['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '2', '--data', '100000', '--regu', '0.2']
2673.9811423761303
episode: 0 training return: tensor(259.4877, device='cuda:0')
episode: 1 training return: tensor(-260.8772, device='cuda:0')
episode: 2 training return: tensor(279.0141, device='cuda:0')
episode: 3 training return: tensor(185.9861, device='cuda:0')
epoch: 1 test_true_pfm: 2869.8456332518276 sim_pfm: 149.059502944001
episode: 4 training return: tensor(212.0844, device='cuda:0')
episode: 5 training return: tensor(343.6296, device='cuda:0')
episode: 6 training return: tensor(77.1406, device='cuda:0')
episode: 7 training return: tensor(271.3344, device='cuda:0')
epoch: 2 test_true_pfm: 3104.076653076178 sim_pfm: 310.53752755051636
episode: 8 training return: tensor(-179.7406, device='cuda:0')
episode: 9 training return: tensor(190.0670, device='cuda:0')
episode: 10 training return: tensor(171.7999, device='cuda:0')
episode: 11 training return: tensor(342.2165, device='cuda:0')
epoch: 3 test_true_pfm: 3364.923846537984 sim_pfm: 277.0128854853295
episode: 12 training return: tensor(279.2561, device='cuda:0')
episode: 13 training return: tensor(339.4800, device='cuda:0')
episode: 14 training return: tensor(297.9510, device='cuda:0')
episode: 15 training return: tensor(322.6113, device='cuda:0')
epoch: 4 test_true_pfm: 3504.0753917435927 sim_pfm: 180.50350556643875
episode: 16 training return: tensor(223.4754, device='cuda:0')
episode: 17 training return: tensor(321.4528, device='cuda:0')
episode: 18 training return: tensor(266.0873, device='cuda:0')
episode: 19 training return: tensor(267.0948, device='cuda:0')
epoch: 5 test_true_pfm: 3548.04443362908 sim_pfm: 373.6904255543971
episode: 20 training return: tensor(216.1254, device='cuda:0')
episode: 21 training return: tensor(209.8554, device='cuda:0')
episode: 22 training return: tensor(122.8237, device='cuda:0')
episode: 23 training return: tensor(-64.8135, device='cuda:0')
epoch: 6 test_true_pfm: 1436.5484965018766 sim_pfm: -58.79213096255747
episode: 24 training return: tensor(239.9464, device='cuda:0')
episode: 25 training return: tensor(326.5735, device='cuda:0')
episode: 26 training return: tensor(236.6958, device='cuda:0')
episode: 27 training return: tensor(62.2755, device='cuda:0')
epoch: 7 test_true_pfm: 1800.8328863597071 sim_pfm: 58.17198473504201
episode: 28 training return: tensor(325.7289, device='cuda:0')
episode: 29 training return: tensor(-69.1821, device='cuda:0')
episode: 30 training return: tensor(359.0390, device='cuda:0')
episode: 31 training return: tensor(172.4981, device='cuda:0')
epoch: 8 test_true_pfm: 2166.359410745227 sim_pfm: -266.8720003213966
episode: 32 training return: tensor(193.7044, device='cuda:0')
episode: 33 training return: tensor(-112.9775, device='cuda:0')
episode: 34 training return: tensor(350.8092, device='cuda:0')
episode: 35 training return: tensor(339.0017, device='cuda:0')
epoch: 9 test_true_pfm: 2617.043505019745 sim_pfm: 69.0463709286026
episode: 36 training return: tensor(-59.6635, device='cuda:0')
episode: 37 training return: tensor(342.7801, device='cuda:0')
episode: 38 training return: tensor(-35.3024, device='cuda:0')
episode: 39 training return: tensor(358.4615, device='cuda:0')
epoch: 10 test_true_pfm: 3304.0594582299436 sim_pfm: -5.637109630876997
episode: 40 training return: tensor(299.0067, device='cuda:0')
episode: 41 training return: tensor(327.4901, device='cuda:0')
episode: 42 training return: tensor(308.1382, device='cuda:0')
episode: 43 training return: tensor(-130.7568, device='cuda:0')
epoch: 11 test_true_pfm: 2581.77881311368 sim_pfm: 236.2781312702185
episode: 44 training return: tensor(-304.3730, device='cuda:0')
episode: 45 training return: tensor(240.0855, device='cuda:0')
episode: 46 training return: tensor(-140.6758, device='cuda:0')
episode: 47 training return: tensor(-57.7122, device='cuda:0')
epoch: 12 test_true_pfm: 3446.549539253754 sim_pfm: 166.15242158943633
episode: 48 training return: tensor(365.0396, device='cuda:0')
episode: 49 training return: tensor(320.4386, device='cuda:0')
episode: 50 training return: tensor(259.5480, device='cuda:0')
episode: 51 training return: tensor(301.8608, device='cuda:0')
epoch: 13 test_true_pfm: 3293.5042389989962 sim_pfm: 289.59202316743904
episode: 52 training return: tensor(277.9616, device='cuda:0')
episode: 53 training return: tensor(-39.0510, device='cuda:0')
episode: 54 training return: tensor(280.2283, device='cuda:0')
episode: 55 training return: tensor(362.4641, device='cuda:0')
epoch: 14 test_true_pfm: 3452.154843742552 sim_pfm: 177.4419225146024
episode: 56 training return: tensor(277.6224, device='cuda:0')
episode: 57 training return: tensor(344.5229, device='cuda:0')
episode: 58 training return: tensor(190.4430, device='cuda:0')
episode: 59 training return: tensor(-223.9780, device='cuda:0')
epoch: 15 test_true_pfm: 3241.949771172203 sim_pfm: 352.96578326120897
episode: 60 training return: tensor(344.2583, device='cuda:0')
episode: 61 training return: tensor(327.8156, device='cuda:0')
episode: 62 training return: tensor(360.4969, device='cuda:0')
episode: 63 training return: tensor(-47.2668, device='cuda:0')
epoch: 16 test_true_pfm: 3506.459929857768 sim_pfm: 346.4845494675392
episode: 64 training return: tensor(263.2233, device='cuda:0')
episode: 65 training return: tensor(323.3929, device='cuda:0')
episode: 66 training return: tensor(258.0878, device='cuda:0')
episode: 67 training return: tensor(285.2667, device='cuda:0')
epoch: 17 test_true_pfm: 3475.343913767117 sim_pfm: 250.09694920361895
episode: 68 training return: tensor(-50.9679, device='cuda:0')
episode: 69 training return: tensor(235.4513, device='cuda:0')
episode: 70 training return: tensor(274.4105, device='cuda:0')
episode: 71 training return: tensor(274.8398, device='cuda:0')
epoch: 18 test_true_pfm: 3388.337195596267 sim_pfm: 310.78725513467606
episode: 72 training return: tensor(290.7968, device='cuda:0')
episode: 73 training return: tensor(302.8471, device='cuda:0')
episode: 74 training return: tensor(300.8210, device='cuda:0')
episode: 75 training return: tensor(236.8884, device='cuda:0')
epoch: 19 test_true_pfm: 2991.269807719646 sim_pfm: 22.30261083005462
episode: 76 training return: tensor(280.5309, device='cuda:0')
episode: 77 training return: tensor(88.5789, device='cuda:0')
episode: 78 training return: tensor(288.4823, device='cuda:0')
episode: 79 training return: tensor(-45.8238, device='cuda:0')
epoch: 20 test_true_pfm: 2503.6297017480097 sim_pfm: 112.1109454271209
episode: 80 training return: tensor(225.8632, device='cuda:0')
episode: 81 training return: tensor(-36.2939, device='cuda:0')
episode: 82 training return: tensor(253.4034, device='cuda:0')
episode: 83 training return: tensor(-28.3720, device='cuda:0')
epoch: 21 test_true_pfm: 3403.611135810852 sim_pfm: 307.75519192959956
episode: 84 training return: tensor(287.8954, device='cuda:0')
episode: 85 training return: tensor(238.7838, device='cuda:0')
episode: 86 training return: tensor(304.2688, device='cuda:0')
episode: 87 training return: tensor(268.1522, device='cuda:0')
epoch: 22 test_true_pfm: 3397.629273779284 sim_pfm: 306.71368085920886
episode: 88 training return: tensor(478.8260, device='cuda:0')
episode: 89 training return: tensor(128.3923, device='cuda:0')
episode: 90 training return: tensor(289.1658, device='cuda:0')
episode: 91 training return: tensor(-242.7294, device='cuda:0')
epoch: 23 test_true_pfm: 3404.9873487987716 sim_pfm: 211.8016279368118
episode: 92 training return: tensor(288.5148, device='cuda:0')
episode: 93 training return: tensor(291.4655, device='cuda:0')
episode: 94 training return: tensor(118.8391, device='cuda:0')
episode: 95 training return: tensor(330.4387, device='cuda:0')
epoch: 24 test_true_pfm: 2257.851057849784 sim_pfm: 144.7971165915175
episode: 96 training return: tensor(327.3159, device='cuda:0')
episode: 97 training return: tensor(-296.1573, device='cuda:0')
episode: 98 training return: tensor(298.5059, device='cuda:0')
episode: 99 training return: tensor(286.9417, device='cuda:0')
epoch: 25 test_true_pfm: 3397.091966165992 sim_pfm: 325.38196888382663
episode: 100 training return: tensor(340.3610, device='cuda:0')
episode: 101 training return: tensor(298.5816, device='cuda:0')
episode: 102 training return: tensor(-257.9415, device='cuda:0')
episode: 103 training return: tensor(314.8478, device='cuda:0')
epoch: 26 test_true_pfm: 3432.90879225463 sim_pfm: 334.86591121803696
episode: 104 training return: tensor(284.8157, device='cuda:0')
episode: 105 training return: tensor(269.9177, device='cuda:0')
episode: 106 training return: tensor(361.6207, device='cuda:0')
episode: 107 training return: tensor(-105.1115, device='cuda:0')
epoch: 27 test_true_pfm: 3504.553349255759 sim_pfm: 349.78243764068856
episode: 108 training return: tensor(304.9446, device='cuda:0')
episode: 109 training return: tensor(305.9707, device='cuda:0')
episode: 110 training return: tensor(-82.6886, device='cuda:0')
episode: 111 training return: tensor(342.6424, device='cuda:0')
epoch: 28 test_true_pfm: 3529.934523001541 sim_pfm: 379.7174923158115
episode: 112 training return: tensor(310.0866, device='cuda:0')
episode: 113 training return: tensor(360.7710, device='cuda:0')
episode: 114 training return: tensor(325.9561, device='cuda:0')
episode: 115 training return: tensor(404.4797, device='cuda:0')
epoch: 29 test_true_pfm: 3484.465122840608 sim_pfm: 122.953289707298
episode: 116 training return: tensor(292.4188, device='cuda:0')
episode: 117 training return: tensor(300.0544, device='cuda:0')
episode: 118 training return: tensor(298.0192, device='cuda:0')
episode: 119 training return: tensor(-200.4852, device='cuda:0')
epoch: 30 test_true_pfm: 3498.370579977207 sim_pfm: 364.6728330855258
episode: 120 training return: tensor(291.6224, device='cuda:0')
episode: 121 training return: tensor(240.6423, device='cuda:0')
episode: 122 training return: tensor(295.1798, device='cuda:0')
episode: 123 training return: tensor(315.9353, device='cuda:0')
epoch: 31 test_true_pfm: 3399.052862598863 sim_pfm: 321.6165120259587
episode: 124 training return: tensor(325.5762, device='cuda:0')
episode: 125 training return: tensor(271.7290, device='cuda:0')
episode: 126 training return: tensor(342.0022, device='cuda:0')
episode: 127 training return: tensor(347.3459, device='cuda:0')
epoch: 32 test_true_pfm: 3474.8300953917555 sim_pfm: 328.457662556107
episode: 128 training return: tensor(289.7651, device='cuda:0')
episode: 129 training return: tensor(347.8998, device='cuda:0')
episode: 130 training return: tensor(245.2947, device='cuda:0')
episode: 131 training return: tensor(257.5373, device='cuda:0')
epoch: 33 test_true_pfm: 3490.8675082470977 sim_pfm: 340.3510762511287
episode: 132 training return: tensor(294.2105, device='cuda:0')
episode: 133 training return: tensor(311.6833, device='cuda:0')
episode: 134 training return: tensor(181.1487, device='cuda:0')
episode: 135 training return: tensor(356.1164, device='cuda:0')
epoch: 34 test_true_pfm: 3421.0911503446064 sim_pfm: 339.9855182536606
episode: 136 training return: tensor(358.6531, device='cuda:0')
episode: 137 training return: tensor(312.5568, device='cuda:0')
episode: 138 training return: tensor(346.3234, device='cuda:0')
episode: 139 training return: tensor(330.3268, device='cuda:0')
epoch: 35 test_true_pfm: 3479.6740851829636 sim_pfm: 354.03551568343147
episode: 140 training return: tensor(329.4808, device='cuda:0')
episode: 141 training return: tensor(311.4215, device='cuda:0')
episode: 142 training return: tensor(316.1552, device='cuda:0')
episode: 143 training return: tensor(-155.7525, device='cuda:0')
epoch: 36 test_true_pfm: 3515.090632305097 sim_pfm: 371.473868157346
episode: 144 training return: tensor(324.2669, device='cuda:0')
episode: 145 training return: tensor(-564.8624, device='cuda:0')
episode: 146 training return: tensor(284.2324, device='cuda:0')
episode: 147 training return: tensor(343.5070, device='cuda:0')
epoch: 37 test_true_pfm: 3531.6205414659685 sim_pfm: 367.3950260587541
episode: 148 training return: tensor(299.0109, device='cuda:0')
episode: 149 training return: tensor(336.0243, device='cuda:0')
episode: 150 training return: tensor(311.1043, device='cuda:0')
episode: 151 training return: tensor(305.8485, device='cuda:0')
epoch: 38 test_true_pfm: 3522.402473779199 sim_pfm: 351.4079368855067
episode: 152 training return: tensor(333.6468, device='cuda:0')
episode: 153 training return: tensor(280.8553, device='cuda:0')
episode: 154 training return: tensor(341.0768, device='cuda:0')
episode: 155 training return: tensor(311.2368, device='cuda:0')
epoch: 39 test_true_pfm: 3552.1993198074256 sim_pfm: 386.88447774668265
episode: 156 training return: tensor(57.1112, device='cuda:0')
episode: 157 training return: tensor(326.4031, device='cuda:0')
episode: 158 training return: tensor(349.7305, device='cuda:0')
episode: 159 training return: tensor(323.5599, device='cuda:0')
epoch: 40 test_true_pfm: 3460.2611551590653 sim_pfm: 210.56152631819714
episode: 160 training return: tensor(247.2858, device='cuda:0')
episode: 161 training return: tensor(296.8839, device='cuda:0')
episode: 162 training return: tensor(304.5792, device='cuda:0')
episode: 163 training return: tensor(354.5384, device='cuda:0')
epoch: 41 test_true_pfm: 3505.480438573719 sim_pfm: 395.84223472206696
episode: 164 training return: tensor(-6.7831, device='cuda:0')
episode: 165 training return: tensor(367.1957, device='cuda:0')
episode: 166 training return: tensor(265.5424, device='cuda:0')
episode: 167 training return: tensor(278.5335, device='cuda:0')
epoch: 42 test_true_pfm: 3581.485395041176 sim_pfm: 399.7220739876696
episode: 168 training return: tensor(316.5385, device='cuda:0')
episode: 169 training return: tensor(122.4339, device='cuda:0')
episode: 170 training return: tensor(340.7075, device='cuda:0')
episode: 171 training return: tensor(356.7655, device='cuda:0')
epoch: 43 test_true_pfm: 3434.1816030915675 sim_pfm: 359.62892661002115
episode: 172 training return: tensor(299.4769, device='cuda:0')
episode: 173 training return: tensor(346.3589, device='cuda:0')
episode: 174 training return: tensor(418.3595, device='cuda:0')
episode: 175 training return: tensor(318.3098, device='cuda:0')
epoch: 44 test_true_pfm: 3502.854171575995 sim_pfm: 368.7662161759217
episode: 176 training return: tensor(242.6838, device='cuda:0')
episode: 177 training return: tensor(277.6208, device='cuda:0')
episode: 178 training return: tensor(300.0940, device='cuda:0')
episode: 179 training return: tensor(379.3028, device='cuda:0')
epoch: 45 test_true_pfm: 3517.5888117674162 sim_pfm: 380.4504895324838
episode: 180 training return: tensor(323.3614, device='cuda:0')
episode: 181 training return: tensor(332.7226, device='cuda:0')
episode: 182 training return: tensor(210.4014, device='cuda:0')
episode: 183 training return: tensor(320.7016, device='cuda:0')
epoch: 46 test_true_pfm: 3528.7165081269836 sim_pfm: 347.0687064542435
episode: 184 training return: tensor(340.1920, device='cuda:0')
episode: 185 training return: tensor(266.6515, device='cuda:0')
episode: 186 training return: tensor(335.0092, device='cuda:0')
episode: 187 training return: tensor(347.7720, device='cuda:0')
epoch: 47 test_true_pfm: 3473.913283355499 sim_pfm: 307.0134740340679
episode: 188 training return: tensor(255.3839, device='cuda:0')
episode: 189 training return: tensor(340.9053, device='cuda:0')
episode: 190 training return: tensor(303.1354, device='cuda:0')
episode: 191 training return: tensor(233.2165, device='cuda:0')
epoch: 48 test_true_pfm: 3514.0871284524815 sim_pfm: 375.57690723845735
episode: 192 training return: tensor(376.9548, device='cuda:0')
episode: 193 training return: tensor(247.7738, device='cuda:0')
episode: 194 training return: tensor(345.0588, device='cuda:0')
episode: 195 training return: tensor(264.1940, device='cuda:0')
epoch: 49 test_true_pfm: 3516.159523848164 sim_pfm: 360.51217271589366
episode: 196 training return: tensor(336.3640, device='cuda:0')
episode: 197 training return: tensor(317.2050, device='cuda:0')
episode: 198 training return: tensor(340.2294, device='cuda:0')
episode: 199 training return: tensor(328.6687, device='cuda:0')
epoch: 50 test_true_pfm: 3493.203875711654 sim_pfm: 350.0518154751432
episode: 200 training return: tensor(426.6465, device='cuda:0')
episode: 201 training return: tensor(311.4460, device='cuda:0')
episode: 202 training return: tensor(346.2587, device='cuda:0')
episode: 203 training return: tensor(347.6009, device='cuda:0')
epoch: 51 test_true_pfm: 3479.0384494022633 sim_pfm: 387.4882008631248
episode: 204 training return: tensor(336.5288, device='cuda:0')
episode: 205 training return: tensor(319.7990, device='cuda:0')
episode: 206 training return: tensor(303.3958, device='cuda:0')
episode: 207 training return: tensor(335.0610, device='cuda:0')
epoch: 52 test_true_pfm: 3555.8127392642987 sim_pfm: 397.9497669856937
episode: 208 training return: tensor(358.0944, device='cuda:0')
episode: 209 training return: tensor(338.4943, device='cuda:0')
episode: 210 training return: tensor(171.3011, device='cuda:0')
episode: 211 training return: tensor(354.8133, device='cuda:0')
epoch: 53 test_true_pfm: 3480.41071415021 sim_pfm: 372.0509317082372
episode: 212 training return: tensor(307.5585, device='cuda:0')
episode: 213 training return: tensor(354.2744, device='cuda:0')
episode: 214 training return: tensor(321.3979, device='cuda:0')
episode: 215 training return: tensor(293.1716, device='cuda:0')
epoch: 54 test_true_pfm: 3472.174703313964 sim_pfm: 365.0102593613362
episode: 216 training return: tensor(322.0133, device='cuda:0')
episode: 217 training return: tensor(319.2594, device='cuda:0')
episode: 218 training return: tensor(304.1486, device='cuda:0')
episode: 219 training return: tensor(336.0305, device='cuda:0')
epoch: 55 test_true_pfm: 3560.953801898411 sim_pfm: 393.9598799173643
episode: 220 training return: tensor(366.0060, device='cuda:0')
episode: 221 training return: tensor(344.8930, device='cuda:0')
episode: 222 training return: tensor(255.7579, device='cuda:0')
episode: 223 training return: tensor(289.1347, device='cuda:0')
epoch: 56 test_true_pfm: 3530.265933920246 sim_pfm: 367.0861282200397
episode: 224 training return: tensor(388.6005, device='cuda:0')
episode: 225 training return: tensor(341.7779, device='cuda:0')
episode: 226 training return: tensor(358.4615, device='cuda:0')
episode: 227 training return: tensor(345.3464, device='cuda:0')
epoch: 57 test_true_pfm: 3551.0962650305396 sim_pfm: 411.5619758574564
episode: 228 training return: tensor(285.2597, device='cuda:0')
episode: 229 training return: tensor(349.6687, device='cuda:0')
episode: 230 training return: tensor(238.0061, device='cuda:0')
episode: 231 training return: tensor(182.3155, device='cuda:0')
epoch: 58 test_true_pfm: 3454.192260929227 sim_pfm: 366.12778600043384
episode: 232 training return: tensor(367.4197, device='cuda:0')
episode: 233 training return: tensor(383.3602, device='cuda:0')
episode: 234 training return: tensor(325.5404, device='cuda:0')
episode: 235 training return: tensor(301.0338, device='cuda:0')
epoch: 59 test_true_pfm: 3567.650118226448 sim_pfm: 385.183563146779
episode: 236 training return: tensor(36.0958, device='cuda:0')
episode: 237 training return: tensor(283.9381, device='cuda:0')
episode: 238 training return: tensor(314.7917, device='cuda:0')
episode: 239 training return: tensor(388.0317, device='cuda:0')
epoch: 60 test_true_pfm: 3483.6098358591776 sim_pfm: 387.08331182746525
episode: 240 training return: tensor(67.4840, device='cuda:0')
episode: 241 training return: tensor(312.0583, device='cuda:0')
episode: 242 training return: tensor(331.0245, device='cuda:0')
episode: 243 training return: tensor(316.9445, device='cuda:0')
epoch: 61 test_true_pfm: 3468.975070090061 sim_pfm: 368.270546758431
episode: 244 training return: tensor(332.8099, device='cuda:0')
episode: 245 training return: tensor(361.0945, device='cuda:0')
episode: 246 training return: tensor(302.5977, device='cuda:0')
episode: 247 training return: tensor(280.9343, device='cuda:0')
epoch: 62 test_true_pfm: 3511.7401471903668 sim_pfm: 353.06408346774214
episode: 248 training return: tensor(310.0215, device='cuda:0')
episode: 249 training return: tensor(321.2085, device='cuda:0')
episode: 250 training return: tensor(331.5530, device='cuda:0')
episode: 251 training return: tensor(304.4095, device='cuda:0')
epoch: 63 test_true_pfm: 3540.8472942835356 sim_pfm: 365.8065500013763
episode: 252 training return: tensor(306.3732, device='cuda:0')
episode: 253 training return: tensor(361.0475, device='cuda:0')
episode: 254 training return: tensor(361.5604, device='cuda:0')
episode: 255 training return: tensor(271.4728, device='cuda:0')
epoch: 64 test_true_pfm: 3543.320618943875 sim_pfm: 375.6281252838671
episode: 256 training return: tensor(333.6804, device='cuda:0')
episode: 257 training return: tensor(282.3542, device='cuda:0')
episode: 258 training return: tensor(360.6599, device='cuda:0')
episode: 259 training return: tensor(286.8233, device='cuda:0')
epoch: 65 test_true_pfm: 3526.8426269965416 sim_pfm: 349.4707363224782
episode: 260 training return: tensor(354.8333, device='cuda:0')
episode: 261 training return: tensor(307.1377, device='cuda:0')
episode: 262 training return: tensor(327.0242, device='cuda:0')
episode: 263 training return: tensor(331.4565, device='cuda:0')
epoch: 66 test_true_pfm: 3540.4431015196947 sim_pfm: 346.3272988462898
episode: 264 training return: tensor(371.2193, device='cuda:0')
episode: 265 training return: tensor(336.4132, device='cuda:0')
episode: 266 training return: tensor(398.8558, device='cuda:0')
episode: 267 training return: tensor(353.4204, device='cuda:0')
epoch: 67 test_true_pfm: 3517.8577864460676 sim_pfm: 393.44583940152853
episode: 268 training return: tensor(239.6434, device='cuda:0')
episode: 269 training return: tensor(310.8975, device='cuda:0')
episode: 270 training return: tensor(318.7815, device='cuda:0')
episode: 271 training return: tensor(284.1282, device='cuda:0')
epoch: 68 test_true_pfm: 3515.8178292600473 sim_pfm: 380.4549753330066
episode: 272 training return: tensor(316.3575, device='cuda:0')
episode: 273 training return: tensor(351.1628, device='cuda:0')
episode: 274 training return: tensor(338.1540, device='cuda:0')
episode: 275 training return: tensor(382.6602, device='cuda:0')
epoch: 69 test_true_pfm: 3523.5705984809024 sim_pfm: 338.3152417201879
episode: 276 training return: tensor(368.8922, device='cuda:0')
episode: 277 training return: tensor(372.2147, device='cuda:0')
episode: 278 training return: tensor(320.7357, device='cuda:0')
episode: 279 training return: tensor(361.6718, device='cuda:0')
epoch: 70 test_true_pfm: 3429.448475021681 sim_pfm: 320.54727633831016
episode: 280 training return: tensor(297.7531, device='cuda:0')
episode: 281 training return: tensor(318.1211, device='cuda:0')
episode: 282 training return: tensor(418.7404, device='cuda:0')
episode: 283 training return: tensor(334.3584, device='cuda:0')
epoch: 71 test_true_pfm: 3496.887462578192 sim_pfm: 380.0000952576714
episode: 284 training return: tensor(362.1207, device='cuda:0')
episode: 285 training return: tensor(328.2539, device='cuda:0')
episode: 286 training return: tensor(349.2144, device='cuda:0')
episode: 287 training return: tensor(365.9120, device='cuda:0')
epoch: 72 test_true_pfm: 3495.122827261679 sim_pfm: 396.1140042389064
episode: 288 training return: tensor(358.1729, device='cuda:0')
episode: 289 training return: tensor(310.3335, device='cuda:0')
episode: 290 training return: tensor(158.2143, device='cuda:0')
episode: 291 training return: tensor(350.5031, device='cuda:0')
epoch: 73 test_true_pfm: 3563.851701394116 sim_pfm: 429.4151366187143
episode: 292 training return: tensor(-326.7212, device='cuda:0')
episode: 293 training return: tensor(350.6060, device='cuda:0')
episode: 294 training return: tensor(350.4007, device='cuda:0')
episode: 295 training return: tensor(345.3622, device='cuda:0')
epoch: 74 test_true_pfm: 3579.336233441844 sim_pfm: 191.51237066694497
episode: 296 training return: tensor(263.6672, device='cuda:0')
episode: 297 training return: tensor(385.7441, device='cuda:0')
episode: 298 training return: tensor(310.4526, device='cuda:0')
episode: 299 training return: tensor(299.6942, device='cuda:0')
epoch: 75 test_true_pfm: 3540.015466425211 sim_pfm: 392.8962468673708
episode: 300 training return: tensor(424.8302, device='cuda:0')
episode: 301 training return: tensor(328.1245, device='cuda:0')
episode: 302 training return: tensor(353.1973, device='cuda:0')
episode: 303 training return: tensor(293.9424, device='cuda:0')
epoch: 76 test_true_pfm: 3594.265154778734 sim_pfm: 405.3132448234828
episode: 304 training return: tensor(291.0923, device='cuda:0')
episode: 305 training return: tensor(333.9681, device='cuda:0')
episode: 306 training return: tensor(296.0219, device='cuda:0')
episode: 307 training return: tensor(346.9307, device='cuda:0')
epoch: 77 test_true_pfm: 3620.018713138588 sim_pfm: 418.2401559606078
episode: 308 training return: tensor(346.7784, device='cuda:0')
episode: 309 training return: tensor(272.7986, device='cuda:0')
episode: 310 training return: tensor(389.2471, device='cuda:0')
episode: 311 training return: tensor(332.8627, device='cuda:0')
epoch: 78 test_true_pfm: 3537.0941036091663 sim_pfm: 418.7643964143451
episode: 312 training return: tensor(329.7016, device='cuda:0')
episode: 313 training return: tensor(294.7778, device='cuda:0')
episode: 314 training return: tensor(347.9350, device='cuda:0')
episode: 315 training return: tensor(410.2469, device='cuda:0')
epoch: 79 test_true_pfm: 3546.760178425651 sim_pfm: 401.57705111285514
episode: 316 training return: tensor(307.2633, device='cuda:0')
episode: 317 training return: tensor(369.0538, device='cuda:0')
episode: 318 training return: tensor(364.5927, device='cuda:0')
episode: 319 training return: tensor(395.0090, device='cuda:0')
epoch: 80 test_true_pfm: 3584.3067308049417 sim_pfm: 409.15350423328346
episode: 320 training return: tensor(310.7640, device='cuda:0')
episode: 321 training return: tensor(355.6247, device='cuda:0')
episode: 322 training return: tensor(344.6403, device='cuda:0')
episode: 323 training return: tensor(268.8368, device='cuda:0')
epoch: 81 test_true_pfm: 3538.0174994605018 sim_pfm: 372.9126885398776
episode: 324 training return: tensor(325.4144, device='cuda:0')
episode: 325 training return: tensor(314.9386, device='cuda:0')
episode: 326 training return: tensor(405.3185, device='cuda:0')
episode: 327 training return: tensor(330.0375, device='cuda:0')
epoch: 82 test_true_pfm: 3521.627994600871 sim_pfm: 408.72965198670863
episode: 328 training return: tensor(306.6704, device='cuda:0')
episode: 329 training return: tensor(343.8070, device='cuda:0')
episode: 330 training return: tensor(313.3156, device='cuda:0')
episode: 331 training return: tensor(358.2770, device='cuda:0')
epoch: 83 test_true_pfm: 3574.7527817378996 sim_pfm: 407.3794908571096
episode: 332 training return: tensor(394.2601, device='cuda:0')
episode: 333 training return: tensor(362.0351, device='cuda:0')
episode: 334 training return: tensor(351.3572, device='cuda:0')
episode: 335 training return: tensor(316.7706, device='cuda:0')
epoch: 84 test_true_pfm: 3525.461863451163 sim_pfm: 370.5898710777595
episode: 336 training return: tensor(364.7544, device='cuda:0')
episode: 337 training return: tensor(366.3130, device='cuda:0')
episode: 338 training return: tensor(319.1140, device='cuda:0')
episode: 339 training return: tensor(356.6513, device='cuda:0')
epoch: 85 test_true_pfm: 3584.5181525635303 sim_pfm: 395.65264161776093
episode: 340 training return: tensor(379.2778, device='cuda:0')
episode: 341 training return: tensor(375.0476, device='cuda:0')
episode: 342 training return: tensor(334.6039, device='cuda:0')
episode: 343 training return: tensor(331.2519, device='cuda:0')
epoch: 86 test_true_pfm: 3521.0788816550375 sim_pfm: 356.122986575152
episode: 344 training return: tensor(326.9059, device='cuda:0')
episode: 345 training return: tensor(358.5213, device='cuda:0')
episode: 346 training return: tensor(346.4472, device='cuda:0')
episode: 347 training return: tensor(298.6801, device='cuda:0')
epoch: 87 test_true_pfm: 3569.025498967432 sim_pfm: 414.89531727057573
episode: 348 training return: tensor(367.2377, device='cuda:0')
episode: 349 training return: tensor(332.4760, device='cuda:0')
episode: 350 training return: tensor(329.3266, device='cuda:0')
episode: 351 training return: tensor(331.9535, device='cuda:0')
epoch: 88 test_true_pfm: 3621.786774413879 sim_pfm: 444.76836984957725
episode: 352 training return: tensor(358.9317, device='cuda:0')
episode: 353 training return: tensor(286.2000, device='cuda:0')
episode: 354 training return: tensor(343.9438, device='cuda:0')
episode: 355 training return: tensor(270.6673, device='cuda:0')
epoch: 89 test_true_pfm: 3586.4035383262776 sim_pfm: 400.2747978416155
episode: 356 training return: tensor(383.2049, device='cuda:0')
episode: 357 training return: tensor(116.4808, device='cuda:0')
episode: 358 training return: tensor(321.4695, device='cuda:0')
episode: 359 training return: tensor(332.8199, device='cuda:0')
epoch: 90 test_true_pfm: 3563.51921439855 sim_pfm: 391.1072461544148
episode: 360 training return: tensor(375.7310, device='cuda:0')
episode: 361 training return: tensor(351.4166, device='cuda:0')
episode: 362 training return: tensor(333.1906, device='cuda:0')
episode: 363 training return: tensor(374.8235, device='cuda:0')
epoch: 91 test_true_pfm: 3504.3806614028886 sim_pfm: 380.20769268124906
episode: 364 training return: tensor(301.8876, device='cuda:0')
episode: 365 training return: tensor(-73.1887, device='cuda:0')
episode: 366 training return: tensor(295.1133, device='cuda:0')
episode: 367 training return: tensor(352.0640, device='cuda:0')
epoch: 92 test_true_pfm: 3594.882192744257 sim_pfm: 404.44360038077383
episode: 368 training return: tensor(315.1004, device='cuda:0')
episode: 369 training return: tensor(408.0331, device='cuda:0')
episode: 370 training return: tensor(325.9514, device='cuda:0')
episode: 371 training return: tensor(365.2116, device='cuda:0')
epoch: 93 test_true_pfm: 3621.8798997132835 sim_pfm: 398.6380973255339
episode: 372 training return: tensor(400.0781, device='cuda:0')
episode: 373 training return: tensor(357.9380, device='cuda:0')
episode: 374 training return: tensor(318.0896, device='cuda:0')
episode: 375 training return: tensor(355.7913, device='cuda:0')
epoch: 94 test_true_pfm: 3543.0050216652803 sim_pfm: 368.6357913496128
episode: 376 training return: tensor(361.3655, device='cuda:0')
episode: 377 training return: tensor(320.7446, device='cuda:0')
episode: 378 training return: tensor(313.1207, device='cuda:0')
episode: 379 training return: tensor(341.6606, device='cuda:0')
epoch: 95 test_true_pfm: 3538.7364043969696 sim_pfm: 340.9911885287535
episode: 380 training return: tensor(285.2738, device='cuda:0')
episode: 381 training return: tensor(375.0774, device='cuda:0')
episode: 382 training return: tensor(318.2533, device='cuda:0')
episode: 383 training return: tensor(346.1094, device='cuda:0')
epoch: 96 test_true_pfm: 3604.9980738203644 sim_pfm: 423.4134878276964
episode: 384 training return: tensor(351.4753, device='cuda:0')
episode: 385 training return: tensor(344.2873, device='cuda:0')
episode: 386 training return: tensor(331.9010, device='cuda:0')
episode: 387 training return: tensor(339.7724, device='cuda:0')
epoch: 97 test_true_pfm: 3572.7722185424373 sim_pfm: 394.93281216791365
episode: 388 training return: tensor(402.2185, device='cuda:0')
episode: 389 training return: tensor(213.5365, device='cuda:0')
episode: 390 training return: tensor(382.1731, device='cuda:0')
episode: 391 training return: tensor(315.4183, device='cuda:0')
epoch: 98 test_true_pfm: 3557.7142368721434 sim_pfm: 440.4091551423189
episode: 392 training return: tensor(-221.6996, device='cuda:0')
episode: 393 training return: tensor(373.3385, device='cuda:0')
episode: 394 training return: tensor(320.3224, device='cuda:0')
episode: 395 training return: tensor(291.4340, device='cuda:0')
epoch: 99 test_true_pfm: 3570.577577905988 sim_pfm: 418.30128354645177
episode: 396 training return: tensor(351.8581, device='cuda:0')
episode: 397 training return: tensor(323.1856, device='cuda:0')
episode: 398 training return: tensor(-229.7620, device='cuda:0')
episode: 399 training return: tensor(325.4544, device='cuda:0')
epoch: 100 test_true_pfm: 3480.4917673530003 sim_pfm: 354.7268818814773
episode: 400 training return: tensor(376.9575, device='cuda:0')
episode: 401 training return: tensor(360.7667, device='cuda:0')
episode: 402 training return: tensor(297.1997, device='cuda:0')
episode: 403 training return: tensor(315.2388, device='cuda:0')
epoch: 101 test_true_pfm: 3612.814770471666 sim_pfm: 413.828510805266
episode: 404 training return: tensor(341.1095, device='cuda:0')
episode: 405 training return: tensor(317.5639, device='cuda:0')
episode: 406 training return: tensor(338.0508, device='cuda:0')
episode: 407 training return: tensor(310.0588, device='cuda:0')
epoch: 102 test_true_pfm: 3585.0886690285006 sim_pfm: 379.97364892832894
episode: 408 training return: tensor(352.8465, device='cuda:0')
episode: 409 training return: tensor(332.8109, device='cuda:0')
episode: 410 training return: tensor(365.2585, device='cuda:0')
episode: 411 training return: tensor(340.8007, device='cuda:0')
epoch: 103 test_true_pfm: 3517.686180391116 sim_pfm: 397.24968118597945
episode: 412 training return: tensor(371.1220, device='cuda:0')
episode: 413 training return: tensor(351.2791, device='cuda:0')
episode: 414 training return: tensor(367.6652, device='cuda:0')
episode: 415 training return: tensor(352.4992, device='cuda:0')
epoch: 104 test_true_pfm: 3502.8580718730896 sim_pfm: 356.36242450230446
episode: 416 training return: tensor(367.5067, device='cuda:0')
episode: 417 training return: tensor(315.5907, device='cuda:0')
episode: 418 training return: tensor(355.4468, device='cuda:0')
episode: 419 training return: tensor(373.9740, device='cuda:0')
epoch: 105 test_true_pfm: 3555.7308458210696 sim_pfm: 232.27061654184945
episode: 420 training return: tensor(214.5828, device='cuda:0')
episode: 421 training return: tensor(363.3538, device='cuda:0')
episode: 422 training return: tensor(320.6388, device='cuda:0')
episode: 423 training return: tensor(313.1434, device='cuda:0')
epoch: 106 test_true_pfm: 3566.032985224769 sim_pfm: 405.0524697118187
episode: 424 training return: tensor(372.7173, device='cuda:0')
episode: 425 training return: tensor(328.8581, device='cuda:0')
episode: 426 training return: tensor(337.3766, device='cuda:0')
episode: 427 training return: tensor(357.0300, device='cuda:0')
epoch: 107 test_true_pfm: 3507.010054985614 sim_pfm: 395.87362187120016
episode: 428 training return: tensor(377.7336, device='cuda:0')
episode: 429 training return: tensor(355.4887, device='cuda:0')
episode: 430 training return: tensor(394.2578, device='cuda:0')
episode: 431 training return: tensor(365.5107, device='cuda:0')
epoch: 108 test_true_pfm: 3509.7090095479634 sim_pfm: 218.85762636495443
episode: 432 training return: tensor(332.2238, device='cuda:0')
episode: 433 training return: tensor(346.7711, device='cuda:0')
episode: 434 training return: tensor(96.4709, device='cuda:0')
episode: 435 training return: tensor(325.1838, device='cuda:0')
epoch: 109 test_true_pfm: 3568.683215316724 sim_pfm: 363.31713602873305
episode: 436 training return: tensor(348.4252, device='cuda:0')
episode: 437 training return: tensor(142.3114, device='cuda:0')
episode: 438 training return: tensor(315.0906, device='cuda:0')
episode: 439 training return: tensor(339.5084, device='cuda:0')
epoch: 110 test_true_pfm: 3572.76884443971 sim_pfm: 429.21793915486586
episode: 440 training return: tensor(20.4258, device='cuda:0')
episode: 441 training return: tensor(-54.8043, device='cuda:0')
episode: 442 training return: tensor(331.5485, device='cuda:0')
episode: 443 training return: tensor(307.3936, device='cuda:0')
epoch: 111 test_true_pfm: 3642.471096540072 sim_pfm: 453.6486157523177
episode: 444 training return: tensor(366.1542, device='cuda:0')
episode: 445 training return: tensor(381.2787, device='cuda:0')
episode: 446 training return: tensor(351.7549, device='cuda:0')
episode: 447 training return: tensor(379.2619, device='cuda:0')
epoch: 112 test_true_pfm: 3531.535325978468 sim_pfm: 409.6653523228015
episode: 448 training return: tensor(379.0449, device='cuda:0')
episode: 449 training return: tensor(388.0380, device='cuda:0')
episode: 450 training return: tensor(325.9474, device='cuda:0')
episode: 451 training return: tensor(361.0762, device='cuda:0')
epoch: 113 test_true_pfm: 3557.270930813455 sim_pfm: 393.9409455024482
episode: 452 training return: tensor(350.2659, device='cuda:0')
episode: 453 training return: tensor(416.8856, device='cuda:0')
episode: 454 training return: tensor(331.2580, device='cuda:0')
episode: 455 training return: tensor(379.8969, device='cuda:0')
epoch: 114 test_true_pfm: 3635.215647296029 sim_pfm: 448.8119415919452
episode: 456 training return: tensor(372.8523, device='cuda:0')
episode: 457 training return: tensor(355.9568, device='cuda:0')
episode: 458 training return: tensor(365.4081, device='cuda:0')
episode: 459 training return: tensor(375.0113, device='cuda:0')
epoch: 115 test_true_pfm: 3594.2442557098043 sim_pfm: 388.3082047748224
episode: 460 training return: tensor(395.0745, device='cuda:0')
episode: 461 training return: tensor(299.6257, device='cuda:0')
episode: 462 training return: tensor(372.7398, device='cuda:0')
episode: 463 training return: tensor(350.3668, device='cuda:0')
epoch: 116 test_true_pfm: 3628.969991741886 sim_pfm: 442.30314131364383
episode: 464 training return: tensor(352.2689, device='cuda:0')
episode: 465 training return: tensor(384.0759, device='cuda:0')
episode: 466 training return: tensor(301.8713, device='cuda:0')
episode: 467 training return: tensor(365.6360, device='cuda:0')
epoch: 117 test_true_pfm: 3487.03796533296 sim_pfm: 411.33756394546555
episode: 468 training return: tensor(327.4828, device='cuda:0')
episode: 469 training return: tensor(344.9952, device='cuda:0')
episode: 470 training return: tensor(350.6689, device='cuda:0')
episode: 471 training return: tensor(346.5121, device='cuda:0')
epoch: 118 test_true_pfm: 3535.6931048220663 sim_pfm: 411.480330805236
episode: 472 training return: tensor(293.1256, device='cuda:0')
episode: 473 training return: tensor(360.2376, device='cuda:0')
episode: 474 training return: tensor(362.1022, device='cuda:0')
episode: 475 training return: tensor(288.6681, device='cuda:0')
epoch: 119 test_true_pfm: 3565.258484262448 sim_pfm: 416.2190449711634
episode: 476 training return: tensor(341.0517, device='cuda:0')
episode: 477 training return: tensor(318.8995, device='cuda:0')
episode: 478 training return: tensor(371.3918, device='cuda:0')
episode: 479 training return: tensor(329.3456, device='cuda:0')
epoch: 120 test_true_pfm: 3599.017353230262 sim_pfm: 421.4780780528672
episode: 480 training return: tensor(355.2180, device='cuda:0')
episode: 481 training return: tensor(268.8448, device='cuda:0')
episode: 482 training return: tensor(373.6448, device='cuda:0')
episode: 483 training return: tensor(364.6028, device='cuda:0')
epoch: 121 test_true_pfm: 3612.498368732871 sim_pfm: 400.22699289536104
episode: 484 training return: tensor(326.8506, device='cuda:0')
episode: 485 training return: tensor(332.9928, device='cuda:0')
episode: 486 training return: tensor(334.4970, device='cuda:0')
episode: 487 training return: tensor(385.1693, device='cuda:0')
epoch: 122 test_true_pfm: 3615.339975766439 sim_pfm: 443.5156988622912
episode: 488 training return: tensor(388.7305, device='cuda:0')
episode: 489 training return: tensor(372.8048, device='cuda:0')
episode: 490 training return: tensor(360.0040, device='cuda:0')
episode: 491 training return: tensor(369.4472, device='cuda:0')
epoch: 123 test_true_pfm: 3577.233699202208 sim_pfm: 438.2668563447466
episode: 492 training return: tensor(399.9733, device='cuda:0')
episode: 493 training return: tensor(378.9623, device='cuda:0')
episode: 494 training return: tensor(368.7898, device='cuda:0')
episode: 495 training return: tensor(399.4162, device='cuda:0')
epoch: 124 test_true_pfm: 3561.219681209177 sim_pfm: 421.1614101076557
episode: 496 training return: tensor(382.1334, device='cuda:0')
episode: 497 training return: tensor(354.2979, device='cuda:0')
episode: 498 training return: tensor(334.9754, device='cuda:0')
episode: 499 training return: tensor(349.1379, device='cuda:0')
epoch: 125 test_true_pfm: 3537.850430766568 sim_pfm: 404.60568799185177
episode: 500 training return: tensor(355.9650, device='cuda:0')
episode: 501 training return: tensor(337.0908, device='cuda:0')
episode: 502 training return: tensor(312.8510, device='cuda:0')
episode: 503 training return: tensor(364.5971, device='cuda:0')
epoch: 126 test_true_pfm: 3594.7820320309347 sim_pfm: 402.86387226800434
episode: 504 training return: tensor(346.3855, device='cuda:0')
episode: 505 training return: tensor(306.0586, device='cuda:0')
episode: 506 training return: tensor(360.2359, device='cuda:0')
episode: 507 training return: tensor(198.0435, device='cuda:0')
epoch: 127 test_true_pfm: 3634.336367422447 sim_pfm: 402.1615120973729
episode: 508 training return: tensor(350.9242, device='cuda:0')
episode: 509 training return: tensor(335.6563, device='cuda:0')
episode: 510 training return: tensor(269.6928, device='cuda:0')
episode: 511 training return: tensor(415.3527, device='cuda:0')
epoch: 128 test_true_pfm: 3583.795753542032 sim_pfm: 416.4926392317866
episode: 512 training return: tensor(376.9043, device='cuda:0')
episode: 513 training return: tensor(348.0123, device='cuda:0')
episode: 514 training return: tensor(342.9816, device='cuda:0')
episode: 515 training return: tensor(383.0443, device='cuda:0')
epoch: 129 test_true_pfm: 3598.71510498163 sim_pfm: 406.32792286666034
episode: 516 training return: tensor(349.1942, device='cuda:0')
episode: 517 training return: tensor(341.8641, device='cuda:0')
episode: 518 training return: tensor(350.9530, device='cuda:0')
episode: 519 training return: tensor(356.6562, device='cuda:0')
epoch: 130 test_true_pfm: 3530.8048312423175 sim_pfm: 392.94683419237845
episode: 520 training return: tensor(366.7694, device='cuda:0')
episode: 521 training return: tensor(320.0251, device='cuda:0')
episode: 522 training return: tensor(310.8659, device='cuda:0')
episode: 523 training return: tensor(415.9712, device='cuda:0')
epoch: 131 test_true_pfm: 3523.2140067614528 sim_pfm: 367.24667670045164
episode: 524 training return: tensor(288.6406, device='cuda:0')
episode: 525 training return: tensor(378.0687, device='cuda:0')
episode: 526 training return: tensor(318.7901, device='cuda:0')
episode: 527 training return: tensor(338.1694, device='cuda:0')
epoch: 132 test_true_pfm: 3481.665762557323 sim_pfm: 339.8824994106156
episode: 528 training return: tensor(364.5966, device='cuda:0')
episode: 529 training return: tensor(310.2533, device='cuda:0')
episode: 530 training return: tensor(321.9627, device='cuda:0')
episode: 531 training return: tensor(359.9811, device='cuda:0')
epoch: 133 test_true_pfm: 3568.7437684407923 sim_pfm: 389.82656405226834
episode: 532 training return: tensor(313.8080, device='cuda:0')
episode: 533 training return: tensor(342.3882, device='cuda:0')
episode: 534 training return: tensor(363.7851, device='cuda:0')
episode: 535 training return: tensor(381.1435, device='cuda:0')
epoch: 134 test_true_pfm: 3577.5330225846756 sim_pfm: 377.01311731919606
episode: 536 training return: tensor(336.5621, device='cuda:0')
episode: 537 training return: tensor(359.1017, device='cuda:0')
episode: 538 training return: tensor(371.9344, device='cuda:0')
episode: 539 training return: tensor(320.1255, device='cuda:0')
epoch: 135 test_true_pfm: 3532.2134936520647 sim_pfm: 397.9466609937469
episode: 540 training return: tensor(367.2975, device='cuda:0')
episode: 541 training return: tensor(341.4907, device='cuda:0')
episode: 542 training return: tensor(336.6049, device='cuda:0')
episode: 543 training return: tensor(390.1220, device='cuda:0')
epoch: 136 test_true_pfm: 3566.21565745384 sim_pfm: 421.75987504280056
episode: 544 training return: tensor(348.9779, device='cuda:0')
episode: 545 training return: tensor(-141.0071, device='cuda:0')
episode: 546 training return: tensor(366.4293, device='cuda:0')
episode: 547 training return: tensor(321.5554, device='cuda:0')
epoch: 137 test_true_pfm: 3518.340348450251 sim_pfm: 387.9656495219485
episode: 548 training return: tensor(326.2299, device='cuda:0')
episode: 549 training return: tensor(439.4897, device='cuda:0')
episode: 550 training return: tensor(344.1601, device='cuda:0')
episode: 551 training return: tensor(335.7041, device='cuda:0')
epoch: 138 test_true_pfm: 3506.5364903431073 sim_pfm: 344.13256358461996
episode: 552 training return: tensor(381.4909, device='cuda:0')
episode: 553 training return: tensor(340.5668, device='cuda:0')
episode: 554 training return: tensor(326.2054, device='cuda:0')
episode: 555 training return: tensor(314.2962, device='cuda:0')
epoch: 139 test_true_pfm: 3538.6708407803376 sim_pfm: 394.59392904684256
episode: 556 training return: tensor(372.6422, device='cuda:0')
episode: 557 training return: tensor(337.0681, device='cuda:0')
episode: 558 training return: tensor(405.2151, device='cuda:0')
episode: 559 training return: tensor(401.1076, device='cuda:0')
epoch: 140 test_true_pfm: 3553.059356901376 sim_pfm: 398.0225887991449
episode: 560 training return: tensor(335.2844, device='cuda:0')
episode: 561 training return: tensor(389.6803, device='cuda:0')
episode: 562 training return: tensor(100.4946, device='cuda:0')
episode: 563 training return: tensor(391.4713, device='cuda:0')
epoch: 141 test_true_pfm: 3581.2295468387606 sim_pfm: 406.70234495436307
episode: 564 training return: tensor(329.7326, device='cuda:0')
episode: 565 training return: tensor(352.5557, device='cuda:0')
episode: 566 training return: tensor(325.8170, device='cuda:0')
episode: 567 training return: tensor(380.2705, device='cuda:0')
epoch: 142 test_true_pfm: 3531.876786239414 sim_pfm: 383.0979507739539
episode: 568 training return: tensor(361.2274, device='cuda:0')
episode: 569 training return: tensor(-214.1572, device='cuda:0')
episode: 570 training return: tensor(335.6205, device='cuda:0')
episode: 571 training return: tensor(332.2508, device='cuda:0')
epoch: 143 test_true_pfm: 3564.266866961385 sim_pfm: 414.5211475265678
episode: 572 training return: tensor(368.7834, device='cuda:0')
episode: 573 training return: tensor(357.4378, device='cuda:0')
episode: 574 training return: tensor(320.9904, device='cuda:0')
episode: 575 training return: tensor(364.8557, device='cuda:0')
epoch: 144 test_true_pfm: 3544.2220217116705 sim_pfm: 411.90799371122074
episode: 576 training return: tensor(350.7706, device='cuda:0')
episode: 577 training return: tensor(356.2330, device='cuda:0')
episode: 578 training return: tensor(397.8464, device='cuda:0')
episode: 579 training return: tensor(333.6622, device='cuda:0')
epoch: 145 test_true_pfm: 3503.5669059249108 sim_pfm: 388.36809104700416
episode: 580 training return: tensor(321.5026, device='cuda:0')
episode: 581 training return: tensor(292.8433, device='cuda:0')
episode: 582 training return: tensor(369.4043, device='cuda:0')
episode: 583 training return: tensor(376.0998, device='cuda:0')
epoch: 146 test_true_pfm: 3565.8865640851855 sim_pfm: 400.2824101416821
episode: 584 training return: tensor(342.2570, device='cuda:0')
episode: 585 training return: tensor(310.4246, device='cuda:0')
episode: 586 training return: tensor(341.1865, device='cuda:0')
episode: 587 training return: tensor(328.7527, device='cuda:0')
epoch: 147 test_true_pfm: 3579.1761653789677 sim_pfm: 431.87804592966376
episode: 588 training return: tensor(355.0374, device='cuda:0')
episode: 589 training return: tensor(364.8849, device='cuda:0')
episode: 590 training return: tensor(351.2759, device='cuda:0')
episode: 591 training return: tensor(334.1190, device='cuda:0')
epoch: 148 test_true_pfm: 3551.7152281745894 sim_pfm: 403.8670555212302
episode: 592 training return: tensor(358.4883, device='cuda:0')
episode: 593 training return: tensor(409.0993, device='cuda:0')
episode: 594 training return: tensor(348.0603, device='cuda:0')
episode: 595 training return: tensor(363.1390, device='cuda:0')
epoch: 149 test_true_pfm: 3588.4923814856024 sim_pfm: 391.638874231731
episode: 596 training return: tensor(351.8289, device='cuda:0')
episode: 597 training return: tensor(364.6696, device='cuda:0')
episode: 598 training return: tensor(352.2912, device='cuda:0')
episode: 599 training return: tensor(339.6844, device='cuda:0')
epoch: 150 test_true_pfm: 3607.865366565747 sim_pfm: 247.99014920927584
