131.6205483293597
episode: 0 training return: tensor(207.8561, device='cuda:0')
episode: 1 training return: tensor(204.3487, device='cuda:0')
episode: 2 training return: tensor(208.5609, device='cuda:0')
episode: 3 training return: tensor(205.0380, device='cuda:0')
epoch: 1 test_true_pfm: 126.71646364205904 sim_pfm: 198.54969743065303
episode: 4 training return: tensor(194.8029, device='cuda:0')
episode: 5 training return: tensor(207.1792, device='cuda:0')
episode: 6 training return: tensor(202.3827, device='cuda:0')
episode: 7 training return: tensor(190.0221, device='cuda:0')
epoch: 2 test_true_pfm: 128.91528429788545 sim_pfm: 195.21717608158943
episode: 8 training return: tensor(201.0489, device='cuda:0')
episode: 9 training return: tensor(200.2947, device='cuda:0')
episode: 10 training return: tensor(181.7225, device='cuda:0')
episode: 11 training return: tensor(198.8453, device='cuda:0')
epoch: 3 test_true_pfm: 132.30021249307106 sim_pfm: 184.99867581648286
episode: 12 training return: tensor(198.1924, device='cuda:0')
episode: 13 training return: tensor(182.3842, device='cuda:0')
episode: 14 training return: tensor(211.5645, device='cuda:0')
episode: 15 training return: tensor(199.6551, device='cuda:0')
epoch: 4 test_true_pfm: 136.08255398405475 sim_pfm: 209.9848556539626
episode: 16 training return: tensor(205.4762, device='cuda:0')
episode: 17 training return: tensor(207.4392, device='cuda:0')
episode: 18 training return: tensor(213.8869, device='cuda:0')
episode: 19 training return: tensor(201.2315, device='cuda:0')
epoch: 5 test_true_pfm: 130.89163759425088 sim_pfm: 205.6580086531816
episode: 20 training return: tensor(197.2154, device='cuda:0')
episode: 21 training return: tensor(187.9789, device='cuda:0')
episode: 22 training return: tensor(204.7066, device='cuda:0')
episode: 23 training return: tensor(207.0950, device='cuda:0')
epoch: 6 test_true_pfm: 137.23430622783417 sim_pfm: 202.6335111080378
episode: 24 training return: tensor(200.6434, device='cuda:0')
episode: 25 training return: tensor(207.9635, device='cuda:0')
episode: 26 training return: tensor(175.2182, device='cuda:0')
episode: 27 training return: tensor(206.8848, device='cuda:0')
epoch: 7 test_true_pfm: 134.01068011074972 sim_pfm: 209.47105715597863
episode: 28 training return: tensor(211.5065, device='cuda:0')
episode: 29 training return: tensor(205.7573, device='cuda:0')
episode: 30 training return: tensor(207.8126, device='cuda:0')
episode: 31 training return: tensor(213.3405, device='cuda:0')
epoch: 8 test_true_pfm: 134.43445709071997 sim_pfm: 215.54238649449545
episode: 32 training return: tensor(208.7740, device='cuda:0')
episode: 33 training return: tensor(212.8213, device='cuda:0')
episode: 34 training return: tensor(254.0120, device='cuda:0')
episode: 35 training return: tensor(215.5298, device='cuda:0')
epoch: 9 test_true_pfm: 130.98545052611098 sim_pfm: 223.7043372127693
episode: 36 training return: tensor(211.8114, device='cuda:0')
episode: 37 training return: tensor(211.7906, device='cuda:0')
episode: 38 training return: tensor(204.5619, device='cuda:0')
episode: 39 training return: tensor(195.3534, device='cuda:0')
epoch: 10 test_true_pfm: 135.07664386389467 sim_pfm: 227.15968113063136
episode: 40 training return: tensor(213.7327, device='cuda:0')
episode: 41 training return: tensor(240.2130, device='cuda:0')
episode: 42 training return: tensor(237.4438, device='cuda:0')
episode: 43 training return: tensor(261.7671, device='cuda:0')
epoch: 11 test_true_pfm: 133.4112604024713 sim_pfm: 218.74048196910297
episode: 44 training return: tensor(233.5415, device='cuda:0')
episode: 45 training return: tensor(194.0427, device='cuda:0')
episode: 46 training return: tensor(217.8297, device='cuda:0')
episode: 47 training return: tensor(246.0330, device='cuda:0')
epoch: 12 test_true_pfm: 135.07051509887717 sim_pfm: 224.53624752953766
episode: 48 training return: tensor(210.5128, device='cuda:0')
episode: 49 training return: tensor(200.1108, device='cuda:0')
episode: 50 training return: tensor(225.5451, device='cuda:0')
episode: 51 training return: tensor(240.8422, device='cuda:0')
epoch: 13 test_true_pfm: 135.83764380201816 sim_pfm: 228.32620402345202
episode: 52 training return: tensor(212.3530, device='cuda:0')
episode: 53 training return: tensor(227.0283, device='cuda:0')
episode: 54 training return: tensor(220.3344, device='cuda:0')
episode: 55 training return: tensor(215.3922, device='cuda:0')
epoch: 14 test_true_pfm: 132.63934132570438 sim_pfm: 222.2257727031596
episode: 56 training return: tensor(215.0580, device='cuda:0')
episode: 57 training return: tensor(248.1660, device='cuda:0')
episode: 58 training return: tensor(204.0669, device='cuda:0')
episode: 59 training return: tensor(210.7439, device='cuda:0')
epoch: 15 test_true_pfm: 127.75737570142056 sim_pfm: 223.98518032687716
episode: 60 training return: tensor(225.4913, device='cuda:0')
episode: 61 training return: tensor(266.2561, device='cuda:0')
episode: 62 training return: tensor(203.0163, device='cuda:0')
episode: 63 training return: tensor(226.2116, device='cuda:0')
epoch: 16 test_true_pfm: 131.8613473884868 sim_pfm: 233.84912343106697
episode: 64 training return: tensor(228.5498, device='cuda:0')
episode: 65 training return: tensor(212.7987, device='cuda:0')
episode: 66 training return: tensor(216.0838, device='cuda:0')
episode: 67 training return: tensor(210.7164, device='cuda:0')
epoch: 17 test_true_pfm: 130.62838353743433 sim_pfm: 222.76917606677162
episode: 68 training return: tensor(203.3563, device='cuda:0')
episode: 69 training return: tensor(230.2070, device='cuda:0')
episode: 70 training return: tensor(208.3351, device='cuda:0')
episode: 71 training return: tensor(262.4655, device='cuda:0')
epoch: 18 test_true_pfm: 130.57106860659422 sim_pfm: 238.60957663101144
episode: 72 training return: tensor(254.7003, device='cuda:0')
episode: 73 training return: tensor(259.0106, device='cuda:0')
episode: 74 training return: tensor(256.7166, device='cuda:0')
episode: 75 training return: tensor(207.6775, device='cuda:0')
epoch: 19 test_true_pfm: 130.32493059814604 sim_pfm: 239.82481666279492
episode: 76 training return: tensor(258.5034, device='cuda:0')
episode: 77 training return: tensor(225.3193, device='cuda:0')
episode: 78 training return: tensor(206.0015, device='cuda:0')
episode: 79 training return: tensor(195.0582, device='cuda:0')
epoch: 20 test_true_pfm: 127.71024554887731 sim_pfm: 243.46246223676718
episode: 80 training return: tensor(240.4283, device='cuda:0')
episode: 81 training return: tensor(233.4829, device='cuda:0')
episode: 82 training return: tensor(214.3901, device='cuda:0')
episode: 83 training return: tensor(228.7117, device='cuda:0')
epoch: 21 test_true_pfm: 128.66070051604714 sim_pfm: 230.40911465829703
episode: 84 training return: tensor(254.5904, device='cuda:0')
episode: 85 training return: tensor(239.7512, device='cuda:0')
episode: 86 training return: tensor(238.4256, device='cuda:0')
episode: 87 training return: tensor(207.2224, device='cuda:0')
epoch: 22 test_true_pfm: 134.91970791245183 sim_pfm: 232.6926857081824
episode: 88 training return: tensor(274.1601, device='cuda:0')
episode: 89 training return: tensor(222.1530, device='cuda:0')
episode: 90 training return: tensor(233.2173, device='cuda:0')
episode: 91 training return: tensor(258.8554, device='cuda:0')
epoch: 23 test_true_pfm: 134.11763254646343 sim_pfm: 243.90811311230064
episode: 92 training return: tensor(272.2939, device='cuda:0')
episode: 93 training return: tensor(246.6043, device='cuda:0')
episode: 94 training return: tensor(237.8342, device='cuda:0')
episode: 95 training return: tensor(261.1379, device='cuda:0')
epoch: 24 test_true_pfm: 131.5095423662753 sim_pfm: 250.3659012977965
episode: 96 training return: tensor(247.9966, device='cuda:0')
episode: 97 training return: tensor(263.6717, device='cuda:0')
episode: 98 training return: tensor(246.2825, device='cuda:0')
episode: 99 training return: tensor(205.9631, device='cuda:0')
epoch: 25 test_true_pfm: 131.86864730757623 sim_pfm: 228.6340300002834
episode: 100 training return: tensor(261.2429, device='cuda:0')
episode: 101 training return: tensor(229.1605, device='cuda:0')
episode: 102 training return: tensor(254.2688, device='cuda:0')
episode: 103 training return: tensor(243.2626, device='cuda:0')
epoch: 26 test_true_pfm: 132.93920173350716 sim_pfm: 250.56864106419962
episode: 104 training return: tensor(272.0235, device='cuda:0')
episode: 105 training return: tensor(255.0290, device='cuda:0')
episode: 106 training return: tensor(218.3987, device='cuda:0')
episode: 107 training return: tensor(252.4140, device='cuda:0')
epoch: 27 test_true_pfm: 135.75670962250976 sim_pfm: 280.5061391863972
episode: 108 training return: tensor(224.0468, device='cuda:0')
episode: 109 training return: tensor(279.9888, device='cuda:0')
episode: 110 training return: tensor(288.7858, device='cuda:0')
episode: 111 training return: tensor(281.9773, device='cuda:0')
epoch: 28 test_true_pfm: 128.50814178553 sim_pfm: 243.5103723861219
episode: 112 training return: tensor(274.6248, device='cuda:0')
episode: 113 training return: tensor(290.5008, device='cuda:0')
episode: 114 training return: tensor(263.0546, device='cuda:0')
episode: 115 training return: tensor(275.9992, device='cuda:0')
epoch: 29 test_true_pfm: 133.5947775566572 sim_pfm: 262.40519907758573
episode: 116 training return: tensor(276.6369, device='cuda:0')
episode: 117 training return: tensor(257.0698, device='cuda:0')
episode: 118 training return: tensor(289.5731, device='cuda:0')
episode: 119 training return: tensor(236.8878, device='cuda:0')
epoch: 30 test_true_pfm: 128.05219019829377 sim_pfm: 260.4575427483418
episode: 120 training return: tensor(237.3117, device='cuda:0')
episode: 121 training return: tensor(270.9994, device='cuda:0')
episode: 122 training return: tensor(216.2768, device='cuda:0')
episode: 123 training return: tensor(220.7691, device='cuda:0')
epoch: 31 test_true_pfm: 137.0661200650154 sim_pfm: 250.28376420154237
episode: 124 training return: tensor(274.5869, device='cuda:0')
episode: 125 training return: tensor(240.6919, device='cuda:0')
episode: 126 training return: tensor(262.4967, device='cuda:0')
episode: 127 training return: tensor(290.4599, device='cuda:0')
epoch: 32 test_true_pfm: 128.37846786238342 sim_pfm: 267.7536008390598
episode: 128 training return: tensor(270.6017, device='cuda:0')
episode: 129 training return: tensor(288.7111, device='cuda:0')
episode: 130 training return: tensor(273.1486, device='cuda:0')
episode: 131 training return: tensor(244.9504, device='cuda:0')
epoch: 33 test_true_pfm: 137.57584670789842 sim_pfm: 252.63034195515792
episode: 132 training return: tensor(257.3046, device='cuda:0')
episode: 133 training return: tensor(212.2579, device='cuda:0')
episode: 134 training return: tensor(233.8744, device='cuda:0')
episode: 135 training return: tensor(271.2144, device='cuda:0')
epoch: 34 test_true_pfm: 138.93900245501555 sim_pfm: 275.3342864159378
episode: 136 training return: tensor(274.0986, device='cuda:0')
episode: 137 training return: tensor(276.4443, device='cuda:0')
episode: 138 training return: tensor(261.9939, device='cuda:0')
episode: 139 training return: tensor(227.3965, device='cuda:0')
epoch: 35 test_true_pfm: 134.70898880563465 sim_pfm: 263.9053811846767
episode: 140 training return: tensor(261.5276, device='cuda:0')
episode: 141 training return: tensor(262.4099, device='cuda:0')
episode: 142 training return: tensor(228.5173, device='cuda:0')
episode: 143 training return: tensor(290.5277, device='cuda:0')
epoch: 36 test_true_pfm: 138.0798191778439 sim_pfm: 258.4642325859983
episode: 144 training return: tensor(280.4994, device='cuda:0')
episode: 145 training return: tensor(211.3306, device='cuda:0')
episode: 146 training return: tensor(214.4960, device='cuda:0')
episode: 147 training return: tensor(229.0626, device='cuda:0')
epoch: 37 test_true_pfm: 136.66750349125 sim_pfm: 275.5815322270617
episode: 148 training return: tensor(225.9443, device='cuda:0')
episode: 149 training return: tensor(251.5317, device='cuda:0')
episode: 150 training return: tensor(272.4517, device='cuda:0')
episode: 151 training return: tensor(248.1438, device='cuda:0')
epoch: 38 test_true_pfm: 136.80644995690744 sim_pfm: 244.24361916074994
episode: 152 training return: tensor(279.5906, device='cuda:0')
episode: 153 training return: tensor(260.0414, device='cuda:0')
episode: 154 training return: tensor(294.3995, device='cuda:0')
episode: 155 training return: tensor(289.5556, device='cuda:0')
epoch: 39 test_true_pfm: 126.4729506725935 sim_pfm: 232.16747647394658
episode: 156 training return: tensor(238.1266, device='cuda:0')
episode: 157 training return: tensor(229.0052, device='cuda:0')
episode: 158 training return: tensor(265.4518, device='cuda:0')
episode: 159 training return: tensor(220.9416, device='cuda:0')
epoch: 40 test_true_pfm: 127.4074095296356 sim_pfm: 229.58031214906367
episode: 160 training return: tensor(221.3926, device='cuda:0')
episode: 161 training return: tensor(238.5279, device='cuda:0')
episode: 162 training return: tensor(219.7898, device='cuda:0')
episode: 163 training return: tensor(289.7213, device='cuda:0')
epoch: 41 test_true_pfm: 131.39260993829515 sim_pfm: 287.1708541899919
episode: 164 training return: tensor(269.8203, device='cuda:0')
episode: 165 training return: tensor(259.1918, device='cuda:0')
episode: 166 training return: tensor(236.1131, device='cuda:0')
episode: 167 training return: tensor(221.3467, device='cuda:0')
epoch: 42 test_true_pfm: 135.10030944691633 sim_pfm: 251.29464001611342
episode: 168 training return: tensor(211.1191, device='cuda:0')
episode: 169 training return: tensor(269.5140, device='cuda:0')
episode: 170 training return: tensor(273.5518, device='cuda:0')
episode: 171 training return: tensor(275.3256, device='cuda:0')
epoch: 43 test_true_pfm: 132.24031506209218 sim_pfm: 275.28923710896635
episode: 172 training return: tensor(219.2116, device='cuda:0')
episode: 173 training return: tensor(268.1350, device='cuda:0')
episode: 174 training return: tensor(265.3461, device='cuda:0')
episode: 175 training return: tensor(272.1683, device='cuda:0')
epoch: 44 test_true_pfm: 139.38955523133836 sim_pfm: 269.1095860810834
episode: 176 training return: tensor(288.1424, device='cuda:0')
episode: 177 training return: tensor(273.1390, device='cuda:0')
episode: 178 training return: tensor(217.1763, device='cuda:0')
episode: 179 training return: tensor(279.0080, device='cuda:0')
epoch: 45 test_true_pfm: 133.50090719908746 sim_pfm: 249.86718491589417
episode: 180 training return: tensor(274.2173, device='cuda:0')
episode: 181 training return: tensor(276.8759, device='cuda:0')
episode: 182 training return: tensor(278.2460, device='cuda:0')
episode: 183 training return: tensor(240.4213, device='cuda:0')
epoch: 46 test_true_pfm: 142.32267571153898 sim_pfm: 269.73108192603104
episode: 184 training return: tensor(274.9783, device='cuda:0')
episode: 185 training return: tensor(282.6641, device='cuda:0')
episode: 186 training return: tensor(213.3762, device='cuda:0')
episode: 187 training return: tensor(275.9422, device='cuda:0')
epoch: 47 test_true_pfm: 132.87154700365878 sim_pfm: 274.5009391867323
episode: 188 training return: tensor(212.5783, device='cuda:0')
episode: 189 training return: tensor(216.2995, device='cuda:0')
episode: 190 training return: tensor(271.4116, device='cuda:0')
episode: 191 training return: tensor(262.8757, device='cuda:0')
epoch: 48 test_true_pfm: 135.92412471783268 sim_pfm: 276.0302087993012
episode: 192 training return: tensor(276.2209, device='cuda:0')
episode: 193 training return: tensor(270.2713, device='cuda:0')
episode: 194 training return: tensor(254.9571, device='cuda:0')
episode: 195 training return: tensor(271.2415, device='cuda:0')
epoch: 49 test_true_pfm: 141.29485865582512 sim_pfm: 281.3924623395316
episode: 196 training return: tensor(265.6272, device='cuda:0')
episode: 197 training return: tensor(267.2092, device='cuda:0')
episode: 198 training return: tensor(273.4519, device='cuda:0')
episode: 199 training return: tensor(287.3737, device='cuda:0')
epoch: 50 test_true_pfm: 133.65459166409818 sim_pfm: 266.76090623706114
episode: 200 training return: tensor(264.7299, device='cuda:0')
episode: 201 training return: tensor(241.4479, device='cuda:0')
episode: 202 training return: tensor(246.9178, device='cuda:0')
episode: 203 training return: tensor(272.1718, device='cuda:0')
epoch: 51 test_true_pfm: 134.2160559574974 sim_pfm: 231.94884746472817
episode: 204 training return: tensor(276.5106, device='cuda:0')
episode: 205 training return: tensor(227.2600, device='cuda:0')
episode: 206 training return: tensor(280.4810, device='cuda:0')
episode: 207 training return: tensor(270.1039, device='cuda:0')
epoch: 52 test_true_pfm: 137.38021131268886 sim_pfm: 280.39573566436303
episode: 208 training return: tensor(255.2270, device='cuda:0')
episode: 209 training return: tensor(268.0543, device='cuda:0')
episode: 210 training return: tensor(280.9534, device='cuda:0')
episode: 211 training return: tensor(260.1423, device='cuda:0')
epoch: 53 test_true_pfm: 135.56504454342377 sim_pfm: 265.1095616334584
episode: 212 training return: tensor(272.2894, device='cuda:0')
episode: 213 training return: tensor(271.4617, device='cuda:0')
episode: 214 training return: tensor(283.3560, device='cuda:0')
episode: 215 training return: tensor(281.4958, device='cuda:0')
epoch: 54 test_true_pfm: 130.78069619766217 sim_pfm: 254.6829266170971
episode: 216 training return: tensor(288.2534, device='cuda:0')
episode: 217 training return: tensor(208.9677, device='cuda:0')
episode: 218 training return: tensor(289.2874, device='cuda:0')
episode: 219 training return: tensor(288.9190, device='cuda:0')
epoch: 55 test_true_pfm: 126.52064322290485 sim_pfm: 259.912912260578
episode: 220 training return: tensor(247.5433, device='cuda:0')
episode: 221 training return: tensor(293.2656, device='cuda:0')
episode: 222 training return: tensor(289.2346, device='cuda:0')
episode: 223 training return: tensor(277.6885, device='cuda:0')
epoch: 56 test_true_pfm: 138.18773116991184 sim_pfm: 249.347635978373
episode: 224 training return: tensor(216.9112, device='cuda:0')
episode: 225 training return: tensor(272.0283, device='cuda:0')
episode: 226 training return: tensor(230.4582, device='cuda:0')
episode: 227 training return: tensor(285.3748, device='cuda:0')
epoch: 57 test_true_pfm: 136.27969027952895 sim_pfm: 261.79550566291437
episode: 228 training return: tensor(286.0757, device='cuda:0')
episode: 229 training return: tensor(263.1510, device='cuda:0')
episode: 230 training return: tensor(230.3823, device='cuda:0')
episode: 231 training return: tensor(284.6686, device='cuda:0')
epoch: 58 test_true_pfm: 136.97165725160832 sim_pfm: 271.74918187069704
episode: 232 training return: tensor(286.4608, device='cuda:0')
episode: 233 training return: tensor(286.1989, device='cuda:0')
episode: 234 training return: tensor(270.2153, device='cuda:0')
episode: 235 training return: tensor(249.1880, device='cuda:0')
epoch: 59 test_true_pfm: 137.7923647894229 sim_pfm: 269.8383269598824
episode: 236 training return: tensor(259.4845, device='cuda:0')
episode: 237 training return: tensor(261.4660, device='cuda:0')
episode: 238 training return: tensor(205.5902, device='cuda:0')
episode: 239 training return: tensor(285.1107, device='cuda:0')
epoch: 60 test_true_pfm: 137.4897803092689 sim_pfm: 282.406125409808
episode: 240 training return: tensor(247.6767, device='cuda:0')
episode: 241 training return: tensor(255.1963, device='cuda:0')
episode: 242 training return: tensor(254.7596, device='cuda:0')
episode: 243 training return: tensor(286.4179, device='cuda:0')
epoch: 61 test_true_pfm: 141.445640745292 sim_pfm: 258.26673564114606
episode: 244 training return: tensor(268.7898, device='cuda:0')
episode: 245 training return: tensor(270.2955, device='cuda:0')
episode: 246 training return: tensor(280.1755, device='cuda:0')
episode: 247 training return: tensor(283.6426, device='cuda:0')
epoch: 62 test_true_pfm: 131.82261819978788 sim_pfm: 260.01038649803377
episode: 248 training return: tensor(266.0807, device='cuda:0')
episode: 249 training return: tensor(269.8222, device='cuda:0')
episode: 250 training return: tensor(270.9023, device='cuda:0')
episode: 251 training return: tensor(265.8353, device='cuda:0')
epoch: 63 test_true_pfm: 139.82198594740265 sim_pfm: 269.1226464397914
episode: 252 training return: tensor(274.9996, device='cuda:0')
episode: 253 training return: tensor(275.1499, device='cuda:0')
episode: 254 training return: tensor(264.3487, device='cuda:0')
episode: 255 training return: tensor(208.9017, device='cuda:0')
epoch: 64 test_true_pfm: 140.38341868412618 sim_pfm: 273.617088445829
episode: 256 training return: tensor(290.0748, device='cuda:0')
episode: 257 training return: tensor(277.3168, device='cuda:0')
episode: 258 training return: tensor(262.5067, device='cuda:0')
episode: 259 training return: tensor(253.3427, device='cuda:0')
epoch: 65 test_true_pfm: 134.18482434607614 sim_pfm: 265.97130621844553
episode: 260 training return: tensor(289.5415, device='cuda:0')
episode: 261 training return: tensor(249.7374, device='cuda:0')
episode: 262 training return: tensor(287.1576, device='cuda:0')
episode: 263 training return: tensor(248.3049, device='cuda:0')
epoch: 66 test_true_pfm: 136.82136489928402 sim_pfm: 267.1431802393287
episode: 264 training return: tensor(280.1590, device='cuda:0')
episode: 265 training return: tensor(276.5356, device='cuda:0')
episode: 266 training return: tensor(291.1191, device='cuda:0')
episode: 267 training return: tensor(276.0321, device='cuda:0')
epoch: 67 test_true_pfm: 139.22255190304918 sim_pfm: 255.22585899168627
episode: 268 training return: tensor(274.3449, device='cuda:0')
episode: 269 training return: tensor(264.5559, device='cuda:0')
episode: 270 training return: tensor(253.8090, device='cuda:0')
episode: 271 training return: tensor(211.3827, device='cuda:0')
epoch: 68 test_true_pfm: 138.53047132156078 sim_pfm: 254.8701723686303
episode: 272 training return: tensor(252.5360, device='cuda:0')
episode: 273 training return: tensor(287.9188, device='cuda:0')
episode: 274 training return: tensor(242.6792, device='cuda:0')
episode: 275 training return: tensor(261.7286, device='cuda:0')
epoch: 69 test_true_pfm: 134.91344007070973 sim_pfm: 264.86826887205245
episode: 276 training return: tensor(254.7648, device='cuda:0')
episode: 277 training return: tensor(259.5177, device='cuda:0')
episode: 278 training return: tensor(251.3105, device='cuda:0')
episode: 279 training return: tensor(231.7850, device='cuda:0')
epoch: 70 test_true_pfm: 133.99620096087702 sim_pfm: 273.4394237341883
episode: 280 training return: tensor(250.3843, device='cuda:0')
episode: 281 training return: tensor(268.9631, device='cuda:0')
episode: 282 training return: tensor(286.4584, device='cuda:0')
episode: 283 training return: tensor(276.2004, device='cuda:0')
epoch: 71 test_true_pfm: 133.9896439334059 sim_pfm: 265.3694358380511
episode: 284 training return: tensor(266.3025, device='cuda:0')
episode: 285 training return: tensor(288.9448, device='cuda:0')
episode: 286 training return: tensor(256.5963, device='cuda:0')
episode: 287 training return: tensor(291.4416, device='cuda:0')
epoch: 72 test_true_pfm: 140.88870106425833 sim_pfm: 256.90925849502673
episode: 288 training return: tensor(271.3846, device='cuda:0')
episode: 289 training return: tensor(245.4139, device='cuda:0')
episode: 290 training return: tensor(270.2116, device='cuda:0')
episode: 291 training return: tensor(242.6358, device='cuda:0')
epoch: 73 test_true_pfm: 137.55209451823623 sim_pfm: 255.90372101062675
episode: 292 training return: tensor(285.8816, device='cuda:0')
episode: 293 training return: tensor(271.1027, device='cuda:0')
episode: 294 training return: tensor(268.8624, device='cuda:0')
episode: 295 training return: tensor(252.2444, device='cuda:0')
epoch: 74 test_true_pfm: 143.07063935068348 sim_pfm: 286.377539161779
episode: 296 training return: tensor(267.8876, device='cuda:0')
episode: 297 training return: tensor(252.2903, device='cuda:0')
episode: 298 training return: tensor(279.0082, device='cuda:0')
episode: 299 training return: tensor(248.8950, device='cuda:0')
epoch: 75 test_true_pfm: 139.10845446967815 sim_pfm: 282.19256226301076
episode: 300 training return: tensor(237.5419, device='cuda:0')
episode: 301 training return: tensor(271.1016, device='cuda:0')
episode: 302 training return: tensor(278.7931, device='cuda:0')
episode: 303 training return: tensor(219.1402, device='cuda:0')
epoch: 76 test_true_pfm: 133.27950314917018 sim_pfm: 236.4537837163545
episode: 304 training return: tensor(246.0591, device='cuda:0')
episode: 305 training return: tensor(272.6909, device='cuda:0')
episode: 306 training return: tensor(262.0427, device='cuda:0')
episode: 307 training return: tensor(284.8781, device='cuda:0')
epoch: 77 test_true_pfm: 131.2282505430053 sim_pfm: 262.3722353520105
episode: 308 training return: tensor(289.8405, device='cuda:0')
episode: 309 training return: tensor(273.9567, device='cuda:0')
episode: 310 training return: tensor(246.5444, device='cuda:0')
episode: 311 training return: tensor(286.6010, device='cuda:0')
epoch: 78 test_true_pfm: 142.2329921500553 sim_pfm: 268.6704226905014
episode: 312 training return: tensor(259.2146, device='cuda:0')
episode: 313 training return: tensor(290.7094, device='cuda:0')
episode: 314 training return: tensor(274.0384, device='cuda:0')
episode: 315 training return: tensor(216.4403, device='cuda:0')
epoch: 79 test_true_pfm: 136.80904192804286 sim_pfm: 278.188792848913
episode: 316 training return: tensor(293.2588, device='cuda:0')
episode: 317 training return: tensor(231.3645, device='cuda:0')
episode: 318 training return: tensor(285.2600, device='cuda:0')
episode: 319 training return: tensor(283.0380, device='cuda:0')
epoch: 80 test_true_pfm: 140.21333315626276 sim_pfm: 261.684579443885
episode: 320 training return: tensor(282.5618, device='cuda:0')
episode: 321 training return: tensor(257.1771, device='cuda:0')
episode: 322 training return: tensor(284.7581, device='cuda:0')
episode: 323 training return: tensor(249.5271, device='cuda:0')
epoch: 81 test_true_pfm: 136.603359898087 sim_pfm: 270.6767571006843
episode: 324 training return: tensor(290.8115, device='cuda:0')
episode: 325 training return: tensor(294.4193, device='cuda:0')
episode: 326 training return: tensor(278.8208, device='cuda:0')
episode: 327 training return: tensor(280.2571, device='cuda:0')
epoch: 82 test_true_pfm: 136.04275346222434 sim_pfm: 270.9411819647124
episode: 328 training return: tensor(252.4388, device='cuda:0')
episode: 329 training return: tensor(238.7706, device='cuda:0')
episode: 330 training return: tensor(288.9853, device='cuda:0')
episode: 331 training return: tensor(248.1316, device='cuda:0')
epoch: 83 test_true_pfm: 126.92519902390056 sim_pfm: 285.40240249980707
episode: 332 training return: tensor(274.0683, device='cuda:0')
episode: 333 training return: tensor(285.5925, device='cuda:0')
episode: 334 training return: tensor(206.7612, device='cuda:0')
episode: 335 training return: tensor(273.0929, device='cuda:0')
epoch: 84 test_true_pfm: 136.73399823676823 sim_pfm: 278.72282866592286
episode: 336 training return: tensor(287.4780, device='cuda:0')
episode: 337 training return: tensor(289.4635, device='cuda:0')
episode: 338 training return: tensor(243.9476, device='cuda:0')
episode: 339 training return: tensor(287.7348, device='cuda:0')
epoch: 85 test_true_pfm: 135.34003531450426 sim_pfm: 279.1953153492417
episode: 340 training return: tensor(284.9057, device='cuda:0')
episode: 341 training return: tensor(279.4022, device='cuda:0')
episode: 342 training return: tensor(255.5203, device='cuda:0')
episode: 343 training return: tensor(277.7953, device='cuda:0')
epoch: 86 test_true_pfm: 134.9172526904859 sim_pfm: 269.0661661173566
episode: 344 training return: tensor(291.0077, device='cuda:0')
episode: 345 training return: tensor(275.6848, device='cuda:0')
episode: 346 training return: tensor(292.0928, device='cuda:0')
episode: 347 training return: tensor(268.4057, device='cuda:0')
epoch: 87 test_true_pfm: 132.22950686221284 sim_pfm: 277.36818545055576
episode: 348 training return: tensor(233.6628, device='cuda:0')
episode: 349 training return: tensor(291.0091, device='cuda:0')
episode: 350 training return: tensor(262.9972, device='cuda:0')
episode: 351 training return: tensor(278.2019, device='cuda:0')
epoch: 88 test_true_pfm: 137.6021171744588 sim_pfm: 259.35479969587175
episode: 352 training return: tensor(222.7949, device='cuda:0')
episode: 353 training return: tensor(225.1336, device='cuda:0')
episode: 354 training return: tensor(235.6199, device='cuda:0')
episode: 355 training return: tensor(209.2282, device='cuda:0')
epoch: 89 test_true_pfm: 139.43341243127293 sim_pfm: 255.09173733872012
episode: 356 training return: tensor(256.5545, device='cuda:0')
episode: 357 training return: tensor(265.7930, device='cuda:0')
episode: 358 training return: tensor(268.2034, device='cuda:0')
episode: 359 training return: tensor(242.5156, device='cuda:0')
epoch: 90 test_true_pfm: 137.6966906348571 sim_pfm: 266.49420840959067
episode: 360 training return: tensor(238.2634, device='cuda:0')
episode: 361 training return: tensor(276.6017, device='cuda:0')
episode: 362 training return: tensor(238.9023, device='cuda:0')
episode: 363 training return: tensor(281.5621, device='cuda:0')
epoch: 91 test_true_pfm: 133.96388287957703 sim_pfm: 266.2359638415743
episode: 364 training return: tensor(260.4557, device='cuda:0')
episode: 365 training return: tensor(261.6085, device='cuda:0')
episode: 366 training return: tensor(287.5445, device='cuda:0')
episode: 367 training return: tensor(254.2100, device='cuda:0')
epoch: 92 test_true_pfm: 140.47720363793817 sim_pfm: 280.9407212886261
episode: 368 training return: tensor(246.7481, device='cuda:0')
episode: 369 training return: tensor(223.2422, device='cuda:0')
episode: 370 training return: tensor(281.3700, device='cuda:0')
episode: 371 training return: tensor(290.0503, device='cuda:0')
epoch: 93 test_true_pfm: 130.6384982029085 sim_pfm: 260.40933804851954
episode: 372 training return: tensor(271.1865, device='cuda:0')
episode: 373 training return: tensor(281.7497, device='cuda:0')
episode: 374 training return: tensor(267.1569, device='cuda:0')
episode: 375 training return: tensor(231.8326, device='cuda:0')
epoch: 94 test_true_pfm: 136.43134437857435 sim_pfm: 277.79586377232334
episode: 376 training return: tensor(267.5522, device='cuda:0')
episode: 377 training return: tensor(267.7639, device='cuda:0')
episode: 378 training return: tensor(267.3936, device='cuda:0')
episode: 379 training return: tensor(264.4678, device='cuda:0')
epoch: 95 test_true_pfm: 143.7519936493072 sim_pfm: 278.0732586762635
episode: 380 training return: tensor(283.0650, device='cuda:0')
episode: 381 training return: tensor(271.1490, device='cuda:0')
episode: 382 training return: tensor(277.3835, device='cuda:0')
episode: 383 training return: tensor(287.0866, device='cuda:0')
epoch: 96 test_true_pfm: 140.38546549575688 sim_pfm: 279.91114309583793
episode: 384 training return: tensor(273.4484, device='cuda:0')
episode: 385 training return: tensor(268.2790, device='cuda:0')
episode: 386 training return: tensor(268.1587, device='cuda:0')
episode: 387 training return: tensor(266.6799, device='cuda:0')
epoch: 97 test_true_pfm: 139.0797157840039 sim_pfm: 279.8731222038274
episode: 388 training return: tensor(285.3924, device='cuda:0')
episode: 389 training return: tensor(273.6297, device='cuda:0')
episode: 390 training return: tensor(253.7779, device='cuda:0')
episode: 391 training return: tensor(275.5450, device='cuda:0')
epoch: 98 test_true_pfm: 134.58728086189507 sim_pfm: 264.07130609531885
episode: 392 training return: tensor(275.4637, device='cuda:0')
episode: 393 training return: tensor(272.5941, device='cuda:0')
episode: 394 training return: tensor(285.8722, device='cuda:0')
episode: 395 training return: tensor(282.7652, device='cuda:0')
epoch: 99 test_true_pfm: 135.91057559489326 sim_pfm: 278.7307453830261
episode: 396 training return: tensor(237.1466, device='cuda:0')
episode: 397 training return: tensor(274.1686, device='cuda:0')
episode: 398 training return: tensor(278.8441, device='cuda:0')
episode: 399 training return: tensor(268.7234, device='cuda:0')
epoch: 100 test_true_pfm: 135.23974030594553 sim_pfm: 272.3933319686854
episode: 400 training return: tensor(235.7851, device='cuda:0')
episode: 401 training return: tensor(246.1330, device='cuda:0')
episode: 402 training return: tensor(251.5546, device='cuda:0')
episode: 403 training return: tensor(292.2933, device='cuda:0')
epoch: 101 test_true_pfm: 129.99813671912136 sim_pfm: 275.6079684085213
episode: 404 training return: tensor(277.8503, device='cuda:0')
episode: 405 training return: tensor(262.6305, device='cuda:0')
episode: 406 training return: tensor(208.5770, device='cuda:0')
episode: 407 training return: tensor(281.5685, device='cuda:0')
epoch: 102 test_true_pfm: 141.86850234034907 sim_pfm: 285.47703780119775
episode: 408 training return: tensor(280.2294, device='cuda:0')
episode: 409 training return: tensor(264.3819, device='cuda:0')
episode: 410 training return: tensor(282.5887, device='cuda:0')
episode: 411 training return: tensor(245.9018, device='cuda:0')
epoch: 103 test_true_pfm: 131.7767034220308 sim_pfm: 272.15330836819487
episode: 412 training return: tensor(255.4800, device='cuda:0')
episode: 413 training return: tensor(274.8434, device='cuda:0')
episode: 414 training return: tensor(238.7234, device='cuda:0')
episode: 415 training return: tensor(289.1508, device='cuda:0')
epoch: 104 test_true_pfm: 134.15134226571337 sim_pfm: 270.35457084742376
episode: 416 training return: tensor(223.3379, device='cuda:0')
episode: 417 training return: tensor(281.9243, device='cuda:0')
episode: 418 training return: tensor(275.5158, device='cuda:0')
episode: 419 training return: tensor(276.2279, device='cuda:0')
epoch: 105 test_true_pfm: 133.49503197284238 sim_pfm: 277.11436540376747
episode: 420 training return: tensor(261.9367, device='cuda:0')
episode: 421 training return: tensor(252.6167, device='cuda:0')
episode: 422 training return: tensor(288.9509, device='cuda:0')
episode: 423 training return: tensor(262.7472, device='cuda:0')
epoch: 106 test_true_pfm: 136.52108581152817 sim_pfm: 273.4144300784916
episode: 424 training return: tensor(265.5467, device='cuda:0')
episode: 425 training return: tensor(275.9285, device='cuda:0')
episode: 426 training return: tensor(277.0163, device='cuda:0')
episode: 427 training return: tensor(281.6349, device='cuda:0')
epoch: 107 test_true_pfm: 132.85229647581951 sim_pfm: 279.0762804073747
episode: 428 training return: tensor(283.9696, device='cuda:0')
episode: 429 training return: tensor(276.5397, device='cuda:0')
episode: 430 training return: tensor(237.5848, device='cuda:0')
episode: 431 training return: tensor(234.4269, device='cuda:0')
epoch: 108 test_true_pfm: 136.97292045983153 sim_pfm: 279.9781640637142
episode: 432 training return: tensor(270.9707, device='cuda:0')
episode: 433 training return: tensor(260.5394, device='cuda:0')
episode: 434 training return: tensor(287.0614, device='cuda:0')
episode: 435 training return: tensor(288.5724, device='cuda:0')
epoch: 109 test_true_pfm: 139.71361469065013 sim_pfm: 266.13646276785875
episode: 436 training return: tensor(250.6995, device='cuda:0')
episode: 437 training return: tensor(239.5596, device='cuda:0')
episode: 438 training return: tensor(263.1828, device='cuda:0')
episode: 439 training return: tensor(254.6179, device='cuda:0')
epoch: 110 test_true_pfm: 139.28588040715283 sim_pfm: 265.458299934736
episode: 440 training return: tensor(281.2701, device='cuda:0')
episode: 441 training return: tensor(274.1328, device='cuda:0')
episode: 442 training return: tensor(225.9007, device='cuda:0')
episode: 443 training return: tensor(240.5894, device='cuda:0')
epoch: 111 test_true_pfm: 140.30947076281413 sim_pfm: 281.44395549692564
episode: 444 training return: tensor(246.3608, device='cuda:0')
episode: 445 training return: tensor(271.7429, device='cuda:0')
episode: 446 training return: tensor(255.9333, device='cuda:0')
episode: 447 training return: tensor(278.8941, device='cuda:0')
epoch: 112 test_true_pfm: 136.36202456702833 sim_pfm: 270.46238549321424
episode: 448 training return: tensor(280.5131, device='cuda:0')
episode: 449 training return: tensor(247.0595, device='cuda:0')
episode: 450 training return: tensor(285.3423, device='cuda:0')
episode: 451 training return: tensor(284.7414, device='cuda:0')
epoch: 113 test_true_pfm: 130.68248369136228 sim_pfm: 259.41691800917033
episode: 452 training return: tensor(269.8719, device='cuda:0')
episode: 453 training return: tensor(226.9250, device='cuda:0')
episode: 454 training return: tensor(254.7885, device='cuda:0')
episode: 455 training return: tensor(214.7075, device='cuda:0')
epoch: 114 test_true_pfm: 132.7185603412082 sim_pfm: 281.7437259710161
episode: 456 training return: tensor(281.2555, device='cuda:0')
episode: 457 training return: tensor(250.6978, device='cuda:0')
episode: 458 training return: tensor(281.1539, device='cuda:0')
episode: 459 training return: tensor(286.3760, device='cuda:0')
epoch: 115 test_true_pfm: 135.69991581860927 sim_pfm: 285.9283179257938
episode: 460 training return: tensor(252.9100, device='cuda:0')
episode: 461 training return: tensor(283.0856, device='cuda:0')
episode: 462 training return: tensor(289.1050, device='cuda:0')
episode: 463 training return: tensor(250.6330, device='cuda:0')
epoch: 116 test_true_pfm: 134.96009481152203 sim_pfm: 267.7995226387866
episode: 464 training return: tensor(260.6598, device='cuda:0')
episode: 465 training return: tensor(277.6829, device='cuda:0')
episode: 466 training return: tensor(277.0080, device='cuda:0')
episode: 467 training return: tensor(273.6382, device='cuda:0')
epoch: 117 test_true_pfm: 139.89177995049977 sim_pfm: 269.21562289933206
episode: 468 training return: tensor(278.4467, device='cuda:0')
episode: 469 training return: tensor(276.6838, device='cuda:0')
episode: 470 training return: tensor(280.5382, device='cuda:0')
episode: 471 training return: tensor(286.5316, device='cuda:0')
epoch: 118 test_true_pfm: 135.9686341968174 sim_pfm: 278.3715837423224
episode: 472 training return: tensor(258.6446, device='cuda:0')
episode: 473 training return: tensor(292.0256, device='cuda:0')
episode: 474 training return: tensor(264.0555, device='cuda:0')
episode: 475 training return: tensor(265.4812, device='cuda:0')
epoch: 119 test_true_pfm: 140.49541614443385 sim_pfm: 257.2324224751443
episode: 476 training return: tensor(250.8605, device='cuda:0')
episode: 477 training return: tensor(267.2172, device='cuda:0')
episode: 478 training return: tensor(280.0055, device='cuda:0')
episode: 479 training return: tensor(291.7891, device='cuda:0')
epoch: 120 test_true_pfm: 140.4553464088317 sim_pfm: 278.21501481034795
episode: 480 training return: tensor(276.4560, device='cuda:0')
episode: 481 training return: tensor(261.5882, device='cuda:0')
episode: 482 training return: tensor(235.1535, device='cuda:0')
episode: 483 training return: tensor(284.1736, device='cuda:0')
epoch: 121 test_true_pfm: 134.57433512171684 sim_pfm: 259.1881958362821
episode: 484 training return: tensor(271.9471, device='cuda:0')
episode: 485 training return: tensor(217.6607, device='cuda:0')
episode: 486 training return: tensor(214.5184, device='cuda:0')
episode: 487 training return: tensor(220.1430, device='cuda:0')
epoch: 122 test_true_pfm: 141.0184114501827 sim_pfm: 265.2700639645453
episode: 488 training return: tensor(278.7562, device='cuda:0')
episode: 489 training return: tensor(270.6737, device='cuda:0')
episode: 490 training return: tensor(273.3191, device='cuda:0')
episode: 491 training return: tensor(276.1728, device='cuda:0')
epoch: 123 test_true_pfm: 142.5232293342444 sim_pfm: 270.5061485796061
episode: 492 training return: tensor(281.7242, device='cuda:0')
episode: 493 training return: tensor(263.2691, device='cuda:0')
episode: 494 training return: tensor(271.9149, device='cuda:0')
episode: 495 training return: tensor(287.8239, device='cuda:0')
epoch: 124 test_true_pfm: 136.63818011415984 sim_pfm: 258.93285217938245
episode: 496 training return: tensor(208.7094, device='cuda:0')
episode: 497 training return: tensor(222.9941, device='cuda:0')
episode: 498 training return: tensor(293.2118, device='cuda:0')
episode: 499 training return: tensor(274.6102, device='cuda:0')
epoch: 125 test_true_pfm: 138.6659960511863 sim_pfm: 265.0097794300294
episode: 500 training return: tensor(285.7566, device='cuda:0')
episode: 501 training return: tensor(282.1644, device='cuda:0')
episode: 502 training return: tensor(290.7676, device='cuda:0')
episode: 503 training return: tensor(270.1886, device='cuda:0')
epoch: 126 test_true_pfm: 140.27168235565892 sim_pfm: 278.7307384344749
episode: 504 training return: tensor(292.5265, device='cuda:0')
episode: 505 training return: tensor(251.6073, device='cuda:0')
episode: 506 training return: tensor(259.3125, device='cuda:0')
episode: 507 training return: tensor(245.7254, device='cuda:0')
epoch: 127 test_true_pfm: 138.7888557102379 sim_pfm: 281.85354594592934
episode: 508 training return: tensor(258.2469, device='cuda:0')
episode: 509 training return: tensor(262.8659, device='cuda:0')
episode: 510 training return: tensor(230.1199, device='cuda:0')
episode: 511 training return: tensor(283.9769, device='cuda:0')
epoch: 128 test_true_pfm: 137.65235900452723 sim_pfm: 278.32990720521195
episode: 512 training return: tensor(265.8440, device='cuda:0')
episode: 513 training return: tensor(234.2025, device='cuda:0')
episode: 514 training return: tensor(244.3483, device='cuda:0')
episode: 515 training return: tensor(285.1462, device='cuda:0')
epoch: 129 test_true_pfm: 138.11469643982352 sim_pfm: 273.53943070017266
episode: 516 training return: tensor(267.1221, device='cuda:0')
episode: 517 training return: tensor(226.2185, device='cuda:0')
episode: 518 training return: tensor(272.1017, device='cuda:0')
episode: 519 training return: tensor(260.9009, device='cuda:0')
epoch: 130 test_true_pfm: 135.22394997137866 sim_pfm: 282.68522915556093
episode: 520 training return: tensor(287.1206, device='cuda:0')
episode: 521 training return: tensor(225.5710, device='cuda:0')
episode: 522 training return: tensor(275.9093, device='cuda:0')
episode: 523 training return: tensor(227.5330, device='cuda:0')
epoch: 131 test_true_pfm: 136.10133912526425 sim_pfm: 264.526095486898
episode: 524 training return: tensor(275.2999, device='cuda:0')
episode: 525 training return: tensor(247.0752, device='cuda:0')
episode: 526 training return: tensor(271.2279, device='cuda:0')
episode: 527 training return: tensor(232.3826, device='cuda:0')
epoch: 132 test_true_pfm: 132.8183715434666 sim_pfm: 266.3054860171454
episode: 528 training return: tensor(290.3875, device='cuda:0')
episode: 529 training return: tensor(281.0181, device='cuda:0')
episode: 530 training return: tensor(230.2487, device='cuda:0')
episode: 531 training return: tensor(233.8965, device='cuda:0')
epoch: 133 test_true_pfm: 137.47315867876733 sim_pfm: 266.7473421351635
episode: 532 training return: tensor(276.9590, device='cuda:0')
episode: 533 training return: tensor(285.1100, device='cuda:0')
episode: 534 training return: tensor(291.1648, device='cuda:0')
episode: 535 training return: tensor(250.9349, device='cuda:0')
epoch: 134 test_true_pfm: 142.34294596109305 sim_pfm: 277.64492294203376
episode: 536 training return: tensor(294.6620, device='cuda:0')
episode: 537 training return: tensor(280.2793, device='cuda:0')
episode: 538 training return: tensor(261.1711, device='cuda:0')
episode: 539 training return: tensor(278.3473, device='cuda:0')
epoch: 135 test_true_pfm: 137.84631641247293 sim_pfm: 253.84293577005155
episode: 540 training return: tensor(262.2299, device='cuda:0')
episode: 541 training return: tensor(242.9280, device='cuda:0')
episode: 542 training return: tensor(257.8003, device='cuda:0')
episode: 543 training return: tensor(285.8211, device='cuda:0')
epoch: 136 test_true_pfm: 129.02949730050355 sim_pfm: 263.2720889163902
episode: 544 training return: tensor(271.1295, device='cuda:0')
episode: 545 training return: tensor(270.9407, device='cuda:0')
episode: 546 training return: tensor(271.8480, device='cuda:0')
episode: 547 training return: tensor(279.5704, device='cuda:0')
epoch: 137 test_true_pfm: 141.5183217970053 sim_pfm: 277.0122918080189
episode: 548 training return: tensor(286.8889, device='cuda:0')
episode: 549 training return: tensor(226.8269, device='cuda:0')
episode: 550 training return: tensor(275.7246, device='cuda:0')
episode: 551 training return: tensor(227.6003, device='cuda:0')
epoch: 138 test_true_pfm: 140.0993837438092 sim_pfm: 259.83619771909434
episode: 552 training return: tensor(274.5712, device='cuda:0')
episode: 553 training return: tensor(238.3337, device='cuda:0')
episode: 554 training return: tensor(282.9597, device='cuda:0')
episode: 555 training return: tensor(275.9050, device='cuda:0')
epoch: 139 test_true_pfm: 137.8283811906947 sim_pfm: 267.252754125162
episode: 556 training return: tensor(242.0024, device='cuda:0')
episode: 557 training return: tensor(268.8043, device='cuda:0')
episode: 558 training return: tensor(276.9258, device='cuda:0')
episode: 559 training return: tensor(282.7590, device='cuda:0')
epoch: 140 test_true_pfm: 136.23634316920388 sim_pfm: 265.8670470300596
episode: 560 training return: tensor(277.0887, device='cuda:0')
episode: 561 training return: tensor(260.0961, device='cuda:0')
episode: 562 training return: tensor(211.9491, device='cuda:0')
episode: 563 training return: tensor(271.8659, device='cuda:0')
epoch: 141 test_true_pfm: 143.93208823286545 sim_pfm: 270.7822221677052
episode: 564 training return: tensor(266.2019, device='cuda:0')
episode: 565 training return: tensor(255.9280, device='cuda:0')
episode: 566 training return: tensor(273.5698, device='cuda:0')
episode: 567 training return: tensor(242.5872, device='cuda:0')
epoch: 142 test_true_pfm: 141.2771411928306 sim_pfm: 276.2939536906546
episode: 568 training return: tensor(288.0905, device='cuda:0')
episode: 569 training return: tensor(267.9973, device='cuda:0')
episode: 570 training return: tensor(292.9626, device='cuda:0')
episode: 571 training return: tensor(267.6682, device='cuda:0')
epoch: 143 test_true_pfm: 133.29640553976452 sim_pfm: 257.00593025611016
episode: 572 training return: tensor(285.3633, device='cuda:0')
episode: 573 training return: tensor(291.6178, device='cuda:0')
episode: 574 training return: tensor(215.9029, device='cuda:0')
episode: 575 training return: tensor(293.5165, device='cuda:0')
epoch: 144 test_true_pfm: 140.94180695674476 sim_pfm: 262.42892405989113
episode: 576 training return: tensor(274.9795, device='cuda:0')
episode: 577 training return: tensor(285.7863, device='cuda:0')
episode: 578 training return: tensor(274.7860, device='cuda:0')
episode: 579 training return: tensor(291.9099, device='cuda:0')
epoch: 145 test_true_pfm: 140.98821683022408 sim_pfm: 254.76460544736474
episode: 580 training return: tensor(277.7400, device='cuda:0')
episode: 581 training return: tensor(270.5283, device='cuda:0')
episode: 582 training return: tensor(236.9849, device='cuda:0')
episode: 583 training return: tensor(279.8953, device='cuda:0')
epoch: 146 test_true_pfm: 136.87640203877555 sim_pfm: 273.7080627563526
episode: 584 training return: tensor(274.3156, device='cuda:0')
episode: 585 training return: tensor(278.3768, device='cuda:0')
episode: 586 training return: tensor(278.8586, device='cuda:0')
episode: 587 training return: tensor(264.9493, device='cuda:0')
epoch: 147 test_true_pfm: 136.94503590443216 sim_pfm: 271.88875557817516
episode: 588 training return: tensor(253.6405, device='cuda:0')
episode: 589 training return: tensor(252.2963, device='cuda:0')
episode: 590 training return: tensor(292.7138, device='cuda:0')
episode: 591 training return: tensor(276.4694, device='cuda:0')
epoch: 148 test_true_pfm: 138.2025474562169 sim_pfm: 260.41052868348777
episode: 592 training return: tensor(270.7955, device='cuda:0')
episode: 593 training return: tensor(264.0408, device='cuda:0')
episode: 594 training return: tensor(260.2804, device='cuda:0')
episode: 595 training return: tensor(267.8799, device='cuda:0')
epoch: 149 test_true_pfm: 138.08500224443145 sim_pfm: 267.5730255033588
episode: 596 training return: tensor(219.3709, device='cuda:0')
episode: 597 training return: tensor(275.7906, device='cuda:0')
episode: 598 training return: tensor(279.0925, device='cuda:0')
episode: 599 training return: tensor(284.8907, device='cuda:0')
epoch: 150 test_true_pfm: 141.12204180083722 sim_pfm: 275.7383640510496
