['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '3']
episode: 0 training return: tensor(-245.0282, device='cuda:0')
episode: 1 training return: tensor(-301.5652, device='cuda:0')
episode: 2 training return: tensor(-237.5035, device='cuda:0')
episode: 3 training return: tensor(-296.9076, device='cuda:0')
epoch: 1 test_true_pfm: 30.84818149110156 sim_pfm: -86.26299218627973
episode: 4 training return: tensor(-292.7900, device='cuda:0')
episode: 5 training return: tensor(-157.2558, device='cuda:0')
episode: 6 training return: tensor(-267.4628, device='cuda:0')
episode: 7 training return: tensor(-338.6018, device='cuda:0')
epoch: 2 test_true_pfm: 39.61209457618255 sim_pfm: -26.35145331995445
episode: 8 training return: tensor(-192.4153, device='cuda:0')
episode: 9 training return: tensor(-88.9734, device='cuda:0')
episode: 10 training return: tensor(-398.3688, device='cuda:0')
episode: 11 training return: tensor(99.6762, device='cuda:0')
epoch: 3 test_true_pfm: -14.535983800871827 sim_pfm: 90.13452008378226
episode: 12 training return: tensor(-171.7213, device='cuda:0')
episode: 13 training return: tensor(-242.0302, device='cuda:0')
episode: 14 training return: tensor(-52.3614, device='cuda:0')
episode: 15 training return: tensor(131.5379, device='cuda:0')
epoch: 4 test_true_pfm: 12.379018904080517 sim_pfm: 219.47920133867882
episode: 16 training return: tensor(246.7527, device='cuda:0')
episode: 17 training return: tensor(287.5881, device='cuda:0')
episode: 18 training return: tensor(190.6134, device='cuda:0')
episode: 19 training return: tensor(116.3350, device='cuda:0')
epoch: 5 test_true_pfm: 28.256019091002088 sim_pfm: -79.54823987449636
episode: 20 training return: tensor(79.0476, device='cuda:0')
episode: 21 training return: tensor(-178.3036, device='cuda:0')
episode: 22 training return: tensor(-153.4773, device='cuda:0')
episode: 23 training return: tensor(4.5266, device='cuda:0')
epoch: 6 test_true_pfm: 17.952979739229065 sim_pfm: -138.73962424211203
episode: 24 training return: tensor(-198.9835, device='cuda:0')
episode: 25 training return: tensor(-101.8778, device='cuda:0')
episode: 26 training return: tensor(0.4489, device='cuda:0')
episode: 27 training return: tensor(-136.6102, device='cuda:0')
epoch: 7 test_true_pfm: 0.0018117236624625832 sim_pfm: -213.57224490595982
episode: 28 training return: tensor(16.0142, device='cuda:0')
episode: 29 training return: tensor(250.6781, device='cuda:0')
episode: 30 training return: tensor(260.6304, device='cuda:0')
episode: 31 training return: tensor(-180.6161, device='cuda:0')
epoch: 8 test_true_pfm: -5.8315406451546234 sim_pfm: 193.3922761018097
episode: 32 training return: tensor(193.0435, device='cuda:0')
episode: 33 training return: tensor(252.8362, device='cuda:0')
episode: 34 training return: tensor(-209.2458, device='cuda:0')
episode: 35 training return: tensor(-115.6009, device='cuda:0')
epoch: 9 test_true_pfm: 39.09360944821137 sim_pfm: -287.8662171771633
episode: 36 training return: tensor(-81.6736, device='cuda:0')
episode: 37 training return: tensor(102.3994, device='cuda:0')
episode: 38 training return: tensor(-14.0911, device='cuda:0')
episode: 39 training return: tensor(-62.8813, device='cuda:0')
epoch: 10 test_true_pfm: 47.86685944921301 sim_pfm: 50.967782011005326
episode: 40 training return: tensor(199.5981, device='cuda:0')
episode: 41 training return: tensor(-120.4210, device='cuda:0')
episode: 42 training return: tensor(20.0921, device='cuda:0')
episode: 43 training return: tensor(249.8053, device='cuda:0')
epoch: 11 test_true_pfm: 55.65345140593886 sim_pfm: 63.48829948897473
episode: 44 training return: tensor(61.2161, device='cuda:0')
episode: 45 training return: tensor(90.3281, device='cuda:0')
episode: 46 training return: tensor(-89.4745, device='cuda:0')
episode: 47 training return: tensor(251.6932, device='cuda:0')
epoch: 12 test_true_pfm: 71.35852502054824 sim_pfm: 313.760742523754
episode: 48 training return: tensor(364.8661, device='cuda:0')
episode: 49 training return: tensor(351.6672, device='cuda:0')
episode: 50 training return: tensor(372.9794, device='cuda:0')
episode: 51 training return: tensor(275.7774, device='cuda:0')
epoch: 13 test_true_pfm: 8.236976087696231 sim_pfm: 222.18689507422968
episode: 52 training return: tensor(21.0438, device='cuda:0')
episode: 53 training return: tensor(4.5611, device='cuda:0')
episode: 54 training return: tensor(92.7662, device='cuda:0')
episode: 55 training return: tensor(-144.7950, device='cuda:0')
epoch: 14 test_true_pfm: 37.49338540131025 sim_pfm: 36.34411885450245
episode: 56 training return: tensor(63.6452, device='cuda:0')
episode: 57 training return: tensor(396.5757, device='cuda:0')
episode: 58 training return: tensor(419.3574, device='cuda:0')
episode: 59 training return: tensor(435.0262, device='cuda:0')
epoch: 15 test_true_pfm: 7.061864020777916 sim_pfm: 238.40246598667
episode: 60 training return: tensor(292.7390, device='cuda:0')
episode: 61 training return: tensor(398.8316, device='cuda:0')
episode: 62 training return: tensor(414.3632, device='cuda:0')
episode: 63 training return: tensor(346.0258, device='cuda:0')
epoch: 16 test_true_pfm: 43.2249194858159 sim_pfm: 469.71126821730866
episode: 64 training return: tensor(438.8277, device='cuda:0')
episode: 65 training return: tensor(412.6505, device='cuda:0')
episode: 66 training return: tensor(408.1371, device='cuda:0')
episode: 67 training return: tensor(498.7389, device='cuda:0')
epoch: 17 test_true_pfm: 44.96517174591612 sim_pfm: 333.226532670809
episode: 68 training return: tensor(553.7914, device='cuda:0')
episode: 69 training return: tensor(601.7775, device='cuda:0')
episode: 70 training return: tensor(219.7825, device='cuda:0')
episode: 71 training return: tensor(394.8342, device='cuda:0')
epoch: 18 test_true_pfm: 41.59576953678238 sim_pfm: 552.6106778961606
episode: 72 training return: tensor(486.6449, device='cuda:0')
episode: 73 training return: tensor(564.1622, device='cuda:0')
episode: 74 training return: tensor(606.2676, device='cuda:0')
episode: 75 training return: tensor(530.7596, device='cuda:0')
epoch: 19 test_true_pfm: 61.41813080953714 sim_pfm: 568.2299016852397
episode: 76 training return: tensor(506.9175, device='cuda:0')
episode: 77 training return: tensor(524.4459, device='cuda:0')
episode: 78 training return: tensor(623.6866, device='cuda:0')
episode: 79 training return: tensor(506.2787, device='cuda:0')
epoch: 20 test_true_pfm: 63.34763793467022 sim_pfm: 505.2481686027953
episode: 80 training return: tensor(461.2432, device='cuda:0')
episode: 81 training return: tensor(557.9871, device='cuda:0')
episode: 82 training return: tensor(583.3959, device='cuda:0')
episode: 83 training return: tensor(495.1371, device='cuda:0')
epoch: 21 test_true_pfm: 50.2698057482464 sim_pfm: 548.7685061110649
episode: 84 training return: tensor(495.0767, device='cuda:0')
episode: 85 training return: tensor(644.7734, device='cuda:0')
episode: 86 training return: tensor(630.2432, device='cuda:0')
episode: 87 training return: tensor(648.9568, device='cuda:0')
epoch: 22 test_true_pfm: 43.535236152809226 sim_pfm: 595.3902782024816
episode: 88 training return: tensor(679.3795, device='cuda:0')
episode: 89 training return: tensor(626.2657, device='cuda:0')
episode: 90 training return: tensor(664.3305, device='cuda:0')
episode: 91 training return: tensor(631.3633, device='cuda:0')
epoch: 23 test_true_pfm: 44.42152588164383 sim_pfm: 689.929542256333
episode: 92 training return: tensor(662.5089, device='cuda:0')
episode: 93 training return: tensor(705.3728, device='cuda:0')
episode: 94 training return: tensor(686.2100, device='cuda:0')
episode: 95 training return: tensor(693.0212, device='cuda:0')
epoch: 24 test_true_pfm: 34.551247273818376 sim_pfm: 721.057325184159
episode: 96 training return: tensor(605.7216, device='cuda:0')
episode: 97 training return: tensor(491.9817, device='cuda:0')
episode: 98 training return: tensor(633.3630, device='cuda:0')
episode: 99 training return: tensor(617.6562, device='cuda:0')
epoch: 25 test_true_pfm: 43.65795222552677 sim_pfm: 634.873979816772
episode: 100 training return: tensor(626.7536, device='cuda:0')
episode: 101 training return: tensor(508.8169, device='cuda:0')
episode: 102 training return: tensor(670.9379, device='cuda:0')
episode: 103 training return: tensor(655.1361, device='cuda:0')
epoch: 26 test_true_pfm: 55.45612017567798 sim_pfm: 721.1116643577814
episode: 104 training return: tensor(689.2976, device='cuda:0')
episode: 105 training return: tensor(674.1143, device='cuda:0')
episode: 106 training return: tensor(698.2526, device='cuda:0')
episode: 107 training return: tensor(661.1397, device='cuda:0')
epoch: 27 test_true_pfm: 51.18515067338966 sim_pfm: 742.1703647341113
episode: 108 training return: tensor(625.2445, device='cuda:0')
episode: 109 training return: tensor(704.1503, device='cuda:0')
episode: 110 training return: tensor(691.9686, device='cuda:0')
episode: 111 training return: tensor(669.2369, device='cuda:0')
epoch: 28 test_true_pfm: 50.2393684596122 sim_pfm: 694.064422834164
episode: 112 training return: tensor(656.2383, device='cuda:0')
episode: 113 training return: tensor(688.4401, device='cuda:0')
episode: 114 training return: tensor(685.9375, device='cuda:0')
episode: 115 training return: tensor(705.9207, device='cuda:0')
epoch: 29 test_true_pfm: 46.14982348780431 sim_pfm: 684.4081838748883
episode: 116 training return: tensor(697.0407, device='cuda:0')
episode: 117 training return: tensor(666.7908, device='cuda:0')
episode: 118 training return: tensor(715.0669, device='cuda:0')
episode: 119 training return: tensor(721.6219, device='cuda:0')
epoch: 30 test_true_pfm: 47.761540365909866 sim_pfm: 727.3730681869667
episode: 120 training return: tensor(632.6436, device='cuda:0')
episode: 121 training return: tensor(653.7766, device='cuda:0')
episode: 122 training return: tensor(661.9289, device='cuda:0')
episode: 123 training return: tensor(726.2062, device='cuda:0')
epoch: 31 test_true_pfm: 40.459744287129 sim_pfm: 671.3370718738064
episode: 124 training return: tensor(699.6300, device='cuda:0')
episode: 125 training return: tensor(721.3700, device='cuda:0')
episode: 126 training return: tensor(729.2863, device='cuda:0')
episode: 127 training return: tensor(731.9714, device='cuda:0')
epoch: 32 test_true_pfm: 47.70722417586164 sim_pfm: 740.2608123542741
episode: 128 training return: tensor(738.1050, device='cuda:0')
episode: 129 training return: tensor(722.0688, device='cuda:0')
episode: 130 training return: tensor(732.5861, device='cuda:0')
episode: 131 training return: tensor(718.2844, device='cuda:0')
epoch: 33 test_true_pfm: 48.40279070321249 sim_pfm: 737.6240143059753
episode: 132 training return: tensor(668.4182, device='cuda:0')
episode: 133 training return: tensor(706.2244, device='cuda:0')
episode: 134 training return: tensor(647.4448, device='cuda:0')
episode: 135 training return: tensor(717.8081, device='cuda:0')
epoch: 34 test_true_pfm: 44.44271515197138 sim_pfm: 710.6461022534407
episode: 136 training return: tensor(698.4951, device='cuda:0')
episode: 137 training return: tensor(732.5057, device='cuda:0')
episode: 138 training return: tensor(728.7228, device='cuda:0')
episode: 139 training return: tensor(734.4969, device='cuda:0')
epoch: 35 test_true_pfm: 42.06188013637203 sim_pfm: 694.1338239339123
episode: 140 training return: tensor(706.7716, device='cuda:0')
episode: 141 training return: tensor(735.7332, device='cuda:0')
episode: 142 training return: tensor(707.9708, device='cuda:0')
episode: 143 training return: tensor(748.8416, device='cuda:0')
epoch: 36 test_true_pfm: 40.0080257541014 sim_pfm: 758.8348519836552
episode: 144 training return: tensor(734.5257, device='cuda:0')
episode: 145 training return: tensor(720.8381, device='cuda:0')
episode: 146 training return: tensor(729.7326, device='cuda:0')
episode: 147 training return: tensor(748.6724, device='cuda:0')
epoch: 37 test_true_pfm: 45.29188049037611 sim_pfm: 785.8848612649366
episode: 148 training return: tensor(783.8308, device='cuda:0')
episode: 149 training return: tensor(757.1281, device='cuda:0')
episode: 150 training return: tensor(800.7625, device='cuda:0')
episode: 151 training return: tensor(770.9360, device='cuda:0')
epoch: 38 test_true_pfm: 43.05522469108503 sim_pfm: 796.3231321880012
episode: 152 training return: tensor(776.0833, device='cuda:0')
episode: 153 training return: tensor(743.4210, device='cuda:0')
episode: 154 training return: tensor(781.9002, device='cuda:0')
episode: 155 training return: tensor(757.6214, device='cuda:0')
epoch: 39 test_true_pfm: 50.14841731058347 sim_pfm: 789.6781946394592
episode: 156 training return: tensor(761.0566, device='cuda:0')
episode: 157 training return: tensor(693.1396, device='cuda:0')
episode: 158 training return: tensor(759.8237, device='cuda:0')
episode: 159 training return: tensor(767.4487, device='cuda:0')
epoch: 40 test_true_pfm: 45.113928782019585 sim_pfm: 772.5759989324957
episode: 160 training return: tensor(744.4762, device='cuda:0')
episode: 161 training return: tensor(734.6011, device='cuda:0')
episode: 162 training return: tensor(717.0779, device='cuda:0')
episode: 163 training return: tensor(774.5870, device='cuda:0')
epoch: 41 test_true_pfm: 42.19366148437964 sim_pfm: 798.8565783258528
episode: 164 training return: tensor(775.2292, device='cuda:0')
episode: 165 training return: tensor(765.7163, device='cuda:0')
episode: 166 training return: tensor(776.8309, device='cuda:0')
episode: 167 training return: tensor(768.5227, device='cuda:0')
epoch: 42 test_true_pfm: 44.36121867125705 sim_pfm: 817.0207855059765
episode: 168 training return: tensor(761.1019, device='cuda:0')
episode: 169 training return: tensor(770.7155, device='cuda:0')
episode: 170 training return: tensor(766.1716, device='cuda:0')
episode: 171 training return: tensor(765.7278, device='cuda:0')
epoch: 43 test_true_pfm: 45.693950391189254 sim_pfm: 787.0156410189345
episode: 172 training return: tensor(767.1009, device='cuda:0')
episode: 173 training return: tensor(775.6755, device='cuda:0')
episode: 174 training return: tensor(745.1186, device='cuda:0')
episode: 175 training return: tensor(787.7112, device='cuda:0')
epoch: 44 test_true_pfm: 44.17797276160029 sim_pfm: 786.9864752601832
episode: 176 training return: tensor(763.1204, device='cuda:0')
episode: 177 training return: tensor(783.1509, device='cuda:0')
episode: 178 training return: tensor(776.0852, device='cuda:0')
episode: 179 training return: tensor(783.3049, device='cuda:0')
epoch: 45 test_true_pfm: 52.86101088638967 sim_pfm: 819.9836328474805
episode: 180 training return: tensor(781.1253, device='cuda:0')
episode: 181 training return: tensor(758.4710, device='cuda:0')
episode: 182 training return: tensor(773.7206, device='cuda:0')
episode: 183 training return: tensor(775.2747, device='cuda:0')
epoch: 46 test_true_pfm: 47.73084101933296 sim_pfm: 768.2378780441359
episode: 184 training return: tensor(775.5593, device='cuda:0')
episode: 185 training return: tensor(772.4603, device='cuda:0')
episode: 186 training return: tensor(788.6602, device='cuda:0')
episode: 187 training return: tensor(805.1125, device='cuda:0')
epoch: 47 test_true_pfm: 51.08630128799953 sim_pfm: 804.6936497037765
episode: 188 training return: tensor(782.2255, device='cuda:0')
episode: 189 training return: tensor(783.7385, device='cuda:0')
episode: 190 training return: tensor(773.2991, device='cuda:0')
episode: 191 training return: tensor(776.8307, device='cuda:0')
epoch: 48 test_true_pfm: 54.20756861363232 sim_pfm: 821.8347637933679
episode: 192 training return: tensor(782.4805, device='cuda:0')
episode: 193 training return: tensor(776.6586, device='cuda:0')
episode: 194 training return: tensor(769.3744, device='cuda:0')
episode: 195 training return: tensor(790.1492, device='cuda:0')
epoch: 49 test_true_pfm: 48.79657698693477 sim_pfm: 789.6329662398435
episode: 196 training return: tensor(760.6141, device='cuda:0')
episode: 197 training return: tensor(787.8252, device='cuda:0')
episode: 198 training return: tensor(781.1238, device='cuda:0')
episode: 199 training return: tensor(789.9106, device='cuda:0')
epoch: 50 test_true_pfm: 42.962726372440656 sim_pfm: 821.5854083502315
episode: 200 training return: tensor(761.4536, device='cuda:0')
episode: 201 training return: tensor(780.7294, device='cuda:0')
episode: 202 training return: tensor(770.3785, device='cuda:0')
episode: 203 training return: tensor(781.0354, device='cuda:0')
epoch: 51 test_true_pfm: 43.4079899913715 sim_pfm: 820.5470143532381
episode: 204 training return: tensor(775.7556, device='cuda:0')
episode: 205 training return: tensor(795.1633, device='cuda:0')
episode: 206 training return: tensor(776.0867, device='cuda:0')
episode: 207 training return: tensor(794.3967, device='cuda:0')
epoch: 52 test_true_pfm: 48.84728429853071 sim_pfm: 831.5252660365775
episode: 208 training return: tensor(795.8394, device='cuda:0')
episode: 209 training return: tensor(796.1884, device='cuda:0')
episode: 210 training return: tensor(790.2060, device='cuda:0')
episode: 211 training return: tensor(756.7542, device='cuda:0')
epoch: 53 test_true_pfm: 47.477630922335074 sim_pfm: 842.2325255163014
episode: 212 training return: tensor(796.2343, device='cuda:0')
episode: 213 training return: tensor(729.9073, device='cuda:0')
episode: 214 training return: tensor(790.0976, device='cuda:0')
episode: 215 training return: tensor(790.5535, device='cuda:0')
epoch: 54 test_true_pfm: 50.45445785795219 sim_pfm: 819.9995463654399
episode: 216 training return: tensor(772.9717, device='cuda:0')
episode: 217 training return: tensor(794.1589, device='cuda:0')
episode: 218 training return: tensor(804.8114, device='cuda:0')
episode: 219 training return: tensor(807.4625, device='cuda:0')
epoch: 55 test_true_pfm: 45.025625926826365 sim_pfm: 834.3680947118439
episode: 220 training return: tensor(786.2069, device='cuda:0')
episode: 221 training return: tensor(803.6696, device='cuda:0')
episode: 222 training return: tensor(775.3005, device='cuda:0')
episode: 223 training return: tensor(783.0581, device='cuda:0')
epoch: 56 test_true_pfm: 42.43969465807184 sim_pfm: 816.3145482387393
episode: 224 training return: tensor(753.1022, device='cuda:0')
episode: 225 training return: tensor(754.8611, device='cuda:0')
episode: 226 training return: tensor(757.2684, device='cuda:0')
episode: 227 training return: tensor(739.3165, device='cuda:0')
epoch: 57 test_true_pfm: 43.280556330867505 sim_pfm: 808.8197160867974
episode: 228 training return: tensor(782.1259, device='cuda:0')
episode: 229 training return: tensor(784.8595, device='cuda:0')
episode: 230 training return: tensor(788.0639, device='cuda:0')
episode: 231 training return: tensor(782.0448, device='cuda:0')
epoch: 58 test_true_pfm: 42.51848804299374 sim_pfm: 835.981523459591
episode: 232 training return: tensor(780.5931, device='cuda:0')
episode: 233 training return: tensor(788.9084, device='cuda:0')
episode: 234 training return: tensor(795.2460, device='cuda:0')
episode: 235 training return: tensor(781.4227, device='cuda:0')
epoch: 59 test_true_pfm: 42.808039359810564 sim_pfm: 834.4115476605482
episode: 236 training return: tensor(796.3405, device='cuda:0')
episode: 237 training return: tensor(798.8406, device='cuda:0')
episode: 238 training return: tensor(770.5760, device='cuda:0')
episode: 239 training return: tensor(798.6394, device='cuda:0')
epoch: 60 test_true_pfm: 43.64524259701962 sim_pfm: 841.1876357071102
episode: 240 training return: tensor(813.3895, device='cuda:0')
episode: 241 training return: tensor(814.5516, device='cuda:0')
episode: 242 training return: tensor(804.1534, device='cuda:0')
episode: 243 training return: tensor(789.4266, device='cuda:0')
epoch: 61 test_true_pfm: 43.9248064808981 sim_pfm: 839.2041832985357
episode: 244 training return: tensor(787.3085, device='cuda:0')
episode: 245 training return: tensor(786.3482, device='cuda:0')
episode: 246 training return: tensor(803.9543, device='cuda:0')
episode: 247 training return: tensor(775.6750, device='cuda:0')
epoch: 62 test_true_pfm: 39.503343619005406 sim_pfm: 825.3963005182799
episode: 248 training return: tensor(787.7482, device='cuda:0')
episode: 249 training return: tensor(780.7399, device='cuda:0')
episode: 250 training return: tensor(800.1989, device='cuda:0')
episode: 251 training return: tensor(785.0953, device='cuda:0')
epoch: 63 test_true_pfm: 33.21699922913763 sim_pfm: 808.8570338442921
episode: 252 training return: tensor(785.2692, device='cuda:0')
episode: 253 training return: tensor(749.5759, device='cuda:0')
episode: 254 training return: tensor(783.6573, device='cuda:0')
episode: 255 training return: tensor(772.5692, device='cuda:0')
epoch: 64 test_true_pfm: 41.478305673661595 sim_pfm: 789.0940062159556
episode: 256 training return: tensor(791.3589, device='cuda:0')
episode: 257 training return: tensor(793.6595, device='cuda:0')
episode: 258 training return: tensor(777.8680, device='cuda:0')
episode: 259 training return: tensor(789.8324, device='cuda:0')
epoch: 65 test_true_pfm: 37.816021380508076 sim_pfm: 838.7156493063085
episode: 260 training return: tensor(792.1486, device='cuda:0')
episode: 261 training return: tensor(767.6627, device='cuda:0')
episode: 262 training return: tensor(799.5411, device='cuda:0')
episode: 263 training return: tensor(803.7410, device='cuda:0')
epoch: 66 test_true_pfm: 37.728868785385494 sim_pfm: 838.0380453139544
episode: 264 training return: tensor(798.9670, device='cuda:0')
episode: 265 training return: tensor(801.7691, device='cuda:0')
episode: 266 training return: tensor(777.3030, device='cuda:0')
episode: 267 training return: tensor(804.2106, device='cuda:0')
epoch: 67 test_true_pfm: 47.60556997278742 sim_pfm: 844.5535513326992
episode: 268 training return: tensor(798.4705, device='cuda:0')
episode: 269 training return: tensor(805.7452, device='cuda:0')
episode: 270 training return: tensor(820.0898, device='cuda:0')
episode: 271 training return: tensor(811.6014, device='cuda:0')
epoch: 68 test_true_pfm: 43.70551977744135 sim_pfm: 841.3385314081097
episode: 272 training return: tensor(801.5518, device='cuda:0')
episode: 273 training return: tensor(787.1480, device='cuda:0')
episode: 274 training return: tensor(800.6427, device='cuda:0')
episode: 275 training return: tensor(795.5613, device='cuda:0')
epoch: 69 test_true_pfm: 39.279392575931816 sim_pfm: 829.3005248204339
episode: 276 training return: tensor(791.5557, device='cuda:0')
episode: 277 training return: tensor(794.0620, device='cuda:0')
episode: 278 training return: tensor(792.5700, device='cuda:0')
episode: 279 training return: tensor(770.4512, device='cuda:0')
epoch: 70 test_true_pfm: 37.46095073194559 sim_pfm: 845.6140733941924
episode: 280 training return: tensor(743.8607, device='cuda:0')
episode: 281 training return: tensor(781.0404, device='cuda:0')
episode: 282 training return: tensor(793.0115, device='cuda:0')
episode: 283 training return: tensor(769.7230, device='cuda:0')
epoch: 71 test_true_pfm: 42.05998479244493 sim_pfm: 809.7260508686304
episode: 284 training return: tensor(776.3814, device='cuda:0')
episode: 285 training return: tensor(800.1009, device='cuda:0')
episode: 286 training return: tensor(800.6526, device='cuda:0')
episode: 287 training return: tensor(798.9250, device='cuda:0')
epoch: 72 test_true_pfm: 44.222403240845 sim_pfm: 815.9608440903946
episode: 288 training return: tensor(775.8214, device='cuda:0')
episode: 289 training return: tensor(801.8339, device='cuda:0')
episode: 290 training return: tensor(788.1534, device='cuda:0')
episode: 291 training return: tensor(779.8933, device='cuda:0')
epoch: 73 test_true_pfm: 39.7709516342047 sim_pfm: 793.5789787017741
episode: 292 training return: tensor(743.3870, device='cuda:0')
episode: 293 training return: tensor(776.1294, device='cuda:0')
episode: 294 training return: tensor(777.6830, device='cuda:0')
episode: 295 training return: tensor(793.9367, device='cuda:0')
epoch: 74 test_true_pfm: 39.21854101764418 sim_pfm: 838.3420716201887
episode: 296 training return: tensor(781.3403, device='cuda:0')
episode: 297 training return: tensor(791.5085, device='cuda:0')
episode: 298 training return: tensor(809.6934, device='cuda:0')
episode: 299 training return: tensor(814.6204, device='cuda:0')
epoch: 75 test_true_pfm: 41.84300641667117 sim_pfm: 844.9711979432032
episode: 300 training return: tensor(787.1646, device='cuda:0')
episode: 301 training return: tensor(811.5067, device='cuda:0')
episode: 302 training return: tensor(811.1834, device='cuda:0')
episode: 303 training return: tensor(814.0389, device='cuda:0')
epoch: 76 test_true_pfm: 44.542846779250354 sim_pfm: 823.4564790337812
episode: 304 training return: tensor(817.6628, device='cuda:0')
episode: 305 training return: tensor(796.0361, device='cuda:0')
episode: 306 training return: tensor(814.9017, device='cuda:0')
episode: 307 training return: tensor(792.8810, device='cuda:0')
epoch: 77 test_true_pfm: 43.1837417854777 sim_pfm: 841.2522628366947
episode: 308 training return: tensor(805.3259, device='cuda:0')
episode: 309 training return: tensor(789.1833, device='cuda:0')
episode: 310 training return: tensor(784.0745, device='cuda:0')
episode: 311 training return: tensor(811.5031, device='cuda:0')
epoch: 78 test_true_pfm: 42.89322013478975 sim_pfm: 818.572084598802
episode: 312 training return: tensor(803.9478, device='cuda:0')
episode: 313 training return: tensor(798.9341, device='cuda:0')
episode: 314 training return: tensor(800.8925, device='cuda:0')
episode: 315 training return: tensor(798.6707, device='cuda:0')
epoch: 79 test_true_pfm: 33.80467694069184 sim_pfm: 850.8646959919482
episode: 316 training return: tensor(809.0271, device='cuda:0')
episode: 317 training return: tensor(816.4287, device='cuda:0')
episode: 318 training return: tensor(798.9884, device='cuda:0')
episode: 319 training return: tensor(791.6273, device='cuda:0')
epoch: 80 test_true_pfm: 39.04953637924308 sim_pfm: 849.5487759326585
episode: 320 training return: tensor(808.6913, device='cuda:0')
episode: 321 training return: tensor(799.0191, device='cuda:0')
episode: 322 training return: tensor(814.8729, device='cuda:0')
episode: 323 training return: tensor(813.5082, device='cuda:0')
epoch: 81 test_true_pfm: 41.09164956902271 sim_pfm: 817.8271882825647
episode: 324 training return: tensor(810.1570, device='cuda:0')
episode: 325 training return: tensor(800.7355, device='cuda:0')
episode: 326 training return: tensor(806.6837, device='cuda:0')
episode: 327 training return: tensor(809.4639, device='cuda:0')
epoch: 82 test_true_pfm: 43.34094802229182 sim_pfm: 844.5892662076745
episode: 328 training return: tensor(779.1182, device='cuda:0')
episode: 329 training return: tensor(785.3978, device='cuda:0')
episode: 330 training return: tensor(806.5555, device='cuda:0')
episode: 331 training return: tensor(786.9964, device='cuda:0')
epoch: 83 test_true_pfm: 37.794500601376726 sim_pfm: 807.5439179200679
episode: 332 training return: tensor(768.9485, device='cuda:0')
episode: 333 training return: tensor(789.1765, device='cuda:0')
episode: 334 training return: tensor(775.5651, device='cuda:0')
episode: 335 training return: tensor(790.8589, device='cuda:0')
epoch: 84 test_true_pfm: 39.97091954867578 sim_pfm: 802.3417712666094
episode: 336 training return: tensor(774.6668, device='cuda:0')
episode: 337 training return: tensor(795.7449, device='cuda:0')
episode: 338 training return: tensor(807.1836, device='cuda:0')
episode: 339 training return: tensor(820.5556, device='cuda:0')
epoch: 85 test_true_pfm: 52.021724401229484 sim_pfm: 840.3192870514933
episode: 340 training return: tensor(815.2261, device='cuda:0')
episode: 341 training return: tensor(799.4580, device='cuda:0')
episode: 342 training return: tensor(806.5952, device='cuda:0')
episode: 343 training return: tensor(797.5090, device='cuda:0')
epoch: 86 test_true_pfm: 40.45561938914534 sim_pfm: 844.1859804291278
episode: 344 training return: tensor(801.2660, device='cuda:0')
episode: 345 training return: tensor(800.4720, device='cuda:0')
episode: 346 training return: tensor(807.0233, device='cuda:0')
episode: 347 training return: tensor(805.2134, device='cuda:0')
epoch: 87 test_true_pfm: 47.61382978858038 sim_pfm: 835.4283449083566
episode: 348 training return: tensor(799.9875, device='cuda:0')
episode: 349 training return: tensor(793.0358, device='cuda:0')
episode: 350 training return: tensor(784.2146, device='cuda:0')
episode: 351 training return: tensor(774.8717, device='cuda:0')
epoch: 88 test_true_pfm: 39.44378469124702 sim_pfm: 848.3631456686184
episode: 352 training return: tensor(820.6379, device='cuda:0')
episode: 353 training return: tensor(800.0294, device='cuda:0')
episode: 354 training return: tensor(814.6148, device='cuda:0')
episode: 355 training return: tensor(826.3215, device='cuda:0')
epoch: 89 test_true_pfm: 33.075759456305775 sim_pfm: 827.574068422243
episode: 356 training return: tensor(805.8281, device='cuda:0')
episode: 357 training return: tensor(811.0611, device='cuda:0')
episode: 358 training return: tensor(791.5912, device='cuda:0')
episode: 359 training return: tensor(790.8588, device='cuda:0')
epoch: 90 test_true_pfm: 38.092242084719224 sim_pfm: 864.5155431604013
episode: 360 training return: tensor(797.1523, device='cuda:0')
episode: 361 training return: tensor(813.3536, device='cuda:0')
episode: 362 training return: tensor(799.5223, device='cuda:0')
episode: 363 training return: tensor(805.6948, device='cuda:0')
epoch: 91 test_true_pfm: 30.54647951817129 sim_pfm: 835.6923543239012
episode: 364 training return: tensor(801.3200, device='cuda:0')
episode: 365 training return: tensor(805.2277, device='cuda:0')
episode: 366 training return: tensor(804.5706, device='cuda:0')
episode: 367 training return: tensor(798.3692, device='cuda:0')
epoch: 92 test_true_pfm: 37.60562770387155 sim_pfm: 847.5437360086478
episode: 368 training return: tensor(793.0494, device='cuda:0')
episode: 369 training return: tensor(824.9279, device='cuda:0')
episode: 370 training return: tensor(798.3350, device='cuda:0')
episode: 371 training return: tensor(808.4117, device='cuda:0')
epoch: 93 test_true_pfm: 42.44723656834049 sim_pfm: 847.1842398818117
episode: 372 training return: tensor(816.8527, device='cuda:0')
episode: 373 training return: tensor(799.3169, device='cuda:0')
episode: 374 training return: tensor(828.5506, device='cuda:0')
episode: 375 training return: tensor(822.1101, device='cuda:0')
epoch: 94 test_true_pfm: 44.88860216156151 sim_pfm: 856.8802490778268
episode: 376 training return: tensor(826.0991, device='cuda:0')
episode: 377 training return: tensor(808.5599, device='cuda:0')
episode: 378 training return: tensor(817.3261, device='cuda:0')
episode: 379 training return: tensor(805.8372, device='cuda:0')
epoch: 95 test_true_pfm: 41.98446216469265 sim_pfm: 853.3051651592134
episode: 380 training return: tensor(809.1500, device='cuda:0')
episode: 381 training return: tensor(800.2928, device='cuda:0')
episode: 382 training return: tensor(798.2384, device='cuda:0')
episode: 383 training return: tensor(811.3362, device='cuda:0')
epoch: 96 test_true_pfm: 37.82702234459099 sim_pfm: 826.6352399989962
episode: 384 training return: tensor(814.7488, device='cuda:0')
episode: 385 training return: tensor(817.8182, device='cuda:0')
episode: 386 training return: tensor(824.2461, device='cuda:0')
episode: 387 training return: tensor(806.3824, device='cuda:0')
epoch: 97 test_true_pfm: 41.15935450181271 sim_pfm: 847.7196960600093
episode: 388 training return: tensor(814.7305, device='cuda:0')
episode: 389 training return: tensor(803.1210, device='cuda:0')
episode: 390 training return: tensor(821.7054, device='cuda:0')
episode: 391 training return: tensor(818.7567, device='cuda:0')
epoch: 98 test_true_pfm: 43.17944865083159 sim_pfm: 845.1869870697149
episode: 392 training return: tensor(803.1434, device='cuda:0')
episode: 393 training return: tensor(817.2691, device='cuda:0')
episode: 394 training return: tensor(805.0511, device='cuda:0')
episode: 395 training return: tensor(817.8110, device='cuda:0')
epoch: 99 test_true_pfm: 34.468601384068776 sim_pfm: 821.1742713261395
episode: 396 training return: tensor(808.0361, device='cuda:0')
episode: 397 training return: tensor(806.9625, device='cuda:0')
episode: 398 training return: tensor(819.4277, device='cuda:0')
episode: 399 training return: tensor(826.6502, device='cuda:0')
epoch: 100 test_true_pfm: 36.566166019047685 sim_pfm: 848.0590215066447
episode: 400 training return: tensor(811.9850, device='cuda:0')
episode: 401 training return: tensor(820.3659, device='cuda:0')
episode: 402 training return: tensor(816.9984, device='cuda:0')
episode: 403 training return: tensor(827.2947, device='cuda:0')
epoch: 101 test_true_pfm: 34.77070795176214 sim_pfm: 830.4273332372308
episode: 404 training return: tensor(823.5592, device='cuda:0')
episode: 405 training return: tensor(788.1693, device='cuda:0')
episode: 406 training return: tensor(819.3819, device='cuda:0')
episode: 407 training return: tensor(805.4061, device='cuda:0')
epoch: 102 test_true_pfm: 40.67261729512897 sim_pfm: 826.0119047835469
episode: 408 training return: tensor(810.1939, device='cuda:0')
episode: 409 training return: tensor(810.9195, device='cuda:0')
episode: 410 training return: tensor(797.3834, device='cuda:0')
episode: 411 training return: tensor(796.5010, device='cuda:0')
epoch: 103 test_true_pfm: 39.21299643943055 sim_pfm: 839.264338555932
episode: 412 training return: tensor(805.7015, device='cuda:0')
episode: 413 training return: tensor(806.4218, device='cuda:0')
episode: 414 training return: tensor(820.6396, device='cuda:0')
episode: 415 training return: tensor(816.0029, device='cuda:0')
epoch: 104 test_true_pfm: 44.13844316304848 sim_pfm: 857.6882077363786
episode: 416 training return: tensor(811.3184, device='cuda:0')
episode: 417 training return: tensor(803.6665, device='cuda:0')
episode: 418 training return: tensor(808.9188, device='cuda:0')
episode: 419 training return: tensor(808.5334, device='cuda:0')
epoch: 105 test_true_pfm: 46.197010294800165 sim_pfm: 843.1810368776321
episode: 420 training return: tensor(811.3621, device='cuda:0')
episode: 421 training return: tensor(790.9279, device='cuda:0')
episode: 422 training return: tensor(807.1399, device='cuda:0')
episode: 423 training return: tensor(809.1868, device='cuda:0')
epoch: 106 test_true_pfm: 35.15752012110506 sim_pfm: 800.3176019325853
episode: 424 training return: tensor(752.1122, device='cuda:0')
episode: 425 training return: tensor(774.6198, device='cuda:0')
episode: 426 training return: tensor(790.9010, device='cuda:0')
episode: 427 training return: tensor(776.8427, device='cuda:0')
epoch: 107 test_true_pfm: 38.003103528118956 sim_pfm: 808.0346565415151
episode: 428 training return: tensor(777.1384, device='cuda:0')
episode: 429 training return: tensor(784.5637, device='cuda:0')
episode: 430 training return: tensor(792.4594, device='cuda:0')
episode: 431 training return: tensor(813.9915, device='cuda:0')
epoch: 108 test_true_pfm: 44.88400393708215 sim_pfm: 838.9042262325063
episode: 432 training return: tensor(816.7658, device='cuda:0')
episode: 433 training return: tensor(821.8792, device='cuda:0')
episode: 434 training return: tensor(814.5574, device='cuda:0')
episode: 435 training return: tensor(807.3071, device='cuda:0')
epoch: 109 test_true_pfm: 37.295379708794535 sim_pfm: 825.4898916937411
episode: 436 training return: tensor(818.6553, device='cuda:0')
episode: 437 training return: tensor(794.6326, device='cuda:0')
episode: 438 training return: tensor(804.4547, device='cuda:0')
episode: 439 training return: tensor(821.2212, device='cuda:0')
epoch: 110 test_true_pfm: 37.54656870288848 sim_pfm: 835.3359915020177
episode: 440 training return: tensor(812.6165, device='cuda:0')
episode: 441 training return: tensor(812.2231, device='cuda:0')
episode: 442 training return: tensor(810.3470, device='cuda:0')
episode: 443 training return: tensor(816.1702, device='cuda:0')
epoch: 111 test_true_pfm: 38.84636506458261 sim_pfm: 855.6601056316634
episode: 444 training return: tensor(816.7111, device='cuda:0')
episode: 445 training return: tensor(818.0908, device='cuda:0')
episode: 446 training return: tensor(816.0354, device='cuda:0')
episode: 447 training return: tensor(814.0289, device='cuda:0')
epoch: 112 test_true_pfm: 39.53019177311315 sim_pfm: 821.8482905657962
episode: 448 training return: tensor(817.4133, device='cuda:0')
episode: 449 training return: tensor(803.0654, device='cuda:0')
episode: 450 training return: tensor(828.8524, device='cuda:0')
episode: 451 training return: tensor(796.4859, device='cuda:0')
epoch: 113 test_true_pfm: 41.12919898350363 sim_pfm: 840.2531784754246
episode: 452 training return: tensor(804.5415, device='cuda:0')
episode: 453 training return: tensor(813.3317, device='cuda:0')
episode: 454 training return: tensor(804.4000, device='cuda:0')
episode: 455 training return: tensor(821.2783, device='cuda:0')
epoch: 114 test_true_pfm: 38.282173879248035 sim_pfm: 832.3815036121756
episode: 456 training return: tensor(819.2435, device='cuda:0')
episode: 457 training return: tensor(822.3824, device='cuda:0')
episode: 458 training return: tensor(795.6905, device='cuda:0')
episode: 459 training return: tensor(793.2278, device='cuda:0')
epoch: 115 test_true_pfm: 37.13073744621708 sim_pfm: 834.8790548481047
episode: 460 training return: tensor(817.2788, device='cuda:0')
episode: 461 training return: tensor(805.3734, device='cuda:0')
episode: 462 training return: tensor(822.2823, device='cuda:0')
episode: 463 training return: tensor(817.5344, device='cuda:0')
epoch: 116 test_true_pfm: 41.315665231309964 sim_pfm: 850.2561085099354
episode: 464 training return: tensor(783.8405, device='cuda:0')
episode: 465 training return: tensor(804.9315, device='cuda:0')
episode: 466 training return: tensor(780.9070, device='cuda:0')
episode: 467 training return: tensor(804.1488, device='cuda:0')
epoch: 117 test_true_pfm: 40.36587760328622 sim_pfm: 852.5716890934855
episode: 468 training return: tensor(814.7388, device='cuda:0')
episode: 469 training return: tensor(818.2540, device='cuda:0')
episode: 470 training return: tensor(807.7669, device='cuda:0')
episode: 471 training return: tensor(798.0827, device='cuda:0')
epoch: 118 test_true_pfm: 36.92288896053685 sim_pfm: 837.1853950715391
episode: 472 training return: tensor(809.9443, device='cuda:0')
episode: 473 training return: tensor(801.2072, device='cuda:0')
episode: 474 training return: tensor(805.0697, device='cuda:0')
episode: 475 training return: tensor(808.9214, device='cuda:0')
epoch: 119 test_true_pfm: 40.801585577102905 sim_pfm: 837.513973531127
episode: 476 training return: tensor(810.2691, device='cuda:0')
episode: 477 training return: tensor(821.8813, device='cuda:0')
episode: 478 training return: tensor(823.6771, device='cuda:0')
episode: 479 training return: tensor(815.2139, device='cuda:0')
epoch: 120 test_true_pfm: 38.47891790972672 sim_pfm: 827.7371620073915
episode: 480 training return: tensor(793.8835, device='cuda:0')
episode: 481 training return: tensor(835.8349, device='cuda:0')
episode: 482 training return: tensor(820.3041, device='cuda:0')
episode: 483 training return: tensor(825.7681, device='cuda:0')
epoch: 121 test_true_pfm: 36.29927949906168 sim_pfm: 841.7742648679763
episode: 484 training return: tensor(815.0764, device='cuda:0')
episode: 485 training return: tensor(813.2811, device='cuda:0')
episode: 486 training return: tensor(815.4549, device='cuda:0')
episode: 487 training return: tensor(811.7113, device='cuda:0')
epoch: 122 test_true_pfm: 33.94631620565608 sim_pfm: 822.2910848341883
episode: 488 training return: tensor(799.4283, device='cuda:0')
episode: 489 training return: tensor(805.0231, device='cuda:0')
episode: 490 training return: tensor(785.1221, device='cuda:0')
episode: 491 training return: tensor(804.3050, device='cuda:0')
epoch: 123 test_true_pfm: 41.39965824605251 sim_pfm: 851.5520605999976
episode: 492 training return: tensor(809.6576, device='cuda:0')
episode: 493 training return: tensor(823.4256, device='cuda:0')
episode: 494 training return: tensor(821.5455, device='cuda:0')
episode: 495 training return: tensor(811.9059, device='cuda:0')
epoch: 124 test_true_pfm: 42.90884868190671 sim_pfm: 840.5766594807617
episode: 496 training return: tensor(797.7955, device='cuda:0')
episode: 497 training return: tensor(817.2183, device='cuda:0')
episode: 498 training return: tensor(813.0270, device='cuda:0')
episode: 499 training return: tensor(809.3186, device='cuda:0')
epoch: 125 test_true_pfm: 45.90090984308521 sim_pfm: 845.6937785994262
episode: 500 training return: tensor(798.2570, device='cuda:0')
episode: 501 training return: tensor(802.1704, device='cuda:0')
episode: 502 training return: tensor(808.2507, device='cuda:0')
episode: 503 training return: tensor(807.2516, device='cuda:0')
epoch: 126 test_true_pfm: 37.01387530927432 sim_pfm: 847.5139899585396
episode: 504 training return: tensor(807.0310, device='cuda:0')
episode: 505 training return: tensor(800.2210, device='cuda:0')
episode: 506 training return: tensor(816.1660, device='cuda:0')
episode: 507 training return: tensor(825.3763, device='cuda:0')
epoch: 127 test_true_pfm: 39.827978326524835 sim_pfm: 853.403757529892
episode: 508 training return: tensor(810.4171, device='cuda:0')
episode: 509 training return: tensor(791.2028, device='cuda:0')
episode: 510 training return: tensor(802.2311, device='cuda:0')
episode: 511 training return: tensor(798.8947, device='cuda:0')
epoch: 128 test_true_pfm: 34.67797988938643 sim_pfm: 834.221314829588
episode: 512 training return: tensor(801.3300, device='cuda:0')
episode: 513 training return: tensor(815.4469, device='cuda:0')
episode: 514 training return: tensor(816.7733, device='cuda:0')
episode: 515 training return: tensor(805.5817, device='cuda:0')
epoch: 129 test_true_pfm: 34.261006816424256 sim_pfm: 840.7718405833468
episode: 516 training return: tensor(806.7460, device='cuda:0')
episode: 517 training return: tensor(816.3505, device='cuda:0')
episode: 518 training return: tensor(815.8278, device='cuda:0')
episode: 519 training return: tensor(795.8768, device='cuda:0')
epoch: 130 test_true_pfm: 37.881444795749886 sim_pfm: 837.3804027950391
episode: 520 training return: tensor(800.9600, device='cuda:0')
episode: 521 training return: tensor(814.2908, device='cuda:0')
episode: 522 training return: tensor(802.6962, device='cuda:0')
episode: 523 training return: tensor(779.0880, device='cuda:0')
epoch: 131 test_true_pfm: 37.61573686616335 sim_pfm: 833.2391008384526
episode: 524 training return: tensor(794.6639, device='cuda:0')
episode: 525 training return: tensor(800.5945, device='cuda:0')
episode: 526 training return: tensor(814.9021, device='cuda:0')
episode: 527 training return: tensor(804.7432, device='cuda:0')
epoch: 132 test_true_pfm: 39.97811460868402 sim_pfm: 819.3445286210626
episode: 528 training return: tensor(804.2461, device='cuda:0')
episode: 529 training return: tensor(806.4279, device='cuda:0')
episode: 530 training return: tensor(811.8015, device='cuda:0')
episode: 531 training return: tensor(802.7296, device='cuda:0')
epoch: 133 test_true_pfm: 34.98319199735376 sim_pfm: 845.6721239596606
episode: 532 training return: tensor(801.3282, device='cuda:0')
episode: 533 training return: tensor(809.5778, device='cuda:0')
episode: 534 training return: tensor(783.7063, device='cuda:0')
episode: 535 training return: tensor(815.0773, device='cuda:0')
epoch: 134 test_true_pfm: 33.82679469009063 sim_pfm: 839.419657932967
episode: 536 training return: tensor(800.3524, device='cuda:0')
episode: 537 training return: tensor(820.7442, device='cuda:0')
episode: 538 training return: tensor(804.3390, device='cuda:0')
episode: 539 training return: tensor(818.6317, device='cuda:0')
epoch: 135 test_true_pfm: 43.74136285312979 sim_pfm: 859.0609668295831
episode: 540 training return: tensor(806.6042, device='cuda:0')
episode: 541 training return: tensor(806.0839, device='cuda:0')
episode: 542 training return: tensor(798.7704, device='cuda:0')
episode: 543 training return: tensor(810.7341, device='cuda:0')
epoch: 136 test_true_pfm: 39.42069057686943 sim_pfm: 857.1337517071515
episode: 544 training return: tensor(812.3053, device='cuda:0')
episode: 545 training return: tensor(816.6171, device='cuda:0')
episode: 546 training return: tensor(801.5804, device='cuda:0')
episode: 547 training return: tensor(805.8042, device='cuda:0')
epoch: 137 test_true_pfm: 34.84546151358107 sim_pfm: 831.4084745563566
episode: 548 training return: tensor(799.0544, device='cuda:0')
episode: 549 training return: tensor(794.5961, device='cuda:0')
episode: 550 training return: tensor(807.8729, device='cuda:0')
episode: 551 training return: tensor(797.2171, device='cuda:0')
epoch: 138 test_true_pfm: 40.474462832115584 sim_pfm: 849.4678233020007
episode: 552 training return: tensor(805.7742, device='cuda:0')
episode: 553 training return: tensor(792.9304, device='cuda:0')
episode: 554 training return: tensor(794.7679, device='cuda:0')
episode: 555 training return: tensor(791.3542, device='cuda:0')
epoch: 139 test_true_pfm: 32.64412392994692 sim_pfm: 823.4908040598035
episode: 556 training return: tensor(813.4910, device='cuda:0')
episode: 557 training return: tensor(818.2147, device='cuda:0')
episode: 558 training return: tensor(804.8796, device='cuda:0')
episode: 559 training return: tensor(789.5056, device='cuda:0')
epoch: 140 test_true_pfm: 41.377873416705306 sim_pfm: 851.9246327426284
episode: 560 training return: tensor(794.9730, device='cuda:0')
episode: 561 training return: tensor(803.8303, device='cuda:0')
episode: 562 training return: tensor(815.8697, device='cuda:0')
episode: 563 training return: tensor(800.9822, device='cuda:0')
epoch: 141 test_true_pfm: 35.879927636324695 sim_pfm: 845.6849249179475
episode: 564 training return: tensor(815.8724, device='cuda:0')
episode: 565 training return: tensor(796.6114, device='cuda:0')
episode: 566 training return: tensor(781.6155, device='cuda:0')
episode: 567 training return: tensor(800.4021, device='cuda:0')
epoch: 142 test_true_pfm: 42.09203789723669 sim_pfm: 857.3939720469061
episode: 568 training return: tensor(791.7756, device='cuda:0')
episode: 569 training return: tensor(795.3954, device='cuda:0')
episode: 570 training return: tensor(804.4500, device='cuda:0')
episode: 571 training return: tensor(801.2949, device='cuda:0')
epoch: 143 test_true_pfm: 38.82112975700824 sim_pfm: 850.7320531560108
episode: 572 training return: tensor(813.4083, device='cuda:0')
episode: 573 training return: tensor(799.4295, device='cuda:0')
episode: 574 training return: tensor(806.2134, device='cuda:0')
episode: 575 training return: tensor(792.5617, device='cuda:0')
epoch: 144 test_true_pfm: 39.84670683820661 sim_pfm: 853.0916006848216
episode: 576 training return: tensor(793.8466, device='cuda:0')
episode: 577 training return: tensor(795.5969, device='cuda:0')
episode: 578 training return: tensor(809.1668, device='cuda:0')
episode: 579 training return: tensor(811.6909, device='cuda:0')
epoch: 145 test_true_pfm: 42.78553875744971 sim_pfm: 850.4505157287931
episode: 580 training return: tensor(803.3856, device='cuda:0')
episode: 581 training return: tensor(792.3615, device='cuda:0')
episode: 582 training return: tensor(761.6417, device='cuda:0')
episode: 583 training return: tensor(806.5162, device='cuda:0')
epoch: 146 test_true_pfm: 34.73439472216352 sim_pfm: 852.269239918515
episode: 584 training return: tensor(792.7905, device='cuda:0')
episode: 585 training return: tensor(815.2943, device='cuda:0')
episode: 586 training return: tensor(804.8309, device='cuda:0')
episode: 587 training return: tensor(793.5096, device='cuda:0')
epoch: 147 test_true_pfm: 39.14891100990539 sim_pfm: 850.3002250283956
episode: 588 training return: tensor(811.7869, device='cuda:0')
episode: 589 training return: tensor(814.9111, device='cuda:0')
episode: 590 training return: tensor(819.2286, device='cuda:0')
episode: 591 training return: tensor(812.5591, device='cuda:0')
epoch: 148 test_true_pfm: 34.58216510892296 sim_pfm: 847.0568191803992
episode: 592 training return: tensor(812.5837, device='cuda:0')
episode: 593 training return: tensor(800.8531, device='cuda:0')
episode: 594 training return: tensor(791.0176, device='cuda:0')
episode: 595 training return: tensor(818.8698, device='cuda:0')
epoch: 149 test_true_pfm: 39.29834908460956 sim_pfm: 854.650256808009
episode: 596 training return: tensor(795.2314, device='cuda:0')
episode: 597 training return: tensor(800.5756, device='cuda:0')
episode: 598 training return: tensor(806.2791, device='cuda:0')
episode: 599 training return: tensor(808.1255, device='cuda:0')
epoch: 150 test_true_pfm: 44.04162697990958 sim_pfm: 866.4199288293719
