['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '0', '--data', '100000', '--regu', '0.3']
2355.0423460730663
episode: 0 training return: tensor(315.4513, device='cuda:0')
episode: 1 training return: tensor(298.3649, device='cuda:0')
episode: 2 training return: tensor(341.2834, device='cuda:0')
episode: 3 training return: tensor(-449.5154, device='cuda:0')
epoch: 1 test_true_pfm: 3032.845592376548 sim_pfm: 44.96545088539521
episode: 4 training return: tensor(-350.2089, device='cuda:0')
episode: 5 training return: tensor(-99.3891, device='cuda:0')
episode: 6 training return: tensor(-295.4009, device='cuda:0')
episode: 7 training return: tensor(-157.2997, device='cuda:0')
epoch: 2 test_true_pfm: 3097.6464471115924 sim_pfm: 166.48535517189885
episode: 8 training return: tensor(248.9313, device='cuda:0')
episode: 9 training return: tensor(396.5134, device='cuda:0')
episode: 10 training return: tensor(302.7547, device='cuda:0')
episode: 11 training return: tensor(278.5988, device='cuda:0')
epoch: 3 test_true_pfm: 3295.91647303909 sim_pfm: 426.55516085081035
episode: 12 training return: tensor(-55.1227, device='cuda:0')
episode: 13 training return: tensor(279.9283, device='cuda:0')
episode: 14 training return: tensor(-137.4806, device='cuda:0')
episode: 15 training return: tensor(328.9075, device='cuda:0')
epoch: 4 test_true_pfm: 1758.911311281576 sim_pfm: -244.38913107533395
episode: 16 training return: tensor(503.3747, device='cuda:0')
episode: 17 training return: tensor(15.6407, device='cuda:0')
episode: 18 training return: tensor(409.5750, device='cuda:0')
episode: 19 training return: tensor(386.4572, device='cuda:0')
epoch: 5 test_true_pfm: 3542.182890053157 sim_pfm: 49.995766658704575
episode: 20 training return: tensor(165.9734, device='cuda:0')
episode: 21 training return: tensor(429.3156, device='cuda:0')
episode: 22 training return: tensor(-121.0188, device='cuda:0')
episode: 23 training return: tensor(-287.6957, device='cuda:0')
epoch: 6 test_true_pfm: 3477.8738171209534 sim_pfm: 429.3287348074761
episode: 24 training return: tensor(-386.9167, device='cuda:0')
episode: 25 training return: tensor(441.7865, device='cuda:0')
episode: 26 training return: tensor(290.9897, device='cuda:0')
episode: 27 training return: tensor(431.4608, device='cuda:0')
epoch: 7 test_true_pfm: 2990.7635371247416 sim_pfm: 294.75373546691844
episode: 28 training return: tensor(402.1513, device='cuda:0')
episode: 29 training return: tensor(293.5689, device='cuda:0')
episode: 30 training return: tensor(374.1407, device='cuda:0')
episode: 31 training return: tensor(360.6285, device='cuda:0')
epoch: 8 test_true_pfm: 3391.748945597412 sim_pfm: 239.03411627246533
episode: 32 training return: tensor(179.2752, device='cuda:0')
episode: 33 training return: tensor(-160.6494, device='cuda:0')
episode: 34 training return: tensor(-51.8751, device='cuda:0')
episode: 35 training return: tensor(370.2156, device='cuda:0')
epoch: 9 test_true_pfm: 3284.6166182772345 sim_pfm: 332.7772060793941
episode: 36 training return: tensor(-317.0854, device='cuda:0')
episode: 37 training return: tensor(-116.9161, device='cuda:0')
episode: 38 training return: tensor(358.7868, device='cuda:0')
episode: 39 training return: tensor(393.0078, device='cuda:0')
epoch: 10 test_true_pfm: 3131.16379113997 sim_pfm: 234.80277702280242
episode: 40 training return: tensor(402.9568, device='cuda:0')
episode: 41 training return: tensor(469.2349, device='cuda:0')
episode: 42 training return: tensor(421.8938, device='cuda:0')
episode: 43 training return: tensor(-379.2321, device='cuda:0')
epoch: 11 test_true_pfm: 3592.75768801614 sim_pfm: 456.51537340070354
episode: 44 training return: tensor(360.8584, device='cuda:0')
episode: 45 training return: tensor(387.9988, device='cuda:0')
episode: 46 training return: tensor(364.7119, device='cuda:0')
episode: 47 training return: tensor(435.2168, device='cuda:0')
epoch: 12 test_true_pfm: 3415.7079908174333 sim_pfm: 379.2020298684559
episode: 48 training return: tensor(414.5053, device='cuda:0')
episode: 49 training return: tensor(440.5775, device='cuda:0')
episode: 50 training return: tensor(158.5517, device='cuda:0')
episode: 51 training return: tensor(397.8613, device='cuda:0')
epoch: 13 test_true_pfm: 3477.9430409224838 sim_pfm: 387.74508664213744
episode: 52 training return: tensor(379.0028, device='cuda:0')
episode: 53 training return: tensor(347.9621, device='cuda:0')
episode: 54 training return: tensor(-78.3149, device='cuda:0')
episode: 55 training return: tensor(-152.3418, device='cuda:0')
epoch: 14 test_true_pfm: 3493.3600816898856 sim_pfm: 380.8988211644658
episode: 56 training return: tensor(-107.0459, device='cuda:0')
episode: 57 training return: tensor(462.2253, device='cuda:0')
episode: 58 training return: tensor(124.9255, device='cuda:0')
episode: 59 training return: tensor(385.7353, device='cuda:0')
epoch: 15 test_true_pfm: 3412.9921800038414 sim_pfm: 387.0805063356626
episode: 60 training return: tensor(113.0782, device='cuda:0')
episode: 61 training return: tensor(342.8988, device='cuda:0')
episode: 62 training return: tensor(392.8065, device='cuda:0')
episode: 63 training return: tensor(-639.9377, device='cuda:0')
epoch: 16 test_true_pfm: 3347.8629415318374 sim_pfm: 341.20408151378314
episode: 64 training return: tensor(451.2613, device='cuda:0')
episode: 65 training return: tensor(380.4992, device='cuda:0')
episode: 66 training return: tensor(420.6387, device='cuda:0')
episode: 67 training return: tensor(384.3205, device='cuda:0')
epoch: 17 test_true_pfm: 3484.5566892595853 sim_pfm: 328.3227371458682
episode: 68 training return: tensor(203.6892, device='cuda:0')
episode: 69 training return: tensor(30.2353, device='cuda:0')
episode: 70 training return: tensor(346.2694, device='cuda:0')
episode: 71 training return: tensor(402.3181, device='cuda:0')
epoch: 18 test_true_pfm: 2850.8769668404316 sim_pfm: 487.8023498876719
episode: 72 training return: tensor(434.3855, device='cuda:0')
episode: 73 training return: tensor(464.7227, device='cuda:0')
episode: 74 training return: tensor(447.9367, device='cuda:0')
episode: 75 training return: tensor(376.3925, device='cuda:0')
epoch: 19 test_true_pfm: 2445.48344843757 sim_pfm: 119.17893736289504
episode: 76 training return: tensor(-447.5918, device='cuda:0')
episode: 77 training return: tensor(403.9311, device='cuda:0')
episode: 78 training return: tensor(383.4029, device='cuda:0')
episode: 79 training return: tensor(79.5556, device='cuda:0')
epoch: 20 test_true_pfm: 2980.2347847601027 sim_pfm: 401.46505471196724
episode: 80 training return: tensor(383.1457, device='cuda:0')
episode: 81 training return: tensor(188.0860, device='cuda:0')
episode: 82 training return: tensor(441.0925, device='cuda:0')
episode: 83 training return: tensor(380.3319, device='cuda:0')
epoch: 21 test_true_pfm: 3434.457335011557 sim_pfm: -66.68481935878906
episode: 84 training return: tensor(364.4623, device='cuda:0')
episode: 85 training return: tensor(231.9987, device='cuda:0')
episode: 86 training return: tensor(464.9077, device='cuda:0')
episode: 87 training return: tensor(457.1406, device='cuda:0')
epoch: 22 test_true_pfm: 3490.029264269729 sim_pfm: 433.9871216964287
episode: 88 training return: tensor(469.0706, device='cuda:0')
episode: 89 training return: tensor(528.2708, device='cuda:0')
episode: 90 training return: tensor(442.5818, device='cuda:0')
episode: 91 training return: tensor(-651.0914, device='cuda:0')
epoch: 23 test_true_pfm: 1819.4481081457727 sim_pfm: -193.81275305049107
episode: 92 training return: tensor(399.1907, device='cuda:0')
episode: 93 training return: tensor(-97.8583, device='cuda:0')
episode: 94 training return: tensor(277.8704, device='cuda:0')
episode: 95 training return: tensor(394.4102, device='cuda:0')
epoch: 24 test_true_pfm: 3035.5654917310108 sim_pfm: 273.3958627283185
episode: 96 training return: tensor(343.0989, device='cuda:0')
episode: 97 training return: tensor(323.8689, device='cuda:0')
episode: 98 training return: tensor(436.1289, device='cuda:0')
episode: 99 training return: tensor(426.3990, device='cuda:0')
epoch: 25 test_true_pfm: 3526.044903006912 sim_pfm: 150.1068263852891
episode: 100 training return: tensor(470.1311, device='cuda:0')
episode: 101 training return: tensor(70.2073, device='cuda:0')
episode: 102 training return: tensor(434.8263, device='cuda:0')
episode: 103 training return: tensor(406.8073, device='cuda:0')
epoch: 26 test_true_pfm: 3470.7955962754518 sim_pfm: 416.70516671727336
episode: 104 training return: tensor(232.4497, device='cuda:0')
episode: 105 training return: tensor(-203.7293, device='cuda:0')
episode: 106 training return: tensor(379.8071, device='cuda:0')
episode: 107 training return: tensor(222.1746, device='cuda:0')
epoch: 27 test_true_pfm: 2663.65792487737 sim_pfm: 5.315179072281656
episode: 108 training return: tensor(384.5641, device='cuda:0')
episode: 109 training return: tensor(367.8518, device='cuda:0')
episode: 110 training return: tensor(373.3823, device='cuda:0')
episode: 111 training return: tensor(118.2611, device='cuda:0')
epoch: 28 test_true_pfm: 3353.715313422059 sim_pfm: 324.44697471368517
episode: 112 training return: tensor(314.9532, device='cuda:0')
episode: 113 training return: tensor(406.0395, device='cuda:0')
episode: 114 training return: tensor(269.3725, device='cuda:0')
episode: 115 training return: tensor(339.3216, device='cuda:0')
epoch: 29 test_true_pfm: 3207.0871200375827 sim_pfm: 268.2974571006489
episode: 116 training return: tensor(324.7989, device='cuda:0')
episode: 117 training return: tensor(34.1921, device='cuda:0')
episode: 118 training return: tensor(321.0528, device='cuda:0')
episode: 119 training return: tensor(307.5508, device='cuda:0')
epoch: 30 test_true_pfm: 3478.554834568856 sim_pfm: 392.924037140862
episode: 120 training return: tensor(408.1823, device='cuda:0')
episode: 121 training return: tensor(345.5978, device='cuda:0')
episode: 122 training return: tensor(12.5914, device='cuda:0')
episode: 123 training return: tensor(388.6948, device='cuda:0')
epoch: 31 test_true_pfm: 3442.7717943876837 sim_pfm: 433.94315606492455
episode: 124 training return: tensor(384.6143, device='cuda:0')
episode: 125 training return: tensor(162.5113, device='cuda:0')
episode: 126 training return: tensor(-660.2581, device='cuda:0')
episode: 127 training return: tensor(323.2050, device='cuda:0')
epoch: 32 test_true_pfm: 3267.5671567584345 sim_pfm: 293.2112608903165
episode: 128 training return: tensor(376.2000, device='cuda:0')
episode: 129 training return: tensor(315.5893, device='cuda:0')
episode: 130 training return: tensor(61.1878, device='cuda:0')
episode: 131 training return: tensor(292.7485, device='cuda:0')
epoch: 33 test_true_pfm: 3388.9766562840573 sim_pfm: 381.64677873145166
episode: 132 training return: tensor(325.7386, device='cuda:0')
episode: 133 training return: tensor(463.1851, device='cuda:0')
episode: 134 training return: tensor(292.0998, device='cuda:0')
episode: 135 training return: tensor(423.8954, device='cuda:0')
epoch: 34 test_true_pfm: 3388.5192712192597 sim_pfm: 358.33018913760316
episode: 136 training return: tensor(425.2243, device='cuda:0')
episode: 137 training return: tensor(371.0020, device='cuda:0')
episode: 138 training return: tensor(-153.4925, device='cuda:0')
episode: 139 training return: tensor(379.8315, device='cuda:0')
epoch: 35 test_true_pfm: 3308.8480015694386 sim_pfm: 344.67924581252737
episode: 140 training return: tensor(367.3660, device='cuda:0')
episode: 141 training return: tensor(320.5532, device='cuda:0')
episode: 142 training return: tensor(429.9012, device='cuda:0')
episode: 143 training return: tensor(-68.4445, device='cuda:0')
epoch: 36 test_true_pfm: 3538.7479183168066 sim_pfm: 429.36131313831237
episode: 144 training return: tensor(367.4880, device='cuda:0')
episode: 145 training return: tensor(448.1776, device='cuda:0')
episode: 146 training return: tensor(315.3679, device='cuda:0')
episode: 147 training return: tensor(381.7595, device='cuda:0')
epoch: 37 test_true_pfm: 3463.597264959264 sim_pfm: 382.13274218143005
episode: 148 training return: tensor(383.4965, device='cuda:0')
episode: 149 training return: tensor(-57.9733, device='cuda:0')
episode: 150 training return: tensor(284.7703, device='cuda:0')
episode: 151 training return: tensor(449.0973, device='cuda:0')
epoch: 38 test_true_pfm: 3369.273058698213 sim_pfm: 355.7414054326364
episode: 152 training return: tensor(383.0543, device='cuda:0')
episode: 153 training return: tensor(409.7517, device='cuda:0')
episode: 154 training return: tensor(-669.2478, device='cuda:0')
episode: 155 training return: tensor(472.2917, device='cuda:0')
epoch: 39 test_true_pfm: 3526.486622211701 sim_pfm: 353.41587963599403
episode: 156 training return: tensor(387.6934, device='cuda:0')
episode: 157 training return: tensor(459.8029, device='cuda:0')
episode: 158 training return: tensor(-257.6397, device='cuda:0')
episode: 159 training return: tensor(391.4595, device='cuda:0')
epoch: 40 test_true_pfm: 3367.911110840643 sim_pfm: 357.8378288690583
episode: 160 training return: tensor(431.4568, device='cuda:0')
episode: 161 training return: tensor(442.2216, device='cuda:0')
episode: 162 training return: tensor(357.4702, device='cuda:0')
episode: 163 training return: tensor(-339.5588, device='cuda:0')
epoch: 41 test_true_pfm: 3420.4704233969865 sim_pfm: 379.23773749751854
episode: 164 training return: tensor(361.9561, device='cuda:0')
episode: 165 training return: tensor(32.4098, device='cuda:0')
episode: 166 training return: tensor(391.5857, device='cuda:0')
episode: 167 training return: tensor(425.5131, device='cuda:0')
epoch: 42 test_true_pfm: 2348.7157708849522 sim_pfm: 400.0471915432233
episode: 168 training return: tensor(91.2767, device='cuda:0')
episode: 169 training return: tensor(433.6814, device='cuda:0')
episode: 170 training return: tensor(283.6403, device='cuda:0')
episode: 171 training return: tensor(444.6582, device='cuda:0')
epoch: 43 test_true_pfm: 3327.7214208769874 sim_pfm: 413.52209494810086
episode: 172 training return: tensor(378.9065, device='cuda:0')
episode: 173 training return: tensor(395.4014, device='cuda:0')
episode: 174 training return: tensor(467.6134, device='cuda:0')
episode: 175 training return: tensor(-312.7942, device='cuda:0')
epoch: 44 test_true_pfm: 3416.819239804751 sim_pfm: 376.16300228769734
episode: 176 training return: tensor(423.9017, device='cuda:0')
episode: 177 training return: tensor(421.2683, device='cuda:0')
episode: 178 training return: tensor(388.1891, device='cuda:0')
episode: 179 training return: tensor(95.3455, device='cuda:0')
epoch: 45 test_true_pfm: 431.06505187169427 sim_pfm: -244.95294980503
episode: 180 training return: tensor(411.1266, device='cuda:0')
episode: 181 training return: tensor(489.3839, device='cuda:0')
episode: 182 training return: tensor(436.2686, device='cuda:0')
episode: 183 training return: tensor(461.5332, device='cuda:0')
epoch: 46 test_true_pfm: 3485.4728396095925 sim_pfm: 407.3105446200061
episode: 184 training return: tensor(426.0921, device='cuda:0')
episode: 185 training return: tensor(443.9144, device='cuda:0')
episode: 186 training return: tensor(417.9724, device='cuda:0')
episode: 187 training return: tensor(450.3216, device='cuda:0')
epoch: 47 test_true_pfm: 3390.2727194383383 sim_pfm: 353.84758901939495
episode: 188 training return: tensor(362.5190, device='cuda:0')
episode: 189 training return: tensor(382.7679, device='cuda:0')
episode: 190 training return: tensor(504.7823, device='cuda:0')
episode: 191 training return: tensor(424.9262, device='cuda:0')
epoch: 48 test_true_pfm: 3312.2266916855647 sim_pfm: 408.04494768285076
episode: 192 training return: tensor(462.7189, device='cuda:0')
episode: 193 training return: tensor(425.0923, device='cuda:0')
episode: 194 training return: tensor(479.7416, device='cuda:0')
episode: 195 training return: tensor(333.5423, device='cuda:0')
epoch: 49 test_true_pfm: 3424.778044866555 sim_pfm: 389.3737397953907
episode: 196 training return: tensor(475.9681, device='cuda:0')
episode: 197 training return: tensor(411.6251, device='cuda:0')
episode: 198 training return: tensor(450.2991, device='cuda:0')
episode: 199 training return: tensor(-311.6531, device='cuda:0')
epoch: 50 test_true_pfm: 3370.0820040555786 sim_pfm: 360.7922428084615
episode: 200 training return: tensor(413.0945, device='cuda:0')
episode: 201 training return: tensor(214.2852, device='cuda:0')
episode: 202 training return: tensor(416.1270, device='cuda:0')
episode: 203 training return: tensor(375.2547, device='cuda:0')
epoch: 51 test_true_pfm: 3356.901071113401 sim_pfm: 348.3809269970322
episode: 204 training return: tensor(434.7827, device='cuda:0')
episode: 205 training return: tensor(-550.4824, device='cuda:0')
episode: 206 training return: tensor(406.7913, device='cuda:0')
episode: 207 training return: tensor(-45.4843, device='cuda:0')
epoch: 52 test_true_pfm: 3576.5812999471145 sim_pfm: 476.65912253780215
episode: 208 training return: tensor(463.7062, device='cuda:0')
episode: 209 training return: tensor(392.3547, device='cuda:0')
episode: 210 training return: tensor(389.2923, device='cuda:0')
episode: 211 training return: tensor(354.9794, device='cuda:0')
epoch: 53 test_true_pfm: 3462.1773110248887 sim_pfm: 440.0177371967778
episode: 212 training return: tensor(382.2078, device='cuda:0')
episode: 213 training return: tensor(388.0412, device='cuda:0')
episode: 214 training return: tensor(445.0282, device='cuda:0')
episode: 215 training return: tensor(175.2363, device='cuda:0')
epoch: 54 test_true_pfm: 3403.1769427573004 sim_pfm: 395.54021670257015
episode: 216 training return: tensor(415.8251, device='cuda:0')
episode: 217 training return: tensor(402.1822, device='cuda:0')
episode: 218 training return: tensor(440.2808, device='cuda:0')
episode: 219 training return: tensor(446.4170, device='cuda:0')
epoch: 55 test_true_pfm: 3477.5528908108645 sim_pfm: 418.30813129253994
episode: 220 training return: tensor(360.1431, device='cuda:0')
episode: 221 training return: tensor(413.0077, device='cuda:0')
episode: 222 training return: tensor(482.9969, device='cuda:0')
episode: 223 training return: tensor(-642.2473, device='cuda:0')
epoch: 56 test_true_pfm: 3363.3972472844557 sim_pfm: 367.2450344016931
episode: 224 training return: tensor(436.3295, device='cuda:0')
episode: 225 training return: tensor(372.1952, device='cuda:0')
episode: 226 training return: tensor(420.0184, device='cuda:0')
episode: 227 training return: tensor(448.3587, device='cuda:0')
epoch: 57 test_true_pfm: 357.9839033186345 sim_pfm: -579.1358908209271
episode: 228 training return: tensor(441.4599, device='cuda:0')
episode: 229 training return: tensor(420.1499, device='cuda:0')
episode: 230 training return: tensor(425.1852, device='cuda:0')
episode: 231 training return: tensor(-111.4943, device='cuda:0')
epoch: 58 test_true_pfm: 3504.195273961786 sim_pfm: 431.65013692336896
episode: 232 training return: tensor(451.9530, device='cuda:0')
episode: 233 training return: tensor(442.0182, device='cuda:0')
episode: 234 training return: tensor(393.6182, device='cuda:0')
episode: 235 training return: tensor(158.0193, device='cuda:0')
epoch: 59 test_true_pfm: 521.7405237846573 sim_pfm: -603.7427544665212
episode: 236 training return: tensor(409.2274, device='cuda:0')
episode: 237 training return: tensor(335.8767, device='cuda:0')
episode: 238 training return: tensor(391.8475, device='cuda:0')
episode: 239 training return: tensor(408.4358, device='cuda:0')
epoch: 60 test_true_pfm: 2408.331200821293 sim_pfm: -271.6572800236366
episode: 240 training return: tensor(340.9463, device='cuda:0')
episode: 241 training return: tensor(441.3853, device='cuda:0')
episode: 242 training return: tensor(467.1610, device='cuda:0')
episode: 243 training return: tensor(472.9409, device='cuda:0')
epoch: 61 test_true_pfm: 3474.6084149647927 sim_pfm: 413.40371864131885
episode: 244 training return: tensor(438.7094, device='cuda:0')
episode: 245 training return: tensor(465.6786, device='cuda:0')
episode: 246 training return: tensor(502.6829, device='cuda:0')
episode: 247 training return: tensor(346.7217, device='cuda:0')
epoch: 62 test_true_pfm: 3434.064591344228 sim_pfm: 387.0147362023029
episode: 248 training return: tensor(370.6533, device='cuda:0')
episode: 249 training return: tensor(420.2037, device='cuda:0')
episode: 250 training return: tensor(421.0071, device='cuda:0')
episode: 251 training return: tensor(412.4207, device='cuda:0')
epoch: 63 test_true_pfm: 3422.524138157105 sim_pfm: 368.47093750767334
episode: 252 training return: tensor(466.2179, device='cuda:0')
episode: 253 training return: tensor(508.8432, device='cuda:0')
episode: 254 training return: tensor(402.7099, device='cuda:0')
episode: 255 training return: tensor(469.4057, device='cuda:0')
epoch: 64 test_true_pfm: 3413.4299510469805 sim_pfm: 408.1899383740383
episode: 256 training return: tensor(399.6083, device='cuda:0')
episode: 257 training return: tensor(393.1051, device='cuda:0')
episode: 258 training return: tensor(396.9529, device='cuda:0')
episode: 259 training return: tensor(365.0296, device='cuda:0')
epoch: 65 test_true_pfm: 3372.1361491084353 sim_pfm: 355.8857930599382
episode: 260 training return: tensor(400.9640, device='cuda:0')
episode: 261 training return: tensor(435.9676, device='cuda:0')
episode: 262 training return: tensor(452.6364, device='cuda:0')
episode: 263 training return: tensor(397.9968, device='cuda:0')
epoch: 66 test_true_pfm: 3449.3223921038116 sim_pfm: 417.52975594669505
episode: 264 training return: tensor(383.7982, device='cuda:0')
episode: 265 training return: tensor(446.3120, device='cuda:0')
episode: 266 training return: tensor(402.9215, device='cuda:0')
episode: 267 training return: tensor(309.8661, device='cuda:0')
epoch: 67 test_true_pfm: 3432.3230259442075 sim_pfm: 384.2635687812581
episode: 268 training return: tensor(418.2278, device='cuda:0')
episode: 269 training return: tensor(399.9706, device='cuda:0')
episode: 270 training return: tensor(403.0050, device='cuda:0')
episode: 271 training return: tensor(374.3963, device='cuda:0')
epoch: 68 test_true_pfm: 3599.890460157398 sim_pfm: 475.293384384034
episode: 272 training return: tensor(386.1966, device='cuda:0')
episode: 273 training return: tensor(397.4662, device='cuda:0')
episode: 274 training return: tensor(359.4330, device='cuda:0')
episode: 275 training return: tensor(453.2021, device='cuda:0')
epoch: 69 test_true_pfm: 3582.9983023260706 sim_pfm: 503.9353006197295
episode: 276 training return: tensor(414.4103, device='cuda:0')
episode: 277 training return: tensor(432.4958, device='cuda:0')
episode: 278 training return: tensor(403.3085, device='cuda:0')
episode: 279 training return: tensor(402.1694, device='cuda:0')
epoch: 70 test_true_pfm: 3438.2503185604123 sim_pfm: 395.0539294097107
episode: 280 training return: tensor(352.4283, device='cuda:0')
episode: 281 training return: tensor(379.3068, device='cuda:0')
episode: 282 training return: tensor(406.8752, device='cuda:0')
episode: 283 training return: tensor(396.4033, device='cuda:0')
epoch: 71 test_true_pfm: 3341.100765319197 sim_pfm: 324.79490777941345
episode: 284 training return: tensor(402.2834, device='cuda:0')
episode: 285 training return: tensor(392.6579, device='cuda:0')
episode: 286 training return: tensor(378.5985, device='cuda:0')
episode: 287 training return: tensor(394.6171, device='cuda:0')
epoch: 72 test_true_pfm: 3425.439644051268 sim_pfm: 420.3263278763043
episode: 288 training return: tensor(307.3195, device='cuda:0')
episode: 289 training return: tensor(421.1188, device='cuda:0')
episode: 290 training return: tensor(390.0587, device='cuda:0')
episode: 291 training return: tensor(400.8019, device='cuda:0')
epoch: 73 test_true_pfm: 3454.5297655492964 sim_pfm: 403.1633291036317
episode: 292 training return: tensor(372.5979, device='cuda:0')
episode: 293 training return: tensor(448.3265, device='cuda:0')
episode: 294 training return: tensor(435.5696, device='cuda:0')
episode: 295 training return: tensor(403.0342, device='cuda:0')
epoch: 74 test_true_pfm: 3533.0139558583196 sim_pfm: 471.2002829283786
episode: 296 training return: tensor(410.2515, device='cuda:0')
episode: 297 training return: tensor(379.7263, device='cuda:0')
episode: 298 training return: tensor(390.6154, device='cuda:0')
episode: 299 training return: tensor(143.9899, device='cuda:0')
epoch: 75 test_true_pfm: 3467.6353272176116 sim_pfm: 435.34866973752895
episode: 300 training return: tensor(357.2494, device='cuda:0')
episode: 301 training return: tensor(363.4920, device='cuda:0')
episode: 302 training return: tensor(462.9598, device='cuda:0')
episode: 303 training return: tensor(377.0869, device='cuda:0')
epoch: 76 test_true_pfm: 3388.403988878128 sim_pfm: 350.42173666198505
episode: 304 training return: tensor(381.2431, device='cuda:0')
episode: 305 training return: tensor(335.7169, device='cuda:0')
episode: 306 training return: tensor(467.7572, device='cuda:0')
episode: 307 training return: tensor(344.3160, device='cuda:0')
epoch: 77 test_true_pfm: 3465.159838752441 sim_pfm: 350.88841824792325
episode: 308 training return: tensor(403.6959, device='cuda:0')
episode: 309 training return: tensor(398.8803, device='cuda:0')
episode: 310 training return: tensor(373.1012, device='cuda:0')
episode: 311 training return: tensor(416.6445, device='cuda:0')
epoch: 78 test_true_pfm: 3446.0553913090757 sim_pfm: 415.95603753401275
episode: 312 training return: tensor(356.7054, device='cuda:0')
episode: 313 training return: tensor(451.3718, device='cuda:0')
episode: 314 training return: tensor(418.5269, device='cuda:0')
episode: 315 training return: tensor(370.8537, device='cuda:0')
epoch: 79 test_true_pfm: 3506.381223008752 sim_pfm: 430.72008010349236
episode: 316 training return: tensor(439.1099, device='cuda:0')
episode: 317 training return: tensor(380.2958, device='cuda:0')
episode: 318 training return: tensor(377.3825, device='cuda:0')
episode: 319 training return: tensor(390.4604, device='cuda:0')
epoch: 80 test_true_pfm: 3487.177975381153 sim_pfm: 431.16555261192843
episode: 320 training return: tensor(368.1651, device='cuda:0')
episode: 321 training return: tensor(-74.9194, device='cuda:0')
episode: 322 training return: tensor(329.2191, device='cuda:0')
episode: 323 training return: tensor(436.9174, device='cuda:0')
epoch: 81 test_true_pfm: 3293.1676353964517 sim_pfm: 302.51104314415716
episode: 324 training return: tensor(356.6618, device='cuda:0')
episode: 325 training return: tensor(389.2589, device='cuda:0')
episode: 326 training return: tensor(388.7041, device='cuda:0')
episode: 327 training return: tensor(411.0072, device='cuda:0')
epoch: 82 test_true_pfm: 3359.136035814223 sim_pfm: 351.66290068040445
episode: 328 training return: tensor(397.0638, device='cuda:0')
episode: 329 training return: tensor(357.0150, device='cuda:0')
episode: 330 training return: tensor(380.1603, device='cuda:0')
episode: 331 training return: tensor(397.2823, device='cuda:0')
epoch: 83 test_true_pfm: 3452.27223652039 sim_pfm: 406.17475001156953
episode: 332 training return: tensor(384.1581, device='cuda:0')
episode: 333 training return: tensor(357.6505, device='cuda:0')
episode: 334 training return: tensor(-566.8584, device='cuda:0')
episode: 335 training return: tensor(394.7806, device='cuda:0')
epoch: 84 test_true_pfm: 3533.7960767137993 sim_pfm: 501.71415869704407
episode: 336 training return: tensor(318.6569, device='cuda:0')
episode: 337 training return: tensor(337.2997, device='cuda:0')
episode: 338 training return: tensor(372.1859, device='cuda:0')
episode: 339 training return: tensor(412.4877, device='cuda:0')
epoch: 85 test_true_pfm: 3427.304222716666 sim_pfm: 388.8728837142019
episode: 340 training return: tensor(365.4479, device='cuda:0')
episode: 341 training return: tensor(375.9029, device='cuda:0')
episode: 342 training return: tensor(361.7491, device='cuda:0')
episode: 343 training return: tensor(360.6666, device='cuda:0')
epoch: 86 test_true_pfm: 3394.2126766512106 sim_pfm: 389.5937685814376
episode: 344 training return: tensor(391.9692, device='cuda:0')
episode: 345 training return: tensor(371.1741, device='cuda:0')
episode: 346 training return: tensor(391.8130, device='cuda:0')
episode: 347 training return: tensor(397.6832, device='cuda:0')
epoch: 87 test_true_pfm: 3467.535065733037 sim_pfm: 435.3378235269338
episode: 348 training return: tensor(344.8702, device='cuda:0')
episode: 349 training return: tensor(389.0523, device='cuda:0')
episode: 350 training return: tensor(327.5547, device='cuda:0')
episode: 351 training return: tensor(428.6044, device='cuda:0')
epoch: 88 test_true_pfm: 3446.224144527519 sim_pfm: 378.2475060087551
episode: 352 training return: tensor(425.1419, device='cuda:0')
episode: 353 training return: tensor(348.9453, device='cuda:0')
episode: 354 training return: tensor(403.6575, device='cuda:0')
episode: 355 training return: tensor(456.3551, device='cuda:0')
epoch: 89 test_true_pfm: 3516.1687994922468 sim_pfm: 493.8643660004503
episode: 356 training return: tensor(408.8176, device='cuda:0')
episode: 357 training return: tensor(471.9366, device='cuda:0')
episode: 358 training return: tensor(342.1691, device='cuda:0')
episode: 359 training return: tensor(363.2288, device='cuda:0')
epoch: 90 test_true_pfm: 3360.8188419635553 sim_pfm: 342.7552410174394
episode: 360 training return: tensor(393.8932, device='cuda:0')
episode: 361 training return: tensor(516.2817, device='cuda:0')
episode: 362 training return: tensor(403.8321, device='cuda:0')
episode: 363 training return: tensor(399.3022, device='cuda:0')
epoch: 91 test_true_pfm: 3395.0428827260353 sim_pfm: 372.072511693812
episode: 364 training return: tensor(452.6442, device='cuda:0')
episode: 365 training return: tensor(410.0056, device='cuda:0')
episode: 366 training return: tensor(312.9672, device='cuda:0')
episode: 367 training return: tensor(368.9092, device='cuda:0')
epoch: 92 test_true_pfm: 3333.741989934313 sim_pfm: 340.9530879346033
episode: 368 training return: tensor(368.8807, device='cuda:0')
episode: 369 training return: tensor(389.1407, device='cuda:0')
episode: 370 training return: tensor(418.1660, device='cuda:0')
episode: 371 training return: tensor(354.7115, device='cuda:0')
epoch: 93 test_true_pfm: 3530.0357609066773 sim_pfm: 462.31668784300564
episode: 372 training return: tensor(359.8114, device='cuda:0')
episode: 373 training return: tensor(405.5918, device='cuda:0')
episode: 374 training return: tensor(405.6263, device='cuda:0')
episode: 375 training return: tensor(499.8567, device='cuda:0')
epoch: 94 test_true_pfm: 3366.8396853486615 sim_pfm: 352.9498447329388
episode: 376 training return: tensor(345.0516, device='cuda:0')
episode: 377 training return: tensor(348.6949, device='cuda:0')
episode: 378 training return: tensor(372.3599, device='cuda:0')
episode: 379 training return: tensor(342.0498, device='cuda:0')
epoch: 95 test_true_pfm: 3453.3998996497844 sim_pfm: 396.0768475536024
episode: 380 training return: tensor(382.3105, device='cuda:0')
episode: 381 training return: tensor(376.4424, device='cuda:0')
episode: 382 training return: tensor(334.1310, device='cuda:0')
episode: 383 training return: tensor(450.5809, device='cuda:0')
epoch: 96 test_true_pfm: 3310.3484044998186 sim_pfm: 311.9932035890233
episode: 384 training return: tensor(409.5753, device='cuda:0')
episode: 385 training return: tensor(433.9809, device='cuda:0')
episode: 386 training return: tensor(367.5434, device='cuda:0')
episode: 387 training return: tensor(387.0730, device='cuda:0')
epoch: 97 test_true_pfm: 3391.0056779496367 sim_pfm: 367.6629840201737
episode: 388 training return: tensor(380.4143, device='cuda:0')
episode: 389 training return: tensor(398.7028, device='cuda:0')
episode: 390 training return: tensor(332.5408, device='cuda:0')
episode: 391 training return: tensor(396.3186, device='cuda:0')
epoch: 98 test_true_pfm: 3410.444739756895 sim_pfm: 411.43900089435436
episode: 392 training return: tensor(419.5919, device='cuda:0')
episode: 393 training return: tensor(387.9369, device='cuda:0')
episode: 394 training return: tensor(336.8635, device='cuda:0')
episode: 395 training return: tensor(362.0063, device='cuda:0')
epoch: 99 test_true_pfm: 3387.386561682379 sim_pfm: 367.62635430374456
episode: 396 training return: tensor(369.4873, device='cuda:0')
episode: 397 training return: tensor(358.4885, device='cuda:0')
episode: 398 training return: tensor(391.7512, device='cuda:0')
episode: 399 training return: tensor(337.8450, device='cuda:0')
epoch: 100 test_true_pfm: 3322.298566671969 sim_pfm: 319.22903998378507
episode: 400 training return: tensor(356.3741, device='cuda:0')
episode: 401 training return: tensor(388.6948, device='cuda:0')
episode: 402 training return: tensor(346.5921, device='cuda:0')
episode: 403 training return: tensor(414.6616, device='cuda:0')
epoch: 101 test_true_pfm: 3363.6640679257343 sim_pfm: 351.9501599763947
episode: 404 training return: tensor(430.6677, device='cuda:0')
episode: 405 training return: tensor(359.9076, device='cuda:0')
episode: 406 training return: tensor(374.1093, device='cuda:0')
episode: 407 training return: tensor(379.1133, device='cuda:0')
epoch: 102 test_true_pfm: 3278.4274630011546 sim_pfm: 283.94737401835545
episode: 408 training return: tensor(378.3893, device='cuda:0')
episode: 409 training return: tensor(404.6306, device='cuda:0')
episode: 410 training return: tensor(389.4399, device='cuda:0')
episode: 411 training return: tensor(411.2150, device='cuda:0')
epoch: 103 test_true_pfm: 3430.17492075956 sim_pfm: 395.85135851074784
episode: 412 training return: tensor(402.0586, device='cuda:0')
episode: 413 training return: tensor(346.0009, device='cuda:0')
episode: 414 training return: tensor(328.8929, device='cuda:0')
episode: 415 training return: tensor(386.8068, device='cuda:0')
epoch: 104 test_true_pfm: 3348.015144818906 sim_pfm: 340.81720310325426
episode: 416 training return: tensor(384.7220, device='cuda:0')
episode: 417 training return: tensor(422.3982, device='cuda:0')
episode: 418 training return: tensor(459.4290, device='cuda:0')
episode: 419 training return: tensor(381.6007, device='cuda:0')
epoch: 105 test_true_pfm: 3319.9780202625207 sim_pfm: 303.78061574030045
episode: 420 training return: tensor(382.0533, device='cuda:0')
episode: 421 training return: tensor(387.2076, device='cuda:0')
episode: 422 training return: tensor(375.0990, device='cuda:0')
episode: 423 training return: tensor(381.7974, device='cuda:0')
epoch: 106 test_true_pfm: 3394.689739273337 sim_pfm: 354.84260138489
episode: 424 training return: tensor(349.9192, device='cuda:0')
episode: 425 training return: tensor(382.7183, device='cuda:0')
episode: 426 training return: tensor(341.9015, device='cuda:0')
episode: 427 training return: tensor(338.6685, device='cuda:0')
epoch: 107 test_true_pfm: 3296.6168799731718 sim_pfm: 300.0110094617509
episode: 428 training return: tensor(401.9622, device='cuda:0')
episode: 429 training return: tensor(320.1371, device='cuda:0')
episode: 430 training return: tensor(431.8752, device='cuda:0')
episode: 431 training return: tensor(374.3491, device='cuda:0')
epoch: 108 test_true_pfm: 3512.348092244847 sim_pfm: 420.5090680719392
episode: 432 training return: tensor(452.5952, device='cuda:0')
episode: 433 training return: tensor(401.1622, device='cuda:0')
episode: 434 training return: tensor(412.9073, device='cuda:0')
episode: 435 training return: tensor(364.5674, device='cuda:0')
epoch: 109 test_true_pfm: 3469.2686372009 sim_pfm: 405.4230732258875
episode: 436 training return: tensor(361.6411, device='cuda:0')
episode: 437 training return: tensor(395.0900, device='cuda:0')
episode: 438 training return: tensor(377.4461, device='cuda:0')
episode: 439 training return: tensor(283.9610, device='cuda:0')
epoch: 110 test_true_pfm: 3418.697759695134 sim_pfm: 397.1928875517527
episode: 440 training return: tensor(311.5088, device='cuda:0')
episode: 441 training return: tensor(334.3374, device='cuda:0')
episode: 442 training return: tensor(369.7915, device='cuda:0')
episode: 443 training return: tensor(376.6710, device='cuda:0')
epoch: 111 test_true_pfm: 3376.263653752571 sim_pfm: 342.09240461419296
episode: 444 training return: tensor(306.9769, device='cuda:0')
episode: 445 training return: tensor(359.7079, device='cuda:0')
episode: 446 training return: tensor(360.8447, device='cuda:0')
episode: 447 training return: tensor(351.2607, device='cuda:0')
epoch: 112 test_true_pfm: 3351.496451333334 sim_pfm: 342.8458215331775
episode: 448 training return: tensor(378.2029, device='cuda:0')
episode: 449 training return: tensor(416.0429, device='cuda:0')
episode: 450 training return: tensor(403.6854, device='cuda:0')
episode: 451 training return: tensor(430.5748, device='cuda:0')
epoch: 113 test_true_pfm: 3338.7156142846666 sim_pfm: 329.39405877838726
episode: 452 training return: tensor(321.5203, device='cuda:0')
episode: 453 training return: tensor(326.3365, device='cuda:0')
episode: 454 training return: tensor(418.2899, device='cuda:0')
episode: 455 training return: tensor(352.6978, device='cuda:0')
epoch: 114 test_true_pfm: 3434.464547531015 sim_pfm: 401.03487832138006
episode: 456 training return: tensor(399.0073, device='cuda:0')
episode: 457 training return: tensor(434.9893, device='cuda:0')
episode: 458 training return: tensor(356.2757, device='cuda:0')
episode: 459 training return: tensor(398.1136, device='cuda:0')
epoch: 115 test_true_pfm: 3539.247879656766 sim_pfm: 449.6772811934837
episode: 460 training return: tensor(351.0480, device='cuda:0')
episode: 461 training return: tensor(383.8908, device='cuda:0')
episode: 462 training return: tensor(332.7114, device='cuda:0')
episode: 463 training return: tensor(296.9890, device='cuda:0')
epoch: 116 test_true_pfm: 3446.9164734105566 sim_pfm: 396.3022830443612
episode: 464 training return: tensor(366.3487, device='cuda:0')
episode: 465 training return: tensor(340.8617, device='cuda:0')
episode: 466 training return: tensor(324.3960, device='cuda:0')
episode: 467 training return: tensor(217.7589, device='cuda:0')
epoch: 117 test_true_pfm: 3312.6723907165747 sim_pfm: 307.3137212653431
episode: 468 training return: tensor(424.3088, device='cuda:0')
episode: 469 training return: tensor(486.3486, device='cuda:0')
episode: 470 training return: tensor(386.6736, device='cuda:0')
episode: 471 training return: tensor(343.7025, device='cuda:0')
epoch: 118 test_true_pfm: 3459.062177058741 sim_pfm: 406.8860071200567
episode: 472 training return: tensor(354.6252, device='cuda:0')
episode: 473 training return: tensor(381.6782, device='cuda:0')
episode: 474 training return: tensor(415.6252, device='cuda:0')
episode: 475 training return: tensor(354.1985, device='cuda:0')
epoch: 119 test_true_pfm: 3282.1441753402664 sim_pfm: 293.83260473340243
episode: 476 training return: tensor(373.7307, device='cuda:0')
episode: 477 training return: tensor(322.4367, device='cuda:0')
episode: 478 training return: tensor(374.5882, device='cuda:0')
episode: 479 training return: tensor(338.4644, device='cuda:0')
epoch: 120 test_true_pfm: 3418.0606640941646 sim_pfm: 372.26235695387004
episode: 480 training return: tensor(482.1758, device='cuda:0')
episode: 481 training return: tensor(349.8189, device='cuda:0')
episode: 482 training return: tensor(396.8718, device='cuda:0')
episode: 483 training return: tensor(389.0468, device='cuda:0')
epoch: 121 test_true_pfm: 3275.5464652154046 sim_pfm: 282.16718238338945
episode: 484 training return: tensor(375.2858, device='cuda:0')
episode: 485 training return: tensor(331.1235, device='cuda:0')
episode: 486 training return: tensor(389.9133, device='cuda:0')
episode: 487 training return: tensor(340.1683, device='cuda:0')
epoch: 122 test_true_pfm: 3403.9794198285304 sim_pfm: 378.0548478383959
episode: 488 training return: tensor(346.2720, device='cuda:0')
episode: 489 training return: tensor(462.0354, device='cuda:0')
episode: 490 training return: tensor(345.5594, device='cuda:0')
episode: 491 training return: tensor(390.0270, device='cuda:0')
epoch: 123 test_true_pfm: 3368.479100722186 sim_pfm: 361.1015040628651
episode: 492 training return: tensor(342.5515, device='cuda:0')
episode: 493 training return: tensor(458.8823, device='cuda:0')
episode: 494 training return: tensor(426.3721, device='cuda:0')
episode: 495 training return: tensor(417.0639, device='cuda:0')
epoch: 124 test_true_pfm: 3396.153164197924 sim_pfm: 366.261305054087
episode: 496 training return: tensor(371.1660, device='cuda:0')
episode: 497 training return: tensor(319.6359, device='cuda:0')
episode: 498 training return: tensor(371.4451, device='cuda:0')
episode: 499 training return: tensor(413.0245, device='cuda:0')
epoch: 125 test_true_pfm: 3423.9804596835074 sim_pfm: 390.57164943953586
episode: 500 training return: tensor(401.4580, device='cuda:0')
episode: 501 training return: tensor(415.4080, device='cuda:0')
episode: 502 training return: tensor(361.8939, device='cuda:0')
episode: 503 training return: tensor(332.2472, device='cuda:0')
epoch: 126 test_true_pfm: 3244.7786597921404 sim_pfm: 271.60977041044197
episode: 504 training return: tensor(353.9569, device='cuda:0')
episode: 505 training return: tensor(353.8666, device='cuda:0')
episode: 506 training return: tensor(395.6870, device='cuda:0')
episode: 507 training return: tensor(372.1062, device='cuda:0')
epoch: 127 test_true_pfm: 3350.693525256065 sim_pfm: 337.4757364568941
episode: 508 training return: tensor(390.3292, device='cuda:0')
episode: 509 training return: tensor(311.7177, device='cuda:0')
episode: 510 training return: tensor(421.9209, device='cuda:0')
episode: 511 training return: tensor(372.6000, device='cuda:0')
epoch: 128 test_true_pfm: 3365.5715543227666 sim_pfm: 356.3128785790759
episode: 512 training return: tensor(389.2896, device='cuda:0')
episode: 513 training return: tensor(399.6485, device='cuda:0')
episode: 514 training return: tensor(412.8391, device='cuda:0')
episode: 515 training return: tensor(378.2098, device='cuda:0')
epoch: 129 test_true_pfm: 3465.7168026733634 sim_pfm: 415.07232920005725
episode: 516 training return: tensor(391.0603, device='cuda:0')
episode: 517 training return: tensor(366.3054, device='cuda:0')
episode: 518 training return: tensor(419.6924, device='cuda:0')
episode: 519 training return: tensor(442.1781, device='cuda:0')
epoch: 130 test_true_pfm: 3457.224202021461 sim_pfm: 415.51403171008377
episode: 520 training return: tensor(384.6337, device='cuda:0')
episode: 521 training return: tensor(357.9889, device='cuda:0')
episode: 522 training return: tensor(402.6945, device='cuda:0')
episode: 523 training return: tensor(470.8719, device='cuda:0')
epoch: 131 test_true_pfm: 3392.429032827489 sim_pfm: 360.0258186071296
episode: 524 training return: tensor(348.9085, device='cuda:0')
episode: 525 training return: tensor(374.5045, device='cuda:0')
episode: 526 training return: tensor(438.8315, device='cuda:0')
episode: 527 training return: tensor(348.5407, device='cuda:0')
epoch: 132 test_true_pfm: 3456.664423750721 sim_pfm: 416.94379384831217
episode: 528 training return: tensor(359.5923, device='cuda:0')
episode: 529 training return: tensor(358.1969, device='cuda:0')
episode: 530 training return: tensor(364.0587, device='cuda:0')
episode: 531 training return: tensor(420.4721, device='cuda:0')
epoch: 133 test_true_pfm: 3337.734599625001 sim_pfm: 319.9468844793931
episode: 532 training return: tensor(424.7499, device='cuda:0')
episode: 533 training return: tensor(396.5659, device='cuda:0')
episode: 534 training return: tensor(385.4021, device='cuda:0')
episode: 535 training return: tensor(332.8682, device='cuda:0')
epoch: 134 test_true_pfm: 3331.232114338209 sim_pfm: 325.0211775493711
episode: 536 training return: tensor(388.0747, device='cuda:0')
episode: 537 training return: tensor(403.0187, device='cuda:0')
episode: 538 training return: tensor(348.4241, device='cuda:0')
episode: 539 training return: tensor(380.0166, device='cuda:0')
epoch: 135 test_true_pfm: 3385.610857004584 sim_pfm: 361.83864443853963
episode: 540 training return: tensor(348.3339, device='cuda:0')
episode: 541 training return: tensor(410.4697, device='cuda:0')
episode: 542 training return: tensor(376.5141, device='cuda:0')
episode: 543 training return: tensor(326.3770, device='cuda:0')
epoch: 136 test_true_pfm: 3361.698199778855 sim_pfm: 352.82771379024297
episode: 544 training return: tensor(413.5959, device='cuda:0')
episode: 545 training return: tensor(388.2534, device='cuda:0')
episode: 546 training return: tensor(401.7567, device='cuda:0')
episode: 547 training return: tensor(377.0882, device='cuda:0')
epoch: 137 test_true_pfm: 3346.2160290886773 sim_pfm: 343.0569355282544
episode: 548 training return: tensor(376.8523, device='cuda:0')
episode: 549 training return: tensor(349.8716, device='cuda:0')
episode: 550 training return: tensor(381.3423, device='cuda:0')
episode: 551 training return: tensor(330.6907, device='cuda:0')
epoch: 138 test_true_pfm: 3378.6663062256557 sim_pfm: 360.0004527182512
episode: 552 training return: tensor(337.4084, device='cuda:0')
episode: 553 training return: tensor(361.5908, device='cuda:0')
episode: 554 training return: tensor(370.6914, device='cuda:0')
episode: 555 training return: tensor(365.5431, device='cuda:0')
epoch: 139 test_true_pfm: 3359.7301407334744 sim_pfm: 347.5503335847946
episode: 556 training return: tensor(422.6393, device='cuda:0')
episode: 557 training return: tensor(386.2677, device='cuda:0')
episode: 558 training return: tensor(405.3548, device='cuda:0')
episode: 559 training return: tensor(372.3861, device='cuda:0')
epoch: 140 test_true_pfm: 3415.9253708269985 sim_pfm: 386.77040363561053
episode: 560 training return: tensor(361.8112, device='cuda:0')
episode: 561 training return: tensor(462.3306, device='cuda:0')
episode: 562 training return: tensor(403.3321, device='cuda:0')
episode: 563 training return: tensor(407.9138, device='cuda:0')
epoch: 141 test_true_pfm: 3372.5510508873235 sim_pfm: 355.1247180417704
episode: 564 training return: tensor(421.7690, device='cuda:0')
episode: 565 training return: tensor(352.5869, device='cuda:0')
episode: 566 training return: tensor(425.6686, device='cuda:0')
episode: 567 training return: tensor(424.1653, device='cuda:0')
epoch: 142 test_true_pfm: 3320.025026763629 sim_pfm: 327.22317626616376
episode: 568 training return: tensor(417.9992, device='cuda:0')
episode: 569 training return: tensor(377.7722, device='cuda:0')
episode: 570 training return: tensor(408.4938, device='cuda:0')
episode: 571 training return: tensor(333.1480, device='cuda:0')
epoch: 143 test_true_pfm: 3361.1501001681313 sim_pfm: 355.81161625508685
episode: 572 training return: tensor(375.1587, device='cuda:0')
episode: 573 training return: tensor(415.1943, device='cuda:0')
episode: 574 training return: tensor(399.6951, device='cuda:0')
episode: 575 training return: tensor(403.3885, device='cuda:0')
epoch: 144 test_true_pfm: 3395.6333989044524 sim_pfm: 370.8196230302371
episode: 576 training return: tensor(364.0007, device='cuda:0')
episode: 577 training return: tensor(374.2343, device='cuda:0')
episode: 578 training return: tensor(438.0730, device='cuda:0')
episode: 579 training return: tensor(406.2619, device='cuda:0')
epoch: 145 test_true_pfm: 3386.700008119107 sim_pfm: 362.6293640039706
episode: 580 training return: tensor(361.3334, device='cuda:0')
episode: 581 training return: tensor(354.8551, device='cuda:0')
episode: 582 training return: tensor(385.6938, device='cuda:0')
episode: 583 training return: tensor(398.8854, device='cuda:0')
epoch: 146 test_true_pfm: 3400.414057016154 sim_pfm: 368.4814367549261
episode: 584 training return: tensor(443.2137, device='cuda:0')
episode: 585 training return: tensor(416.6158, device='cuda:0')
episode: 586 training return: tensor(395.1127, device='cuda:0')
episode: 587 training return: tensor(373.3834, device='cuda:0')
epoch: 147 test_true_pfm: 3395.0834335367617 sim_pfm: 377.61305391150137
episode: 588 training return: tensor(415.2712, device='cuda:0')
episode: 589 training return: tensor(366.3171, device='cuda:0')
episode: 590 training return: tensor(368.4350, device='cuda:0')
episode: 591 training return: tensor(356.1922, device='cuda:0')
epoch: 148 test_true_pfm: 3456.01979114606 sim_pfm: 392.3369089786235
episode: 592 training return: tensor(386.1280, device='cuda:0')
episode: 593 training return: tensor(384.0866, device='cuda:0')
episode: 594 training return: tensor(399.5613, device='cuda:0')
episode: 595 training return: tensor(369.4224, device='cuda:0')
epoch: 149 test_true_pfm: 3378.6199801407834 sim_pfm: 348.7436376933474
episode: 596 training return: tensor(361.3473, device='cuda:0')
episode: 597 training return: tensor(368.7355, device='cuda:0')
episode: 598 training return: tensor(402.8505, device='cuda:0')
episode: 599 training return: tensor(359.5135, device='cuda:0')
epoch: 150 test_true_pfm: 3363.2629501732204 sim_pfm: 355.01321244023467
