['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '4']
episode: 0 training return: tensor(-541.6235, device='cuda:0')
episode: 1 training return: tensor(-619.0460, device='cuda:0')
episode: 2 training return: tensor(-368.8610, device='cuda:0')
episode: 3 training return: tensor(-435.4135, device='cuda:0')
epoch: 1 test_true_pfm: 222.00450210536624 sim_pfm: -458.0497244398478
episode: 4 training return: tensor(-667.4684, device='cuda:0')
episode: 5 training return: tensor(-611.7503, device='cuda:0')
episode: 6 training return: tensor(-408.1973, device='cuda:0')
episode: 7 training return: tensor(-640.2177, device='cuda:0')
epoch: 2 test_true_pfm: -196.6413596861099 sim_pfm: -556.7972951940222
episode: 8 training return: tensor(-345.6989, device='cuda:0')
episode: 9 training return: tensor(-385.6597, device='cuda:0')
episode: 10 training return: tensor(-716.2604, device='cuda:0')
episode: 11 training return: tensor(-385.7639, device='cuda:0')
epoch: 3 test_true_pfm: 138.4308376030468 sim_pfm: -437.07264886931324
episode: 12 training return: tensor(-302.9248, device='cuda:0')
episode: 13 training return: tensor(-631.0910, device='cuda:0')
episode: 14 training return: tensor(-301.4254, device='cuda:0')
episode: 15 training return: tensor(-600.4123, device='cuda:0')
epoch: 4 test_true_pfm: -307.445192828455 sim_pfm: -601.4660182242515
episode: 16 training return: tensor(-593.2252, device='cuda:0')
episode: 17 training return: tensor(-598.8303, device='cuda:0')
episode: 18 training return: tensor(-326.2775, device='cuda:0')
episode: 19 training return: tensor(-357.7610, device='cuda:0')
epoch: 5 test_true_pfm: 112.72329035593044 sim_pfm: -612.008419106404
episode: 20 training return: tensor(-628.5093, device='cuda:0')
episode: 21 training return: tensor(-442.1064, device='cuda:0')
episode: 22 training return: tensor(-552.5200, device='cuda:0')
episode: 23 training return: tensor(-401.0880, device='cuda:0')
epoch: 6 test_true_pfm: 118.21122801406227 sim_pfm: -209.4840644757302
episode: 24 training return: tensor(-542.4822, device='cuda:0')
episode: 25 training return: tensor(-438.8922, device='cuda:0')
episode: 26 training return: tensor(-657.4036, device='cuda:0')
episode: 27 training return: tensor(-546.5807, device='cuda:0')
epoch: 7 test_true_pfm: 326.85388757879156 sim_pfm: -447.80385573774885
episode: 28 training return: tensor(-699.3330, device='cuda:0')
episode: 29 training return: tensor(-720.8394, device='cuda:0')
episode: 30 training return: tensor(-738.3976, device='cuda:0')
episode: 31 training return: tensor(-696.2927, device='cuda:0')
epoch: 8 test_true_pfm: 136.20722243656357 sim_pfm: -718.1833642758429
episode: 32 training return: tensor(-714.3303, device='cuda:0')
episode: 33 training return: tensor(-385.7333, device='cuda:0')
episode: 34 training return: tensor(-689.3636, device='cuda:0')
episode: 35 training return: tensor(-615.5118, device='cuda:0')
epoch: 9 test_true_pfm: 24.449108389431306 sim_pfm: -280.3647160202575
episode: 36 training return: tensor(-335.2442, device='cuda:0')
episode: 37 training return: tensor(-719.9949, device='cuda:0')
episode: 38 training return: tensor(-725.7639, device='cuda:0')
episode: 39 training return: tensor(-714.7451, device='cuda:0')
epoch: 10 test_true_pfm: 140.5844646226379 sim_pfm: -718.9600466957005
episode: 40 training return: tensor(-738.4633, device='cuda:0')
episode: 41 training return: tensor(-706.7383, device='cuda:0')
episode: 42 training return: tensor(-712.2497, device='cuda:0')
episode: 43 training return: tensor(-726.3218, device='cuda:0')
epoch: 11 test_true_pfm: 151.04289341296322 sim_pfm: -719.6476684094523
episode: 44 training return: tensor(-698.4359, device='cuda:0')
episode: 45 training return: tensor(-347.3165, device='cuda:0')
episode: 46 training return: tensor(-728.3550, device='cuda:0')
episode: 47 training return: tensor(-714.6556, device='cuda:0')
epoch: 12 test_true_pfm: 152.53307171771897 sim_pfm: -686.5319381890198
episode: 48 training return: tensor(-319.8037, device='cuda:0')
episode: 49 training return: tensor(-706.2000, device='cuda:0')
episode: 50 training return: tensor(-745.0446, device='cuda:0')
episode: 51 training return: tensor(-679.6237, device='cuda:0')
epoch: 13 test_true_pfm: 133.97019782637904 sim_pfm: -670.5797477729502
episode: 52 training return: tensor(-628.3152, device='cuda:0')
episode: 53 training return: tensor(-617.3301, device='cuda:0')
episode: 54 training return: tensor(-628.8386, device='cuda:0')
episode: 55 training return: tensor(-636.1872, device='cuda:0')
epoch: 14 test_true_pfm: 165.40390747331867 sim_pfm: -607.4619457060859
episode: 56 training return: tensor(-630.3788, device='cuda:0')
episode: 57 training return: tensor(-620.7073, device='cuda:0')
episode: 58 training return: tensor(-624.5552, device='cuda:0')
episode: 59 training return: tensor(-647.0671, device='cuda:0')
epoch: 15 test_true_pfm: 121.25368014538975 sim_pfm: -606.0395391628845
episode: 60 training return: tensor(-635.0162, device='cuda:0')
episode: 61 training return: tensor(-628.6810, device='cuda:0')
episode: 62 training return: tensor(-613.9598, device='cuda:0')
episode: 63 training return: tensor(-617.2859, device='cuda:0')
epoch: 16 test_true_pfm: 131.84749746748392 sim_pfm: -598.9343434110439
episode: 64 training return: tensor(-592.3362, device='cuda:0')
episode: 65 training return: tensor(-603.9493, device='cuda:0')
episode: 66 training return: tensor(-602.8425, device='cuda:0')
episode: 67 training return: tensor(-576.0566, device='cuda:0')
epoch: 17 test_true_pfm: 139.06674831443593 sim_pfm: -597.410615372782
episode: 68 training return: tensor(-572.3569, device='cuda:0')
episode: 69 training return: tensor(-604.8488, device='cuda:0')
episode: 70 training return: tensor(-584.8291, device='cuda:0')
episode: 71 training return: tensor(-565.8746, device='cuda:0')
epoch: 18 test_true_pfm: 123.5102017614302 sim_pfm: -605.4268645308912
episode: 72 training return: tensor(-591.5212, device='cuda:0')
episode: 73 training return: tensor(-523.8552, device='cuda:0')
episode: 74 training return: tensor(-536.8500, device='cuda:0')
episode: 75 training return: tensor(-523.3143, device='cuda:0')
epoch: 19 test_true_pfm: 152.17982939176764 sim_pfm: -598.9122684883574
episode: 76 training return: tensor(-510.6427, device='cuda:0')
episode: 77 training return: tensor(-495.9059, device='cuda:0')
episode: 78 training return: tensor(-437.8925, device='cuda:0')
episode: 79 training return: tensor(-429.5435, device='cuda:0')
epoch: 20 test_true_pfm: 149.3277790599622 sim_pfm: -604.1672631942978
episode: 80 training return: tensor(-412.9359, device='cuda:0')
episode: 81 training return: tensor(-415.4533, device='cuda:0')
episode: 82 training return: tensor(-399.4260, device='cuda:0')
episode: 83 training return: tensor(-449.4409, device='cuda:0')
epoch: 21 test_true_pfm: 45.60279146284541 sim_pfm: -387.36981091469835
episode: 84 training return: tensor(-466.6640, device='cuda:0')
episode: 85 training return: tensor(-398.4729, device='cuda:0')
episode: 86 training return: tensor(-426.9247, device='cuda:0')
episode: 87 training return: tensor(-462.9774, device='cuda:0')
epoch: 22 test_true_pfm: 150.60342775548506 sim_pfm: -509.75187029029865
episode: 88 training return: tensor(-423.9106, device='cuda:0')
episode: 89 training return: tensor(-389.5030, device='cuda:0')
episode: 90 training return: tensor(-373.1228, device='cuda:0')
episode: 91 training return: tensor(-403.4684, device='cuda:0')
epoch: 23 test_true_pfm: 35.46509634242221 sim_pfm: -380.90857506690855
episode: 92 training return: tensor(-394.7267, device='cuda:0')
episode: 93 training return: tensor(-422.1380, device='cuda:0')
episode: 94 training return: tensor(-418.5565, device='cuda:0')
episode: 95 training return: tensor(-430.4624, device='cuda:0')
epoch: 24 test_true_pfm: 319.6316663792771 sim_pfm: -375.0203992926399
episode: 96 training return: tensor(-421.4966, device='cuda:0')
episode: 97 training return: tensor(-384.2683, device='cuda:0')
episode: 98 training return: tensor(-387.5453, device='cuda:0')
episode: 99 training return: tensor(-401.5008, device='cuda:0')
epoch: 25 test_true_pfm: 195.55551263347806 sim_pfm: -362.0511718033037
episode: 100 training return: tensor(-374.3597, device='cuda:0')
episode: 101 training return: tensor(-350.2693, device='cuda:0')
episode: 102 training return: tensor(-399.5947, device='cuda:0')
episode: 103 training return: tensor(-370.5695, device='cuda:0')
epoch: 26 test_true_pfm: 415.3080285962241 sim_pfm: -330.82393897503306
episode: 104 training return: tensor(-377.1469, device='cuda:0')
episode: 105 training return: tensor(-335.2050, device='cuda:0')
episode: 106 training return: tensor(-437.2556, device='cuda:0')
episode: 107 training return: tensor(-375.1909, device='cuda:0')
epoch: 27 test_true_pfm: 67.93234370600868 sim_pfm: -320.0676245976938
episode: 108 training return: tensor(-371.6334, device='cuda:0')
episode: 109 training return: tensor(-366.0185, device='cuda:0')
episode: 110 training return: tensor(-382.0044, device='cuda:0')
episode: 111 training return: tensor(-342.5553, device='cuda:0')
epoch: 28 test_true_pfm: 453.4398988246826 sim_pfm: -289.1225569631594
episode: 112 training return: tensor(-361.1085, device='cuda:0')
episode: 113 training return: tensor(-290.7003, device='cuda:0')
episode: 114 training return: tensor(-335.9481, device='cuda:0')
episode: 115 training return: tensor(-322.1458, device='cuda:0')
epoch: 29 test_true_pfm: 228.598055041653 sim_pfm: -305.43633924257784
episode: 116 training return: tensor(-372.8930, device='cuda:0')
episode: 117 training return: tensor(-377.5451, device='cuda:0')
episode: 118 training return: tensor(-372.9203, device='cuda:0')
episode: 119 training return: tensor(-349.5230, device='cuda:0')
epoch: 30 test_true_pfm: 318.555075327693 sim_pfm: -333.9361132097062
episode: 120 training return: tensor(-385.5770, device='cuda:0')
episode: 121 training return: tensor(-372.9616, device='cuda:0')
episode: 122 training return: tensor(-391.0040, device='cuda:0')
episode: 123 training return: tensor(-363.2568, device='cuda:0')
epoch: 31 test_true_pfm: 300.67594647922846 sim_pfm: -335.0999578734239
episode: 124 training return: tensor(-361.4345, device='cuda:0')
episode: 125 training return: tensor(-392.7307, device='cuda:0')
episode: 126 training return: tensor(-350.5014, device='cuda:0')
episode: 127 training return: tensor(-362.6843, device='cuda:0')
epoch: 32 test_true_pfm: 385.6562998363445 sim_pfm: -295.2557216421895
episode: 128 training return: tensor(-368.2286, device='cuda:0')
episode: 129 training return: tensor(-359.7471, device='cuda:0')
episode: 130 training return: tensor(-335.2303, device='cuda:0')
episode: 131 training return: tensor(-307.7899, device='cuda:0')
epoch: 33 test_true_pfm: 343.6167577207206 sim_pfm: -288.3371647803967
episode: 132 training return: tensor(-351.3806, device='cuda:0')
episode: 133 training return: tensor(-362.1422, device='cuda:0')
episode: 134 training return: tensor(-348.0960, device='cuda:0')
episode: 135 training return: tensor(-351.3585, device='cuda:0')
epoch: 34 test_true_pfm: 426.27909445148447 sim_pfm: -321.41221859829966
episode: 136 training return: tensor(-356.0572, device='cuda:0')
episode: 137 training return: tensor(-320.2635, device='cuda:0')
episode: 138 training return: tensor(-379.2339, device='cuda:0')
episode: 139 training return: tensor(-354.0429, device='cuda:0')
epoch: 35 test_true_pfm: 378.02491552931656 sim_pfm: -311.96694030584575
episode: 140 training return: tensor(-384.1489, device='cuda:0')
episode: 141 training return: tensor(-346.2233, device='cuda:0')
episode: 142 training return: tensor(-351.9279, device='cuda:0')
episode: 143 training return: tensor(-322.1748, device='cuda:0')
epoch: 36 test_true_pfm: 474.9551403440323 sim_pfm: -289.106617906257
episode: 144 training return: tensor(-334.9836, device='cuda:0')
episode: 145 training return: tensor(-344.8232, device='cuda:0')
episode: 146 training return: tensor(-363.9343, device='cuda:0')
episode: 147 training return: tensor(-362.7438, device='cuda:0')
epoch: 37 test_true_pfm: 429.3820544173844 sim_pfm: -286.89844543089083
episode: 148 training return: tensor(-327.9804, device='cuda:0')
episode: 149 training return: tensor(-333.2991, device='cuda:0')
episode: 150 training return: tensor(-372.7585, device='cuda:0')
episode: 151 training return: tensor(-311.2255, device='cuda:0')
epoch: 38 test_true_pfm: 353.59989014552775 sim_pfm: -310.90623782399535
episode: 152 training return: tensor(-345.5610, device='cuda:0')
episode: 153 training return: tensor(-343.0199, device='cuda:0')
episode: 154 training return: tensor(-349.2144, device='cuda:0')
episode: 155 training return: tensor(-335.4299, device='cuda:0')
epoch: 39 test_true_pfm: 491.9500750035316 sim_pfm: -301.0829740782113
episode: 156 training return: tensor(-308.9464, device='cuda:0')
episode: 157 training return: tensor(-324.2820, device='cuda:0')
episode: 158 training return: tensor(-334.3830, device='cuda:0')
episode: 159 training return: tensor(-369.4381, device='cuda:0')
epoch: 40 test_true_pfm: 339.0540030213861 sim_pfm: -318.63415519404225
episode: 160 training return: tensor(-212.4037, device='cuda:0')
episode: 161 training return: tensor(-345.7068, device='cuda:0')
episode: 162 training return: tensor(-335.6874, device='cuda:0')
episode: 163 training return: tensor(-349.2261, device='cuda:0')
epoch: 41 test_true_pfm: 298.42800334376324 sim_pfm: -308.9747457556853
episode: 164 training return: tensor(-303.2279, device='cuda:0')
episode: 165 training return: tensor(-292.4532, device='cuda:0')
episode: 166 training return: tensor(-326.3295, device='cuda:0')
episode: 167 training return: tensor(-296.5605, device='cuda:0')
epoch: 42 test_true_pfm: 174.74242076893722 sim_pfm: -333.8929605926387
episode: 168 training return: tensor(-340.6109, device='cuda:0')
episode: 169 training return: tensor(-353.1572, device='cuda:0')
episode: 170 training return: tensor(-345.0172, device='cuda:0')
episode: 171 training return: tensor(-373.0700, device='cuda:0')
epoch: 43 test_true_pfm: 355.5155452685569 sim_pfm: -310.9741433494103
episode: 172 training return: tensor(-365.8946, device='cuda:0')
episode: 173 training return: tensor(-321.2681, device='cuda:0')
episode: 174 training return: tensor(-329.6170, device='cuda:0')
episode: 175 training return: tensor(-336.7139, device='cuda:0')
epoch: 44 test_true_pfm: 260.17602002266966 sim_pfm: -307.50746959698154
episode: 176 training return: tensor(-335.3965, device='cuda:0')
episode: 177 training return: tensor(-345.8869, device='cuda:0')
episode: 178 training return: tensor(-306.2431, device='cuda:0')
episode: 179 training return: tensor(-342.0694, device='cuda:0')
epoch: 45 test_true_pfm: 138.41463849239213 sim_pfm: -332.3369497662837
episode: 180 training return: tensor(-343.1980, device='cuda:0')
episode: 181 training return: tensor(-333.5604, device='cuda:0')
episode: 182 training return: tensor(-354.1580, device='cuda:0')
episode: 183 training return: tensor(-337.8083, device='cuda:0')
epoch: 46 test_true_pfm: 177.29840814738154 sim_pfm: -336.4405218049651
episode: 184 training return: tensor(-367.6317, device='cuda:0')
episode: 185 training return: tensor(-322.6080, device='cuda:0')
episode: 186 training return: tensor(-328.8861, device='cuda:0')
episode: 187 training return: tensor(-311.2870, device='cuda:0')
epoch: 47 test_true_pfm: 167.8448872392351 sim_pfm: -306.695792694188
episode: 188 training return: tensor(-330.2660, device='cuda:0')
episode: 189 training return: tensor(-344.0290, device='cuda:0')
episode: 190 training return: tensor(-328.4433, device='cuda:0')
episode: 191 training return: tensor(-332.0080, device='cuda:0')
epoch: 48 test_true_pfm: 222.3305921311561 sim_pfm: -300.9934086134308
episode: 192 training return: tensor(-339.4526, device='cuda:0')
episode: 193 training return: tensor(-325.5365, device='cuda:0')
episode: 194 training return: tensor(-329.4640, device='cuda:0')
episode: 195 training return: tensor(-495.1983, device='cuda:0')
epoch: 49 test_true_pfm: 415.7250666136093 sim_pfm: -323.27307040629483
episode: 196 training return: tensor(-317.6701, device='cuda:0')
episode: 197 training return: tensor(-329.7339, device='cuda:0')
episode: 198 training return: tensor(-339.2662, device='cuda:0')
episode: 199 training return: tensor(-321.3792, device='cuda:0')
epoch: 50 test_true_pfm: 327.93389608054105 sim_pfm: -303.6240408652714
episode: 200 training return: tensor(-300.4588, device='cuda:0')
episode: 201 training return: tensor(-336.8474, device='cuda:0')
episode: 202 training return: tensor(-330.9673, device='cuda:0')
episode: 203 training return: tensor(-377.8297, device='cuda:0')
epoch: 51 test_true_pfm: 304.533138769668 sim_pfm: -323.52903778201045
episode: 204 training return: tensor(-322.0423, device='cuda:0')
episode: 205 training return: tensor(-326.8607, device='cuda:0')
episode: 206 training return: tensor(-354.6154, device='cuda:0')
episode: 207 training return: tensor(-325.0342, device='cuda:0')
epoch: 52 test_true_pfm: 226.17523476110594 sim_pfm: -325.0924327059377
episode: 208 training return: tensor(-323.3707, device='cuda:0')
episode: 209 training return: tensor(-340.5550, device='cuda:0')
episode: 210 training return: tensor(-391.4784, device='cuda:0')
episode: 211 training return: tensor(-351.4388, device='cuda:0')
epoch: 53 test_true_pfm: 450.0961488281027 sim_pfm: -279.17189759528264
episode: 212 training return: tensor(-311.8951, device='cuda:0')
episode: 213 training return: tensor(-362.2763, device='cuda:0')
episode: 214 training return: tensor(-328.6491, device='cuda:0')
episode: 215 training return: tensor(-348.8123, device='cuda:0')
epoch: 54 test_true_pfm: 262.36558602380705 sim_pfm: -333.10617420321796
episode: 216 training return: tensor(-322.6717, device='cuda:0')
episode: 217 training return: tensor(-340.8699, device='cuda:0')
episode: 218 training return: tensor(-350.0359, device='cuda:0')
episode: 219 training return: tensor(-334.5021, device='cuda:0')
epoch: 55 test_true_pfm: 363.13459125298067 sim_pfm: -271.0385568554436
episode: 220 training return: tensor(-382.6485, device='cuda:0')
episode: 221 training return: tensor(-313.0021, device='cuda:0')
episode: 222 training return: tensor(-324.4932, device='cuda:0')
episode: 223 training return: tensor(-355.7552, device='cuda:0')
epoch: 56 test_true_pfm: 415.4464051933491 sim_pfm: -301.4845251097965
episode: 224 training return: tensor(-311.9742, device='cuda:0')
episode: 225 training return: tensor(-321.7998, device='cuda:0')
episode: 226 training return: tensor(-419.7906, device='cuda:0')
episode: 227 training return: tensor(-334.6440, device='cuda:0')
epoch: 57 test_true_pfm: 320.64544027229226 sim_pfm: -337.1184007821236
episode: 228 training return: tensor(-332.9792, device='cuda:0')
episode: 229 training return: tensor(-343.3103, device='cuda:0')
episode: 230 training return: tensor(-300.3519, device='cuda:0')
episode: 231 training return: tensor(-325.3137, device='cuda:0')
epoch: 58 test_true_pfm: 400.68325334659374 sim_pfm: -271.74667846934364
episode: 232 training return: tensor(-304.1209, device='cuda:0')
episode: 233 training return: tensor(-324.5634, device='cuda:0')
episode: 234 training return: tensor(-487.1797, device='cuda:0')
episode: 235 training return: tensor(-327.6158, device='cuda:0')
epoch: 59 test_true_pfm: 291.22446129264927 sim_pfm: -302.5862365595531
episode: 236 training return: tensor(-296.3734, device='cuda:0')
episode: 237 training return: tensor(-349.6839, device='cuda:0')
episode: 238 training return: tensor(-355.6668, device='cuda:0')
episode: 239 training return: tensor(-326.3959, device='cuda:0')
epoch: 60 test_true_pfm: 295.70178129416405 sim_pfm: -277.49757008587284
episode: 240 training return: tensor(-325.8148, device='cuda:0')
episode: 241 training return: tensor(-336.1189, device='cuda:0')
episode: 242 training return: tensor(-299.1541, device='cuda:0')
episode: 243 training return: tensor(-283.5375, device='cuda:0')
epoch: 61 test_true_pfm: 226.27584902594472 sim_pfm: -296.74528693256434
episode: 244 training return: tensor(-329.6287, device='cuda:0')
episode: 245 training return: tensor(-310.0403, device='cuda:0')
episode: 246 training return: tensor(-334.4349, device='cuda:0')
episode: 247 training return: tensor(-304.7343, device='cuda:0')
epoch: 62 test_true_pfm: 250.26115747657596 sim_pfm: -302.6599070765563
episode: 248 training return: tensor(-308.7439, device='cuda:0')
episode: 249 training return: tensor(-323.7558, device='cuda:0')
episode: 250 training return: tensor(-307.8643, device='cuda:0')
episode: 251 training return: tensor(-323.3181, device='cuda:0')
epoch: 63 test_true_pfm: 100.77581916386589 sim_pfm: -312.11134465746
episode: 252 training return: tensor(-307.0120, device='cuda:0')
episode: 253 training return: tensor(-355.3272, device='cuda:0')
episode: 254 training return: tensor(-344.4886, device='cuda:0')
episode: 255 training return: tensor(-352.0598, device='cuda:0')
epoch: 64 test_true_pfm: 295.38092195963276 sim_pfm: -310.72230997588485
episode: 256 training return: tensor(-354.2533, device='cuda:0')
episode: 257 training return: tensor(-342.3605, device='cuda:0')
episode: 258 training return: tensor(-303.6067, device='cuda:0')
episode: 259 training return: tensor(-302.3199, device='cuda:0')
epoch: 65 test_true_pfm: 351.7030388333244 sim_pfm: -306.25966891041026
episode: 260 training return: tensor(-304.9861, device='cuda:0')
episode: 261 training return: tensor(-316.1005, device='cuda:0')
episode: 262 training return: tensor(-306.8968, device='cuda:0')
episode: 263 training return: tensor(-323.3634, device='cuda:0')
epoch: 66 test_true_pfm: 302.7976373645924 sim_pfm: -288.1716650834812
episode: 264 training return: tensor(-307.7995, device='cuda:0')
episode: 265 training return: tensor(-327.3396, device='cuda:0')
episode: 266 training return: tensor(-362.1725, device='cuda:0')
episode: 267 training return: tensor(-329.5094, device='cuda:0')
epoch: 67 test_true_pfm: 412.0283298324234 sim_pfm: -283.91762774031184
episode: 268 training return: tensor(-300.6851, device='cuda:0')
episode: 269 training return: tensor(-332.8726, device='cuda:0')
episode: 270 training return: tensor(-337.0214, device='cuda:0')
episode: 271 training return: tensor(-284.8139, device='cuda:0')
epoch: 68 test_true_pfm: 384.460734785197 sim_pfm: -296.1559216727231
episode: 272 training return: tensor(-322.6517, device='cuda:0')
episode: 273 training return: tensor(-353.7532, device='cuda:0')
episode: 274 training return: tensor(-306.4000, device='cuda:0')
episode: 275 training return: tensor(-301.8940, device='cuda:0')
epoch: 69 test_true_pfm: 331.24344699721775 sim_pfm: -290.30866139162873
episode: 276 training return: tensor(-341.3369, device='cuda:0')
episode: 277 training return: tensor(-344.0256, device='cuda:0')
episode: 278 training return: tensor(-310.2057, device='cuda:0')
episode: 279 training return: tensor(-298.7199, device='cuda:0')
epoch: 70 test_true_pfm: 569.2182455330798 sim_pfm: -251.00814013381023
episode: 280 training return: tensor(-361.7298, device='cuda:0')
episode: 281 training return: tensor(-303.6686, device='cuda:0')
episode: 282 training return: tensor(-305.6505, device='cuda:0')
episode: 283 training return: tensor(-327.9230, device='cuda:0')
epoch: 71 test_true_pfm: 399.9375516484797 sim_pfm: -275.23920446424745
episode: 284 training return: tensor(-332.9847, device='cuda:0')
episode: 285 training return: tensor(-319.7847, device='cuda:0')
episode: 286 training return: tensor(-366.1757, device='cuda:0')
episode: 287 training return: tensor(-299.1884, device='cuda:0')
epoch: 72 test_true_pfm: 356.6317026919349 sim_pfm: -265.29423431794083
episode: 288 training return: tensor(-303.0822, device='cuda:0')
episode: 289 training return: tensor(-316.1515, device='cuda:0')
episode: 290 training return: tensor(-376.0205, device='cuda:0')
episode: 291 training return: tensor(-308.8398, device='cuda:0')
epoch: 73 test_true_pfm: 473.0469253565086 sim_pfm: -275.4492375209811
episode: 292 training return: tensor(-306.1589, device='cuda:0')
episode: 293 training return: tensor(-324.8857, device='cuda:0')
episode: 294 training return: tensor(-297.7617, device='cuda:0')
episode: 295 training return: tensor(-338.0272, device='cuda:0')
epoch: 74 test_true_pfm: 459.4433478553783 sim_pfm: -260.2033276542982
episode: 296 training return: tensor(-316.7388, device='cuda:0')
episode: 297 training return: tensor(-315.4008, device='cuda:0')
episode: 298 training return: tensor(-359.6282, device='cuda:0')
episode: 299 training return: tensor(-315.8364, device='cuda:0')
epoch: 75 test_true_pfm: 421.3646078872853 sim_pfm: -281.6996523695222
episode: 300 training return: tensor(-321.4078, device='cuda:0')
episode: 301 training return: tensor(-307.0261, device='cuda:0')
episode: 302 training return: tensor(-318.6266, device='cuda:0')
episode: 303 training return: tensor(-326.2222, device='cuda:0')
epoch: 76 test_true_pfm: 242.6606996368536 sim_pfm: -298.70152720391826
episode: 304 training return: tensor(-305.4235, device='cuda:0')
episode: 305 training return: tensor(-345.8178, device='cuda:0')
episode: 306 training return: tensor(-372.5879, device='cuda:0')
episode: 307 training return: tensor(-317.0658, device='cuda:0')
epoch: 77 test_true_pfm: 435.1249856319511 sim_pfm: -281.167640877354
episode: 308 training return: tensor(-285.7249, device='cuda:0')
episode: 309 training return: tensor(-327.8706, device='cuda:0')
episode: 310 training return: tensor(-307.3618, device='cuda:0')
episode: 311 training return: tensor(-320.8812, device='cuda:0')
epoch: 78 test_true_pfm: 474.7647154231766 sim_pfm: -261.97428924865864
episode: 312 training return: tensor(-346.4810, device='cuda:0')
episode: 313 training return: tensor(-307.7890, device='cuda:0')
episode: 314 training return: tensor(-303.0334, device='cuda:0')
episode: 315 training return: tensor(-289.4539, device='cuda:0')
epoch: 79 test_true_pfm: 549.2874991799795 sim_pfm: -254.63832716976563
episode: 316 training return: tensor(-267.7942, device='cuda:0')
episode: 317 training return: tensor(-335.7557, device='cuda:0')
episode: 318 training return: tensor(-343.4907, device='cuda:0')
episode: 319 training return: tensor(-364.8606, device='cuda:0')
epoch: 80 test_true_pfm: 438.2658205818775 sim_pfm: -271.27739310235484
episode: 320 training return: tensor(-313.5853, device='cuda:0')
episode: 321 training return: tensor(-353.8697, device='cuda:0')
episode: 322 training return: tensor(-301.1749, device='cuda:0')
episode: 323 training return: tensor(-315.2566, device='cuda:0')
epoch: 81 test_true_pfm: 271.4839519797722 sim_pfm: -290.6114356116159
episode: 324 training return: tensor(-325.7146, device='cuda:0')
episode: 325 training return: tensor(-322.9541, device='cuda:0')
episode: 326 training return: tensor(-305.4660, device='cuda:0')
episode: 327 training return: tensor(-280.5598, device='cuda:0')
epoch: 82 test_true_pfm: 593.2487949825171 sim_pfm: -229.61848130082944
episode: 328 training return: tensor(-380.5384, device='cuda:0')
episode: 329 training return: tensor(-341.9772, device='cuda:0')
episode: 330 training return: tensor(-355.4924, device='cuda:0')
episode: 331 training return: tensor(-310.4753, device='cuda:0')
epoch: 83 test_true_pfm: 490.8222680656151 sim_pfm: -269.623586543273
episode: 332 training return: tensor(-318.9625, device='cuda:0')
episode: 333 training return: tensor(-246.9891, device='cuda:0')
episode: 334 training return: tensor(-311.8579, device='cuda:0')
episode: 335 training return: tensor(-341.4085, device='cuda:0')
epoch: 84 test_true_pfm: 544.3093552788605 sim_pfm: -236.87694888014812
episode: 336 training return: tensor(-342.6908, device='cuda:0')
episode: 337 training return: tensor(-278.0073, device='cuda:0')
episode: 338 training return: tensor(-297.1171, device='cuda:0')
episode: 339 training return: tensor(-289.9407, device='cuda:0')
epoch: 85 test_true_pfm: 393.11281049161107 sim_pfm: -263.6950856868352
episode: 340 training return: tensor(-319.3383, device='cuda:0')
episode: 341 training return: tensor(-293.2270, device='cuda:0')
episode: 342 training return: tensor(-327.6341, device='cuda:0')
episode: 343 training return: tensor(-287.7618, device='cuda:0')
epoch: 86 test_true_pfm: 527.4108205036406 sim_pfm: -243.72210562160276
episode: 344 training return: tensor(-315.1559, device='cuda:0')
episode: 345 training return: tensor(-320.3846, device='cuda:0')
episode: 346 training return: tensor(-289.1541, device='cuda:0')
episode: 347 training return: tensor(-284.9478, device='cuda:0')
epoch: 87 test_true_pfm: 599.7096157257115 sim_pfm: -243.67277165455744
episode: 348 training return: tensor(-313.1655, device='cuda:0')
episode: 349 training return: tensor(-294.9747, device='cuda:0')
episode: 350 training return: tensor(-344.8950, device='cuda:0')
episode: 351 training return: tensor(-342.6238, device='cuda:0')
epoch: 88 test_true_pfm: 422.1070285342609 sim_pfm: -255.0838977061018
episode: 352 training return: tensor(-302.7199, device='cuda:0')
episode: 353 training return: tensor(-279.2307, device='cuda:0')
episode: 354 training return: tensor(-309.5704, device='cuda:0')
episode: 355 training return: tensor(-308.8955, device='cuda:0')
epoch: 89 test_true_pfm: 559.1902633509079 sim_pfm: -267.12253457579453
episode: 356 training return: tensor(-316.0206, device='cuda:0')
episode: 357 training return: tensor(-282.9024, device='cuda:0')
episode: 358 training return: tensor(-454.3128, device='cuda:0')
episode: 359 training return: tensor(-335.3835, device='cuda:0')
epoch: 90 test_true_pfm: 449.218984966863 sim_pfm: -242.52780843743435
episode: 360 training return: tensor(-302.9474, device='cuda:0')
episode: 361 training return: tensor(-340.2236, device='cuda:0')
episode: 362 training return: tensor(-326.6747, device='cuda:0')
episode: 363 training return: tensor(-281.5403, device='cuda:0')
epoch: 91 test_true_pfm: 598.5955588089697 sim_pfm: -249.14065241561426
episode: 364 training return: tensor(-353.6241, device='cuda:0')
episode: 365 training return: tensor(-296.3928, device='cuda:0')
episode: 366 training return: tensor(-302.4585, device='cuda:0')
episode: 367 training return: tensor(-319.8399, device='cuda:0')
epoch: 92 test_true_pfm: 518.4812331418144 sim_pfm: -262.82062593096634
episode: 368 training return: tensor(-330.3392, device='cuda:0')
episode: 369 training return: tensor(-285.4001, device='cuda:0')
episode: 370 training return: tensor(-317.6252, device='cuda:0')
episode: 371 training return: tensor(-301.5059, device='cuda:0')
epoch: 93 test_true_pfm: 529.9316927807758 sim_pfm: -247.94324296354898
episode: 372 training return: tensor(-343.3474, device='cuda:0')
episode: 373 training return: tensor(-315.1642, device='cuda:0')
episode: 374 training return: tensor(-298.2838, device='cuda:0')
episode: 375 training return: tensor(-309.3672, device='cuda:0')
epoch: 94 test_true_pfm: 676.3975548482737 sim_pfm: -236.9696613593454
episode: 376 training return: tensor(-308.3488, device='cuda:0')
episode: 377 training return: tensor(-290.4390, device='cuda:0')
episode: 378 training return: tensor(-336.7698, device='cuda:0')
episode: 379 training return: tensor(-319.1856, device='cuda:0')
epoch: 95 test_true_pfm: 629.3346006631758 sim_pfm: -268.2632799443866
episode: 380 training return: tensor(-321.0048, device='cuda:0')
episode: 381 training return: tensor(-307.3485, device='cuda:0')
episode: 382 training return: tensor(-326.0716, device='cuda:0')
episode: 383 training return: tensor(-331.1363, device='cuda:0')
epoch: 96 test_true_pfm: 528.3107186101806 sim_pfm: -243.71322054648772
episode: 384 training return: tensor(-314.2083, device='cuda:0')
episode: 385 training return: tensor(-310.8854, device='cuda:0')
episode: 386 training return: tensor(-309.0485, device='cuda:0')
episode: 387 training return: tensor(-305.4223, device='cuda:0')
epoch: 97 test_true_pfm: 428.01727578495 sim_pfm: -264.34844034883037
episode: 388 training return: tensor(-293.6410, device='cuda:0')
episode: 389 training return: tensor(-304.1468, device='cuda:0')
episode: 390 training return: tensor(-312.1246, device='cuda:0')
episode: 391 training return: tensor(-333.7151, device='cuda:0')
epoch: 98 test_true_pfm: 470.42845962935576 sim_pfm: -255.99595829537915
episode: 392 training return: tensor(-289.1875, device='cuda:0')
episode: 393 training return: tensor(-342.2540, device='cuda:0')
episode: 394 training return: tensor(-327.6771, device='cuda:0')
episode: 395 training return: tensor(-286.0257, device='cuda:0')
epoch: 99 test_true_pfm: 616.7160259206989 sim_pfm: -266.06018632347696
episode: 396 training return: tensor(-305.0970, device='cuda:0')
episode: 397 training return: tensor(-294.9964, device='cuda:0')
episode: 398 training return: tensor(-308.0706, device='cuda:0')
episode: 399 training return: tensor(-271.7238, device='cuda:0')
epoch: 100 test_true_pfm: 602.0156927390698 sim_pfm: -226.95734985273643
episode: 400 training return: tensor(-291.2942, device='cuda:0')
episode: 401 training return: tensor(-314.3719, device='cuda:0')
episode: 402 training return: tensor(-269.9050, device='cuda:0')
episode: 403 training return: tensor(-326.3927, device='cuda:0')
epoch: 101 test_true_pfm: 662.269774322701 sim_pfm: -262.916134029588
episode: 404 training return: tensor(-286.8458, device='cuda:0')
episode: 405 training return: tensor(-327.6244, device='cuda:0')
episode: 406 training return: tensor(-306.6608, device='cuda:0')
episode: 407 training return: tensor(-310.0071, device='cuda:0')
epoch: 102 test_true_pfm: 504.0729575882489 sim_pfm: -261.2551780064629
episode: 408 training return: tensor(-312.0422, device='cuda:0')
episode: 409 training return: tensor(-326.6023, device='cuda:0')
episode: 410 training return: tensor(-302.8066, device='cuda:0')
episode: 411 training return: tensor(-314.0574, device='cuda:0')
epoch: 103 test_true_pfm: 545.1622078448237 sim_pfm: -252.8970078099422
episode: 412 training return: tensor(-339.3892, device='cuda:0')
episode: 413 training return: tensor(-310.8617, device='cuda:0')
episode: 414 training return: tensor(-324.8138, device='cuda:0')
episode: 415 training return: tensor(-316.1336, device='cuda:0')
epoch: 104 test_true_pfm: 581.0952675585289 sim_pfm: -264.4241675544957
episode: 416 training return: tensor(-341.5625, device='cuda:0')
episode: 417 training return: tensor(-292.1376, device='cuda:0')
episode: 418 training return: tensor(-294.5934, device='cuda:0')
episode: 419 training return: tensor(-584.3861, device='cuda:0')
epoch: 105 test_true_pfm: 547.2678634096535 sim_pfm: -228.6832908760213
episode: 420 training return: tensor(-310.8236, device='cuda:0')
episode: 421 training return: tensor(-306.3753, device='cuda:0')
episode: 422 training return: tensor(-322.0970, device='cuda:0')
episode: 423 training return: tensor(-319.3844, device='cuda:0')
epoch: 106 test_true_pfm: 714.3822706470687 sim_pfm: -223.11671322447364
episode: 424 training return: tensor(-297.7327, device='cuda:0')
episode: 425 training return: tensor(-282.7116, device='cuda:0')
episode: 426 training return: tensor(-340.4237, device='cuda:0')
episode: 427 training return: tensor(-317.6458, device='cuda:0')
epoch: 107 test_true_pfm: 402.2722845902961 sim_pfm: -260.89454251896433
episode: 428 training return: tensor(-321.0691, device='cuda:0')
episode: 429 training return: tensor(-319.2981, device='cuda:0')
episode: 430 training return: tensor(-577.9703, device='cuda:0')
episode: 431 training return: tensor(-258.4195, device='cuda:0')
epoch: 108 test_true_pfm: 616.2585247785554 sim_pfm: -221.16776385432846
episode: 432 training return: tensor(-321.8197, device='cuda:0')
episode: 433 training return: tensor(-341.3612, device='cuda:0')
episode: 434 training return: tensor(-308.9785, device='cuda:0')
episode: 435 training return: tensor(-318.0133, device='cuda:0')
epoch: 109 test_true_pfm: 533.9860810033251 sim_pfm: -261.88199612192693
episode: 436 training return: tensor(-304.5457, device='cuda:0')
episode: 437 training return: tensor(-316.6470, device='cuda:0')
episode: 438 training return: tensor(-319.0923, device='cuda:0')
episode: 439 training return: tensor(-268.5558, device='cuda:0')
epoch: 110 test_true_pfm: 660.06187725283 sim_pfm: -264.6557217676503
episode: 440 training return: tensor(-309.2092, device='cuda:0')
episode: 441 training return: tensor(-306.3396, device='cuda:0')
episode: 442 training return: tensor(-343.9359, device='cuda:0')
episode: 443 training return: tensor(-297.1523, device='cuda:0')
epoch: 111 test_true_pfm: 547.5239212235713 sim_pfm: -250.59722752927337
episode: 444 training return: tensor(-311.9041, device='cuda:0')
episode: 445 training return: tensor(-312.9062, device='cuda:0')
episode: 446 training return: tensor(-321.3048, device='cuda:0')
episode: 447 training return: tensor(-318.9181, device='cuda:0')
epoch: 112 test_true_pfm: 553.1874256293271 sim_pfm: -256.47404423053376
episode: 448 training return: tensor(-334.5893, device='cuda:0')
episode: 449 training return: tensor(-570.1640, device='cuda:0')
episode: 450 training return: tensor(-272.1476, device='cuda:0')
episode: 451 training return: tensor(-298.5090, device='cuda:0')
epoch: 113 test_true_pfm: 713.015299434844 sim_pfm: -212.12879740459417
episode: 452 training return: tensor(-307.6580, device='cuda:0')
episode: 453 training return: tensor(-337.4453, device='cuda:0')
episode: 454 training return: tensor(-320.6007, device='cuda:0')
episode: 455 training return: tensor(-336.0152, device='cuda:0')
epoch: 114 test_true_pfm: 681.6228013113196 sim_pfm: -238.21544146193386
episode: 456 training return: tensor(-286.7586, device='cuda:0')
episode: 457 training return: tensor(-314.1478, device='cuda:0')
episode: 458 training return: tensor(-301.9924, device='cuda:0')
episode: 459 training return: tensor(-315.5640, device='cuda:0')
epoch: 115 test_true_pfm: 673.5740183130357 sim_pfm: -234.59876856560973
episode: 460 training return: tensor(-290.2010, device='cuda:0')
episode: 461 training return: tensor(-273.3460, device='cuda:0')
episode: 462 training return: tensor(-307.1036, device='cuda:0')
episode: 463 training return: tensor(-294.9453, device='cuda:0')
epoch: 116 test_true_pfm: 520.7480343441183 sim_pfm: -242.05270819736566
episode: 464 training return: tensor(-299.0634, device='cuda:0')
episode: 465 training return: tensor(-300.0349, device='cuda:0')
episode: 466 training return: tensor(-280.2578, device='cuda:0')
episode: 467 training return: tensor(-328.1323, device='cuda:0')
epoch: 117 test_true_pfm: 599.098137006103 sim_pfm: -240.64430663506695
episode: 468 training return: tensor(-298.4595, device='cuda:0')
episode: 469 training return: tensor(-305.0845, device='cuda:0')
episode: 470 training return: tensor(-292.6446, device='cuda:0')
episode: 471 training return: tensor(-294.4975, device='cuda:0')
epoch: 118 test_true_pfm: 623.1237688078905 sim_pfm: -222.20884184044553
episode: 472 training return: tensor(-305.0398, device='cuda:0')
episode: 473 training return: tensor(-333.8378, device='cuda:0')
episode: 474 training return: tensor(-277.6818, device='cuda:0')
episode: 475 training return: tensor(-324.8524, device='cuda:0')
epoch: 119 test_true_pfm: 553.9256363421956 sim_pfm: -258.19916251307586
episode: 476 training return: tensor(-286.1400, device='cuda:0')
episode: 477 training return: tensor(-264.6500, device='cuda:0')
episode: 478 training return: tensor(-298.4938, device='cuda:0')
episode: 479 training return: tensor(-322.5081, device='cuda:0')
epoch: 120 test_true_pfm: 569.4930305192547 sim_pfm: -239.55632853055917
episode: 480 training return: tensor(-287.7487, device='cuda:0')
episode: 481 training return: tensor(-325.0800, device='cuda:0')
episode: 482 training return: tensor(-287.9261, device='cuda:0')
episode: 483 training return: tensor(-287.6052, device='cuda:0')
epoch: 121 test_true_pfm: 719.5302009070402 sim_pfm: -230.99606633011717
episode: 484 training return: tensor(-295.0163, device='cuda:0')
episode: 485 training return: tensor(-289.9493, device='cuda:0')
episode: 486 training return: tensor(-268.8216, device='cuda:0')
episode: 487 training return: tensor(-339.5956, device='cuda:0')
epoch: 122 test_true_pfm: 620.6874726675111 sim_pfm: -255.27637141791638
episode: 488 training return: tensor(-303.8403, device='cuda:0')
episode: 489 training return: tensor(-285.0175, device='cuda:0')
episode: 490 training return: tensor(-311.0729, device='cuda:0')
episode: 491 training return: tensor(-308.7791, device='cuda:0')
epoch: 123 test_true_pfm: 473.9958489789149 sim_pfm: -228.2354657034351
episode: 492 training return: tensor(-289.2982, device='cuda:0')
episode: 493 training return: tensor(-303.4583, device='cuda:0')
episode: 494 training return: tensor(-295.7584, device='cuda:0')
episode: 495 training return: tensor(-296.4569, device='cuda:0')
epoch: 124 test_true_pfm: 583.5928148493417 sim_pfm: -239.42353922342105
episode: 496 training return: tensor(-334.5266, device='cuda:0')
episode: 497 training return: tensor(-265.5294, device='cuda:0')
episode: 498 training return: tensor(-285.0525, device='cuda:0')
episode: 499 training return: tensor(-314.3545, device='cuda:0')
epoch: 125 test_true_pfm: 558.0455167651766 sim_pfm: -249.9549698740399
episode: 500 training return: tensor(-348.9476, device='cuda:0')
episode: 501 training return: tensor(-299.7149, device='cuda:0')
episode: 502 training return: tensor(-305.6599, device='cuda:0')
episode: 503 training return: tensor(-281.0460, device='cuda:0')
epoch: 126 test_true_pfm: 725.9681064233256 sim_pfm: -257.6216434294086
episode: 504 training return: tensor(-342.9322, device='cuda:0')
episode: 505 training return: tensor(-274.4568, device='cuda:0')
episode: 506 training return: tensor(-291.8540, device='cuda:0')
episode: 507 training return: tensor(-280.7570, device='cuda:0')
epoch: 127 test_true_pfm: 643.6578182761895 sim_pfm: -247.2794170495666
episode: 508 training return: tensor(-310.3057, device='cuda:0')
episode: 509 training return: tensor(-333.2271, device='cuda:0')
episode: 510 training return: tensor(-303.7556, device='cuda:0')
episode: 511 training return: tensor(-322.8204, device='cuda:0')
epoch: 128 test_true_pfm: 569.3877783776837 sim_pfm: -250.02129179841722
episode: 512 training return: tensor(-299.5242, device='cuda:0')
episode: 513 training return: tensor(-274.3024, device='cuda:0')
episode: 514 training return: tensor(-295.5252, device='cuda:0')
episode: 515 training return: tensor(-300.4105, device='cuda:0')
epoch: 129 test_true_pfm: 636.9357379056302 sim_pfm: -251.13281634570254
episode: 516 training return: tensor(-291.7049, device='cuda:0')
episode: 517 training return: tensor(-306.8600, device='cuda:0')
episode: 518 training return: tensor(-326.1075, device='cuda:0')
episode: 519 training return: tensor(-328.9254, device='cuda:0')
epoch: 130 test_true_pfm: 688.523958600424 sim_pfm: -237.374057932427
episode: 520 training return: tensor(-284.5117, device='cuda:0')
episode: 521 training return: tensor(-303.3882, device='cuda:0')
episode: 522 training return: tensor(-307.9243, device='cuda:0')
episode: 523 training return: tensor(-312.7666, device='cuda:0')
epoch: 131 test_true_pfm: 521.1388182789241 sim_pfm: -231.20167192114363
episode: 524 training return: tensor(-329.6477, device='cuda:0')
episode: 525 training return: tensor(-292.1342, device='cuda:0')
episode: 526 training return: tensor(-302.4301, device='cuda:0')
episode: 527 training return: tensor(-269.5740, device='cuda:0')
epoch: 132 test_true_pfm: 533.0819744696383 sim_pfm: -221.65685470051054
episode: 528 training return: tensor(-286.8899, device='cuda:0')
episode: 529 training return: tensor(-319.1885, device='cuda:0')
episode: 530 training return: tensor(-303.7548, device='cuda:0')
episode: 531 training return: tensor(-307.0089, device='cuda:0')
epoch: 133 test_true_pfm: 491.03237080602366 sim_pfm: -236.38583892177363
episode: 532 training return: tensor(-286.4331, device='cuda:0')
episode: 533 training return: tensor(-341.6247, device='cuda:0')
episode: 534 training return: tensor(-301.2531, device='cuda:0')
episode: 535 training return: tensor(-300.2881, device='cuda:0')
epoch: 134 test_true_pfm: 571.4405395429218 sim_pfm: -251.8391551609578
episode: 536 training return: tensor(-332.0689, device='cuda:0')
episode: 537 training return: tensor(-334.5760, device='cuda:0')
episode: 538 training return: tensor(-295.4868, device='cuda:0')
episode: 539 training return: tensor(-283.6763, device='cuda:0')
epoch: 135 test_true_pfm: 619.1123551465777 sim_pfm: -238.16810300585348
episode: 540 training return: tensor(-288.1829, device='cuda:0')
episode: 541 training return: tensor(-314.4838, device='cuda:0')
episode: 542 training return: tensor(-294.4447, device='cuda:0')
episode: 543 training return: tensor(-278.9453, device='cuda:0')
epoch: 136 test_true_pfm: 618.1630101587393 sim_pfm: -240.17475450815013
episode: 544 training return: tensor(-272.4027, device='cuda:0')
episode: 545 training return: tensor(-290.6985, device='cuda:0')
episode: 546 training return: tensor(-298.0758, device='cuda:0')
episode: 547 training return: tensor(-594.0800, device='cuda:0')
epoch: 137 test_true_pfm: 449.6595273097599 sim_pfm: -248.44328505227654
episode: 548 training return: tensor(-336.9850, device='cuda:0')
episode: 549 training return: tensor(-283.9981, device='cuda:0')
episode: 550 training return: tensor(-311.8936, device='cuda:0')
episode: 551 training return: tensor(-281.0975, device='cuda:0')
epoch: 138 test_true_pfm: 644.4107584864138 sim_pfm: -221.00623864283747
episode: 552 training return: tensor(-253.1376, device='cuda:0')
episode: 553 training return: tensor(-301.5834, device='cuda:0')
episode: 554 training return: tensor(-289.0669, device='cuda:0')
episode: 555 training return: tensor(-288.7307, device='cuda:0')
epoch: 139 test_true_pfm: 675.9128132286464 sim_pfm: -222.33716034317817
episode: 556 training return: tensor(-272.1222, device='cuda:0')
episode: 557 training return: tensor(-302.1955, device='cuda:0')
episode: 558 training return: tensor(-310.5434, device='cuda:0')
episode: 559 training return: tensor(-323.8658, device='cuda:0')
epoch: 140 test_true_pfm: 530.4029623127009 sim_pfm: -230.30069473517747
episode: 560 training return: tensor(-314.2749, device='cuda:0')
episode: 561 training return: tensor(-315.0597, device='cuda:0')
episode: 562 training return: tensor(-320.6371, device='cuda:0')
episode: 563 training return: tensor(-272.9784, device='cuda:0')
epoch: 141 test_true_pfm: 576.7452316407915 sim_pfm: -250.0454927237879
episode: 564 training return: tensor(-287.7807, device='cuda:0')
episode: 565 training return: tensor(-274.9243, device='cuda:0')
episode: 566 training return: tensor(-303.6002, device='cuda:0')
episode: 567 training return: tensor(-304.7087, device='cuda:0')
epoch: 142 test_true_pfm: 684.1507157428301 sim_pfm: -222.89954773395826
episode: 568 training return: tensor(-294.7497, device='cuda:0')
episode: 569 training return: tensor(-328.8007, device='cuda:0')
episode: 570 training return: tensor(-290.6991, device='cuda:0')
episode: 571 training return: tensor(-283.5863, device='cuda:0')
epoch: 143 test_true_pfm: 649.5783414800138 sim_pfm: -227.6509638581192
episode: 572 training return: tensor(-281.9580, device='cuda:0')
episode: 573 training return: tensor(-303.8103, device='cuda:0')
episode: 574 training return: tensor(-313.5782, device='cuda:0')
episode: 575 training return: tensor(-303.1698, device='cuda:0')
epoch: 144 test_true_pfm: 613.1474421054932 sim_pfm: -244.13452495174715
episode: 576 training return: tensor(-322.4409, device='cuda:0')
episode: 577 training return: tensor(-337.3198, device='cuda:0')
episode: 578 training return: tensor(-296.6550, device='cuda:0')
episode: 579 training return: tensor(-311.8880, device='cuda:0')
epoch: 145 test_true_pfm: 604.2971383184923 sim_pfm: -238.73181197151038
episode: 580 training return: tensor(-301.9580, device='cuda:0')
episode: 581 training return: tensor(-308.0406, device='cuda:0')
episode: 582 training return: tensor(-307.9444, device='cuda:0')
episode: 583 training return: tensor(-291.4179, device='cuda:0')
epoch: 146 test_true_pfm: 513.5894919679489 sim_pfm: -257.1701519850758
episode: 584 training return: tensor(-268.8486, device='cuda:0')
episode: 585 training return: tensor(-291.1571, device='cuda:0')
episode: 586 training return: tensor(-275.8801, device='cuda:0')
episode: 587 training return: tensor(-334.6818, device='cuda:0')
epoch: 147 test_true_pfm: 598.874927222828 sim_pfm: -224.27099611737262
episode: 588 training return: tensor(-313.0219, device='cuda:0')
episode: 589 training return: tensor(-307.7359, device='cuda:0')
episode: 590 training return: tensor(-303.8726, device='cuda:0')
episode: 591 training return: tensor(-267.6059, device='cuda:0')
epoch: 148 test_true_pfm: 642.8325068281447 sim_pfm: -246.35883118607066
episode: 592 training return: tensor(-312.8511, device='cuda:0')
episode: 593 training return: tensor(-286.6030, device='cuda:0')
episode: 594 training return: tensor(-276.6819, device='cuda:0')
episode: 595 training return: tensor(-327.2734, device='cuda:0')
epoch: 149 test_true_pfm: 718.7172139168196 sim_pfm: -216.37237352872035
episode: 596 training return: tensor(-317.9062, device='cuda:0')
episode: 597 training return: tensor(-299.1042, device='cuda:0')
episode: 598 training return: tensor(-274.3482, device='cuda:0')
episode: 599 training return: tensor(-278.6411, device='cuda:0')
epoch: 150 test_true_pfm: 727.6728458894463 sim_pfm: -206.20907179793963
