 18 test_true_pfm: 5569.160963710776 sim_pfm: 457.1711057333353
episode: 72 training return: tensor(205.1089, device='cuda:0')
episode: 73 training return: tensor(183.5057, device='cuda:0')
episode: 74 training return: tensor(198.5509, device='cuda:0')
episode: 75 training return: tensor(279.1922, device='cuda:0')
epoch: 19 test_true_pfm: 5453.583505395019 sim_pfm: 415.67962995969964
episode: 76 training return: tensor(267.3999, device='cuda:0')
episode: 77 training return: tensor(219.2944, device='cuda:0')
episode: 78 training return: tensor(219.6495, device='cuda:0')
episode: 79 training return: tensor(266.1154, device='cuda:0')
epoch: 20 test_true_pfm: 5641.872593009576 sim_pfm: 426.24908824002097
episode: 80 training return: tensor(227.0705, device='cuda:0')
episode: 81 training return: tensor(228.5378, device='cuda:0')
episode: 82 training return: tensor(160.7565, device='cuda:0')
episode: 83 training return: tensor(134.4353, device='cuda:0')
epoch: 21 test_true_pfm: 5696.550205214576 sim_pfm: 412.62103621006827
episode: 84 training return: tensor(310.2608, device='cuda:0')
episode: 85 training return: tensor(275.2310, device='cuda:0')
episode: 86 training return: tensor(396.2256, device='cuda:0')
episode: 87 training return: tensor(218.8580, device='cuda:0')
epoch: 22 test_true_pfm: 5764.28027764663 sim_pfm: 521.4284888431042
episode: 88 training return: tensor(229.9685, device='cuda:0')
episode: 89 training return: tensor(202.2179, device='cuda:0')
episode: 90 training return: tensor(214.6488, device='cuda:0')
episode: 91 training return: tensor(322.4295, device='cuda:0')
epoch: 23 test_true_pfm: 5700.111702218562 sim_pfm: 485.38942887212033
episode: 92 training return: tensor(158.1821, device='cuda:0')
episode: 93 training return: tensor(204.8823, device='cuda:0')
episode: 94 training return: tensor(126.4823, device='cuda:0')
episode: 95 training return: tensor(284.6427, device='cuda:0')
epoch: 24 test_true_pfm: 5695.950148744799 sim_pfm: 478.6428055157885
episode: 96 training return: tensor(199.7865, device='cuda:0')
episode: 97 training return: tensor(270.1747, device='cuda:0')
episode: 98 training return: tensor(322.7287, device='cuda:0')
episode: 99 training return: tensor(253.8482, device='cuda:0')
epoch: 25 test_true_pfm: 5642.277596098121 sim_pfm: 476.8658144515939
episode: 100 training return: tensor(306.8002, device='cuda:0')
episode: 101 training return: tensor(268.1730, device='cuda:0')
episode: 102 training return: tensor(233.6611, device='cuda:0')
episode: 103 training return: tensor(215.8586, device='cuda:0')
epoch: 26 test_true_pfm: 5693.573048560423 sim_pfm: 475.0574975929533
episode: 104 training return: tensor(241.2576, device='cuda:0')
episode: 105 training return: tensor(336.4552, device='cuda:0')
episode: 106 training return: tensor(335.3130, device='cuda:0')
episode: 107 training return: tensor(343.9551, device='cuda:0')
epoch: 27 test_true_pfm: 5642.224989390542 sim_pfm: 430.83695278384647
episode: 108 training return: tensor(269.7368, device='cuda:0')
episode: 109 training return: tensor(235.0961, device='cuda:0')
episode: 110 training return: tensor(333.2032, device='cuda:0')
episode: 111 training return: tensor(260.8619, device='cuda:0')
epoch: 28 test_true_pfm: 5665.457146595621 sim_pfm: 490.2764095874348
episode: 112 training return: tensor(282.3260, device='cuda:0')
episode: 113 training return: tensor(361.7035, device='cuda:0')
episode: 114 training return: tensor(351.6075, device='cuda:0')
episode: 115 training return: tensor(336.7552, device='cuda:0')
epoch: 29 test_true_pfm: 5853.230192983526 sim_pfm: 526.7564304851306
episode: 116 training return: tensor(390.1756, device='cuda:0')
episode: 117 training return: tensor(306.0591, device='cuda:0')
episode: 118 training return: tensor(354.9081, device='cuda:0')
episode: 119 training return: tensor(389.5048, device='cuda:0')
epoch: 30 test_true_pfm: 5796.356006626523 sim_pfm: 458.9791386573149
episode: 120 training return: tensor(312.2738, device='cuda:0')
episode: 121 training return: tensor(337.4993, device='cuda:0')
episode: 122 training return: tensor(404.3651, device='cuda:0')
episode: 123 training return: tensor(310.0904, device='cuda:0')
epoch: 31 test_true_pfm: 5919.527898967307 sim_pfm: 586.7571780808115
episode: 124 training return: tensor(309.9073, device='cuda:0')
episode: 125 training return: tensor(270.5803, device='cuda:0')
episode: 126 training return: tensor(385.7201, device='cuda:0')
episode: 127 training return: tensor(330.1558, device='cuda:0')
epoch: 32 test_true_pfm: 5891.498403078807 sim_pfm: 594.6739236645711
episode: 128 training return: tensor(283.3514, device='cuda:0')
episode: 129 training return: tensor(299.1471, device='cuda:0')
episode: 130 training return: tensor(426.9637, device='cuda:0')
episode: 131 training return: tensor(338.6633, device='cuda:0')
epoch: 33 test_true_pfm: 5873.3067902745315 sim_pfm: 496.7406913442537
episode: 132 training return: tensor(453.8833, device='cuda:0')
episode: 133 training return: tensor(349.9618, device='cuda:0')
episode: 134 training return: tensor(270.9485, device='cuda:0')
episode: 135 training return: tensor(316.3859, device='cuda:0')
epoch: 34 test_true_pfm: 5948.208984686319 sim_pfm: 565.6351752964352
episode: 136 training return: tensor(402.5567, device='cuda:0')
episode: 137 training return: tensor(363.6505, device='cuda:0')
episode: 138 training return: tensor(413.9070, device='cuda:0')
episode: 139 training return: tensor(368.5212, device='cuda:0')
epoch: 35 test_true_pfm: 5959.0338802062615 sim_pfm: 582.3476048717275
episode: 140 training return: tensor(320.2646, device='cuda:0')
episode: 141 training return: tensor(282.6117, device='cuda:0')
episode: 142 training return: tensor(447.7061, device='cuda:0')
episode: 143 training return: tensor(384.4810, device='cuda:0')
epoch: 36 test_true_pfm: 5899.347104978998 sim_pfm: 507.2983196054508
episode: 144 training return: tensor(347.2259, device='cuda:0')
episode: 145 training return: tensor(370.8322, device='cuda:0')
episode: 146 training return: tensor(393.7643, device='cuda:0')
episode: 147 training return: tensor(444.9487, device='cuda:0')
epoch: 37 test_true_pfm: 5936.308386780045 sim_pfm: 600.655937511668
episode: 148 training return: tensor(391.4547, device='cuda:0')
episode: 149 training return: tensor(451.1673, device='cuda:0')
episode: 150 training return: tensor(412.0104, device='cuda:0')
episode: 151 training return: tensor(372.8260, device='cuda:0')
epoch: 38 test_true_pfm: 5903.674041230229 sim_pfm: 579.3144336467958
episode: 152 training return: tensor(363.4433, device='cuda:0')
episode: 153 training return: tensor(385.9430, device='cuda:0')
episode: 154 training return: tensor(519.5456, device='cuda:0')
episode: 155 training return: tensor(372.9435, device='cuda:0')
epoch: 39 test_true_pfm: 5874.347249510338 sim_pfm: 580.411268412155
episode: 156 training return: tensor(368.1907, device='cuda:0')
episode: 157 training return: tensor(482.7977, device='cuda:0')
episode: 158 training return: tensor(294.4848, device='cuda:0')
episode: 159 training return: tensor(487.1214, device='cuda:0')
epoch: 40 test_true_pfm: 6066.288613213201 sim_pfm: 616.9592345766723
episode: 160 training return: tensor(464.8844, device='cuda:0')
episode: 161 training return: tensor(457.9297, device='cuda:0')
episode: 162 training return: tensor(398.4647, device='cuda:0')
episode: 163 training return: tensor(441.3032, device='cuda:0')
epoch: 41 test_true_pfm: 5956.3019469825695 sim_pfm: 644.6004601911603
episode: 164 training return: tensor(484.9481, device='cuda:0')
episode: 165 training return: tensor(464.0825, device='cuda:0')
episode: 166 training return: tensor(423.7944, device='cuda:0')
episode: 167 training return: tensor(440.4503, device='cuda:0')
epoch: 42 test_true_pfm: 5968.61616877191 sim_pfm: 628.2927559935002
episode: 168 training return: tensor(395.3398, device='cuda:0')
episode: 169 training return: tensor(440.4016, device='cuda:0')
episode: 170 training return: tensor(454.0870, device='cuda:0')
episode: 171 training return: tensor(419.2224, device='cuda:0')
epoch: 43 test_true_pfm: 5922.217499988011 sim_pfm: 580.3765087382247
episode: 172 training return: tensor(437.4955, device='cuda:0')
episode: 173 training return: tensor(435.2617, device='cuda:0')
episode: 174 training return: tensor(406.9697, device='cuda:0')
episode: 175 training return: tensor(498.3874, device='cuda:0')
epoch: 44 test_true_pfm: 5949.8022455340115 sim_pfm: 617.2212332346049
episode: 176 training return: tensor(451.7123, device='cuda:0')
episode: 177 training return: tensor(431.3640, device='cuda:0')
episode: 178 training return: tensor(502.0518, device='cuda:0')
episode: 179 training return: tensor(399.7348, device='cuda:0')
epoch: 45 test_true_pfm: 5926.520552120125 sim_pfm: 622.5125088343242
episode: 180 training return: tensor(558.5392, device='cuda:0')
episode: 181 training return: tensor(430.0154, device='cuda:0')
episode: 182 training return: tensor(446.2038, device='cuda:0')
episode: 183 training return: tensor(495.7172, device='cuda:0')
epoch: 46 test_true_pfm: 5991.516997776346 sim_pfm: 633.9257425123263
episode: 184 training return: tensor(368.4417, device='cuda:0')
episode: 185 training return: tensor(476.6170, device='cuda:0')
episode: 186 training return: tensor(415.0804, device='cuda:0')
episode: 187 training return: tensor(469.9711, device='cuda:0')
epoch: 47 test_true_pfm: 6116.343016093441 sim_pfm: 637.113869616626
episode: 188 training return: tensor(488.5160, device='cuda:0')
episode: 189 training return: tensor(472.1940, device='cuda:0')
episode: 190 training return: tensor(526.4877, device='cuda:0')
episode: 191 training return: tensor(452.4716, device='cuda:0')
epoch: 48 test_true_pfm: 6093.952074304331 sim_pfm: 646.7189202732407
episode: 192 training return: tensor(454.6960, device='cuda:0')
episode: 193 training return: tensor(491.3250, device='cuda:0')
episode: 194 training return: tensor(374.3738, device='cuda:0')
episode: 195 training return: tensor(521.8522, device='cuda:0')
epoch: 49 test_true_pfm: 6002.265504102477 sim_pfm: 623.8047886071727
episode: 196 training return: tensor(422.4456, device='cuda:0')
episode: 197 training return: tensor(502.9193, device='cuda:0')
episode: 198 training return: tensor(462.6597, device='cuda:0')
episode: 199 training return: tensor(464.4079, device='cuda:0')
epoch: 50 test_true_pfm: 5994.718577695768 sim_pfm: 605.5517838087786
episode: 200 training return: tensor(478.4939, device='cuda:0')
episode: 201 training return: tensor(486.2033, device='cuda:0')
episode: 202 training return: tensor(467.9058, device='cuda:0')
episode: 203 training return: tensor(452.8694, device='cuda:0')
epoch: 51 test_true_pfm: 5947.925377960618 sim_pfm: 598.6967880028145
episode: 204 training return: tensor(497.2609, device='cuda:0')
episode: 205 training return: tensor(467.3737, device='cuda:0')
episode: 206 training return: tensor(487.0177, device='cuda:0')
episode: 207 training return: tensor(528.8648, device='cuda:0')
epoch: 52 test_true_pfm: 6138.541768844862 sim_pfm: 711.3890004432664
episode: 208 training return: tensor(516.4449, device='cuda:0')
episode: 209 training return: tensor(512.1531, device='cuda:0')
episode: 210 training return: tensor(518.6115, device='cuda:0')
episode: 211 training return: tensor(496.6973, device='cuda:0')
epoch: 53 test_true_pfm: 6044.699460184257 sim_pfm: 669.5181553194221
episode: 212 training return: tensor(531.1475, device='cuda:0')
episode: 213 training return: tensor(542.7365, device='cuda:0')
episode: 214 training return: tensor(537.4141, device='cuda:0')
episode: 215 training return: tensor(486.2032, device='cuda:0')
epoch: 54 test_true_pfm: 6076.631398971124 sim_pfm: 652.2983243156535
episode: 216 training return: tensor(392.1314, device='cuda:0')
episode: 217 training return: tensor(392.4000, device='cuda:0')
episode: 218 training return: tensor(544.0205, device='cuda:0')
episode: 219 training return: tensor(532.8964, device='cuda:0')
epoch: 55 test_true_pfm: 6072.852520309471 sim_pfm: 688.2059171554865
episode: 220 training return: tensor(544.0737, device='cuda:0')
episode: 221 training return: tensor(504.5723, device='cuda:0')
episode: 222 training return: tensor(508.9317, device='cuda:0')
episode: 223 training return: tensor(511.2807, device='cuda:0')
epoch: 56 test_true_pfm: 6041.893356461315 sim_pfm: 664.8027726538324
episode: 224 training return: tensor(458.1972, device='cuda:0')
episode: 225 training return: tensor(460.4223, device='cuda:0')
episode: 226 training return: tensor(543.0999, device='cuda:0')
episode: 227 training return: tensor(509.2585, device='cuda:0')
epoch: 57 test_true_pfm: 6039.741099695607 sim_pfm: 657.8985680549522
episode: 228 training return: tensor(487.8055, device='cuda:0')
episode: 229 training return: tensor(501.6295, device='cuda:0')
episode: 230 training return: tensor(514.4850, device='cuda:0')
episode: 231 training return: tensor(525.4569, device='cuda:0')
epoch: 58 test_true_pfm: 6082.874050759917 sim_pfm: 660.0478340570893
episode: 232 training return: tensor(523.8694, device='cuda:0')
episode: 233 training return: tensor(462.8487, device='cuda:0')
episode: 234 training return: tensor(493.7196, device='cuda:0')
episode: 235 training return: tensor(508.9801, device='cuda:0')
epoch: 59 test_true_pfm: 6100.948115168902 sim_pfm: 654.8921373396685
episode: 236 training return: tensor(515.7959, device='cuda:0')
episode: 237 training return: tensor(567.7331, device='cuda:0')
episode: 238 training return: tensor(470.6052, device='cuda:0')
episode: 239 training return: tensor(567.0922, device='cuda:0')
epoch: 60 test_true_pfm: 6053.002170942013 sim_pfm: 701.6470303015085
episode: 240 training return: tensor(482.7801, device='cuda:0')
episode: 241 training return: tensor(519.5154, device='cuda:0')
episode: 242 training return: tensor(518.7147, device='cuda:0')
episode: 243 training return: tensor(513.5724, device='cuda:0')
epoch: 61 test_true_pfm: 6097.570525452719 sim_pfm: 685.8315117588887
episode: 244 training return: tensor(607.7081, device='cuda:0')
episode: 245 training return: tensor(547.1502, device='cuda:0')
episode: 246 training return: tensor(518.0297, device='cuda:0')
episode: 247 training return: tensor(521.8589, device='cuda:0')
epoch: 62 test_true_pfm: 6171.324748846328 sim_pfm: 709.4320820587454
episode: 248 training return: tensor(594.1396, device='cuda:0')
episode: 249 training return: tensor(513.5029, device='cuda:0')
episode: 250 training return: tensor(500.9786, device='cuda:0')
episode: 251 training return: tensor(581.1727, device='cuda:0')
epoch: 63 test_true_pfm: 4330.447817916448 sim_pfm: 693.2445900718061
episode: 252 training return: tensor(539.0686, device='cuda:0')
episode: 253 training return: tensor(547.2989, device='cuda:0')
episode: 254 training return: tensor(495.5811, device='cuda:0')
episode: 255 training return: tensor(557.1639, device='cuda:0')
epoch: 64 test_true_pfm: 5972.478990300647 sim_pfm: 619.6491379183329
episode: 256 training return: tensor(564.5693, device='cuda:0')
episode: 257 training return: tensor(480.1215, device='cuda:0')
episode: 258 training return: tensor(596.9061, device='cuda:0')
episode: 259 training return: tensor(542.0507, device='cuda:0')
epoch: 65 test_true_pfm: 6147.9114010653475 sim_pfm: 669.8421169912908
episode: 260 training return: tensor(525.2911, device='cuda:0')
episode: 261 training return: tensor(540.1790, device='cuda:0')
episode: 262 training return: tensor(521.0721, device='cuda:0')
episode: 263 training return: tensor(468.1177, device='cuda:0')
epoch: 66 test_true_pfm: 6124.625350623094 sim_pfm: 697.2929739657169
episode: 264 training return: tensor(536.5768, device='cuda:0')
episode: 265 training return: tensor(608.3550, device='cuda:0')
episode: 266 training return: tensor(528.3899, device='cuda:0')
episode: 267 training return: tensor(515.4728, device='cuda:0')
epoch: 67 test_true_pfm: 6142.9430991618365 sim_pfm: 683.6217614334504
episode: 268 training return: tensor(508.4345, device='cuda:0')
episode: 269 training return: tensor(498.0774, device='cuda:0')
episode: 270 training return: tensor(514.2661, device='cuda:0')
episode: 271 training return: tensor(596.0011, device='cuda:0')
epoch: 68 test_true_pfm: 6162.399717761101 sim_pfm: 647.635331624498
episode: 272 training return: tensor(505.0047, device='cuda:0')
episode: 273 training return: tensor(512.8028, device='cuda:0')
episode: 274 training return: tensor(576.1049, device='cuda:0')
episode: 275 training return: tensor(563.5980, device='cuda:0')
epoch: 69 test_true_pfm: 6100.553066139614 sim_pfm: 671.048220624992
episode: 276 training return: tensor(551.2642, device='cuda:0')
episode: 277 training return: tensor(503.4202, device='cuda:0')
episode: 278 training return: tensor(555.8185, device='cuda:0')
episode: 279 training return: tensor(523.0494, device='cuda:0')
epoch: 70 test_true_pfm: 6147.429439757558 sim_pfm: 702.097938286839
episode: 280 training return: tensor(542.0350, device='cuda:0')
episode: 281 training return: tensor(513.1156, device='cuda:0')
episode: 282 training return: tensor(556.5751, device='cuda:0')
episode: 283 training return: tensor(604.3845, device='cuda:0')
epoch: 71 test_true_pfm: 6101.222767390733 sim_pfm: 700.0629596357854
episode: 284 training return: tensor(511.4182, device='cuda:0')
episode: 285 training return: tensor(571.0645, device='cuda:0')
episode: 286 training return: tensor(564.0612, device='cuda:0')
episode: 287 training return: tensor(548.7023, device='cuda:0')
epoch: 72 test_true_pfm: 6101.030529094473 sim_pfm: 673.9702824343889
episode: 288 training return: tensor(575.2239, device='cuda:0')
episode: 289 training return: tensor(452.3500, device='cuda:0')
episode: 290 training return: tensor(589.3909, device='cuda:0')
episode: 291 training return: tensor(567.4095, device='cuda:0')
epoch: 73 test_true_pfm: 6148.6958161519515 sim_pfm: 698.2663824878206
episode: 292 training return: tensor(567.5905, device='cuda:0')
episode: 293 training return: tensor(557.4356, device='cuda:0')
episode: 294 training return: tensor(627.6565, device='cuda:0')
episode: 295 training return: tensor(540.0934, device='cuda:0')
epoch: 74 test_true_pfm: 6195.6921955432035 sim_pfm: 696.0400987173585
episode: 296 training return: tensor(517.3474, device='cuda:0')
episode: 297 training return: tensor(544.1854, device='cuda:0')
episode: 298 training return: tensor(528.0612, device='cuda:0')
episode: 299 training return: tensor(591.4117, device='cuda:0')
epoch: 75 test_true_pfm: 6228.129340508521 sim_pfm: 719.7381997949173
episode: 300 training return: tensor(579.7632, device='cuda:0')
episode: 301 training return: tensor(514.8438, device='cuda:0')
episode: 302 training return: tensor(563.4713, device='cuda:0')
episode: 303 training return: tensor(544.3541, device='cuda:0')
epoch: 76 test_true_pfm: 6179.253153791586 sim_pfm: 689.5473188200849
episode: 304 training return: tensor(583.0552, device='cuda:0')
episode: 305 training return: tensor(556.9027, device='cuda:0')
episode: 306 training return: tensor(617.9646, device='cuda:0')
episode: 307 training return: tensor(425.2098, device='cuda:0')
epoch: 77 test_true_pfm: 6203.165273714108 sim_pfm: 728.135561616548
episode: 308 training return: tensor(510.2569, device='cuda:0')
episode: 309 training return: tensor(491.4423, device='cuda:0')
episode: 310 training return: tensor(537.7802, device='cuda:0')
episode: 311 training return: tensor(173.3714, device='cuda:0')
epoch: 78 test_true_pfm: 6201.142795553974 sim_pfm: 705.5305738258758
episode: 312 training return: tensor(571.2386, device='cuda:0')
episode: 313 training return: tensor(615.9136, device='cuda:0')
episode: 314 training return: tensor(523.1612, device='cuda:0')
episode: 315 training return: tensor(580.7271, device='cuda:0')
epoch: 79 test_true_pfm: 6128.612087521756 sim_pfm: 722.1283368349153
episode: 316 training return: tensor(587.4072, device='cuda:0')
episode: 317 training return: tensor(532.9855, device='cuda:0')
episode: 318 training return: tensor(521.0977, device='cuda:0')
episode: 319 training return: tensor(545.3395, device='cuda:0')
epoch: 80 test_true_pfm: 6172.063201184581 sim_pfm: 695.9013885473056
episode: 320 training return: tensor(543.5726, device='cuda:0')
episode: 321 training return: tensor(547.5933, device='cuda:0')
episode: 322 training return: tensor(574.0270, device='cuda:0')
episode: 323 training return: tensor(563.1503, device='cuda:0')
epoch: 81 test_true_pfm: 6153.194516158886 sim_pfm: 715.3902891261387
episode: 324 training return: tensor(595.5092, device='cuda:0')
episode: 325 training return: tensor(539.5997, device='cuda:0')
episode: 326 training return: tensor(595.2072, device='cuda:0')
episode: 327 training return: tensor(538.0385, device='cuda:0')
epoch: 82 test_true_pfm: 6161.022929902174 sim_pfm: 708.521651811238
episode: 328 training return: tensor(518.4521, device='cuda:0')
episode: 329 training return: tensor(598.0458, device='cuda:0')
episode: 330 training return: tensor(563.5355, device='cuda:0')
episode: 331 training return: tensor(614.1490, device='cuda:0')
epoch: 83 test_true_pfm: 6166.249499200862 sim_pfm: 679.870732642943
episode: 332 training return: tensor(576.7636, device='cuda:0')
episode: 333 training return: tensor(562.6357, device='cuda:0')
episode: 334 training return: tensor(500.7838, device='cuda:0')
episode: 335 training return: tensor(623.3881, device='cuda:0')
epoch: 84 test_true_pfm: 6174.252384188899 sim_pfm: 724.5466494630867
episode: 336 training return: tensor(582.5065, device='cuda:0')
episode: 337 training return: tensor(602.6151, device='cuda:0')
episode: 338 training return: tensor(605.0509, device='cuda:0')
episode: 339 training return: tensor(584.1829, device='cuda:0')
epoch: 85 test_true_pfm: 6251.872352456495 sim_pfm: 718.861352381995
episode: 340 training return: tensor(588.1911, device='cuda:0')
episode: 341 training return: tensor(530.4802, device='cuda:0')
episode: 342 training return: tensor(559.1678, device='cuda:0')
episode: 343 training return: tensor(602.4957, device='cuda:0')
epoch: 86 test_true_pfm: 6177.02160754447 sim_pfm: 712.68709029494
episode: 344 training return: tensor(579.6942, device='cuda:0')
episode: 345 training return: tensor(597.7719, device='cuda:0')
episode: 346 training return: tensor(609.7112, device='cuda:0')
episode: 347 training return: tensor(550.1440, device='cuda:0')
epoch: 87 test_true_pfm: 6265.270940461339 sim_pfm: 728.3823453991208
episode: 348 training return: tensor(566.5640, device='cuda:0')
episode: 349 training return: tensor(584.6635, device='cuda:0')
episode: 350 training return: tensor(588.8453, device='cuda:0')
episode: 351 training return: tensor(542.1611, device='cuda:0')
epoch: 88 test_true_pfm: 6210.354658983923 sim_pfm: 729.4181213697108
episode: 352 training return: tensor(579.1136, device='cuda:0')
episode: 353 training return: tensor(538.8194, device='cuda:0')
episode: 354 training return: tensor(594.5441, device='cuda:0')
episode: 355 training return: tensor(578.6261, device='cuda:0')
epoch: 89 test_true_pfm: 6191.328759722793 sim_pfm: 719.972959295536
episode: 356 training return: tensor(524.5154, device='cuda:0')
episode: 357 training return: tensor(589.5167, device='cuda:0')
episode: 358 training return: tensor(591.0070, device='cuda:0')
episode: 359 training return: tensor(593.0034, device='cuda:0')
epoch: 90 test_true_pfm: 6255.864035047627 sim_pfm: 713.5655181171993
episode: 360 training return: tensor(579.3820, device='cuda:0')
episode: 361 training return: tensor(597.3057, device='cuda:0')
episode: 362 training return: tensor(586.5642, device='cuda:0')
episode: 363 training return: tensor(586.3455, device='cuda:0')
epoch: 91 test_true_pfm: 6189.96806428555 sim_pfm: 714.3315108526343
episode: 364 training return: tensor(596.3458, device='cuda:0')
episode: 365 training return: tensor(635.2326, device='cuda:0')
episode: 366 training return: tensor(595.2938, device='cuda:0')
episode: 367 training return: tensor(536.0867, device='cuda:0')
epoch: 92 test_true_pfm: 6192.67600662801 sim_pfm: 693.2918239276236
episode: 368 training return: tensor(595.7229, device='cuda:0')
episode: 369 training return: tensor(603.1578, device='cuda:0')
episode: 370 training return: tensor(545.6776, device='cuda:0')
episode: 371 training return: tensor(568.7353, device='cuda:0')
epoch: 93 test_true_pfm: 6122.895456295525 sim_pfm: 712.7752706440709
episode: 372 training return: tensor(512.4607, device='cuda:0')
episode: 373 training return: tensor(604.1789, device='cuda:0')
episode: 374 training return: tensor(604.3886, device='cuda:0')
episode: 375 training return: tensor(611.5637, device='cuda:0')
epoch: 94 test_true_pfm: 6218.418556254436 sim_pfm: 725.5891829116348
episode: 376 training return: tensor(593.8481, device='cuda:0')
episode: 377 training return: tensor(521.6996, device='cuda:0')
episode: 378 training return: tensor(645.0706, device='cuda:0')
episode: 379 training return: tensor(667.9999, device='cuda:0')
epoch: 95 test_true_pfm: 6217.451959869872 sim_pfm: 710.3317189913554
episode: 380 training return: tensor(503.0039, device='cuda:0')
episode: 381 training return: tensor(619.8219, device='cuda:0')
episode: 382 training return: tensor(569.3818, device='cuda:0')
episode: 383 training return: tensor(582.9510, device='cuda:0')
epoch: 96 test_true_pfm: 6158.918112983182 sim_pfm: 713.5845576804035
episode: 384 training return: tensor(551.6758, device='cuda:0')
episode: 385 training return: tensor(552.1796, device='cuda:0')
episode: 386 training return: tensor(624.5760, device='cuda:0')
episode: 387 training return: tensor(571.3824, device='cuda:0')
epoch: 97 test_true_pfm: 6234.2040729042055 sim_pfm: 719.6875024631154
episode: 388 training return: tensor(620.9139, device='cuda:0')
episode: 389 training return: tensor(529.3531, device='cuda:0')
episode: 390 training return: tensor(642.7473, device='cuda:0')
episode: 391 training return: tensor(518.0682, device='cuda:0')
epoch: 98 test_true_pfm: 6188.882001912151 sim_pfm: 732.6282483254714
episode: 392 training return: tensor(586.7482, device='cuda:0')
episode: 393 training return: tensor(670.0318, device='cuda:0')
episode: 394 training return: tensor(554.3414, device='cuda:0')
episode: 395 training return: tensor(582.2760, device='cuda:0')
epoch: 99 test_true_pfm: 6212.050132960799 sim_pfm: 740.9884382619057
episode: 396 training return: tensor(614.4307, device='cuda:0')
episode: 397 training return: tensor(606.7859, device='cuda:0')
episode: 398 training return: tensor(554.3566, device='cuda:0')
episode: 399 training return: tensor(587.6944, device='cuda:0')
epoch: 100 test_true_pfm: 6205.158578139512 sim_pfm: 712.2829934655068
episode: 400 training return: tensor(601.2399, device='cuda:0')
episode: 401 training return: tensor(537.4774, device='cuda:0')
episode: 402 training return: tensor(578.9060, device='cuda:0')
episode: 403 training return: tensor(580.0754, device='cuda:0')
epoch: 101 test_true_pfm: 6283.413847942939 sim_pfm: 740.2988310467141
episode: 404 training return: tensor(598.8373, device='cuda:0')
episode: 405 training return: tensor(625.8677, device='cuda:0')
episode: 406 training return: tensor(578.6140, device='cuda:0')
episode: 407 training return: tensor(612.8026, device='cuda:0')
epoch: 102 test_true_pfm: 6294.102669356747 sim_pfm: 746.2011097792225
episode: 408 training return: tensor(639.4995, device='cuda:0')
episode: 409 training return: tensor(594.6924, device='cuda:0')
episode: 410 training return: tensor(560.5204, device='cuda:0')
episode: 411 training return: tensor(522.5715, device='cuda:0')
epoch: 103 test_true_pfm: 6216.944110539916 sim_pfm: 714.8024689763164
episode: 412 training return: tensor(598.3620, device='cuda:0')
episode: 413 training return: tensor(651.5615, device='cuda:0')
episode: 414 training return: tensor(589.3851, device='cuda:0')
episode: 415 training return: tensor(580.6180, device='cuda:0')
epoch: 104 test_true_pfm: 6223.9577510756235 sim_pfm: 730.2395775391875
episode: 416 training return: tensor(627.6861, device='cuda:0')
episode: 417 training return: tensor(576.2377, device='cuda:0')
episode: 418 training return: tensor(592.1899, device='cuda:0')
episode: 419 training return: tensor(625.8235, device='cuda:0')
epoch: 105 test_true_pfm: 6260.627672197627 sim_pfm: 769.514910078297
episode: 420 training return: tensor(581.3556, device='cuda:0')
episode: 421 training return: tensor(608.1278, device='cuda:0')
episode: 422 training return: tensor(566.4458, device='cuda:0')
episode: 423 training return: tensor(605.7610, device='cuda:0')
epoch: 106 test_true_pfm: 6298.775290088397 sim_pfm: 759.4269408253409
episode: 424 training return: tensor(630.9808, device='cuda:0')
episode: 425 training return: tensor(581.0956, device='cuda:0')
episode: 426 training return: tensor(622.7737, device='cuda:0')
episode: 427 training return: tensor(599.4905, device='cuda:0')
epoch: 107 test_true_pfm: 6296.035821574408 sim_pfm: 756.5283311182478
episode: 428 training return: tensor(581.9641, device='cuda:0')
episode: 429 training return: tensor(575.1257, device='cuda:0')
episode: 430 training return: tensor(548.8107, device='cuda:0')
episode: 431 training return: tensor(567.2757, device='cuda:0')
epoch: 108 test_true_pfm: 6218.66047208988 sim_pfm: 756.0346924366119
episode: 432 training return: tensor(626.3889, device='cuda:0')
episode: 433 training return: tensor(606.8463, device='cuda:0')
episode: 434 training return: tensor(564.6006, device='cuda:0')
episode: 435 training return: tensor(602.1360, device='cuda:0')
epoch: 109 test_true_pfm: 6173.157188949627 sim_pfm: 719.192092970227
episode: 436 training return: tensor(632.5928, device='cuda:0')
episode: 437 training return: tensor(630.5195, device='cuda:0')
episode: 438 training return: tensor(643.0621, device='cuda:0')
episode: 439 training return: tensor(565.6885, device='cuda:0')
epoch: 110 test_true_pfm: 6270.691927746055 sim_pfm: 725.3734706495889
episode: 440 training return: tensor(577.2112, device='cuda:0')
episode: 441 training return: tensor(583.0734, device='cuda:0')
episode: 442 training return: tensor(585.1838, device='cuda:0')
episode: 443 training return: tensor(612.3883, device='cuda:0')
epoch: 111 test_true_pfm: 6254.589485600576 sim_pfm: 746.3780226200664
episode: 444 training return: tensor(569.9727, device='cuda:0')
episode: 445 training return: tensor(610.4523, device='cuda:0')
episode: 446 training return: tensor(601.0269, device='cuda:0')
episode: 447 training return: tensor(596.3174, device='cuda:0')
epoch: 112 test_true_pfm: 6173.005937325827 sim_pfm: 721.3327820861401
episode: 448 training return: tensor(637.8386, device='cuda:0')
episode: 449 training return: tensor(578.6685, device='cuda:0')
episode: 450 training return: tensor(606.3901, device='cuda:0')
episode: 451 training return: tensor(609.8344, device='cuda:0')
epoch: 113 test_true_pfm: 6326.654415961729 sim_pfm: 762.2893983158283
episode: 452 training return: tensor(603.6013, device='cuda:0')
episode: 453 training return: tensor(487.1162, device='cuda:0')
episode: 454 training return: tensor(580.3624, device='cuda:0')
episode: 455 training return: tensor(645.3931, device='cuda:0')
epoch: 114 test_true_pfm: 6276.505101220285 sim_pfm: 750.2879753351832
episode: 456 training return: tensor(665.2839, device='cuda:0')
episode: 457 training return: tensor(634.0452, device='cuda:0')
episode: 458 training return: tensor(616.5688, device='cuda:0')
episode: 459 training return: tensor(568.7825, device='cuda:0')
epoch: 115 test_true_pfm: 6261.227754542066 sim_pfm: 731.3677778154766
episode: 460 training return: tensor(623.1443, device='cuda:0')
episode: 461 training return: tensor(651.1193, device='cuda:0')
episode: 462 training return: tensor(622.5764, device='cuda:0')
episode: 463 training return: tensor(639.4797, device='cuda:0')
epoch: 116 test_true_pfm: 6174.022144779895 sim_pfm: 706.3185700917771
episode: 464 training return: tensor(578.2791, device='cuda:0')
episode: 465 training return: tensor(654.0067, device='cuda:0')
episode: 466 training return: tensor(603.3908, device='cuda:0')
episode: 467 training return: tensor(552.0927, device='cuda:0')
epoch: 117 test_true_pfm: 6234.701152889514 sim_pfm: 743.4123700527707
episode: 468 training return: tensor(612.5475, device='cuda:0')
episode: 469 training return: tensor(544.3618, device='cuda:0')
episode: 470 training return: tensor(668.8817, device='cuda:0')
episode: 471 training return: tensor(651.6913, device='cuda:0')
epoch: 118 test_true_pfm: 6203.98060326008 sim_pfm: 744.0867029400542
episode: 472 training return: tensor(604.3237, device='cuda:0')
episode: 473 training return: tensor(478.2858, device='cuda:0')
episode: 474 training return: tensor(578.3795, device='cuda:0')
episode: 475 training return: tensor(580.5915, device='cuda:0')
epoch: 119 test_true_pfm: 6268.8083023532445 sim_pfm: 723.1798959818358
episode: 476 training return: tensor(589.6553, device='cuda:0')
episode: 477 training return: tensor(612.9260, device='cuda:0')
episode: 478 training return: tensor(635.2951, device='cuda:0')
episode: 479 training return: tensor(619.8344, device='cuda:0')
epoch: 120 test_true_pfm: 6200.187411148464 sim_pfm: 748.4973881486416
episode: 480 training return: tensor(589.9210, device='cuda:0')
episode: 481 training return: tensor(620.0593, device='cuda:0')
episode: 482 training return: tensor(592.6782, device='cuda:0')
episode: 483 training return: tensor(609.3793, device='cuda:0')
epoch: 121 test_true_pfm: 6209.5664941781 sim_pfm: 742.6482860770387
episode: 484 training return: tensor(605.1277, device='cuda:0')
episode: 485 training return: tensor(605.5274, device='cuda:0')
episode: 486 training return: tensor(596.7263, device='cuda:0')
episode: 487 training return: tensor(600.7360, device='cuda:0')
epoch: 122 test_true_pfm: 6327.057678036909 sim_pfm: 748.1188602643088
episode: 488 training return: tensor(566.1356, device='cuda:0')
episode: 489 training return: tensor(636.3987, device='cuda:0')
episode: 490 training return: tensor(624.2253, device='cuda:0')
episode: 491 training return: tensor(625.6072, device='cuda:0')
epoch: 123 test_true_pfm: 6179.446397821688 sim_pfm: 705.1717716261919
episode: 492 training return: tensor(613.4741, device='cuda:0')
episode: 493 training return: tensor(621.3290, device='cuda:0')
episode: 494 training return: tensor(653.5623, device='cuda:0')
episode: 495 training return: tensor(644.1552, device='cuda:0')
epoch: 124 test_true_pfm: 6301.876922728611 sim_pfm: 740.758811120914
episode: 496 training return: tensor(594.0767, device='cuda:0')
episode: 497 training return: tensor(637.5889, device='cuda:0')
episode: 498 training return: tensor(576.5325, device='cuda:0')
episode: 499 training return: tensor(638.1215, device='cuda:0')
epoch: 125 test_true_pfm: 6205.881555923986 sim_pfm: 732.7248304965906
episode: 500 training return: tensor(626.9736, device='cuda:0')
episode: 501 training return: tensor(566.3863, device='cuda:0')
episode: 502 training return: tensor(603.4864, device='cuda:0')
episode: 503 training return: tensor(640.1792, device='cuda:0')
epoch: 126 test_true_pfm: 6220.122486035863 sim_pfm: 717.1872821274834
episode: 504 training return: tensor(644.5367, device='cuda:0')
episode: 505 training return: tensor(627.0510, device='cuda:0')
episode: 506 training return: tensor(629.9659, device='cuda:0')
episode: 507 training return: tensor(598.2650, device='cuda:0')
epoch: 127 test_true_pfm: 6182.798832573706 sim_pfm: 741.8419313609289
episode: 508 training return: tensor(632.9883, device='cuda:0')
episode: 509 training return: tensor(636.0345, device='cuda:0')
episode: 510 training return: tensor(627.6732, device='cuda:0')
episode: 511 training return: tensor(629.6788, device='cuda:0')
epoch: 128 test_true_pfm: 6258.152941933349 sim_pfm: 768.6554079186171
episode: 512 training return: tensor(646.8060, device='cuda:0')
episode: 513 training return: tensor(521.0370, device='cuda:0')
episode: 514 training return: tensor(607.7342, device='cuda:0')
episode: 515 training return: tensor(637.3325, device='cuda:0')
epoch: 129 test_true_pfm: 6263.281110946442 sim_pfm: 745.2655074736103
episode: 516 training return: tensor(619.5533, device='cuda:0')
episode: 517 training return: tensor(640.1366, device='cuda:0')
episode: 518 training return: tensor(633.8046, device='cuda:0')
episode: 519 training return: tensor(597.4658, device='cuda:0')
epoch: 130 test_true_pfm: 6277.077473825033 sim_pfm: 734.7240829632307
episode: 520 training return: tensor(663.5446, device='cuda:0')
episode: 521 training return: tensor(616.5344, device='cuda:0')
episode: 522 training return: tensor(630.6098, device='cuda:0')
episode: 523 training return: tensor(548.9308, device='cuda:0')
epoch: 131 test_true_pfm: 6304.1365249583905 sim_pfm: 767.3609177313047
episode: 524 training return: tensor(650.8160, device='cuda:0')
episode: 525 training return: tensor(640.6014, device='cuda:0')
episode: 526 training return: tensor(616.3539, device='cuda:0')
episode: 527 training return: tensor(632.1063, device='cuda:0')
epoch: 132 test_true_pfm: 6282.020083205673 sim_pfm: 732.6583054036988
episode: 528 training return: tensor(607.8220, device='cuda:0')
episode: 529 training return: tensor(665.1686, device='cuda:0')
episode: 530 training return: tensor(656.3433, device='cuda:0')
episode: 531 training return: tensor(597.2757, device='cuda:0')
epoch: 133 test_true_pfm: 6364.835121134304 sim_pfm: 775.6274293027818
episode: 532 training return: tensor(680.4467, device='cuda:0')
episode: 533 training return: tensor(587.2006, device='cuda:0')
episode: 534 training return: tensor(592.2166, device='cuda:0')
episode: 535 training return: tensor(659.4964, device='cuda:0')
epoch: 134 test_true_pfm: 6283.350143251194 sim_pfm: 761.7452391483821
episode: 536 training return: tensor(660.6769, device='cuda:0')
episode: 537 training return: tensor(646.0781, device='cuda:0')
episode: 538 training return: tensor(582.5828, device='cuda:0')
episode: 539 training return: tensor(608.2065, device='cuda:0')
epoch: 135 test_true_pfm: 6291.77895663715 sim_pfm: 747.2481409832253
episode: 540 training return: tensor(634.2015, device='cuda:0')
episode: 541 training return: tensor(622.9109, device='cuda:0')
episode: 542 training return: tensor(599.1514, device='cuda:0')
episode: 543 training return: tensor(638.4929, device='cuda:0')
epoch: 136 test_true_pfm: 6259.463158232419 sim_pfm: 753.3319787568374
episode: 544 training return: tensor(624.5711, device='cuda:0')
episode: 545 training return: tensor(644.9636, device='cuda:0')
episode: 546 training return: tensor(595.1281, device='cuda:0')
episode: 547 training return: tensor(633.8243, device='cuda:0')
epoch: 137 test_true_pfm: 6229.818811564267 sim_pfm: 749.1733431403214
episode: 548 training return: tensor(645.6425, device='cuda:0')
episode: 549 training return: tensor(653.0286, device='cuda:0')
episode: 550 training return: tensor(572.9658, device='cuda:0')
episode: 551 training return: tensor(599.1954, device='cuda:0')
epoch: 138 test_true_pfm: 6293.4754702016435 sim_pfm: 763.9454803671688
episode: 552 training return: tensor(609.7134, device='cuda:0')
episode: 553 training return: tensor(589.1544, device='cuda:0')
episode: 554 training return: tensor(609.3236, device='cuda:0')
episode: 555 training return: tensor(651.1361, device='cuda:0')
epoch: 139 test_true_pfm: 6295.311001029558 sim_pfm: 752.2157045361819
episode: 556 training return: tensor(603.7986, device='cuda:0')
episode: 557 training return: tensor(567.0916, device='cuda:0')
episode: 558 training return: tensor(645.8197, device='cuda:0')
episode: 559 training return: tensor(631.6227, device='cuda:0')
epoch: 140 test_true_pfm: 6271.386889047408 sim_pfm: 764.4682260091067
episode: 560 training return: tensor(624.4038, device='cuda:0')
episode: 561 training return: tensor(626.4588, device='cuda:0')
episode: 562 training return: tensor(635.7792, device='cuda:0')
episode: 563 training return: tensor(587.6512, device='cuda:0')
epoch: 141 test_true_pfm: 6288.329505168021 sim_pfm: 757.8258934762174
episode: 564 training return: tensor(625.7286, device='cuda:0')
episode: 565 training return: tensor(585.0137, device='cuda:0')
episode: 566 training return: tensor(611.4483, device='cuda:0')
episode: 567 training return: tensor(625.2425, device='cuda:0')
epoch: 142 test_true_pfm: 6268.759500967732 sim_pfm: 756.3275249768049
episode: 568 training return: tensor(588.3990, device='cuda:0')
episode: 569 training return: tensor(551.8193, device='cuda:0')
episode: 570 training return: tensor(624.3509, device='cuda:0')
episode: 571 training return: tensor(629.4302, device='cuda:0')
epoch: 143 test_true_pfm: 6246.654177142899 sim_pfm: 745.2119013840953
episode: 572 training return: tensor(645.8841, device='cuda:0')
episode: 573 training return: tensor(625.4734, device='cuda:0')
episode: 574 training return: tensor(657.3161, device='cuda:0')
episode: 575 training return: tensor(604.6394, device='cuda:0')
epoch: 144 test_true_pfm: 6259.092085801373 sim_pfm: 780.88786981379
episode: 576 training return: tensor(622.9706, device='cuda:0')
episode: 577 training return: tensor(622.0164, device='cuda:0')
episode: 578 training return: tensor(604.0164, device='cuda:0')
episode: 579 training return: tensor(647.3885, device='cuda:0')
epoch: 145 test_true_pfm: 6326.284171104919 sim_pfm: 772.7090275664814
episode: 580 training return: tensor(633.5916, device='cuda:0')
episode: 581 training return: tensor(623.2645, device='cuda:0')
episode: 582 training return: tensor(662.0108, device='cuda:0')
episode: 583 training return: tensor(568.9863, device='cuda:0')
epoch: 146 test_true_pfm: 6290.629445686501 sim_pfm: 746.0908433352209
episode: 584 training return: tensor(635.5444, device='cuda:0')
episode: 585 training return: tensor(642.4814, device='cuda:0')
episode: 586 training return: tensor(608.0928, device='cuda:0')
episode: 587 training return: tensor(615.7527, device='cuda:0')
epoch: 147 test_true_pfm: 6358.764165891654 sim_pfm: 770.7948666520728
episode: 588 training return: tensor(620.6497, device='cuda:0')
episode: 589 training return: tensor(582.7014, device='cuda:0')
episode: 590 training return: tensor(651.3474, device='cuda:0')
episode: 591 training return: tensor(558.9683, device='cuda:0')
epoch: 148 test_true_pfm: 6320.651574092241 sim_pfm: 749.4233042064589
episode: 592 training return: tensor(632.6716, device='cuda:0')
episode: 593 training return: tensor(639.3332, device='cuda:0')
episode: 594 training return: tensor(610.4163, device='cuda:0')
episode: 595 training return: tensor(627.5618, device='cuda:0')
epoch: 149 test_true_pfm: 6226.326471735884 sim_pfm: 709.5037605918673
episode: 596 training return: tensor(651.0330, device='cuda:0')
episode: 597 training return: tensor(613.7369, device='cuda:0')
episode: 598 training return: tensor(594.3381, device='cuda:0')
episode: 599 training return: tensor(613.2675, device='cuda:0')
epoch: 150 test_true_pfm: 6248.329600082718 sim_pfm: 738.5724769807808
