['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '3', '--data', '100000', '--regu', '0.2']
3079.515640996394
episode: 0 training return: tensor(303.7049, device='cuda:0')
episode: 1 training return: tensor(-121.5442, device='cuda:0')
episode: 2 training return: tensor(266.2099, device='cuda:0')
episode: 3 training return: tensor(245.1765, device='cuda:0')
epoch: 1 test_true_pfm: 3368.4425033978973 sim_pfm: 296.87520117476623
episode: 4 training return: tensor(238.8335, device='cuda:0')
episode: 5 training return: tensor(128.2855, device='cuda:0')
episode: 6 training return: tensor(267.8173, device='cuda:0')
episode: 7 training return: tensor(238.6500, device='cuda:0')
epoch: 2 test_true_pfm: 3222.4089172564927 sim_pfm: 137.3293541611541
episode: 8 training return: tensor(247.8582, device='cuda:0')
episode: 9 training return: tensor(142.1740, device='cuda:0')
episode: 10 training return: tensor(-140.2014, device='cuda:0')
episode: 11 training return: tensor(-237.8943, device='cuda:0')
epoch: 3 test_true_pfm: 2864.20013874597 sim_pfm: 216.6850126972616
episode: 12 training return: tensor(143.6332, device='cuda:0')
episode: 13 training return: tensor(267.6428, device='cuda:0')
episode: 14 training return: tensor(299.6104, device='cuda:0')
episode: 15 training return: tensor(-29.6192, device='cuda:0')
epoch: 4 test_true_pfm: 2682.592395392925 sim_pfm: 128.53758077682383
episode: 16 training return: tensor(-11.3103, device='cuda:0')
episode: 17 training return: tensor(-111.9696, device='cuda:0')
episode: 18 training return: tensor(-320.9593, device='cuda:0')
episode: 19 training return: tensor(393.9537, device='cuda:0')
epoch: 5 test_true_pfm: 2534.880430851851 sim_pfm: -26.014420744109277
episode: 20 training return: tensor(-182.3262, device='cuda:0')
episode: 21 training return: tensor(428.7397, device='cuda:0')
episode: 22 training return: tensor(-5.9689, device='cuda:0')
episode: 23 training return: tensor(400.5564, device='cuda:0')
epoch: 6 test_true_pfm: 2813.3287131931233 sim_pfm: 320.95083922180737
episode: 24 training return: tensor(297.7603, device='cuda:0')
episode: 25 training return: tensor(306.2959, device='cuda:0')
episode: 26 training return: tensor(355.8795, device='cuda:0')
episode: 27 training return: tensor(230.9958, device='cuda:0')
epoch: 7 test_true_pfm: 3120.823715995078 sim_pfm: 154.14680991187925
episode: 28 training return: tensor(412.0641, device='cuda:0')
episode: 29 training return: tensor(248.2617, device='cuda:0')
episode: 30 training return: tensor(-274.7305, device='cuda:0')
episode: 31 training return: tensor(406.0430, device='cuda:0')
epoch: 8 test_true_pfm: 2472.871308462201 sim_pfm: 120.85708050262959
episode: 32 training return: tensor(365.4920, device='cuda:0')
episode: 33 training return: tensor(303.0570, device='cuda:0')
episode: 34 training return: tensor(-133.0463, device='cuda:0')
episode: 35 training return: tensor(196.1291, device='cuda:0')
epoch: 9 test_true_pfm: 1639.117176692673 sim_pfm: 130.85756202795892
episode: 36 training return: tensor(-43.8487, device='cuda:0')
episode: 37 training return: tensor(62.3976, device='cuda:0')
episode: 38 training return: tensor(70.7454, device='cuda:0')
episode: 39 training return: tensor(166.2212, device='cuda:0')
epoch: 10 test_true_pfm: 2599.16598523699 sim_pfm: 108.53779808616189
episode: 40 training return: tensor(292.5122, device='cuda:0')
episode: 41 training return: tensor(331.3214, device='cuda:0')
episode: 42 training return: tensor(305.9715, device='cuda:0')
episode: 43 training return: tensor(365.0755, device='cuda:0')
epoch: 11 test_true_pfm: 2786.3150011453204 sim_pfm: 211.6085962878618
episode: 44 training return: tensor(108.1090, device='cuda:0')
episode: 45 training return: tensor(338.8815, device='cuda:0')
episode: 46 training return: tensor(403.5865, device='cuda:0')
episode: 47 training return: tensor(248.2196, device='cuda:0')
epoch: 12 test_true_pfm: 2925.5559568492245 sim_pfm: 279.7255468808774
episode: 48 training return: tensor(367.6803, device='cuda:0')
episode: 49 training return: tensor(254.8770, device='cuda:0')
episode: 50 training return: tensor(-245.6605, device='cuda:0')
episode: 51 training return: tensor(382.4421, device='cuda:0')
epoch: 13 test_true_pfm: 3244.4339842430963 sim_pfm: 218.88666932445872
episode: 52 training return: tensor(-210.5058, device='cuda:0')
episode: 53 training return: tensor(347.6371, device='cuda:0')
episode: 54 training return: tensor(324.2063, device='cuda:0')
episode: 55 training return: tensor(-181.3545, device='cuda:0')
epoch: 14 test_true_pfm: 3301.1397075863056 sim_pfm: 153.3887321446479
episode: 56 training return: tensor(273.0005, device='cuda:0')
episode: 57 training return: tensor(148.8015, device='cuda:0')
episode: 58 training return: tensor(346.9915, device='cuda:0')
episode: 59 training return: tensor(355.8933, device='cuda:0')
epoch: 15 test_true_pfm: 3116.8786540941487 sim_pfm: 284.4332877071477
episode: 60 training return: tensor(324.3805, device='cuda:0')
episode: 61 training return: tensor(-349.6780, device='cuda:0')
episode: 62 training return: tensor(219.9371, device='cuda:0')
episode: 63 training return: tensor(310.2850, device='cuda:0')
epoch: 16 test_true_pfm: 3379.2375359048797 sim_pfm: 284.81133805968176
episode: 64 training return: tensor(282.8069, device='cuda:0')
episode: 65 training return: tensor(311.2029, device='cuda:0')
episode: 66 training return: tensor(329.4137, device='cuda:0')
episode: 67 training return: tensor(324.2395, device='cuda:0')
epoch: 17 test_true_pfm: 3424.8161953422764 sim_pfm: 143.47589880536543
episode: 68 training return: tensor(285.4873, device='cuda:0')
episode: 69 training return: tensor(369.3283, device='cuda:0')
episode: 70 training return: tensor(-23.7129, device='cuda:0')
episode: 71 training return: tensor(276.1223, device='cuda:0')
epoch: 18 test_true_pfm: 3526.1169181175733 sim_pfm: 384.0193663337947
episode: 72 training return: tensor(374.7913, device='cuda:0')
episode: 73 training return: tensor(406.1148, device='cuda:0')
episode: 74 training return: tensor(377.5494, device='cuda:0')
episode: 75 training return: tensor(310.3234, device='cuda:0')
epoch: 19 test_true_pfm: 3392.862509481866 sim_pfm: 292.14891491403495
episode: 76 training return: tensor(376.9454, device='cuda:0')
episode: 77 training return: tensor(262.8807, device='cuda:0')
episode: 78 training return: tensor(357.9465, device='cuda:0')
episode: 79 training return: tensor(303.1591, device='cuda:0')
epoch: 20 test_true_pfm: 3496.480635039217 sim_pfm: 169.5388223103558
episode: 80 training return: tensor(378.1215, device='cuda:0')
episode: 81 training return: tensor(347.4247, device='cuda:0')
episode: 82 training return: tensor(366.1968, device='cuda:0')
episode: 83 training return: tensor(369.0038, device='cuda:0')
epoch: 21 test_true_pfm: 3343.6731767946926 sim_pfm: 303.97621851661825
episode: 84 training return: tensor(365.2306, device='cuda:0')
episode: 85 training return: tensor(409.5041, device='cuda:0')
episode: 86 training return: tensor(317.7697, device='cuda:0')
episode: 87 training return: tensor(349.0326, device='cuda:0')
epoch: 22 test_true_pfm: 3515.0383624690458 sim_pfm: 402.8697410281554
episode: 88 training return: tensor(337.0412, device='cuda:0')
episode: 89 training return: tensor(353.8532, device='cuda:0')
episode: 90 training return: tensor(351.2155, device='cuda:0')
episode: 91 training return: tensor(356.7583, device='cuda:0')
epoch: 23 test_true_pfm: 3430.560465100087 sim_pfm: 342.90087424532976
episode: 92 training return: tensor(390.2186, device='cuda:0')
episode: 93 training return: tensor(408.2545, device='cuda:0')
episode: 94 training return: tensor(223.2829, device='cuda:0')
episode: 95 training return: tensor(309.0315, device='cuda:0')
epoch: 24 test_true_pfm: 3486.2720478746355 sim_pfm: 388.9710750860395
episode: 96 training return: tensor(374.4067, device='cuda:0')
episode: 97 training return: tensor(300.2390, device='cuda:0')
episode: 98 training return: tensor(364.8367, device='cuda:0')
episode: 99 training return: tensor(360.9727, device='cuda:0')
epoch: 25 test_true_pfm: 3417.8275425819024 sim_pfm: 349.1282208726043
episode: 100 training return: tensor(406.6665, device='cuda:0')
episode: 101 training return: tensor(397.6183, device='cuda:0')
episode: 102 training return: tensor(386.8849, device='cuda:0')
episode: 103 training return: tensor(318.6523, device='cuda:0')
epoch: 26 test_true_pfm: 3490.9562776160287 sim_pfm: 416.33555636481225
episode: 104 training return: tensor(416.8049, device='cuda:0')
episode: 105 training return: tensor(405.9783, device='cuda:0')
episode: 106 training return: tensor(370.0902, device='cuda:0')
episode: 107 training return: tensor(363.5245, device='cuda:0')
epoch: 27 test_true_pfm: 3517.8583862783175 sim_pfm: 412.92029621846933
episode: 108 training return: tensor(392.3903, device='cuda:0')
episode: 109 training return: tensor(347.2737, device='cuda:0')
episode: 110 training return: tensor(104.9542, device='cuda:0')
episode: 111 training return: tensor(370.9320, device='cuda:0')
epoch: 28 test_true_pfm: 3547.0020762478575 sim_pfm: 419.3254943692009
episode: 112 training return: tensor(391.2216, device='cuda:0')
episode: 113 training return: tensor(-663.1965, device='cuda:0')
episode: 114 training return: tensor(441.3364, device='cuda:0')
episode: 115 training return: tensor(347.3301, device='cuda:0')
epoch: 29 test_true_pfm: 3536.612394313135 sim_pfm: 405.1116401173834
episode: 116 training return: tensor(359.5804, device='cuda:0')
episode: 117 training return: tensor(396.2836, device='cuda:0')
episode: 118 training return: tensor(414.5133, device='cuda:0')
episode: 119 training return: tensor(357.1312, device='cuda:0')
epoch: 30 test_true_pfm: 3511.025481386017 sim_pfm: 415.273142112778
episode: 120 training return: tensor(404.8941, device='cuda:0')
episode: 121 training return: tensor(406.5787, device='cuda:0')
episode: 122 training return: tensor(429.5200, device='cuda:0')
episode: 123 training return: tensor(367.1036, device='cuda:0')
epoch: 31 test_true_pfm: 3483.3442812329413 sim_pfm: 413.03342978982255
episode: 124 training return: tensor(320.8660, device='cuda:0')
episode: 125 training return: tensor(330.4215, device='cuda:0')
episode: 126 training return: tensor(390.9534, device='cuda:0')
episode: 127 training return: tensor(381.0064, device='cuda:0')
epoch: 32 test_true_pfm: 3487.9063328530046 sim_pfm: 403.6264717472174
episode: 128 training return: tensor(350.0806, device='cuda:0')
episode: 129 training return: tensor(415.0669, device='cuda:0')
episode: 130 training return: tensor(367.9437, device='cuda:0')
episode: 131 training return: tensor(371.4413, device='cuda:0')
epoch: 33 test_true_pfm: 3495.973984148666 sim_pfm: 404.43685268005356
episode: 132 training return: tensor(395.7422, device='cuda:0')
episode: 133 training return: tensor(373.1093, device='cuda:0')
episode: 134 training return: tensor(387.6046, device='cuda:0')
episode: 135 training return: tensor(414.3522, device='cuda:0')
epoch: 34 test_true_pfm: 3428.6028737225515 sim_pfm: 355.6991359477688
episode: 136 training return: tensor(332.5985, device='cuda:0')
episode: 137 training return: tensor(421.1441, device='cuda:0')
episode: 138 training return: tensor(390.0486, device='cuda:0')
episode: 139 training return: tensor(322.6440, device='cuda:0')
epoch: 35 test_true_pfm: 3597.9651673887915 sim_pfm: 449.38958300386247
episode: 140 training return: tensor(308.0791, device='cuda:0')
episode: 141 training return: tensor(380.7956, device='cuda:0')
episode: 142 training return: tensor(396.2041, device='cuda:0')
episode: 143 training return: tensor(409.5865, device='cuda:0')
epoch: 36 test_true_pfm: 3546.914516770281 sim_pfm: 427.74391077736317
episode: 144 training return: tensor(391.4910, device='cuda:0')
episode: 145 training return: tensor(415.1812, device='cuda:0')
episode: 146 training return: tensor(410.5238, device='cuda:0')
episode: 147 training return: tensor(359.2614, device='cuda:0')
epoch: 37 test_true_pfm: 3510.9380908949956 sim_pfm: 412.4203252430113
episode: 148 training return: tensor(369.0071, device='cuda:0')
episode: 149 training return: tensor(379.0492, device='cuda:0')
episode: 150 training return: tensor(371.1104, device='cuda:0')
episode: 151 training return: tensor(394.7581, device='cuda:0')
epoch: 38 test_true_pfm: 3406.3768769967573 sim_pfm: 337.6706813776788
episode: 152 training return: tensor(365.2314, device='cuda:0')
episode: 153 training return: tensor(362.5800, device='cuda:0')
episode: 154 training return: tensor(441.2604, device='cuda:0')
episode: 155 training return: tensor(401.4967, device='cuda:0')
epoch: 39 test_true_pfm: 3461.3748271865857 sim_pfm: 382.45404756750213
episode: 156 training return: tensor(459.7219, device='cuda:0')
episode: 157 training return: tensor(402.9257, device='cuda:0')
episode: 158 training return: tensor(416.9568, device='cuda:0')
episode: 159 training return: tensor(401.9830, device='cuda:0')
epoch: 40 test_true_pfm: 3612.6117453482634 sim_pfm: 464.79255484987516
episode: 160 training return: tensor(436.0775, device='cuda:0')
episode: 161 training return: tensor(406.2533, device='cuda:0')
episode: 162 training return: tensor(330.1152, device='cuda:0')
episode: 163 training return: tensor(387.4243, device='cuda:0')
epoch: 41 test_true_pfm: 3569.1749144849286 sim_pfm: 447.83140267955605
episode: 164 training return: tensor(410.1962, device='cuda:0')
episode: 165 training return: tensor(384.6365, device='cuda:0')
episode: 166 training return: tensor(444.4337, device='cuda:0')
episode: 167 training return: tensor(414.2879, device='cuda:0')
epoch: 42 test_true_pfm: 3429.893574073214 sim_pfm: 368.03940957712865
episode: 168 training return: tensor(421.8740, device='cuda:0')
episode: 169 training return: tensor(391.9730, device='cuda:0')
episode: 170 training return: tensor(425.3735, device='cuda:0')
episode: 171 training return: tensor(409.3777, device='cuda:0')
epoch: 43 test_true_pfm: 3544.8933729853998 sim_pfm: 426.09057491930434
episode: 172 training return: tensor(400.9793, device='cuda:0')
episode: 173 training return: tensor(406.0309, device='cuda:0')
episode: 174 training return: tensor(407.3755, device='cuda:0')
episode: 175 training return: tensor(430.1545, device='cuda:0')
epoch: 44 test_true_pfm: 3546.304849179041 sim_pfm: 432.13062808736385
episode: 176 training return: tensor(363.6124, device='cuda:0')
episode: 177 training return: tensor(394.1682, device='cuda:0')
episode: 178 training return: tensor(413.5545, device='cuda:0')
episode: 179 training return: tensor(406.2001, device='cuda:0')
epoch: 45 test_true_pfm: 3514.181494308723 sim_pfm: 407.68416126912535
episode: 180 training return: tensor(397.4379, device='cuda:0')
episode: 181 training return: tensor(408.2876, device='cuda:0')
episode: 182 training return: tensor(436.4992, device='cuda:0')
episode: 183 training return: tensor(377.4955, device='cuda:0')
epoch: 46 test_true_pfm: 3413.528192317635 sim_pfm: 354.3952170338792
episode: 184 training return: tensor(391.7264, device='cuda:0')
episode: 185 training return: tensor(436.0028, device='cuda:0')
episode: 186 training return: tensor(365.1760, device='cuda:0')
episode: 187 training return: tensor(437.8888, device='cuda:0')
epoch: 47 test_true_pfm: 3495.5437685374977 sim_pfm: 405.70480681132176
episode: 188 training return: tensor(412.5167, device='cuda:0')
episode: 189 training return: tensor(417.8793, device='cuda:0')
episode: 190 training return: tensor(386.4295, device='cuda:0')
episode: 191 training return: tensor(417.0612, device='cuda:0')
epoch: 48 test_true_pfm: 3638.3209837720638 sim_pfm: 482.95469411625527
episode: 192 training return: tensor(401.7912, device='cuda:0')
episode: 193 training return: tensor(356.0972, device='cuda:0')
episode: 194 training return: tensor(427.0381, device='cuda:0')
episode: 195 training return: tensor(388.9155, device='cuda:0')
epoch: 49 test_true_pfm: 3528.9660565154522 sim_pfm: 427.1265212910269
episode: 196 training return: tensor(406.1922, device='cuda:0')
episode: 197 training return: tensor(431.3077, device='cuda:0')
episode: 198 training return: tensor(411.1677, device='cuda:0')
episode: 199 training return: tensor(421.5037, device='cuda:0')
epoch: 50 test_true_pfm: 3474.3275417959826 sim_pfm: 383.88189882979106
episode: 200 training return: tensor(456.9937, device='cuda:0')
episode: 201 training return: tensor(433.1895, device='cuda:0')
episode: 202 training return: tensor(404.4212, device='cuda:0')
episode: 203 training return: tensor(369.6458, device='cuda:0')
epoch: 51 test_true_pfm: 3474.611169060665 sim_pfm: 392.3702045128836
episode: 204 training return: tensor(416.6351, device='cuda:0')
episode: 205 training return: tensor(391.1871, device='cuda:0')
episode: 206 training return: tensor(393.3027, device='cuda:0')
episode: 207 training return: tensor(422.6376, device='cuda:0')
epoch: 52 test_true_pfm: 3552.795052610374 sim_pfm: 446.6202362366312
episode: 208 training return: tensor(353.0322, device='cuda:0')
episode: 209 training return: tensor(389.5111, device='cuda:0')
episode: 210 training return: tensor(400.3037, device='cuda:0')
episode: 211 training return: tensor(416.7165, device='cuda:0')
epoch: 53 test_true_pfm: 3507.3182824432843 sim_pfm: 418.42033822655986
episode: 212 training return: tensor(402.2159, device='cuda:0')
episode: 213 training return: tensor(404.2813, device='cuda:0')
episode: 214 training return: tensor(386.8115, device='cuda:0')
episode: 215 training return: tensor(397.3437, device='cuda:0')
epoch: 54 test_true_pfm: 3523.455673927359 sim_pfm: 420.1880472887812
episode: 216 training return: tensor(426.3430, device='cuda:0')
episode: 217 training return: tensor(426.5268, device='cuda:0')
episode: 218 training return: tensor(436.1333, device='cuda:0')
episode: 219 training return: tensor(460.4317, device='cuda:0')
epoch: 55 test_true_pfm: 3470.1346693936152 sim_pfm: 393.2023483750527
episode: 220 training return: tensor(449.6829, device='cuda:0')
episode: 221 training return: tensor(356.6512, device='cuda:0')
episode: 222 training return: tensor(417.3094, device='cuda:0')
episode: 223 training return: tensor(402.9538, device='cuda:0')
epoch: 56 test_true_pfm: 3479.6989489644043 sim_pfm: 390.77199368030415
episode: 224 training return: tensor(425.0352, device='cuda:0')
episode: 225 training return: tensor(419.2320, device='cuda:0')
episode: 226 training return: tensor(453.5088, device='cuda:0')
episode: 227 training return: tensor(420.3180, device='cuda:0')
epoch: 57 test_true_pfm: 3476.301041002896 sim_pfm: 400.56925054616295
episode: 228 training return: tensor(372.0419, device='cuda:0')
episode: 229 training return: tensor(393.7210, device='cuda:0')
episode: 230 training return: tensor(405.7763, device='cuda:0')
episode: 231 training return: tensor(418.8991, device='cuda:0')
epoch: 58 test_true_pfm: 3524.6652698050602 sim_pfm: 427.80842125755345
episode: 232 training return: tensor(440.1049, device='cuda:0')
episode: 233 training return: tensor(436.8479, device='cuda:0')
episode: 234 training return: tensor(403.4114, device='cuda:0')
episode: 235 training return: tensor(432.6130, device='cuda:0')
epoch: 59 test_true_pfm: 3563.4876357358103 sim_pfm: 440.59038910417195
episode: 236 training return: tensor(409.2710, device='cuda:0')
episode: 237 training return: tensor(406.4110, device='cuda:0')
episode: 238 training return: tensor(423.4572, device='cuda:0')
episode: 239 training return: tensor(426.0182, device='cuda:0')
epoch: 60 test_true_pfm: 3581.9526333826566 sim_pfm: 455.0089404332296
episode: 240 training return: tensor(421.2312, device='cuda:0')
episode: 241 training return: tensor(393.6817, device='cuda:0')
episode: 242 training return: tensor(403.8859, device='cuda:0')
episode: 243 training return: tensor(401.1426, device='cuda:0')
epoch: 61 test_true_pfm: 3514.542146645455 sim_pfm: 420.56084809217526
episode: 244 training return: tensor(448.6445, device='cuda:0')
episode: 245 training return: tensor(388.1257, device='cuda:0')
episode: 246 training return: tensor(409.9596, device='cuda:0')
episode: 247 training return: tensor(419.9469, device='cuda:0')
epoch: 62 test_true_pfm: 3478.320774048237 sim_pfm: 407.47233214582474
episode: 248 training return: tensor(407.5082, device='cuda:0')
episode: 249 training return: tensor(416.4923, device='cuda:0')
episode: 250 training return: tensor(385.4471, device='cuda:0')
episode: 251 training return: tensor(467.3475, device='cuda:0')
epoch: 63 test_true_pfm: 3513.609998884689 sim_pfm: 417.13981660884264
episode: 252 training return: tensor(460.5307, device='cuda:0')
episode: 253 training return: tensor(373.6224, device='cuda:0')
episode: 254 training return: tensor(368.7220, device='cuda:0')
episode: 255 training return: tensor(415.2759, device='cuda:0')
epoch: 64 test_true_pfm: 3515.737175450562 sim_pfm: 412.05889103173587
episode: 256 training return: tensor(440.8566, device='cuda:0')
episode: 257 training return: tensor(402.0079, device='cuda:0')
episode: 258 training return: tensor(399.8909, device='cuda:0')
episode: 259 training return: tensor(387.6360, device='cuda:0')
epoch: 65 test_true_pfm: 3508.4128019209643 sim_pfm: 419.3723720480727
episode: 260 training return: tensor(498.7549, device='cuda:0')
episode: 261 training return: tensor(202.0016, device='cuda:0')
episode: 262 training return: tensor(411.6924, device='cuda:0')
episode: 263 training return: tensor(408.2520, device='cuda:0')
epoch: 66 test_true_pfm: 3524.0988608677885 sim_pfm: 411.82202809715335
episode: 264 training return: tensor(429.9866, device='cuda:0')
episode: 265 training return: tensor(420.5821, device='cuda:0')
episode: 266 training return: tensor(440.2536, device='cuda:0')
episode: 267 training return: tensor(394.8594, device='cuda:0')
epoch: 67 test_true_pfm: 3544.8342854528105 sim_pfm: 440.807137522342
episode: 268 training return: tensor(445.1787, device='cuda:0')
episode: 269 training return: tensor(389.3325, device='cuda:0')
episode: 270 training return: tensor(460.8523, device='cuda:0')
episode: 271 training return: tensor(450.0273, device='cuda:0')
epoch: 68 test_true_pfm: 3550.9486732149744 sim_pfm: 441.65865022638656
episode: 272 training return: tensor(391.3618, device='cuda:0')
episode: 273 training return: tensor(442.9406, device='cuda:0')
episode: 274 training return: tensor(424.6819, device='cuda:0')
episode: 275 training return: tensor(420.9364, device='cuda:0')
epoch: 69 test_true_pfm: 3471.8123419920253 sim_pfm: 392.81362481954665
episode: 276 training return: tensor(409.7226, device='cuda:0')
episode: 277 training return: tensor(400.4861, device='cuda:0')
episode: 278 training return: tensor(423.4320, device='cuda:0')
episode: 279 training return: tensor(407.4093, device='cuda:0')
epoch: 70 test_true_pfm: 3519.6949203396357 sim_pfm: 435.6601346941122
episode: 280 training return: tensor(393.8763, device='cuda:0')
episode: 281 training return: tensor(377.5818, device='cuda:0')
episode: 282 training return: tensor(419.2879, device='cuda:0')
episode: 283 training return: tensor(408.9894, device='cuda:0')
epoch: 71 test_true_pfm: 3540.6308716458757 sim_pfm: 428.9363153464316
episode: 284 training return: tensor(443.6919, device='cuda:0')
episode: 285 training return: tensor(491.9828, device='cuda:0')
episode: 286 training return: tensor(435.7331, device='cuda:0')
episode: 287 training return: tensor(401.5646, device='cuda:0')
epoch: 72 test_true_pfm: 3552.997609716543 sim_pfm: 436.60072684046463
episode: 288 training return: tensor(408.7585, device='cuda:0')
episode: 289 training return: tensor(389.2401, device='cuda:0')
episode: 290 training return: tensor(392.9669, device='cuda:0')
episode: 291 training return: tensor(434.8322, device='cuda:0')
epoch: 73 test_true_pfm: 3557.444486435957 sim_pfm: 438.12589220471756
episode: 292 training return: tensor(418.6495, device='cuda:0')
episode: 293 training return: tensor(392.1429, device='cuda:0')
episode: 294 training return: tensor(386.3171, device='cuda:0')
episode: 295 training return: tensor(439.7564, device='cuda:0')
epoch: 74 test_true_pfm: 3490.939640564082 sim_pfm: 400.92449447882245
episode: 296 training return: tensor(404.3241, device='cuda:0')
episode: 297 training return: tensor(387.0887, device='cuda:0')
episode: 298 training return: tensor(403.4585, device='cuda:0')
episode: 299 training return: tensor(396.0266, device='cuda:0')
epoch: 75 test_true_pfm: 3604.311278054362 sim_pfm: 462.2237791319688
episode: 300 training return: tensor(420.4234, device='cuda:0')
episode: 301 training return: tensor(408.2578, device='cuda:0')
episode: 302 training return: tensor(448.0652, device='cuda:0')
episode: 303 training return: tensor(384.6870, device='cuda:0')
epoch: 76 test_true_pfm: 3485.1498845502156 sim_pfm: 392.93323728969943
episode: 304 training return: tensor(432.6662, device='cuda:0')
episode: 305 training return: tensor(445.6133, device='cuda:0')
episode: 306 training return: tensor(442.6026, device='cuda:0')
episode: 307 training return: tensor(417.8224, device='cuda:0')
epoch: 77 test_true_pfm: 3497.5895093226113 sim_pfm: 405.9704113988749
episode: 308 training return: tensor(449.3584, device='cuda:0')
episode: 309 training return: tensor(419.9610, device='cuda:0')
episode: 310 training return: tensor(444.7294, device='cuda:0')
episode: 311 training return: tensor(451.7905, device='cuda:0')
epoch: 78 test_true_pfm: 3580.02391167642 sim_pfm: 449.10338338156
episode: 312 training return: tensor(430.0098, device='cuda:0')
episode: 313 training return: tensor(409.6052, device='cuda:0')
episode: 314 training return: tensor(429.8004, device='cuda:0')
episode: 315 training return: tensor(429.8371, device='cuda:0')
epoch: 79 test_true_pfm: 3549.806250924778 sim_pfm: 435.3652339390537
episode: 316 training return: tensor(416.4653, device='cuda:0')
episode: 317 training return: tensor(398.3582, device='cuda:0')
episode: 318 training return: tensor(442.2819, device='cuda:0')
episode: 319 training return: tensor(401.2360, device='cuda:0')
epoch: 80 test_true_pfm: 3524.4061625113245 sim_pfm: 414.7365760975711
episode: 320 training return: tensor(410.6172, device='cuda:0')
episode: 321 training return: tensor(424.0063, device='cuda:0')
episode: 322 training return: tensor(441.2640, device='cuda:0')
episode: 323 training return: tensor(418.4182, device='cuda:0')
epoch: 81 test_true_pfm: 3571.10557293434 sim_pfm: 435.13241068209754
episode: 324 training return: tensor(437.8574, device='cuda:0')
episode: 325 training return: tensor(433.4272, device='cuda:0')
episode: 326 training return: tensor(409.7117, device='cuda:0')
episode: 327 training return: tensor(374.5623, device='cuda:0')
epoch: 82 test_true_pfm: 3545.3355325389834 sim_pfm: 438.5813997104803
episode: 328 training return: tensor(25.2935, device='cuda:0')
episode: 329 training return: tensor(447.3955, device='cuda:0')
episode: 330 training return: tensor(439.2065, device='cuda:0')
episode: 331 training return: tensor(431.1713, device='cuda:0')
epoch: 83 test_true_pfm: 3579.9167625253717 sim_pfm: 456.42817099248833
episode: 332 training return: tensor(443.5981, device='cuda:0')
episode: 333 training return: tensor(411.8704, device='cuda:0')
episode: 334 training return: tensor(422.0729, device='cuda:0')
episode: 335 training return: tensor(394.7807, device='cuda:0')
epoch: 84 test_true_pfm: 3493.2656116762532 sim_pfm: 402.36808142629644
episode: 336 training return: tensor(414.8309, device='cuda:0')
episode: 337 training return: tensor(443.7583, device='cuda:0')
episode: 338 training return: tensor(419.0908, device='cuda:0')
episode: 339 training return: tensor(418.7492, device='cuda:0')
epoch: 85 test_true_pfm: 3575.6300482953575 sim_pfm: 448.02787175793975
episode: 340 training return: tensor(413.4737, device='cuda:0')
episode: 341 training return: tensor(406.4495, device='cuda:0')
episode: 342 training return: tensor(410.0102, device='cuda:0')
episode: 343 training return: tensor(420.1162, device='cuda:0')
epoch: 86 test_true_pfm: 3535.338424836465 sim_pfm: 427.69641790740815
episode: 344 training return: tensor(427.9766, device='cuda:0')
episode: 345 training return: tensor(433.9352, device='cuda:0')
episode: 346 training return: tensor(412.6175, device='cuda:0')
episode: 347 training return: tensor(441.5807, device='cuda:0')
epoch: 87 test_true_pfm: 3518.24866172909 sim_pfm: 418.567645210084
episode: 348 training return: tensor(445.4509, device='cuda:0')
episode: 349 training return: tensor(401.3394, device='cuda:0')
episode: 350 training return: tensor(414.3053, device='cuda:0')
episode: 351 training return: tensor(409.1159, device='cuda:0')
epoch: 88 test_true_pfm: 3545.6799123664155 sim_pfm: 431.04177551256726
episode: 352 training return: tensor(425.9200, device='cuda:0')
episode: 353 training return: tensor(428.1940, device='cuda:0')
episode: 354 training return: tensor(457.0863, device='cuda:0')
episode: 355 training return: tensor(420.8352, device='cuda:0')
epoch: 89 test_true_pfm: 3560.501410033574 sim_pfm: 442.17444964773796
episode: 356 training return: tensor(416.5078, device='cuda:0')
episode: 357 training return: tensor(402.4826, device='cuda:0')
episode: 358 training return: tensor(424.5558, device='cuda:0')
episode: 359 training return: tensor(404.6591, device='cuda:0')
epoch: 90 test_true_pfm: 3503.996991424963 sim_pfm: 409.2485577623399
episode: 360 training return: tensor(432.8707, device='cuda:0')
episode: 361 training return: tensor(397.6719, device='cuda:0')
episode: 362 training return: tensor(412.1160, device='cuda:0')
episode: 363 training return: tensor(403.5903, device='cuda:0')
epoch: 91 test_true_pfm: 3528.5177729335323 sim_pfm: 428.60781154892175
episode: 364 training return: tensor(454.2304, device='cuda:0')
episode: 365 training return: tensor(407.3573, device='cuda:0')
episode: 366 training return: tensor(369.3364, device='cuda:0')
episode: 367 training return: tensor(434.5812, device='cuda:0')
epoch: 92 test_true_pfm: 3565.9659339432 sim_pfm: 445.5788957752811
episode: 368 training return: tensor(410.9349, device='cuda:0')
episode: 369 training return: tensor(393.3476, device='cuda:0')
episode: 370 training return: tensor(427.1638, device='cuda:0')
episode: 371 training return: tensor(424.8762, device='cuda:0')
epoch: 93 test_true_pfm: 3585.055927910466 sim_pfm: 461.21580540650757
episode: 372 training return: tensor(403.1964, device='cuda:0')
episode: 373 training return: tensor(422.0638, device='cuda:0')
episode: 374 training return: tensor(435.3746, device='cuda:0')
episode: 375 training return: tensor(419.0096, device='cuda:0')
epoch: 94 test_true_pfm: 3499.44163677375 sim_pfm: 406.2949939339014
episode: 376 training return: tensor(426.1728, device='cuda:0')
episode: 377 training return: tensor(416.2177, device='cuda:0')
episode: 378 training return: tensor(436.1669, device='cuda:0')
episode: 379 training return: tensor(434.3937, device='cuda:0')
epoch: 95 test_true_pfm: 3559.779552802282 sim_pfm: 439.12039498076774
episode: 380 training return: tensor(418.2375, device='cuda:0')
episode: 381 training return: tensor(418.6536, device='cuda:0')
episode: 382 training return: tensor(428.9294, device='cuda:0')
episode: 383 training return: tensor(431.8687, device='cuda:0')
epoch: 96 test_true_pfm: 3522.596646631249 sim_pfm: 425.8118886424927
episode: 384 training return: tensor(437.9923, device='cuda:0')
episode: 385 training return: tensor(409.8108, device='cuda:0')
episode: 386 training return: tensor(421.9956, device='cuda:0')
episode: 387 training return: tensor(417.1762, device='cuda:0')
epoch: 97 test_true_pfm: 3532.620728801888 sim_pfm: 427.3981883773813
episode: 388 training return: tensor(398.4439, device='cuda:0')
episode: 389 training return: tensor(430.6032, device='cuda:0')
episode: 390 training return: tensor(405.8156, device='cuda:0')
episode: 391 training return: tensor(328.3417, device='cuda:0')
epoch: 98 test_true_pfm: 3557.8471865390115 sim_pfm: 439.66739795087295
episode: 392 training return: tensor(473.8734, device='cuda:0')
episode: 393 training return: tensor(430.3285, device='cuda:0')
episode: 394 training return: tensor(431.7739, device='cuda:0')
episode: 395 training return: tensor(462.5369, device='cuda:0')
epoch: 99 test_true_pfm: 3521.652578674053 sim_pfm: 419.1348472528625
episode: 396 training return: tensor(414.5818, device='cuda:0')
episode: 397 training return: tensor(456.0627, device='cuda:0')
episode: 398 training return: tensor(403.2983, device='cuda:0')
episode: 399 training return: tensor(420.3377, device='cuda:0')
epoch: 100 test_true_pfm: 3530.974350681929 sim_pfm: 438.55705443030456
episode: 400 training return: tensor(431.5811, device='cuda:0')
episode: 401 training return: tensor(416.0774, device='cuda:0')
episode: 402 training return: tensor(418.3506, device='cuda:0')
episode: 403 training return: tensor(414.2398, device='cuda:0')
epoch: 101 test_true_pfm: 3546.525664157212 sim_pfm: 435.11615092487773
episode: 404 training return: tensor(424.0958, device='cuda:0')
episode: 405 training return: tensor(433.0011, device='cuda:0')
episode: 406 training return: tensor(430.4255, device='cuda:0')
episode: 407 training return: tensor(424.1700, device='cuda:0')
epoch: 102 test_true_pfm: 3545.7663785194623 sim_pfm: 430.60339226127445
episode: 408 training return: tensor(407.9007, device='cuda:0')
episode: 409 training return: tensor(432.5380, device='cuda:0')
episode: 410 training return: tensor(426.5631, device='cuda:0')
episode: 411 training return: tensor(438.1966, device='cuda:0')
epoch: 103 test_true_pfm: 3536.8646113361033 sim_pfm: 437.5837729140573
episode: 412 training return: tensor(445.4518, device='cuda:0')
episode: 413 training return: tensor(411.7992, device='cuda:0')
episode: 414 training return: tensor(410.7349, device='cuda:0')
episode: 415 training return: tensor(434.7921, device='cuda:0')
epoch: 104 test_true_pfm: 3578.6710999422417 sim_pfm: 450.911464210328
episode: 416 training return: tensor(440.1849, device='cuda:0')
episode: 417 training return: tensor(432.8394, device='cuda:0')
episode: 418 training return: tensor(404.5899, device='cuda:0')
episode: 419 training return: tensor(441.4082, device='cuda:0')
epoch: 105 test_true_pfm: 3573.9023768122224 sim_pfm: 451.2962129697553
episode: 420 training return: tensor(422.2042, device='cuda:0')
episode: 421 training return: tensor(418.3878, device='cuda:0')
episode: 422 training return: tensor(428.1571, device='cuda:0')
episode: 423 training return: tensor(428.1154, device='cuda:0')
epoch: 106 test_true_pfm: 3547.6581159134694 sim_pfm: 435.57389800755
episode: 424 training return: tensor(428.3867, device='cuda:0')
episode: 425 training return: tensor(424.0048, device='cuda:0')
episode: 426 training return: tensor(419.8963, device='cuda:0')
episode: 427 training return: tensor(416.2119, device='cuda:0')
epoch: 107 test_true_pfm: 3566.006938162973 sim_pfm: 450.201218639384
episode: 428 training return: tensor(416.0114, device='cuda:0')
episode: 429 training return: tensor(407.2183, device='cuda:0')
episode: 430 training return: tensor(420.2753, device='cuda:0')
episode: 431 training return: tensor(382.5868, device='cuda:0')
epoch: 108 test_true_pfm: 3549.5838873042 sim_pfm: 440.5378321291258
episode: 432 training return: tensor(431.2142, device='cuda:0')
episode: 433 training return: tensor(400.1550, device='cuda:0')
episode: 434 training return: tensor(420.4100, device='cuda:0')
episode: 435 training return: tensor(471.2885, device='cuda:0')
epoch: 109 test_true_pfm: 3542.6831305285705 sim_pfm: 436.92914961171726
episode: 436 training return: tensor(421.5698, device='cuda:0')
episode: 437 training return: tensor(449.8161, device='cuda:0')
episode: 438 training return: tensor(424.3337, device='cuda:0')
episode: 439 training return: tensor(425.4550, device='cuda:0')
epoch: 110 test_true_pfm: 3592.1580247083234 sim_pfm: 458.00916586393333
episode: 440 training return: tensor(445.0190, device='cuda:0')
episode: 441 training return: tensor(404.4858, device='cuda:0')
episode: 442 training return: tensor(446.8671, device='cuda:0')
episode: 443 training return: tensor(435.5023, device='cuda:0')
epoch: 111 test_true_pfm: 3594.583296082887 sim_pfm: 462.51688156669843
episode: 444 training return: tensor(445.3230, device='cuda:0')
episode: 445 training return: tensor(419.9990, device='cuda:0')
episode: 446 training return: tensor(425.7261, device='cuda:0')
episode: 447 training return: tensor(426.4392, device='cuda:0')
epoch: 112 test_true_pfm: 3548.075475278116 sim_pfm: 433.5022055145625
episode: 448 training return: tensor(445.4641, device='cuda:0')
episode: 449 training return: tensor(426.9464, device='cuda:0')
episode: 450 training return: tensor(446.3979, device='cuda:0')
episode: 451 training return: tensor(459.8600, device='cuda:0')
epoch: 113 test_true_pfm: 3524.583594855723 sim_pfm: 420.92502190285205
episode: 452 training return: tensor(435.0546, device='cuda:0')
episode: 453 training return: tensor(419.2086, device='cuda:0')
episode: 454 training return: tensor(410.6101, device='cuda:0')
episode: 455 training return: tensor(452.6625, device='cuda:0')
epoch: 114 test_true_pfm: 3569.3434317932083 sim_pfm: 446.20418888439116
episode: 456 training return: tensor(432.3235, device='cuda:0')
episode: 457 training return: tensor(414.6489, device='cuda:0')
episode: 458 training return: tensor(426.2745, device='cuda:0')
episode: 459 training return: tensor(447.5757, device='cuda:0')
epoch: 115 test_true_pfm: 3582.5625688440764 sim_pfm: 464.6169331842878
episode: 460 training return: tensor(452.3438, device='cuda:0')
episode: 461 training return: tensor(430.6776, device='cuda:0')
episode: 462 training return: tensor(438.3669, device='cuda:0')
episode: 463 training return: tensor(428.7591, device='cuda:0')
epoch: 116 test_true_pfm: 3574.283085366014 sim_pfm: 458.2595203385863
episode: 464 training return: tensor(445.1113, device='cuda:0')
episode: 465 training return: tensor(417.4340, device='cuda:0')
episode: 466 training return: tensor(445.8398, device='cuda:0')
episode: 467 training return: tensor(406.0364, device='cuda:0')
epoch: 117 test_true_pfm: 3556.547341950867 sim_pfm: 444.60609993097995
episode: 468 training return: tensor(424.7213, device='cuda:0')
episode: 469 training return: tensor(441.7272, device='cuda:0')
episode: 470 training return: tensor(409.2029, device='cuda:0')
episode: 471 training return: tensor(407.8142, device='cuda:0')
epoch: 118 test_true_pfm: 3501.1498664978913 sim_pfm: 416.3200680091298
episode: 472 training return: tensor(413.8759, device='cuda:0')
episode: 473 training return: tensor(430.5626, device='cuda:0')
episode: 474 training return: tensor(426.2888, device='cuda:0')
episode: 475 training return: tensor(449.8067, device='cuda:0')
epoch: 119 test_true_pfm: 3575.9231610677416 sim_pfm: 449.6184824805047
episode: 476 training return: tensor(446.2946, device='cuda:0')
episode: 477 training return: tensor(425.5975, device='cuda:0')
episode: 478 training return: tensor(397.4727, device='cuda:0')
episode: 479 training return: tensor(424.1541, device='cuda:0')
epoch: 120 test_true_pfm: 3600.772542972154 sim_pfm: 465.36406006799854
episode: 480 training return: tensor(447.6920, device='cuda:0')
episode: 481 training return: tensor(439.9832, device='cuda:0')
episode: 482 training return: tensor(426.9247, device='cuda:0')
episode: 483 training return: tensor(428.3395, device='cuda:0')
epoch: 121 test_true_pfm: 3578.004510469269 sim_pfm: 454.2732601389677
episode: 484 training return: tensor(436.5613, device='cuda:0')
episode: 485 training return: tensor(437.4547, device='cuda:0')
episode: 486 training return: tensor(413.4911, device='cuda:0')
episode: 487 training return: tensor(433.0255, device='cuda:0')
epoch: 122 test_true_pfm: 3559.357919327009 sim_pfm: 440.5441974166315
episode: 488 training return: tensor(413.2271, device='cuda:0')
episode: 489 training return: tensor(426.0712, device='cuda:0')
episode: 490 training return: tensor(416.0863, device='cuda:0')
episode: 491 training return: tensor(427.1801, device='cuda:0')
epoch: 123 test_true_pfm: 3552.183245247912 sim_pfm: 438.3109278504271
episode: 492 training return: tensor(432.6004, device='cuda:0')
episode: 493 training return: tensor(443.6969, device='cuda:0')
episode: 494 training return: tensor(436.8097, device='cuda:0')
episode: 495 training return: tensor(415.7029, device='cuda:0')
epoch: 124 test_true_pfm: 3588.65239019682 sim_pfm: 461.84890550142154
episode: 496 training return: tensor(416.4164, device='cuda:0')
episode: 497 training return: tensor(431.6162, device='cuda:0')
episode: 498 training return: tensor(425.1799, device='cuda:0')
episode: 499 training return: tensor(444.7376, device='cuda:0')
epoch: 125 test_true_pfm: 3567.1571228839553 sim_pfm: 438.94515291795443
episode: 500 training return: tensor(409.6030, device='cuda:0')
episode: 501 training return: tensor(449.0603, device='cuda:0')
episode: 502 training return: tensor(456.2610, device='cuda:0')
episode: 503 training return: tensor(432.4545, device='cuda:0')
epoch: 126 test_true_pfm: 3584.8457201156866 sim_pfm: 451.4330581529066
episode: 504 training return: tensor(440.1796, device='cuda:0')
episode: 505 training return: tensor(438.6068, device='cuda:0')
episode: 506 training return: tensor(481.1127, device='cuda:0')
episode: 507 training return: tensor(433.1486, device='cuda:0')
epoch: 127 test_true_pfm: 3555.271295536219 sim_pfm: 435.59560306865023
episode: 508 training return: tensor(428.4767, device='cuda:0')
episode: 509 training return: tensor(448.4439, device='cuda:0')
episode: 510 training return: tensor(478.5916, device='cuda:0')
episode: 511 training return: tensor(427.5132, device='cuda:0')
epoch: 128 test_true_pfm: 3579.4998652571035 sim_pfm: 447.82377242154325
episode: 512 training return: tensor(419.0104, device='cuda:0')
episode: 513 training return: tensor(411.5497, device='cuda:0')
episode: 514 training return: tensor(448.1960, device='cuda:0')
episode: 515 training return: tensor(430.5977, device='cuda:0')
epoch: 129 test_true_pfm: 3595.2178730739847 sim_pfm: 466.89340737485327
episode: 516 training return: tensor(465.9154, device='cuda:0')
episode: 517 training return: tensor(432.3988, device='cuda:0')
episode: 518 training return: tensor(433.4740, device='cuda:0')
episode: 519 training return: tensor(430.1338, device='cuda:0')
epoch: 130 test_true_pfm: 3567.608859506265 sim_pfm: 449.9327535206976
episode: 520 training return: tensor(442.1088, device='cuda:0')
episode: 521 training return: tensor(425.2636, device='cuda:0')
episode: 522 training return: tensor(387.9594, device='cuda:0')
episode: 523 training return: tensor(429.2432, device='cuda:0')
epoch: 131 test_true_pfm: 3560.175322360063 sim_pfm: 444.92790183560766
episode: 524 training return: tensor(436.0309, device='cuda:0')
episode: 525 training return: tensor(421.2789, device='cuda:0')
episode: 526 training return: tensor(433.7348, device='cuda:0')
episode: 527 training return: tensor(425.1299, device='cuda:0')
epoch: 132 test_true_pfm: 3557.367249494746 sim_pfm: 441.049824968155
episode: 528 training return: tensor(437.4254, device='cuda:0')
episode: 529 training return: tensor(418.9240, device='cuda:0')
episode: 530 training return: tensor(443.3639, device='cuda:0')
episode: 531 training return: tensor(440.7671, device='cuda:0')
epoch: 133 test_true_pfm: 3610.5002666824134 sim_pfm: 465.90036361284245
episode: 532 training return: tensor(463.3125, device='cuda:0')
episode: 533 training return: tensor(443.8958, device='cuda:0')
episode: 534 training return: tensor(423.9439, device='cuda:0')
episode: 535 training return: tensor(441.0124, device='cuda:0')
epoch: 134 test_true_pfm: 3564.142439244606 sim_pfm: 460.9115271599342
episode: 536 training return: tensor(431.2547, device='cuda:0')
episode: 537 training return: tensor(473.5087, device='cuda:0')
episode: 538 training return: tensor(454.4255, device='cuda:0')
episode: 539 training return: tensor(448.9744, device='cuda:0')
epoch: 135 test_true_pfm: 3618.5049620415357 sim_pfm: 473.96155281285365
episode: 540 training return: tensor(465.4152, device='cuda:0')
episode: 541 training return: tensor(456.6988, device='cuda:0')
episode: 542 training return: tensor(454.9629, device='cuda:0')
episode: 543 training return: tensor(433.9077, device='cuda:0')
epoch: 136 test_true_pfm: 3575.560787294222 sim_pfm: 458.0164657490871
episode: 544 training return: tensor(448.2552, device='cuda:0')
episode: 545 training return: tensor(411.6234, device='cuda:0')
episode: 546 training return: tensor(429.0569, device='cuda:0')
episode: 547 training return: tensor(448.4362, device='cuda:0')
epoch: 137 test_true_pfm: 3598.9150650303304 sim_pfm: 460.0102243835572
episode: 548 training return: tensor(451.7585, device='cuda:0')
episode: 549 training return: tensor(425.1056, device='cuda:0')
episode: 550 training return: tensor(426.8528, device='cuda:0')
episode: 551 training return: tensor(441.0086, device='cuda:0')
epoch: 138 test_true_pfm: 3575.892407712087 sim_pfm: 456.11763232802815
episode: 552 training return: tensor(425.5106, device='cuda:0')
episode: 553 training return: tensor(465.5364, device='cuda:0')
episode: 554 training return: tensor(412.2436, device='cuda:0')
episode: 555 training return: tensor(446.5380, device='cuda:0')
epoch: 139 test_true_pfm: 3574.8567802222933 sim_pfm: 453.7699455722856
episode: 556 training return: tensor(426.8439, device='cuda:0')
episode: 557 training return: tensor(413.6006, device='cuda:0')
episode: 558 training return: tensor(424.5780, device='cuda:0')
episode: 559 training return: tensor(443.4116, device='cuda:0')
epoch: 140 test_true_pfm: 3598.26218209957 sim_pfm: 461.01241952439887
episode: 560 training return: tensor(448.9532, device='cuda:0')
episode: 561 training return: tensor(457.4895, device='cuda:0')
episode: 562 training return: tensor(458.9895, device='cuda:0')
episode: 563 training return: tensor(465.9267, device='cuda:0')
epoch: 141 test_true_pfm: 3584.6040097759815 sim_pfm: 458.5264008586334
episode: 564 training return: tensor(433.5654, device='cuda:0')
episode: 565 training return: tensor(452.2971, device='cuda:0')
episode: 566 training return: tensor(394.7146, device='cuda:0')
episode: 567 training return: tensor(429.1597, device='cuda:0')
epoch: 142 test_true_pfm: 3597.460713297136 sim_pfm: 460.7193517706085
episode: 568 training return: tensor(427.2318, device='cuda:0')
episode: 569 training return: tensor(425.9132, device='cuda:0')
episode: 570 training return: tensor(424.9455, device='cuda:0')
episode: 571 training return: tensor(450.9263, device='cuda:0')
epoch: 143 test_true_pfm: 3574.6061508644584 sim_pfm: 452.1636899037015
episode: 572 training return: tensor(443.9881, device='cuda:0')
episode: 573 training return: tensor(435.6773, device='cuda:0')
episode: 574 training return: tensor(423.6119, device='cuda:0')
episode: 575 training return: tensor(425.6974, device='cuda:0')
epoch: 144 test_true_pfm: 3610.4983421949255 sim_pfm: 472.30410655490897
episode: 576 training return: tensor(444.9868, device='cuda:0')
episode: 577 training return: tensor(404.1093, device='cuda:0')
episode: 578 training return: tensor(443.9685, device='cuda:0')
episode: 579 training return: tensor(400.3591, device='cuda:0')
epoch: 145 test_true_pfm: 3579.6565543309443 sim_pfm: 458.19068976778846
episode: 580 training return: tensor(425.4558, device='cuda:0')
episode: 581 training return: tensor(393.4251, device='cuda:0')
episode: 582 training return: tensor(442.3418, device='cuda:0')
episode: 583 training return: tensor(429.1480, device='cuda:0')
epoch: 146 test_true_pfm: 3572.513231403547 sim_pfm: 451.2600072415274
episode: 584 training return: tensor(439.6875, device='cuda:0')
episode: 585 training return: tensor(444.9225, device='cuda:0')
episode: 586 training return: tensor(463.9878, device='cuda:0')
episode: 587 training return: tensor(433.2659, device='cuda:0')
epoch: 147 test_true_pfm: 3578.091021342598 sim_pfm: 458.6512636247401
episode: 588 training return: tensor(428.5046, device='cuda:0')
episode: 589 training return: tensor(426.6728, device='cuda:0')
episode: 590 training return: tensor(462.6720, device='cuda:0')
episode: 591 training return: tensor(421.4743, device='cuda:0')
epoch: 148 test_true_pfm: 3609.318646992449 sim_pfm: 472.3822264985647
episode: 592 training return: tensor(443.7147, device='cuda:0')
episode: 593 training return: tensor(432.6749, device='cuda:0')
episode: 594 training return: tensor(449.7848, device='cuda:0')
episode: 595 training return: tensor(455.0315, device='cuda:0')
epoch: 149 test_true_pfm: 3592.9097517405394 sim_pfm: 458.93504553299863
episode: 596 training return: tensor(416.9897, device='cuda:0')
episode: 597 training return: tensor(413.9633, device='cuda:0')
episode: 598 training return: tensor(427.4081, device='cuda:0')
episode: 599 training return: tensor(445.7260, device='cuda:0')
epoch: 150 test_true_pfm: 3581.1456797134647 sim_pfm: 461.10115509980824
