['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '3', '--data', '100000', '--regu', '0.3']
2727.19671285111
episode: 0 training return: tensor(218.3306, device='cuda:0')
episode: 1 training return: tensor(226.0859, device='cuda:0')
episode: 2 training return: tensor(244.2370, device='cuda:0')
episode: 3 training return: tensor(-68.1720, device='cuda:0')
epoch: 1 test_true_pfm: 3178.274147114218 sim_pfm: -273.3066517462915
episode: 4 training return: tensor(332.0500, device='cuda:0')
episode: 5 training return: tensor(305.3493, device='cuda:0')
episode: 6 training return: tensor(-300.0952, device='cuda:0')
episode: 7 training return: tensor(289.9123, device='cuda:0')
epoch: 2 test_true_pfm: 2779.0193386790847 sim_pfm: 58.76212748968586
episode: 8 training return: tensor(-44.6430, device='cuda:0')
episode: 9 training return: tensor(-215.6237, device='cuda:0')
episode: 10 training return: tensor(-588.5515, device='cuda:0')
episode: 11 training return: tensor(367.9330, device='cuda:0')
epoch: 3 test_true_pfm: 2917.9394910638425 sim_pfm: 237.38395527602793
episode: 12 training return: tensor(-553.6190, device='cuda:0')
episode: 13 training return: tensor(454.0562, device='cuda:0')
episode: 14 training return: tensor(258.4404, device='cuda:0')
episode: 15 training return: tensor(428.3043, device='cuda:0')
epoch: 4 test_true_pfm: 2834.3292992039555 sim_pfm: 333.8884392482869
episode: 16 training return: tensor(65.3311, device='cuda:0')
episode: 17 training return: tensor(-79.6302, device='cuda:0')
episode: 18 training return: tensor(107.4274, device='cuda:0')
episode: 19 training return: tensor(168.0930, device='cuda:0')
epoch: 5 test_true_pfm: 2004.5841988572654 sim_pfm: -104.32992889736003
episode: 20 training return: tensor(332.9851, device='cuda:0')
episode: 21 training return: tensor(365.8375, device='cuda:0')
episode: 22 training return: tensor(30.2903, device='cuda:0')
episode: 23 training return: tensor(329.4072, device='cuda:0')
epoch: 6 test_true_pfm: 2002.2382088846898 sim_pfm: 546.9598450303989
episode: 24 training return: tensor(54.4222, device='cuda:0')
episode: 25 training return: tensor(213.8076, device='cuda:0')
episode: 26 training return: tensor(362.9577, device='cuda:0')
episode: 27 training return: tensor(362.3499, device='cuda:0')
epoch: 7 test_true_pfm: 3502.45751659455 sim_pfm: 390.66512310145964
episode: 28 training return: tensor(373.5523, device='cuda:0')
episode: 29 training return: tensor(380.6003, device='cuda:0')
episode: 30 training return: tensor(424.7296, device='cuda:0')
episode: 31 training return: tensor(-48.0964, device='cuda:0')
epoch: 8 test_true_pfm: 2809.1455837144185 sim_pfm: 188.44562884354187
episode: 32 training return: tensor(374.5933, device='cuda:0')
episode: 33 training return: tensor(-433.7450, device='cuda:0')
episode: 34 training return: tensor(407.7311, device='cuda:0')
episode: 35 training return: tensor(291.8833, device='cuda:0')
epoch: 9 test_true_pfm: 3180.087536731848 sim_pfm: 251.17909938120283
episode: 36 training return: tensor(384.3676, device='cuda:0')
episode: 37 training return: tensor(417.0194, device='cuda:0')
episode: 38 training return: tensor(375.9395, device='cuda:0')
episode: 39 training return: tensor(377.6681, device='cuda:0')
epoch: 10 test_true_pfm: 3481.3357402404345 sim_pfm: 424.20961392195505
episode: 40 training return: tensor(-207.6270, device='cuda:0')
episode: 41 training return: tensor(242.6712, device='cuda:0')
episode: 42 training return: tensor(385.1526, device='cuda:0')
episode: 43 training return: tensor(314.2646, device='cuda:0')
epoch: 11 test_true_pfm: 3280.4864078855294 sim_pfm: 294.63902754184284
episode: 44 training return: tensor(392.2541, device='cuda:0')
episode: 45 training return: tensor(444.2954, device='cuda:0')
episode: 46 training return: tensor(412.7776, device='cuda:0')
episode: 47 training return: tensor(397.1676, device='cuda:0')
epoch: 12 test_true_pfm: 3484.480204975269 sim_pfm: 432.8396636636074
episode: 48 training return: tensor(203.4724, device='cuda:0')
episode: 49 training return: tensor(-221.0931, device='cuda:0')
episode: 50 training return: tensor(438.5130, device='cuda:0')
episode: 51 training return: tensor(312.7974, device='cuda:0')
epoch: 13 test_true_pfm: 1590.5862275501133 sim_pfm: -242.33103662073458
episode: 52 training return: tensor(343.2888, device='cuda:0')
episode: 53 training return: tensor(405.9152, device='cuda:0')
episode: 54 training return: tensor(-116.9426, device='cuda:0')
episode: 55 training return: tensor(-161.1677, device='cuda:0')
epoch: 14 test_true_pfm: 2781.3680999332987 sim_pfm: 0.21056519448757172
episode: 56 training return: tensor(378.4890, device='cuda:0')
episode: 57 training return: tensor(424.1013, device='cuda:0')
episode: 58 training return: tensor(257.4897, device='cuda:0')
episode: 59 training return: tensor(-2.4109, device='cuda:0')
epoch: 15 test_true_pfm: 2360.6737744953675 sim_pfm: 22.141412224290736
episode: 60 training return: tensor(470.5301, device='cuda:0')
episode: 61 training return: tensor(344.0289, device='cuda:0')
episode: 62 training return: tensor(377.9823, device='cuda:0')
episode: 63 training return: tensor(19.1645, device='cuda:0')
epoch: 16 test_true_pfm: 3171.3403901857723 sim_pfm: 136.76904307598792
episode: 64 training return: tensor(384.1348, device='cuda:0')
episode: 65 training return: tensor(256.9135, device='cuda:0')
episode: 66 training return: tensor(356.2704, device='cuda:0')
episode: 67 training return: tensor(351.6769, device='cuda:0')
epoch: 17 test_true_pfm: 3652.8728648995443 sim_pfm: 470.830011963951
episode: 68 training return: tensor(345.8506, device='cuda:0')
episode: 69 training return: tensor(-14.7546, device='cuda:0')
episode: 70 training return: tensor(-153.4301, device='cuda:0')
episode: 71 training return: tensor(402.2029, device='cuda:0')
epoch: 18 test_true_pfm: 3388.7491442502383 sim_pfm: 182.91234198272772
episode: 72 training return: tensor(445.2407, device='cuda:0')
episode: 73 training return: tensor(357.4934, device='cuda:0')
episode: 74 training return: tensor(181.7042, device='cuda:0')
episode: 75 training return: tensor(-92.8688, device='cuda:0')
epoch: 19 test_true_pfm: 3126.8825466704443 sim_pfm: 273.3181827266235
episode: 76 training return: tensor(477.3729, device='cuda:0')
episode: 77 training return: tensor(164.1307, device='cuda:0')
episode: 78 training return: tensor(-127.8809, device='cuda:0')
episode: 79 training return: tensor(-309.0778, device='cuda:0')
epoch: 20 test_true_pfm: 2822.203125458201 sim_pfm: 441.2407123599357
episode: 80 training return: tensor(354.5459, device='cuda:0')
episode: 81 training return: tensor(-177.8806, device='cuda:0')
episode: 82 training return: tensor(382.6082, device='cuda:0')
episode: 83 training return: tensor(-102.0914, device='cuda:0')
epoch: 21 test_true_pfm: 3542.559557434973 sim_pfm: 421.39963424080634
episode: 84 training return: tensor(404.4925, device='cuda:0')
episode: 85 training return: tensor(-170.2731, device='cuda:0')
episode: 86 training return: tensor(-626.4933, device='cuda:0')
episode: 87 training return: tensor(376.1022, device='cuda:0')
epoch: 22 test_true_pfm: 3247.5079023286003 sim_pfm: 467.65049634472234
episode: 88 training return: tensor(461.7676, device='cuda:0')
episode: 89 training return: tensor(-269.0875, device='cuda:0')
episode: 90 training return: tensor(363.0685, device='cuda:0')
episode: 91 training return: tensor(-285.3296, device='cuda:0')
epoch: 23 test_true_pfm: 3438.8094849481736 sim_pfm: 366.24014121137833
episode: 92 training return: tensor(231.9297, device='cuda:0')
episode: 93 training return: tensor(310.5503, device='cuda:0')
episode: 94 training return: tensor(274.7625, device='cuda:0')
episode: 95 training return: tensor(271.9601, device='cuda:0')
epoch: 24 test_true_pfm: 3438.3086908419414 sim_pfm: 378.1109549012811
episode: 96 training return: tensor(422.8837, device='cuda:0')
episode: 97 training return: tensor(309.2024, device='cuda:0')
episode: 98 training return: tensor(308.4671, device='cuda:0')
episode: 99 training return: tensor(152.4045, device='cuda:0')
epoch: 25 test_true_pfm: 3465.2357081225164 sim_pfm: 360.7943960556295
episode: 100 training return: tensor(414.0708, device='cuda:0')
episode: 101 training return: tensor(341.7885, device='cuda:0')
episode: 102 training return: tensor(391.8101, device='cuda:0')
episode: 103 training return: tensor(334.1099, device='cuda:0')
epoch: 26 test_true_pfm: 3437.418958979481 sim_pfm: 431.0849508207563
episode: 104 training return: tensor(335.5558, device='cuda:0')
episode: 105 training return: tensor(296.3620, device='cuda:0')
episode: 106 training return: tensor(300.4698, device='cuda:0')
episode: 107 training return: tensor(352.8895, device='cuda:0')
epoch: 27 test_true_pfm: 3373.2567320857474 sim_pfm: 337.0019971138875
episode: 108 training return: tensor(382.4939, device='cuda:0')
episode: 109 training return: tensor(403.2108, device='cuda:0')
episode: 110 training return: tensor(347.8399, device='cuda:0')
episode: 111 training return: tensor(401.4324, device='cuda:0')
epoch: 28 test_true_pfm: 3469.240238819693 sim_pfm: 255.4531902782716
episode: 112 training return: tensor(381.4382, device='cuda:0')
episode: 113 training return: tensor(406.0301, device='cuda:0')
episode: 114 training return: tensor(384.9400, device='cuda:0')
episode: 115 training return: tensor(416.2108, device='cuda:0')
epoch: 29 test_true_pfm: 3463.7975787831947 sim_pfm: 401.9528747839504
episode: 116 training return: tensor(397.9599, device='cuda:0')
episode: 117 training return: tensor(299.6610, device='cuda:0')
episode: 118 training return: tensor(429.8890, device='cuda:0')
episode: 119 training return: tensor(318.8771, device='cuda:0')
epoch: 30 test_true_pfm: 3705.2224627100936 sim_pfm: 382.95595255168155
episode: 120 training return: tensor(430.0816, device='cuda:0')
episode: 121 training return: tensor(344.0175, device='cuda:0')
episode: 122 training return: tensor(409.1552, device='cuda:0')
episode: 123 training return: tensor(350.1265, device='cuda:0')
epoch: 31 test_true_pfm: 3501.428442789252 sim_pfm: 538.9831013968214
episode: 124 training return: tensor(344.8037, device='cuda:0')
episode: 125 training return: tensor(307.9891, device='cuda:0')
episode: 126 training return: tensor(411.6035, device='cuda:0')
episode: 127 training return: tensor(389.3790, device='cuda:0')
epoch: 32 test_true_pfm: 3252.5634750508666 sim_pfm: 469.11862817204866
episode: 128 training return: tensor(430.0615, device='cuda:0')
episode: 129 training return: tensor(414.3994, device='cuda:0')
episode: 130 training return: tensor(39.6814, device='cuda:0')
episode: 131 training return: tensor(452.2365, device='cuda:0')
epoch: 33 test_true_pfm: 3479.461465788599 sim_pfm: 415.4272781036173
episode: 132 training return: tensor(395.9162, device='cuda:0')
episode: 133 training return: tensor(445.6238, device='cuda:0')
episode: 134 training return: tensor(496.3513, device='cuda:0')
episode: 135 training return: tensor(412.6507, device='cuda:0')
epoch: 34 test_true_pfm: 3538.7553144071676 sim_pfm: 424.741672963554
episode: 136 training return: tensor(390.4815, device='cuda:0')
episode: 137 training return: tensor(413.5562, device='cuda:0')
episode: 138 training return: tensor(402.2253, device='cuda:0')
episode: 139 training return: tensor(419.4193, device='cuda:0')
epoch: 35 test_true_pfm: 3501.042354746029 sim_pfm: 339.3837145444316
episode: 140 training return: tensor(405.3545, device='cuda:0')
episode: 141 training return: tensor(379.4876, device='cuda:0')
episode: 142 training return: tensor(410.0535, device='cuda:0')
episode: 143 training return: tensor(402.8553, device='cuda:0')
epoch: 36 test_true_pfm: 2936.0912885879247 sim_pfm: 271.63677736969356
episode: 144 training return: tensor(429.7476, device='cuda:0')
episode: 145 training return: tensor(368.2033, device='cuda:0')
episode: 146 training return: tensor(434.1841, device='cuda:0')
episode: 147 training return: tensor(450.0263, device='cuda:0')
epoch: 37 test_true_pfm: 3463.5463928389977 sim_pfm: 379.10187852564076
episode: 148 training return: tensor(379.6678, device='cuda:0')
episode: 149 training return: tensor(408.9936, device='cuda:0')
episode: 150 training return: tensor(386.9547, device='cuda:0')
episode: 151 training return: tensor(339.8557, device='cuda:0')
epoch: 38 test_true_pfm: 3447.195524504152 sim_pfm: 376.18126741959713
episode: 152 training return: tensor(403.5528, device='cuda:0')
episode: 153 training return: tensor(454.1755, device='cuda:0')
episode: 154 training return: tensor(-92.1432, device='cuda:0')
episode: 155 training return: tensor(415.8672, device='cuda:0')
epoch: 39 test_true_pfm: 3587.4312238818547 sim_pfm: 480.1388129875995
episode: 156 training return: tensor(449.5514, device='cuda:0')
episode: 157 training return: tensor(410.5126, device='cuda:0')
episode: 158 training return: tensor(345.6745, device='cuda:0')
episode: 159 training return: tensor(440.2087, device='cuda:0')
epoch: 40 test_true_pfm: 3533.512169555321 sim_pfm: 428.24045267811744
episode: 160 training return: tensor(385.1974, device='cuda:0')
episode: 161 training return: tensor(450.6899, device='cuda:0')
episode: 162 training return: tensor(416.3471, device='cuda:0')
episode: 163 training return: tensor(388.5961, device='cuda:0')
epoch: 41 test_true_pfm: 3134.2550919494606 sim_pfm: 516.1524248893062
episode: 164 training return: tensor(242.9186, device='cuda:0')
episode: 165 training return: tensor(478.5027, device='cuda:0')
episode: 166 training return: tensor(483.1732, device='cuda:0')
episode: 167 training return: tensor(415.3669, device='cuda:0')
epoch: 42 test_true_pfm: 3574.221616370216 sim_pfm: 444.8694179196609
episode: 168 training return: tensor(398.7358, device='cuda:0')
episode: 169 training return: tensor(388.3773, device='cuda:0')
episode: 170 training return: tensor(466.3934, device='cuda:0')
episode: 171 training return: tensor(342.7110, device='cuda:0')
epoch: 43 test_true_pfm: 3499.1661419795655 sim_pfm: 406.9456482822231
episode: 172 training return: tensor(395.2301, device='cuda:0')
episode: 173 training return: tensor(-6.7134, device='cuda:0')
episode: 174 training return: tensor(366.2494, device='cuda:0')
episode: 175 training return: tensor(387.9285, device='cuda:0')
epoch: 44 test_true_pfm: 3504.4177514655116 sim_pfm: 413.6198768718168
episode: 176 training return: tensor(446.2422, device='cuda:0')
episode: 177 training return: tensor(419.6459, device='cuda:0')
episode: 178 training return: tensor(401.7640, device='cuda:0')
episode: 179 training return: tensor(367.9354, device='cuda:0')
epoch: 45 test_true_pfm: 3566.5991050069056 sim_pfm: 419.15922415266203
episode: 180 training return: tensor(108.8974, device='cuda:0')
episode: 181 training return: tensor(-29.5256, device='cuda:0')
episode: 182 training return: tensor(397.5378, device='cuda:0')
episode: 183 training return: tensor(425.3250, device='cuda:0')
epoch: 46 test_true_pfm: 3301.330122525364 sim_pfm: 398.913307913482
episode: 184 training return: tensor(441.5029, device='cuda:0')
episode: 185 training return: tensor(439.1537, device='cuda:0')
episode: 186 training return: tensor(416.3809, device='cuda:0')
episode: 187 training return: tensor(427.1263, device='cuda:0')
epoch: 47 test_true_pfm: 3680.3589009990915 sim_pfm: 426.3478052734863
episode: 188 training return: tensor(427.5058, device='cuda:0')
episode: 189 training return: tensor(409.0955, device='cuda:0')
episode: 190 training return: tensor(426.9718, device='cuda:0')
episode: 191 training return: tensor(263.2273, device='cuda:0')
epoch: 48 test_true_pfm: 3567.9598187209754 sim_pfm: 450.6526513979382
episode: 192 training return: tensor(388.9378, device='cuda:0')
episode: 193 training return: tensor(390.6278, device='cuda:0')
episode: 194 training return: tensor(426.0306, device='cuda:0')
episode: 195 training return: tensor(111.1671, device='cuda:0')
epoch: 49 test_true_pfm: 3458.869881201412 sim_pfm: 385.4237761617017
episode: 196 training return: tensor(371.0298, device='cuda:0')
episode: 197 training return: tensor(431.7898, device='cuda:0')
episode: 198 training return: tensor(405.0929, device='cuda:0')
episode: 199 training return: tensor(442.7604, device='cuda:0')
epoch: 50 test_true_pfm: 3668.5364475602114 sim_pfm: 504.9553963262976
episode: 200 training return: tensor(430.8632, device='cuda:0')
episode: 201 training return: tensor(484.6779, device='cuda:0')
episode: 202 training return: tensor(407.6757, device='cuda:0')
episode: 203 training return: tensor(457.5450, device='cuda:0')
epoch: 51 test_true_pfm: 3606.2516383449624 sim_pfm: 472.37636529343825
episode: 204 training return: tensor(439.6566, device='cuda:0')
episode: 205 training return: tensor(384.1977, device='cuda:0')
episode: 206 training return: tensor(438.4623, device='cuda:0')
episode: 207 training return: tensor(409.3266, device='cuda:0')
epoch: 52 test_true_pfm: 3629.8029244072095 sim_pfm: 483.6259380149422
episode: 208 training return: tensor(372.6151, device='cuda:0')
episode: 209 training return: tensor(446.0087, device='cuda:0')
episode: 210 training return: tensor(468.9532, device='cuda:0')
episode: 211 training return: tensor(388.2657, device='cuda:0')
epoch: 53 test_true_pfm: 2984.9152399867016 sim_pfm: 435.4272210397564
episode: 212 training return: tensor(379.7919, device='cuda:0')
episode: 213 training return: tensor(438.2440, device='cuda:0')
episode: 214 training return: tensor(416.8094, device='cuda:0')
episode: 215 training return: tensor(445.2590, device='cuda:0')
epoch: 54 test_true_pfm: 3621.380433509343 sim_pfm: 487.3817784119553
episode: 216 training return: tensor(445.2351, device='cuda:0')
episode: 217 training return: tensor(478.1999, device='cuda:0')
episode: 218 training return: tensor(338.1740, device='cuda:0')
episode: 219 training return: tensor(342.5352, device='cuda:0')
epoch: 55 test_true_pfm: 3523.978935413339 sim_pfm: 420.8528878792907
episode: 220 training return: tensor(356.0477, device='cuda:0')
episode: 221 training return: tensor(438.3454, device='cuda:0')
episode: 222 training return: tensor(323.5608, device='cuda:0')
episode: 223 training return: tensor(521.8892, device='cuda:0')
epoch: 56 test_true_pfm: 3671.6318339936224 sim_pfm: 499.02577026817016
episode: 224 training return: tensor(418.8443, device='cuda:0')
episode: 225 training return: tensor(463.1774, device='cuda:0')
episode: 226 training return: tensor(483.8235, device='cuda:0')
episode: 227 training return: tensor(433.8011, device='cuda:0')
epoch: 57 test_true_pfm: 3653.5754716643555 sim_pfm: 417.9089736822061
episode: 228 training return: tensor(410.8584, device='cuda:0')
episode: 229 training return: tensor(424.0590, device='cuda:0')
episode: 230 training return: tensor(396.5870, device='cuda:0')
episode: 231 training return: tensor(406.9447, device='cuda:0')
epoch: 58 test_true_pfm: 3515.441048485665 sim_pfm: 411.98396615860594
episode: 232 training return: tensor(420.8537, device='cuda:0')
episode: 233 training return: tensor(436.9440, device='cuda:0')
episode: 234 training return: tensor(433.1252, device='cuda:0')
episode: 235 training return: tensor(436.2149, device='cuda:0')
epoch: 59 test_true_pfm: 3613.53886677336 sim_pfm: 471.43309195001103
episode: 236 training return: tensor(452.6223, device='cuda:0')
episode: 237 training return: tensor(-127.4410, device='cuda:0')
episode: 238 training return: tensor(485.9758, device='cuda:0')
episode: 239 training return: tensor(390.9577, device='cuda:0')
epoch: 60 test_true_pfm: 3553.569732250869 sim_pfm: 458.99619321602705
episode: 240 training return: tensor(431.5765, device='cuda:0')
episode: 241 training return: tensor(404.6142, device='cuda:0')
episode: 242 training return: tensor(451.5609, device='cuda:0')
episode: 243 training return: tensor(396.2283, device='cuda:0')
epoch: 61 test_true_pfm: 3635.0776512562547 sim_pfm: 498.4845099210991
episode: 244 training return: tensor(465.1012, device='cuda:0')
episode: 245 training return: tensor(405.7761, device='cuda:0')
episode: 246 training return: tensor(489.4986, device='cuda:0')
episode: 247 training return: tensor(495.7784, device='cuda:0')
epoch: 62 test_true_pfm: 3642.2188683904237 sim_pfm: 491.6477469175006
episode: 248 training return: tensor(108.1051, device='cuda:0')
episode: 249 training return: tensor(451.0120, device='cuda:0')
episode: 250 training return: tensor(451.1577, device='cuda:0')
episode: 251 training return: tensor(456.8957, device='cuda:0')
epoch: 63 test_true_pfm: 3594.995048349443 sim_pfm: 474.9582375709627
episode: 252 training return: tensor(437.2787, device='cuda:0')
episode: 253 training return: tensor(454.1102, device='cuda:0')
episode: 254 training return: tensor(441.1985, device='cuda:0')
episode: 255 training return: tensor(154.9261, device='cuda:0')
epoch: 64 test_true_pfm: 3706.5567137939856 sim_pfm: 521.9327311659775
episode: 256 training return: tensor(474.8529, device='cuda:0')
episode: 257 training return: tensor(490.8093, device='cuda:0')
episode: 258 training return: tensor(429.2998, device='cuda:0')
episode: 259 training return: tensor(-9.8771, device='cuda:0')
epoch: 65 test_true_pfm: 3523.81869234908 sim_pfm: 428.978137434305
episode: 260 training return: tensor(446.5488, device='cuda:0')
episode: 261 training return: tensor(364.7891, device='cuda:0')
episode: 262 training return: tensor(-240.4556, device='cuda:0')
episode: 263 training return: tensor(303.3282, device='cuda:0')
epoch: 66 test_true_pfm: 3590.5350207824454 sim_pfm: 471.3166772675274
episode: 264 training return: tensor(398.3825, device='cuda:0')
episode: 265 training return: tensor(445.7568, device='cuda:0')
episode: 266 training return: tensor(416.6129, device='cuda:0')
episode: 267 training return: tensor(412.6388, device='cuda:0')
epoch: 67 test_true_pfm: 3629.9455139898 sim_pfm: 477.9950292251694
episode: 268 training return: tensor(375.8064, device='cuda:0')
episode: 269 training return: tensor(419.6152, device='cuda:0')
episode: 270 training return: tensor(423.2140, device='cuda:0')
episode: 271 training return: tensor(436.7636, device='cuda:0')
epoch: 68 test_true_pfm: 3608.2721237831915 sim_pfm: 482.17084427255514
episode: 272 training return: tensor(419.7158, device='cuda:0')
episode: 273 training return: tensor(434.3499, device='cuda:0')
episode: 274 training return: tensor(427.4584, device='cuda:0')
episode: 275 training return: tensor(431.7310, device='cuda:0')
epoch: 69 test_true_pfm: 3632.689392596925 sim_pfm: 366.34126166599646
episode: 276 training return: tensor(455.7323, device='cuda:0')
episode: 277 training return: tensor(454.2144, device='cuda:0')
episode: 278 training return: tensor(453.0089, device='cuda:0')
episode: 279 training return: tensor(480.6420, device='cuda:0')
epoch: 70 test_true_pfm: 3604.3776618763536 sim_pfm: 470.6279259573009
episode: 280 training return: tensor(433.0132, device='cuda:0')
episode: 281 training return: tensor(422.2357, device='cuda:0')
episode: 282 training return: tensor(418.0472, device='cuda:0')
episode: 283 training return: tensor(487.0248, device='cuda:0')
epoch: 71 test_true_pfm: 3570.2274513739176 sim_pfm: 462.1513509388703
episode: 284 training return: tensor(405.2814, device='cuda:0')
episode: 285 training return: tensor(465.7277, device='cuda:0')
episode: 286 training return: tensor(83.3907, device='cuda:0')
episode: 287 training return: tensor(419.6493, device='cuda:0')
epoch: 72 test_true_pfm: 3583.9258437421813 sim_pfm: 464.0966255417443
episode: 288 training return: tensor(380.5041, device='cuda:0')
episode: 289 training return: tensor(188.8010, device='cuda:0')
episode: 290 training return: tensor(437.4199, device='cuda:0')
episode: 291 training return: tensor(429.0022, device='cuda:0')
epoch: 73 test_true_pfm: 3497.636199852235 sim_pfm: 409.92816230569343
episode: 292 training return: tensor(437.3531, device='cuda:0')
episode: 293 training return: tensor(442.1745, device='cuda:0')
episode: 294 training return: tensor(447.6616, device='cuda:0')
episode: 295 training return: tensor(416.3880, device='cuda:0')
epoch: 74 test_true_pfm: 3588.310754074833 sim_pfm: 467.80885094501235
episode: 296 training return: tensor(473.7192, device='cuda:0')
episode: 297 training return: tensor(252.3148, device='cuda:0')
episode: 298 training return: tensor(421.6841, device='cuda:0')
episode: 299 training return: tensor(547.6414, device='cuda:0')
epoch: 75 test_true_pfm: 3621.945973200676 sim_pfm: 479.8408687033225
episode: 300 training return: tensor(438.3585, device='cuda:0')
episode: 301 training return: tensor(354.2491, device='cuda:0')
episode: 302 training return: tensor(414.6418, device='cuda:0')
episode: 303 training return: tensor(293.7655, device='cuda:0')
epoch: 76 test_true_pfm: 3503.1084174320663 sim_pfm: 418.0960256111187
episode: 304 training return: tensor(427.5422, device='cuda:0')
episode: 305 training return: tensor(399.9403, device='cuda:0')
episode: 306 training return: tensor(456.5461, device='cuda:0')
episode: 307 training return: tensor(444.7849, device='cuda:0')
epoch: 77 test_true_pfm: 3664.083158978123 sim_pfm: 514.2226907871664
episode: 308 training return: tensor(422.1781, device='cuda:0')
episode: 309 training return: tensor(434.8657, device='cuda:0')
episode: 310 training return: tensor(425.2990, device='cuda:0')
episode: 311 training return: tensor(464.7754, device='cuda:0')
epoch: 78 test_true_pfm: 3571.366257457879 sim_pfm: 456.6901597035273
episode: 312 training return: tensor(431.1028, device='cuda:0')
episode: 313 training return: tensor(449.7549, device='cuda:0')
episode: 314 training return: tensor(468.5505, device='cuda:0')
episode: 315 training return: tensor(493.0203, device='cuda:0')
epoch: 79 test_true_pfm: 3462.2943505902804 sim_pfm: 378.5099893033815
episode: 316 training return: tensor(464.0926, device='cuda:0')
episode: 317 training return: tensor(490.6100, device='cuda:0')
episode: 318 training return: tensor(423.1985, device='cuda:0')
episode: 319 training return: tensor(517.6463, device='cuda:0')
epoch: 80 test_true_pfm: 3657.540428763085 sim_pfm: 499.357338101215
episode: 320 training return: tensor(352.4935, device='cuda:0')
episode: 321 training return: tensor(460.1432, device='cuda:0')
episode: 322 training return: tensor(-47.6275, device='cuda:0')
episode: 323 training return: tensor(488.9398, device='cuda:0')
epoch: 81 test_true_pfm: 3554.6146306442247 sim_pfm: 468.66748228574096
episode: 324 training return: tensor(397.8674, device='cuda:0')
episode: 325 training return: tensor(408.8039, device='cuda:0')
episode: 326 training return: tensor(321.8109, device='cuda:0')
episode: 327 training return: tensor(461.4166, device='cuda:0')
epoch: 82 test_true_pfm: 3527.610612249733 sim_pfm: 418.102901002625
episode: 328 training return: tensor(407.4749, device='cuda:0')
episode: 329 training return: tensor(437.2412, device='cuda:0')
episode: 330 training return: tensor(450.8998, device='cuda:0')
episode: 331 training return: tensor(253.3146, device='cuda:0')
epoch: 83 test_true_pfm: 3564.1834366157177 sim_pfm: 452.91984287047916
episode: 332 training return: tensor(461.5829, device='cuda:0')
episode: 333 training return: tensor(422.1745, device='cuda:0')
episode: 334 training return: tensor(452.5157, device='cuda:0')
episode: 335 training return: tensor(472.4805, device='cuda:0')
epoch: 84 test_true_pfm: 3286.862476192094 sim_pfm: 486.46692271507345
episode: 336 training return: tensor(411.8944, device='cuda:0')
episode: 337 training return: tensor(413.4633, device='cuda:0')
episode: 338 training return: tensor(430.0705, device='cuda:0')
episode: 339 training return: tensor(426.3029, device='cuda:0')
epoch: 85 test_true_pfm: 3501.282555976175 sim_pfm: 420.6984933129279
episode: 340 training return: tensor(421.8404, device='cuda:0')
episode: 341 training return: tensor(430.8739, device='cuda:0')
episode: 342 training return: tensor(417.4906, device='cuda:0')
episode: 343 training return: tensor(478.8434, device='cuda:0')
epoch: 86 test_true_pfm: 3634.71368876272 sim_pfm: 493.63738492395106
episode: 344 training return: tensor(451.2529, device='cuda:0')
episode: 345 training return: tensor(452.2917, device='cuda:0')
episode: 346 training return: tensor(436.1370, device='cuda:0')
episode: 347 training return: tensor(442.4908, device='cuda:0')
epoch: 87 test_true_pfm: 3564.454499527203 sim_pfm: 462.10354452357086
episode: 348 training return: tensor(460.1096, device='cuda:0')
episode: 349 training return: tensor(458.6854, device='cuda:0')
episode: 350 training return: tensor(443.3035, device='cuda:0')
episode: 351 training return: tensor(474.0521, device='cuda:0')
epoch: 88 test_true_pfm: 3567.2913127363395 sim_pfm: 457.31530704256147
episode: 352 training return: tensor(445.0306, device='cuda:0')
episode: 353 training return: tensor(453.7532, device='cuda:0')
episode: 354 training return: tensor(440.3306, device='cuda:0')
episode: 355 training return: tensor(469.6629, device='cuda:0')
epoch: 89 test_true_pfm: 3602.126303938956 sim_pfm: 472.82238569195033
episode: 356 training return: tensor(457.2653, device='cuda:0')
episode: 357 training return: tensor(472.9640, device='cuda:0')
episode: 358 training return: tensor(451.3727, device='cuda:0')
episode: 359 training return: tensor(436.7550, device='cuda:0')
epoch: 90 test_true_pfm: 3515.6132844471304 sim_pfm: 429.5629204931708
episode: 360 training return: tensor(416.9205, device='cuda:0')
episode: 361 training return: tensor(421.6113, device='cuda:0')
episode: 362 training return: tensor(457.6841, device='cuda:0')
episode: 363 training return: tensor(471.6965, device='cuda:0')
epoch: 91 test_true_pfm: 3598.651464340899 sim_pfm: 466.9227662074263
episode: 364 training return: tensor(460.7798, device='cuda:0')
episode: 365 training return: tensor(494.0908, device='cuda:0')
episode: 366 training return: tensor(482.6907, device='cuda:0')
episode: 367 training return: tensor(447.9301, device='cuda:0')
epoch: 92 test_true_pfm: 3560.415455125914 sim_pfm: 461.91284469344345
episode: 368 training return: tensor(405.2415, device='cuda:0')
episode: 369 training return: tensor(418.5742, device='cuda:0')
episode: 370 training return: tensor(438.5087, device='cuda:0')
episode: 371 training return: tensor(400.4048, device='cuda:0')
epoch: 93 test_true_pfm: 3535.478072303249 sim_pfm: 426.78885976341553
episode: 372 training return: tensor(491.9460, device='cuda:0')
episode: 373 training return: tensor(455.1923, device='cuda:0')
episode: 374 training return: tensor(147.3561, device='cuda:0')
episode: 375 training return: tensor(428.2770, device='cuda:0')
epoch: 94 test_true_pfm: 3589.5837882629367 sim_pfm: 459.21238155834726
episode: 376 training return: tensor(453.3894, device='cuda:0')
episode: 377 training return: tensor(446.8935, device='cuda:0')
episode: 378 training return: tensor(158.5704, device='cuda:0')
episode: 379 training return: tensor(454.8839, device='cuda:0')
epoch: 95 test_true_pfm: 3677.3232105922148 sim_pfm: 509.78895681753056
episode: 380 training return: tensor(433.9586, device='cuda:0')
episode: 381 training return: tensor(450.5265, device='cuda:0')
episode: 382 training return: tensor(-7.9021, device='cuda:0')
episode: 383 training return: tensor(429.3976, device='cuda:0')
epoch: 96 test_true_pfm: 3528.796299198513 sim_pfm: 419.3917672779838
episode: 384 training return: tensor(384.6809, device='cuda:0')
episode: 385 training return: tensor(396.4258, device='cuda:0')
episode: 386 training return: tensor(423.3234, device='cuda:0')
episode: 387 training return: tensor(394.7264, device='cuda:0')
epoch: 97 test_true_pfm: 3521.8692954279727 sim_pfm: 425.30035316742334
episode: 388 training return: tensor(440.5561, device='cuda:0')
episode: 389 training return: tensor(419.5251, device='cuda:0')
episode: 390 training return: tensor(455.2751, device='cuda:0')
episode: 391 training return: tensor(469.9521, device='cuda:0')
epoch: 98 test_true_pfm: 3613.954775821261 sim_pfm: 491.5186420340712
episode: 392 training return: tensor(511.5876, device='cuda:0')
episode: 393 training return: tensor(435.2752, device='cuda:0')
episode: 394 training return: tensor(406.2284, device='cuda:0')
episode: 395 training return: tensor(483.2006, device='cuda:0')
epoch: 99 test_true_pfm: 3578.7698631549697 sim_pfm: 466.5678367841562
episode: 396 training return: tensor(475.7230, device='cuda:0')
episode: 397 training return: tensor(408.5027, device='cuda:0')
episode: 398 training return: tensor(398.5951, device='cuda:0')
episode: 399 training return: tensor(399.0558, device='cuda:0')
epoch: 100 test_true_pfm: 3502.0747786737243 sim_pfm: 426.63544684415683
episode: 400 training return: tensor(433.6141, device='cuda:0')
episode: 401 training return: tensor(500.8697, device='cuda:0')
episode: 402 training return: tensor(463.9824, device='cuda:0')
episode: 403 training return: tensor(345.8582, device='cuda:0')
epoch: 101 test_true_pfm: 3606.393688279257 sim_pfm: 481.0616985837114
episode: 404 training return: tensor(482.0927, device='cuda:0')
episode: 405 training return: tensor(388.8148, device='cuda:0')
episode: 406 training return: tensor(442.6212, device='cuda:0')
episode: 407 training return: tensor(450.0108, device='cuda:0')
epoch: 102 test_true_pfm: 3562.317789875689 sim_pfm: 447.71630095131695
episode: 408 training return: tensor(418.1950, device='cuda:0')
episode: 409 training return: tensor(464.4102, device='cuda:0')
episode: 410 training return: tensor(423.2680, device='cuda:0')
episode: 411 training return: tensor(476.4846, device='cuda:0')
epoch: 103 test_true_pfm: 3625.6345090718946 sim_pfm: 482.23820011147956
episode: 412 training return: tensor(462.0903, device='cuda:0')
episode: 413 training return: tensor(461.0388, device='cuda:0')
episode: 414 training return: tensor(417.5501, device='cuda:0')
episode: 415 training return: tensor(402.8529, device='cuda:0')
epoch: 104 test_true_pfm: 3615.426182830339 sim_pfm: 446.2295665681983
episode: 416 training return: tensor(417.7678, device='cuda:0')
episode: 417 training return: tensor(452.9635, device='cuda:0')
episode: 418 training return: tensor(457.4658, device='cuda:0')
episode: 419 training return: tensor(218.2068, device='cuda:0')
epoch: 105 test_true_pfm: 3516.5412661786468 sim_pfm: 416.97184272436425
episode: 420 training return: tensor(465.3275, device='cuda:0')
episode: 421 training return: tensor(453.1688, device='cuda:0')
episode: 422 training return: tensor(423.4931, device='cuda:0')
episode: 423 training return: tensor(421.2516, device='cuda:0')
epoch: 106 test_true_pfm: 3598.745225431747 sim_pfm: 469.19944317569025
episode: 424 training return: tensor(354.7694, device='cuda:0')
episode: 425 training return: tensor(458.6123, device='cuda:0')
episode: 426 training return: tensor(444.1842, device='cuda:0')
episode: 427 training return: tensor(446.6621, device='cuda:0')
epoch: 107 test_true_pfm: 3556.6404355921227 sim_pfm: 453.89656037441455
episode: 428 training return: tensor(415.3055, device='cuda:0')
episode: 429 training return: tensor(414.8854, device='cuda:0')
episode: 430 training return: tensor(423.0492, device='cuda:0')
episode: 431 training return: tensor(407.2455, device='cuda:0')
epoch: 108 test_true_pfm: 3560.344262456813 sim_pfm: 442.41344197375776
episode: 432 training return: tensor(459.0164, device='cuda:0')
episode: 433 training return: tensor(439.5636, device='cuda:0')
episode: 434 training return: tensor(418.9899, device='cuda:0')
episode: 435 training return: tensor(488.1929, device='cuda:0')
epoch: 109 test_true_pfm: 3584.993116336854 sim_pfm: 456.9463378860576
episode: 436 training return: tensor(416.6106, device='cuda:0')
episode: 437 training return: tensor(455.7395, device='cuda:0')
episode: 438 training return: tensor(470.1794, device='cuda:0')
episode: 439 training return: tensor(437.2864, device='cuda:0')
epoch: 110 test_true_pfm: 3549.7864886727134 sim_pfm: 454.74573695518
episode: 440 training return: tensor(465.0410, device='cuda:0')
episode: 441 training return: tensor(460.4290, device='cuda:0')
episode: 442 training return: tensor(410.2704, device='cuda:0')
episode: 443 training return: tensor(447.3076, device='cuda:0')
epoch: 111 test_true_pfm: 3513.3057380280316 sim_pfm: 423.78159801495104
episode: 444 training return: tensor(382.9861, device='cuda:0')
episode: 445 training return: tensor(446.1131, device='cuda:0')
episode: 446 training return: tensor(-179.6087, device='cuda:0')
episode: 447 training return: tensor(443.1663, device='cuda:0')
epoch: 112 test_true_pfm: 3497.2845647021095 sim_pfm: 424.47913979149115
episode: 448 training return: tensor(483.4313, device='cuda:0')
episode: 449 training return: tensor(439.8842, device='cuda:0')
episode: 450 training return: tensor(490.5538, device='cuda:0')
episode: 451 training return: tensor(444.2323, device='cuda:0')
epoch: 113 test_true_pfm: 3534.7116875998577 sim_pfm: 438.05502099144115
episode: 452 training return: tensor(436.5855, device='cuda:0')
episode: 453 training return: tensor(449.5958, device='cuda:0')
episode: 454 training return: tensor(527.2452, device='cuda:0')
episode: 455 training return: tensor(475.6876, device='cuda:0')
epoch: 114 test_true_pfm: 3567.9267714403286 sim_pfm: 443.10214594514883
episode: 456 training return: tensor(418.8574, device='cuda:0')
episode: 457 training return: tensor(457.3202, device='cuda:0')
episode: 458 training return: tensor(405.3609, device='cuda:0')
episode: 459 training return: tensor(458.0533, device='cuda:0')
epoch: 115 test_true_pfm: 3587.7228801294564 sim_pfm: 466.07772856595693
episode: 460 training return: tensor(396.4960, device='cuda:0')
episode: 461 training return: tensor(449.5154, device='cuda:0')
episode: 462 training return: tensor(458.1234, device='cuda:0')
episode: 463 training return: tensor(403.1746, device='cuda:0')
epoch: 116 test_true_pfm: 3532.149012402662 sim_pfm: 431.2772848421785
episode: 464 training return: tensor(425.2226, device='cuda:0')
episode: 465 training return: tensor(396.4758, device='cuda:0')
episode: 466 training return: tensor(440.7953, device='cuda:0')
episode: 467 training return: tensor(439.1378, device='cuda:0')
epoch: 117 test_true_pfm: 3586.4276823094187 sim_pfm: 469.27579601797817
episode: 468 training return: tensor(458.3860, device='cuda:0')
episode: 469 training return: tensor(443.1930, device='cuda:0')
episode: 470 training return: tensor(448.9445, device='cuda:0')
episode: 471 training return: tensor(515.9672, device='cuda:0')
epoch: 118 test_true_pfm: 3582.2311684198407 sim_pfm: 448.08098195132334
episode: 472 training return: tensor(429.4268, device='cuda:0')
episode: 473 training return: tensor(448.6669, device='cuda:0')
episode: 474 training return: tensor(388.6182, device='cuda:0')
episode: 475 training return: tensor(452.1481, device='cuda:0')
epoch: 119 test_true_pfm: 3541.5200936419933 sim_pfm: 439.87570098480984
episode: 476 training return: tensor(424.5393, device='cuda:0')
episode: 477 training return: tensor(393.1316, device='cuda:0')
episode: 478 training return: tensor(451.9183, device='cuda:0')
episode: 479 training return: tensor(430.1078, device='cuda:0')
epoch: 120 test_true_pfm: 3509.713984379989 sim_pfm: 418.9165882866558
episode: 480 training return: tensor(428.8874, device='cuda:0')
episode: 481 training return: tensor(448.1650, device='cuda:0')
episode: 482 training return: tensor(460.0846, device='cuda:0')
episode: 483 training return: tensor(406.9646, device='cuda:0')
epoch: 121 test_true_pfm: 3538.1153537214855 sim_pfm: 437.04884249700507
episode: 484 training return: tensor(446.2506, device='cuda:0')
episode: 485 training return: tensor(421.8445, device='cuda:0')
episode: 486 training return: tensor(400.9647, device='cuda:0')
episode: 487 training return: tensor(483.9496, device='cuda:0')
epoch: 122 test_true_pfm: 3572.6112049167045 sim_pfm: 452.4299469270045
episode: 488 training return: tensor(467.6234, device='cuda:0')
episode: 489 training return: tensor(409.4804, device='cuda:0')
episode: 490 training return: tensor(414.4895, device='cuda:0')
episode: 491 training return: tensor(446.5556, device='cuda:0')
epoch: 123 test_true_pfm: 3559.755682851159 sim_pfm: 458.7501557741198
episode: 492 training return: tensor(425.3411, device='cuda:0')
episode: 493 training return: tensor(428.6880, device='cuda:0')
episode: 494 training return: tensor(420.3884, device='cuda:0')
episode: 495 training return: tensor(433.5263, device='cuda:0')
epoch: 124 test_true_pfm: 3512.0617965682736 sim_pfm: 419.7621903466449
episode: 496 training return: tensor(411.1951, device='cuda:0')
episode: 497 training return: tensor(471.4692, device='cuda:0')
episode: 498 training return: tensor(423.1831, device='cuda:0')
episode: 499 training return: tensor(461.8095, device='cuda:0')
epoch: 125 test_true_pfm: 3522.790669426528 sim_pfm: 418.31989536238444
episode: 500 training return: tensor(468.6198, device='cuda:0')
episode: 501 training return: tensor(456.4604, device='cuda:0')
episode: 502 training return: tensor(423.3987, device='cuda:0')
episode: 503 training return: tensor(408.4473, device='cuda:0')
epoch: 126 test_true_pfm: 3582.1520168127918 sim_pfm: 467.4761017379836
episode: 504 training return: tensor(435.9915, device='cuda:0')
episode: 505 training return: tensor(463.3236, device='cuda:0')
episode: 506 training return: tensor(464.8029, device='cuda:0')
episode: 507 training return: tensor(450.5528, device='cuda:0')
epoch: 127 test_true_pfm: 3630.0396650264847 sim_pfm: 486.02128494645393
episode: 508 training return: tensor(387.2874, device='cuda:0')
episode: 509 training return: tensor(455.7869, device='cuda:0')
episode: 510 training return: tensor(449.6144, device='cuda:0')
episode: 511 training return: tensor(429.8045, device='cuda:0')
epoch: 128 test_true_pfm: 3528.0852795955284 sim_pfm: 433.10145481221844
episode: 512 training return: tensor(454.3602, device='cuda:0')
episode: 513 training return: tensor(451.8384, device='cuda:0')
episode: 514 training return: tensor(439.1923, device='cuda:0')
episode: 515 training return: tensor(397.0213, device='cuda:0')
epoch: 129 test_true_pfm: 3519.502247637547 sim_pfm: 414.43960368623567
episode: 516 training return: tensor(433.3578, device='cuda:0')
episode: 517 training return: tensor(391.7595, device='cuda:0')
episode: 518 training return: tensor(425.7335, device='cuda:0')
episode: 519 training return: tensor(462.9965, device='cuda:0')
epoch: 130 test_true_pfm: 3508.3671208661835 sim_pfm: 408.3705451857434
episode: 520 training return: tensor(424.4030, device='cuda:0')
episode: 521 training return: tensor(432.3958, device='cuda:0')
episode: 522 training return: tensor(464.5572, device='cuda:0')
episode: 523 training return: tensor(435.0746, device='cuda:0')
epoch: 131 test_true_pfm: 3545.8919161296785 sim_pfm: 440.1431051828743
episode: 524 training return: tensor(445.0522, device='cuda:0')
episode: 525 training return: tensor(346.6731, device='cuda:0')
episode: 526 training return: tensor(421.8925, device='cuda:0')
episode: 527 training return: tensor(469.9084, device='cuda:0')
epoch: 132 test_true_pfm: 3534.6349067519636 sim_pfm: 426.2550813630708
episode: 528 training return: tensor(420.5378, device='cuda:0')
episode: 529 training return: tensor(440.6082, device='cuda:0')
episode: 530 training return: tensor(433.2597, device='cuda:0')
episode: 531 training return: tensor(460.8767, device='cuda:0')
epoch: 133 test_true_pfm: 3551.853400911807 sim_pfm: 444.97026041324716
episode: 532 training return: tensor(485.2378, device='cuda:0')
episode: 533 training return: tensor(457.4621, device='cuda:0')
episode: 534 training return: tensor(446.4028, device='cuda:0')
episode: 535 training return: tensor(413.3620, device='cuda:0')
epoch: 134 test_true_pfm: 3515.3208465782523 sim_pfm: 425.7125875343918
episode: 536 training return: tensor(422.7241, device='cuda:0')
episode: 537 training return: tensor(438.1626, device='cuda:0')
episode: 538 training return: tensor(438.7121, device='cuda:0')
episode: 539 training return: tensor(431.0002, device='cuda:0')
epoch: 135 test_true_pfm: 3525.574602027212 sim_pfm: 425.47245259125094
episode: 540 training return: tensor(443.4004, device='cuda:0')
episode: 541 training return: tensor(429.5658, device='cuda:0')
episode: 542 training return: tensor(425.6408, device='cuda:0')
episode: 543 training return: tensor(421.1081, device='cuda:0')
epoch: 136 test_true_pfm: 3608.8650771192515 sim_pfm: 484.0060474118897
episode: 544 training return: tensor(417.4710, device='cuda:0')
episode: 545 training return: tensor(468.4651, device='cuda:0')
episode: 546 training return: tensor(417.5978, device='cuda:0')
episode: 547 training return: tensor(424.7375, device='cuda:0')
epoch: 137 test_true_pfm: 3515.9661248937205 sim_pfm: 418.5517329897266
episode: 548 training return: tensor(455.3564, device='cuda:0')
episode: 549 training return: tensor(469.6799, device='cuda:0')
episode: 550 training return: tensor(439.5229, device='cuda:0')
episode: 551 training return: tensor(462.4427, device='cuda:0')
epoch: 138 test_true_pfm: 3592.792003391787 sim_pfm: 473.6400304249837
episode: 552 training return: tensor(438.6085, device='cuda:0')
episode: 553 training return: tensor(433.6866, device='cuda:0')
episode: 554 training return: tensor(453.3140, device='cuda:0')
episode: 555 training return: tensor(481.8724, device='cuda:0')
epoch: 139 test_true_pfm: 3604.7408631841463 sim_pfm: 468.21702590122004
episode: 556 training return: tensor(475.9275, device='cuda:0')
episode: 557 training return: tensor(439.0523, device='cuda:0')
episode: 558 training return: tensor(505.5436, device='cuda:0')
episode: 559 training return: tensor(427.3763, device='cuda:0')
epoch: 140 test_true_pfm: 3568.1545603101313 sim_pfm: 459.89035869552754
episode: 560 training return: tensor(423.3436, device='cuda:0')
episode: 561 training return: tensor(409.6281, device='cuda:0')
episode: 562 training return: tensor(427.7702, device='cuda:0')
episode: 563 training return: tensor(497.3571, device='cuda:0')
epoch: 141 test_true_pfm: 3599.847362877969 sim_pfm: 468.90720503241755
episode: 564 training return: tensor(452.3893, device='cuda:0')
episode: 565 training return: tensor(430.8634, device='cuda:0')
episode: 566 training return: tensor(456.0868, device='cuda:0')
episode: 567 training return: tensor(460.8971, device='cuda:0')
epoch: 142 test_true_pfm: 3578.7841872826357 sim_pfm: 457.01780527325656
episode: 568 training return: tensor(413.5806, device='cuda:0')
episode: 569 training return: tensor(421.5119, device='cuda:0')
episode: 570 training return: tensor(429.2251, device='cuda:0')
episode: 571 training return: tensor(407.3920, device='cuda:0')
epoch: 143 test_true_pfm: 3501.559344681454 sim_pfm: 408.40778073715046
episode: 572 training return: tensor(420.4853, device='cuda:0')
episode: 573 training return: tensor(415.8751, device='cuda:0')
episode: 574 training return: tensor(429.3599, device='cuda:0')
episode: 575 training return: tensor(439.3070, device='cuda:0')
epoch: 144 test_true_pfm: 3550.554388126107 sim_pfm: 443.6182413063264
episode: 576 training return: tensor(444.3369, device='cuda:0')
episode: 577 training return: tensor(440.6402, device='cuda:0')
episode: 578 training return: tensor(457.8034, device='cuda:0')
episode: 579 training return: tensor(431.7631, device='cuda:0')
epoch: 145 test_true_pfm: 3531.488796451158 sim_pfm: 437.1195800535109
episode: 580 training return: tensor(439.1503, device='cuda:0')
episode: 581 training return: tensor(479.3147, device='cuda:0')
episode: 582 training return: tensor(488.1165, device='cuda:0')
episode: 583 training return: tensor(499.0678, device='cuda:0')
epoch: 146 test_true_pfm: 3543.9907287222377 sim_pfm: 432.7716450137086
episode: 584 training return: tensor(440.1941, device='cuda:0')
episode: 585 training return: tensor(398.0775, device='cuda:0')
episode: 586 training return: tensor(437.1043, device='cuda:0')
episode: 587 training return: tensor(460.8767, device='cuda:0')
epoch: 147 test_true_pfm: 3579.2554627464137 sim_pfm: 465.37543896762264
episode: 588 training return: tensor(413.1452, device='cuda:0')
episode: 589 training return: tensor(417.6050, device='cuda:0')
episode: 590 training return: tensor(504.6476, device='cuda:0')
episode: 591 training return: tensor(450.1031, device='cuda:0')
epoch: 148 test_true_pfm: 3564.24227902778 sim_pfm: 454.3357380366263
episode: 592 training return: tensor(458.6938, device='cuda:0')
episode: 593 training return: tensor(438.7925, device='cuda:0')
episode: 594 training return: tensor(445.6904, device='cuda:0')
episode: 595 training return: tensor(462.9303, device='cuda:0')
epoch: 149 test_true_pfm: 3559.884089451551 sim_pfm: 448.98456874633365
episode: 596 training return: tensor(498.6070, device='cuda:0')
episode: 597 training return: tensor(491.7139, device='cuda:0')
episode: 598 training return: tensor(417.1435, device='cuda:0')
episode: 599 training return: tensor(471.4143, device='cuda:0')
epoch: 150 test_true_pfm: 3552.1977927290386 sim_pfm: 447.8014500173255
