['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '0', '--data', '100000', '--regu', '0.05']
2103.3482969988772
episode: 0 training return: tensor(-193.2389, device='cuda:0')
episode: 1 training return: tensor(-295.9526, device='cuda:0')
episode: 2 training return: tensor(-161.5574, device='cuda:0')
episode: 3 training return: tensor(33.9712, device='cuda:0')
epoch: 1 test_true_pfm: 1850.7355442978949 sim_pfm: -256.7615846915772
episode: 4 training return: tensor(-280.1767, device='cuda:0')
episode: 5 training return: tensor(-254.3607, device='cuda:0')
episode: 6 training return: tensor(-37.1784, device='cuda:0')
episode: 7 training return: tensor(-342.7826, device='cuda:0')
epoch: 2 test_true_pfm: 2219.004793739466 sim_pfm: -52.932652146400265
episode: 8 training return: tensor(-208.8204, device='cuda:0')
episode: 9 training return: tensor(-339.7958, device='cuda:0')
episode: 10 training return: tensor(-278.1643, device='cuda:0')
episode: 11 training return: tensor(348.4937, device='cuda:0')
epoch: 3 test_true_pfm: 2351.9639098437315 sim_pfm: -102.99625038328425
episode: 12 training return: tensor(-199.5492, device='cuda:0')
episode: 13 training return: tensor(-292.6716, device='cuda:0')
episode: 14 training return: tensor(-277.7970, device='cuda:0')
episode: 15 training return: tensor(199.6327, device='cuda:0')
epoch: 4 test_true_pfm: 2442.3573896613802 sim_pfm: -74.94692848583993
episode: 16 training return: tensor(-208.0720, device='cuda:0')
episode: 17 training return: tensor(-346.9182, device='cuda:0')
episode: 18 training return: tensor(-87.7617, device='cuda:0')
episode: 19 training return: tensor(-316.4403, device='cuda:0')
epoch: 5 test_true_pfm: 2324.403771414234 sim_pfm: 76.66295616815721
episode: 20 training return: tensor(-287.9251, device='cuda:0')
episode: 21 training return: tensor(55.3262, device='cuda:0')
episode: 22 training return: tensor(-56.6463, device='cuda:0')
episode: 23 training return: tensor(-314.2790, device='cuda:0')
epoch: 6 test_true_pfm: 2361.7028214007364 sim_pfm: -127.97353171561069
episode: 24 training return: tensor(323.5300, device='cuda:0')
episode: 25 training return: tensor(-351.7024, device='cuda:0')
episode: 26 training return: tensor(-253.1867, device='cuda:0')
episode: 27 training return: tensor(354.2188, device='cuda:0')
epoch: 7 test_true_pfm: 1573.2223186804524 sim_pfm: -231.46354411620027
episode: 28 training return: tensor(-346.6404, device='cuda:0')
episode: 29 training return: tensor(381.8347, device='cuda:0')
episode: 30 training return: tensor(-360.7532, device='cuda:0')
episode: 31 training return: tensor(-152.3407, device='cuda:0')
epoch: 8 test_true_pfm: 2049.3272541449287 sim_pfm: 84.47330987375851
episode: 32 training return: tensor(388.3929, device='cuda:0')
episode: 33 training return: tensor(-348.2657, device='cuda:0')
episode: 34 training return: tensor(-12.8267, device='cuda:0')
episode: 35 training return: tensor(-353.5823, device='cuda:0')
epoch: 9 test_true_pfm: 2560.651026274394 sim_pfm: -325.23239192320034
episode: 36 training return: tensor(-337.0560, device='cuda:0')
episode: 37 training return: tensor(-300.0757, device='cuda:0')
episode: 38 training return: tensor(352.6208, device='cuda:0')
episode: 39 training return: tensor(-315.2831, device='cuda:0')
epoch: 10 test_true_pfm: 2022.2411006367468 sim_pfm: -174.45705668486576
episode: 40 training return: tensor(211.8691, device='cuda:0')
episode: 41 training return: tensor(-342.1583, device='cuda:0')
episode: 42 training return: tensor(-201.7841, device='cuda:0')
episode: 43 training return: tensor(-16.2729, device='cuda:0')
epoch: 11 test_true_pfm: 1926.5402944774298 sim_pfm: 265.4913910066146
episode: 44 training return: tensor(-230.4951, device='cuda:0')
episode: 45 training return: tensor(40.0192, device='cuda:0')
episode: 46 training return: tensor(-109.2201, device='cuda:0')
episode: 47 training return: tensor(30.4504, device='cuda:0')
epoch: 12 test_true_pfm: 2870.4423992104744 sim_pfm: 66.57338188557576
episode: 48 training return: tensor(-336.7188, device='cuda:0')
episode: 49 training return: tensor(327.1159, device='cuda:0')
episode: 50 training return: tensor(-160.1823, device='cuda:0')
episode: 51 training return: tensor(-217.5972, device='cuda:0')
epoch: 13 test_true_pfm: 2703.8661202633934 sim_pfm: 122.63344753512258
episode: 52 training return: tensor(-253.6861, device='cuda:0')
episode: 53 training return: tensor(336.3900, device='cuda:0')
episode: 54 training return: tensor(-236.9334, device='cuda:0')
episode: 55 training return: tensor(-179.1926, device='cuda:0')
epoch: 14 test_true_pfm: 1888.1396804713056 sim_pfm: 3.1952021360824197
episode: 56 training return: tensor(-105.3040, device='cuda:0')
episode: 57 training return: tensor(374.9513, device='cuda:0')
episode: 58 training return: tensor(-173.6470, device='cuda:0')
episode: 59 training return: tensor(-293.0852, device='cuda:0')
epoch: 15 test_true_pfm: 2144.567060819412 sim_pfm: 230.20946274926732
episode: 60 training return: tensor(-282.5246, device='cuda:0')
episode: 61 training return: tensor(-291.3170, device='cuda:0')
episode: 62 training return: tensor(-337.1700, device='cuda:0')
episode: 63 training return: tensor(-159.2073, device='cuda:0')
epoch: 16 test_true_pfm: 2279.7379017467288 sim_pfm: -126.81445571120518
episode: 64 training return: tensor(80.5381, device='cuda:0')
episode: 65 training return: tensor(-350.9500, device='cuda:0')
episode: 66 training return: tensor(-266.1344, device='cuda:0')
episode: 67 training return: tensor(-360.4121, device='cuda:0')
epoch: 17 test_true_pfm: 2348.9756140115987 sim_pfm: -63.225224176547876
episode: 68 training return: tensor(-158.8559, device='cuda:0')
episode: 69 training return: tensor(421.9165, device='cuda:0')
episode: 70 training return: tensor(326.4200, device='cuda:0')
episode: 71 training return: tensor(-274.8387, device='cuda:0')
epoch: 18 test_true_pfm: 1800.6088592484487 sim_pfm: 104.64534717974796
episode: 72 training return: tensor(-260.5480, device='cuda:0')
episode: 73 training return: tensor(-346.3753, device='cuda:0')
episode: 74 training return: tensor(-254.8319, device='cuda:0')
episode: 75 training return: tensor(-233.1019, device='cuda:0')
epoch: 19 test_true_pfm: 2439.7002891728503 sim_pfm: 107.160936618282
episode: 76 training return: tensor(-338.2277, device='cuda:0')
episode: 77 training return: tensor(-282.3940, device='cuda:0')
episode: 78 training return: tensor(-279.4000, device='cuda:0')
episode: 79 training return: tensor(-315.0411, device='cuda:0')
epoch: 20 test_true_pfm: 2578.8755108216264 sim_pfm: -95.46921326425702
episode: 80 training return: tensor(-31.2948, device='cuda:0')
episode: 81 training return: tensor(-112.3818, device='cuda:0')
episode: 82 training return: tensor(-155.9168, device='cuda:0')
episode: 83 training return: tensor(347.7838, device='cuda:0')
epoch: 21 test_true_pfm: 2374.8600957134227 sim_pfm: 263.7734069190531
episode: 84 training return: tensor(353.1861, device='cuda:0')
episode: 85 training return: tensor(-298.9813, device='cuda:0')
episode: 86 training return: tensor(-269.6173, device='cuda:0')
episode: 87 training return: tensor(-289.3609, device='cuda:0')
epoch: 22 test_true_pfm: 2175.314831535187 sim_pfm: 114.48350479777825
episode: 88 training return: tensor(-336.9856, device='cuda:0')
episode: 89 training return: tensor(348.7673, device='cuda:0')
episode: 90 training return: tensor(-340.5877, device='cuda:0')
episode: 91 training return: tensor(-279.7081, device='cuda:0')
epoch: 23 test_true_pfm: 2418.7453616131656 sim_pfm: -40.45502516143218
episode: 92 training return: tensor(-348.3053, device='cuda:0')
episode: 93 training return: tensor(-336.7110, device='cuda:0')
episode: 94 training return: tensor(-248.7066, device='cuda:0')
episode: 95 training return: tensor(-334.9971, device='cuda:0')
epoch: 24 test_true_pfm: 2504.6900372677046 sim_pfm: 214.0008267276959
episode: 96 training return: tensor(-171.2876, device='cuda:0')
episode: 97 training return: tensor(-342.0556, device='cuda:0')
episode: 98 training return: tensor(-347.1489, device='cuda:0')
episode: 99 training return: tensor(-91.6793, device='cuda:0')
epoch: 25 test_true_pfm: 2011.2849707039416 sim_pfm: -68.92134044119545
episode: 100 training return: tensor(-349.2018, device='cuda:0')
episode: 101 training return: tensor(-96.3128, device='cuda:0')
episode: 102 training return: tensor(-352.2712, device='cuda:0')
episode: 103 training return: tensor(-200.2500, device='cuda:0')
epoch: 26 test_true_pfm: 2176.8439407203805 sim_pfm: -81.64221809798619
episode: 104 training return: tensor(-1.4168, device='cuda:0')
episode: 105 training return: tensor(378.8253, device='cuda:0')
episode: 106 training return: tensor(-151.5892, device='cuda:0')
episode: 107 training return: tensor(-345.2258, device='cuda:0')
epoch: 27 test_true_pfm: 2508.829280924457 sim_pfm: -14.531254979946729
episode: 108 training return: tensor(-337.5406, device='cuda:0')
episode: 109 training return: tensor(343.7486, device='cuda:0')
episode: 110 training return: tensor(-238.4078, device='cuda:0')
episode: 111 training return: tensor(44.7091, device='cuda:0')
epoch: 28 test_true_pfm: 2563.9230430417297 sim_pfm: -106.9956739495198
episode: 112 training return: tensor(-75.7778, device='cuda:0')
episode: 113 training return: tensor(-345.8719, device='cuda:0')
episode: 114 training return: tensor(-347.2918, device='cuda:0')
episode: 115 training return: tensor(-75.3692, device='cuda:0')
epoch: 29 test_true_pfm: 2457.6829182180377 sim_pfm: 231.90250643526088
episode: 116 training return: tensor(-66.2812, device='cuda:0')
episode: 117 training return: tensor(-200.7052, device='cuda:0')
episode: 118 training return: tensor(-246.2426, device='cuda:0')
episode: 119 training return: tensor(-251.4580, device='cuda:0')
epoch: 30 test_true_pfm: 2898.876189464765 sim_pfm: 3.72151043547395
episode: 120 training return: tensor(-332.6578, device='cuda:0')
episode: 121 training return: tensor(-267.6812, device='cuda:0')
episode: 122 training return: tensor(-298.9892, device='cuda:0')
episode: 123 training return: tensor(333.4302, device='cuda:0')
epoch: 31 test_true_pfm: 2377.9173649165787 sim_pfm: 54.7724329563595
episode: 124 training return: tensor(-341.5427, device='cuda:0')
episode: 125 training return: tensor(-162.9211, device='cuda:0')
episode: 126 training return: tensor(-344.6465, device='cuda:0')
episode: 127 training return: tensor(-343.3920, device='cuda:0')
epoch: 32 test_true_pfm: 2365.3326135462216 sim_pfm: 61.73306353087537
episode: 128 training return: tensor(-342.1267, device='cuda:0')
episode: 129 training return: tensor(-53.4643, device='cuda:0')
episode: 130 training return: tensor(55.1311, device='cuda:0')
episode: 131 training return: tensor(-305.4641, device='cuda:0')
epoch: 33 test_true_pfm: 2228.7378819221235 sim_pfm: -219.12077468565744
episode: 132 training return: tensor(-322.7347, device='cuda:0')
episode: 133 training return: tensor(-358.9487, device='cuda:0')
episode: 134 training return: tensor(-151.3527, device='cuda:0')
episode: 135 training return: tensor(-60.1348, device='cuda:0')
epoch: 34 test_true_pfm: 2356.489374374865 sim_pfm: 229.11432311047488
episode: 136 training return: tensor(168.6100, device='cuda:0')
episode: 137 training return: tensor(-43.9298, device='cuda:0')
episode: 138 training return: tensor(-17.2984, device='cuda:0')
episode: 139 training return: tensor(57.6829, device='cuda:0')
epoch: 35 test_true_pfm: 2733.704872107863 sim_pfm: -11.573980713204946
episode: 140 training return: tensor(-247.9475, device='cuda:0')
episode: 141 training return: tensor(-279.9039, device='cuda:0')
episode: 142 training return: tensor(-16.4045, device='cuda:0')
episode: 143 training return: tensor(-189.4773, device='cuda:0')
epoch: 36 test_true_pfm: 2034.352055344906 sim_pfm: 234.93118843777725
episode: 144 training return: tensor(271.9795, device='cuda:0')
episode: 145 training return: tensor(327.1125, device='cuda:0')
episode: 146 training return: tensor(-342.0180, device='cuda:0')
episode: 147 training return: tensor(-343.6008, device='cuda:0')
epoch: 37 test_true_pfm: 2172.0327139504675 sim_pfm: 17.216827502823435
episode: 148 training return: tensor(-347.1366, device='cuda:0')
episode: 149 training return: tensor(54.4942, device='cuda:0')
episode: 150 training return: tensor(-364.7953, device='cuda:0')
episode: 151 training return: tensor(-325.6425, device='cuda:0')
epoch: 38 test_true_pfm: 1773.2313118051252 sim_pfm: -295.4004872320511
episode: 152 training return: tensor(-354.5618, device='cuda:0')
episode: 153 training return: tensor(-61.5158, device='cuda:0')
episode: 154 training return: tensor(-291.0020, device='cuda:0')
episode: 155 training return: tensor(-62.6761, device='cuda:0')
epoch: 39 test_true_pfm: 2705.163112817807 sim_pfm: 45.988822604180314
episode: 156 training return: tensor(-344.2410, device='cuda:0')
episode: 157 training return: tensor(-309.4141, device='cuda:0')
episode: 158 training return: tensor(-59.5305, device='cuda:0')
episode: 159 training return: tensor(-108.1010, device='cuda:0')
epoch: 40 test_true_pfm: 2492.9954064803046 sim_pfm: -73.29077111099225
episode: 160 training return: tensor(-345.8572, device='cuda:0')
episode: 161 training return: tensor(-346.3223, device='cuda:0')
episode: 162 training return: tensor(-41.8529, device='cuda:0')
episode: 163 training return: tensor(5.6731, device='cuda:0')
epoch: 41 test_true_pfm: 2889.991400500088 sim_pfm: -284.39141740017413
episode: 164 training return: tensor(-263.4481, device='cuda:0')
episode: 165 training return: tensor(74.8717, device='cuda:0')
episode: 166 training return: tensor(-257.7787, device='cuda:0')
episode: 167 training return: tensor(-346.7586, device='cuda:0')
epoch: 42 test_true_pfm: 2045.9361770772982 sim_pfm: -59.36608281229079
episode: 168 training return: tensor(-150.0511, device='cuda:0')
episode: 169 training return: tensor(36.8612, device='cuda:0')
episode: 170 training return: tensor(-55.8890, device='cuda:0')
episode: 171 training return: tensor(370.9220, device='cuda:0')
epoch: 43 test_true_pfm: 2832.7694130344553 sim_pfm: -27.113588879272964
episode: 172 training return: tensor(-270.2263, device='cuda:0')
episode: 173 training return: tensor(-79.8622, device='cuda:0')
episode: 174 training return: tensor(-145.3702, device='cuda:0')
episode: 175 training return: tensor(-155.8377, device='cuda:0')
epoch: 44 test_true_pfm: 2863.583492131221 sim_pfm: 40.106690232215136
episode: 176 training return: tensor(257.5219, device='cuda:0')
episode: 177 training return: tensor(209.3591, device='cuda:0')
episode: 178 training return: tensor(-153.4867, device='cuda:0')
episode: 179 training return: tensor(360.6989, device='cuda:0')
epoch: 45 test_true_pfm: 1929.444999240827 sim_pfm: 31.149902030903224
episode: 180 training return: tensor(36.3753, device='cuda:0')
episode: 181 training return: tensor(20.7544, device='cuda:0')
episode: 182 training return: tensor(-348.8030, device='cuda:0')
episode: 183 training return: tensor(-95.3329, device='cuda:0')
epoch: 46 test_true_pfm: 2202.6977739925424 sim_pfm: -77.39264323168511
episode: 184 training return: tensor(-339.0217, device='cuda:0')
episode: 185 training return: tensor(-242.5934, device='cuda:0')
episode: 186 training return: tensor(-309.7172, device='cuda:0')
episode: 187 training return: tensor(-359.9827, device='cuda:0')
epoch: 47 test_true_pfm: 2286.777367109217 sim_pfm: 127.47328015401338
episode: 188 training return: tensor(-166.2247, device='cuda:0')
episode: 189 training return: tensor(231.5146, device='cuda:0')
episode: 190 training return: tensor(-252.6318, device='cuda:0')
episode: 191 training return: tensor(-179.6222, device='cuda:0')
epoch: 48 test_true_pfm: 2107.329743573979 sim_pfm: -125.14904441561278
episode: 192 training return: tensor(103.6316, device='cuda:0')
episode: 193 training return: tensor(-242.5603, device='cuda:0')
episode: 194 training return: tensor(-245.3368, device='cuda:0')
episode: 195 training return: tensor(354.7253, device='cuda:0')
epoch: 49 test_true_pfm: 2386.242717680654 sim_pfm: -38.97222291763561
episode: 196 training return: tensor(41.7471, device='cuda:0')
episode: 197 training return: tensor(-127.0779, device='cuda:0')
episode: 198 training return: tensor(-252.7863, device='cuda:0')
episode: 199 training return: tensor(-337.7766, device='cuda:0')
epoch: 50 test_true_pfm: 2038.36366424705 sim_pfm: -94.14471861522179
episode: 200 training return: tensor(393.7012, device='cuda:0')
episode: 201 training return: tensor(-345.4387, device='cuda:0')
episode: 202 training return: tensor(382.4540, device='cuda:0')
episode: 203 training return: tensor(-235.7282, device='cuda:0')
epoch: 51 test_true_pfm: 2512.7335022078782 sim_pfm: -28.406863860000158
episode: 204 training return: tensor(370.7949, device='cuda:0')
episode: 205 training return: tensor(-193.4375, device='cuda:0')
episode: 206 training return: tensor(-343.8470, device='cuda:0')
episode: 207 training return: tensor(371.5594, device='cuda:0')
epoch: 52 test_true_pfm: 1968.1134075348143 sim_pfm: -136.72546631741957
episode: 208 training return: tensor(-292.1038, device='cuda:0')
episode: 209 training return: tensor(-339.7869, device='cuda:0')
episode: 210 training return: tensor(-345.1114, device='cuda:0')
episode: 211 training return: tensor(-322.0681, device='cuda:0')
epoch: 53 test_true_pfm: 2702.872887051786 sim_pfm: -43.652774497614395
episode: 212 training return: tensor(-56.4549, device='cuda:0')
episode: 213 training return: tensor(-350.2925, device='cuda:0')
episode: 214 training return: tensor(249.7967, device='cuda:0')
episode: 215 training return: tensor(-128.6602, device='cuda:0')
epoch: 54 test_true_pfm: 2397.977275337771 sim_pfm: 150.91704782114053
episode: 216 training return: tensor(-275.8135, device='cuda:0')
episode: 217 training return: tensor(-130.2675, device='cuda:0')
episode: 218 training return: tensor(-281.6814, device='cuda:0')
episode: 219 training return: tensor(-273.0586, device='cuda:0')
epoch: 55 test_true_pfm: 2172.217493476048 sim_pfm: -6.581755087361671
episode: 220 training return: tensor(-246.4363, device='cuda:0')
episode: 221 training return: tensor(6.2174, device='cuda:0')
episode: 222 training return: tensor(-222.8371, device='cuda:0')
episode: 223 training return: tensor(320.4494, device='cuda:0')
epoch: 56 test_true_pfm: 2129.204425239783 sim_pfm: 162.33463972134632
episode: 224 training return: tensor(-347.1111, device='cuda:0')
episode: 225 training return: tensor(-344.9254, device='cuda:0')
episode: 226 training return: tensor(363.0378, device='cuda:0')
episode: 227 training return: tensor(-332.8571, device='cuda:0')
epoch: 57 test_true_pfm: 2579.585076723521 sim_pfm: -11.92871525650844
episode: 228 training return: tensor(-47.0415, device='cuda:0')
episode: 229 training return: tensor(-243.5322, device='cuda:0')
episode: 230 training return: tensor(105.7431, device='cuda:0')
episode: 231 training return: tensor(-246.3041, device='cuda:0')
epoch: 58 test_true_pfm: 2606.3339476168826 sim_pfm: 290.28552455788787
episode: 232 training return: tensor(-249.7827, device='cuda:0')
episode: 233 training return: tensor(-93.4532, device='cuda:0')
episode: 234 training return: tensor(-47.2831, device='cuda:0')
episode: 235 training return: tensor(-295.4552, device='cuda:0')
epoch: 59 test_true_pfm: 1927.6676030631886 sim_pfm: -123.05060505039485
episode: 236 training return: tensor(-50.3979, device='cuda:0')
episode: 237 training return: tensor(-347.8375, device='cuda:0')
episode: 238 training return: tensor(-296.4265, device='cuda:0')
episode: 239 training return: tensor(-336.3872, device='cuda:0')
epoch: 60 test_true_pfm: 3109.3567645218886 sim_pfm: 62.54072401806479
episode: 240 training return: tensor(-293.7522, device='cuda:0')
episode: 241 training return: tensor(411.7677, device='cuda:0')
episode: 242 training return: tensor(353.7121, device='cuda:0')
episode: 243 training return: tensor(-60.2192, device='cuda:0')
epoch: 61 test_true_pfm: 2583.884384452879 sim_pfm: 6.742032690924437
episode: 244 training return: tensor(-246.6299, device='cuda:0')
episode: 245 training return: tensor(-252.1816, device='cuda:0')
episode: 246 training return: tensor(-265.5876, device='cuda:0')
episode: 247 training return: tensor(-290.4576, device='cuda:0')
epoch: 62 test_true_pfm: 2534.80087457938 sim_pfm: 164.9052128329446
episode: 248 training return: tensor(-271.4618, device='cuda:0')
episode: 249 training return: tensor(154.4748, device='cuda:0')
episode: 250 training return: tensor(-161.6405, device='cuda:0')
episode: 251 training return: tensor(-263.9446, device='cuda:0')
epoch: 63 test_true_pfm: 1919.6446330501929 sim_pfm: 81.09640097866456
episode: 252 training return: tensor(-263.2104, device='cuda:0')
episode: 253 training return: tensor(-62.4147, device='cuda:0')
episode: 254 training return: tensor(368.5322, device='cuda:0')
episode: 255 training return: tensor(161.3482, device='cuda:0')
epoch: 64 test_true_pfm: 2418.448778099351 sim_pfm: 60.02473438060648
episode: 256 training return: tensor(225.7724, device='cuda:0')
episode: 257 training return: tensor(-281.8547, device='cuda:0')
episode: 258 training return: tensor(-252.1920, device='cuda:0')
episode: 259 training return: tensor(-342.9978, device='cuda:0')
epoch: 65 test_true_pfm: 2881.521656334176 sim_pfm: 70.91325437654935
episode: 260 training return: tensor(-349.9337, device='cuda:0')
episode: 261 training return: tensor(-55.5381, device='cuda:0')
episode: 262 training return: tensor(-275.2541, device='cuda:0')
episode: 263 training return: tensor(-92.7630, device='cuda:0')
epoch: 66 test_true_pfm: 2426.6953815898846 sim_pfm: 38.926642258651555
episode: 264 training return: tensor(338.0860, device='cuda:0')
episode: 265 training return: tensor(53.9497, device='cuda:0')
episode: 266 training return: tensor(139.2636, device='cuda:0')
episode: 267 training return: tensor(-287.7735, device='cuda:0')
epoch: 67 test_true_pfm: 2524.906093182228 sim_pfm: 44.72784422341889
episode: 268 training return: tensor(-351.4054, device='cuda:0')
episode: 269 training return: tensor(-60.9028, device='cuda:0')
episode: 270 training return: tensor(-204.0871, device='cuda:0')
episode: 271 training return: tensor(-157.0641, device='cuda:0')
epoch: 68 test_true_pfm: 2657.0039335026922 sim_pfm: 93.28174387772258
episode: 272 training return: tensor(-229.3774, device='cuda:0')
episode: 273 training return: tensor(-257.9750, device='cuda:0')
episode: 274 training return: tensor(336.8712, device='cuda:0')
episode: 275 training return: tensor(-299.8597, device='cuda:0')
epoch: 69 test_true_pfm: 2347.1735155346846 sim_pfm: -17.06095337642667
episode: 276 training return: tensor(-86.2306, device='cuda:0')
episode: 277 training return: tensor(65.4093, device='cuda:0')
episode: 278 training return: tensor(-252.1403, device='cuda:0')
episode: 279 training return: tensor(-268.3715, device='cuda:0')
epoch: 70 test_true_pfm: 2095.958879133412 sim_pfm: -70.78633220874083
episode: 280 training return: tensor(369.1370, device='cuda:0')
episode: 281 training return: tensor(-96.9597, device='cuda:0')
episode: 282 training return: tensor(363.2627, device='cuda:0')
episode: 283 training return: tensor(-288.8833, device='cuda:0')
epoch: 71 test_true_pfm: 2787.4795734298045 sim_pfm: -92.90327850183046
episode: 284 training return: tensor(-73.3114, device='cuda:0')
episode: 285 training return: tensor(-253.2177, device='cuda:0')
episode: 286 training return: tensor(-54.9064, device='cuda:0')
episode: 287 training return: tensor(-236.7702, device='cuda:0')
epoch: 72 test_true_pfm: 2034.9709285178797 sim_pfm: -100.32552039644604
episode: 288 training return: tensor(-328.9343, device='cuda:0')
episode: 289 training return: tensor(-217.6299, device='cuda:0')
episode: 290 training return: tensor(-337.2890, device='cuda:0')
episode: 291 training return: tensor(-334.7214, device='cuda:0')
epoch: 73 test_true_pfm: 2619.7413079228845 sim_pfm: -125.9762215113733
episode: 292 training return: tensor(-201.1055, device='cuda:0')
episode: 293 training return: tensor(82.0279, device='cuda:0')
episode: 294 training return: tensor(-363.8936, device='cuda:0')
episode: 295 training return: tensor(-242.6304, device='cuda:0')
epoch: 74 test_true_pfm: 2803.9820062618423 sim_pfm: 163.71341387747088
episode: 296 training return: tensor(-302.9831, device='cuda:0')
episode: 297 training return: tensor(14.9960, device='cuda:0')
episode: 298 training return: tensor(-25.6312, device='cuda:0')
episode: 299 training return: tensor(410.1632, device='cuda:0')
epoch: 75 test_true_pfm: 2830.5912244932606 sim_pfm: -79.24538126241532
episode: 300 training return: tensor(-82.1826, device='cuda:0')
episode: 301 training return: tensor(-344.1090, device='cuda:0')
episode: 302 training return: tensor(341.2708, device='cuda:0')
episode: 303 training return: tensor(-48.2421, device='cuda:0')
epoch: 76 test_true_pfm: 2125.7859987154875 sim_pfm: -18.41306029071954
episode: 304 training return: tensor(-359.3648, device='cuda:0')
episode: 305 training return: tensor(-340.0054, device='cuda:0')
episode: 306 training return: tensor(-339.9899, device='cuda:0')
episode: 307 training return: tensor(-79.6634, device='cuda:0')
epoch: 77 test_true_pfm: 2809.653635736009 sim_pfm: 132.95265817405502
episode: 308 training return: tensor(-340.5003, device='cuda:0')
episode: 309 training return: tensor(-264.7517, device='cuda:0')
episode: 310 training return: tensor(-118.4046, device='cuda:0')
episode: 311 training return: tensor(-194.6076, device='cuda:0')
epoch: 78 test_true_pfm: 2303.0711430118367 sim_pfm: 134.27407872820427
episode: 312 training return: tensor(-64.7122, device='cuda:0')
episode: 313 training return: tensor(-197.8501, device='cuda:0')
episode: 314 training return: tensor(136.7525, device='cuda:0')
episode: 315 training return: tensor(131.4444, device='cuda:0')
epoch: 79 test_true_pfm: 2234.4392456885794 sim_pfm: 246.8260256953848
episode: 316 training return: tensor(127.6739, device='cuda:0')
episode: 317 training return: tensor(-340.8346, device='cuda:0')
episode: 318 training return: tensor(-46.9602, device='cuda:0')
episode: 319 training return: tensor(-282.1923, device='cuda:0')
epoch: 80 test_true_pfm: 2303.396743050622 sim_pfm: 72.15719721167504
episode: 320 training return: tensor(392.8610, device='cuda:0')
episode: 321 training return: tensor(-348.1269, device='cuda:0')
episode: 322 training return: tensor(-297.3376, device='cuda:0')
episode: 323 training return: tensor(5.2051, device='cuda:0')
epoch: 81 test_true_pfm: 1815.944243060235 sim_pfm: -75.29644539684523
episode: 324 training return: tensor(-155.1603, device='cuda:0')
episode: 325 training return: tensor(-16.0340, device='cuda:0')
episode: 326 training return: tensor(371.2315, device='cuda:0')
episode: 327 training return: tensor(403.1623, device='cuda:0')
epoch: 82 test_true_pfm: 2067.4213310964446 sim_pfm: 116.48504713724833
episode: 328 training return: tensor(386.1332, device='cuda:0')
episode: 329 training return: tensor(-119.7642, device='cuda:0')
episode: 330 training return: tensor(-249.0048, device='cuda:0')
episode: 331 training return: tensor(-339.5147, device='cuda:0')
epoch: 83 test_true_pfm: 2255.264477122991 sim_pfm: 107.98297609794342
episode: 332 training return: tensor(-278.5080, device='cuda:0')
episode: 333 training return: tensor(-154.4993, device='cuda:0')
episode: 334 training return: tensor(-152.7539, device='cuda:0')
episode: 335 training return: tensor(167.6366, device='cuda:0')
epoch: 84 test_true_pfm: 2771.0616943270556 sim_pfm: 269.7865868444981
episode: 336 training return: tensor(-326.2267, device='cuda:0')
episode: 337 training return: tensor(-249.3390, device='cuda:0')
episode: 338 training return: tensor(-345.6671, device='cuda:0')
episode: 339 training return: tensor(316.7040, device='cuda:0')
epoch: 85 test_true_pfm: 1542.1227639120077 sim_pfm: -224.22841796137314
episode: 340 training return: tensor(-346.6224, device='cuda:0')
episode: 341 training return: tensor(353.2291, device='cuda:0')
episode: 342 training return: tensor(32.2346, device='cuda:0')
episode: 343 training return: tensor(92.9029, device='cuda:0')
epoch: 86 test_true_pfm: 1827.478341818108 sim_pfm: -179.87655812934585
episode: 344 training return: tensor(-313.7786, device='cuda:0')
episode: 345 training return: tensor(-57.4594, device='cuda:0')
episode: 346 training return: tensor(-362.5555, device='cuda:0')
episode: 347 training return: tensor(150.2496, device='cuda:0')
epoch: 87 test_true_pfm: 2302.543696113643 sim_pfm: 43.49320523343825
episode: 348 training return: tensor(-347.6665, device='cuda:0')
episode: 349 training return: tensor(-337.4131, device='cuda:0')
episode: 350 training return: tensor(-296.4149, device='cuda:0')
episode: 351 training return: tensor(-173.6544, device='cuda:0')
epoch: 88 test_true_pfm: 2172.5562400769613 sim_pfm: -149.32686325589506
episode: 352 training return: tensor(-153.0861, device='cuda:0')
episode: 353 training return: tensor(62.4181, device='cuda:0')
episode: 354 training return: tensor(-332.0408, device='cuda:0')
episode: 355 training return: tensor(-207.7221, device='cuda:0')
epoch: 89 test_true_pfm: 2609.4019580160657 sim_pfm: 151.44854685654477
episode: 356 training return: tensor(-151.9115, device='cuda:0')
episode: 357 training return: tensor(69.5075, device='cuda:0')
episode: 358 training return: tensor(176.1649, device='cuda:0')
episode: 359 training return: tensor(-97.1015, device='cuda:0')
epoch: 90 test_true_pfm: 1608.184681909712 sim_pfm: -100.13851115742
episode: 360 training return: tensor(-90.0836, device='cuda:0')
episode: 361 training return: tensor(-245.9931, device='cuda:0')
episode: 362 training return: tensor(-346.3979, device='cuda:0')
episode: 363 training return: tensor(-347.2638, device='cuda:0')
epoch: 91 test_true_pfm: 2378.2381089748465 sim_pfm: -70.4960151486254
episode: 364 training return: tensor(-346.8368, device='cuda:0')
episode: 365 training return: tensor(-202.1838, device='cuda:0')
episode: 366 training return: tensor(-276.9637, device='cuda:0')
episode: 367 training return: tensor(-347.4425, device='cuda:0')
epoch: 92 test_true_pfm: 2396.477943963299 sim_pfm: 124.85427598430154
episode: 368 training return: tensor(-112.7735, device='cuda:0')
episode: 369 training return: tensor(-285.1067, device='cuda:0')
episode: 370 training return: tensor(-231.4998, device='cuda:0')
episode: 371 training return: tensor(-366.1369, device='cuda:0')
epoch: 93 test_true_pfm: 2148.850859753106 sim_pfm: 135.1992418471879
episode: 372 training return: tensor(-255.7515, device='cuda:0')
episode: 373 training return: tensor(-222.2959, device='cuda:0')
episode: 374 training return: tensor(-113.9542, device='cuda:0')
episode: 375 training return: tensor(330.8636, device='cuda:0')
epoch: 94 test_true_pfm: 1980.6135485254472 sim_pfm: 112.21621641314898
episode: 376 training return: tensor(-321.3493, device='cuda:0')
episode: 377 training return: tensor(-330.1059, device='cuda:0')
episode: 378 training return: tensor(-249.3014, device='cuda:0')
episode: 379 training return: tensor(-80.6547, device='cuda:0')
epoch: 95 test_true_pfm: 2614.925810528599 sim_pfm: -103.68026540471085
episode: 380 training return: tensor(-46.2911, device='cuda:0')
episode: 381 training return: tensor(457.6696, device='cuda:0')
episode: 382 training return: tensor(-247.8937, device='cuda:0')
episode: 383 training return: tensor(-341.8363, device='cuda:0')
epoch: 96 test_true_pfm: 2412.790915501288 sim_pfm: -111.3815718269713
episode: 384 training return: tensor(-110.9016, device='cuda:0')
episode: 385 training return: tensor(50.0376, device='cuda:0')
episode: 386 training return: tensor(-281.4952, device='cuda:0')
episode: 387 training return: tensor(-253.5492, device='cuda:0')
epoch: 97 test_true_pfm: 3087.614283249939 sim_pfm: -90.94035533990245
episode: 388 training return: tensor(-59.7477, device='cuda:0')
episode: 389 training return: tensor(-240.2184, device='cuda:0')
episode: 390 training return: tensor(26.0837, device='cuda:0')
episode: 391 training return: tensor(-367.0782, device='cuda:0')
epoch: 98 test_true_pfm: 2290.0820391684956 sim_pfm: 8.736991738143843
episode: 392 training return: tensor(-250.7177, device='cuda:0')
episode: 393 training return: tensor(-326.8964, device='cuda:0')
episode: 394 training return: tensor(96.3173, device='cuda:0')
episode: 395 training return: tensor(390.5413, device='cuda:0')
epoch: 99 test_true_pfm: 2964.040993522265 sim_pfm: 162.3330090030989
episode: 396 training return: tensor(374.7949, device='cuda:0')
episode: 397 training return: tensor(79.0204, device='cuda:0')
episode: 398 training return: tensor(-346.7383, device='cuda:0')
episode: 399 training return: tensor(-247.7581, device='cuda:0')
epoch: 100 test_true_pfm: 2301.5928267609875 sim_pfm: 107.61965570887939
episode: 400 training return: tensor(-262.8846, device='cuda:0')
episode: 401 training return: tensor(-263.7591, device='cuda:0')
episode: 402 training return: tensor(-231.9060, device='cuda:0')
episode: 403 training return: tensor(-253.1853, device='cuda:0')
epoch: 101 test_true_pfm: 2454.8232671000806 sim_pfm: -19.494662294765778
episode: 404 training return: tensor(441.2238, device='cuda:0')
episode: 405 training return: tensor(197.6121, device='cuda:0')
episode: 406 training return: tensor(39.9188, device='cuda:0')
episode: 407 training return: tensor(-241.0584, device='cuda:0')
epoch: 102 test_true_pfm: 2141.5940223660023 sim_pfm: -142.20322344143642
episode: 408 training return: tensor(-339.9107, device='cuda:0')
episode: 409 training return: tensor(-294.7589, device='cuda:0')
episode: 410 training return: tensor(-297.4595, device='cuda:0')
episode: 411 training return: tensor(-376.0894, device='cuda:0')
epoch: 103 test_true_pfm: 2181.4490298095016 sim_pfm: -64.21191923206788
episode: 412 training return: tensor(-348.9753, device='cuda:0')
episode: 413 training return: tensor(-290.5369, device='cuda:0')
episode: 414 training return: tensor(-246.8964, device='cuda:0')
episode: 415 training return: tensor(-291.3065, device='cuda:0')
epoch: 104 test_true_pfm: 2206.7338537980663 sim_pfm: -59.27258244093779
episode: 416 training return: tensor(-53.4920, device='cuda:0')
episode: 417 training return: tensor(-288.8770, device='cuda:0')
episode: 418 training return: tensor(-61.9738, device='cuda:0')
episode: 419 training return: tensor(-291.3239, device='cuda:0')
epoch: 105 test_true_pfm: 2756.8404710597583 sim_pfm: -189.15356548962882
episode: 420 training return: tensor(-293.1203, device='cuda:0')
episode: 421 training return: tensor(-344.2920, device='cuda:0')
episode: 422 training return: tensor(-18.3800, device='cuda:0')
episode: 423 training return: tensor(-76.8936, device='cuda:0')
epoch: 106 test_true_pfm: 2132.232277129115 sim_pfm: -98.47206667081143
episode: 424 training return: tensor(-200.0554, device='cuda:0')
episode: 425 training return: tensor(22.7637, device='cuda:0')
episode: 426 training return: tensor(52.5067, device='cuda:0')
episode: 427 training return: tensor(127.4078, device='cuda:0')
epoch: 107 test_true_pfm: 2228.898001012278 sim_pfm: 255.10129368079166
episode: 428 training return: tensor(-263.2369, device='cuda:0')
episode: 429 training return: tensor(350.6907, device='cuda:0')
episode: 430 training return: tensor(-268.3402, device='cuda:0')
episode: 431 training return: tensor(-8.9180, device='cuda:0')
epoch: 108 test_true_pfm: 2407.7134417173247 sim_pfm: 193.92301436311877
episode: 432 training return: tensor(-159.0761, device='cuda:0')
episode: 433 training return: tensor(1.3734, device='cuda:0')
episode: 434 training return: tensor(-153.7511, device='cuda:0')
episode: 435 training return: tensor(-252.2753, device='cuda:0')
epoch: 109 test_true_pfm: 2280.8924944421997 sim_pfm: 172.15832339196155
episode: 436 training return: tensor(374.6093, device='cuda:0')
episode: 437 training return: tensor(397.2106, device='cuda:0')
episode: 438 training return: tensor(-98.4083, device='cuda:0')
episode: 439 training return: tensor(380.7984, device='cuda:0')
epoch: 110 test_true_pfm: 2779.9568158819784 sim_pfm: 208.91646613373692
episode: 440 training return: tensor(-276.8128, device='cuda:0')
episode: 441 training return: tensor(-206.0094, device='cuda:0')
episode: 442 training return: tensor(-330.4780, device='cuda:0')
episode: 443 training return: tensor(356.6187, device='cuda:0')
epoch: 111 test_true_pfm: 2629.6686601448578 sim_pfm: -112.6603569558162
episode: 444 training return: tensor(-248.9507, device='cuda:0')
episode: 445 training return: tensor(257.0541, device='cuda:0')
episode: 446 training return: tensor(345.4235, device='cuda:0')
episode: 447 training return: tensor(-348.7491, device='cuda:0')
epoch: 112 test_true_pfm: 1466.186717096989 sim_pfm: -124.51536596671212
episode: 448 training return: tensor(355.9209, device='cuda:0')
episode: 449 training return: tensor(-201.5702, device='cuda:0')
episode: 450 training return: tensor(-185.2771, device='cuda:0')
episode: 451 training return: tensor(-255.3984, device='cuda:0')
epoch: 113 test_true_pfm: 1998.2513125686721 sim_pfm: 19.18504701143441
episode: 452 training return: tensor(-343.2390, device='cuda:0')
episode: 453 training return: tensor(-346.0310, device='cuda:0')
episode: 454 training return: tensor(-336.4991, device='cuda:0')
episode: 455 training return: tensor(-336.5448, device='cuda:0')
epoch: 114 test_true_pfm: 2384.2620988694557 sim_pfm: 76.43086257522616
episode: 456 training return: tensor(-339.8831, device='cuda:0')
episode: 457 training return: tensor(-149.5356, device='cuda:0')
episode: 458 training return: tensor(-45.6533, device='cuda:0')
episode: 459 training return: tensor(-155.6263, device='cuda:0')
epoch: 115 test_true_pfm: 2336.686560431486 sim_pfm: 203.11419482707666
episode: 460 training return: tensor(-237.9342, device='cuda:0')
episode: 461 training return: tensor(-197.5483, device='cuda:0')
episode: 462 training return: tensor(240.0358, device='cuda:0')
episode: 463 training return: tensor(335.4960, device='cuda:0')
epoch: 116 test_true_pfm: 2026.8605840133998 sim_pfm: 366.9037476860297
episode: 464 training return: tensor(-10.9251, device='cuda:0')
episode: 465 training return: tensor(-46.0370, device='cuda:0')
episode: 466 training return: tensor(-205.9442, device='cuda:0')
episode: 467 training return: tensor(-95.9121, device='cuda:0')
epoch: 117 test_true_pfm: 2235.9851069478564 sim_pfm: 79.57061804885355
episode: 468 training return: tensor(-99.4936, device='cuda:0')
episode: 469 training return: tensor(234.8238, device='cuda:0')
episode: 470 training return: tensor(-339.1603, device='cuda:0')
episode: 471 training return: tensor(-350.5478, device='cuda:0')
epoch: 118 test_true_pfm: 1894.8069037056418 sim_pfm: -81.0801390351262
episode: 472 training return: tensor(-341.2187, device='cuda:0')
episode: 473 training return: tensor(-57.1380, device='cuda:0')
episode: 474 training return: tensor(-362.2844, device='cuda:0')
episode: 475 training return: tensor(-90.1989, device='cuda:0')
epoch: 119 test_true_pfm: 1836.084778554626 sim_pfm: 115.7108371173963
episode: 476 training return: tensor(-175.8144, device='cuda:0')
episode: 477 training return: tensor(340.7136, device='cuda:0')
episode: 478 training return: tensor(186.4191, device='cuda:0')
episode: 479 training return: tensor(-201.6302, device='cuda:0')
epoch: 120 test_true_pfm: 2279.687980887577 sim_pfm: -56.47946234295765
episode: 480 training return: tensor(-265.0542, device='cuda:0')
episode: 481 training return: tensor(-299.1917, device='cuda:0')
episode: 482 training return: tensor(-361.2696, device='cuda:0')
episode: 483 training return: tensor(-187.2797, device='cuda:0')
epoch: 121 test_true_pfm: 2477.052124443732 sim_pfm: 202.57856409296315
episode: 484 training return: tensor(405.7710, device='cuda:0')
episode: 485 training return: tensor(-248.8226, device='cuda:0')
episode: 486 training return: tensor(-248.4439, device='cuda:0')
episode: 487 training return: tensor(-99.5401, device='cuda:0')
epoch: 122 test_true_pfm: 2378.161172247114 sim_pfm: 150.85082339530345
episode: 488 training return: tensor(358.9120, device='cuda:0')
episode: 489 training return: tensor(-241.9486, device='cuda:0')
episode: 490 training return: tensor(408.4005, device='cuda:0')
episode: 491 training return: tensor(363.3051, device='cuda:0')
epoch: 123 test_true_pfm: 2492.8685857101004 sim_pfm: -143.87568352476228
episode: 492 training return: tensor(171.9144, device='cuda:0')
episode: 493 training return: tensor(107.0372, device='cuda:0')
episode: 494 training return: tensor(-114.6065, device='cuda:0')
episode: 495 training return: tensor(90.5144, device='cuda:0')
epoch: 124 test_true_pfm: 1862.704058690948 sim_pfm: -74.14557524721992
episode: 496 training return: tensor(-43.0438, device='cuda:0')
episode: 497 training return: tensor(385.4462, device='cuda:0')
episode: 498 training return: tensor(-287.1294, device='cuda:0')
episode: 499 training return: tensor(-15.4855, device='cuda:0')
epoch: 125 test_true_pfm: 2079.7477185349085 sim_pfm: 300.72799425632303
episode: 500 training return: tensor(-280.0180, device='cuda:0')
episode: 501 training return: tensor(-75.7768, device='cuda:0')
episode: 502 training return: tensor(-172.6209, device='cuda:0')
episode: 503 training return: tensor(-335.6297, device='cuda:0')
epoch: 126 test_true_pfm: 2881.6470125577903 sim_pfm: -147.1204978459864
episode: 504 training return: tensor(124.2947, device='cuda:0')
episode: 505 training return: tensor(-342.8055, device='cuda:0')
episode: 506 training return: tensor(-44.9271, device='cuda:0')
episode: 507 training return: tensor(345.0499, device='cuda:0')
epoch: 127 test_true_pfm: 2125.5400838695673 sim_pfm: -41.55751595040783
episode: 508 training return: tensor(-356.1379, device='cuda:0')
episode: 509 training return: tensor(-339.2433, device='cuda:0')
episode: 510 training return: tensor(-337.4760, device='cuda:0')
episode: 511 training return: tensor(-345.6064, device='cuda:0')
epoch: 128 test_true_pfm: 1568.6931497624582 sim_pfm: 56.69802913127933
episode: 512 training return: tensor(-350.5894, device='cuda:0')
episode: 513 training return: tensor(-346.3665, device='cuda:0')
episode: 514 training return: tensor(-175.4934, device='cuda:0')
episode: 515 training return: tensor(-344.1037, device='cuda:0')
epoch: 129 test_true_pfm: 2573.741930466406 sim_pfm: 4.829838587233098
episode: 516 training return: tensor(-238.6100, device='cuda:0')
episode: 517 training return: tensor(-343.3886, device='cuda:0')
episode: 518 training return: tensor(-343.8084, device='cuda:0')
episode: 519 training return: tensor(177.3212, device='cuda:0')
epoch: 130 test_true_pfm: 2684.184856017716 sim_pfm: 2.401409557525767
episode: 520 training return: tensor(354.1946, device='cuda:0')
episode: 521 training return: tensor(-343.2031, device='cuda:0')
episode: 522 training return: tensor(-215.8213, device='cuda:0')
episode: 523 training return: tensor(-154.1348, device='cuda:0')
epoch: 131 test_true_pfm: 2230.3303648792057 sim_pfm: 2.4224150754744187
episode: 524 training return: tensor(-237.9466, device='cuda:0')
episode: 525 training return: tensor(-233.5388, device='cuda:0')
episode: 526 training return: tensor(-346.0887, device='cuda:0')
episode: 527 training return: tensor(273.0492, device='cuda:0')
epoch: 132 test_true_pfm: 2894.2927480039148 sim_pfm: -4.659148013840119
episode: 528 training return: tensor(62.4980, device='cuda:0')
episode: 529 training return: tensor(337.5446, device='cuda:0')
episode: 530 training return: tensor(369.7283, device='cuda:0')
episode: 531 training return: tensor(-69.0891, device='cuda:0')
epoch: 133 test_true_pfm: 1723.9860342572458 sim_pfm: -144.57010786642786
episode: 532 training return: tensor(-249.7675, device='cuda:0')
episode: 533 training return: tensor(-239.1268, device='cuda:0')
episode: 534 training return: tensor(-334.2339, device='cuda:0')
episode: 535 training return: tensor(-343.0905, device='cuda:0')
epoch: 134 test_true_pfm: 2205.3027632805283 sim_pfm: -145.19690779722683
episode: 536 training return: tensor(-217.8277, device='cuda:0')
episode: 537 training return: tensor(-338.8343, device='cuda:0')
episode: 538 training return: tensor(-339.9737, device='cuda:0')
episode: 539 training return: tensor(-71.0980, device='cuda:0')
epoch: 135 test_true_pfm: 2253.3654198217105 sim_pfm: -11.496593927498907
episode: 540 training return: tensor(21.2313, device='cuda:0')
episode: 541 training return: tensor(-335.3492, device='cuda:0')
episode: 542 training return: tensor(-341.5308, device='cuda:0')
episode: 543 training return: tensor(-340.6824, device='cuda:0')
epoch: 136 test_true_pfm: 2094.6483075729475 sim_pfm: -118.8883315633866
episode: 544 training return: tensor(-255.4174, device='cuda:0')
episode: 545 training return: tensor(-353.3755, device='cuda:0')
episode: 546 training return: tensor(-347.6727, device='cuda:0')
episode: 547 training return: tensor(-341.6156, device='cuda:0')
epoch: 137 test_true_pfm: 1986.5232375882224 sim_pfm: -246.41484443986943
episode: 548 training return: tensor(-119.3520, device='cuda:0')
episode: 549 training return: tensor(-339.2995, device='cuda:0')
episode: 550 training return: tensor(-101.7689, device='cuda:0')
episode: 551 training return: tensor(-174.3316, device='cuda:0')
epoch: 138 test_true_pfm: 2335.8739408782208 sim_pfm: 12.475863633735571
episode: 552 training return: tensor(-343.0648, device='cuda:0')
episode: 553 training return: tensor(-342.9886, device='cuda:0')
episode: 554 training return: tensor(315.4517, device='cuda:0')
episode: 555 training return: tensor(-301.0785, device='cuda:0')
epoch: 139 test_true_pfm: 2042.4685029040265 sim_pfm: 48.77587121230317
episode: 556 training return: tensor(143.0791, device='cuda:0')
episode: 557 training return: tensor(-239.0582, device='cuda:0')
episode: 558 training return: tensor(-159.6179, device='cuda:0')
episode: 559 training return: tensor(-350.0833, device='cuda:0')
epoch: 140 test_true_pfm: 2837.608042829616 sim_pfm: 118.78504569029126
episode: 560 training return: tensor(136.5131, device='cuda:0')
episode: 561 training return: tensor(-205.2690, device='cuda:0')
episode: 562 training return: tensor(-8.8216, device='cuda:0')
episode: 563 training return: tensor(98.5440, device='cuda:0')
epoch: 141 test_true_pfm: 2358.9859690707817 sim_pfm: 15.12583818557323
episode: 564 training return: tensor(370.9912, device='cuda:0')
episode: 565 training return: tensor(-345.0442, device='cuda:0')
episode: 566 training return: tensor(-254.8566, device='cuda:0')
episode: 567 training return: tensor(-237.7086, device='cuda:0')
epoch: 142 test_true_pfm: 1852.3690570198817 sim_pfm: -222.8695596108931
episode: 568 training return: tensor(-337.7539, device='cuda:0')
episode: 569 training return: tensor(131.7504, device='cuda:0')
episode: 570 training return: tensor(-343.4655, device='cuda:0')
episode: 571 training return: tensor(-339.3963, device='cuda:0')
epoch: 143 test_true_pfm: 2213.487211845124 sim_pfm: -86.12132125192632
episode: 572 training return: tensor(-278.5125, device='cuda:0')
episode: 573 training return: tensor(-340.6816, device='cuda:0')
episode: 574 training return: tensor(-292.1621, device='cuda:0')
episode: 575 training return: tensor(-60.3598, device='cuda:0')
epoch: 144 test_true_pfm: 2625.8546061317497 sim_pfm: 80.11375484796979
episode: 576 training return: tensor(401.7341, device='cuda:0')
episode: 577 training return: tensor(-351.1068, device='cuda:0')
episode: 578 training return: tensor(-292.8869, device='cuda:0')
episode: 579 training return: tensor(-333.5824, device='cuda:0')
epoch: 145 test_true_pfm: 1651.5520762191125 sim_pfm: -168.68923037390536
episode: 580 training return: tensor(-282.8344, device='cuda:0')
episode: 581 training return: tensor(-69.7054, device='cuda:0')
episode: 582 training return: tensor(-57.8532, device='cuda:0')
episode: 583 training return: tensor(-338.7309, device='cuda:0')
epoch: 146 test_true_pfm: 2644.2597262401982 sim_pfm: -175.31316832418088
episode: 584 training return: tensor(-303.6960, device='cuda:0')
episode: 585 training return: tensor(163.9844, device='cuda:0')
episode: 586 training return: tensor(438.8511, device='cuda:0')
episode: 587 training return: tensor(23.9347, device='cuda:0')
epoch: 147 test_true_pfm: 1462.6282764683003 sim_pfm: -22.82091125442336
episode: 588 training return: tensor(-151.8080, device='cuda:0')
episode: 589 training return: tensor(-366.4320, device='cuda:0')
episode: 590 training return: tensor(-308.7389, device='cuda:0')
episode: 591 training return: tensor(-177.9536, device='cuda:0')
epoch: 148 test_true_pfm: 3241.9431737973573 sim_pfm: 57.22960107874436
episode: 592 training return: tensor(-348.1262, device='cuda:0')
episode: 593 training return: tensor(-302.8017, device='cuda:0')
episode: 594 training return: tensor(-335.7694, device='cuda:0')
episode: 595 training return: tensor(372.1927, device='cuda:0')
epoch: 149 test_true_pfm: 2050.491561852352 sim_pfm: -199.73947364458581
episode: 596 training return: tensor(-300.5725, device='cuda:0')
episode: 597 training return: tensor(370.6352, device='cuda:0')
episode: 598 training return: tensor(-285.4500, device='cuda:0')
episode: 599 training return: tensor(99.5877, device='cuda:0')
epoch: 150 test_true_pfm: 1612.2032628658226 sim_pfm: 132.13438604925372
