['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '0', '--data', '100000', '--regu', '0.3']
2137.3817152188217
episode: 0 training return: tensor(-357.9594, device='cuda:0')
episode: 1 training return: tensor(-194.0442, device='cuda:0')
episode: 2 training return: tensor(-184.6308, device='cuda:0')
episode: 3 training return: tensor(366.4538, device='cuda:0')
epoch: 1 test_true_pfm: 3119.324141342952 sim_pfm: 115.67427502721937
episode: 4 training return: tensor(-464.4851, device='cuda:0')
episode: 5 training return: tensor(-273.5326, device='cuda:0')
episode: 6 training return: tensor(-190.2197, device='cuda:0')
episode: 7 training return: tensor(154.0549, device='cuda:0')
epoch: 2 test_true_pfm: 2074.6434020881075 sim_pfm: -46.162646763492376
episode: 8 training return: tensor(-207.8528, device='cuda:0')
episode: 9 training return: tensor(-470.0566, device='cuda:0')
episode: 10 training return: tensor(-386.3406, device='cuda:0')
episode: 11 training return: tensor(-314.0534, device='cuda:0')
epoch: 3 test_true_pfm: 1690.3514067915758 sim_pfm: 87.12247671631242
episode: 12 training return: tensor(-413.5526, device='cuda:0')
episode: 13 training return: tensor(-263.8169, device='cuda:0')
episode: 14 training return: tensor(-468.3988, device='cuda:0')
episode: 15 training return: tensor(277.3935, device='cuda:0')
epoch: 4 test_true_pfm: 1127.4009765400626 sim_pfm: -359.31117450548726
episode: 16 training return: tensor(-379.3068, device='cuda:0')
episode: 17 training return: tensor(-414.0763, device='cuda:0')
episode: 18 training return: tensor(-333.7397, device='cuda:0')
episode: 19 training return: tensor(-479.2886, device='cuda:0')
epoch: 5 test_true_pfm: 1785.7822475979565 sim_pfm: 5.857561131978097
episode: 20 training return: tensor(-365.7369, device='cuda:0')
episode: 21 training return: tensor(-372.5604, device='cuda:0')
episode: 22 training return: tensor(-433.9604, device='cuda:0')
episode: 23 training return: tensor(-361.6665, device='cuda:0')
epoch: 6 test_true_pfm: 1742.4384596050152 sim_pfm: -103.46744714996505
episode: 24 training return: tensor(-469.7253, device='cuda:0')
episode: 25 training return: tensor(-134.7748, device='cuda:0')
episode: 26 training return: tensor(-446.8688, device='cuda:0')
episode: 27 training return: tensor(-409.9593, device='cuda:0')
epoch: 7 test_true_pfm: 958.3607401686949 sim_pfm: -469.7990195830741
episode: 28 training return: tensor(-491.0587, device='cuda:0')
episode: 29 training return: tensor(-507.6453, device='cuda:0')
episode: 30 training return: tensor(-451.5761, device='cuda:0')
episode: 31 training return: tensor(-506.0829, device='cuda:0')
epoch: 8 test_true_pfm: 1007.7737679259004 sim_pfm: -456.8626303342947
episode: 32 training return: tensor(-490.3721, device='cuda:0')
episode: 33 training return: tensor(-454.8932, device='cuda:0')
episode: 34 training return: tensor(-377.5616, device='cuda:0')
episode: 35 training return: tensor(-468.9442, device='cuda:0')
epoch: 9 test_true_pfm: 1142.9346658841912 sim_pfm: -426.6177336804879
episode: 36 training return: tensor(-469.4942, device='cuda:0')
episode: 37 training return: tensor(-223.1931, device='cuda:0')
episode: 38 training return: tensor(-458.1715, device='cuda:0')
episode: 39 training return: tensor(-390.2298, device='cuda:0')
epoch: 10 test_true_pfm: 1426.2152387244566 sim_pfm: -316.69797223199083
episode: 40 training return: tensor(-451.6885, device='cuda:0')
episode: 41 training return: tensor(-405.7698, device='cuda:0')
episode: 42 training return: tensor(-481.1725, device='cuda:0')
episode: 43 training return: tensor(-212.3645, device='cuda:0')
epoch: 11 test_true_pfm: 1575.6625118859154 sim_pfm: -295.95962933691527
episode: 44 training return: tensor(-462.4726, device='cuda:0')
episode: 45 training return: tensor(-366.1882, device='cuda:0')
episode: 46 training return: tensor(-397.3954, device='cuda:0')
episode: 47 training return: tensor(-239.8015, device='cuda:0')
epoch: 12 test_true_pfm: 1285.12134008509 sim_pfm: -293.22082451106206
episode: 48 training return: tensor(-264.5555, device='cuda:0')
episode: 49 training return: tensor(-181.7488, device='cuda:0')
episode: 50 training return: tensor(-286.7950, device='cuda:0')
episode: 51 training return: tensor(-161.8327, device='cuda:0')
epoch: 13 test_true_pfm: 1246.1177410979114 sim_pfm: -373.5248333074463
episode: 52 training return: tensor(-379.4197, device='cuda:0')
episode: 53 training return: tensor(-420.8984, device='cuda:0')
episode: 54 training return: tensor(-290.9173, device='cuda:0')
episode: 55 training return: tensor(-367.9577, device='cuda:0')
epoch: 14 test_true_pfm: 2793.513031098572 sim_pfm: -118.70247145897399
episode: 56 training return: tensor(-426.2668, device='cuda:0')
episode: 57 training return: tensor(-104.6933, device='cuda:0')
episode: 58 training return: tensor(-315.3835, device='cuda:0')
episode: 59 training return: tensor(-165.7569, device='cuda:0')
epoch: 15 test_true_pfm: 1792.5611917734925 sim_pfm: -191.43545167675862
episode: 60 training return: tensor(-79.0944, device='cuda:0')
episode: 61 training return: tensor(-381.9649, device='cuda:0')
episode: 62 training return: tensor(-266.1975, device='cuda:0')
episode: 63 training return: tensor(-245.0392, device='cuda:0')
epoch: 16 test_true_pfm: 1783.740871392585 sim_pfm: 169.21044344206652
episode: 64 training return: tensor(-157.6102, device='cuda:0')
episode: 65 training return: tensor(-350.1853, device='cuda:0')
episode: 66 training return: tensor(-350.1576, device='cuda:0')
episode: 67 training return: tensor(-119.2979, device='cuda:0')
epoch: 17 test_true_pfm: 2414.3100239016026 sim_pfm: 185.4413511257153
episode: 68 training return: tensor(48.4342, device='cuda:0')
episode: 69 training return: tensor(-159.1160, device='cuda:0')
episode: 70 training return: tensor(-353.7315, device='cuda:0')
episode: 71 training return: tensor(-424.9455, device='cuda:0')
epoch: 18 test_true_pfm: 1309.2164526307154 sim_pfm: -321.1120230544475
episode: 72 training return: tensor(-350.8659, device='cuda:0')
episode: 73 training return: tensor(-180.4973, device='cuda:0')
episode: 74 training return: tensor(-250.4103, device='cuda:0')
episode: 75 training return: tensor(-156.6295, device='cuda:0')
epoch: 19 test_true_pfm: 1870.8908232145122 sim_pfm: -234.73433025926352
episode: 76 training return: tensor(-250.2322, device='cuda:0')
episode: 77 training return: tensor(12.7683, device='cuda:0')
episode: 78 training return: tensor(-25.3822, device='cuda:0')
episode: 79 training return: tensor(398.6965, device='cuda:0')
epoch: 20 test_true_pfm: 2590.2342682626268 sim_pfm: -123.59592980984598
episode: 80 training return: tensor(-342.7183, device='cuda:0')
episode: 81 training return: tensor(-257.4296, device='cuda:0')
episode: 82 training return: tensor(9.1527, device='cuda:0')
episode: 83 training return: tensor(-306.5522, device='cuda:0')
epoch: 21 test_true_pfm: 1272.5883709821414 sim_pfm: -361.90045608250267
episode: 84 training return: tensor(-168.9427, device='cuda:0')
episode: 85 training return: tensor(-313.3676, device='cuda:0')
episode: 86 training return: tensor(-336.5908, device='cuda:0')
episode: 87 training return: tensor(-225.7383, device='cuda:0')
epoch: 22 test_true_pfm: 1970.8908747289524 sim_pfm: -89.61981685492599
episode: 88 training return: tensor(-240.7627, device='cuda:0')
episode: 89 training return: tensor(-152.7334, device='cuda:0')
episode: 90 training return: tensor(-62.2238, device='cuda:0')
episode: 91 training return: tensor(-288.5374, device='cuda:0')
epoch: 23 test_true_pfm: 1549.3040418040453 sim_pfm: -224.07058673359765
episode: 92 training return: tensor(-301.0404, device='cuda:0')
episode: 93 training return: tensor(-360.6275, device='cuda:0')
episode: 94 training return: tensor(-85.0708, device='cuda:0')
episode: 95 training return: tensor(-253.3277, device='cuda:0')
epoch: 24 test_true_pfm: 2240.182540235992 sim_pfm: -50.8625789245901
episode: 96 training return: tensor(-375.7355, device='cuda:0')
episode: 97 training return: tensor(-186.0343, device='cuda:0')
episode: 98 training return: tensor(-35.8308, device='cuda:0')
episode: 99 training return: tensor(-353.4766, device='cuda:0')
epoch: 25 test_true_pfm: 1427.082589607724 sim_pfm: -32.25773967810286
episode: 100 training return: tensor(-14.5141, device='cuda:0')
episode: 101 training return: tensor(-266.5072, device='cuda:0')
episode: 102 training return: tensor(-180.2868, device='cuda:0')
episode: 103 training return: tensor(-164.3781, device='cuda:0')
epoch: 26 test_true_pfm: 1383.4149101094533 sim_pfm: -158.48868100413043
episode: 104 training return: tensor(104.1247, device='cuda:0')
episode: 105 training return: tensor(82.2804, device='cuda:0')
episode: 106 training return: tensor(113.8691, device='cuda:0')
episode: 107 training return: tensor(-370.2735, device='cuda:0')
epoch: 27 test_true_pfm: 1800.6487246656072 sim_pfm: 3.7419926932392023
episode: 108 training return: tensor(-85.6713, device='cuda:0')
episode: 109 training return: tensor(-406.2529, device='cuda:0')
episode: 110 training return: tensor(-182.6739, device='cuda:0')
episode: 111 training return: tensor(-216.2688, device='cuda:0')
epoch: 28 test_true_pfm: 2434.5624432453446 sim_pfm: -42.16785251981734
episode: 112 training return: tensor(-194.6579, device='cuda:0')
episode: 113 training return: tensor(19.1632, device='cuda:0')
episode: 114 training return: tensor(-365.9935, device='cuda:0')
episode: 115 training return: tensor(121.9818, device='cuda:0')
epoch: 29 test_true_pfm: 1878.0468236112963 sim_pfm: 112.9880118839598
episode: 116 training return: tensor(-285.5306, device='cuda:0')
episode: 117 training return: tensor(-135.0855, device='cuda:0')
episode: 118 training return: tensor(-164.1950, device='cuda:0')
episode: 119 training return: tensor(-164.9179, device='cuda:0')
epoch: 30 test_true_pfm: 1559.4614860532383 sim_pfm: -240.03608946998915
episode: 120 training return: tensor(-256.6786, device='cuda:0')
episode: 121 training return: tensor(52.1056, device='cuda:0')
episode: 122 training return: tensor(-220.1024, device='cuda:0')
episode: 123 training return: tensor(-263.9514, device='cuda:0')
epoch: 31 test_true_pfm: 1585.7565548424027 sim_pfm: 168.44810719512557
episode: 124 training return: tensor(-187.8113, device='cuda:0')
episode: 125 training return: tensor(-364.1443, device='cuda:0')
episode: 126 training return: tensor(-381.3079, device='cuda:0')
episode: 127 training return: tensor(-374.5383, device='cuda:0')
epoch: 32 test_true_pfm: 2640.157409124226 sim_pfm: 20.5362981831034
episode: 128 training return: tensor(-322.6592, device='cuda:0')
episode: 129 training return: tensor(-303.7400, device='cuda:0')
episode: 130 training return: tensor(-276.0962, device='cuda:0')
episode: 131 training return: tensor(-161.8481, device='cuda:0')
epoch: 33 test_true_pfm: 1899.805405823343 sim_pfm: -237.45882970913468
episode: 132 training return: tensor(-363.6205, device='cuda:0')
episode: 133 training return: tensor(-182.4279, device='cuda:0')
episode: 134 training return: tensor(-230.7892, device='cuda:0')
episode: 135 training return: tensor(-373.3080, device='cuda:0')
epoch: 34 test_true_pfm: 1583.0389453065761 sim_pfm: -48.88572211385084
episode: 136 training return: tensor(-246.3400, device='cuda:0')
episode: 137 training return: tensor(-287.2677, device='cuda:0')
episode: 138 training return: tensor(-422.3298, device='cuda:0')
episode: 139 training return: tensor(-417.9336, device='cuda:0')
epoch: 35 test_true_pfm: 1307.1359791585471 sim_pfm: -336.79215848764096
episode: 140 training return: tensor(-296.5012, device='cuda:0')
episode: 141 training return: tensor(-251.1727, device='cuda:0')
episode: 142 training return: tensor(-368.1889, device='cuda:0')
episode: 143 training return: tensor(-276.2512, device='cuda:0')
epoch: 36 test_true_pfm: 2818.2233423154507 sim_pfm: -81.04164471511224
episode: 144 training return: tensor(-8.3082, device='cuda:0')
episode: 145 training return: tensor(-186.4212, device='cuda:0')
episode: 146 training return: tensor(-10.8982, device='cuda:0')
episode: 147 training return: tensor(-382.8511, device='cuda:0')
epoch: 37 test_true_pfm: 1312.8583534499742 sim_pfm: -326.5879799024745
episode: 148 training return: tensor(-197.1746, device='cuda:0')
episode: 149 training return: tensor(-32.7784, device='cuda:0')
episode: 150 training return: tensor(-353.8023, device='cuda:0')
episode: 151 training return: tensor(-230.7191, device='cuda:0')
epoch: 38 test_true_pfm: 2125.1866016044864 sim_pfm: -31.9438156481289
episode: 152 training return: tensor(-407.2730, device='cuda:0')
episode: 153 training return: tensor(-73.3371, device='cuda:0')
episode: 154 training return: tensor(-422.2431, device='cuda:0')
episode: 155 training return: tensor(-203.3654, device='cuda:0')
epoch: 39 test_true_pfm: 2295.08073837576 sim_pfm: 32.027930319968924
episode: 156 training return: tensor(-428.2422, device='cuda:0')
episode: 157 training return: tensor(441.0721, device='cuda:0')
episode: 158 training return: tensor(-346.9869, device='cuda:0')
episode: 159 training return: tensor(142.3026, device='cuda:0')
epoch: 40 test_true_pfm: 2516.1000273420705 sim_pfm: 146.9508112214195
episode: 160 training return: tensor(-276.9888, device='cuda:0')
episode: 161 training return: tensor(-73.8662, device='cuda:0')
episode: 162 training return: tensor(-190.9512, device='cuda:0')
episode: 163 training return: tensor(-272.4234, device='cuda:0')
epoch: 41 test_true_pfm: 1698.4059137777224 sim_pfm: 96.36871534776098
episode: 164 training return: tensor(-46.0464, device='cuda:0')
episode: 165 training return: tensor(-52.5922, device='cuda:0')
episode: 166 training return: tensor(-465.7479, device='cuda:0')
episode: 167 training return: tensor(-450.6522, device='cuda:0')
epoch: 42 test_true_pfm: 2072.8764661603996 sim_pfm: 18.157667331048287
episode: 168 training return: tensor(-244.0939, device='cuda:0')
episode: 169 training return: tensor(41.6260, device='cuda:0')
episode: 170 training return: tensor(-35.9906, device='cuda:0')
episode: 171 training return: tensor(-276.0909, device='cuda:0')
epoch: 43 test_true_pfm: 1601.7448904146493 sim_pfm: -262.3031970760785
episode: 172 training return: tensor(58.4650, device='cuda:0')
episode: 173 training return: tensor(-244.5220, device='cuda:0')
episode: 174 training return: tensor(-366.5211, device='cuda:0')
episode: 175 training return: tensor(-267.2298, device='cuda:0')
epoch: 44 test_true_pfm: 1651.733267608406 sim_pfm: -167.08615011296934
episode: 176 training return: tensor(-302.0642, device='cuda:0')
episode: 177 training return: tensor(-90.3070, device='cuda:0')
episode: 178 training return: tensor(159.0664, device='cuda:0')
episode: 179 training return: tensor(-247.2944, device='cuda:0')
epoch: 45 test_true_pfm: 2614.964133994608 sim_pfm: 407.0182655203001
episode: 180 training return: tensor(-420.6529, device='cuda:0')
episode: 181 training return: tensor(-3.4242, device='cuda:0')
episode: 182 training return: tensor(-412.8582, device='cuda:0')
episode: 183 training return: tensor(-145.8987, device='cuda:0')
epoch: 46 test_true_pfm: 3069.063687804501 sim_pfm: 137.04992770496756
episode: 184 training return: tensor(-176.8434, device='cuda:0')
episode: 185 training return: tensor(-65.8213, device='cuda:0')
episode: 186 training return: tensor(-380.4151, device='cuda:0')
episode: 187 training return: tensor(368.7318, device='cuda:0')
epoch: 47 test_true_pfm: 2449.03014408306 sim_pfm: 288.2733328817412
episode: 188 training return: tensor(-336.7500, device='cuda:0')
episode: 189 training return: tensor(-349.4323, device='cuda:0')
episode: 190 training return: tensor(-179.7928, device='cuda:0')
episode: 191 training return: tensor(-178.5417, device='cuda:0')
epoch: 48 test_true_pfm: 2175.144590555086 sim_pfm: 286.8944042126338
episode: 192 training return: tensor(-302.7415, device='cuda:0')
episode: 193 training return: tensor(-223.4766, device='cuda:0')
episode: 194 training return: tensor(-183.5533, device='cuda:0')
episode: 195 training return: tensor(-260.6194, device='cuda:0')
epoch: 49 test_true_pfm: 3326.623962087857 sim_pfm: 401.4436178747371
episode: 196 training return: tensor(-67.6740, device='cuda:0')
episode: 197 training return: tensor(-130.9893, device='cuda:0')
episode: 198 training return: tensor(-357.9625, device='cuda:0')
episode: 199 training return: tensor(-118.0396, device='cuda:0')
epoch: 50 test_true_pfm: 1811.9362408007203 sim_pfm: -77.83567639517908
episode: 200 training return: tensor(-178.3904, device='cuda:0')
episode: 201 training return: tensor(-360.3195, device='cuda:0')
episode: 202 training return: tensor(-298.1610, device='cuda:0')
episode: 203 training return: tensor(-27.1699, device='cuda:0')
epoch: 51 test_true_pfm: 2999.4819983314515 sim_pfm: -45.31332908072121
episode: 204 training return: tensor(-394.1029, device='cuda:0')
episode: 205 training return: tensor(-414.9011, device='cuda:0')
episode: 206 training return: tensor(-308.7956, device='cuda:0')
episode: 207 training return: tensor(-220.2059, device='cuda:0')
epoch: 52 test_true_pfm: 2676.9641203239134 sim_pfm: 103.71926836393929
episode: 208 training return: tensor(-232.9556, device='cuda:0')
episode: 209 training return: tensor(-349.5984, device='cuda:0')
episode: 210 training return: tensor(-276.6403, device='cuda:0')
episode: 211 training return: tensor(173.8354, device='cuda:0')
epoch: 53 test_true_pfm: 3274.5657912771517 sim_pfm: 398.59712145578425
episode: 212 training return: tensor(-86.2222, device='cuda:0')
episode: 213 training return: tensor(-444.9229, device='cuda:0')
episode: 214 training return: tensor(435.6312, device='cuda:0')
episode: 215 training return: tensor(100.2111, device='cuda:0')
epoch: 54 test_true_pfm: 1922.31361894568 sim_pfm: 62.99037418749261
episode: 216 training return: tensor(-379.7865, device='cuda:0')
episode: 217 training return: tensor(-327.0534, device='cuda:0')
episode: 218 training return: tensor(-210.2619, device='cuda:0')
episode: 219 training return: tensor(-376.0976, device='cuda:0')
epoch: 55 test_true_pfm: 1898.5864309679775 sim_pfm: 216.0544535193476
episode: 220 training return: tensor(-141.7570, device='cuda:0')
episode: 221 training return: tensor(-369.4034, device='cuda:0')
episode: 222 training return: tensor(-137.9184, device='cuda:0')
episode: 223 training return: tensor(-329.7079, device='cuda:0')
epoch: 56 test_true_pfm: 3290.8287363185186 sim_pfm: 164.5698571781783
episode: 224 training return: tensor(-214.0970, device='cuda:0')
episode: 225 training return: tensor(-104.4381, device='cuda:0')
episode: 226 training return: tensor(-382.8265, device='cuda:0')
episode: 227 training return: tensor(-312.0887, device='cuda:0')
epoch: 57 test_true_pfm: 3052.677797013175 sim_pfm: 170.4002767475516
episode: 228 training return: tensor(-274.8523, device='cuda:0')
episode: 229 training return: tensor(-129.6586, device='cuda:0')
episode: 230 training return: tensor(-355.8235, device='cuda:0')
episode: 231 training return: tensor(-190.2995, device='cuda:0')
epoch: 58 test_true_pfm: 2264.2517288152317 sim_pfm: 7.220823989414687
episode: 232 training return: tensor(-290.1745, device='cuda:0')
episode: 233 training return: tensor(-105.6636, device='cuda:0')
episode: 234 training return: tensor(-380.4720, device='cuda:0')
episode: 235 training return: tensor(-364.9450, device='cuda:0')
epoch: 59 test_true_pfm: 2846.659516763593 sim_pfm: 395.55639231919
episode: 236 training return: tensor(-177.6296, device='cuda:0')
episode: 237 training return: tensor(-419.3297, device='cuda:0')
episode: 238 training return: tensor(-60.7220, device='cuda:0')
episode: 239 training return: tensor(-35.9364, device='cuda:0')
epoch: 60 test_true_pfm: 3148.3461102002916 sim_pfm: 85.64049672835002
episode: 240 training return: tensor(-46.9039, device='cuda:0')
episode: 241 training return: tensor(125.0460, device='cuda:0')
episode: 242 training return: tensor(-32.6434, device='cuda:0')
episode: 243 training return: tensor(-449.6364, device='cuda:0')
epoch: 61 test_true_pfm: 3245.5305384662424 sim_pfm: 166.30202539746338
episode: 244 training return: tensor(23.9362, device='cuda:0')
episode: 245 training return: tensor(-85.6910, device='cuda:0')
episode: 246 training return: tensor(-266.8652, device='cuda:0')
episode: 247 training return: tensor(-338.3449, device='cuda:0')
epoch: 62 test_true_pfm: 2219.296603175249 sim_pfm: 286.81568866223097
episode: 248 training return: tensor(-236.9650, device='cuda:0')
episode: 249 training return: tensor(-215.1066, device='cuda:0')
episode: 250 training return: tensor(-308.2275, device='cuda:0')
episode: 251 training return: tensor(-299.7909, device='cuda:0')
epoch: 63 test_true_pfm: 2096.9138604140517 sim_pfm: 155.02124098300314
episode: 252 training return: tensor(27.0789, device='cuda:0')
episode: 253 training return: tensor(356.4642, device='cuda:0')
episode: 254 training return: tensor(-409.2231, device='cuda:0')
episode: 255 training return: tensor(-283.5389, device='cuda:0')
epoch: 64 test_true_pfm: 2996.9033514860857 sim_pfm: 247.46436366281705
episode: 256 training return: tensor(-457.2329, device='cuda:0')
episode: 257 training return: tensor(-473.9525, device='cuda:0')
episode: 258 training return: tensor(-132.7403, device='cuda:0')
episode: 259 training return: tensor(-358.9684, device='cuda:0')
epoch: 65 test_true_pfm: 2909.807283595755 sim_pfm: 397.80395219723385
episode: 260 training return: tensor(-157.2200, device='cuda:0')
episode: 261 training return: tensor(-249.5154, device='cuda:0')
episode: 262 training return: tensor(-373.9657, device='cuda:0')
episode: 263 training return: tensor(-414.4955, device='cuda:0')
epoch: 66 test_true_pfm: 3152.0759731697167 sim_pfm: 391.0609972005089
episode: 264 training return: tensor(-350.9691, device='cuda:0')
episode: 265 training return: tensor(-242.6521, device='cuda:0')
episode: 266 training return: tensor(-185.9422, device='cuda:0')
episode: 267 training return: tensor(-198.2779, device='cuda:0')
epoch: 67 test_true_pfm: 3305.8528155686477 sim_pfm: 400.72157070366666
episode: 268 training return: tensor(-292.9836, device='cuda:0')
episode: 269 training return: tensor(250.1199, device='cuda:0')
episode: 270 training return: tensor(17.7549, device='cuda:0')
episode: 271 training return: tensor(-73.6188, device='cuda:0')
epoch: 68 test_true_pfm: 2947.0716831619034 sim_pfm: 241.915434774186
episode: 272 training return: tensor(-157.8103, device='cuda:0')
episode: 273 training return: tensor(332.6919, device='cuda:0')
episode: 274 training return: tensor(-280.5544, device='cuda:0')
episode: 275 training return: tensor(-321.6676, device='cuda:0')
epoch: 69 test_true_pfm: 3316.6703566287647 sim_pfm: 404.88446128135547
episode: 276 training return: tensor(-79.2245, device='cuda:0')
episode: 277 training return: tensor(-381.8365, device='cuda:0')
episode: 278 training return: tensor(-41.7978, device='cuda:0')
episode: 279 training return: tensor(407.2535, device='cuda:0')
epoch: 70 test_true_pfm: 2373.24585753229 sim_pfm: -6.4781049405379845
episode: 280 training return: tensor(-392.7890, device='cuda:0')
episode: 281 training return: tensor(365.8642, device='cuda:0')
episode: 282 training return: tensor(-64.8798, device='cuda:0')
episode: 283 training return: tensor(-466.4854, device='cuda:0')
epoch: 71 test_true_pfm: 3335.334514286403 sim_pfm: 410.47913092465996
episode: 284 training return: tensor(-211.9349, device='cuda:0')
episode: 285 training return: tensor(-3.4379, device='cuda:0')
episode: 286 training return: tensor(-309.4664, device='cuda:0')
episode: 287 training return: tensor(-177.3775, device='cuda:0')
epoch: 72 test_true_pfm: 1753.7445413479354 sim_pfm: -222.735749105302
episode: 288 training return: tensor(-458.2338, device='cuda:0')
episode: 289 training return: tensor(-461.5574, device='cuda:0')
episode: 290 training return: tensor(-178.2639, device='cuda:0')
episode: 291 training return: tensor(377.7220, device='cuda:0')
epoch: 73 test_true_pfm: 2522.2431290202744 sim_pfm: 411.63599298964255
episode: 292 training return: tensor(-299.8542, device='cuda:0')
episode: 293 training return: tensor(-408.2313, device='cuda:0')
episode: 294 training return: tensor(404.5175, device='cuda:0')
episode: 295 training return: tensor(-134.9127, device='cuda:0')
epoch: 74 test_true_pfm: 3292.8442349630136 sim_pfm: 400.3003718367545
episode: 296 training return: tensor(18.7954, device='cuda:0')
episode: 297 training return: tensor(-356.3443, device='cuda:0')
episode: 298 training return: tensor(-240.7304, device='cuda:0')
episode: 299 training return: tensor(-43.2049, device='cuda:0')
epoch: 75 test_true_pfm: 3293.762788233021 sim_pfm: 394.74162166086415
episode: 300 training return: tensor(-401.4900, device='cuda:0')
episode: 301 training return: tensor(-313.8479, device='cuda:0')
episode: 302 training return: tensor(3.0268, device='cuda:0')
episode: 303 training return: tensor(-174.3087, device='cuda:0')
epoch: 76 test_true_pfm: 3326.6071452846277 sim_pfm: 341.0626423534316
episode: 304 training return: tensor(-354.9801, device='cuda:0')
episode: 305 training return: tensor(-381.3587, device='cuda:0')
episode: 306 training return: tensor(-214.7971, device='cuda:0')
episode: 307 training return: tensor(-385.7517, device='cuda:0')
epoch: 77 test_true_pfm: 3316.1898275687586 sim_pfm: 412.7007923886413
episode: 308 training return: tensor(-402.1973, device='cuda:0')
episode: 309 training return: tensor(-68.0108, device='cuda:0')
episode: 310 training return: tensor(-302.7892, device='cuda:0')
episode: 311 training return: tensor(-365.3988, device='cuda:0')
epoch: 78 test_true_pfm: 3300.006844277453 sim_pfm: 403.38144390719634
episode: 312 training return: tensor(-30.6508, device='cuda:0')
episode: 313 training return: tensor(15.0992, device='cuda:0')
episode: 314 training return: tensor(-167.4772, device='cuda:0')
episode: 315 training return: tensor(86.5880, device='cuda:0')
epoch: 79 test_true_pfm: 3306.5504297682714 sim_pfm: 402.6056424033207
episode: 316 training return: tensor(170.4666, device='cuda:0')
episode: 317 training return: tensor(-391.6910, device='cuda:0')
episode: 318 training return: tensor(-187.4916, device='cuda:0')
episode: 319 training return: tensor(-383.4264, device='cuda:0')
epoch: 80 test_true_pfm: 3290.755645668769 sim_pfm: 405.9500344611685
episode: 320 training return: tensor(-233.2485, device='cuda:0')
episode: 321 training return: tensor(-219.3855, device='cuda:0')
episode: 322 training return: tensor(-340.5697, device='cuda:0')
episode: 323 training return: tensor(-286.2269, device='cuda:0')
epoch: 81 test_true_pfm: 3021.6724345923963 sim_pfm: 237.914029450311
episode: 324 training return: tensor(-239.1694, device='cuda:0')
episode: 325 training return: tensor(-389.5485, device='cuda:0')
episode: 326 training return: tensor(77.1317, device='cuda:0')
episode: 327 training return: tensor(-104.7508, device='cuda:0')
epoch: 82 test_true_pfm: 2527.2820577600482 sim_pfm: 107.59096740389941
episode: 328 training return: tensor(-360.6730, device='cuda:0')
episode: 329 training return: tensor(-202.4606, device='cuda:0')
episode: 330 training return: tensor(-274.6288, device='cuda:0')
episode: 331 training return: tensor(305.2863, device='cuda:0')
epoch: 83 test_true_pfm: 3240.1346840621136 sim_pfm: 402.81963187258225
episode: 332 training return: tensor(-442.0758, device='cuda:0')
episode: 333 training return: tensor(-329.4804, device='cuda:0')
episode: 334 training return: tensor(-81.6391, device='cuda:0')
episode: 335 training return: tensor(-398.9778, device='cuda:0')
epoch: 84 test_true_pfm: 3067.7689819617176 sim_pfm: 158.64455697701
episode: 336 training return: tensor(-379.4072, device='cuda:0')
episode: 337 training return: tensor(-379.4334, device='cuda:0')
episode: 338 training return: tensor(-120.3501, device='cuda:0')
episode: 339 training return: tensor(-275.4189, device='cuda:0')
epoch: 85 test_true_pfm: 3276.012180011659 sim_pfm: 402.4515131462831
episode: 340 training return: tensor(-297.6823, device='cuda:0')
episode: 341 training return: tensor(-392.0094, device='cuda:0')
episode: 342 training return: tensor(-188.7148, device='cuda:0')
episode: 343 training return: tensor(-108.7165, device='cuda:0')
epoch: 86 test_true_pfm: 2646.2090168873656 sim_pfm: 366.4289094298535
episode: 344 training return: tensor(-6.0099, device='cuda:0')
episode: 345 training return: tensor(-395.2378, device='cuda:0')
episode: 346 training return: tensor(-207.4330, device='cuda:0')
episode: 347 training return: tensor(-453.3300, device='cuda:0')
epoch: 87 test_true_pfm: 2431.315254459756 sim_pfm: 423.4519546283021
episode: 348 training return: tensor(-171.1910, device='cuda:0')
episode: 349 training return: tensor(-176.4429, device='cuda:0')
episode: 350 training return: tensor(-372.7826, device='cuda:0')
episode: 351 training return: tensor(-261.0562, device='cuda:0')
epoch: 88 test_true_pfm: 2892.485474162404 sim_pfm: 312.2108243239345
episode: 352 training return: tensor(-181.6761, device='cuda:0')
episode: 353 training return: tensor(-216.1615, device='cuda:0')
episode: 354 training return: tensor(-219.1878, device='cuda:0')
episode: 355 training return: tensor(-183.9480, device='cuda:0')
epoch: 89 test_true_pfm: 3051.361098801413 sim_pfm: 410.05498128800537
episode: 356 training return: tensor(-22.1496, device='cuda:0')
episode: 357 training return: tensor(-362.3889, device='cuda:0')
episode: 358 training return: tensor(-380.7563, device='cuda:0')
episode: 359 training return: tensor(-397.5160, device='cuda:0')
epoch: 90 test_true_pfm: 3067.7266530176876 sim_pfm: 412.5053446831589
episode: 360 training return: tensor(6.9798, device='cuda:0')
episode: 361 training return: tensor(-355.7325, device='cuda:0')
episode: 362 training return: tensor(-335.6552, device='cuda:0')
episode: 363 training return: tensor(-335.1030, device='cuda:0')
epoch: 91 test_true_pfm: 2736.348498769036 sim_pfm: 206.17607389751356
episode: 364 training return: tensor(-380.5496, device='cuda:0')
episode: 365 training return: tensor(-369.0056, device='cuda:0')
episode: 366 training return: tensor(-425.4174, device='cuda:0')
episode: 367 training return: tensor(-167.8214, device='cuda:0')
epoch: 92 test_true_pfm: 3300.8817599510216 sim_pfm: 406.28902992388856
episode: 368 training return: tensor(119.0387, device='cuda:0')
episode: 369 training return: tensor(-454.5174, device='cuda:0')
episode: 370 training return: tensor(-439.1432, device='cuda:0')
episode: 371 training return: tensor(-446.8747, device='cuda:0')
epoch: 93 test_true_pfm: 2806.890497627408 sim_pfm: 198.2761546143738
episode: 372 training return: tensor(-134.5310, device='cuda:0')
episode: 373 training return: tensor(-185.6071, device='cuda:0')
episode: 374 training return: tensor(-394.0840, device='cuda:0')
episode: 375 training return: tensor(-223.5966, device='cuda:0')
epoch: 94 test_true_pfm: 3012.373978390188 sim_pfm: 413.07112712513964
episode: 376 training return: tensor(-176.1583, device='cuda:0')
episode: 377 training return: tensor(-381.8133, device='cuda:0')
episode: 378 training return: tensor(-164.9618, device='cuda:0')
episode: 379 training return: tensor(-339.0540, device='cuda:0')
epoch: 95 test_true_pfm: 3086.705799430638 sim_pfm: 344.86592744740966
episode: 380 training return: tensor(-264.1341, device='cuda:0')
episode: 381 training return: tensor(-201.5980, device='cuda:0')
episode: 382 training return: tensor(-146.3523, device='cuda:0')
episode: 383 training return: tensor(-278.1117, device='cuda:0')
epoch: 96 test_true_pfm: 3063.6531292964773 sim_pfm: 426.371658060787
episode: 384 training return: tensor(-75.2515, device='cuda:0')
episode: 385 training return: tensor(-426.1213, device='cuda:0')
episode: 386 training return: tensor(-243.2651, device='cuda:0')
episode: 387 training return: tensor(-147.4324, device='cuda:0')
epoch: 97 test_true_pfm: 2414.319909358115 sim_pfm: 432.67598492698744
episode: 388 training return: tensor(-183.1278, device='cuda:0')
episode: 389 training return: tensor(-184.3603, device='cuda:0')
episode: 390 training return: tensor(-186.0679, device='cuda:0')
episode: 391 training return: tensor(-469.7488, device='cuda:0')
epoch: 98 test_true_pfm: 3305.8587259868186 sim_pfm: 405.3500339450159
episode: 392 training return: tensor(7.5488, device='cuda:0')
episode: 393 training return: tensor(-423.4026, device='cuda:0')
episode: 394 training return: tensor(5.5957, device='cuda:0')
episode: 395 training return: tensor(-374.5193, device='cuda:0')
epoch: 99 test_true_pfm: 2872.5898814650973 sim_pfm: 358.75414397753775
episode: 396 training return: tensor(-379.1555, device='cuda:0')
episode: 397 training return: tensor(-155.4142, device='cuda:0')
episode: 398 training return: tensor(62.9184, device='cuda:0')
episode: 399 training return: tensor(-284.1384, device='cuda:0')
epoch: 100 test_true_pfm: 2823.0424631794244 sim_pfm: 405.8625074150429
episode: 400 training return: tensor(-79.1998, device='cuda:0')
episode: 401 training return: tensor(-44.1989, device='cuda:0')
episode: 402 training return: tensor(-204.0037, device='cuda:0')
episode: 403 training return: tensor(-162.8861, device='cuda:0')
epoch: 101 test_true_pfm: 2857.368012723229 sim_pfm: 268.03558065447334
episode: 404 training return: tensor(-202.4280, device='cuda:0')
episode: 405 training return: tensor(-374.5358, device='cuda:0')
episode: 406 training return: tensor(-140.7807, device='cuda:0')
episode: 407 training return: tensor(-182.6361, device='cuda:0')
epoch: 102 test_true_pfm: 2991.1996224531467 sim_pfm: 414.31553341428906
episode: 408 training return: tensor(66.9081, device='cuda:0')
episode: 409 training return: tensor(420.6046, device='cuda:0')
episode: 410 training return: tensor(-434.0678, device='cuda:0')
episode: 411 training return: tensor(-367.1371, device='cuda:0')
epoch: 103 test_true_pfm: 3017.377967043189 sim_pfm: 291.9888690235869
episode: 412 training return: tensor(270.8940, device='cuda:0')
episode: 413 training return: tensor(-257.4979, device='cuda:0')
episode: 414 training return: tensor(-190.5464, device='cuda:0')
episode: 415 training return: tensor(22.8103, device='cuda:0')
epoch: 104 test_true_pfm: 2644.2547109183647 sim_pfm: 424.31906793515856
episode: 416 training return: tensor(-267.7260, device='cuda:0')
episode: 417 training return: tensor(-360.0749, device='cuda:0')
episode: 418 training return: tensor(-224.8880, device='cuda:0')
episode: 419 training return: tensor(-403.7237, device='cuda:0')
epoch: 105 test_true_pfm: 2992.338535975024 sim_pfm: 425.9138365924882
episode: 420 training return: tensor(418.6384, device='cuda:0')
episode: 421 training return: tensor(-380.1886, device='cuda:0')
episode: 422 training return: tensor(-333.0257, device='cuda:0')
episode: 423 training return: tensor(-287.8571, device='cuda:0')
epoch: 106 test_true_pfm: 2965.894352164392 sim_pfm: 419.8137519286635
episode: 424 training return: tensor(-219.3577, device='cuda:0')
episode: 425 training return: tensor(-309.5623, device='cuda:0')
episode: 426 training return: tensor(-168.0529, device='cuda:0')
episode: 427 training return: tensor(-345.3140, device='cuda:0')
epoch: 107 test_true_pfm: 2640.442610524424 sim_pfm: 107.78053470545758
episode: 428 training return: tensor(-417.1250, device='cuda:0')
episode: 429 training return: tensor(-96.0775, device='cuda:0')
episode: 430 training return: tensor(97.1603, device='cuda:0')
episode: 431 training return: tensor(21.3999, device='cuda:0')
epoch: 108 test_true_pfm: 2978.2331525827417 sim_pfm: -50.79473384593924
episode: 432 training return: tensor(-122.9197, device='cuda:0')
episode: 433 training return: tensor(-109.5410, device='cuda:0')
episode: 434 training return: tensor(-11.5773, device='cuda:0')
episode: 435 training return: tensor(-81.3449, device='cuda:0')
epoch: 109 test_true_pfm: 3260.7451469080465 sim_pfm: 401.59916612226516
episode: 436 training return: tensor(-419.5987, device='cuda:0')
episode: 437 training return: tensor(-378.2772, device='cuda:0')
episode: 438 training return: tensor(109.4170, device='cuda:0')
episode: 439 training return: tensor(-399.2091, device='cuda:0')
epoch: 110 test_true_pfm: 3334.5538121047225 sim_pfm: 391.46982859789085
episode: 440 training return: tensor(365.6099, device='cuda:0')
episode: 441 training return: tensor(-444.7595, device='cuda:0')
episode: 442 training return: tensor(-417.0924, device='cuda:0')
episode: 443 training return: tensor(-423.1096, device='cuda:0')
epoch: 111 test_true_pfm: 3311.8893751203536 sim_pfm: 408.50951791570213
episode: 444 training return: tensor(14.5632, device='cuda:0')
episode: 445 training return: tensor(-409.4367, device='cuda:0')
episode: 446 training return: tensor(-371.2355, device='cuda:0')
episode: 447 training return: tensor(-352.1170, device='cuda:0')
epoch: 112 test_true_pfm: 2144.604832764544 sim_pfm: 285.31498436664697
episode: 448 training return: tensor(-330.5169, device='cuda:0')
episode: 449 training return: tensor(441.3582, device='cuda:0')
episode: 450 training return: tensor(-299.1480, device='cuda:0')
episode: 451 training return: tensor(-222.4581, device='cuda:0')
epoch: 113 test_true_pfm: 3278.3209414147163 sim_pfm: 239.23909511355063
episode: 452 training return: tensor(21.2224, device='cuda:0')
episode: 453 training return: tensor(-291.9954, device='cuda:0')
episode: 454 training return: tensor(172.5476, device='cuda:0')
episode: 455 training return: tensor(-291.3767, device='cuda:0')
epoch: 114 test_true_pfm: 2715.800939713259 sim_pfm: 41.31004806701094
episode: 456 training return: tensor(-307.4211, device='cuda:0')
episode: 457 training return: tensor(-398.7996, device='cuda:0')
episode: 458 training return: tensor(-384.8990, device='cuda:0')
episode: 459 training return: tensor(-302.1235, device='cuda:0')
epoch: 115 test_true_pfm: 3318.3898562976415 sim_pfm: 426.7378508512629
episode: 460 training return: tensor(-497.3825, device='cuda:0')
episode: 461 training return: tensor(-397.5844, device='cuda:0')
episode: 462 training return: tensor(-385.0442, device='cuda:0')
episode: 463 training return: tensor(-416.3243, device='cuda:0')
epoch: 116 test_true_pfm: 3332.1646333442077 sim_pfm: 415.4312972158659
episode: 464 training return: tensor(-387.7397, device='cuda:0')
episode: 465 training return: tensor(-382.3044, device='cuda:0')
episode: 466 training return: tensor(-364.2479, device='cuda:0')
episode: 467 training return: tensor(-374.2662, device='cuda:0')
epoch: 117 test_true_pfm: 2563.5754360005853 sim_pfm: 432.7730672213559
episode: 468 training return: tensor(-306.4832, device='cuda:0')
episode: 469 training return: tensor(-322.4688, device='cuda:0')
episode: 470 training return: tensor(-103.3352, device='cuda:0')
episode: 471 training return: tensor(-11.4973, device='cuda:0')
epoch: 118 test_true_pfm: 3018.7419660285127 sim_pfm: 397.9947607278203
episode: 472 training return: tensor(-327.9749, device='cuda:0')
episode: 473 training return: tensor(-273.5763, device='cuda:0')
episode: 474 training return: tensor(9.5388, device='cuda:0')
episode: 475 training return: tensor(-405.1024, device='cuda:0')
epoch: 119 test_true_pfm: 3315.5724019235054 sim_pfm: 413.85733158665244
episode: 476 training return: tensor(-381.1262, device='cuda:0')
episode: 477 training return: tensor(-394.0268, device='cuda:0')
episode: 478 training return: tensor(-177.6139, device='cuda:0')
episode: 479 training return: tensor(418.0299, device='cuda:0')
epoch: 120 test_true_pfm: 3301.438679494878 sim_pfm: 269.98518192449893
episode: 480 training return: tensor(-404.6179, device='cuda:0')
episode: 481 training return: tensor(422.0067, device='cuda:0')
episode: 482 training return: tensor(-408.8264, device='cuda:0')
episode: 483 training return: tensor(-226.2559, device='cuda:0')
epoch: 121 test_true_pfm: 3323.985423627011 sim_pfm: 409.25136061257217
episode: 484 training return: tensor(-386.0006, device='cuda:0')
episode: 485 training return: tensor(-165.5820, device='cuda:0')
episode: 486 training return: tensor(-172.6049, device='cuda:0')
episode: 487 training return: tensor(-404.4061, device='cuda:0')
epoch: 122 test_true_pfm: 3316.4486964519087 sim_pfm: 406.4005972458787
episode: 488 training return: tensor(-206.8478, device='cuda:0')
episode: 489 training return: tensor(-188.2032, device='cuda:0')
episode: 490 training return: tensor(-164.2141, device='cuda:0')
episode: 491 training return: tensor(-104.4064, device='cuda:0')
epoch: 123 test_true_pfm: 2565.4694267906198 sim_pfm: 222.91147152986377
episode: 492 training return: tensor(-21.9147, device='cuda:0')
episode: 493 training return: tensor(-197.3954, device='cuda:0')
episode: 494 training return: tensor(-234.6065, device='cuda:0')
episode: 495 training return: tensor(-377.0145, device='cuda:0')
epoch: 124 test_true_pfm: 2071.1238647085825 sim_pfm: -314.3218044428698
episode: 496 training return: tensor(-407.7741, device='cuda:0')
episode: 497 training return: tensor(-396.6922, device='cuda:0')
episode: 498 training return: tensor(-383.4968, device='cuda:0')
episode: 499 training return: tensor(-385.1081, device='cuda:0')
epoch: 125 test_true_pfm: 3048.420903407007 sim_pfm: 248.70523627866837
episode: 500 training return: tensor(-319.9819, device='cuda:0')
episode: 501 training return: tensor(-187.6500, device='cuda:0')
episode: 502 training return: tensor(-67.8525, device='cuda:0')
episode: 503 training return: tensor(-389.5031, device='cuda:0')
epoch: 126 test_true_pfm: 3308.8879153860184 sim_pfm: 380.2289281085444
episode: 504 training return: tensor(-330.7982, device='cuda:0')
episode: 505 training return: tensor(-403.2155, device='cuda:0')
episode: 506 training return: tensor(-465.2188, device='cuda:0')
episode: 507 training return: tensor(-411.3183, device='cuda:0')
epoch: 127 test_true_pfm: 2987.5262279714093 sim_pfm: 347.3990578984764
episode: 508 training return: tensor(-269.0671, device='cuda:0')
episode: 509 training return: tensor(-176.4423, device='cuda:0')
episode: 510 training return: tensor(-214.7265, device='cuda:0')
episode: 511 training return: tensor(-344.8432, device='cuda:0')
epoch: 128 test_true_pfm: 2810.5483936078476 sim_pfm: 269.6507266028396
episode: 512 training return: tensor(-209.3086, device='cuda:0')
episode: 513 training return: tensor(-402.9113, device='cuda:0')
episode: 514 training return: tensor(-455.3982, device='cuda:0')
episode: 515 training return: tensor(-310.9790, device='cuda:0')
epoch: 129 test_true_pfm: 2463.2934589736633 sim_pfm: 409.3051241339126
episode: 516 training return: tensor(404.9496, device='cuda:0')
episode: 517 training return: tensor(-350.8839, device='cuda:0')
episode: 518 training return: tensor(-439.2126, device='cuda:0')
episode: 519 training return: tensor(-380.4948, device='cuda:0')
epoch: 130 test_true_pfm: 3313.221473390755 sim_pfm: 407.82257106291945
episode: 520 training return: tensor(-326.4213, device='cuda:0')
episode: 521 training return: tensor(-267.2247, device='cuda:0')
episode: 522 training return: tensor(-287.8557, device='cuda:0')
episode: 523 training return: tensor(-365.1466, device='cuda:0')
epoch: 131 test_true_pfm: 2914.210983904904 sim_pfm: 217.36413369094953
episode: 524 training return: tensor(-395.5681, device='cuda:0')
episode: 525 training return: tensor(-420.4160, device='cuda:0')
episode: 526 training return: tensor(-400.5258, device='cuda:0')
episode: 527 training return: tensor(-298.0867, device='cuda:0')
epoch: 132 test_true_pfm: 2633.3974145355037 sim_pfm: 428.7051266757674
episode: 528 training return: tensor(-372.8917, device='cuda:0')
episode: 529 training return: tensor(-347.9162, device='cuda:0')
episode: 530 training return: tensor(-387.0674, device='cuda:0')
episode: 531 training return: tensor(-301.4883, device='cuda:0')
epoch: 133 test_true_pfm: 1165.0239229713347 sim_pfm: -360.6940854168497
episode: 532 training return: tensor(-368.5305, device='cuda:0')
episode: 533 training return: tensor(-403.2805, device='cuda:0')
episode: 534 training return: tensor(-307.5498, device='cuda:0')
episode: 535 training return: tensor(-329.4892, device='cuda:0')
epoch: 134 test_true_pfm: 3330.5418666278965 sim_pfm: 320.56694713137887
episode: 536 training return: tensor(-163.6328, device='cuda:0')
episode: 537 training return: tensor(-421.2852, device='cuda:0')
episode: 538 training return: tensor(-376.5892, device='cuda:0')
episode: 539 training return: tensor(-420.5126, device='cuda:0')
epoch: 135 test_true_pfm: 3058.781758086145 sim_pfm: 422.27086940966547
episode: 540 training return: tensor(-369.0423, device='cuda:0')
episode: 541 training return: tensor(-392.6053, device='cuda:0')
episode: 542 training return: tensor(-429.7683, device='cuda:0')
episode: 543 training return: tensor(-398.0736, device='cuda:0')
epoch: 136 test_true_pfm: 2483.0779920921455 sim_pfm: 253.95527747878805
episode: 544 training return: tensor(-327.5550, device='cuda:0')
episode: 545 training return: tensor(-366.0991, device='cuda:0')
episode: 546 training return: tensor(-369.9901, device='cuda:0')
episode: 547 training return: tensor(-351.0916, device='cuda:0')
epoch: 137 test_true_pfm: 2049.083939801455 sim_pfm: -321.08502056092647
episode: 548 training return: tensor(-406.7130, device='cuda:0')
episode: 549 training return: tensor(-279.4442, device='cuda:0')
episode: 550 training return: tensor(-235.5914, device='cuda:0')
episode: 551 training return: tensor(-384.0636, device='cuda:0')
epoch: 138 test_true_pfm: 1540.7231969377697 sim_pfm: -214.19946071878076
episode: 552 training return: tensor(-401.7160, device='cuda:0')
episode: 553 training return: tensor(-412.6641, device='cuda:0')
episode: 554 training return: tensor(-257.0543, device='cuda:0')
episode: 555 training return: tensor(-364.7462, device='cuda:0')
epoch: 139 test_true_pfm: 2688.0511737428537 sim_pfm: 81.25389767531306
episode: 556 training return: tensor(-453.8131, device='cuda:0')
episode: 557 training return: tensor(-348.8972, device='cuda:0')
episode: 558 training return: tensor(-390.4585, device='cuda:0')
episode: 559 training return: tensor(-413.9917, device='cuda:0')
epoch: 140 test_true_pfm: 3345.4121055277633 sim_pfm: 419.88638302901137
episode: 560 training return: tensor(-372.7969, device='cuda:0')
episode: 561 training return: tensor(-387.2165, device='cuda:0')
episode: 562 training return: tensor(-393.2684, device='cuda:0')
episode: 563 training return: tensor(-175.1189, device='cuda:0')
epoch: 141 test_true_pfm: 2658.00986881228 sim_pfm: 415.84585812517133
episode: 564 training return: tensor(-384.0452, device='cuda:0')
episode: 565 training return: tensor(-264.4565, device='cuda:0')
episode: 566 training return: tensor(-420.0658, device='cuda:0')
episode: 567 training return: tensor(-234.1095, device='cuda:0')
epoch: 142 test_true_pfm: 2976.34084277247 sim_pfm: 398.60854648549383
episode: 568 training return: tensor(-344.2682, device='cuda:0')
episode: 569 training return: tensor(-323.2464, device='cuda:0')
episode: 570 training return: tensor(-422.4791, device='cuda:0')
episode: 571 training return: tensor(-381.5867, device='cuda:0')
epoch: 143 test_true_pfm: 2263.814532735279 sim_pfm: 185.7491183419091
episode: 572 training return: tensor(-420.7310, device='cuda:0')
episode: 573 training return: tensor(-396.7057, device='cuda:0')
episode: 574 training return: tensor(-279.3761, device='cuda:0')
episode: 575 training return: tensor(-357.7637, device='cuda:0')
epoch: 144 test_true_pfm: 3317.9634317152377 sim_pfm: 367.3821673883746
episode: 576 training return: tensor(-440.8342, device='cuda:0')
episode: 577 training return: tensor(-276.3953, device='cuda:0')
episode: 578 training return: tensor(-330.1727, device='cuda:0')
episode: 579 training return: tensor(-396.3968, device='cuda:0')
epoch: 145 test_true_pfm: 2788.323001236991 sim_pfm: 362.42612760983565
episode: 580 training return: tensor(-278.7175, device='cuda:0')
episode: 581 training return: tensor(-186.6571, device='cuda:0')
episode: 582 training return: tensor(-341.5780, device='cuda:0')
episode: 583 training return: tensor(-397.1804, device='cuda:0')
epoch: 146 test_true_pfm: 3315.719488488572 sim_pfm: 408.24640563953045
episode: 584 training return: tensor(-415.1666, device='cuda:0')
episode: 585 training return: tensor(-394.2157, device='cuda:0')
episode: 586 training return: tensor(-117.3877, device='cuda:0')
episode: 587 training return: tensor(-389.0009, device='cuda:0')
epoch: 147 test_true_pfm: 1179.2735371628617 sim_pfm: -392.29096488691476
episode: 588 training return: tensor(-357.9327, device='cuda:0')
episode: 589 training return: tensor(-408.1448, device='cuda:0')
episode: 590 training return: tensor(-408.0886, device='cuda:0')
episode: 591 training return: tensor(-354.6353, device='cuda:0')
epoch: 148 test_true_pfm: 2023.8342259547026 sim_pfm: 191.01754807902034
episode: 592 training return: tensor(-328.3394, device='cuda:0')
episode: 593 training return: tensor(-410.9152, device='cuda:0')
episode: 594 training return: tensor(389.1429, device='cuda:0')
episode: 595 training return: tensor(-434.1616, device='cuda:0')
epoch: 149 test_true_pfm: 2084.1713641041215 sim_pfm: -297.14212092376937
episode: 596 training return: tensor(-386.0458, device='cuda:0')
episode: 597 training return: tensor(-372.0735, device='cuda:0')
episode: 598 training return: tensor(-402.4902, device='cuda:0')
episode: 599 training return: tensor(-392.4705, device='cuda:0')
epoch: 150 test_true_pfm: 1238.8254373811428 sim_pfm: -353.9907878905069
