['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'behavior', '--traj', 'medium', '--seed', '4', '--data', '100000', '--regu', '0.3']
5092.630754171268
episode: 0 training return: tensor(-454.6393, device='cuda:0')
episode: 1 training return: tensor(-321.8900, device='cuda:0')
episode: 2 training return: tensor(-430.3216, device='cuda:0')
episode: 3 training return: tensor(-368.9871, device='cuda:0')
epoch: 1 test_true_pfm: 4848.684243531019 sim_pfm: -323.2679479472281
episode: 4 training return: tensor(-388.0071, device='cuda:0')
episode: 5 training return: tensor(-377.9658, device='cuda:0')
episode: 6 training return: tensor(-346.4806, device='cuda:0')
episode: 7 training return: tensor(-402.1552, device='cuda:0')
epoch: 2 test_true_pfm: 4917.46248180274 sim_pfm: -241.18869024556867
episode: 8 training return: tensor(-251.6730, device='cuda:0')
episode: 9 training return: tensor(-294.9186, device='cuda:0')
episode: 10 training return: tensor(-378.0132, device='cuda:0')
episode: 11 training return: tensor(-294.6616, device='cuda:0')
epoch: 3 test_true_pfm: 4533.823285411464 sim_pfm: -418.799944493842
episode: 12 training return: tensor(-507.4365, device='cuda:0')
episode: 13 training return: tensor(-223.1547, device='cuda:0')
episode: 14 training return: tensor(-398.0962, device='cuda:0')
episode: 15 training return: tensor(-221.0710, device='cuda:0')
epoch: 4 test_true_pfm: 4999.238759509762 sim_pfm: -259.0952279222353
episode: 16 training return: tensor(-251.9398, device='cuda:0')
episode: 17 training return: tensor(-235.1075, device='cuda:0')
episode: 18 training return: tensor(-225.4909, device='cuda:0')
episode: 19 training return: tensor(-270.6494, device='cuda:0')
epoch: 5 test_true_pfm: 4957.789716532297 sim_pfm: -93.25706300649715
episode: 20 training return: tensor(-76.9981, device='cuda:0')
episode: 21 training return: tensor(-296.9164, device='cuda:0')
episode: 22 training return: tensor(-289.2604, device='cuda:0')
episode: 23 training return: tensor(-298.0464, device='cuda:0')
epoch: 6 test_true_pfm: 5126.075805851405 sim_pfm: 77.13433611065072
episode: 24 training return: tensor(-246.0646, device='cuda:0')
episode: 25 training return: tensor(-252.7954, device='cuda:0')
episode: 26 training return: tensor(-245.4378, device='cuda:0')
episode: 27 training return: tensor(-220.8243, device='cuda:0')
epoch: 7 test_true_pfm: 5104.51012211982 sim_pfm: -53.66883884067647
episode: 28 training return: tensor(-210.7489, device='cuda:0')
episode: 29 training return: tensor(-152.5108, device='cuda:0')
episode: 30 training return: tensor(-167.6599, device='cuda:0')
episode: 31 training return: tensor(-85.4478, device='cuda:0')
epoch: 8 test_true_pfm: 5318.104366742289 sim_pfm: 71.11483072745614
episode: 32 training return: tensor(-116.5281, device='cuda:0')
episode: 33 training return: tensor(-258.7135, device='cuda:0')
episode: 34 training return: tensor(-225.8321, device='cuda:0')
episode: 35 training return: tensor(-200.5704, device='cuda:0')
epoch: 9 test_true_pfm: 5113.516730914783 sim_pfm: 70.41764509657514
episode: 36 training return: tensor(-117.3630, device='cuda:0')
episode: 37 training return: tensor(-212.9406, device='cuda:0')
episode: 38 training return: tensor(-276.3796, device='cuda:0')
episode: 39 training return: tensor(-92.5635, device='cuda:0')
epoch: 10 test_true_pfm: 5158.886485540075 sim_pfm: 81.03945032759414
episode: 40 training return: tensor(-134.2133, device='cuda:0')
episode: 41 training return: tensor(-61.4552, device='cuda:0')
episode: 42 training return: tensor(-136.4758, device='cuda:0')
episode: 43 training return: tensor(-109.9975, device='cuda:0')
epoch: 11 test_true_pfm: 5202.10154993768 sim_pfm: 109.23943692888133
episode: 44 training return: tensor(-447.5578, device='cuda:0')
episode: 45 training return: tensor(-39.1101, device='cuda:0')
episode: 46 training return: tensor(-179.8216, device='cuda:0')
episode: 47 training return: tensor(-14.5115, device='cuda:0')
epoch: 12 test_true_pfm: 5385.067042754185 sim_pfm: 75.81078658691452
episode: 48 training return: tensor(-233.5395, device='cuda:0')
episode: 49 training return: tensor(-24.7940, device='cuda:0')
episode: 50 training return: tensor(-30.6879, device='cuda:0')
episode: 51 training return: tensor(-17.4991, device='cuda:0')
epoch: 13 test_true_pfm: 5454.9824554294855 sim_pfm: 180.65845550932377
episode: 52 training return: tensor(-109.1479, device='cuda:0')
episode: 53 training return: tensor(-31.1379, device='cuda:0')
episode: 54 training return: tensor(-34.4274, device='cuda:0')
episode: 55 training return: tensor(72.0750, device='cuda:0')
epoch: 14 test_true_pfm: 5508.159737287616 sim_pfm: 245.87269532333207
episode: 56 training return: tensor(-71.4944, device='cuda:0')
episode: 57 training return: tensor(9.2809, device='cuda:0')
episode: 58 training return: tensor(1.7212, device='cuda:0')
episode: 59 training return: tensor(-50.5206, device='cuda:0')
epoch: 15 test_true_pfm: 5477.488858401263 sim_pfm: 239.71846316192145
episode: 60 training return: tensor(-4.7669, device='cuda:0')
episode: 61 training return: tensor(89.7485, device='cuda:0')
episode: 62 training return: tensor(105.5066, device='cuda:0')
episode: 63 training return: tensor(54.8311, device='cuda:0')
epoch: 16 test_true_pfm: 5405.042420561897 sim_pfm: 341.177550026332
episode: 64 training return: tensor(-10.5535, device='cuda:0')
episode: 65 training return: tensor(29.8685, device='cuda:0')
episode: 66 training return: tensor(4.8479, device='cuda:0')
episode: 67 training return: tensor(21.4708, device='cuda:0')
epoch: 17 test_true_pfm: 5371.72950242585 sim_pfm: 194.12322486681902
episode: 68 training return: tensor(64.9742, device='cuda:0')
episode: 69 training return: tensor(92.6873, device='cuda:0')
episode: 70 training return: tensor(55.3685, device='cuda:0')
episode: 71 training return: tensor(51.5703, device='cuda:0')
epoch: 18 test_true_pfm: 5542.8152124910075 sim_pfm: 288.09501539098954
episode: 72 training return: tensor(32.4506, device='cuda:0')
episode: 73 training return: tensor(77.6037, device='cuda:0')
episode: 74 training return: tensor(20.5870, device='cuda:0')
episode: 75 training return: tensor(49.3144, device='cuda:0')
epoch: 19 test_true_pfm: 5620.184957259759 sim_pfm: 307.0244332558844
episode: 76 training return: tensor(55.0397, device='cuda:0')
episode: 77 training return: tensor(198.6721, device='cuda:0')
episode: 78 training return: tensor(82.0573, device='cuda:0')
episode: 79 training return: tensor(-21.1405, device='cuda:0')
epoch: 20 test_true_pfm: 5590.168195126706 sim_pfm: 249.34417731642802
episode: 80 training return: tensor(-28.7939, device='cuda:0')
episode: 81 training return: tensor(29.8945, device='cuda:0')
episode: 82 training return: tensor(-16.4963, device='cuda:0')
episode: 83 training return: tensor(49.5242, device='cuda:0')
epoch: 21 test_true_pfm: 5628.227692440095 sim_pfm: 345.5605724134754
episode: 84 training return: tensor(167.6564, device='cuda:0')
episode: 85 training return: tensor(45.4947, device='cuda:0')
episode: 86 training return: tensor(202.1664, device='cuda:0')
episode: 87 training return: tensor(41.7588, device='cuda:0')
epoch: 22 test_true_pfm: 5542.750313212706 sim_pfm: 371.7699752123929
episode: 88 training return: tensor(9.8656, device='cuda:0')
episode: 89 training return: tensor(198.1750, device='cuda:0')
episode: 90 training return: tensor(208.5899, device='cuda:0')
episode: 91 training return: tensor(154.6875, device='cuda:0')
epoch: 23 test_true_pfm: 5628.846792826863 sim_pfm: 344.69787171761465
episode: 92 training return: tensor(207.0753, device='cuda:0')
episode: 93 training return: tensor(274.8144, device='cuda:0')
episode: 94 training return: tensor(273.6222, device='cuda:0')
episode: 95 training return: tensor(234.5934, device='cuda:0')
epoch: 24 test_true_pfm: 5769.264889602303 sim_pfm: 368.7699689013534
episode: 96 training return: tensor(188.5759, device='cuda:0')
episode: 97 training return: tensor(102.0564, device='cuda:0')
episode: 98 training return: tensor(254.8746, device='cuda:0')
episode: 99 training return: tensor(192.2871, device='cuda:0')
epoch: 25 test_true_pfm: 5608.818971468082 sim_pfm: 446.14991939761484
episode: 100 training return: tensor(210.3324, device='cuda:0')
episode: 101 training return: tensor(273.0679, device='cuda:0')
episode: 102 training return: tensor(226.1514, device='cuda:0')
episode: 103 training return: tensor(217.7582, device='cuda:0')
epoch: 26 test_true_pfm: 5645.928155164135 sim_pfm: 370.72274211478845
episode: 104 training return: tensor(323.5795, device='cuda:0')
episode: 105 training return: tensor(219.0910, device='cuda:0')
episode: 106 training return: tensor(173.7787, device='cuda:0')
episode: 107 training return: tensor(190.2618, device='cuda:0')
epoch: 27 test_true_pfm: 5684.254237300676 sim_pfm: 468.1452064161228
episode: 108 training return: tensor(211.0397, device='cuda:0')
episode: 109 training return: tensor(291.7904, device='cuda:0')
episode: 110 training return: tensor(210.8282, device='cuda:0')
episode: 111 training return: tensor(178.6831, device='cuda:0')
epoch: 28 test_true_pfm: 5801.1198502298275 sim_pfm: 468.7424749248894
episode: 112 training return: tensor(307.1138, device='cuda:0')
episode: 113 training return: tensor(260.0435, device='cuda:0')
episode: 114 training return: tensor(241.8034, device='cuda:0')
episode: 115 training return: tensor(387.3779, device='cuda:0')
epoch: 29 test_true_pfm: 5741.786701677239 sim_pfm: 524.5938637833848
episode: 116 training return: tensor(281.5253, device='cuda:0')
episode: 117 training return: tensor(249.6007, device='cuda:0')
episode: 118 training return: tensor(268.4246, device='cuda:0')
episode: 119 training return: tensor(189.3335, device='cuda:0')
epoch: 30 test_true_pfm: 5812.722153143665 sim_pfm: 374.9023029982345
episode: 120 training return: tensor(240.9158, device='cuda:0')
episode: 121 training return: tensor(145.8725, device='cuda:0')
episode: 122 training return: tensor(308.7108, device='cuda:0')
episode: 123 training return: tensor(230.7272, device='cuda:0')
epoch: 31 test_true_pfm: 5844.034257615811 sim_pfm: 491.83797109825537
episode: 124 training return: tensor(337.7251, device='cuda:0')
episode: 125 training return: tensor(228.9720, device='cuda:0')
episode: 126 training return: tensor(338.3476, device='cuda:0')
episode: 127 training return: tensor(319.7737, device='cuda:0')
epoch: 32 test_true_pfm: 5869.922695628046 sim_pfm: 575.7749756874595
episode: 128 training return: tensor(192.8964, device='cuda:0')
episode: 129 training return: tensor(179.4637, device='cuda:0')
episode: 130 training return: tensor(287.8535, device='cuda:0')
episode: 131 training return: tensor(358.2258, device='cuda:0')
epoch: 33 test_true_pfm: 5828.319685399169 sim_pfm: 433.67844954189303
episode: 132 training return: tensor(317.0990, device='cuda:0')
episode: 133 training return: tensor(280.2963, device='cuda:0')
episode: 134 training return: tensor(370.9717, device='cuda:0')
episode: 135 training return: tensor(289.5787, device='cuda:0')
epoch: 34 test_true_pfm: 5959.639307374985 sim_pfm: 506.29978136050823
episode: 136 training return: tensor(291.0160, device='cuda:0')
episode: 137 training return: tensor(354.5546, device='cuda:0')
episode: 138 training return: tensor(310.4089, device='cuda:0')
episode: 139 training return: tensor(289.1708, device='cuda:0')
epoch: 35 test_true_pfm: 5945.923667428131 sim_pfm: 535.9036404527529
episode: 140 training return: tensor(316.1197, device='cuda:0')
episode: 141 training return: tensor(254.7205, device='cuda:0')
episode: 142 training return: tensor(448.7463, device='cuda:0')
episode: 143 training return: tensor(360.0636, device='cuda:0')
epoch: 36 test_true_pfm: 5899.8512139217055 sim_pfm: 515.6476322275508
episode: 144 training return: tensor(217.9674, device='cuda:0')
episode: 145 training return: tensor(212.1876, device='cuda:0')
episode: 146 training return: tensor(290.1518, device='cuda:0')
episode: 147 training return: tensor(388.5967, device='cuda:0')
epoch: 37 test_true_pfm: 5843.884808817435 sim_pfm: 530.473681886661
episode: 148 training return: tensor(341.1405, device='cuda:0')
episode: 149 training return: tensor(366.6058, device='cuda:0')
episode: 150 training return: tensor(285.1134, device='cuda:0')
episode: 151 training return: tensor(356.6149, device='cuda:0')
epoch: 38 test_true_pfm: 5832.354038279039 sim_pfm: 546.871628786088
episode: 152 training return: tensor(382.0237, device='cuda:0')
episode: 153 training return: tensor(361.8723, device='cuda:0')
episode: 154 training return: tensor(443.3998, device='cuda:0')
episode: 155 training return: tensor(283.7631, device='cuda:0')
epoch: 39 test_true_pfm: 5973.3519656089375 sim_pfm: 547.375885961587
episode: 156 training return: tensor(326.1594, device='cuda:0')
episode: 157 training return: tensor(363.9626, device='cuda:0')
episode: 158 training return: tensor(397.2443, device='cuda:0')
episode: 159 training return: tensor(358.5808, device='cuda:0')
epoch: 40 test_true_pfm: 5887.926355967681 sim_pfm: 517.7387500199256
episode: 160 training return: tensor(371.1957, device='cuda:0')
episode: 161 training return: tensor(248.2715, device='cuda:0')
episode: 162 training return: tensor(313.5982, device='cuda:0')
episode: 163 training return: tensor(384.0334, device='cuda:0')
epoch: 41 test_true_pfm: 6020.46761374229 sim_pfm: 598.254796652783
episode: 164 training return: tensor(370.6409, device='cuda:0')
episode: 165 training return: tensor(348.3126, device='cuda:0')
episode: 166 training return: tensor(389.7661, device='cuda:0')
episode: 167 training return: tensor(336.5437, device='cuda:0')
epoch: 42 test_true_pfm: 5948.896034171089 sim_pfm: 553.7062095205474
episode: 168 training return: tensor(378.3163, device='cuda:0')
episode: 169 training return: tensor(312.9757, device='cuda:0')
episode: 170 training return: tensor(281.4468, device='cuda:0')
episode: 171 training return: tensor(371.7000, device='cuda:0')
epoch: 43 test_true_pfm: 5995.704056080638 sim_pfm: 580.4865719026615
episode: 172 training return: tensor(349.3031, device='cuda:0')
episode: 173 training return: tensor(354.7698, device='cuda:0')
episode: 174 training return: tensor(307.0101, device='cuda:0')
episode: 175 training return: tensor(365.7180, device='cuda:0')
epoch: 44 test_true_pfm: 5945.779126872079 sim_pfm: 597.4798921800684
episode: 176 training return: tensor(375.3014, device='cuda:0')
episode: 177 training return: tensor(363.2443, device='cuda:0')
episode: 178 training return: tensor(358.6694, device='cuda:0')
episode: 179 training return: tensor(404.2132, device='cuda:0')
epoch: 45 test_true_pfm: 5937.833397565369 sim_pfm: 542.1523676848932
episode: 180 training return: tensor(303.1184, device='cuda:0')
episode: 181 training return: tensor(340.5658, device='cuda:0')
episode: 182 training return: tensor(437.4729, device='cuda:0')
episode: 183 training return: tensor(365.6584, device='cuda:0')
epoch: 46 test_true_pfm: 6073.031426726164 sim_pfm: 595.2362995051468
episode: 184 training return: tensor(418.4038, device='cuda:0')
episode: 185 training return: tensor(318.5505, device='cuda:0')
episode: 186 training return: tensor(409.2549, device='cuda:0')
episode: 187 training return: tensor(430.5137, device='cuda:0')
epoch: 47 test_true_pfm: 6059.590704946753 sim_pfm: 597.7825139872244
episode: 188 training return: tensor(440.9864, device='cuda:0')
episode: 189 training return: tensor(471.8710, device='cuda:0')
episode: 190 training return: tensor(446.9675, device='cuda:0')
episode: 191 training return: tensor(256.8612, device='cuda:0')
epoch: 48 test_true_pfm: 5975.653276049474 sim_pfm: 630.0833264055545
episode: 192 training return: tensor(423.2634, device='cuda:0')
episode: 193 training return: tensor(413.2654, device='cuda:0')
episode: 194 training return: tensor(405.8668, device='cuda:0')
episode: 195 training return: tensor(451.5392, device='cuda:0')
epoch: 49 test_true_pfm: 5999.700910643026 sim_pfm: 568.8664476824148
episode: 196 training return: tensor(400.7027, device='cuda:0')
episode: 197 training return: tensor(388.5222, device='cuda:0')
episode: 198 training return: tensor(395.9597, device='cuda:0')
episode: 199 training return: tensor(341.5747, device='cuda:0')
epoch: 50 test_true_pfm: 6049.308969286704 sim_pfm: 630.5921361218207
episode: 200 training return: tensor(404.5019, device='cuda:0')
episode: 201 training return: tensor(368.3047, device='cuda:0')
episode: 202 training return: tensor(387.7502, device='cuda:0')
episode: 203 training return: tensor(438.5984, device='cuda:0')
epoch: 51 test_true_pfm: 6088.288824359285 sim_pfm: 614.5070871190013
episode: 204 training return: tensor(455.2077, device='cuda:0')
episode: 205 training return: tensor(492.6021, device='cuda:0')
episode: 206 training return: tensor(444.6021, device='cuda:0')
episode: 207 training return: tensor(464.6983, device='cuda:0')
epoch: 52 test_true_pfm: 5988.138795698913 sim_pfm: 605.4916792262908
episode: 208 training return: tensor(418.0086, device='cuda:0')
episode: 209 training return: tensor(478.8911, device='cuda:0')
episode: 210 training return: tensor(425.0958, device='cuda:0')
episode: 211 training return: tensor(499.8981, device='cuda:0')
epoch: 53 test_true_pfm: 6027.676238186566 sim_pfm: 612.342781701164
episode: 212 training return: tensor(407.3511, device='cuda:0')
episode: 213 training return: tensor(503.9818, device='cuda:0')
episode: 214 training return: tensor(415.1899, device='cuda:0')
episode: 215 training return: tensor(408.9056, device='cuda:0')
epoch: 54 test_true_pfm: 6030.442885863272 sim_pfm: 619.9084403206944
episode: 216 training return: tensor(361.1759, device='cuda:0')
episode: 217 training return: tensor(496.4293, device='cuda:0')
episode: 218 training return: tensor(370.9304, device='cuda:0')
episode: 219 training return: tensor(465.2655, device='cuda:0')
epoch: 55 test_true_pfm: 5997.612887552777 sim_pfm: 622.659773713133
episode: 220 training return: tensor(426.4016, device='cuda:0')
episode: 221 training return: tensor(445.0149, device='cuda:0')
episode: 222 training return: tensor(448.1531, device='cuda:0')
episode: 223 training return: tensor(410.2239, device='cuda:0')
epoch: 56 test_true_pfm: 6091.416462965728 sim_pfm: 608.0437563639911
episode: 224 training return: tensor(384.1015, device='cuda:0')
episode: 225 training return: tensor(475.9176, device='cuda:0')
episode: 226 training return: tensor(432.9248, device='cuda:0')
episode: 227 training return: tensor(464.7800, device='cuda:0')
epoch: 57 test_true_pfm: 5936.287508259024 sim_pfm: 603.0014955847291
episode: 228 training return: tensor(467.3977, device='cuda:0')
episode: 229 training return: tensor(517.7585, device='cuda:0')
episode: 230 training return: tensor(488.4067, device='cuda:0')
episode: 231 training return: tensor(464.9088, device='cuda:0')
epoch: 58 test_true_pfm: 6028.480577983821 sim_pfm: 592.0581919709415
episode: 232 training return: tensor(514.4766, device='cuda:0')
episode: 233 training return: tensor(441.2270, device='cuda:0')
episode: 234 training return: tensor(353.5043, device='cuda:0')
episode: 235 training return: tensor(447.5569, device='cuda:0')
epoch: 59 test_true_pfm: 6077.542691371072 sim_pfm: 641.2185472231553
episode: 236 training return: tensor(463.0283, device='cuda:0')
episode: 237 training return: tensor(457.8527, device='cuda:0')
episode: 238 training return: tensor(399.5353, device='cuda:0')
episode: 239 training return: tensor(473.9659, device='cuda:0')
epoch: 60 test_true_pfm: 6047.255172196204 sim_pfm: 601.8595326174012
episode: 240 training return: tensor(436.5446, device='cuda:0')
episode: 241 training return: tensor(452.2913, device='cuda:0')
episode: 242 training return: tensor(483.3286, device='cuda:0')
episode: 243 training return: tensor(484.2295, device='cuda:0')
epoch: 61 test_true_pfm: 6071.545888096415 sim_pfm: 639.08758295601
episode: 244 training return: tensor(408.4073, device='cuda:0')
episode: 245 training return: tensor(489.5573, device='cuda:0')
episode: 246 training return: tensor(493.8783, device='cuda:0')
episode: 247 training return: tensor(385.2034, device='cuda:0')
epoch: 62 test_true_pfm: 6056.244342855712 sim_pfm: 601.3647954083668
episode: 248 training return: tensor(531.3506, device='cuda:0')
episode: 249 training return: tensor(522.8442, device='cuda:0')
episode: 250 training return: tensor(481.3647, device='cuda:0')
episode: 251 training return: tensor(495.4406, device='cuda:0')
epoch: 63 test_true_pfm: 6173.777560340437 sim_pfm: 630.687711035988
episode: 252 training return: tensor(511.4635, device='cuda:0')
episode: 253 training return: tensor(502.4075, device='cuda:0')
episode: 254 training return: tensor(465.8344, device='cuda:0')
episode: 255 training return: tensor(384.6486, device='cuda:0')
epoch: 64 test_true_pfm: 6108.154740302404 sim_pfm: 610.4381626144362
episode: 256 training return: tensor(534.4341, device='cuda:0')
episode: 257 training return: tensor(433.5551, device='cuda:0')
episode: 258 training return: tensor(517.5477, device='cuda:0')
episode: 259 training return: tensor(505.1295, device='cuda:0')
epoch: 65 test_true_pfm: 6108.182641915669 sim_pfm: 684.9902382044432
episode: 260 training return: tensor(411.1940, device='cuda:0')
episode: 261 training return: tensor(468.6964, device='cuda:0')
episode: 262 training return: tensor(413.1067, device='cuda:0')
episode: 263 training return: tensor(477.4911, device='cuda:0')
epoch: 66 test_true_pfm: 6076.8040339394975 sim_pfm: 653.8331929861257
episode: 264 training return: tensor(457.8797, device='cuda:0')
episode: 265 training return: tensor(482.9502, device='cuda:0')
episode: 266 training return: tensor(386.6346, device='cuda:0')
episode: 267 training return: tensor(516.0988, device='cuda:0')
epoch: 67 test_true_pfm: 6134.0640181929675 sim_pfm: 634.7574960708929
episode: 268 training return: tensor(447.4958, device='cuda:0')
episode: 269 training return: tensor(432.3007, device='cuda:0')
episode: 270 training return: tensor(428.9800, device='cuda:0')
episode: 271 training return: tensor(407.0150, device='cuda:0')
epoch: 68 test_true_pfm: 6106.080430845988 sim_pfm: 652.7170887246806
episode: 272 training return: tensor(425.8269, device='cuda:0')
episode: 273 training return: tensor(516.4079, device='cuda:0')
episode: 274 training return: tensor(510.6985, device='cuda:0')
episode: 275 training return: tensor(433.7944, device='cuda:0')
epoch: 69 test_true_pfm: 6078.735506154241 sim_pfm: 654.9269762850987
episode: 276 training return: tensor(422.3348, device='cuda:0')
episode: 277 training return: tensor(453.9790, device='cuda:0')
episode: 278 training return: tensor(463.2599, device='cuda:0')
episode: 279 training return: tensor(433.5029, device='cuda:0')
epoch: 70 test_true_pfm: 6127.576729047036 sim_pfm: 646.0674325070189
episode: 280 training return: tensor(480.4866, device='cuda:0')
episode: 281 training return: tensor(522.7079, device='cuda:0')
episode: 282 training return: tensor(439.7196, device='cuda:0')
episode: 283 training return: tensor(486.6383, device='cuda:0')
epoch: 71 test_true_pfm: 6097.6189190047035 sim_pfm: 643.5971572414661
episode: 284 training return: tensor(488.8099, device='cuda:0')
episode: 285 training return: tensor(455.0992, device='cuda:0')
episode: 286 training return: tensor(520.2489, device='cuda:0')
episode: 287 training return: tensor(469.2677, device='cuda:0')
epoch: 72 test_true_pfm: 6144.805159131193 sim_pfm: 634.3634857980456
episode: 288 training return: tensor(422.1115, device='cuda:0')
episode: 289 training return: tensor(526.8270, device='cuda:0')
episode: 290 training return: tensor(534.5816, device='cuda:0')
episode: 291 training return: tensor(528.1761, device='cuda:0')
epoch: 73 test_true_pfm: 6139.156602879055 sim_pfm: 661.8777988225144
episode: 292 training return: tensor(507.5588, device='cuda:0')
episode: 293 training return: tensor(538.9052, device='cuda:0')
episode: 294 training return: tensor(550.3390, device='cuda:0')
episode: 295 training return: tensor(481.5355, device='cuda:0')
epoch: 74 test_true_pfm: 6069.378140054668 sim_pfm: 674.8681332624983
episode: 296 training return: tensor(485.5088, device='cuda:0')
episode: 297 training return: tensor(538.0335, device='cuda:0')
episode: 298 training return: tensor(483.8027, device='cuda:0')
episode: 299 training return: tensor(499.9727, device='cuda:0')
epoch: 75 test_true_pfm: 6126.783899412711 sim_pfm: 622.7185392872198
episode: 300 training return: tensor(570.0593, device='cuda:0')
episode: 301 training return: tensor(519.7897, device='cuda:0')
episode: 302 training return: tensor(443.1507, device='cuda:0')
episode: 303 training return: tensor(500.5586, device='cuda:0')
epoch: 76 test_true_pfm: 6119.492564635158 sim_pfm: 623.0937833425318
episode: 304 training return: tensor(522.4791, device='cuda:0')
episode: 305 training return: tensor(465.9672, device='cuda:0')
episode: 306 training return: tensor(440.6400, device='cuda:0')
episode: 307 training return: tensor(529.2753, device='cuda:0')
epoch: 77 test_true_pfm: 6071.597103851699 sim_pfm: 656.1592247022005
episode: 308 training return: tensor(503.2136, device='cuda:0')
episode: 309 training return: tensor(566.1780, device='cuda:0')
episode: 310 training return: tensor(532.3235, device='cuda:0')
episode: 311 training return: tensor(526.2443, device='cuda:0')
epoch: 78 test_true_pfm: 6156.761716864177 sim_pfm: 650.1671754682902
episode: 312 training return: tensor(462.4137, device='cuda:0')
episode: 313 training return: tensor(448.0205, device='cuda:0')
episode: 314 training return: tensor(442.2343, device='cuda:0')
episode: 315 training return: tensor(447.4826, device='cuda:0')
epoch: 79 test_true_pfm: 6155.353077380542 sim_pfm: 652.9420715700835
episode: 316 training return: tensor(523.5814, device='cuda:0')
episode: 317 training return: tensor(512.0952, device='cuda:0')
episode: 318 training return: tensor(512.8169, device='cuda:0')
episode: 319 training return: tensor(474.8138, device='cuda:0')
epoch: 80 test_true_pfm: 6122.207170854065 sim_pfm: 674.5572106344625
episode: 320 training return: tensor(419.8937, device='cuda:0')
episode: 321 training return: tensor(512.2427, device='cuda:0')
episode: 322 training return: tensor(467.0796, device='cuda:0')
episode: 323 training return: tensor(583.3753, device='cuda:0')
epoch: 81 test_true_pfm: 6199.372962879534 sim_pfm: 636.5266794910809
episode: 324 training return: tensor(524.2598, device='cuda:0')
episode: 325 training return: tensor(555.1709, device='cuda:0')
episode: 326 training return: tensor(513.3110, device='cuda:0')
episode: 327 training return: tensor(492.2057, device='cuda:0')
epoch: 82 test_true_pfm: 6193.900979512865 sim_pfm: 659.7599305021964
episode: 328 training return: tensor(511.2617, device='cuda:0')
episode: 329 training return: tensor(467.9645, device='cuda:0')
episode: 330 training return: tensor(558.9264, device='cuda:0')
episode: 331 training return: tensor(553.9182, device='cuda:0')
epoch: 83 test_true_pfm: 6144.55521611986 sim_pfm: 647.0929391315052
episode: 332 training return: tensor(528.5460, device='cuda:0')
episode: 333 training return: tensor(496.3188, device='cuda:0')
episode: 334 training return: tensor(519.3583, device='cuda:0')
episode: 335 training return: tensor(526.5146, device='cuda:0')
epoch: 84 test_true_pfm: 6076.251274827574 sim_pfm: 618.0144218724841
episode: 336 training return: tensor(498.7739, device='cuda:0')
episode: 337 training return: tensor(476.8583, device='cuda:0')
episode: 338 training return: tensor(488.7131, device='cuda:0')
episode: 339 training return: tensor(495.0916, device='cuda:0')
epoch: 85 test_true_pfm: 6132.256293610775 sim_pfm: 613.3944813413449
episode: 340 training return: tensor(450.5964, device='cuda:0')
episode: 341 training return: tensor(544.7512, device='cuda:0')
episode: 342 training return: tensor(541.5353, device='cuda:0')
episode: 343 training return: tensor(578.2094, device='cuda:0')
epoch: 86 test_true_pfm: 6177.661946791111 sim_pfm: 656.5721525745466
episode: 344 training return: tensor(525.5607, device='cuda:0')
episode: 345 training return: tensor(537.8481, device='cuda:0')
episode: 346 training return: tensor(573.7415, device='cuda:0')
episode: 347 training return: tensor(553.6161, device='cuda:0')
epoch: 87 test_true_pfm: 6096.338675095133 sim_pfm: 650.700243830448
episode: 348 training return: tensor(525.4949, device='cuda:0')
episode: 349 training return: tensor(538.1763, device='cuda:0')
episode: 350 training return: tensor(496.5634, device='cuda:0')
episode: 351 training return: tensor(586.5098, device='cuda:0')
epoch: 88 test_true_pfm: 6111.402048116262 sim_pfm: 655.003701362526
episode: 352 training return: tensor(522.3726, device='cuda:0')
episode: 353 training return: tensor(515.3397, device='cuda:0')
episode: 354 training return: tensor(566.6340, device='cuda:0')
episode: 355 training return: tensor(410.7098, device='cuda:0')
epoch: 89 test_true_pfm: 6124.523694480381 sim_pfm: 641.0331858947369
episode: 356 training return: tensor(544.8007, device='cuda:0')
episode: 357 training return: tensor(504.9713, device='cuda:0')
episode: 358 training return: tensor(554.5222, device='cuda:0')
episode: 359 training return: tensor(507.9008, device='cuda:0')
epoch: 90 test_true_pfm: 6222.18960463555 sim_pfm: 658.8575756414406
episode: 360 training return: tensor(475.2919, device='cuda:0')
episode: 361 training return: tensor(460.3424, device='cuda:0')
episode: 362 training return: tensor(523.1469, device='cuda:0')
episode: 363 training return: tensor(514.5344, device='cuda:0')
epoch: 91 test_true_pfm: 6200.444233855499 sim_pfm: 693.7911604436425
episode: 364 training return: tensor(564.4310, device='cuda:0')
episode: 365 training return: tensor(541.7365, device='cuda:0')
episode: 366 training return: tensor(451.9870, device='cuda:0')
episode: 367 training return: tensor(530.6257, device='cuda:0')
epoch: 92 test_true_pfm: 6177.623716392923 sim_pfm: 676.6327803643265
episode: 368 training return: tensor(529.6531, device='cuda:0')
episode: 369 training return: tensor(530.5797, device='cuda:0')
episode: 370 training return: tensor(449.5837, device='cuda:0')
episode: 371 training return: tensor(506.1714, device='cuda:0')
epoch: 93 test_true_pfm: 6182.248472500843 sim_pfm: 684.9681885435324
episode: 372 training return: tensor(499.7479, device='cuda:0')
episode: 373 training return: tensor(558.7974, device='cuda:0')
episode: 374 training return: tensor(558.1987, device='cuda:0')
episode: 375 training return: tensor(532.1375, device='cuda:0')
epoch: 94 test_true_pfm: 6114.164753558446 sim_pfm: 671.6156877444591
episode: 376 training return: tensor(413.5198, device='cuda:0')
episode: 377 training return: tensor(509.2129, device='cuda:0')
episode: 378 training return: tensor(560.7864, device='cuda:0')
episode: 379 training return: tensor(468.9368, device='cuda:0')
epoch: 95 test_true_pfm: 6277.355156755599 sim_pfm: 696.8708072308024
episode: 380 training return: tensor(582.8154, device='cuda:0')
episode: 381 training return: tensor(574.5922, device='cuda:0')
episode: 382 training return: tensor(508.5584, device='cuda:0')
episode: 383 training return: tensor(505.1190, device='cuda:0')
epoch: 96 test_true_pfm: 6204.206098553847 sim_pfm: 680.4299171697348
episode: 384 training return: tensor(509.5287, device='cuda:0')
episode: 385 training return: tensor(488.0735, device='cuda:0')
episode: 386 training return: tensor(479.7078, device='cuda:0')
episode: 387 training return: tensor(549.4692, device='cuda:0')
epoch: 97 test_true_pfm: 6224.966655814457 sim_pfm: 674.5950125807431
episode: 388 training return: tensor(553.9267, device='cuda:0')
episode: 389 training return: tensor(531.4864, device='cuda:0')
episode: 390 training return: tensor(570.8464, device='cuda:0')
episode: 391 training return: tensor(566.4977, device='cuda:0')
epoch: 98 test_true_pfm: 6084.334418550404 sim_pfm: 627.0248168965918
episode: 392 training return: tensor(561.7192, device='cuda:0')
episode: 393 training return: tensor(602.6331, device='cuda:0')
episode: 394 training return: tensor(486.8674, device='cuda:0')
episode: 395 training return: tensor(533.6961, device='cuda:0')
epoch: 99 test_true_pfm: 6155.902450676906 sim_pfm: 665.6955678573964
episode: 396 training return: tensor(484.0882, device='cuda:0')
episode: 397 training return: tensor(519.9514, device='cuda:0')
episode: 398 training return: tensor(565.1027, device='cuda:0')
episode: 399 training return: tensor(552.9212, device='cuda:0')
epoch: 100 test_true_pfm: 6287.324812965521 sim_pfm: 666.7356408541867
episode: 400 training return: tensor(526.0063, device='cuda:0')
episode: 401 training return: tensor(594.6723, device='cuda:0')
episode: 402 training return: tensor(514.9309, device='cuda:0')
episode: 403 training return: tensor(561.5059, device='cuda:0')
epoch: 101 test_true_pfm: 6188.080143913026 sim_pfm: 700.0613598070728
episode: 404 training return: tensor(556.6689, device='cuda:0')
episode: 405 training return: tensor(593.9005, device='cuda:0')
episode: 406 training return: tensor(497.3387, device='cuda:0')
episode: 407 training return: tensor(570.2931, device='cuda:0')
epoch: 102 test_true_pfm: 6271.592523677707 sim_pfm: 682.1404449522961
episode: 408 training return: tensor(531.5588, device='cuda:0')
episode: 409 training return: tensor(536.0378, device='cuda:0')
episode: 410 training return: tensor(538.2408, device='cuda:0')
episode: 411 training return: tensor(531.9712, device='cuda:0')
epoch: 103 test_true_pfm: 6209.9526114577375 sim_pfm: 692.3214742660833
episode: 412 training return: tensor(534.0893, device='cuda:0')
episode: 413 training return: tensor(534.5663, device='cuda:0')
episode: 414 training return: tensor(542.1982, device='cuda:0')
episode: 415 training return: tensor(560.9842, device='cuda:0')
epoch: 104 test_true_pfm: 6177.407342364827 sim_pfm: 665.4611148976643
episode: 416 training return: tensor(415.1426, device='cuda:0')
episode: 417 training return: tensor(500.4577, device='cuda:0')
episode: 418 training return: tensor(560.5727, device='cuda:0')
episode: 419 training return: tensor(585.4124, device='cuda:0')
epoch: 105 test_true_pfm: 6274.387039860553 sim_pfm: 706.8752433791524
episode: 420 training return: tensor(603.6099, device='cuda:0')
episode: 421 training return: tensor(533.6207, device='cuda:0')
episode: 422 training return: tensor(586.8256, device='cuda:0')
episode: 423 training return: tensor(522.3028, device='cuda:0')
epoch: 106 test_true_pfm: 6153.7182255411635 sim_pfm: 710.8216038886845
episode: 424 training return: tensor(560.2039, device='cuda:0')
episode: 425 training return: tensor(532.6265, device='cuda:0')
episode: 426 training return: tensor(605.0252, device='cuda:0')
episode: 427 training return: tensor(607.0264, device='cuda:0')
epoch: 107 test_true_pfm: 6203.871655165217 sim_pfm: 689.5490914676338
episode: 428 training return: tensor(514.4431, device='cuda:0')
episode: 429 training return: tensor(608.6466, device='cuda:0')
episode: 430 training return: tensor(545.5706, device='cuda:0')
episode: 431 training return: tensor(548.4408, device='cuda:0')
epoch: 108 test_true_pfm: 4719.466501443158 sim_pfm: 688.0251479867535
episode: 432 training return: tensor(530.9630, device='cuda:0')
episode: 433 training return: tensor(585.9006, device='cuda:0')
episode: 434 training return: tensor(544.9851, device='cuda:0')
episode: 435 training return: tensor(582.2496, device='cuda:0')
epoch: 109 test_true_pfm: 6249.496246876465 sim_pfm: 715.8520806665474
episode: 436 training return: tensor(503.7795, device='cuda:0')
episode: 437 training return: tensor(567.5249, device='cuda:0')
episode: 438 training return: tensor(545.9763, device='cuda:0')
episode: 439 training return: tensor(518.7279, device='cuda:0')
epoch: 110 test_true_pfm: 6182.077264433986 sim_pfm: 641.3847147489723
episode: 440 training return: tensor(529.7963, device='cuda:0')
episode: 441 training return: tensor(618.5186, device='cuda:0')
episode: 442 training return: tensor(568.7382, device='cuda:0')
episode: 443 training return: tensor(527.9073, device='cuda:0')
epoch: 111 test_true_pfm: 6258.602484145169 sim_pfm: 686.8951556459069
episode: 444 training return: tensor(509.8290, device='cuda:0')
episode: 445 training return: tensor(548.2472, device='cuda:0')
episode: 446 training return: tensor(605.1587, device='cuda:0')
episode: 447 training return: tensor(572.3698, device='cuda:0')
epoch: 112 test_true_pfm: 6214.461937556086 sim_pfm: 691.2413353434822
episode: 448 training return: tensor(476.1306, device='cuda:0')
episode: 449 training return: tensor(510.6128, device='cuda:0')
episode: 450 training return: tensor(630.5140, device='cuda:0')
episode: 451 training return: tensor(534.9644, device='cuda:0')
epoch: 113 test_true_pfm: 6268.515131950761 sim_pfm: 701.1665185707776
episode: 452 training return: tensor(494.1727, device='cuda:0')
episode: 453 training return: tensor(567.8785, device='cuda:0')
episode: 454 training return: tensor(538.6554, device='cuda:0')
episode: 455 training return: tensor(529.5641, device='cuda:0')
epoch: 114 test_true_pfm: 6196.040453147766 sim_pfm: 680.5780331290638
episode: 456 training return: tensor(616.0126, device='cuda:0')
episode: 457 training return: tensor(551.5304, device='cuda:0')
episode: 458 training return: tensor(563.8040, device='cuda:0')
episode: 459 training return: tensor(504.2893, device='cuda:0')
epoch: 115 test_true_pfm: 6305.385921115861 sim_pfm: 707.9807654979522
episode: 460 training return: tensor(601.3340, device='cuda:0')
episode: 461 training return: tensor(564.6363, device='cuda:0')
episode: 462 training return: tensor(549.9988, device='cuda:0')
episode: 463 training return: tensor(553.5429, device='cuda:0')
epoch: 116 test_true_pfm: 6202.520956464777 sim_pfm: 698.9798573728962
episode: 464 training return: tensor(576.8056, device='cuda:0')
episode: 465 training return: tensor(542.3937, device='cuda:0')
episode: 466 training return: tensor(626.0023, device='cuda:0')
episode: 467 training return: tensor(548.3600, device='cuda:0')
epoch: 117 test_true_pfm: 6199.591270996779 sim_pfm: 695.4042078546869
episode: 468 training return: tensor(523.6325, device='cuda:0')
episode: 469 training return: tensor(597.0372, device='cuda:0')
episode: 470 training return: tensor(571.7733, device='cuda:0')
episode: 471 training return: tensor(561.2374, device='cuda:0')
epoch: 118 test_true_pfm: 6188.874490334742 sim_pfm: 671.7742959323417
episode: 472 training return: tensor(551.3990, device='cuda:0')
episode: 473 training return: tensor(577.2903, device='cuda:0')
episode: 474 training return: tensor(601.1558, device='cuda:0')
episode: 475 training return: tensor(580.7275, device='cuda:0')
epoch: 119 test_true_pfm: 6244.159615340995 sim_pfm: 711.1627709748378
episode: 476 training return: tensor(564.2290, device='cuda:0')
episode: 477 training return: tensor(592.6525, device='cuda:0')
episode: 478 training return: tensor(470.0916, device='cuda:0')
episode: 479 training return: tensor(597.1763, device='cuda:0')
epoch: 120 test_true_pfm: 6223.6812826261 sim_pfm: 701.9391560766768
episode: 480 training return: tensor(564.4991, device='cuda:0')
episode: 481 training return: tensor(552.8682, device='cuda:0')
episode: 482 training return: tensor(554.2112, device='cuda:0')
episode: 483 training return: tensor(557.3657, device='cuda:0')
epoch: 121 test_true_pfm: 6181.872828060982 sim_pfm: 683.43848698691
episode: 484 training return: tensor(546.1299, device='cuda:0')
episode: 485 training return: tensor(548.1428, device='cuda:0')
episode: 486 training return: tensor(607.7786, device='cuda:0')
episode: 487 training return: tensor(506.1196, device='cuda:0')
epoch: 122 test_true_pfm: 6285.597942708214 sim_pfm: 726.8198301833278
episode: 488 training return: tensor(552.2086, device='cuda:0')
episode: 489 training return: tensor(573.1776, device='cuda:0')
episode: 490 training return: tensor(597.3509, device='cuda:0')
episode: 491 training return: tensor(566.7499, device='cuda:0')
epoch: 123 test_true_pfm: 6146.473550727923 sim_pfm: 673.1375179165625
episode: 492 training return: tensor(589.1486, device='cuda:0')
episode: 493 training return: tensor(499.9660, device='cuda:0')
episode: 494 training return: tensor(526.3391, device='cuda:0')
episode: 495 training return: tensor(486.2277, device='cuda:0')
epoch: 124 test_true_pfm: 6262.119522832368 sim_pfm: 703.5614845565482
episode: 496 training return: tensor(573.5505, device='cuda:0')
episode: 497 training return: tensor(570.3318, device='cuda:0')
episode: 498 training return: tensor(541.8284, device='cuda:0')
episode: 499 training return: tensor(557.8721, device='cuda:0')
epoch: 125 test_true_pfm: 6282.341563014345 sim_pfm: 720.580029905696
episode: 500 training return: tensor(571.4098, device='cuda:0')
episode: 501 training return: tensor(573.7749, device='cuda:0')
episode: 502 training return: tensor(518.6855, device='cuda:0')
episode: 503 training return: tensor(578.7740, device='cuda:0')
epoch: 126 test_true_pfm: 6326.976514769504 sim_pfm: 722.4853074447407
episode: 504 training return: tensor(532.7618, device='cuda:0')
episode: 505 training return: tensor(525.6244, device='cuda:0')
episode: 506 training return: tensor(516.9759, device='cuda:0')
episode: 507 training return: tensor(591.7455, device='cuda:0')
epoch: 127 test_true_pfm: 6255.543818408068 sim_pfm: 715.7358016421398
episode: 508 training return: tensor(528.3530, device='cuda:0')
episode: 509 training return: tensor(580.1154, device='cuda:0')
episode: 510 training return: tensor(549.5676, device='cuda:0')
episode: 511 training return: tensor(566.1959, device='cuda:0')
epoch: 128 test_true_pfm: 6192.753460666882 sim_pfm: 666.8857418371675
episode: 512 training return: tensor(598.8170, device='cuda:0')
episode: 513 training return: tensor(524.3722, device='cuda:0')
episode: 514 training return: tensor(557.3971, device='cuda:0')
episode: 515 training return: tensor(497.7203, device='cuda:0')
epoch: 129 test_true_pfm: 6196.828682382783 sim_pfm: 668.7831841930456
episode: 516 training return: tensor(562.2164, device='cuda:0')
episode: 517 training return: tensor(582.4894, device='cuda:0')
episode: 518 training return: tensor(601.3002, device='cuda:0')
episode: 519 training return: tensor(569.9390, device='cuda:0')
epoch: 130 test_true_pfm: 6318.324907930946 sim_pfm: 736.5492046508007
episode: 520 training return: tensor(559.0559, device='cuda:0')
episode: 521 training return: tensor(562.6606, device='cuda:0')
episode: 522 training return: tensor(622.7196, device='cuda:0')
episode: 523 training return: tensor(604.8181, device='cuda:0')
epoch: 131 test_true_pfm: 6246.457342224131 sim_pfm: 715.6898273677507
episode: 524 training return: tensor(597.6105, device='cuda:0')
episode: 525 training return: tensor(590.1705, device='cuda:0')
episode: 526 training return: tensor(553.9414, device='cuda:0')
episode: 527 training return: tensor(603.5511, device='cuda:0')
epoch: 132 test_true_pfm: 6208.819882450133 sim_pfm: 712.6173877930074
episode: 528 training return: tensor(589.0565, device='cuda:0')
episode: 529 training return: tensor(528.8386, device='cuda:0')
episode: 530 training return: tensor(575.7775, device='cuda:0')
episode: 531 training return: tensor(580.5109, device='cuda:0')
epoch: 133 test_true_pfm: 6339.943809111249 sim_pfm: 696.7700123100464
episode: 532 training return: tensor(604.3871, device='cuda:0')
episode: 533 training return: tensor(569.6212, device='cuda:0')
episode: 534 training return: tensor(498.1941, device='cuda:0')
episode: 535 training return: tensor(576.7846, device='cuda:0')
epoch: 134 test_true_pfm: 6226.073054666827 sim_pfm: 676.4865429232208
episode: 536 training return: tensor(575.5762, device='cuda:0')
episode: 537 training return: tensor(568.0442, device='cuda:0')
episode: 538 training return: tensor(561.2065, device='cuda:0')
episode: 539 training return: tensor(619.4498, device='cuda:0')
epoch: 135 test_true_pfm: 6259.381879045905 sim_pfm: 702.0235512307845
episode: 540 training return: tensor(550.5531, device='cuda:0')
episode: 541 training return: tensor(589.5129, device='cuda:0')
episode: 542 training return: tensor(576.6106, device='cuda:0')
episode: 543 training return: tensor(522.7589, device='cuda:0')
epoch: 136 test_true_pfm: 6265.988497627466 sim_pfm: 703.4810116315881
episode: 544 training return: tensor(517.6112, device='cuda:0')
episode: 545 training return: tensor(579.0690, device='cuda:0')
episode: 546 training return: tensor(601.1431, device='cuda:0')
episode: 547 training return: tensor(585.3151, device='cuda:0')
epoch: 137 test_true_pfm: 6269.25022562261 sim_pfm: 721.676918057104
episode: 548 training return: tensor(574.9872, device='cuda:0')
episode: 549 training return: tensor(586.6113, device='cuda:0')
episode: 550 training return: tensor(626.2812, device='cuda:0')
episode: 551 training return: tensor(573.1595, device='cuda:0')
epoch: 138 test_true_pfm: 6254.956951717904 sim_pfm: 713.4693465024078
episode: 552 training return: tensor(570.2467, device='cuda:0')
episode: 553 training return: tensor(576.1622, device='cuda:0')
episode: 554 training return: tensor(568.7258, device='cuda:0')
episode: 555 training return: tensor(608.9686, device='cuda:0')
epoch: 139 test_true_pfm: 6316.454278337828 sim_pfm: 723.8495201598076
episode: 556 training return: tensor(580.9617, device='cuda:0')
episode: 557 training return: tensor(586.4243, device='cuda:0')
episode: 558 training return: tensor(576.5925, device='cuda:0')
episode: 559 training return: tensor(576.9066, device='cuda:0')
epoch: 140 test_true_pfm: 6310.715998070408 sim_pfm: 716.2196735790834
episode: 560 training return: tensor(538.9890, device='cuda:0')
episode: 561 training return: tensor(542.5206, device='cuda:0')
episode: 562 training return: tensor(567.6139, device='cuda:0')
episode: 563 training return: tensor(588.0426, device='cuda:0')
epoch: 141 test_true_pfm: 6199.938753501233 sim_pfm: 705.9988627661951
episode: 564 training return: tensor(584.6708, device='cuda:0')
episode: 565 training return: tensor(559.2828, device='cuda:0')
episode: 566 training return: tensor(568.5479, device='cuda:0')
episode: 567 training return: tensor(624.2603, device='cuda:0')
epoch: 142 test_true_pfm: 6258.762247805161 sim_pfm: 708.5107129668662
episode: 568 training return: tensor(586.1841, device='cuda:0')
episode: 569 training return: tensor(571.7225, device='cuda:0')
episode: 570 training return: tensor(591.7108, device='cuda:0')
episode: 571 training return: tensor(586.5669, device='cuda:0')
epoch: 143 test_true_pfm: 6221.086287318528 sim_pfm: 707.3479662220343
episode: 572 training return: tensor(634.7999, device='cuda:0')
episode: 573 training return: tensor(614.8980, device='cuda:0')
episode: 574 training return: tensor(592.1037, device='cuda:0')
episode: 575 training return: tensor(572.1747, device='cuda:0')
epoch: 144 test_true_pfm: 6280.2528640448545 sim_pfm: 741.6871401627237
episode: 576 training return: tensor(590.5649, device='cuda:0')
episode: 577 training return: tensor(591.9102, device='cuda:0')
episode: 578 training return: tensor(548.9349, device='cuda:0')
episode: 579 training return: tensor(627.5956, device='cuda:0')
epoch: 145 test_true_pfm: 6121.1570114325 sim_pfm: 676.5475816863667
episode: 580 training return: tensor(572.9886, device='cuda:0')
episode: 581 training return: tensor(597.4703, device='cuda:0')
episode: 582 training return: tensor(599.1210, device='cuda:0')
episode: 583 training return: tensor(550.3884, device='cuda:0')
epoch: 146 test_true_pfm: 6289.128026873804 sim_pfm: 709.5844816333071
episode: 584 training return: tensor(598.7989, device='cuda:0')
episode: 585 training return: tensor(529.0839, device='cuda:0')
episode: 586 training return: tensor(611.2307, device='cuda:0')
episode: 587 training return: tensor(539.0695, device='cuda:0')
epoch: 147 test_true_pfm: 6326.5470027907095 sim_pfm: 718.1898960205726
episode: 588 training return: tensor(573.5240, device='cuda:0')
episode: 589 training return: tensor(593.8523, device='cuda:0')
episode: 590 training return: tensor(565.7689, device='cuda:0')
episode: 591 training return: tensor(190.2160, device='cuda:0')
epoch: 148 test_true_pfm: 6241.831461848342 sim_pfm: 718.6818710218262
episode: 592 training return: tensor(603.1565, device='cuda:0')
episode: 593 training return: tensor(591.5531, device='cuda:0')
episode: 594 training return: tensor(614.1780, device='cuda:0')
episode: 595 training return: tensor(481.5522, device='cuda:0')
epoch: 149 test_true_pfm: 6308.052779291608 sim_pfm: 745.766993461235
episode: 596 training return: tensor(595.1691, device='cuda:0')
episode: 597 training return: tensor(585.8631, device='cuda:0')
episode: 598 training return: tensor(544.1178, device='cuda:0')
episode: 599 training return: tensor(581.0114, device='cuda:0')
epoch: 150 test_true_pfm: 6364.413518242302 sim_pfm: 731.7062984110477
