['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '2']
episode: 0 training return: tensor(-458.2411, device='cuda:0')
episode: 1 training return: tensor(-635.5112, device='cuda:0')
episode: 2 training return: tensor(-414.6529, device='cuda:0')
episode: 3 training return: tensor(-520.6348, device='cuda:0')
epoch: 1 test_true_pfm: -6.29381783171159 sim_pfm: -627.2007687745305
episode: 4 training return: tensor(-423.5479, device='cuda:0')
episode: 5 training return: tensor(-642.4874, device='cuda:0')
episode: 6 training return: tensor(-438.6059, device='cuda:0')
episode: 7 training return: tensor(-476.8554, device='cuda:0')
epoch: 2 test_true_pfm: -117.99788423527212 sim_pfm: -101.27682013561328
episode: 8 training return: tensor(-349.3192, device='cuda:0')
episode: 9 training return: tensor(-440.3755, device='cuda:0')
episode: 10 training return: tensor(-254.6463, device='cuda:0')
episode: 11 training return: tensor(-369.7236, device='cuda:0')
epoch: 3 test_true_pfm: -8.388164042605696 sim_pfm: -331.7230235983734
episode: 12 training return: tensor(-522.5111, device='cuda:0')
episode: 13 training return: tensor(-301.4337, device='cuda:0')
episode: 14 training return: tensor(-217.3807, device='cuda:0')
episode: 15 training return: tensor(-450.5348, device='cuda:0')
epoch: 4 test_true_pfm: -125.11880638960635 sim_pfm: -491.7065496795597
episode: 16 training return: tensor(-391.7004, device='cuda:0')
episode: 17 training return: tensor(-585.4004, device='cuda:0')
episode: 18 training return: tensor(-594.1088, device='cuda:0')
episode: 19 training return: tensor(-277.5242, device='cuda:0')
epoch: 5 test_true_pfm: 298.2174929127512 sim_pfm: -204.08360188123575
episode: 20 training return: tensor(-217.7279, device='cuda:0')
episode: 21 training return: tensor(-255.5191, device='cuda:0')
episode: 22 training return: tensor(-424.2037, device='cuda:0')
episode: 23 training return: tensor(-477.6458, device='cuda:0')
epoch: 6 test_true_pfm: -81.09613926537567 sim_pfm: -337.1457638924476
episode: 24 training return: tensor(-287.6268, device='cuda:0')
episode: 25 training return: tensor(-49.7745, device='cuda:0')
episode: 26 training return: tensor(169.1180, device='cuda:0')
episode: 27 training return: tensor(131.5909, device='cuda:0')
epoch: 7 test_true_pfm: 35.49556573432313 sim_pfm: 92.63828458481778
episode: 28 training return: tensor(-483.1219, device='cuda:0')
episode: 29 training return: tensor(-465.4601, device='cuda:0')
episode: 30 training return: tensor(-723.6048, device='cuda:0')
episode: 31 training return: tensor(-139.5412, device='cuda:0')
epoch: 8 test_true_pfm: -11.59813779412668 sim_pfm: -569.4722285306392
episode: 32 training return: tensor(-252.8384, device='cuda:0')
episode: 33 training return: tensor(-3.3140, device='cuda:0')
episode: 34 training return: tensor(-292.8763, device='cuda:0')
episode: 35 training return: tensor(-155.0139, device='cuda:0')
epoch: 9 test_true_pfm: 203.87402086014677 sim_pfm: -182.53027569450205
episode: 36 training return: tensor(-13.6847, device='cuda:0')
episode: 37 training return: tensor(-328.9069, device='cuda:0')
episode: 38 training return: tensor(-242.1399, device='cuda:0')
episode: 39 training return: tensor(-230.3847, device='cuda:0')
epoch: 10 test_true_pfm: 180.01039431171873 sim_pfm: -260.8966231139493
episode: 40 training return: tensor(-612.1736, device='cuda:0')
episode: 41 training return: tensor(-691.7115, device='cuda:0')
episode: 42 training return: tensor(-711.9265, device='cuda:0')
episode: 43 training return: tensor(-717.0342, device='cuda:0')
epoch: 11 test_true_pfm: 233.69687948663992 sim_pfm: -712.8207279472457
episode: 44 training return: tensor(-733.3391, device='cuda:0')
episode: 45 training return: tensor(-721.5602, device='cuda:0')
episode: 46 training return: tensor(-685.3370, device='cuda:0')
episode: 47 training return: tensor(-579.7737, device='cuda:0')
epoch: 12 test_true_pfm: 199.64611309861047 sim_pfm: -235.3720090908173
episode: 48 training return: tensor(-535.6074, device='cuda:0')
episode: 49 training return: tensor(-450.1754, device='cuda:0')
episode: 50 training return: tensor(-423.9136, device='cuda:0')
episode: 51 training return: tensor(-487.5162, device='cuda:0')
epoch: 13 test_true_pfm: 123.59856625192594 sim_pfm: -564.0673093556737
episode: 52 training return: tensor(-607.0562, device='cuda:0')
episode: 53 training return: tensor(-565.2231, device='cuda:0')
episode: 54 training return: tensor(-470.3651, device='cuda:0')
episode: 55 training return: tensor(-368.9616, device='cuda:0')
epoch: 14 test_true_pfm: 142.17189335076674 sim_pfm: -247.32139900677916
episode: 56 training return: tensor(-269.6823, device='cuda:0')
episode: 57 training return: tensor(-13.5276, device='cuda:0')
episode: 58 training return: tensor(-606.1490, device='cuda:0')
episode: 59 training return: tensor(-14.6788, device='cuda:0')
epoch: 15 test_true_pfm: 448.27629042935587 sim_pfm: -30.355099634315895
episode: 60 training return: tensor(18.7021, device='cuda:0')
episode: 61 training return: tensor(-44.1995, device='cuda:0')
episode: 62 training return: tensor(-26.0036, device='cuda:0')
episode: 63 training return: tensor(-128.1658, device='cuda:0')
epoch: 16 test_true_pfm: 58.31085508253818 sim_pfm: -101.22394560758646
episode: 64 training return: tensor(91.1067, device='cuda:0')
episode: 65 training return: tensor(77.9425, device='cuda:0')
episode: 66 training return: tensor(-110.4510, device='cuda:0')
episode: 67 training return: tensor(-37.1596, device='cuda:0')
epoch: 17 test_true_pfm: 847.3708365633066 sim_pfm: 127.76203261587459
episode: 68 training return: tensor(50.0399, device='cuda:0')
episode: 69 training return: tensor(-68.0645, device='cuda:0')
episode: 70 training return: tensor(21.1177, device='cuda:0')
episode: 71 training return: tensor(81.3035, device='cuda:0')
epoch: 18 test_true_pfm: 770.1437806424092 sim_pfm: 96.01177527710873
episode: 72 training return: tensor(113.5035, device='cuda:0')
episode: 73 training return: tensor(-251.4929, device='cuda:0')
episode: 74 training return: tensor(-225.2598, device='cuda:0')
episode: 75 training return: tensor(44.8965, device='cuda:0')
epoch: 19 test_true_pfm: 587.0307483337203 sim_pfm: 73.27940488241923
episode: 76 training return: tensor(106.0953, device='cuda:0')
episode: 77 training return: tensor(86.5327, device='cuda:0')
episode: 78 training return: tensor(103.3960, device='cuda:0')
episode: 79 training return: tensor(78.1329, device='cuda:0')
epoch: 20 test_true_pfm: -42.16742080887503 sim_pfm: 100.1612177065108
episode: 80 training return: tensor(119.9457, device='cuda:0')
episode: 81 training return: tensor(112.7668, device='cuda:0')
episode: 82 training return: tensor(72.6446, device='cuda:0')
episode: 83 training return: tensor(144.2060, device='cuda:0')
epoch: 21 test_true_pfm: 985.8944559731627 sim_pfm: 237.9984415944782
episode: 84 training return: tensor(176.2606, device='cuda:0')
episode: 85 training return: tensor(98.6426, device='cuda:0')
episode: 86 training return: tensor(43.1026, device='cuda:0')
episode: 87 training return: tensor(33.6887, device='cuda:0')
epoch: 22 test_true_pfm: 24.402322945235216 sim_pfm: 139.25790608135867
episode: 88 training return: tensor(161.8758, device='cuda:0')
episode: 89 training return: tensor(57.5592, device='cuda:0')
episode: 90 training return: tensor(211.5644, device='cuda:0')
episode: 91 training return: tensor(230.4723, device='cuda:0')
epoch: 23 test_true_pfm: 15.834192630365186 sim_pfm: 94.3682397150745
episode: 92 training return: tensor(74.7367, device='cuda:0')
episode: 93 training return: tensor(72.4293, device='cuda:0')
episode: 94 training return: tensor(176.0373, device='cuda:0')
episode: 95 training return: tensor(121.1739, device='cuda:0')
epoch: 24 test_true_pfm: 32.56212885510825 sim_pfm: 156.44662194233388
episode: 96 training return: tensor(59.4126, device='cuda:0')
episode: 97 training return: tensor(192.6560, device='cuda:0')
episode: 98 training return: tensor(226.0790, device='cuda:0')
episode: 99 training return: tensor(199.5821, device='cuda:0')
epoch: 25 test_true_pfm: 507.93383025789757 sim_pfm: 39.95644053838138
episode: 100 training return: tensor(188.9257, device='cuda:0')
episode: 101 training return: tensor(221.1886, device='cuda:0')
episode: 102 training return: tensor(210.8429, device='cuda:0')
episode: 103 training return: tensor(148.9363, device='cuda:0')
epoch: 26 test_true_pfm: 462.81613883707604 sim_pfm: 90.11428241914837
episode: 104 training return: tensor(149.1843, device='cuda:0')
episode: 105 training return: tensor(164.0665, device='cuda:0')
episode: 106 training return: tensor(211.0622, device='cuda:0')
episode: 107 training return: tensor(151.9456, device='cuda:0')
epoch: 27 test_true_pfm: 1118.4613434407931 sim_pfm: 256.5396833458217
episode: 108 training return: tensor(217.7435, device='cuda:0')
episode: 109 training return: tensor(-1.9108, device='cuda:0')
episode: 110 training return: tensor(198.5589, device='cuda:0')
episode: 111 training return: tensor(156.4967, device='cuda:0')
epoch: 28 test_true_pfm: 31.17659857821052 sim_pfm: 157.23805986358397
episode: 112 training return: tensor(86.9247, device='cuda:0')
episode: 113 training return: tensor(155.6466, device='cuda:0')
episode: 114 training return: tensor(48.4605, device='cuda:0')
episode: 115 training return: tensor(133.9941, device='cuda:0')
epoch: 29 test_true_pfm: 10.842485468652987 sim_pfm: 127.29345464023451
episode: 116 training return: tensor(137.5613, device='cuda:0')
episode: 117 training return: tensor(146.8465, device='cuda:0')
episode: 118 training return: tensor(144.7450, device='cuda:0')
episode: 119 training return: tensor(90.3363, device='cuda:0')
epoch: 30 test_true_pfm: 20.975292118130284 sim_pfm: 129.42793558937652
episode: 120 training return: tensor(248.8308, device='cuda:0')
episode: 121 training return: tensor(145.0086, device='cuda:0')
episode: 122 training return: tensor(205.8185, device='cuda:0')
episode: 123 training return: tensor(272.7936, device='cuda:0')
epoch: 31 test_true_pfm: 18.024055984252964 sim_pfm: -176.5658656259378
episode: 124 training return: tensor(123.7967, device='cuda:0')
episode: 125 training return: tensor(162.6479, device='cuda:0')
episode: 126 training return: tensor(148.3102, device='cuda:0')
episode: 127 training return: tensor(130.1759, device='cuda:0')
epoch: 32 test_true_pfm: 42.562675719654834 sim_pfm: 142.85657988023013
episode: 128 training return: tensor(149.9175, device='cuda:0')
episode: 129 training return: tensor(128.6685, device='cuda:0')
episode: 130 training return: tensor(280.4959, device='cuda:0')
episode: 131 training return: tensor(133.7513, device='cuda:0')
epoch: 33 test_true_pfm: 37.94198724457261 sim_pfm: 160.19896487237807
episode: 132 training return: tensor(69.5317, device='cuda:0')
episode: 133 training return: tensor(177.3405, device='cuda:0')
episode: 134 training return: tensor(144.7020, device='cuda:0')
episode: 135 training return: tensor(144.5741, device='cuda:0')
epoch: 34 test_true_pfm: 376.35672178516415 sim_pfm: 130.0913871790981
episode: 136 training return: tensor(159.8441, device='cuda:0')
episode: 137 training return: tensor(259.6227, device='cuda:0')
episode: 138 training return: tensor(245.9152, device='cuda:0')
episode: 139 training return: tensor(129.8132, device='cuda:0')
epoch: 35 test_true_pfm: 52.63560444603851 sim_pfm: 131.37358232036544
episode: 140 training return: tensor(220.9351, device='cuda:0')
episode: 141 training return: tensor(68.5343, device='cuda:0')
episode: 142 training return: tensor(146.8029, device='cuda:0')
episode: 143 training return: tensor(132.1144, device='cuda:0')
epoch: 36 test_true_pfm: 50.10333611067906 sim_pfm: -226.0094190913563
episode: 144 training return: tensor(134.8421, device='cuda:0')
episode: 145 training return: tensor(127.5404, device='cuda:0')
episode: 146 training return: tensor(89.8520, device='cuda:0')
episode: 147 training return: tensor(130.7662, device='cuda:0')
epoch: 37 test_true_pfm: 38.85208414890019 sim_pfm: 132.5500071334342
episode: 148 training return: tensor(141.0298, device='cuda:0')
episode: 149 training return: tensor(162.3932, device='cuda:0')
episode: 150 training return: tensor(140.5459, device='cuda:0')
episode: 151 training return: tensor(202.0207, device='cuda:0')
epoch: 38 test_true_pfm: 45.931098167561174 sim_pfm: 178.07906150848916
episode: 152 training return: tensor(170.7245, device='cuda:0')
episode: 153 training return: tensor(109.3989, device='cuda:0')
episode: 154 training return: tensor(46.6659, device='cuda:0')
episode: 155 training return: tensor(244.0906, device='cuda:0')
epoch: 39 test_true_pfm: 1234.8300207333161 sim_pfm: 323.6750554679505
episode: 156 training return: tensor(103.5035, device='cuda:0')
episode: 157 training return: tensor(50.1962, device='cuda:0')
episode: 158 training return: tensor(279.3135, device='cuda:0')
episode: 159 training return: tensor(264.6710, device='cuda:0')
epoch: 40 test_true_pfm: 67.59369225439406 sim_pfm: 152.54063858518688
episode: 160 training return: tensor(120.9580, device='cuda:0')
episode: 161 training return: tensor(212.7176, device='cuda:0')
episode: 162 training return: tensor(210.1531, device='cuda:0')
episode: 163 training return: tensor(60.7905, device='cuda:0')
epoch: 41 test_true_pfm: -322.02245745277975 sim_pfm: 370.4083215093124
episode: 164 training return: tensor(113.4578, device='cuda:0')
episode: 165 training return: tensor(296.7220, device='cuda:0')
episode: 166 training return: tensor(309.6324, device='cuda:0')
episode: 167 training return: tensor(267.5421, device='cuda:0')
epoch: 42 test_true_pfm: 626.3171592466256 sim_pfm: 175.440474716248
episode: 168 training return: tensor(247.6130, device='cuda:0')
episode: 169 training return: tensor(286.5984, device='cuda:0')
episode: 170 training return: tensor(337.5367, device='cuda:0')
episode: 171 training return: tensor(283.4630, device='cuda:0')
epoch: 43 test_true_pfm: -84.49423322730254 sim_pfm: 238.34049003897235
episode: 172 training return: tensor(302.7354, device='cuda:0')
episode: 173 training return: tensor(295.3046, device='cuda:0')
episode: 174 training return: tensor(317.0908, device='cuda:0')
episode: 175 training return: tensor(275.6230, device='cuda:0')
epoch: 44 test_true_pfm: 1186.9253886663275 sim_pfm: 286.68514973373385
episode: 176 training return: tensor(320.2106, device='cuda:0')
episode: 177 training return: tensor(324.4004, device='cuda:0')
episode: 178 training return: tensor(298.0065, device='cuda:0')
episode: 179 training return: tensor(297.9530, device='cuda:0')
epoch: 45 test_true_pfm: 1252.4562497563757 sim_pfm: 304.9524972299114
episode: 180 training return: tensor(290.8012, device='cuda:0')
episode: 181 training return: tensor(332.7751, device='cuda:0')
episode: 182 training return: tensor(168.3980, device='cuda:0')
episode: 183 training return: tensor(341.4250, device='cuda:0')
epoch: 46 test_true_pfm: 1337.0634719845455 sim_pfm: 352.2723563436496
episode: 184 training return: tensor(353.8731, device='cuda:0')
episode: 185 training return: tensor(286.7861, device='cuda:0')
episode: 186 training return: tensor(308.7976, device='cuda:0')
episode: 187 training return: tensor(290.2686, device='cuda:0')
epoch: 47 test_true_pfm: 1239.1274359360712 sim_pfm: 329.1000085278938
episode: 188 training return: tensor(186.0674, device='cuda:0')
episode: 189 training return: tensor(278.1688, device='cuda:0')
episode: 190 training return: tensor(196.0143, device='cuda:0')
episode: 191 training return: tensor(305.5280, device='cuda:0')
epoch: 48 test_true_pfm: 1219.7042071822104 sim_pfm: 279.46059687872184
episode: 192 training return: tensor(327.1662, device='cuda:0')
episode: 193 training return: tensor(192.5400, device='cuda:0')
episode: 194 training return: tensor(338.8007, device='cuda:0')
episode: 195 training return: tensor(229.3848, device='cuda:0')
epoch: 49 test_true_pfm: 1464.437758474257 sim_pfm: 392.5644613855111
episode: 196 training return: tensor(51.5107, device='cuda:0')
episode: 197 training return: tensor(321.3892, device='cuda:0')
episode: 198 training return: tensor(296.4699, device='cuda:0')
episode: 199 training return: tensor(153.5859, device='cuda:0')
epoch: 50 test_true_pfm: 1425.7185176699832 sim_pfm: 409.9340063323519
episode: 200 training return: tensor(341.6211, device='cuda:0')
episode: 201 training return: tensor(364.2213, device='cuda:0')
episode: 202 training return: tensor(377.7493, device='cuda:0')
episode: 203 training return: tensor(93.9181, device='cuda:0')
epoch: 51 test_true_pfm: 1375.1807396567663 sim_pfm: 372.4478900473429
episode: 204 training return: tensor(264.0229, device='cuda:0')
episode: 205 training return: tensor(139.3088, device='cuda:0')
episode: 206 training return: tensor(345.9743, device='cuda:0')
episode: 207 training return: tensor(391.8755, device='cuda:0')
epoch: 52 test_true_pfm: 1478.324437156257 sim_pfm: 418.8561629061587
episode: 208 training return: tensor(386.7601, device='cuda:0')
episode: 209 training return: tensor(135.6836, device='cuda:0')
episode: 210 training return: tensor(375.6789, device='cuda:0')
episode: 211 training return: tensor(411.4575, device='cuda:0')
epoch: 53 test_true_pfm: 1443.2268301899555 sim_pfm: 350.97385325236246
episode: 212 training return: tensor(202.0188, device='cuda:0')
episode: 213 training return: tensor(382.7993, device='cuda:0')
episode: 214 training return: tensor(115.4906, device='cuda:0')
episode: 215 training return: tensor(415.2920, device='cuda:0')
epoch: 54 test_true_pfm: 1625.3349596446726 sim_pfm: 483.76663832797203
episode: 216 training return: tensor(265.9098, device='cuda:0')
episode: 217 training return: tensor(108.9888, device='cuda:0')
episode: 218 training return: tensor(381.6246, device='cuda:0')
episode: 219 training return: tensor(138.8391, device='cuda:0')
epoch: 55 test_true_pfm: 1675.731605295471 sim_pfm: 489.8269608454527
episode: 220 training return: tensor(78.8902, device='cuda:0')
episode: 221 training return: tensor(397.2320, device='cuda:0')
episode: 222 training return: tensor(364.2834, device='cuda:0')
episode: 223 training return: tensor(426.5898, device='cuda:0')
epoch: 56 test_true_pfm: 1568.6201550084868 sim_pfm: 451.6618373127906
episode: 224 training return: tensor(419.8271, device='cuda:0')
episode: 225 training return: tensor(370.9563, device='cuda:0')
episode: 226 training return: tensor(447.6292, device='cuda:0')
episode: 227 training return: tensor(405.5537, device='cuda:0')
epoch: 57 test_true_pfm: 1584.49423133289 sim_pfm: 397.7814815551974
episode: 228 training return: tensor(93.4755, device='cuda:0')
episode: 229 training return: tensor(423.0184, device='cuda:0')
episode: 230 training return: tensor(448.3722, device='cuda:0')
episode: 231 training return: tensor(109.8381, device='cuda:0')
epoch: 58 test_true_pfm: 1438.261131542013 sim_pfm: 404.9184821481661
episode: 232 training return: tensor(468.0979, device='cuda:0')
episode: 233 training return: tensor(432.9196, device='cuda:0')
episode: 234 training return: tensor(467.3558, device='cuda:0')
episode: 235 training return: tensor(347.2894, device='cuda:0')
epoch: 59 test_true_pfm: 1522.5788784936801 sim_pfm: 438.52459898179706
episode: 236 training return: tensor(433.5858, device='cuda:0')
episode: 237 training return: tensor(443.7542, device='cuda:0')
episode: 238 training return: tensor(425.3537, device='cuda:0')
episode: 239 training return: tensor(435.1964, device='cuda:0')
epoch: 60 test_true_pfm: 1599.3249009723468 sim_pfm: 371.00872090198874
episode: 240 training return: tensor(198.7854, device='cuda:0')
episode: 241 training return: tensor(186.4413, device='cuda:0')
episode: 242 training return: tensor(195.8545, device='cuda:0')
episode: 243 training return: tensor(434.1133, device='cuda:0')
epoch: 61 test_true_pfm: 1699.3912526585034 sim_pfm: 504.7888762933532
episode: 244 training return: tensor(438.1664, device='cuda:0')
episode: 245 training return: tensor(125.3933, device='cuda:0')
episode: 246 training return: tensor(390.4911, device='cuda:0')
episode: 247 training return: tensor(97.6967, device='cuda:0')
epoch: 62 test_true_pfm: 1844.2869566547 sim_pfm: 574.148903261938
episode: 248 training return: tensor(390.8492, device='cuda:0')
episode: 249 training return: tensor(456.9633, device='cuda:0')
episode: 250 training return: tensor(470.5439, device='cuda:0')
episode: 251 training return: tensor(430.1621, device='cuda:0')
epoch: 63 test_true_pfm: 1919.7522492698997 sim_pfm: 552.062186160639
episode: 252 training return: tensor(474.5100, device='cuda:0')
episode: 253 training return: tensor(409.7337, device='cuda:0')
episode: 254 training return: tensor(491.7657, device='cuda:0')
episode: 255 training return: tensor(195.7966, device='cuda:0')
epoch: 64 test_true_pfm: 1994.1230809891897 sim_pfm: 607.8971233078628
episode: 256 training return: tensor(217.0889, device='cuda:0')
episode: 257 training return: tensor(429.4444, device='cuda:0')
episode: 258 training return: tensor(478.9702, device='cuda:0')
episode: 259 training return: tensor(482.4370, device='cuda:0')
epoch: 65 test_true_pfm: 1712.7151649766765 sim_pfm: 528.0643623439246
episode: 260 training return: tensor(259.0319, device='cuda:0')
episode: 261 training return: tensor(442.1887, device='cuda:0')
episode: 262 training return: tensor(456.1661, device='cuda:0')
episode: 263 training return: tensor(525.1678, device='cuda:0')
epoch: 66 test_true_pfm: 2088.361380225068 sim_pfm: 587.6827284005316
episode: 264 training return: tensor(446.2810, device='cuda:0')
episode: 265 training return: tensor(459.2505, device='cuda:0')
episode: 266 training return: tensor(275.2450, device='cuda:0')
episode: 267 training return: tensor(506.1211, device='cuda:0')
epoch: 67 test_true_pfm: 2013.6895333834084 sim_pfm: 603.8260871103848
episode: 268 training return: tensor(486.2640, device='cuda:0')
episode: 269 training return: tensor(476.1078, device='cuda:0')
episode: 270 training return: tensor(200.8314, device='cuda:0')
episode: 271 training return: tensor(525.9548, device='cuda:0')
epoch: 68 test_true_pfm: 1901.272864961146 sim_pfm: 583.1467008581773
episode: 272 training return: tensor(425.3389, device='cuda:0')
episode: 273 training return: tensor(529.3771, device='cuda:0')
episode: 274 training return: tensor(471.6450, device='cuda:0')
episode: 275 training return: tensor(470.8512, device='cuda:0')
epoch: 69 test_true_pfm: 1898.6508855816146 sim_pfm: 580.5839206046658
episode: 276 training return: tensor(547.6020, device='cuda:0')
episode: 277 training return: tensor(464.6442, device='cuda:0')
episode: 278 training return: tensor(500.7632, device='cuda:0')
episode: 279 training return: tensor(504.5335, device='cuda:0')
epoch: 70 test_true_pfm: 1986.7597016862746 sim_pfm: 486.4094868320972
episode: 280 training return: tensor(515.7006, device='cuda:0')
episode: 281 training return: tensor(497.1247, device='cuda:0')
episode: 282 training return: tensor(446.2559, device='cuda:0')
episode: 283 training return: tensor(545.4450, device='cuda:0')
epoch: 71 test_true_pfm: 1977.3758109722748 sim_pfm: 602.8723717050938
episode: 284 training return: tensor(539.0895, device='cuda:0')
episode: 285 training return: tensor(314.5270, device='cuda:0')
episode: 286 training return: tensor(500.2334, device='cuda:0')
episode: 287 training return: tensor(514.0468, device='cuda:0')
epoch: 72 test_true_pfm: 1955.8184874241194 sim_pfm: 610.6851340131834
episode: 288 training return: tensor(555.9666, device='cuda:0')
episode: 289 training return: tensor(534.6002, device='cuda:0')
episode: 290 training return: tensor(514.0629, device='cuda:0')
episode: 291 training return: tensor(534.4188, device='cuda:0')
epoch: 73 test_true_pfm: 1938.3606173599037 sim_pfm: 602.0508274351014
episode: 292 training return: tensor(205.8884, device='cuda:0')
episode: 293 training return: tensor(198.6552, device='cuda:0')
episode: 294 training return: tensor(205.8011, device='cuda:0')
episode: 295 training return: tensor(519.8196, device='cuda:0')
epoch: 74 test_true_pfm: 2076.911358158905 sim_pfm: 623.4298946145767
episode: 296 training return: tensor(327.9238, device='cuda:0')
episode: 297 training return: tensor(547.5826, device='cuda:0')
episode: 298 training return: tensor(552.8401, device='cuda:0')
episode: 299 training return: tensor(540.6336, device='cuda:0')
epoch: 75 test_true_pfm: 1992.1884041071232 sim_pfm: 619.0416702327784
episode: 300 training return: tensor(513.6400, device='cuda:0')
episode: 301 training return: tensor(491.7791, device='cuda:0')
episode: 302 training return: tensor(538.5305, device='cuda:0')
episode: 303 training return: tensor(561.2212, device='cuda:0')
epoch: 76 test_true_pfm: 2000.65349293348 sim_pfm: 629.6426108959713
episode: 304 training return: tensor(429.8544, device='cuda:0')
episode: 305 training return: tensor(242.2810, device='cuda:0')
episode: 306 training return: tensor(557.4454, device='cuda:0')
episode: 307 training return: tensor(553.5880, device='cuda:0')
epoch: 77 test_true_pfm: 2005.5807922074328 sim_pfm: 617.6191109536061
episode: 308 training return: tensor(498.8235, device='cuda:0')
episode: 309 training return: tensor(576.3598, device='cuda:0')
episode: 310 training return: tensor(580.1446, device='cuda:0')
episode: 311 training return: tensor(546.9592, device='cuda:0')
epoch: 78 test_true_pfm: 2087.404631726291 sim_pfm: 603.4933539665557
episode: 312 training return: tensor(577.5384, device='cuda:0')
episode: 313 training return: tensor(556.6956, device='cuda:0')
episode: 314 training return: tensor(546.6998, device='cuda:0')
episode: 315 training return: tensor(555.3677, device='cuda:0')
epoch: 79 test_true_pfm: 2050.109688500061 sim_pfm: 624.985259302271
episode: 316 training return: tensor(518.9409, device='cuda:0')
episode: 317 training return: tensor(575.4240, device='cuda:0')
episode: 318 training return: tensor(542.5212, device='cuda:0')
episode: 319 training return: tensor(196.7507, device='cuda:0')
epoch: 80 test_true_pfm: 2103.8375555111766 sim_pfm: 644.8586580138654
episode: 320 training return: tensor(497.7353, device='cuda:0')
episode: 321 training return: tensor(351.5130, device='cuda:0')
episode: 322 training return: tensor(553.7137, device='cuda:0')
episode: 323 training return: tensor(575.9119, device='cuda:0')
epoch: 81 test_true_pfm: 2094.492972868147 sim_pfm: 626.3032961423063
episode: 324 training return: tensor(577.9503, device='cuda:0')
episode: 325 training return: tensor(520.1969, device='cuda:0')
episode: 326 training return: tensor(413.7264, device='cuda:0')
episode: 327 training return: tensor(537.6469, device='cuda:0')
epoch: 82 test_true_pfm: 2165.923919527324 sim_pfm: 634.1671706064566
episode: 328 training return: tensor(520.3148, device='cuda:0')
episode: 329 training return: tensor(600.9844, device='cuda:0')
episode: 330 training return: tensor(306.3366, device='cuda:0')
episode: 331 training return: tensor(528.0247, device='cuda:0')
epoch: 83 test_true_pfm: 2107.146894754534 sim_pfm: 621.1706114396802
episode: 332 training return: tensor(568.3339, device='cuda:0')
episode: 333 training return: tensor(580.5370, device='cuda:0')
episode: 334 training return: tensor(556.9506, device='cuda:0')
episode: 335 training return: tensor(556.3298, device='cuda:0')
epoch: 84 test_true_pfm: 2159.2054992285243 sim_pfm: 633.1000043896978
episode: 336 training return: tensor(585.5681, device='cuda:0')
episode: 337 training return: tensor(564.3940, device='cuda:0')
episode: 338 training return: tensor(339.5922, device='cuda:0')
episode: 339 training return: tensor(576.0976, device='cuda:0')
epoch: 85 test_true_pfm: 1661.004827894102 sim_pfm: 458.0762415936527
episode: 340 training return: tensor(523.7128, device='cuda:0')
episode: 341 training return: tensor(192.7817, device='cuda:0')
episode: 342 training return: tensor(561.9205, device='cuda:0')
episode: 343 training return: tensor(580.1287, device='cuda:0')
epoch: 86 test_true_pfm: 2184.125911968346 sim_pfm: 641.6595863306817
episode: 344 training return: tensor(549.6281, device='cuda:0')
episode: 345 training return: tensor(602.9600, device='cuda:0')
episode: 346 training return: tensor(574.9056, device='cuda:0')
episode: 347 training return: tensor(574.0106, device='cuda:0')
epoch: 87 test_true_pfm: 2135.7405013806497 sim_pfm: 597.464884671499
episode: 348 training return: tensor(524.9904, device='cuda:0')
episode: 349 training return: tensor(524.7489, device='cuda:0')
episode: 350 training return: tensor(470.2156, device='cuda:0')
episode: 351 training return: tensor(562.4449, device='cuda:0')
epoch: 88 test_true_pfm: 2208.8664474769607 sim_pfm: 658.2328633502281
episode: 352 training return: tensor(279.9973, device='cuda:0')
episode: 353 training return: tensor(543.8502, device='cuda:0')
episode: 354 training return: tensor(508.2238, device='cuda:0')
episode: 355 training return: tensor(575.9694, device='cuda:0')
epoch: 89 test_true_pfm: 2093.921191982264 sim_pfm: 604.1275504378718
episode: 356 training return: tensor(509.2697, device='cuda:0')
episode: 357 training return: tensor(376.5487, device='cuda:0')
episode: 358 training return: tensor(510.5670, device='cuda:0')
episode: 359 training return: tensor(256.1957, device='cuda:0')
epoch: 90 test_true_pfm: 2184.2973510674706 sim_pfm: 651.7061134923715
episode: 360 training return: tensor(280.6381, device='cuda:0')
episode: 361 training return: tensor(572.5739, device='cuda:0')
episode: 362 training return: tensor(419.3578, device='cuda:0')
episode: 363 training return: tensor(590.9383, device='cuda:0')
epoch: 91 test_true_pfm: 2134.1338541888986 sim_pfm: 653.8582316652561
episode: 364 training return: tensor(272.7683, device='cuda:0')
episode: 365 training return: tensor(509.7558, device='cuda:0')
episode: 366 training return: tensor(348.4482, device='cuda:0')
episode: 367 training return: tensor(552.1940, device='cuda:0')
epoch: 92 test_true_pfm: 2247.891410912327 sim_pfm: 653.2699009881277
episode: 368 training return: tensor(413.8862, device='cuda:0')
episode: 369 training return: tensor(555.9559, device='cuda:0')
episode: 370 training return: tensor(591.8544, device='cuda:0')
episode: 371 training return: tensor(387.8702, device='cuda:0')
epoch: 93 test_true_pfm: 2102.737197924736 sim_pfm: 609.6203121836879
episode: 372 training return: tensor(204.6863, device='cuda:0')
episode: 373 training return: tensor(199.4048, device='cuda:0')
episode: 374 training return: tensor(541.2994, device='cuda:0')
episode: 375 training return: tensor(565.8581, device='cuda:0')
epoch: 94 test_true_pfm: 2227.8375996482832 sim_pfm: 628.4213489587613
episode: 376 training return: tensor(517.4464, device='cuda:0')
episode: 377 training return: tensor(535.8181, device='cuda:0')
episode: 378 training return: tensor(575.3164, device='cuda:0')
episode: 379 training return: tensor(582.3263, device='cuda:0')
epoch: 95 test_true_pfm: 2010.46876740415 sim_pfm: 586.541889272281
episode: 380 training return: tensor(580.8223, device='cuda:0')
episode: 381 training return: tensor(505.7664, device='cuda:0')
episode: 382 training return: tensor(571.7157, device='cuda:0')
episode: 383 training return: tensor(598.1932, device='cuda:0')
epoch: 96 test_true_pfm: 2098.1076490135274 sim_pfm: 585.4272984620766
episode: 384 training return: tensor(616.7944, device='cuda:0')
episode: 385 training return: tensor(573.8128, device='cuda:0')
episode: 386 training return: tensor(583.2836, device='cuda:0')
episode: 387 training return: tensor(578.1666, device='cuda:0')
epoch: 97 test_true_pfm: 2223.062683170846 sim_pfm: 643.6584267111903
episode: 388 training return: tensor(564.8557, device='cuda:0')
episode: 389 training return: tensor(578.4278, device='cuda:0')
episode: 390 training return: tensor(578.1284, device='cuda:0')
episode: 391 training return: tensor(548.1908, device='cuda:0')
epoch: 98 test_true_pfm: 2065.6124020489265 sim_pfm: 525.8854587298507
episode: 392 training return: tensor(556.3576, device='cuda:0')
episode: 393 training return: tensor(588.1135, device='cuda:0')
episode: 394 training return: tensor(597.8817, device='cuda:0')
episode: 395 training return: tensor(572.5212, device='cuda:0')
epoch: 99 test_true_pfm: 2213.2839823116005 sim_pfm: 645.0139411502751
episode: 396 training return: tensor(588.4294, device='cuda:0')
episode: 397 training return: tensor(543.5889, device='cuda:0')
episode: 398 training return: tensor(578.8995, device='cuda:0')
episode: 399 training return: tensor(603.5560, device='cuda:0')
epoch: 100 test_true_pfm: 2260.17360230455 sim_pfm: 626.5764729122166
episode: 400 training return: tensor(540.5771, device='cuda:0')
episode: 401 training return: tensor(544.2769, device='cuda:0')
episode: 402 training return: tensor(576.6249, device='cuda:0')
episode: 403 training return: tensor(569.2130, device='cuda:0')
epoch: 101 test_true_pfm: 2075.7937544164647 sim_pfm: 622.3480033958816
episode: 404 training return: tensor(600.3171, device='cuda:0')
episode: 405 training return: tensor(578.6959, device='cuda:0')
episode: 406 training return: tensor(537.1818, device='cuda:0')
episode: 407 training return: tensor(570.7247, device='cuda:0')
epoch: 102 test_true_pfm: 2111.4876508392426 sim_pfm: 565.6201168553283
episode: 408 training return: tensor(581.3348, device='cuda:0')
episode: 409 training return: tensor(562.9345, device='cuda:0')
episode: 410 training return: tensor(539.2802, device='cuda:0')
episode: 411 training return: tensor(499.2988, device='cuda:0')
epoch: 103 test_true_pfm: 2214.1860478280228 sim_pfm: 633.232613050146
episode: 412 training return: tensor(576.3306, device='cuda:0')
episode: 413 training return: tensor(605.2380, device='cuda:0')
episode: 414 training return: tensor(608.2960, device='cuda:0')
episode: 415 training return: tensor(595.0909, device='cuda:0')
epoch: 104 test_true_pfm: 2344.0746015670206 sim_pfm: 651.5258319133621
episode: 416 training return: tensor(566.7875, device='cuda:0')
episode: 417 training return: tensor(611.5829, device='cuda:0')
episode: 418 training return: tensor(599.5721, device='cuda:0')
episode: 419 training return: tensor(607.6313, device='cuda:0')
epoch: 105 test_true_pfm: 2180.1867817759307 sim_pfm: 661.2963266676719
episode: 420 training return: tensor(600.5255, device='cuda:0')
episode: 421 training return: tensor(571.1301, device='cuda:0')
episode: 422 training return: tensor(597.7016, device='cuda:0')
episode: 423 training return: tensor(559.1641, device='cuda:0')
epoch: 106 test_true_pfm: 2205.243280671298 sim_pfm: 674.5373291313493
episode: 424 training return: tensor(607.7759, device='cuda:0')
episode: 425 training return: tensor(568.1124, device='cuda:0')
episode: 426 training return: tensor(624.4506, device='cuda:0')
episode: 427 training return: tensor(572.4549, device='cuda:0')
epoch: 107 test_true_pfm: 2229.808829364196 sim_pfm: 630.0851792374742
episode: 428 training return: tensor(566.2936, device='cuda:0')
episode: 429 training return: tensor(542.4263, device='cuda:0')
episode: 430 training return: tensor(590.2164, device='cuda:0')
episode: 431 training return: tensor(516.3719, device='cuda:0')
epoch: 108 test_true_pfm: 2286.920042021736 sim_pfm: 665.4598954570247
episode: 432 training return: tensor(587.0413, device='cuda:0')
episode: 433 training return: tensor(581.4277, device='cuda:0')
episode: 434 training return: tensor(560.4387, device='cuda:0')
episode: 435 training return: tensor(587.2050, device='cuda:0')
epoch: 109 test_true_pfm: 2203.359102255206 sim_pfm: 642.993389581466
episode: 436 training return: tensor(594.8655, device='cuda:0')
episode: 437 training return: tensor(571.3104, device='cuda:0')
episode: 438 training return: tensor(572.6650, device='cuda:0')
episode: 439 training return: tensor(589.8978, device='cuda:0')
epoch: 110 test_true_pfm: 2175.107052902418 sim_pfm: 619.0631528074155
episode: 440 training return: tensor(587.9698, device='cuda:0')
episode: 441 training return: tensor(591.8049, device='cuda:0')
episode: 442 training return: tensor(607.2086, device='cuda:0')
episode: 443 training return: tensor(578.0151, device='cuda:0')
epoch: 111 test_true_pfm: 2268.380891084051 sim_pfm: 644.4236490313391
episode: 444 training return: tensor(595.5933, device='cuda:0')
episode: 445 training return: tensor(595.7745, device='cuda:0')
episode: 446 training return: tensor(530.4320, device='cuda:0')
episode: 447 training return: tensor(600.8257, device='cuda:0')
epoch: 112 test_true_pfm: 2215.3673258595595 sim_pfm: 677.6735303376141
episode: 448 training return: tensor(592.1137, device='cuda:0')
episode: 449 training return: tensor(612.1545, device='cuda:0')
episode: 450 training return: tensor(589.0251, device='cuda:0')
episode: 451 training return: tensor(609.8813, device='cuda:0')
epoch: 113 test_true_pfm: 2214.6371621272488 sim_pfm: 646.5583389824993
episode: 452 training return: tensor(572.3644, device='cuda:0')
episode: 453 training return: tensor(578.4851, device='cuda:0')
episode: 454 training return: tensor(570.8794, device='cuda:0')
episode: 455 training return: tensor(591.5640, device='cuda:0')
epoch: 114 test_true_pfm: 2197.24564844971 sim_pfm: 637.1645298161893
episode: 456 training return: tensor(587.0040, device='cuda:0')
episode: 457 training return: tensor(585.6226, device='cuda:0')
episode: 458 training return: tensor(606.4633, device='cuda:0')
episode: 459 training return: tensor(590.0768, device='cuda:0')
epoch: 115 test_true_pfm: 2207.406941399274 sim_pfm: 644.6474294813137
episode: 460 training return: tensor(599.6365, device='cuda:0')
episode: 461 training return: tensor(595.0291, device='cuda:0')
episode: 462 training return: tensor(558.0251, device='cuda:0')
episode: 463 training return: tensor(590.0565, device='cuda:0')
epoch: 116 test_true_pfm: 2160.4041098233974 sim_pfm: 656.1636831894672
episode: 464 training return: tensor(605.0355, device='cuda:0')
episode: 465 training return: tensor(587.9379, device='cuda:0')
episode: 466 training return: tensor(599.9761, device='cuda:0')
episode: 467 training return: tensor(590.1452, device='cuda:0')
epoch: 117 test_true_pfm: 2258.3505120141144 sim_pfm: 648.1725311909491
episode: 468 training return: tensor(567.6837, device='cuda:0')
episode: 469 training return: tensor(570.2745, device='cuda:0')
episode: 470 training return: tensor(584.6027, device='cuda:0')
episode: 471 training return: tensor(609.3585, device='cuda:0')
epoch: 118 test_true_pfm: 2224.1528584364282 sim_pfm: 672.4196048825397
episode: 472 training return: tensor(598.6252, device='cuda:0')
episode: 473 training return: tensor(593.7104, device='cuda:0')
episode: 474 training return: tensor(597.8632, device='cuda:0')
episode: 475 training return: tensor(603.2665, device='cuda:0')
epoch: 119 test_true_pfm: 2318.973635880499 sim_pfm: 663.1738210557572
episode: 476 training return: tensor(567.7551, device='cuda:0')
episode: 477 training return: tensor(601.2140, device='cuda:0')
episode: 478 training return: tensor(622.1752, device='cuda:0')
episode: 479 training return: tensor(595.7017, device='cuda:0')
epoch: 120 test_true_pfm: 2206.4144253179147 sim_pfm: 642.4835448668551
episode: 480 training return: tensor(597.1384, device='cuda:0')
episode: 481 training return: tensor(594.1917, device='cuda:0')
episode: 482 training return: tensor(597.4416, device='cuda:0')
episode: 483 training return: tensor(524.5096, device='cuda:0')
epoch: 121 test_true_pfm: 2001.7388692497668 sim_pfm: 619.215097224107
episode: 484 training return: tensor(609.4197, device='cuda:0')
episode: 485 training return: tensor(594.6680, device='cuda:0')
episode: 486 training return: tensor(572.6115, device='cuda:0')
episode: 487 training return: tensor(621.3605, device='cuda:0')
epoch: 122 test_true_pfm: 2275.725904213682 sim_pfm: 662.4490483274373
episode: 488 training return: tensor(611.9908, device='cuda:0')
episode: 489 training return: tensor(588.5323, device='cuda:0')
episode: 490 training return: tensor(598.6961, device='cuda:0')
episode: 491 training return: tensor(602.4987, device='cuda:0')
epoch: 123 test_true_pfm: 2273.811133117722 sim_pfm: 663.0060008531049
episode: 492 training return: tensor(616.6096, device='cuda:0')
episode: 493 training return: tensor(599.9060, device='cuda:0')
episode: 494 training return: tensor(614.2961, device='cuda:0')
episode: 495 training return: tensor(600.5409, device='cuda:0')
epoch: 124 test_true_pfm: 2214.645107146844 sim_pfm: 638.9688868197845
episode: 496 training return: tensor(594.8992, device='cuda:0')
episode: 497 training return: tensor(583.6637, device='cuda:0')
episode: 498 training return: tensor(609.0382, device='cuda:0')
episode: 499 training return: tensor(612.4960, device='cuda:0')
epoch: 125 test_true_pfm: 2244.037649851231 sim_pfm: 648.2418476272918
episode: 500 training return: tensor(601.1853, device='cuda:0')
episode: 501 training return: tensor(601.0408, device='cuda:0')
episode: 502 training return: tensor(603.7878, device='cuda:0')
episode: 503 training return: tensor(596.4633, device='cuda:0')
epoch: 126 test_true_pfm: 2362.981413384352 sim_pfm: 654.2292253545796
episode: 504 training return: tensor(595.8030, device='cuda:0')
episode: 505 training return: tensor(601.0441, device='cuda:0')
episode: 506 training return: tensor(608.0320, device='cuda:0')
episode: 507 training return: tensor(614.4818, device='cuda:0')
epoch: 127 test_true_pfm: 2356.552882413496 sim_pfm: 655.9330285995189
episode: 508 training return: tensor(603.1142, device='cuda:0')
episode: 509 training return: tensor(602.6245, device='cuda:0')
episode: 510 training return: tensor(577.8076, device='cuda:0')
episode: 511 training return: tensor(586.5132, device='cuda:0')
epoch: 128 test_true_pfm: 2211.8053425948588 sim_pfm: 611.103582052805
episode: 512 training return: tensor(604.9608, device='cuda:0')
episode: 513 training return: tensor(574.8258, device='cuda:0')
episode: 514 training return: tensor(599.6184, device='cuda:0')
episode: 515 training return: tensor(612.8554, device='cuda:0')
epoch: 129 test_true_pfm: 2173.389773683824 sim_pfm: 669.9082084524756
episode: 516 training return: tensor(595.5131, device='cuda:0')
episode: 517 training return: tensor(605.4030, device='cuda:0')
episode: 518 training return: tensor(596.6532, device='cuda:0')
episode: 519 training return: tensor(613.3395, device='cuda:0')
epoch: 130 test_true_pfm: 2289.0631190100144 sim_pfm: 681.137159478385
episode: 520 training return: tensor(570.8725, device='cuda:0')
episode: 521 training return: tensor(596.5164, device='cuda:0')
episode: 522 training return: tensor(613.2166, device='cuda:0')
episode: 523 training return: tensor(605.5510, device='cuda:0')
epoch: 131 test_true_pfm: 2252.3360699792775 sim_pfm: 622.0668035562654
episode: 524 training return: tensor(590.5850, device='cuda:0')
episode: 525 training return: tensor(582.5546, device='cuda:0')
episode: 526 training return: tensor(600.1459, device='cuda:0')
episode: 527 training return: tensor(577.1580, device='cuda:0')
epoch: 132 test_true_pfm: 2317.643931180124 sim_pfm: 672.3973329755439
episode: 528 training return: tensor(575.0947, device='cuda:0')
episode: 529 training return: tensor(615.5554, device='cuda:0')
episode: 530 training return: tensor(602.3485, device='cuda:0')
episode: 531 training return: tensor(599.3606, device='cuda:0')
epoch: 133 test_true_pfm: 2327.8611217016587 sim_pfm: 667.2505083557335
episode: 532 training return: tensor(598.7854, device='cuda:0')
episode: 533 training return: tensor(586.4164, device='cuda:0')
episode: 534 training return: tensor(592.3354, device='cuda:0')
episode: 535 training return: tensor(584.6276, device='cuda:0')
epoch: 134 test_true_pfm: 2279.2749239580357 sim_pfm: 643.2268990192097
episode: 536 training return: tensor(631.4554, device='cuda:0')
episode: 537 training return: tensor(593.8647, device='cuda:0')
episode: 538 training return: tensor(621.6096, device='cuda:0')
episode: 539 training return: tensor(609.8939, device='cuda:0')
epoch: 135 test_true_pfm: 2244.1174711795525 sim_pfm: 653.1351641907822
episode: 540 training return: tensor(250.0333, device='cuda:0')
episode: 541 training return: tensor(594.5239, device='cuda:0')
episode: 542 training return: tensor(605.3362, device='cuda:0')
episode: 543 training return: tensor(603.2518, device='cuda:0')
epoch: 136 test_true_pfm: 2314.520983880464 sim_pfm: 660.8295491190705
episode: 544 training return: tensor(618.0067, device='cuda:0')
episode: 545 training return: tensor(605.5980, device='cuda:0')
episode: 546 training return: tensor(603.9772, device='cuda:0')
episode: 547 training return: tensor(588.6906, device='cuda:0')
epoch: 137 test_true_pfm: 2194.098764094218 sim_pfm: 677.3677241637682
episode: 548 training return: tensor(602.8871, device='cuda:0')
episode: 549 training return: tensor(597.6905, device='cuda:0')
episode: 550 training return: tensor(563.6703, device='cuda:0')
episode: 551 training return: tensor(617.2751, device='cuda:0')
epoch: 138 test_true_pfm: 2310.550798777593 sim_pfm: 676.3897180483327
episode: 552 training return: tensor(626.9069, device='cuda:0')
episode: 553 training return: tensor(609.5869, device='cuda:0')
episode: 554 training return: tensor(604.1479, device='cuda:0')
episode: 555 training return: tensor(575.0696, device='cuda:0')
epoch: 139 test_true_pfm: 2212.5380986996975 sim_pfm: 648.6771773668685
episode: 556 training return: tensor(609.4835, device='cuda:0')
episode: 557 training return: tensor(597.9973, device='cuda:0')
episode: 558 training return: tensor(605.2639, device='cuda:0')
episode: 559 training return: tensor(620.4334, device='cuda:0')
epoch: 140 test_true_pfm: 2388.27465470101 sim_pfm: 676.5387581889421
episode: 560 training return: tensor(611.1740, device='cuda:0')
episode: 561 training return: tensor(569.6486, device='cuda:0')
episode: 562 training return: tensor(593.4528, device='cuda:0')
episode: 563 training return: tensor(613.0060, device='cuda:0')
epoch: 141 test_true_pfm: 2205.3735704067694 sim_pfm: 682.5318952933885
episode: 564 training return: tensor(548.0021, device='cuda:0')
episode: 565 training return: tensor(589.6491, device='cuda:0')
episode: 566 training return: tensor(611.9951, device='cuda:0')
episode: 567 training return: tensor(627.7885, device='cuda:0')
epoch: 142 test_true_pfm: 2257.3470648586135 sim_pfm: 691.2944639213965
episode: 568 training return: tensor(604.7642, device='cuda:0')
episode: 569 training return: tensor(592.5584, device='cuda:0')
episode: 570 training return: tensor(597.8123, device='cuda:0')
episode: 571 training return: tensor(618.9053, device='cuda:0')
epoch: 143 test_true_pfm: 2320.900102041337 sim_pfm: 668.3440599511183
episode: 572 training return: tensor(597.2053, device='cuda:0')
episode: 573 training return: tensor(603.5604, device='cuda:0')
episode: 574 training return: tensor(587.9485, device='cuda:0')
episode: 575 training return: tensor(577.7004, device='cuda:0')
epoch: 144 test_true_pfm: 2324.2496855653403 sim_pfm: 666.3825018456167
episode: 576 training return: tensor(605.7743, device='cuda:0')
episode: 577 training return: tensor(607.7911, device='cuda:0')
episode: 578 training return: tensor(636.3364, device='cuda:0')
episode: 579 training return: tensor(606.5931, device='cuda:0')
epoch: 145 test_true_pfm: 2274.1247241030683 sim_pfm: 658.8833476462556
episode: 580 training return: tensor(608.8136, device='cuda:0')
episode: 581 training return: tensor(577.1267, device='cuda:0')
episode: 582 training return: tensor(603.4761, device='cuda:0')
episode: 583 training return: tensor(547.1050, device='cuda:0')
epoch: 146 test_true_pfm: 2266.9176040033376 sim_pfm: 678.4009742214306
episode: 584 training return: tensor(565.6098, device='cuda:0')
episode: 585 training return: tensor(596.1900, device='cuda:0')
episode: 586 training return: tensor(617.3496, device='cuda:0')
episode: 587 training return: tensor(606.1492, device='cuda:0')
epoch: 147 test_true_pfm: 2298.9727819022232 sim_pfm: 656.3954077310433
episode: 588 training return: tensor(631.8832, device='cuda:0')
episode: 589 training return: tensor(616.7012, device='cuda:0')
episode: 590 training return: tensor(623.8465, device='cuda:0')
episode: 591 training return: tensor(604.3519, device='cuda:0')
epoch: 148 test_true_pfm: 2271.1283211239456 sim_pfm: 678.0660408447729
episode: 592 training return: tensor(598.4182, device='cuda:0')
episode: 593 training return: tensor(625.2837, device='cuda:0')
episode: 594 training return: tensor(641.8963, device='cuda:0')
episode: 595 training return: tensor(633.0646, device='cuda:0')
epoch: 149 test_true_pfm: 2246.3869941827966 sim_pfm: 664.4301278213292
episode: 596 training return: tensor(619.9313, device='cuda:0')
episode: 597 training return: tensor(582.2207, device='cuda:0')
episode: 598 training return: tensor(622.6152, device='cuda:0')
episode: 599 training return: tensor(594.5473, device='cuda:0')
epoch: 150 test_true_pfm: 2289.139301197967 sim_pfm: 671.5524077656349
