['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '4', '--data', '100000', '--regu', '0.05']
2661.491715021024
episode: 0 training return: tensor(-254.8635, device='cuda:0')
episode: 1 training return: tensor(-165.2920, device='cuda:0')
episode: 2 training return: tensor(49.6486, device='cuda:0')
episode: 3 training return: tensor(274.3253, device='cuda:0')
epoch: 1 test_true_pfm: 2875.7225982833656 sim_pfm: 21.46742424486244
episode: 4 training return: tensor(327.9589, device='cuda:0')
episode: 5 training return: tensor(-163.0218, device='cuda:0')
episode: 6 training return: tensor(285.5111, device='cuda:0')
episode: 7 training return: tensor(-177.1751, device='cuda:0')
epoch: 2 test_true_pfm: 1971.7743261632388 sim_pfm: 163.94535328971688
episode: 8 training return: tensor(369.4519, device='cuda:0')
episode: 9 training return: tensor(-21.5690, device='cuda:0')
episode: 10 training return: tensor(221.9511, device='cuda:0')
episode: 11 training return: tensor(6.9852, device='cuda:0')
epoch: 3 test_true_pfm: 3052.674317795197 sim_pfm: 14.168127213410722
episode: 12 training return: tensor(-85.1229, device='cuda:0')
episode: 13 training return: tensor(-89.0803, device='cuda:0')
episode: 14 training return: tensor(-173.6693, device='cuda:0')
episode: 15 training return: tensor(172.7000, device='cuda:0')
epoch: 4 test_true_pfm: 2864.090833187751 sim_pfm: 97.00170062536684
episode: 16 training return: tensor(39.3694, device='cuda:0')
episode: 17 training return: tensor(-28.2390, device='cuda:0')
episode: 18 training return: tensor(-220.8311, device='cuda:0')
episode: 19 training return: tensor(-162.5486, device='cuda:0')
epoch: 5 test_true_pfm: 2086.3690408291927 sim_pfm: 10.18741048957842
episode: 20 training return: tensor(-49.0525, device='cuda:0')
episode: 21 training return: tensor(-160.1035, device='cuda:0')
episode: 22 training return: tensor(264.6178, device='cuda:0')
episode: 23 training return: tensor(341.8923, device='cuda:0')
epoch: 6 test_true_pfm: 3396.4632849167815 sim_pfm: 133.25461168281618
episode: 24 training return: tensor(20.7120, device='cuda:0')
episode: 25 training return: tensor(271.0848, device='cuda:0')
episode: 26 training return: tensor(251.1203, device='cuda:0')
episode: 27 training return: tensor(269.6106, device='cuda:0')
epoch: 7 test_true_pfm: 2383.5399134918785 sim_pfm: 103.23504585693202
episode: 28 training return: tensor(-170.1047, device='cuda:0')
episode: 29 training return: tensor(-175.0865, device='cuda:0')
episode: 30 training return: tensor(-73.4494, device='cuda:0')
episode: 31 training return: tensor(86.6250, device='cuda:0')
epoch: 8 test_true_pfm: 2453.4906360322448 sim_pfm: 158.40064738570558
episode: 32 training return: tensor(243.2169, device='cuda:0')
episode: 33 training return: tensor(90.7953, device='cuda:0')
episode: 34 training return: tensor(81.6789, device='cuda:0')
episode: 35 training return: tensor(44.2690, device='cuda:0')
epoch: 9 test_true_pfm: 2670.591202595975 sim_pfm: 212.57339654752286
episode: 36 training return: tensor(-71.1381, device='cuda:0')
episode: 37 training return: tensor(286.0301, device='cuda:0')
episode: 38 training return: tensor(9.3118, device='cuda:0')
episode: 39 training return: tensor(293.0363, device='cuda:0')
epoch: 10 test_true_pfm: 2896.352724249445 sim_pfm: 263.1006693167922
episode: 40 training return: tensor(-106.7442, device='cuda:0')
episode: 41 training return: tensor(-178.2207, device='cuda:0')
episode: 42 training return: tensor(-199.1766, device='cuda:0')
episode: 43 training return: tensor(297.9702, device='cuda:0')
epoch: 11 test_true_pfm: 2735.886665398748 sim_pfm: 215.0949552251259
episode: 44 training return: tensor(252.8087, device='cuda:0')
episode: 45 training return: tensor(276.4060, device='cuda:0')
episode: 46 training return: tensor(256.2026, device='cuda:0')
episode: 47 training return: tensor(138.8920, device='cuda:0')
epoch: 12 test_true_pfm: 2654.23815087745 sim_pfm: -34.86598501779372
episode: 48 training return: tensor(59.6053, device='cuda:0')
episode: 49 training return: tensor(244.6889, device='cuda:0')
episode: 50 training return: tensor(-369.2527, device='cuda:0')
episode: 51 training return: tensor(162.2896, device='cuda:0')
epoch: 13 test_true_pfm: 2660.078951505578 sim_pfm: 92.73733001489502
episode: 52 training return: tensor(-114.8047, device='cuda:0')
episode: 53 training return: tensor(240.3038, device='cuda:0')
episode: 54 training return: tensor(-63.4178, device='cuda:0')
episode: 55 training return: tensor(227.5796, device='cuda:0')
epoch: 14 test_true_pfm: 3277.2152473826623 sim_pfm: 125.09682786997291
episode: 56 training return: tensor(-176.0842, device='cuda:0')
episode: 57 training return: tensor(-199.3900, device='cuda:0')
episode: 58 training return: tensor(-151.0343, device='cuda:0')
episode: 59 training return: tensor(274.9532, device='cuda:0')
epoch: 15 test_true_pfm: 3105.0575113113846 sim_pfm: 300.1578113719006
episode: 60 training return: tensor(266.6981, device='cuda:0')
episode: 61 training return: tensor(-28.1303, device='cuda:0')
episode: 62 training return: tensor(305.0210, device='cuda:0')
episode: 63 training return: tensor(-157.2892, device='cuda:0')
epoch: 16 test_true_pfm: 3373.0369261998653 sim_pfm: 124.21203343905897
episode: 64 training return: tensor(230.5067, device='cuda:0')
episode: 65 training return: tensor(-65.5533, device='cuda:0')
episode: 66 training return: tensor(264.7086, device='cuda:0')
episode: 67 training return: tensor(53.5365, device='cuda:0')
epoch: 17 test_true_pfm: 2773.6351762979034 sim_pfm: 187.8341849525847
episode: 68 training return: tensor(36.0406, device='cuda:0')
episode: 69 training return: tensor(-220.0320, device='cuda:0')
episode: 70 training return: tensor(271.9337, device='cuda:0')
episode: 71 training return: tensor(-277.9364, device='cuda:0')
epoch: 18 test_true_pfm: 3352.0455993034952 sim_pfm: 266.22876221494516
episode: 72 training return: tensor(190.3744, device='cuda:0')
episode: 73 training return: tensor(232.8427, device='cuda:0')
episode: 74 training return: tensor(-115.1339, device='cuda:0')
episode: 75 training return: tensor(-40.2545, device='cuda:0')
epoch: 19 test_true_pfm: 3070.2640730586995 sim_pfm: 84.90381368988892
episode: 76 training return: tensor(148.7484, device='cuda:0')
episode: 77 training return: tensor(-103.6125, device='cuda:0')
episode: 78 training return: tensor(281.3081, device='cuda:0')
episode: 79 training return: tensor(264.8066, device='cuda:0')
epoch: 20 test_true_pfm: 3326.8369182858246 sim_pfm: -42.91651769725528
episode: 80 training return: tensor(238.7860, device='cuda:0')
episode: 81 training return: tensor(318.8922, device='cuda:0')
episode: 82 training return: tensor(285.8571, device='cuda:0')
episode: 83 training return: tensor(-242.3565, device='cuda:0')
epoch: 21 test_true_pfm: 2684.952558702398 sim_pfm: 287.8573994472681
episode: 84 training return: tensor(128.9973, device='cuda:0')
episode: 85 training return: tensor(-130.2328, device='cuda:0')
episode: 86 training return: tensor(46.7829, device='cuda:0')
episode: 87 training return: tensor(-195.2819, device='cuda:0')
epoch: 22 test_true_pfm: 2759.5164937318295 sim_pfm: -138.30133071972523
episode: 88 training return: tensor(305.8752, device='cuda:0')
episode: 89 training return: tensor(305.0048, device='cuda:0')
episode: 90 training return: tensor(273.2145, device='cuda:0')
episode: 91 training return: tensor(-128.6323, device='cuda:0')
epoch: 23 test_true_pfm: 3008.7307163154187 sim_pfm: 255.10910823585195
episode: 92 training return: tensor(247.5767, device='cuda:0')
episode: 93 training return: tensor(252.3432, device='cuda:0')
episode: 94 training return: tensor(391.7981, device='cuda:0')
episode: 95 training return: tensor(-146.3489, device='cuda:0')
epoch: 24 test_true_pfm: 3344.1200652583702 sim_pfm: 304.55963204453775
episode: 96 training return: tensor(13.2847, device='cuda:0')
episode: 97 training return: tensor(291.2528, device='cuda:0')
episode: 98 training return: tensor(-112.6795, device='cuda:0')
episode: 99 training return: tensor(-48.7702, device='cuda:0')
epoch: 25 test_true_pfm: 3328.9425388292334 sim_pfm: 144.4605072286989
episode: 100 training return: tensor(-189.4134, device='cuda:0')
episode: 101 training return: tensor(234.6846, device='cuda:0')
episode: 102 training return: tensor(267.4592, device='cuda:0')
episode: 103 training return: tensor(114.7637, device='cuda:0')
epoch: 26 test_true_pfm: 3350.561485159309 sim_pfm: 214.55910518428814
episode: 104 training return: tensor(-227.9495, device='cuda:0')
episode: 105 training return: tensor(330.0862, device='cuda:0')
episode: 106 training return: tensor(154.0380, device='cuda:0')
episode: 107 training return: tensor(224.3044, device='cuda:0')
epoch: 27 test_true_pfm: 3346.668730728599 sim_pfm: 275.030519549764
episode: 108 training return: tensor(234.7171, device='cuda:0')
episode: 109 training return: tensor(186.4265, device='cuda:0')
episode: 110 training return: tensor(-199.2645, device='cuda:0')
episode: 111 training return: tensor(195.6822, device='cuda:0')
epoch: 28 test_true_pfm: 2831.916074400559 sim_pfm: 88.32478921901202
episode: 112 training return: tensor(299.5158, device='cuda:0')
episode: 113 training return: tensor(283.7390, device='cuda:0')
episode: 114 training return: tensor(250.6002, device='cuda:0')
episode: 115 training return: tensor(71.9529, device='cuda:0')
epoch: 29 test_true_pfm: 2613.5621362083434 sim_pfm: 282.62608267346513
episode: 116 training return: tensor(-183.0754, device='cuda:0')
episode: 117 training return: tensor(-92.7645, device='cuda:0')
episode: 118 training return: tensor(-56.9141, device='cuda:0')
episode: 119 training return: tensor(308.7804, device='cuda:0')
epoch: 30 test_true_pfm: 2883.3237444022975 sim_pfm: 284.43043060950004
episode: 120 training return: tensor(257.8419, device='cuda:0')
episode: 121 training return: tensor(304.2275, device='cuda:0')
episode: 122 training return: tensor(246.9829, device='cuda:0')
episode: 123 training return: tensor(244.3031, device='cuda:0')
epoch: 31 test_true_pfm: 3392.0052618907666 sim_pfm: 276.5867977833453
episode: 124 training return: tensor(273.4012, device='cuda:0')
episode: 125 training return: tensor(266.8083, device='cuda:0')
episode: 126 training return: tensor(308.6790, device='cuda:0')
episode: 127 training return: tensor(253.1208, device='cuda:0')
epoch: 32 test_true_pfm: 3309.6191267149566 sim_pfm: 296.15318095385254
episode: 128 training return: tensor(-200.1173, device='cuda:0')
episode: 129 training return: tensor(292.8267, device='cuda:0')
episode: 130 training return: tensor(302.5716, device='cuda:0')
episode: 131 training return: tensor(236.1663, device='cuda:0')
epoch: 33 test_true_pfm: 3357.7024537624316 sim_pfm: 247.11913721001474
episode: 132 training return: tensor(279.8560, device='cuda:0')
episode: 133 training return: tensor(276.8154, device='cuda:0')
episode: 134 training return: tensor(281.2967, device='cuda:0')
episode: 135 training return: tensor(268.5395, device='cuda:0')
epoch: 34 test_true_pfm: 3089.1707850899534 sim_pfm: 213.75172256599762
episode: 136 training return: tensor(-148.3558, device='cuda:0')
episode: 137 training return: tensor(286.3710, device='cuda:0')
episode: 138 training return: tensor(-40.3735, device='cuda:0')
episode: 139 training return: tensor(-76.7779, device='cuda:0')
epoch: 35 test_true_pfm: 2884.0170112955566 sim_pfm: 16.860127120278776
episode: 140 training return: tensor(-229.1400, device='cuda:0')
episode: 141 training return: tensor(69.4898, device='cuda:0')
episode: 142 training return: tensor(288.4885, device='cuda:0')
episode: 143 training return: tensor(330.3494, device='cuda:0')
epoch: 36 test_true_pfm: 2816.030486255156 sim_pfm: 154.31019228858835
episode: 144 training return: tensor(255.1072, device='cuda:0')
episode: 145 training return: tensor(368.2367, device='cuda:0')
episode: 146 training return: tensor(-81.4581, device='cuda:0')
episode: 147 training return: tensor(249.6883, device='cuda:0')
epoch: 37 test_true_pfm: 2666.6003619299313 sim_pfm: 191.0583239146023
episode: 148 training return: tensor(302.8363, device='cuda:0')
episode: 149 training return: tensor(72.3295, device='cuda:0')
episode: 150 training return: tensor(296.1763, device='cuda:0')
episode: 151 training return: tensor(-271.1783, device='cuda:0')
epoch: 38 test_true_pfm: 3028.079275885943 sim_pfm: 40.29008911795487
episode: 152 training return: tensor(348.1057, device='cuda:0')
episode: 153 training return: tensor(274.9788, device='cuda:0')
episode: 154 training return: tensor(288.2381, device='cuda:0')
episode: 155 training return: tensor(323.8401, device='cuda:0')
epoch: 39 test_true_pfm: 3341.0313582204217 sim_pfm: 149.9989568470531
episode: 156 training return: tensor(-42.3773, device='cuda:0')
episode: 157 training return: tensor(323.1977, device='cuda:0')
episode: 158 training return: tensor(246.9470, device='cuda:0')
episode: 159 training return: tensor(245.2096, device='cuda:0')
epoch: 40 test_true_pfm: 3056.4973176330063 sim_pfm: 216.74291636871445
episode: 160 training return: tensor(-119.6960, device='cuda:0')
episode: 161 training return: tensor(292.1362, device='cuda:0')
episode: 162 training return: tensor(387.7735, device='cuda:0')
episode: 163 training return: tensor(310.8950, device='cuda:0')
epoch: 41 test_true_pfm: 3441.702458071 sim_pfm: 273.9213450427924
episode: 164 training return: tensor(239.4652, device='cuda:0')
episode: 165 training return: tensor(349.3108, device='cuda:0')
episode: 166 training return: tensor(298.1667, device='cuda:0')
episode: 167 training return: tensor(304.2728, device='cuda:0')
epoch: 42 test_true_pfm: 3355.6493538573523 sim_pfm: 64.44906657095028
episode: 168 training return: tensor(264.0551, device='cuda:0')
episode: 169 training return: tensor(218.7557, device='cuda:0')
episode: 170 training return: tensor(224.8236, device='cuda:0')
episode: 171 training return: tensor(286.2232, device='cuda:0')
epoch: 43 test_true_pfm: 2506.019139848627 sim_pfm: 332.4444731052111
episode: 172 training return: tensor(185.2177, device='cuda:0')
episode: 173 training return: tensor(306.5584, device='cuda:0')
episode: 174 training return: tensor(287.6121, device='cuda:0')
episode: 175 training return: tensor(-166.2438, device='cuda:0')
epoch: 44 test_true_pfm: 3013.965589578774 sim_pfm: 147.69974762235265
episode: 176 training return: tensor(274.2356, device='cuda:0')
episode: 177 training return: tensor(214.2355, device='cuda:0')
episode: 178 training return: tensor(-101.9386, device='cuda:0')
episode: 179 training return: tensor(312.9650, device='cuda:0')
epoch: 45 test_true_pfm: 3328.360294135311 sim_pfm: 167.25964293512516
episode: 180 training return: tensor(291.9688, device='cuda:0')
episode: 181 training return: tensor(332.2139, device='cuda:0')
episode: 182 training return: tensor(271.2292, device='cuda:0')
episode: 183 training return: tensor(321.6363, device='cuda:0')
epoch: 46 test_true_pfm: 3006.6541868441177 sim_pfm: 106.0335583477281
episode: 184 training return: tensor(235.3822, device='cuda:0')
episode: 185 training return: tensor(177.5424, device='cuda:0')
episode: 186 training return: tensor(280.8636, device='cuda:0')
episode: 187 training return: tensor(216.9804, device='cuda:0')
epoch: 47 test_true_pfm: 3208.1754801597417 sim_pfm: 311.63383541446336
episode: 188 training return: tensor(219.2636, device='cuda:0')
episode: 189 training return: tensor(78.2842, device='cuda:0')
episode: 190 training return: tensor(283.7480, device='cuda:0')
episode: 191 training return: tensor(316.0293, device='cuda:0')
epoch: 48 test_true_pfm: 2955.8964614999154 sim_pfm: 176.59405131544918
episode: 192 training return: tensor(287.0583, device='cuda:0')
episode: 193 training return: tensor(278.5682, device='cuda:0')
episode: 194 training return: tensor(138.2789, device='cuda:0')
episode: 195 training return: tensor(-73.6537, device='cuda:0')
epoch: 49 test_true_pfm: 3345.262469107238 sim_pfm: 299.0707428102808
episode: 196 training return: tensor(280.1061, device='cuda:0')
episode: 197 training return: tensor(202.1391, device='cuda:0')
episode: 198 training return: tensor(194.3747, device='cuda:0')
episode: 199 training return: tensor(65.8993, device='cuda:0')
epoch: 50 test_true_pfm: 2545.1612553602026 sim_pfm: 279.7733963525
episode: 200 training return: tensor(-11.2399, device='cuda:0')
episode: 201 training return: tensor(-100.3703, device='cuda:0')
episode: 202 training return: tensor(-92.6763, device='cuda:0')
episode: 203 training return: tensor(275.4699, device='cuda:0')
epoch: 51 test_true_pfm: 3146.8423903127773 sim_pfm: 311.2702194521844
episode: 204 training return: tensor(294.5385, device='cuda:0')
episode: 205 training return: tensor(332.3962, device='cuda:0')
episode: 206 training return: tensor(-230.5528, device='cuda:0')
episode: 207 training return: tensor(298.6942, device='cuda:0')
epoch: 52 test_true_pfm: 3358.6152496211707 sim_pfm: 216.2806612230294
episode: 208 training return: tensor(292.4331, device='cuda:0')
episode: 209 training return: tensor(290.5894, device='cuda:0')
episode: 210 training return: tensor(70.0075, device='cuda:0')
episode: 211 training return: tensor(259.3239, device='cuda:0')
epoch: 53 test_true_pfm: 3380.3712358651096 sim_pfm: 311.6456656877417
episode: 212 training return: tensor(272.3136, device='cuda:0')
episode: 213 training return: tensor(-72.4671, device='cuda:0')
episode: 214 training return: tensor(167.3413, device='cuda:0')
episode: 215 training return: tensor(231.2264, device='cuda:0')
epoch: 54 test_true_pfm: 2665.005776706197 sim_pfm: -46.07866651983932
episode: 216 training return: tensor(334.8704, device='cuda:0')
episode: 217 training return: tensor(290.0427, device='cuda:0')
episode: 218 training return: tensor(259.6306, device='cuda:0')
episode: 219 training return: tensor(271.2997, device='cuda:0')
epoch: 55 test_true_pfm: 2806.68602810158 sim_pfm: 282.1551025435717
episode: 220 training return: tensor(231.6661, device='cuda:0')
episode: 221 training return: tensor(-4.1318, device='cuda:0')
episode: 222 training return: tensor(241.5240, device='cuda:0')
episode: 223 training return: tensor(284.6652, device='cuda:0')
epoch: 56 test_true_pfm: 2878.1746142255465 sim_pfm: 285.10160447323386
episode: 224 training return: tensor(300.7837, device='cuda:0')
episode: 225 training return: tensor(322.5727, device='cuda:0')
episode: 226 training return: tensor(232.5921, device='cuda:0')
episode: 227 training return: tensor(283.1937, device='cuda:0')
epoch: 57 test_true_pfm: 2858.066699837635 sim_pfm: 300.75426987665315
episode: 228 training return: tensor(264.5272, device='cuda:0')
episode: 229 training return: tensor(253.7887, device='cuda:0')
episode: 230 training return: tensor(244.8552, device='cuda:0')
episode: 231 training return: tensor(-173.6842, device='cuda:0')
epoch: 58 test_true_pfm: 3348.730559631944 sim_pfm: 223.1293272410791
episode: 232 training return: tensor(-112.1236, device='cuda:0')
episode: 233 training return: tensor(-167.4737, device='cuda:0')
episode: 234 training return: tensor(243.4954, device='cuda:0')
episode: 235 training return: tensor(-134.2958, device='cuda:0')
epoch: 59 test_true_pfm: 2721.9303374082447 sim_pfm: 166.62139639198236
episode: 236 training return: tensor(250.4765, device='cuda:0')
episode: 237 training return: tensor(279.0438, device='cuda:0')
episode: 238 training return: tensor(298.6535, device='cuda:0')
episode: 239 training return: tensor(255.5411, device='cuda:0')
epoch: 60 test_true_pfm: 2985.051320100332 sim_pfm: 278.7496244289796
episode: 240 training return: tensor(262.8561, device='cuda:0')
episode: 241 training return: tensor(299.5606, device='cuda:0')
episode: 242 training return: tensor(327.1733, device='cuda:0')
episode: 243 training return: tensor(299.1113, device='cuda:0')
epoch: 61 test_true_pfm: 3386.4178016718415 sim_pfm: 231.95077599313422
episode: 244 training return: tensor(260.3393, device='cuda:0')
episode: 245 training return: tensor(-319.8262, device='cuda:0')
episode: 246 training return: tensor(-126.0937, device='cuda:0')
episode: 247 training return: tensor(272.1200, device='cuda:0')
epoch: 62 test_true_pfm: 2955.207552340413 sim_pfm: 288.45052252168534
episode: 248 training return: tensor(-134.9440, device='cuda:0')
episode: 249 training return: tensor(296.0522, device='cuda:0')
episode: 250 training return: tensor(-60.9843, device='cuda:0')
episode: 251 training return: tensor(280.8533, device='cuda:0')
epoch: 63 test_true_pfm: 2998.740577450426 sim_pfm: 284.8629579384772
episode: 252 training return: tensor(79.9409, device='cuda:0')
episode: 253 training return: tensor(-234.8069, device='cuda:0')
episode: 254 training return: tensor(-67.0007, device='cuda:0')
episode: 255 training return: tensor(396.3026, device='cuda:0')
epoch: 64 test_true_pfm: 3375.893698793807 sim_pfm: 261.4672728102111
episode: 256 training return: tensor(251.1732, device='cuda:0')
episode: 257 training return: tensor(283.4297, device='cuda:0')
episode: 258 training return: tensor(3.3635, device='cuda:0')
episode: 259 training return: tensor(360.3226, device='cuda:0')
epoch: 65 test_true_pfm: 3318.321233641356 sim_pfm: -10.42509228528555
episode: 260 training return: tensor(-91.4588, device='cuda:0')
episode: 261 training return: tensor(280.6070, device='cuda:0')
episode: 262 training return: tensor(281.1617, device='cuda:0')
episode: 263 training return: tensor(302.7011, device='cuda:0')
epoch: 66 test_true_pfm: 3347.528154430583 sim_pfm: 279.0556555816729
episode: 264 training return: tensor(230.4489, device='cuda:0')
episode: 265 training return: tensor(311.4813, device='cuda:0')
episode: 266 training return: tensor(173.0119, device='cuda:0')
episode: 267 training return: tensor(292.1131, device='cuda:0')
epoch: 67 test_true_pfm: 3378.601182275314 sim_pfm: 264.5933149221819
episode: 268 training return: tensor(291.5392, device='cuda:0')
episode: 269 training return: tensor(236.5268, device='cuda:0')
episode: 270 training return: tensor(-162.9315, device='cuda:0')
episode: 271 training return: tensor(279.2836, device='cuda:0')
epoch: 68 test_true_pfm: 2960.8716910717794 sim_pfm: 190.23806803064267
episode: 272 training return: tensor(301.2159, device='cuda:0')
episode: 273 training return: tensor(296.2457, device='cuda:0')
episode: 274 training return: tensor(-149.1044, device='cuda:0')
episode: 275 training return: tensor(266.0450, device='cuda:0')
epoch: 69 test_true_pfm: 3333.735100038031 sim_pfm: 274.2942508880321
episode: 276 training return: tensor(266.7793, device='cuda:0')
episode: 277 training return: tensor(308.3029, device='cuda:0')
episode: 278 training return: tensor(288.5702, device='cuda:0')
episode: 279 training return: tensor(265.7855, device='cuda:0')
epoch: 70 test_true_pfm: 2510.127578693042 sim_pfm: 285.07533217117697
episode: 280 training return: tensor(307.6572, device='cuda:0')
episode: 281 training return: tensor(279.1067, device='cuda:0')
episode: 282 training return: tensor(251.8993, device='cuda:0')
episode: 283 training return: tensor(306.0425, device='cuda:0')
epoch: 71 test_true_pfm: 2504.8467965148598 sim_pfm: 264.8347659774493
episode: 284 training return: tensor(247.0126, device='cuda:0')
episode: 285 training return: tensor(-154.4478, device='cuda:0')
episode: 286 training return: tensor(274.8002, device='cuda:0')
episode: 287 training return: tensor(283.6324, device='cuda:0')
epoch: 72 test_true_pfm: 3082.8797369194795 sim_pfm: 143.83079200117695
episode: 288 training return: tensor(306.9623, device='cuda:0')
episode: 289 training return: tensor(-2.2713, device='cuda:0')
episode: 290 training return: tensor(296.3172, device='cuda:0')
episode: 291 training return: tensor(233.7913, device='cuda:0')
epoch: 73 test_true_pfm: 3002.2133976220125 sim_pfm: 110.58317822140332
episode: 292 training return: tensor(269.6916, device='cuda:0')
episode: 293 training return: tensor(-7.9044, device='cuda:0')
episode: 294 training return: tensor(295.2978, device='cuda:0')
episode: 295 training return: tensor(323.6509, device='cuda:0')
epoch: 74 test_true_pfm: 2510.3459391852844 sim_pfm: -28.15201403204507
episode: 296 training return: tensor(214.8096, device='cuda:0')
episode: 297 training return: tensor(320.6708, device='cuda:0')
episode: 298 training return: tensor(-93.4962, device='cuda:0')
episode: 299 training return: tensor(266.3911, device='cuda:0')
epoch: 75 test_true_pfm: 3335.6055504950004 sim_pfm: 282.34311448668205
episode: 300 training return: tensor(275.4629, device='cuda:0')
episode: 301 training return: tensor(-158.3716, device='cuda:0')
episode: 302 training return: tensor(303.2190, device='cuda:0')
episode: 303 training return: tensor(305.3344, device='cuda:0')
epoch: 76 test_true_pfm: 2701.7713284621464 sim_pfm: 213.07579494880824
episode: 304 training return: tensor(-162.7282, device='cuda:0')
episode: 305 training return: tensor(271.2929, device='cuda:0')
episode: 306 training return: tensor(296.3459, device='cuda:0')
episode: 307 training return: tensor(15.1015, device='cuda:0')
epoch: 77 test_true_pfm: 3340.6699604871806 sim_pfm: -93.17699783073233
episode: 308 training return: tensor(309.1626, device='cuda:0')
episode: 309 training return: tensor(265.4742, device='cuda:0')
episode: 310 training return: tensor(270.5367, device='cuda:0')
episode: 311 training return: tensor(178.2200, device='cuda:0')
epoch: 78 test_true_pfm: 2515.390400239418 sim_pfm: 279.55261434106313
episode: 312 training return: tensor(272.5707, device='cuda:0')
episode: 313 training return: tensor(147.7834, device='cuda:0')
episode: 314 training return: tensor(-124.8291, device='cuda:0')
episode: 315 training return: tensor(58.8309, device='cuda:0')
epoch: 79 test_true_pfm: 3150.416545079754 sim_pfm: 280.7361144343352
episode: 316 training return: tensor(304.2574, device='cuda:0')
episode: 317 training return: tensor(279.5393, device='cuda:0')
episode: 318 training return: tensor(308.6842, device='cuda:0')
episode: 319 training return: tensor(-188.2498, device='cuda:0')
epoch: 80 test_true_pfm: 3104.5200093443104 sim_pfm: 244.75330763197658
episode: 320 training return: tensor(235.3584, device='cuda:0')
episode: 321 training return: tensor(279.8829, device='cuda:0')
episode: 322 training return: tensor(305.8432, device='cuda:0')
episode: 323 training return: tensor(28.2504, device='cuda:0')
epoch: 81 test_true_pfm: 3023.328051957489 sim_pfm: 263.0854928707704
episode: 324 training return: tensor(299.3008, device='cuda:0')
episode: 325 training return: tensor(336.7962, device='cuda:0')
episode: 326 training return: tensor(306.4450, device='cuda:0')
episode: 327 training return: tensor(116.7955, device='cuda:0')
epoch: 82 test_true_pfm: 3372.80472055445 sim_pfm: 280.6496530548514
episode: 328 training return: tensor(270.4511, device='cuda:0')
episode: 329 training return: tensor(23.5455, device='cuda:0')
episode: 330 training return: tensor(169.7878, device='cuda:0')
episode: 331 training return: tensor(-34.5303, device='cuda:0')
epoch: 83 test_true_pfm: 3366.196785208062 sim_pfm: 297.92485025388305
episode: 332 training return: tensor(299.8721, device='cuda:0')
episode: 333 training return: tensor(255.0560, device='cuda:0')
episode: 334 training return: tensor(297.7331, device='cuda:0')
episode: 335 training return: tensor(310.7506, device='cuda:0')
epoch: 84 test_true_pfm: 2739.397342510451 sim_pfm: 278.33720305443666
episode: 336 training return: tensor(-156.7895, device='cuda:0')
episode: 337 training return: tensor(278.7518, device='cuda:0')
episode: 338 training return: tensor(318.1933, device='cuda:0')
episode: 339 training return: tensor(316.3838, device='cuda:0')
epoch: 85 test_true_pfm: 3147.65893572154 sim_pfm: 294.69894201058196
episode: 340 training return: tensor(-158.7909, device='cuda:0')
episode: 341 training return: tensor(267.8462, device='cuda:0')
episode: 342 training return: tensor(328.4487, device='cuda:0')
episode: 343 training return: tensor(248.8341, device='cuda:0')
epoch: 86 test_true_pfm: 3131.6654133827374 sim_pfm: 313.1248232143407
episode: 344 training return: tensor(224.0359, device='cuda:0')
episode: 345 training return: tensor(297.8965, device='cuda:0')
episode: 346 training return: tensor(271.8481, device='cuda:0')
episode: 347 training return: tensor(239.3123, device='cuda:0')
epoch: 87 test_true_pfm: 3070.6975820841567 sim_pfm: 273.9020681303712
episode: 348 training return: tensor(307.2273, device='cuda:0')
episode: 349 training return: tensor(-155.9991, device='cuda:0')
episode: 350 training return: tensor(333.9718, device='cuda:0')
episode: 351 training return: tensor(397.8277, device='cuda:0')
epoch: 88 test_true_pfm: 2989.4254774322276 sim_pfm: 304.2236581546119
episode: 352 training return: tensor(189.2283, device='cuda:0')
episode: 353 training return: tensor(-19.2739, device='cuda:0')
episode: 354 training return: tensor(284.3581, device='cuda:0')
episode: 355 training return: tensor(267.7962, device='cuda:0')
epoch: 89 test_true_pfm: 3349.9693539600926 sim_pfm: 294.7351088854096
episode: 356 training return: tensor(-73.8134, device='cuda:0')
episode: 357 training return: tensor(38.5272, device='cuda:0')
episode: 358 training return: tensor(243.8965, device='cuda:0')
episode: 359 training return: tensor(335.9287, device='cuda:0')
epoch: 90 test_true_pfm: 2986.390071240928 sim_pfm: 119.41783167599351
episode: 360 training return: tensor(263.1117, device='cuda:0')
episode: 361 training return: tensor(-166.4764, device='cuda:0')
episode: 362 training return: tensor(334.0273, device='cuda:0')
episode: 363 training return: tensor(211.7663, device='cuda:0')
epoch: 91 test_true_pfm: 3371.568097523075 sim_pfm: 151.43760823373063
episode: 364 training return: tensor(259.8143, device='cuda:0')
episode: 365 training return: tensor(278.6218, device='cuda:0')
episode: 366 training return: tensor(284.2724, device='cuda:0')
episode: 367 training return: tensor(254.2995, device='cuda:0')
epoch: 92 test_true_pfm: 2934.2513011925116 sim_pfm: 246.95983074758746
episode: 368 training return: tensor(-191.8559, device='cuda:0')
episode: 369 training return: tensor(304.8470, device='cuda:0')
episode: 370 training return: tensor(280.3129, device='cuda:0')
episode: 371 training return: tensor(135.0443, device='cuda:0')
epoch: 93 test_true_pfm: 3130.5099907494955 sim_pfm: 152.97485489106234
episode: 372 training return: tensor(278.6943, device='cuda:0')
episode: 373 training return: tensor(-109.6507, device='cuda:0')
episode: 374 training return: tensor(-19.9326, device='cuda:0')
episode: 375 training return: tensor(99.8489, device='cuda:0')
epoch: 94 test_true_pfm: 2880.1878535841993 sim_pfm: 94.84924924374597
episode: 376 training return: tensor(104.0336, device='cuda:0')
episode: 377 training return: tensor(292.7148, device='cuda:0')
episode: 378 training return: tensor(356.0112, device='cuda:0')
episode: 379 training return: tensor(-190.2077, device='cuda:0')
epoch: 95 test_true_pfm: 2854.7931624581693 sim_pfm: 280.60927158398164
episode: 380 training return: tensor(290.7259, device='cuda:0')
episode: 381 training return: tensor(266.3014, device='cuda:0')
episode: 382 training return: tensor(-192.3020, device='cuda:0')
episode: 383 training return: tensor(313.2257, device='cuda:0')
epoch: 96 test_true_pfm: 3032.198943007461 sim_pfm: 290.1490226400395
episode: 384 training return: tensor(289.3849, device='cuda:0')
episode: 385 training return: tensor(295.3855, device='cuda:0')
episode: 386 training return: tensor(133.6938, device='cuda:0')
episode: 387 training return: tensor(287.9372, device='cuda:0')
epoch: 97 test_true_pfm: 3364.7382850691865 sim_pfm: 146.5697597695786
episode: 388 training return: tensor(-95.5294, device='cuda:0')
episode: 389 training return: tensor(315.9287, device='cuda:0')
episode: 390 training return: tensor(-170.7131, device='cuda:0')
episode: 391 training return: tensor(289.0395, device='cuda:0')
epoch: 98 test_true_pfm: 3304.4876434626954 sim_pfm: 275.382890273487
episode: 392 training return: tensor(283.0563, device='cuda:0')
episode: 393 training return: tensor(219.2822, device='cuda:0')
episode: 394 training return: tensor(273.8105, device='cuda:0')
episode: 395 training return: tensor(-245.2876, device='cuda:0')
epoch: 99 test_true_pfm: 3378.7258776329813 sim_pfm: 270.2681770507479
episode: 396 training return: tensor(54.8926, device='cuda:0')
episode: 397 training return: tensor(262.9983, device='cuda:0')
episode: 398 training return: tensor(253.5953, device='cuda:0')
episode: 399 training return: tensor(211.9054, device='cuda:0')
epoch: 100 test_true_pfm: 2195.529972594173 sim_pfm: 164.3012264445424
episode: 400 training return: tensor(285.3918, device='cuda:0')
episode: 401 training return: tensor(316.2024, device='cuda:0')
episode: 402 training return: tensor(268.8820, device='cuda:0')
episode: 403 training return: tensor(-113.6493, device='cuda:0')
epoch: 101 test_true_pfm: 3146.630623094081 sim_pfm: 48.50008469701667
episode: 404 training return: tensor(31.0979, device='cuda:0')
episode: 405 training return: tensor(249.9334, device='cuda:0')
episode: 406 training return: tensor(285.6453, device='cuda:0')
episode: 407 training return: tensor(254.2146, device='cuda:0')
epoch: 102 test_true_pfm: 3339.1002041785646 sim_pfm: 101.21609873432317
episode: 408 training return: tensor(270.8769, device='cuda:0')
episode: 409 training return: tensor(200.3141, device='cuda:0')
episode: 410 training return: tensor(287.1714, device='cuda:0')
episode: 411 training return: tensor(343.0730, device='cuda:0')
epoch: 103 test_true_pfm: 3392.9513361519926 sim_pfm: 290.73625096768956
episode: 412 training return: tensor(270.8545, device='cuda:0')
episode: 413 training return: tensor(242.1876, device='cuda:0')
episode: 414 training return: tensor(286.8132, device='cuda:0')
episode: 415 training return: tensor(271.6374, device='cuda:0')
epoch: 104 test_true_pfm: 2426.704369318606 sim_pfm: 156.5251792695975
episode: 416 training return: tensor(51.5908, device='cuda:0')
episode: 417 training return: tensor(318.4022, device='cuda:0')
episode: 418 training return: tensor(276.1060, device='cuda:0')
episode: 419 training return: tensor(301.6293, device='cuda:0')
epoch: 105 test_true_pfm: 3389.282808287917 sim_pfm: 309.9056036361532
episode: 420 training return: tensor(372.0321, device='cuda:0')
episode: 421 training return: tensor(285.4923, device='cuda:0')
episode: 422 training return: tensor(292.0969, device='cuda:0')
episode: 423 training return: tensor(312.2775, device='cuda:0')
epoch: 106 test_true_pfm: 3388.5886062150635 sim_pfm: 273.1542859420685
episode: 424 training return: tensor(298.8449, device='cuda:0')
episode: 425 training return: tensor(277.6517, device='cuda:0')
episode: 426 training return: tensor(287.4364, device='cuda:0')
episode: 427 training return: tensor(313.0066, device='cuda:0')
epoch: 107 test_true_pfm: 2797.379657892004 sim_pfm: 304.21736052287935
episode: 428 training return: tensor(28.4730, device='cuda:0')
episode: 429 training return: tensor(281.3034, device='cuda:0')
episode: 430 training return: tensor(224.6306, device='cuda:0')
episode: 431 training return: tensor(258.9818, device='cuda:0')
epoch: 108 test_true_pfm: 2944.9854202295023 sim_pfm: 279.8456084208544
episode: 432 training return: tensor(244.3037, device='cuda:0')
episode: 433 training return: tensor(320.5543, device='cuda:0')
episode: 434 training return: tensor(368.8930, device='cuda:0')
episode: 435 training return: tensor(375.8416, device='cuda:0')
epoch: 109 test_true_pfm: 2492.835057956339 sim_pfm: 302.27786631465034
episode: 436 training return: tensor(275.9780, device='cuda:0')
episode: 437 training return: tensor(271.4496, device='cuda:0')
episode: 438 training return: tensor(276.9725, device='cuda:0')
episode: 439 training return: tensor(75.2255, device='cuda:0')
epoch: 110 test_true_pfm: 3371.271635064991 sim_pfm: 307.12427488478716
episode: 440 training return: tensor(255.6332, device='cuda:0')
episode: 441 training return: tensor(331.6584, device='cuda:0')
episode: 442 training return: tensor(293.8640, device='cuda:0')
episode: 443 training return: tensor(-33.2925, device='cuda:0')
epoch: 111 test_true_pfm: 3256.2811529758183 sim_pfm: 280.8375640322726
episode: 444 training return: tensor(28.3268, device='cuda:0')
episode: 445 training return: tensor(-3.3747, device='cuda:0')
episode: 446 training return: tensor(-243.6298, device='cuda:0')
episode: 447 training return: tensor(-29.1315, device='cuda:0')
epoch: 112 test_true_pfm: 3356.125359532951 sim_pfm: 175.38702629816058
episode: 448 training return: tensor(29.6567, device='cuda:0')
episode: 449 training return: tensor(313.8639, device='cuda:0')
episode: 450 training return: tensor(277.5579, device='cuda:0')
episode: 451 training return: tensor(222.7253, device='cuda:0')
epoch: 113 test_true_pfm: 3396.3938845913094 sim_pfm: 150.25343443543534
episode: 452 training return: tensor(341.8764, device='cuda:0')
episode: 453 training return: tensor(288.0738, device='cuda:0')
episode: 454 training return: tensor(-60.4052, device='cuda:0')
episode: 455 training return: tensor(283.4091, device='cuda:0')
epoch: 114 test_true_pfm: 3188.68633453051 sim_pfm: 281.7055143667773
episode: 456 training return: tensor(-102.4681, device='cuda:0')
episode: 457 training return: tensor(273.1359, device='cuda:0')
episode: 458 training return: tensor(307.7352, device='cuda:0')
episode: 459 training return: tensor(304.6406, device='cuda:0')
epoch: 115 test_true_pfm: 3341.556073305892 sim_pfm: 277.00513121452724
episode: 460 training return: tensor(272.7666, device='cuda:0')
episode: 461 training return: tensor(307.2700, device='cuda:0')
episode: 462 training return: tensor(231.7840, device='cuda:0')
episode: 463 training return: tensor(325.7085, device='cuda:0')
epoch: 116 test_true_pfm: 3242.587779364819 sim_pfm: 129.4235897195273
episode: 464 training return: tensor(265.8635, device='cuda:0')
episode: 465 training return: tensor(293.7029, device='cuda:0')
episode: 466 training return: tensor(295.7230, device='cuda:0')
episode: 467 training return: tensor(272.9291, device='cuda:0')
epoch: 117 test_true_pfm: 3303.351248184139 sim_pfm: 297.85413710577023
episode: 468 training return: tensor(214.9355, device='cuda:0')
episode: 469 training return: tensor(225.4277, device='cuda:0')
episode: 470 training return: tensor(298.1865, device='cuda:0')
episode: 471 training return: tensor(282.8765, device='cuda:0')
epoch: 118 test_true_pfm: 3105.956261965892 sim_pfm: 179.2175887465322
episode: 472 training return: tensor(-48.5463, device='cuda:0')
episode: 473 training return: tensor(299.7107, device='cuda:0')
episode: 474 training return: tensor(200.7422, device='cuda:0')
episode: 475 training return: tensor(-228.9337, device='cuda:0')
epoch: 119 test_true_pfm: 3367.870295338484 sim_pfm: -14.710391276651839
episode: 476 training return: tensor(239.3136, device='cuda:0')
episode: 477 training return: tensor(231.5387, device='cuda:0')
episode: 478 training return: tensor(263.6680, device='cuda:0')
episode: 479 training return: tensor(248.7895, device='cuda:0')
epoch: 120 test_true_pfm: 3045.5515601529974 sim_pfm: 221.40738314033175
episode: 480 training return: tensor(326.7729, device='cuda:0')
episode: 481 training return: tensor(-166.2785, device='cuda:0')
episode: 482 training return: tensor(-88.6791, device='cuda:0')
episode: 483 training return: tensor(309.2492, device='cuda:0')
epoch: 121 test_true_pfm: 2918.3197566767903 sim_pfm: 245.3722792866174
episode: 484 training return: tensor(294.1300, device='cuda:0')
episode: 485 training return: tensor(-164.5335, device='cuda:0')
episode: 486 training return: tensor(269.6216, device='cuda:0')
episode: 487 training return: tensor(332.0366, device='cuda:0')
epoch: 122 test_true_pfm: 3355.077700150931 sim_pfm: 152.64693504599077
episode: 488 training return: tensor(96.4238, device='cuda:0')
episode: 489 training return: tensor(330.1903, device='cuda:0')
episode: 490 training return: tensor(182.2797, device='cuda:0')
episode: 491 training return: tensor(288.4740, device='cuda:0')
epoch: 123 test_true_pfm: 3054.7826626743877 sim_pfm: 273.09389249656425
episode: 492 training return: tensor(283.9456, device='cuda:0')
episode: 493 training return: tensor(266.9833, device='cuda:0')
episode: 494 training return: tensor(340.0029, device='cuda:0')
episode: 495 training return: tensor(274.7599, device='cuda:0')
epoch: 124 test_true_pfm: 3144.237378600292 sim_pfm: 262.97751226902864
episode: 496 training return: tensor(275.6797, device='cuda:0')
episode: 497 training return: tensor(332.6283, device='cuda:0')
episode: 498 training return: tensor(-223.9409, device='cuda:0')
episode: 499 training return: tensor(-63.6691, device='cuda:0')
epoch: 125 test_true_pfm: 3318.5822318199002 sim_pfm: 233.98830050009806
episode: 500 training return: tensor(-30.8876, device='cuda:0')
episode: 501 training return: tensor(245.4744, device='cuda:0')
episode: 502 training return: tensor(256.3277, device='cuda:0')
episode: 503 training return: tensor(109.3505, device='cuda:0')
epoch: 126 test_true_pfm: 2879.6096560997885 sim_pfm: 142.940133400989
episode: 504 training return: tensor(218.2639, device='cuda:0')
episode: 505 training return: tensor(247.2961, device='cuda:0')
episode: 506 training return: tensor(51.3345, device='cuda:0')
episode: 507 training return: tensor(226.1985, device='cuda:0')
epoch: 127 test_true_pfm: 2971.5653584378706 sim_pfm: 150.7357316602914
episode: 508 training return: tensor(-135.7205, device='cuda:0')
episode: 509 training return: tensor(313.4754, device='cuda:0')
episode: 510 training return: tensor(279.4232, device='cuda:0')
episode: 511 training return: tensor(282.4113, device='cuda:0')
epoch: 128 test_true_pfm: 3372.1645750731404 sim_pfm: 277.9798581423141
episode: 512 training return: tensor(253.3501, device='cuda:0')
episode: 513 training return: tensor(-19.1924, device='cuda:0')
episode: 514 training return: tensor(81.9405, device='cuda:0')
episode: 515 training return: tensor(236.3974, device='cuda:0')
epoch: 129 test_true_pfm: 3311.304896008635 sim_pfm: 290.82669962685515
episode: 516 training return: tensor(-105.6865, device='cuda:0')
episode: 517 training return: tensor(304.6240, device='cuda:0')
episode: 518 training return: tensor(280.8717, device='cuda:0')
episode: 519 training return: tensor(-86.6314, device='cuda:0')
epoch: 130 test_true_pfm: 2380.278881496595 sim_pfm: 279.91621682218585
episode: 520 training return: tensor(299.1169, device='cuda:0')
episode: 521 training return: tensor(254.6281, device='cuda:0')
episode: 522 training return: tensor(309.6718, device='cuda:0')
episode: 523 training return: tensor(-252.2554, device='cuda:0')
epoch: 131 test_true_pfm: 3042.1829307697385 sim_pfm: 238.19809163627602
episode: 524 training return: tensor(294.5750, device='cuda:0')
episode: 525 training return: tensor(265.8114, device='cuda:0')
episode: 526 training return: tensor(296.6009, device='cuda:0')
episode: 527 training return: tensor(45.2061, device='cuda:0')
epoch: 132 test_true_pfm: 3422.770714930377 sim_pfm: 238.06389407401244
episode: 528 training return: tensor(295.5157, device='cuda:0')
episode: 529 training return: tensor(-183.6761, device='cuda:0')
episode: 530 training return: tensor(-130.8346, device='cuda:0')
episode: 531 training return: tensor(-18.8701, device='cuda:0')
epoch: 133 test_true_pfm: 3362.2906973047825 sim_pfm: 283.2118659777528
episode: 532 training return: tensor(232.4609, device='cuda:0')
episode: 533 training return: tensor(272.8997, device='cuda:0')
episode: 534 training return: tensor(284.2666, device='cuda:0')
episode: 535 training return: tensor(-80.8121, device='cuda:0')
epoch: 134 test_true_pfm: 3199.58631451361 sim_pfm: 123.16627056722064
episode: 536 training return: tensor(52.2921, device='cuda:0')
episode: 537 training return: tensor(144.1593, device='cuda:0')
episode: 538 training return: tensor(270.5334, device='cuda:0')
episode: 539 training return: tensor(301.2400, device='cuda:0')
epoch: 135 test_true_pfm: 2329.9735845321575 sim_pfm: 168.12139719016463
episode: 540 training return: tensor(260.4417, device='cuda:0')
episode: 541 training return: tensor(352.8030, device='cuda:0')
episode: 542 training return: tensor(-4.7007, device='cuda:0')
episode: 543 training return: tensor(299.2618, device='cuda:0')
epoch: 136 test_true_pfm: 2899.0729511997415 sim_pfm: 41.91888008112437
episode: 544 training return: tensor(284.5197, device='cuda:0')
episode: 545 training return: tensor(303.4821, device='cuda:0')
episode: 546 training return: tensor(277.6636, device='cuda:0')
episode: 547 training return: tensor(317.1649, device='cuda:0')
epoch: 137 test_true_pfm: 3385.597155325204 sim_pfm: 173.9049268778957
episode: 548 training return: tensor(-97.9847, device='cuda:0')
episode: 549 training return: tensor(-253.5701, device='cuda:0')
episode: 550 training return: tensor(40.1918, device='cuda:0')
episode: 551 training return: tensor(333.5358, device='cuda:0')
epoch: 138 test_true_pfm: 3358.232919899218 sim_pfm: 192.305500705319
episode: 552 training return: tensor(-37.6649, device='cuda:0')
episode: 553 training return: tensor(323.1841, device='cuda:0')
episode: 554 training return: tensor(309.0089, device='cuda:0')
episode: 555 training return: tensor(207.7391, device='cuda:0')
epoch: 139 test_true_pfm: 3259.04105443456 sim_pfm: 278.0896671259349
episode: 556 training return: tensor(-140.4002, device='cuda:0')
episode: 557 training return: tensor(231.3069, device='cuda:0')
episode: 558 training return: tensor(300.8174, device='cuda:0')
episode: 559 training return: tensor(275.0432, device='cuda:0')
epoch: 140 test_true_pfm: 3359.9011323135514 sim_pfm: 279.7794075457302
episode: 560 training return: tensor(248.4249, device='cuda:0')
episode: 561 training return: tensor(289.4037, device='cuda:0')
episode: 562 training return: tensor(-18.4902, device='cuda:0')
episode: 563 training return: tensor(-21.3288, device='cuda:0')
epoch: 141 test_true_pfm: 3163.696724400737 sim_pfm: 150.89058752241544
episode: 564 training return: tensor(325.3838, device='cuda:0')
episode: 565 training return: tensor(303.7669, device='cuda:0')
episode: 566 training return: tensor(310.1521, device='cuda:0')
episode: 567 training return: tensor(60.7124, device='cuda:0')
epoch: 142 test_true_pfm: 3311.976771385112 sim_pfm: 261.7680675010876
episode: 568 training return: tensor(323.3188, device='cuda:0')
episode: 569 training return: tensor(277.4225, device='cuda:0')
episode: 570 training return: tensor(263.7527, device='cuda:0')
episode: 571 training return: tensor(254.7079, device='cuda:0')
epoch: 143 test_true_pfm: 3075.256269301962 sim_pfm: 89.47951840838262
episode: 572 training return: tensor(287.3558, device='cuda:0')
episode: 573 training return: tensor(277.1318, device='cuda:0')
episode: 574 training return: tensor(283.2836, device='cuda:0')
episode: 575 training return: tensor(239.9597, device='cuda:0')
epoch: 144 test_true_pfm: 3328.079071853888 sim_pfm: 108.66456361157664
episode: 576 training return: tensor(-199.6589, device='cuda:0')
episode: 577 training return: tensor(248.5997, device='cuda:0')
episode: 578 training return: tensor(221.7926, device='cuda:0')
episode: 579 training return: tensor(287.8738, device='cuda:0')
epoch: 145 test_true_pfm: 3417.9347723322626 sim_pfm: 242.78022695471495
episode: 580 training return: tensor(-111.0310, device='cuda:0')
episode: 581 training return: tensor(39.0411, device='cuda:0')
episode: 582 training return: tensor(112.3646, device='cuda:0')
episode: 583 training return: tensor(245.5809, device='cuda:0')
epoch: 146 test_true_pfm: 3318.945139517086 sim_pfm: 175.12690233171452
episode: 584 training return: tensor(348.0065, device='cuda:0')
episode: 585 training return: tensor(233.6302, device='cuda:0')
episode: 586 training return: tensor(285.4651, device='cuda:0')
episode: 587 training return: tensor(270.7458, device='cuda:0')
epoch: 147 test_true_pfm: 3318.7251277432174 sim_pfm: 77.31995128264923
episode: 588 training return: tensor(274.0824, device='cuda:0')
episode: 589 training return: tensor(-82.8696, device='cuda:0')
episode: 590 training return: tensor(328.2879, device='cuda:0')
episode: 591 training return: tensor(185.2985, device='cuda:0')
epoch: 148 test_true_pfm: 2624.7599906456303 sim_pfm: -17.264701567279797
episode: 592 training return: tensor(-92.1713, device='cuda:0')
episode: 593 training return: tensor(261.8618, device='cuda:0')
episode: 594 training return: tensor(27.5523, device='cuda:0')
episode: 595 training return: tensor(236.7880, device='cuda:0')
epoch: 149 test_true_pfm: 3385.6982987237766 sim_pfm: 282.1837570242545
episode: 596 training return: tensor(280.6494, device='cuda:0')
episode: 597 training return: tensor(226.4205, device='cuda:0')
episode: 598 training return: tensor(219.5038, device='cuda:0')
episode: 599 training return: tensor(333.5621, device='cuda:0')
epoch: 150 test_true_pfm: 2928.9564634793146 sim_pfm: 157.82130086487936
