['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '2']
episode: 0 training return: tensor(-219.3399, device='cuda:0')
episode: 1 training return: tensor(-164.2575, device='cuda:0')
episode: 2 training return: tensor(-134.4546, device='cuda:0')
episode: 3 training return: tensor(-128.5569, device='cuda:0')
epoch: 1 test_true_pfm: 27.802833281999767 sim_pfm: 139.00298148196308
episode: 4 training return: tensor(-202.1349, device='cuda:0')
episode: 5 training return: tensor(-232.0206, device='cuda:0')
episode: 6 training return: tensor(-249.4436, device='cuda:0')
episode: 7 training return: tensor(-212.7895, device='cuda:0')
epoch: 2 test_true_pfm: 9.874551651270727 sim_pfm: -259.2506321778521
episode: 8 training return: tensor(-136.3009, device='cuda:0')
episode: 9 training return: tensor(-199.3087, device='cuda:0')
episode: 10 training return: tensor(-157.1955, device='cuda:0')
episode: 11 training return: tensor(-162.2441, device='cuda:0')
epoch: 3 test_true_pfm: 21.741429746653107 sim_pfm: -267.0616104074521
episode: 12 training return: tensor(-202.3271, device='cuda:0')
episode: 13 training return: tensor(-162.7903, device='cuda:0')
episode: 14 training return: tensor(-328.5897, device='cuda:0')
episode: 15 training return: tensor(-197.7225, device='cuda:0')
epoch: 4 test_true_pfm: 25.72321624282207 sim_pfm: -82.03775918765459
episode: 16 training return: tensor(16.5845, device='cuda:0')
episode: 17 training return: tensor(-198.4410, device='cuda:0')
episode: 18 training return: tensor(-108.5033, device='cuda:0')
episode: 19 training return: tensor(-145.5217, device='cuda:0')
epoch: 5 test_true_pfm: 21.435598911808547 sim_pfm: -165.21234314159375
episode: 20 training return: tensor(-113.5798, device='cuda:0')
episode: 21 training return: tensor(-153.7415, device='cuda:0')
episode: 22 training return: tensor(35.4423, device='cuda:0')
episode: 23 training return: tensor(43.3856, device='cuda:0')
epoch: 6 test_true_pfm: 2.1569650569717242 sim_pfm: 288.2490729284182
episode: 24 training return: tensor(-98.6378, device='cuda:0')
episode: 25 training return: tensor(81.0551, device='cuda:0')
episode: 26 training return: tensor(70.8140, device='cuda:0')
episode: 27 training return: tensor(151.8860, device='cuda:0')
epoch: 7 test_true_pfm: 21.844272512788166 sim_pfm: 11.47860209653154
episode: 28 training return: tensor(-338.8813, device='cuda:0')
episode: 29 training return: tensor(252.4980, device='cuda:0')
episode: 30 training return: tensor(40.3240, device='cuda:0')
episode: 31 training return: tensor(-14.7114, device='cuda:0')
epoch: 8 test_true_pfm: 33.951283028407296 sim_pfm: 78.84526579456288
episode: 32 training return: tensor(68.2400, device='cuda:0')
episode: 33 training return: tensor(33.0887, device='cuda:0')
episode: 34 training return: tensor(-4.3195, device='cuda:0')
episode: 35 training return: tensor(146.7259, device='cuda:0')
epoch: 9 test_true_pfm: 30.815949945086203 sim_pfm: 114.09138263355707
episode: 36 training return: tensor(195.4611, device='cuda:0')
episode: 37 training return: tensor(111.0956, device='cuda:0')
episode: 38 training return: tensor(484.7990, device='cuda:0')
episode: 39 training return: tensor(588.6321, device='cuda:0')
epoch: 10 test_true_pfm: 35.1029854608829 sim_pfm: 524.7940915664251
episode: 40 training return: tensor(480.9301, device='cuda:0')
episode: 41 training return: tensor(541.3414, device='cuda:0')
episode: 42 training return: tensor(474.0928, device='cuda:0')
episode: 43 training return: tensor(590.8969, device='cuda:0')
epoch: 11 test_true_pfm: 22.85462120201376 sim_pfm: 632.91122609179
episode: 44 training return: tensor(565.3901, device='cuda:0')
episode: 45 training return: tensor(530.7429, device='cuda:0')
episode: 46 training return: tensor(462.5574, device='cuda:0')
episode: 47 training return: tensor(426.4863, device='cuda:0')
epoch: 12 test_true_pfm: 24.908815174477162 sim_pfm: 662.2290749134612
episode: 48 training return: tensor(372.5442, device='cuda:0')
episode: 49 training return: tensor(607.5197, device='cuda:0')
episode: 50 training return: tensor(609.6498, device='cuda:0')
episode: 51 training return: tensor(679.2140, device='cuda:0')
epoch: 13 test_true_pfm: 29.188932486466193 sim_pfm: 618.994794994127
episode: 52 training return: tensor(606.9110, device='cuda:0')
episode: 53 training return: tensor(682.1814, device='cuda:0')
episode: 54 training return: tensor(546.3171, device='cuda:0')
episode: 55 training return: tensor(627.4135, device='cuda:0')
epoch: 14 test_true_pfm: 38.50157925873373 sim_pfm: 650.3013299726881
episode: 56 training return: tensor(605.3912, device='cuda:0')
episode: 57 training return: tensor(617.3677, device='cuda:0')
episode: 58 training return: tensor(620.7131, device='cuda:0')
episode: 59 training return: tensor(621.7299, device='cuda:0')
epoch: 15 test_true_pfm: 31.98754759126487 sim_pfm: 653.879178245226
episode: 60 training return: tensor(620.3792, device='cuda:0')
episode: 61 training return: tensor(640.9166, device='cuda:0')
episode: 62 training return: tensor(630.0226, device='cuda:0')
episode: 63 training return: tensor(647.5876, device='cuda:0')
epoch: 16 test_true_pfm: 31.879063600562308 sim_pfm: 685.7977504749782
episode: 64 training return: tensor(647.9996, device='cuda:0')
episode: 65 training return: tensor(653.8890, device='cuda:0')
episode: 66 training return: tensor(640.4362, device='cuda:0')
episode: 67 training return: tensor(658.7012, device='cuda:0')
epoch: 17 test_true_pfm: 42.96555283219918 sim_pfm: 686.4385295620189
episode: 68 training return: tensor(637.5036, device='cuda:0')
episode: 69 training return: tensor(652.2887, device='cuda:0')
episode: 70 training return: tensor(669.6559, device='cuda:0')
episode: 71 training return: tensor(670.7350, device='cuda:0')
epoch: 18 test_true_pfm: 36.30532763064114 sim_pfm: 704.2438438685145
episode: 72 training return: tensor(676.7935, device='cuda:0')
episode: 73 training return: tensor(664.5653, device='cuda:0')
episode: 74 training return: tensor(690.4356, device='cuda:0')
episode: 75 training return: tensor(698.5783, device='cuda:0')
epoch: 19 test_true_pfm: 28.01914141118981 sim_pfm: 724.3504451389192
episode: 76 training return: tensor(697.6396, device='cuda:0')
episode: 77 training return: tensor(710.2796, device='cuda:0')
episode: 78 training return: tensor(712.3663, device='cuda:0')
episode: 79 training return: tensor(703.3315, device='cuda:0')
epoch: 20 test_true_pfm: 44.035130423277856 sim_pfm: 691.9901912480593
episode: 80 training return: tensor(693.8657, device='cuda:0')
episode: 81 training return: tensor(713.5474, device='cuda:0')
episode: 82 training return: tensor(714.3422, device='cuda:0')
episode: 83 training return: tensor(693.0530, device='cuda:0')
epoch: 21 test_true_pfm: 49.85316995475339 sim_pfm: 704.8844239465892
episode: 84 training return: tensor(687.4472, device='cuda:0')
episode: 85 training return: tensor(693.8190, device='cuda:0')
episode: 86 training return: tensor(683.8671, device='cuda:0')
episode: 87 training return: tensor(685.8682, device='cuda:0')
epoch: 22 test_true_pfm: 49.332024044899704 sim_pfm: 696.5339396750554
episode: 88 training return: tensor(688.9097, device='cuda:0')
episode: 89 training return: tensor(688.3470, device='cuda:0')
episode: 90 training return: tensor(696.2000, device='cuda:0')
episode: 91 training return: tensor(706.3953, device='cuda:0')
epoch: 23 test_true_pfm: 42.08625603739993 sim_pfm: 731.5334743745159
episode: 92 training return: tensor(713.6681, device='cuda:0')
episode: 93 training return: tensor(696.8638, device='cuda:0')
episode: 94 training return: tensor(716.2758, device='cuda:0')
episode: 95 training return: tensor(702.5577, device='cuda:0')
epoch: 24 test_true_pfm: 36.85181570829117 sim_pfm: 706.9040092257317
episode: 96 training return: tensor(701.6589, device='cuda:0')
episode: 97 training return: tensor(707.6579, device='cuda:0')
episode: 98 training return: tensor(705.0720, device='cuda:0')
episode: 99 training return: tensor(699.7610, device='cuda:0')
epoch: 25 test_true_pfm: 31.79754623087132 sim_pfm: 729.7133515338879
episode: 100 training return: tensor(701.5060, device='cuda:0')
episode: 101 training return: tensor(705.7690, device='cuda:0')
episode: 102 training return: tensor(709.2126, device='cuda:0')
episode: 103 training return: tensor(708.3836, device='cuda:0')
epoch: 26 test_true_pfm: 35.96544118009681 sim_pfm: 733.4210437467322
episode: 104 training return: tensor(700.7097, device='cuda:0')
episode: 105 training return: tensor(698.4134, device='cuda:0')
episode: 106 training return: tensor(693.8200, device='cuda:0')
episode: 107 training return: tensor(705.5576, device='cuda:0')
epoch: 27 test_true_pfm: 39.86359771967324 sim_pfm: 728.0553135178983
episode: 108 training return: tensor(710.0770, device='cuda:0')
episode: 109 training return: tensor(693.3050, device='cuda:0')
episode: 110 training return: tensor(694.8296, device='cuda:0')
episode: 111 training return: tensor(722.9402, device='cuda:0')
epoch: 28 test_true_pfm: 43.40060048448295 sim_pfm: 713.5543605139479
episode: 112 training return: tensor(709.7091, device='cuda:0')
episode: 113 training return: tensor(717.4319, device='cuda:0')
episode: 114 training return: tensor(690.3171, device='cuda:0')
episode: 115 training return: tensor(696.5924, device='cuda:0')
epoch: 29 test_true_pfm: 42.74379476782302 sim_pfm: 725.999498309195
episode: 116 training return: tensor(708.6979, device='cuda:0')
episode: 117 training return: tensor(703.7590, device='cuda:0')
episode: 118 training return: tensor(712.2150, device='cuda:0')
episode: 119 training return: tensor(708.0615, device='cuda:0')
epoch: 30 test_true_pfm: 43.56200051624991 sim_pfm: 731.855939630419
episode: 120 training return: tensor(695.1072, device='cuda:0')
episode: 121 training return: tensor(709.6442, device='cuda:0')
episode: 122 training return: tensor(706.0930, device='cuda:0')
episode: 123 training return: tensor(715.0439, device='cuda:0')
epoch: 31 test_true_pfm: 39.10109686388519 sim_pfm: 735.1323886595667
episode: 124 training return: tensor(723.2866, device='cuda:0')
episode: 125 training return: tensor(705.1135, device='cuda:0')
episode: 126 training return: tensor(707.7658, device='cuda:0')
episode: 127 training return: tensor(722.3947, device='cuda:0')
epoch: 32 test_true_pfm: 35.05948198406472 sim_pfm: 744.8416548061883
episode: 128 training return: tensor(704.9105, device='cuda:0')
episode: 129 training return: tensor(700.1179, device='cuda:0')
episode: 130 training return: tensor(694.9656, device='cuda:0')
episode: 131 training return: tensor(708.9150, device='cuda:0')
epoch: 33 test_true_pfm: 40.63257544913428 sim_pfm: 723.607177711837
episode: 132 training return: tensor(679.0570, device='cuda:0')
episode: 133 training return: tensor(715.4579, device='cuda:0')
episode: 134 training return: tensor(682.5592, device='cuda:0')
episode: 135 training return: tensor(704.6049, device='cuda:0')
epoch: 34 test_true_pfm: 45.20090134027105 sim_pfm: 749.4169678498059
episode: 136 training return: tensor(698.6652, device='cuda:0')
episode: 137 training return: tensor(688.5273, device='cuda:0')
episode: 138 training return: tensor(682.7103, device='cuda:0')
episode: 139 training return: tensor(675.0925, device='cuda:0')
epoch: 35 test_true_pfm: 42.62804229069959 sim_pfm: 682.3081748634577
episode: 140 training return: tensor(690.1151, device='cuda:0')
episode: 141 training return: tensor(682.7404, device='cuda:0')
episode: 142 training return: tensor(699.0963, device='cuda:0')
episode: 143 training return: tensor(692.9602, device='cuda:0')
epoch: 36 test_true_pfm: 44.56529759742028 sim_pfm: 701.7628348934929
episode: 144 training return: tensor(704.5804, device='cuda:0')
episode: 145 training return: tensor(717.5943, device='cuda:0')
episode: 146 training return: tensor(695.5712, device='cuda:0')
episode: 147 training return: tensor(685.6995, device='cuda:0')
epoch: 37 test_true_pfm: 50.734997217742944 sim_pfm: 721.5468517005444
episode: 148 training return: tensor(666.7285, device='cuda:0')
episode: 149 training return: tensor(687.8979, device='cuda:0')
episode: 150 training return: tensor(705.1031, device='cuda:0')
episode: 151 training return: tensor(671.0533, device='cuda:0')
epoch: 38 test_true_pfm: 44.51994382106664 sim_pfm: 635.450582158193
episode: 152 training return: tensor(640.6400, device='cuda:0')
episode: 153 training return: tensor(656.2604, device='cuda:0')
episode: 154 training return: tensor(663.9587, device='cuda:0')
episode: 155 training return: tensor(702.8565, device='cuda:0')
epoch: 39 test_true_pfm: 41.44177412453139 sim_pfm: 716.9642570190132
episode: 156 training return: tensor(676.5368, device='cuda:0')
episode: 157 training return: tensor(699.9606, device='cuda:0')
episode: 158 training return: tensor(701.2921, device='cuda:0')
episode: 159 training return: tensor(697.6490, device='cuda:0')
epoch: 40 test_true_pfm: 44.75258809858177 sim_pfm: 726.883805012703
episode: 160 training return: tensor(688.4032, device='cuda:0')
episode: 161 training return: tensor(703.2070, device='cuda:0')
episode: 162 training return: tensor(700.4536, device='cuda:0')
episode: 163 training return: tensor(726.6208, device='cuda:0')
epoch: 41 test_true_pfm: 42.64694890808434 sim_pfm: 748.8396441395395
episode: 164 training return: tensor(696.0709, device='cuda:0')
episode: 165 training return: tensor(717.4478, device='cuda:0')
episode: 166 training return: tensor(704.4071, device='cuda:0')
episode: 167 training return: tensor(713.8138, device='cuda:0')
epoch: 42 test_true_pfm: 40.82450562553688 sim_pfm: 740.0574196275323
episode: 168 training return: tensor(692.3584, device='cuda:0')
episode: 169 training return: tensor(713.0808, device='cuda:0')
episode: 170 training return: tensor(702.4214, device='cuda:0')
episode: 171 training return: tensor(689.3997, device='cuda:0')
epoch: 43 test_true_pfm: 39.8474524068305 sim_pfm: 752.8472580341622
episode: 172 training return: tensor(718.8937, device='cuda:0')
episode: 173 training return: tensor(715.1768, device='cuda:0')
episode: 174 training return: tensor(706.2944, device='cuda:0')
episode: 175 training return: tensor(704.4054, device='cuda:0')
epoch: 44 test_true_pfm: 39.640344471870996 sim_pfm: 753.3454283924773
episode: 176 training return: tensor(739.8467, device='cuda:0')
episode: 177 training return: tensor(713.3893, device='cuda:0')
episode: 178 training return: tensor(720.2347, device='cuda:0')
episode: 179 training return: tensor(722.6336, device='cuda:0')
epoch: 45 test_true_pfm: 21.216286520654258 sim_pfm: 720.3789041988551
episode: 180 training return: tensor(721.7124, device='cuda:0')
episode: 181 training return: tensor(692.0744, device='cuda:0')
episode: 182 training return: tensor(718.9870, device='cuda:0')
episode: 183 training return: tensor(702.5466, device='cuda:0')
epoch: 46 test_true_pfm: 42.59751456129218 sim_pfm: 737.9940673040226
episode: 184 training return: tensor(710.4459, device='cuda:0')
episode: 185 training return: tensor(730.8254, device='cuda:0')
episode: 186 training return: tensor(706.6283, device='cuda:0')
episode: 187 training return: tensor(715.9140, device='cuda:0')
epoch: 47 test_true_pfm: 40.22091829235647 sim_pfm: 736.5696529811714
episode: 188 training return: tensor(719.9507, device='cuda:0')
episode: 189 training return: tensor(692.3242, device='cuda:0')
episode: 190 training return: tensor(702.9518, device='cuda:0')
episode: 191 training return: tensor(721.3297, device='cuda:0')
epoch: 48 test_true_pfm: 40.07061490778455 sim_pfm: 738.4643778555095
episode: 192 training return: tensor(671.7648, device='cuda:0')
episode: 193 training return: tensor(696.1494, device='cuda:0')
episode: 194 training return: tensor(728.0662, device='cuda:0')
episode: 195 training return: tensor(711.6793, device='cuda:0')
epoch: 49 test_true_pfm: 37.93715540270462 sim_pfm: 746.600846693106
episode: 196 training return: tensor(716.2134, device='cuda:0')
episode: 197 training return: tensor(731.5980, device='cuda:0')
episode: 198 training return: tensor(714.0246, device='cuda:0')
episode: 199 training return: tensor(681.2194, device='cuda:0')
epoch: 50 test_true_pfm: 40.41954454004623 sim_pfm: 742.560358939739
episode: 200 training return: tensor(695.3972, device='cuda:0')
episode: 201 training return: tensor(742.7325, device='cuda:0')
episode: 202 training return: tensor(727.0682, device='cuda:0')
episode: 203 training return: tensor(720.2003, device='cuda:0')
epoch: 51 test_true_pfm: 41.892138162151866 sim_pfm: 756.0791734457016
episode: 204 training return: tensor(732.0544, device='cuda:0')
episode: 205 training return: tensor(698.5486, device='cuda:0')
episode: 206 training return: tensor(740.4163, device='cuda:0')
episode: 207 training return: tensor(697.5317, device='cuda:0')
epoch: 52 test_true_pfm: 36.010720807004816 sim_pfm: 740.0565235558897
episode: 208 training return: tensor(725.6219, device='cuda:0')
episode: 209 training return: tensor(732.1829, device='cuda:0')
episode: 210 training return: tensor(742.2969, device='cuda:0')
episode: 211 training return: tensor(709.7502, device='cuda:0')
epoch: 53 test_true_pfm: 44.61572531769658 sim_pfm: 745.3171198099851
episode: 212 training return: tensor(729.0386, device='cuda:0')
episode: 213 training return: tensor(747.6017, device='cuda:0')
episode: 214 training return: tensor(733.3797, device='cuda:0')
episode: 215 training return: tensor(734.1352, device='cuda:0')
epoch: 54 test_true_pfm: 40.09509685872555 sim_pfm: 753.9155747091456
episode: 216 training return: tensor(748.6846, device='cuda:0')
episode: 217 training return: tensor(719.4217, device='cuda:0')
episode: 218 training return: tensor(726.3220, device='cuda:0')
episode: 219 training return: tensor(714.1508, device='cuda:0')
epoch: 55 test_true_pfm: 44.06673740571281 sim_pfm: 758.9318837543484
episode: 220 training return: tensor(733.1528, device='cuda:0')
episode: 221 training return: tensor(720.3192, device='cuda:0')
episode: 222 training return: tensor(749.1390, device='cuda:0')
episode: 223 training return: tensor(737.4210, device='cuda:0')
epoch: 56 test_true_pfm: 46.070423076792416 sim_pfm: 770.9186657220125
episode: 224 training return: tensor(723.8948, device='cuda:0')
episode: 225 training return: tensor(734.3491, device='cuda:0')
episode: 226 training return: tensor(727.7235, device='cuda:0')
episode: 227 training return: tensor(723.0679, device='cuda:0')
epoch: 57 test_true_pfm: 48.70273468240275 sim_pfm: 776.6725854218006
episode: 228 training return: tensor(734.0984, device='cuda:0')
episode: 229 training return: tensor(738.1655, device='cuda:0')
episode: 230 training return: tensor(716.1984, device='cuda:0')
episode: 231 training return: tensor(745.5063, device='cuda:0')
epoch: 58 test_true_pfm: 46.048162810724065 sim_pfm: 758.8333042062819
episode: 232 training return: tensor(743.4362, device='cuda:0')
episode: 233 training return: tensor(744.3217, device='cuda:0')
episode: 234 training return: tensor(728.6510, device='cuda:0')
episode: 235 training return: tensor(727.9779, device='cuda:0')
epoch: 59 test_true_pfm: 42.59388975548427 sim_pfm: 766.0970193132758
episode: 236 training return: tensor(729.1699, device='cuda:0')
episode: 237 training return: tensor(720.9282, device='cuda:0')
episode: 238 training return: tensor(724.0732, device='cuda:0')
episode: 239 training return: tensor(730.2476, device='cuda:0')
epoch: 60 test_true_pfm: 36.19482311838349 sim_pfm: 759.0969636356924
episode: 240 training return: tensor(739.2535, device='cuda:0')
episode: 241 training return: tensor(737.2823, device='cuda:0')
episode: 242 training return: tensor(730.9713, device='cuda:0')
episode: 243 training return: tensor(738.6113, device='cuda:0')
epoch: 61 test_true_pfm: 47.311233692211395 sim_pfm: 758.4323549959809
episode: 244 training return: tensor(740.3230, device='cuda:0')
episode: 245 training return: tensor(733.6810, device='cuda:0')
episode: 246 training return: tensor(726.6167, device='cuda:0')
episode: 247 training return: tensor(737.5734, device='cuda:0')
epoch: 62 test_true_pfm: 46.50910933270079 sim_pfm: 758.8870852895081
episode: 248 training return: tensor(735.3379, device='cuda:0')
episode: 249 training return: tensor(717.5135, device='cuda:0')
episode: 250 training return: tensor(730.1795, device='cuda:0')
episode: 251 training return: tensor(727.1265, device='cuda:0')
epoch: 63 test_true_pfm: 41.204804539480385 sim_pfm: 752.0871197273955
episode: 252 training return: tensor(712.6411, device='cuda:0')
episode: 253 training return: tensor(713.6309, device='cuda:0')
episode: 254 training return: tensor(742.9180, device='cuda:0')
episode: 255 training return: tensor(712.3549, device='cuda:0')
epoch: 64 test_true_pfm: 46.96021173139836 sim_pfm: 737.1061205923558
episode: 256 training return: tensor(736.4312, device='cuda:0')
episode: 257 training return: tensor(738.5269, device='cuda:0')
episode: 258 training return: tensor(741.9202, device='cuda:0')
episode: 259 training return: tensor(725.3979, device='cuda:0')
epoch: 65 test_true_pfm: 45.139970771953315 sim_pfm: 762.8925541160977
episode: 260 training return: tensor(737.1287, device='cuda:0')
episode: 261 training return: tensor(740.4183, device='cuda:0')
episode: 262 training return: tensor(723.7795, device='cuda:0')
episode: 263 training return: tensor(723.2089, device='cuda:0')
epoch: 66 test_true_pfm: 43.51106491671531 sim_pfm: 756.3706894558388
episode: 264 training return: tensor(722.9922, device='cuda:0')
episode: 265 training return: tensor(712.0073, device='cuda:0')
episode: 266 training return: tensor(735.5393, device='cuda:0')
episode: 267 training return: tensor(715.0137, device='cuda:0')
epoch: 67 test_true_pfm: 42.94223055458061 sim_pfm: 752.3179649692029
episode: 268 training return: tensor(699.5054, device='cuda:0')
episode: 269 training return: tensor(724.1620, device='cuda:0')
episode: 270 training return: tensor(735.5060, device='cuda:0')
episode: 271 training return: tensor(725.3771, device='cuda:0')
epoch: 68 test_true_pfm: 40.913234049215944 sim_pfm: 766.4823740207124
episode: 272 training return: tensor(725.9288, device='cuda:0')
episode: 273 training return: tensor(713.8493, device='cuda:0')
episode: 274 training return: tensor(744.8870, device='cuda:0')
episode: 275 training return: tensor(729.4716, device='cuda:0')
epoch: 69 test_true_pfm: 43.98888992691465 sim_pfm: 769.8687532206881
episode: 276 training return: tensor(723.4988, device='cuda:0')
episode: 277 training return: tensor(723.3782, device='cuda:0')
episode: 278 training return: tensor(725.2297, device='cuda:0')
episode: 279 training return: tensor(724.4941, device='cuda:0')
epoch: 70 test_true_pfm: 46.38249569264291 sim_pfm: 756.2163626910187
episode: 280 training return: tensor(745.6653, device='cuda:0')
episode: 281 training return: tensor(718.0437, device='cuda:0')
episode: 282 training return: tensor(688.2012, device='cuda:0')
episode: 283 training return: tensor(727.0903, device='cuda:0')
epoch: 71 test_true_pfm: 43.2196421629246 sim_pfm: 742.825478738919
episode: 284 training return: tensor(705.8094, device='cuda:0')
episode: 285 training return: tensor(713.4152, device='cuda:0')
episode: 286 training return: tensor(729.0941, device='cuda:0')
episode: 287 training return: tensor(720.6489, device='cuda:0')
epoch: 72 test_true_pfm: 40.888343153308575 sim_pfm: 763.6375928808004
episode: 288 training return: tensor(717.4474, device='cuda:0')
episode: 289 training return: tensor(740.5358, device='cuda:0')
episode: 290 training return: tensor(726.1234, device='cuda:0')
episode: 291 training return: tensor(730.0402, device='cuda:0')
epoch: 73 test_true_pfm: 46.53612998616247 sim_pfm: 759.0472177176969
episode: 292 training return: tensor(739.9800, device='cuda:0')
episode: 293 training return: tensor(739.8575, device='cuda:0')
episode: 294 training return: tensor(742.1392, device='cuda:0')
episode: 295 training return: tensor(729.3828, device='cuda:0')
epoch: 74 test_true_pfm: 40.054120497619564 sim_pfm: 747.1434131888673
episode: 296 training return: tensor(724.1882, device='cuda:0')
episode: 297 training return: tensor(721.0386, device='cuda:0')
episode: 298 training return: tensor(741.6883, device='cuda:0')
episode: 299 training return: tensor(700.0454, device='cuda:0')
epoch: 75 test_true_pfm: 43.02481809559371 sim_pfm: 772.7709748003632
episode: 300 training return: tensor(683.0119, device='cuda:0')
episode: 301 training return: tensor(727.5363, device='cuda:0')
episode: 302 training return: tensor(732.9382, device='cuda:0')
episode: 303 training return: tensor(727.8676, device='cuda:0')
epoch: 76 test_true_pfm: 44.18453709818883 sim_pfm: 763.935191976279
episode: 304 training return: tensor(732.9831, device='cuda:0')
episode: 305 training return: tensor(736.6659, device='cuda:0')
episode: 306 training return: tensor(731.5413, device='cuda:0')
episode: 307 training return: tensor(720.2891, device='cuda:0')
epoch: 77 test_true_pfm: 46.39809904140104 sim_pfm: 755.440710780397
episode: 308 training return: tensor(738.5118, device='cuda:0')
episode: 309 training return: tensor(720.1898, device='cuda:0')
episode: 310 training return: tensor(736.6505, device='cuda:0')
episode: 311 training return: tensor(723.0276, device='cuda:0')
epoch: 78 test_true_pfm: 45.129311285840274 sim_pfm: 765.9039838738739
episode: 312 training return: tensor(728.0163, device='cuda:0')
episode: 313 training return: tensor(713.6401, device='cuda:0')
episode: 314 training return: tensor(713.2941, device='cuda:0')
episode: 315 training return: tensor(724.9533, device='cuda:0')
epoch: 79 test_true_pfm: 38.195116065837865 sim_pfm: 755.3972497530282
episode: 316 training return: tensor(737.8962, device='cuda:0')
episode: 317 training return: tensor(750.0833, device='cuda:0')
episode: 318 training return: tensor(732.5009, device='cuda:0')
episode: 319 training return: tensor(737.7781, device='cuda:0')
epoch: 80 test_true_pfm: 41.45232439398898 sim_pfm: 760.3244965137914
episode: 320 training return: tensor(738.1470, device='cuda:0')
episode: 321 training return: tensor(735.4404, device='cuda:0')
episode: 322 training return: tensor(750.2758, device='cuda:0')
episode: 323 training return: tensor(717.4431, device='cuda:0')
epoch: 81 test_true_pfm: 42.277079802789906 sim_pfm: 772.2537699148058
episode: 324 training return: tensor(743.7943, device='cuda:0')
episode: 325 training return: tensor(737.5298, device='cuda:0')
episode: 326 training return: tensor(731.3666, device='cuda:0')
episode: 327 training return: tensor(745.4030, device='cuda:0')
epoch: 82 test_true_pfm: 46.485067152599804 sim_pfm: 774.1342231968534
episode: 328 training return: tensor(725.9005, device='cuda:0')
episode: 329 training return: tensor(744.3383, device='cuda:0')
episode: 330 training return: tensor(731.0662, device='cuda:0')
episode: 331 training return: tensor(741.9820, device='cuda:0')
epoch: 83 test_true_pfm: 42.633947448922946 sim_pfm: 759.7248350605369
episode: 332 training return: tensor(717.9045, device='cuda:0')
episode: 333 training return: tensor(742.5627, device='cuda:0')
episode: 334 training return: tensor(742.8151, device='cuda:0')
episode: 335 training return: tensor(727.6000, device='cuda:0')
epoch: 84 test_true_pfm: 47.31709431162603 sim_pfm: 770.1587652526796
episode: 336 training return: tensor(726.8516, device='cuda:0')
episode: 337 training return: tensor(729.0939, device='cuda:0')
episode: 338 training return: tensor(726.8907, device='cuda:0')
episode: 339 training return: tensor(736.7811, device='cuda:0')
epoch: 85 test_true_pfm: 44.26330772225474 sim_pfm: 761.7214454028756
episode: 340 training return: tensor(728.5379, device='cuda:0')
episode: 341 training return: tensor(743.1118, device='cuda:0')
episode: 342 training return: tensor(738.2580, device='cuda:0')
episode: 343 training return: tensor(742.3588, device='cuda:0')
epoch: 86 test_true_pfm: 36.59057330581402 sim_pfm: 765.2005406923593
episode: 344 training return: tensor(742.5608, device='cuda:0')
episode: 345 training return: tensor(752.9833, device='cuda:0')
episode: 346 training return: tensor(717.8497, device='cuda:0')
episode: 347 training return: tensor(739.9481, device='cuda:0')
epoch: 87 test_true_pfm: 40.04249103701514 sim_pfm: 778.8026309341192
episode: 348 training return: tensor(727.3616, device='cuda:0')
episode: 349 training return: tensor(744.1942, device='cuda:0')
episode: 350 training return: tensor(739.0229, device='cuda:0')
episode: 351 training return: tensor(744.5707, device='cuda:0')
epoch: 88 test_true_pfm: 48.86281727096911 sim_pfm: 771.6787472363561
episode: 352 training return: tensor(745.0524, device='cuda:0')
episode: 353 training return: tensor(729.9797, device='cuda:0')
episode: 354 training return: tensor(724.7393, device='cuda:0')
episode: 355 training return: tensor(727.3487, device='cuda:0')
epoch: 89 test_true_pfm: 48.06894485271699 sim_pfm: 768.9233421891928
episode: 356 training return: tensor(758.3322, device='cuda:0')
episode: 357 training return: tensor(744.1492, device='cuda:0')
episode: 358 training return: tensor(725.8981, device='cuda:0')
episode: 359 training return: tensor(751.6041, device='cuda:0')
epoch: 90 test_true_pfm: 45.25132712198233 sim_pfm: 772.9261836282909
episode: 360 training return: tensor(734.8954, device='cuda:0')
episode: 361 training return: tensor(735.0057, device='cuda:0')
episode: 362 training return: tensor(728.4274, device='cuda:0')
episode: 363 training return: tensor(711.9209, device='cuda:0')
epoch: 91 test_true_pfm: 51.75151191546644 sim_pfm: 700.8817161029438
episode: 364 training return: tensor(720.5020, device='cuda:0')
episode: 365 training return: tensor(700.1665, device='cuda:0')
episode: 366 training return: tensor(690.9750, device='cuda:0')
episode: 367 training return: tensor(729.3904, device='cuda:0')
epoch: 92 test_true_pfm: 47.419835953330065 sim_pfm: 749.7317433323711
episode: 368 training return: tensor(744.8651, device='cuda:0')
episode: 369 training return: tensor(735.1948, device='cuda:0')
episode: 370 training return: tensor(737.3247, device='cuda:0')
episode: 371 training return: tensor(753.1936, device='cuda:0')
epoch: 93 test_true_pfm: 37.08766711913907 sim_pfm: 777.4998778134584
episode: 372 training return: tensor(747.0769, device='cuda:0')
episode: 373 training return: tensor(731.5062, device='cuda:0')
episode: 374 training return: tensor(740.8431, device='cuda:0')
episode: 375 training return: tensor(726.2349, device='cuda:0')
epoch: 94 test_true_pfm: 41.60074414055405 sim_pfm: 777.1320980470628
episode: 376 training return: tensor(748.7149, device='cuda:0')
episode: 377 training return: tensor(742.1205, device='cuda:0')
episode: 378 training return: tensor(748.9913, device='cuda:0')
episode: 379 training return: tensor(764.0430, device='cuda:0')
epoch: 95 test_true_pfm: 43.055717093519455 sim_pfm: 772.4133494950831
episode: 380 training return: tensor(744.3315, device='cuda:0')
episode: 381 training return: tensor(744.7211, device='cuda:0')
episode: 382 training return: tensor(740.1119, device='cuda:0')
episode: 383 training return: tensor(748.7815, device='cuda:0')
epoch: 96 test_true_pfm: 36.65976034956949 sim_pfm: 777.2077385727316
episode: 384 training return: tensor(746.5558, device='cuda:0')
episode: 385 training return: tensor(750.3973, device='cuda:0')
episode: 386 training return: tensor(749.5002, device='cuda:0')
episode: 387 training return: tensor(734.2479, device='cuda:0')
epoch: 97 test_true_pfm: 39.77538622585711 sim_pfm: 753.8417779842391
episode: 388 training return: tensor(743.6202, device='cuda:0')
episode: 389 training return: tensor(756.9337, device='cuda:0')
episode: 390 training return: tensor(754.0748, device='cuda:0')
episode: 391 training return: tensor(735.7265, device='cuda:0')
epoch: 98 test_true_pfm: 45.5753807242148 sim_pfm: 760.8288397058611
episode: 392 training return: tensor(735.7594, device='cuda:0')
episode: 393 training return: tensor(732.2521, device='cuda:0')
episode: 394 training return: tensor(729.4055, device='cuda:0')
episode: 395 training return: tensor(746.8840, device='cuda:0')
epoch: 99 test_true_pfm: 52.365046619184135 sim_pfm: 770.2527840606868
episode: 396 training return: tensor(736.5684, device='cuda:0')
episode: 397 training return: tensor(723.5703, device='cuda:0')
episode: 398 training return: tensor(734.6072, device='cuda:0')
episode: 399 training return: tensor(735.7308, device='cuda:0')
epoch: 100 test_true_pfm: 47.26204344118365 sim_pfm: 758.5812636161223
episode: 400 training return: tensor(751.3278, device='cuda:0')
episode: 401 training return: tensor(733.0077, device='cuda:0')
episode: 402 training return: tensor(753.5138, device='cuda:0')
episode: 403 training return: tensor(744.1993, device='cuda:0')
epoch: 101 test_true_pfm: 47.438527616716556 sim_pfm: 769.4346496464684
episode: 404 training return: tensor(730.0818, device='cuda:0')
episode: 405 training return: tensor(735.3837, device='cuda:0')
episode: 406 training return: tensor(741.3221, device='cuda:0')
episode: 407 training return: tensor(742.3591, device='cuda:0')
epoch: 102 test_true_pfm: 44.965598698851295 sim_pfm: 766.2147073998116
episode: 408 training return: tensor(751.2781, device='cuda:0')
episode: 409 training return: tensor(742.5609, device='cuda:0')
episode: 410 training return: tensor(722.8324, device='cuda:0')
episode: 411 training return: tensor(742.3074, device='cuda:0')
epoch: 103 test_true_pfm: 41.351199039868035 sim_pfm: 772.6485430836677
episode: 412 training return: tensor(724.6073, device='cuda:0')
episode: 413 training return: tensor(759.0806, device='cuda:0')
episode: 414 training return: tensor(746.9426, device='cuda:0')
episode: 415 training return: tensor(747.5284, device='cuda:0')
epoch: 104 test_true_pfm: 48.34772851905539 sim_pfm: 770.5064372483641
episode: 416 training return: tensor(755.8972, device='cuda:0')
episode: 417 training return: tensor(758.5076, device='cuda:0')
episode: 418 training return: tensor(746.1029, device='cuda:0')
episode: 419 training return: tensor(753.1911, device='cuda:0')
epoch: 105 test_true_pfm: 45.05999135439341 sim_pfm: 788.0424962405116
episode: 420 training return: tensor(756.2562, device='cuda:0')
episode: 421 training return: tensor(745.9169, device='cuda:0')
episode: 422 training return: tensor(737.6051, device='cuda:0')
episode: 423 training return: tensor(719.4314, device='cuda:0')
epoch: 106 test_true_pfm: 45.60967566046447 sim_pfm: 764.3899075372144
episode: 424 training return: tensor(723.8875, device='cuda:0')
episode: 425 training return: tensor(725.5306, device='cuda:0')
episode: 426 training return: tensor(713.9260, device='cuda:0')
episode: 427 training return: tensor(707.0800, device='cuda:0')
epoch: 107 test_true_pfm: 42.33298222103251 sim_pfm: 771.86629255414
episode: 428 training return: tensor(732.9701, device='cuda:0')
episode: 429 training return: tensor(732.5061, device='cuda:0')
episode: 430 training return: tensor(707.5965, device='cuda:0')
episode: 431 training return: tensor(742.8793, device='cuda:0')
epoch: 108 test_true_pfm: 41.78035219294433 sim_pfm: 752.9996939450502
episode: 432 training return: tensor(721.5518, device='cuda:0')
episode: 433 training return: tensor(726.6147, device='cuda:0')
episode: 434 training return: tensor(732.3444, device='cuda:0')
episode: 435 training return: tensor(732.8954, device='cuda:0')
epoch: 109 test_true_pfm: 36.657591820627616 sim_pfm: 760.7038198679686
episode: 436 training return: tensor(727.0680, device='cuda:0')
episode: 437 training return: tensor(736.2816, device='cuda:0')
episode: 438 training return: tensor(724.8090, device='cuda:0')
episode: 439 training return: tensor(742.2027, device='cuda:0')
epoch: 110 test_true_pfm: 43.00466608986288 sim_pfm: 767.1696590647101
episode: 440 training return: tensor(747.6229, device='cuda:0')
episode: 441 training return: tensor(726.4604, device='cuda:0')
episode: 442 training return: tensor(742.8550, device='cuda:0')
episode: 443 training return: tensor(745.8715, device='cuda:0')
epoch: 111 test_true_pfm: 47.00991140125389 sim_pfm: 770.8718637108802
episode: 444 training return: tensor(749.9857, device='cuda:0')
episode: 445 training return: tensor(730.2199, device='cuda:0')
episode: 446 training return: tensor(732.0741, device='cuda:0')
episode: 447 training return: tensor(737.7455, device='cuda:0')
epoch: 112 test_true_pfm: 47.94941647759267 sim_pfm: 765.7879814419896
episode: 448 training return: tensor(733.5189, device='cuda:0')
episode: 449 training return: tensor(727.6119, device='cuda:0')
episode: 450 training return: tensor(748.7750, device='cuda:0')
episode: 451 training return: tensor(719.1007, device='cuda:0')
epoch: 113 test_true_pfm: 51.82883094034859 sim_pfm: 749.8301917999983
episode: 452 training return: tensor(710.2227, device='cuda:0')
episode: 453 training return: tensor(738.4147, device='cuda:0')
episode: 454 training return: tensor(746.8192, device='cuda:0')
episode: 455 training return: tensor(743.9929, device='cuda:0')
epoch: 114 test_true_pfm: 47.86775780448711 sim_pfm: 759.7052266381681
episode: 456 training return: tensor(743.2416, device='cuda:0')
episode: 457 training return: tensor(748.9011, device='cuda:0')
episode: 458 training return: tensor(746.2662, device='cuda:0')
episode: 459 training return: tensor(742.0024, device='cuda:0')
epoch: 115 test_true_pfm: 48.17002414013192 sim_pfm: 767.6222442914732
episode: 460 training return: tensor(737.7615, device='cuda:0')
episode: 461 training return: tensor(740.5892, device='cuda:0')
episode: 462 training return: tensor(748.6204, device='cuda:0')
episode: 463 training return: tensor(748.8915, device='cuda:0')
epoch: 116 test_true_pfm: 59.76331121745973 sim_pfm: 762.1655528211966
episode: 464 training return: tensor(747.9738, device='cuda:0')
episode: 465 training return: tensor(742.6301, device='cuda:0')
episode: 466 training return: tensor(757.0173, device='cuda:0')
episode: 467 training return: tensor(752.5919, device='cuda:0')
epoch: 117 test_true_pfm: 46.2130849961214 sim_pfm: 778.9461500100791
episode: 468 training return: tensor(736.3694, device='cuda:0')
episode: 469 training return: tensor(755.7579, device='cuda:0')
episode: 470 training return: tensor(699.0807, device='cuda:0')
episode: 471 training return: tensor(748.1250, device='cuda:0')
epoch: 118 test_true_pfm: 41.43937491516255 sim_pfm: 774.3367642790079
episode: 472 training return: tensor(738.0176, device='cuda:0')
episode: 473 training return: tensor(758.2437, device='cuda:0')
episode: 474 training return: tensor(758.0239, device='cuda:0')
episode: 475 training return: tensor(747.8082, device='cuda:0')
epoch: 119 test_true_pfm: 48.98766912342593 sim_pfm: 778.7309856627137
episode: 476 training return: tensor(754.5606, device='cuda:0')
episode: 477 training return: tensor(755.8032, device='cuda:0')
episode: 478 training return: tensor(736.8928, device='cuda:0')
episode: 479 training return: tensor(745.9849, device='cuda:0')
epoch: 120 test_true_pfm: 53.86756833465593 sim_pfm: 754.1849815505208
episode: 480 training return: tensor(743.7894, device='cuda:0')
episode: 481 training return: tensor(741.7075, device='cuda:0')
episode: 482 training return: tensor(744.1794, device='cuda:0')
episode: 483 training return: tensor(753.6271, device='cuda:0')
epoch: 121 test_true_pfm: 40.29374780450265 sim_pfm: 772.6269176528789
episode: 484 training return: tensor(745.5715, device='cuda:0')
episode: 485 training return: tensor(755.8935, device='cuda:0')
episode: 486 training return: tensor(749.2225, device='cuda:0')
episode: 487 training return: tensor(758.5753, device='cuda:0')
epoch: 122 test_true_pfm: 54.783292389650114 sim_pfm: 770.6440938021988
episode: 488 training return: tensor(759.3044, device='cuda:0')
episode: 489 training return: tensor(743.7316, device='cuda:0')
episode: 490 training return: tensor(762.7770, device='cuda:0')
episode: 491 training return: tensor(765.4675, device='cuda:0')
epoch: 123 test_true_pfm: 43.93408667290787 sim_pfm: 781.4464144831524
episode: 492 training return: tensor(731.8019, device='cuda:0')
episode: 493 training return: tensor(725.3004, device='cuda:0')
episode: 494 training return: tensor(744.4860, device='cuda:0')
episode: 495 training return: tensor(731.8958, device='cuda:0')
epoch: 124 test_true_pfm: 44.947064854823275 sim_pfm: 775.2560822818429
episode: 496 training return: tensor(736.3176, device='cuda:0')
episode: 497 training return: tensor(738.1359, device='cuda:0')
episode: 498 training return: tensor(741.8301, device='cuda:0')
episode: 499 training return: tensor(763.9724, device='cuda:0')
epoch: 125 test_true_pfm: 50.9680468898402 sim_pfm: 773.3674060713499
episode: 500 training return: tensor(721.8159, device='cuda:0')
episode: 501 training return: tensor(740.7851, device='cuda:0')
episode: 502 training return: tensor(764.3147, device='cuda:0')
episode: 503 training return: tensor(744.3696, device='cuda:0')
epoch: 126 test_true_pfm: 44.19449213678433 sim_pfm: 763.7609534844756
episode: 504 training return: tensor(717.1358, device='cuda:0')
episode: 505 training return: tensor(755.9414, device='cuda:0')
episode: 506 training return: tensor(744.4898, device='cuda:0')
episode: 507 training return: tensor(745.4534, device='cuda:0')
epoch: 127 test_true_pfm: 47.15268326886476 sim_pfm: 779.2710770694539
episode: 508 training return: tensor(748.9164, device='cuda:0')
episode: 509 training return: tensor(748.8037, device='cuda:0')
episode: 510 training return: tensor(760.8141, device='cuda:0')
episode: 511 training return: tensor(753.6453, device='cuda:0')
epoch: 128 test_true_pfm: 48.34068030392178 sim_pfm: 781.0753559762612
episode: 512 training return: tensor(751.5159, device='cuda:0')
episode: 513 training return: tensor(758.9368, device='cuda:0')
episode: 514 training return: tensor(740.9957, device='cuda:0')
episode: 515 training return: tensor(749.0560, device='cuda:0')
epoch: 129 test_true_pfm: 46.893354602153366 sim_pfm: 775.0861446741968
episode: 516 training return: tensor(747.1772, device='cuda:0')
episode: 517 training return: tensor(759.8362, device='cuda:0')
episode: 518 training return: tensor(741.1364, device='cuda:0')
episode: 519 training return: tensor(734.9725, device='cuda:0')
epoch: 130 test_true_pfm: 45.34568821111983 sim_pfm: 779.0723148342222
episode: 520 training return: tensor(761.0182, device='cuda:0')
episode: 521 training return: tensor(757.4586, device='cuda:0')
episode: 522 training return: tensor(759.4276, device='cuda:0')
episode: 523 training return: tensor(751.3950, device='cuda:0')
epoch: 131 test_true_pfm: 44.025635058953 sim_pfm: 783.564152111765
episode: 524 training return: tensor(747.8742, device='cuda:0')
episode: 525 training return: tensor(766.1196, device='cuda:0')
episode: 526 training return: tensor(736.6562, device='cuda:0')
episode: 527 training return: tensor(742.3405, device='cuda:0')
epoch: 132 test_true_pfm: 48.88229653809451 sim_pfm: 779.5513649899513
episode: 528 training return: tensor(747.8302, device='cuda:0')
episode: 529 training return: tensor(750.0721, device='cuda:0')
episode: 530 training return: tensor(751.1237, device='cuda:0')
episode: 531 training return: tensor(753.6083, device='cuda:0')
epoch: 133 test_true_pfm: 39.95398835142234 sim_pfm: 776.5820642098785
episode: 532 training return: tensor(742.9993, device='cuda:0')
episode: 533 training return: tensor(739.6522, device='cuda:0')
episode: 534 training return: tensor(739.7195, device='cuda:0')
episode: 535 training return: tensor(748.6974, device='cuda:0')
epoch: 134 test_true_pfm: 36.708965701956565 sim_pfm: 766.6751149561256
episode: 536 training return: tensor(750.4145, device='cuda:0')
episode: 537 training return: tensor(760.2459, device='cuda:0')
episode: 538 training return: tensor(719.6309, device='cuda:0')
episode: 539 training return: tensor(744.3891, device='cuda:0')
epoch: 135 test_true_pfm: 45.18427117408081 sim_pfm: 788.0945623628795
episode: 540 training return: tensor(751.5749, device='cuda:0')
episode: 541 training return: tensor(727.8077, device='cuda:0')
episode: 542 training return: tensor(745.8289, device='cuda:0')
episode: 543 training return: tensor(756.5988, device='cuda:0')
epoch: 136 test_true_pfm: 44.671849350969076 sim_pfm: 772.3741395133081
episode: 544 training return: tensor(749.4315, device='cuda:0')
episode: 545 training return: tensor(755.8533, device='cuda:0')
episode: 546 training return: tensor(729.2276, device='cuda:0')
episode: 547 training return: tensor(743.3137, device='cuda:0')
epoch: 137 test_true_pfm: 49.93597646841703 sim_pfm: 779.8746724884957
episode: 548 training return: tensor(743.4866, device='cuda:0')
episode: 549 training return: tensor(754.6661, device='cuda:0')
episode: 550 training return: tensor(748.3259, device='cuda:0')
episode: 551 training return: tensor(741.0864, device='cuda:0')
epoch: 138 test_true_pfm: 43.760976382565694 sim_pfm: 735.8075108969584
episode: 552 training return: tensor(741.1386, device='cuda:0')
episode: 553 training return: tensor(732.1755, device='cuda:0')
episode: 554 training return: tensor(740.9140, device='cuda:0')
episode: 555 training return: tensor(742.6744, device='cuda:0')
epoch: 139 test_true_pfm: 37.47373733102954 sim_pfm: 770.7001282501966
episode: 556 training return: tensor(755.6061, device='cuda:0')
episode: 557 training return: tensor(754.9168, device='cuda:0')
episode: 558 training return: tensor(746.4695, device='cuda:0')
episode: 559 training return: tensor(757.7887, device='cuda:0')
epoch: 140 test_true_pfm: 49.90847229582192 sim_pfm: 782.4837570442818
episode: 560 training return: tensor(752.0165, device='cuda:0')
episode: 561 training return: tensor(740.2983, device='cuda:0')
episode: 562 training return: tensor(749.6267, device='cuda:0')
episode: 563 training return: tensor(761.1956, device='cuda:0')
epoch: 141 test_true_pfm: 49.873494134389276 sim_pfm: 779.3740288039669
episode: 564 training return: tensor(760.2788, device='cuda:0')
episode: 565 training return: tensor(759.4998, device='cuda:0')
episode: 566 training return: tensor(743.2695, device='cuda:0')
episode: 567 training return: tensor(755.5032, device='cuda:0')
epoch: 142 test_true_pfm: 43.49720098447238 sim_pfm: 790.1820643185638
episode: 568 training return: tensor(760.6407, device='cuda:0')
episode: 569 training return: tensor(767.7947, device='cuda:0')
episode: 570 training return: tensor(759.5499, device='cuda:0')
episode: 571 training return: tensor(767.2930, device='cuda:0')
epoch: 143 test_true_pfm: 47.845505540108725 sim_pfm: 772.0441702179611
episode: 572 training return: tensor(760.7910, device='cuda:0')
episode: 573 training return: tensor(767.6604, device='cuda:0')
episode: 574 training return: tensor(764.1006, device='cuda:0')
episode: 575 training return: tensor(758.4432, device='cuda:0')
epoch: 144 test_true_pfm: 45.32899685577819 sim_pfm: 786.7204307879322
episode: 576 training return: tensor(759.2874, device='cuda:0')
episode: 577 training return: tensor(729.5220, device='cuda:0')
episode: 578 training return: tensor(733.9922, device='cuda:0')
episode: 579 training return: tensor(748.7327, device='cuda:0')
epoch: 145 test_true_pfm: 41.048701544844405 sim_pfm: 789.6301374667789
episode: 580 training return: tensor(748.1776, device='cuda:0')
episode: 581 training return: tensor(756.6610, device='cuda:0')
episode: 582 training return: tensor(757.4888, device='cuda:0')
episode: 583 training return: tensor(766.2136, device='cuda:0')
epoch: 146 test_true_pfm: 42.40422263255256 sim_pfm: 781.7139085419476
episode: 584 training return: tensor(742.8351, device='cuda:0')
episode: 585 training return: tensor(739.5843, device='cuda:0')
episode: 586 training return: tensor(759.3834, device='cuda:0')
episode: 587 training return: tensor(747.7433, device='cuda:0')
epoch: 147 test_true_pfm: 48.46345510914993 sim_pfm: 791.9105888044927
episode: 588 training return: tensor(746.4484, device='cuda:0')
episode: 589 training return: tensor(755.6482, device='cuda:0')
episode: 590 training return: tensor(755.9225, device='cuda:0')
episode: 591 training return: tensor(758.4797, device='cuda:0')
epoch: 148 test_true_pfm: 50.73727786518982 sim_pfm: 801.7756558455527
episode: 592 training return: tensor(769.0872, device='cuda:0')
episode: 593 training return: tensor(759.5297, device='cuda:0')
episode: 594 training return: tensor(759.2167, device='cuda:0')
episode: 595 training return: tensor(753.3015, device='cuda:0')
epoch: 149 test_true_pfm: 43.92603132401325 sim_pfm: 779.1090216158889
episode: 596 training return: tensor(756.6562, device='cuda:0')
episode: 597 training return: tensor(759.3696, device='cuda:0')
episode: 598 training return: tensor(749.8746, device='cuda:0')
episode: 599 training return: tensor(761.7715, device='cuda:0')
epoch: 150 test_true_pfm: 43.771988102173125 sim_pfm: 786.0077306445688
