['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'baseline', '--traj', 'expert', '--seed', '1']
episode: 0 training return: tensor(-998.8860, device='cuda:0')
episode: 1 training return: tensor(-989.0761, device='cuda:0')
episode: 2 training return: tensor(-998.8898, device='cuda:0')
episode: 3 training return: tensor(-997.2083, device='cuda:0')
epoch: 1 test_true_pfm: 277.6237368817363 sim_pfm: -967.998754988114
episode: 4 training return: tensor(-994.2759, device='cuda:0')
episode: 5 training return: tensor(-999.8959, device='cuda:0')
episode: 6 training return: tensor(-998.6300, device='cuda:0')
episode: 7 training return: tensor(-975.2462, device='cuda:0')
epoch: 2 test_true_pfm: 208.33445636598663 sim_pfm: -945.8200589420157
episode: 8 training return: tensor(-993.8864, device='cuda:0')
episode: 9 training return: tensor(-994.0087, device='cuda:0')
episode: 10 training return: tensor(-963.7408, device='cuda:0')
episode: 11 training return: tensor(-996.8997, device='cuda:0')
epoch: 3 test_true_pfm: 259.6377864557314 sim_pfm: -951.6473579059044
episode: 12 training return: tensor(-983.3985, device='cuda:0')
episode: 13 training return: tensor(-927.6683, device='cuda:0')
episode: 14 training return: tensor(-945.6990, device='cuda:0')
episode: 15 training return: tensor(-934.4987, device='cuda:0')
epoch: 4 test_true_pfm: 199.00265494067222 sim_pfm: -943.0436650641883
episode: 16 training return: tensor(-940.5506, device='cuda:0')
episode: 17 training return: tensor(-949.7392, device='cuda:0')
episode: 18 training return: tensor(-939.7668, device='cuda:0')
episode: 19 training return: tensor(-941.9928, device='cuda:0')
epoch: 5 test_true_pfm: 205.84346525894168 sim_pfm: -947.2037187662596
episode: 20 training return: tensor(-947.4028, device='cuda:0')
episode: 21 training return: tensor(-939.6114, device='cuda:0')
episode: 22 training return: tensor(-909.9854, device='cuda:0')
episode: 23 training return: tensor(-915.3248, device='cuda:0')
epoch: 6 test_true_pfm: 246.01132469886082 sim_pfm: -913.550286476966
episode: 24 training return: tensor(-917.1618, device='cuda:0')
episode: 25 training return: tensor(-915.8204, device='cuda:0')
episode: 26 training return: tensor(-933.9056, device='cuda:0')
episode: 27 training return: tensor(-915.0782, device='cuda:0')
epoch: 7 test_true_pfm: 247.474566390906 sim_pfm: -922.3402548452917
episode: 28 training return: tensor(-935.4543, device='cuda:0')
episode: 29 training return: tensor(-930.5312, device='cuda:0')
episode: 30 training return: tensor(-931.7964, device='cuda:0')
episode: 31 training return: tensor(-907.7507, device='cuda:0')
epoch: 8 test_true_pfm: 260.6821572880236 sim_pfm: -888.0096640537959
episode: 32 training return: tensor(-900.9077, device='cuda:0')
episode: 33 training return: tensor(-906.5693, device='cuda:0')
episode: 34 training return: tensor(-914.6406, device='cuda:0')
episode: 35 training return: tensor(-906.8830, device='cuda:0')
epoch: 9 test_true_pfm: 262.9307849636562 sim_pfm: -900.4508136090299
episode: 36 training return: tensor(-889.9301, device='cuda:0')
episode: 37 training return: tensor(-896.1675, device='cuda:0')
episode: 38 training return: tensor(-907.2325, device='cuda:0')
episode: 39 training return: tensor(-925.2097, device='cuda:0')
epoch: 10 test_true_pfm: 237.64099236586569 sim_pfm: -931.0955213969961
episode: 40 training return: tensor(-888.7109, device='cuda:0')
episode: 41 training return: tensor(-871.2023, device='cuda:0')
episode: 42 training return: tensor(-864.3118, device='cuda:0')
episode: 43 training return: tensor(-894.7961, device='cuda:0')
epoch: 11 test_true_pfm: 100.98808972648482 sim_pfm: -917.2291672418747
episode: 44 training return: tensor(-879.5828, device='cuda:0')
episode: 45 training return: tensor(-861.3766, device='cuda:0')
episode: 46 training return: tensor(-868.8177, device='cuda:0')
episode: 47 training return: tensor(-871.1119, device='cuda:0')
epoch: 12 test_true_pfm: 181.079793669825 sim_pfm: -868.2423661617019
episode: 48 training return: tensor(-878.6160, device='cuda:0')
episode: 49 training return: tensor(-878.4119, device='cuda:0')
episode: 50 training return: tensor(-873.4306, device='cuda:0')
episode: 51 training return: tensor(-872.0958, device='cuda:0')
epoch: 13 test_true_pfm: 187.9789500874074 sim_pfm: -871.0949823837727
episode: 52 training return: tensor(-871.8393, device='cuda:0')
episode: 53 training return: tensor(-888.9533, device='cuda:0')
episode: 54 training return: tensor(-904.7583, device='cuda:0')
episode: 55 training return: tensor(-862.8635, device='cuda:0')
epoch: 14 test_true_pfm: 304.0573667827232 sim_pfm: -856.5575839422332
episode: 56 training return: tensor(-876.9011, device='cuda:0')
episode: 57 training return: tensor(-868.8191, device='cuda:0')
episode: 58 training return: tensor(-874.1993, device='cuda:0')
episode: 59 training return: tensor(-862.4569, device='cuda:0')
epoch: 15 test_true_pfm: 315.02561319365424 sim_pfm: -865.7864670743389
episode: 60 training return: tensor(-867.2854, device='cuda:0')
episode: 61 training return: tensor(-860.6852, device='cuda:0')
episode: 62 training return: tensor(-872.9303, device='cuda:0')
episode: 63 training return: tensor(-869.8257, device='cuda:0')
epoch: 16 test_true_pfm: 318.2130989632076 sim_pfm: -852.349983077244
episode: 64 training return: tensor(-859.7919, device='cuda:0')
episode: 65 training return: tensor(-861.9605, device='cuda:0')
episode: 66 training return: tensor(-873.0454, device='cuda:0')
episode: 67 training return: tensor(-865.4975, device='cuda:0')
epoch: 17 test_true_pfm: 302.40601749794223 sim_pfm: -858.48880676184
episode: 68 training return: tensor(-884.4182, device='cuda:0')
episode: 69 training return: tensor(-873.8481, device='cuda:0')
episode: 70 training return: tensor(-873.3152, device='cuda:0')
episode: 71 training return: tensor(-869.0012, device='cuda:0')
epoch: 18 test_true_pfm: 314.58356718771034 sim_pfm: -856.5253642885946
episode: 72 training return: tensor(-863.0334, device='cuda:0')
episode: 73 training return: tensor(-879.2275, device='cuda:0')
episode: 74 training return: tensor(-875.8158, device='cuda:0')
episode: 75 training return: tensor(-877.8359, device='cuda:0')
epoch: 19 test_true_pfm: 325.0390370200653 sim_pfm: -842.8627710058354
episode: 76 training return: tensor(-862.4310, device='cuda:0')
episode: 77 training return: tensor(-855.5643, device='cuda:0')
episode: 78 training return: tensor(-855.4031, device='cuda:0')
episode: 79 training return: tensor(-864.5832, device='cuda:0')
epoch: 20 test_true_pfm: 309.55098864218235 sim_pfm: -853.0313755202418
episode: 80 training return: tensor(-856.6829, device='cuda:0')
episode: 81 training return: tensor(-848.3785, device='cuda:0')
episode: 82 training return: tensor(-846.1201, device='cuda:0')
episode: 83 training return: tensor(-853.2719, device='cuda:0')
epoch: 21 test_true_pfm: 313.4466466331096 sim_pfm: -858.6362930970887
episode: 84 training return: tensor(-867.4293, device='cuda:0')
episode: 85 training return: tensor(-860.4630, device='cuda:0')
episode: 86 training return: tensor(-864.8444, device='cuda:0')
episode: 87 training return: tensor(-852.7876, device='cuda:0')
epoch: 22 test_true_pfm: 337.1384379123277 sim_pfm: -849.1477223973101
episode: 88 training return: tensor(-857.0963, device='cuda:0')
episode: 89 training return: tensor(-854.4905, device='cuda:0')
episode: 90 training return: tensor(-853.7982, device='cuda:0')
episode: 91 training return: tensor(-859.7401, device='cuda:0')
epoch: 23 test_true_pfm: 337.61182923465753 sim_pfm: -853.9753823634237
episode: 92 training return: tensor(-863.5173, device='cuda:0')
episode: 93 training return: tensor(-859.0408, device='cuda:0')
episode: 94 training return: tensor(-871.5177, device='cuda:0')
episode: 95 training return: tensor(-859.4608, device='cuda:0')
epoch: 24 test_true_pfm: 323.1399024907548 sim_pfm: -850.5482733068056
episode: 96 training return: tensor(-859.9484, device='cuda:0')
episode: 97 training return: tensor(-845.8171, device='cuda:0')
episode: 98 training return: tensor(-853.1180, device='cuda:0')
episode: 99 training return: tensor(-853.7633, device='cuda:0')
epoch: 25 test_true_pfm: 328.8492356216918 sim_pfm: -849.4340351567176
episode: 100 training return: tensor(-854.3275, device='cuda:0')
episode: 101 training return: tensor(-849.3060, device='cuda:0')
episode: 102 training return: tensor(-868.9208, device='cuda:0')
episode: 103 training return: tensor(-862.6458, device='cuda:0')
epoch: 26 test_true_pfm: 328.6763950117201 sim_pfm: -855.3283886027639
episode: 104 training return: tensor(-861.2087, device='cuda:0')
episode: 105 training return: tensor(-853.2652, device='cuda:0')
episode: 106 training return: tensor(-861.3298, device='cuda:0')
episode: 107 training return: tensor(-871.3282, device='cuda:0')
epoch: 27 test_true_pfm: 339.4026301570536 sim_pfm: -849.7973845182083
episode: 108 training return: tensor(-862.2610, device='cuda:0')
episode: 109 training return: tensor(-840.0787, device='cuda:0')
episode: 110 training return: tensor(-869.3405, device='cuda:0')
episode: 111 training return: tensor(-858.0005, device='cuda:0')
epoch: 28 test_true_pfm: 342.52491199324663 sim_pfm: -844.1968245187696
episode: 112 training return: tensor(-858.3298, device='cuda:0')
episode: 113 training return: tensor(-851.9180, device='cuda:0')
episode: 114 training return: tensor(-855.8712, device='cuda:0')
episode: 115 training return: tensor(-843.6802, device='cuda:0')
epoch: 29 test_true_pfm: 332.781734944938 sim_pfm: -851.2026498198198
episode: 116 training return: tensor(-858.8294, device='cuda:0')
episode: 117 training return: tensor(-847.6157, device='cuda:0')
episode: 118 training return: tensor(-854.4419, device='cuda:0')
episode: 119 training return: tensor(-846.9020, device='cuda:0')
epoch: 30 test_true_pfm: 337.7114264560366 sim_pfm: -846.9291270201405
episode: 120 training return: tensor(-862.7634, device='cuda:0')
episode: 121 training return: tensor(-861.0032, device='cuda:0')
episode: 122 training return: tensor(-860.4264, device='cuda:0')
episode: 123 training return: tensor(-841.2462, device='cuda:0')
epoch: 31 test_true_pfm: 344.6564016393361 sim_pfm: -841.2434462364763
episode: 124 training return: tensor(-848.6314, device='cuda:0')
episode: 125 training return: tensor(-853.7900, device='cuda:0')
episode: 126 training return: tensor(-843.7656, device='cuda:0')
episode: 127 training return: tensor(-841.4276, device='cuda:0')
epoch: 32 test_true_pfm: 343.54603407907234 sim_pfm: -841.1724188813629
episode: 128 training return: tensor(-848.6736, device='cuda:0')
episode: 129 training return: tensor(-849.6846, device='cuda:0')
episode: 130 training return: tensor(-856.6911, device='cuda:0')
episode: 131 training return: tensor(-857.8740, device='cuda:0')
epoch: 33 test_true_pfm: 347.82205617514 sim_pfm: -839.0143124610186
episode: 132 training return: tensor(-850.9291, device='cuda:0')
episode: 133 training return: tensor(-845.5163, device='cuda:0')
episode: 134 training return: tensor(-844.7036, device='cuda:0')
episode: 135 training return: tensor(-848.5762, device='cuda:0')
epoch: 34 test_true_pfm: 341.8390229608424 sim_pfm: -842.596769054071
episode: 136 training return: tensor(-852.1667, device='cuda:0')
episode: 137 training return: tensor(-848.7023, device='cuda:0')
episode: 138 training return: tensor(-850.2438, device='cuda:0')
episode: 139 training return: tensor(-842.3004, device='cuda:0')
epoch: 35 test_true_pfm: 338.78294608585185 sim_pfm: -840.2877380376061
episode: 140 training return: tensor(-841.8543, device='cuda:0')
episode: 141 training return: tensor(-853.9003, device='cuda:0')
episode: 142 training return: tensor(-848.4919, device='cuda:0')
episode: 143 training return: tensor(-849.6113, device='cuda:0')
epoch: 36 test_true_pfm: 346.3400862228616 sim_pfm: -843.8055578609928
episode: 144 training return: tensor(-845.7334, device='cuda:0')
episode: 145 training return: tensor(-842.9307, device='cuda:0')
episode: 146 training return: tensor(-855.0026, device='cuda:0')
episode: 147 training return: tensor(-848.1754, device='cuda:0')
epoch: 37 test_true_pfm: 339.94882722271944 sim_pfm: -841.9371331864968
episode: 148 training return: tensor(-842.0259, device='cuda:0')
episode: 149 training return: tensor(-841.6826, device='cuda:0')
episode: 150 training return: tensor(-838.5217, device='cuda:0')
episode: 151 training return: tensor(-843.3947, device='cuda:0')
epoch: 38 test_true_pfm: 339.3616870909502 sim_pfm: -839.0522545619557
episode: 152 training return: tensor(-851.1294, device='cuda:0')
episode: 153 training return: tensor(-854.9752, device='cuda:0')
episode: 154 training return: tensor(-845.3375, device='cuda:0')
episode: 155 training return: tensor(-851.3818, device='cuda:0')
epoch: 39 test_true_pfm: 347.5317561931526 sim_pfm: -838.6957251597778
episode: 156 training return: tensor(-847.1899, device='cuda:0')
episode: 157 training return: tensor(-849.0576, device='cuda:0')
episode: 158 training return: tensor(-847.1423, device='cuda:0')
episode: 159 training return: tensor(-849.5397, device='cuda:0')
epoch: 40 test_true_pfm: 344.36449788059 sim_pfm: -839.6387081011198
episode: 160 training return: tensor(-841.6592, device='cuda:0')
episode: 161 training return: tensor(-851.5488, device='cuda:0')
episode: 162 training return: tensor(-841.6310, device='cuda:0')
episode: 163 training return: tensor(-837.6519, device='cuda:0')
epoch: 41 test_true_pfm: 349.284800283084 sim_pfm: -839.8505678562797
episode: 164 training return: tensor(-844.7859, device='cuda:0')
episode: 165 training return: tensor(-860.9489, device='cuda:0')
episode: 166 training return: tensor(-840.3685, device='cuda:0')
episode: 167 training return: tensor(-842.0452, device='cuda:0')
epoch: 42 test_true_pfm: 352.02759987627684 sim_pfm: -836.1903928746275
episode: 168 training return: tensor(-838.1782, device='cuda:0')
episode: 169 training return: tensor(-841.2554, device='cuda:0')
episode: 170 training return: tensor(-848.7847, device='cuda:0')
episode: 171 training return: tensor(-846.1864, device='cuda:0')
epoch: 43 test_true_pfm: 361.1933895180207 sim_pfm: -837.2369951810784
episode: 172 training return: tensor(-842.4023, device='cuda:0')
episode: 173 training return: tensor(-844.0498, device='cuda:0')
episode: 174 training return: tensor(-835.3768, device='cuda:0')
episode: 175 training return: tensor(-836.1201, device='cuda:0')
epoch: 44 test_true_pfm: 342.4542134383516 sim_pfm: -839.390971881027
episode: 176 training return: tensor(-847.9434, device='cuda:0')
episode: 177 training return: tensor(-837.2182, device='cuda:0')
episode: 178 training return: tensor(-841.3638, device='cuda:0')
episode: 179 training return: tensor(-842.7067, device='cuda:0')
epoch: 45 test_true_pfm: 343.7064712363813 sim_pfm: -836.4116352473696
episode: 180 training return: tensor(-852.5602, device='cuda:0')
episode: 181 training return: tensor(-848.6381, device='cuda:0')
episode: 182 training return: tensor(-839.2229, device='cuda:0')
episode: 183 training return: tensor(-846.2694, device='cuda:0')
epoch: 46 test_true_pfm: 333.5026299895491 sim_pfm: -844.3139438483244
episode: 184 training return: tensor(-837.9501, device='cuda:0')
episode: 185 training return: tensor(-837.2271, device='cuda:0')
episode: 186 training return: tensor(-837.4914, device='cuda:0')
episode: 187 training return: tensor(-839.8353, device='cuda:0')
epoch: 47 test_true_pfm: 350.45215959666456 sim_pfm: -838.3274538076172
episode: 188 training return: tensor(-845.2303, device='cuda:0')
episode: 189 training return: tensor(-836.1723, device='cuda:0')
episode: 190 training return: tensor(-838.6204, device='cuda:0')
episode: 191 training return: tensor(-845.2349, device='cuda:0')
epoch: 48 test_true_pfm: 354.03380775347887 sim_pfm: -839.0162426427705
episode: 192 training return: tensor(-850.9210, device='cuda:0')
episode: 193 training return: tensor(-846.0873, device='cuda:0')
episode: 194 training return: tensor(-843.1689, device='cuda:0')
episode: 195 training return: tensor(-853.4492, device='cuda:0')
epoch: 49 test_true_pfm: 350.1303364197956 sim_pfm: -841.1499803708866
episode: 196 training return: tensor(-847.4273, device='cuda:0')
episode: 197 training return: tensor(-837.5937, device='cuda:0')
episode: 198 training return: tensor(-851.1332, device='cuda:0')
episode: 199 training return: tensor(-841.3855, device='cuda:0')
epoch: 50 test_true_pfm: 350.83126297707696 sim_pfm: -833.802161316659
episode: 200 training return: tensor(-845.1194, device='cuda:0')
episode: 201 training return: tensor(-836.9675, device='cuda:0')
episode: 202 training return: tensor(-840.8034, device='cuda:0')
episode: 203 training return: tensor(-843.4808, device='cuda:0')
epoch: 51 test_true_pfm: 351.24829045186056 sim_pfm: -838.3298793596526
episode: 204 training return: tensor(-841.9694, device='cuda:0')
episode: 205 training return: tensor(-846.7452, device='cuda:0')
episode: 206 training return: tensor(-842.4015, device='cuda:0')
episode: 207 training return: tensor(-841.2984, device='cuda:0')
epoch: 52 test_true_pfm: 348.87915508974055 sim_pfm: -834.7646543498462
episode: 208 training return: tensor(-837.2645, device='cuda:0')
episode: 209 training return: tensor(-836.3505, device='cuda:0')
episode: 210 training return: tensor(-840.2695, device='cuda:0')
episode: 211 training return: tensor(-847.0255, device='cuda:0')
epoch: 53 test_true_pfm: 360.9881497175329 sim_pfm: -834.7513772337697
episode: 212 training return: tensor(-842.2559, device='cuda:0')
episode: 213 training return: tensor(-847.9112, device='cuda:0')
episode: 214 training return: tensor(-846.1613, device='cuda:0')
episode: 215 training return: tensor(-843.2183, device='cuda:0')
epoch: 54 test_true_pfm: 356.38395008177923 sim_pfm: -834.8981176780071
episode: 216 training return: tensor(-842.5037, device='cuda:0')
episode: 217 training return: tensor(-846.5342, device='cuda:0')
episode: 218 training return: tensor(-847.7043, device='cuda:0')
episode: 219 training return: tensor(-843.1496, device='cuda:0')
epoch: 55 test_true_pfm: 350.2854497285618 sim_pfm: -838.1387888047224
episode: 220 training return: tensor(-849.4622, device='cuda:0')
episode: 221 training return: tensor(-845.7819, device='cuda:0')
episode: 222 training return: tensor(-838.8345, device='cuda:0')
episode: 223 training return: tensor(-839.3323, device='cuda:0')
epoch: 56 test_true_pfm: 347.2747831367051 sim_pfm: -837.4544713913152
episode: 224 training return: tensor(-857.5898, device='cuda:0')
episode: 225 training return: tensor(-854.7557, device='cuda:0')
episode: 226 training return: tensor(-839.7146, device='cuda:0')
episode: 227 training return: tensor(-848.8922, device='cuda:0')
epoch: 57 test_true_pfm: 345.6291835461646 sim_pfm: -835.9167210835343
episode: 228 training return: tensor(-842.2521, device='cuda:0')
episode: 229 training return: tensor(-837.4008, device='cuda:0')
episode: 230 training return: tensor(-842.6326, device='cuda:0')
episode: 231 training return: tensor(-838.8677, device='cuda:0')
epoch: 58 test_true_pfm: 340.20750852185824 sim_pfm: -837.5146831488624
episode: 232 training return: tensor(-849.3207, device='cuda:0')
episode: 233 training return: tensor(-848.3763, device='cuda:0')
episode: 234 training return: tensor(-844.4532, device='cuda:0')
episode: 235 training return: tensor(-846.8217, device='cuda:0')
epoch: 59 test_true_pfm: 351.70242155556747 sim_pfm: -835.3349324085478
episode: 236 training return: tensor(-846.8990, device='cuda:0')
episode: 237 training return: tensor(-848.8942, device='cuda:0')
episode: 238 training return: tensor(-845.5601, device='cuda:0')
episode: 239 training return: tensor(-843.4982, device='cuda:0')
epoch: 60 test_true_pfm: 334.78776934749203 sim_pfm: -842.9247311888417
episode: 240 training return: tensor(-841.8516, device='cuda:0')
episode: 241 training return: tensor(-844.0955, device='cuda:0')
episode: 242 training return: tensor(-845.7448, device='cuda:0')
episode: 243 training return: tensor(-845.6775, device='cuda:0')
epoch: 61 test_true_pfm: 341.5326468929479 sim_pfm: -839.2593809442284
episode: 244 training return: tensor(-851.1377, device='cuda:0')
episode: 245 training return: tensor(-842.4243, device='cuda:0')
episode: 246 training return: tensor(-842.2759, device='cuda:0')
episode: 247 training return: tensor(-847.5091, device='cuda:0')
epoch: 62 test_true_pfm: 340.8238529096314 sim_pfm: -840.5130718387663
episode: 248 training return: tensor(-846.2299, device='cuda:0')
episode: 249 training return: tensor(-844.0530, device='cuda:0')
episode: 250 training return: tensor(-835.6877, device='cuda:0')
episode: 251 training return: tensor(-845.2460, device='cuda:0')
epoch: 63 test_true_pfm: 348.02361220766716 sim_pfm: -838.3855053251609
episode: 252 training return: tensor(-851.5772, device='cuda:0')
episode: 253 training return: tensor(-843.5921, device='cuda:0')
episode: 254 training return: tensor(-839.6560, device='cuda:0')
episode: 255 training return: tensor(-844.0302, device='cuda:0')
epoch: 64 test_true_pfm: 344.7611752435516 sim_pfm: -843.4513077338537
episode: 256 training return: tensor(-846.8154, device='cuda:0')
episode: 257 training return: tensor(-844.0182, device='cuda:0')
episode: 258 training return: tensor(-842.4856, device='cuda:0')
episode: 259 training return: tensor(-845.2304, device='cuda:0')
epoch: 65 test_true_pfm: 346.75826659360746 sim_pfm: -838.2511148250973
episode: 260 training return: tensor(-841.3339, device='cuda:0')
episode: 261 training return: tensor(-839.0201, device='cuda:0')
episode: 262 training return: tensor(-839.4319, device='cuda:0')
episode: 263 training return: tensor(-841.0304, device='cuda:0')
epoch: 66 test_true_pfm: 352.80770669852996 sim_pfm: -837.7667151694963
episode: 264 training return: tensor(-848.0264, device='cuda:0')
episode: 265 training return: tensor(-851.3804, device='cuda:0')
episode: 266 training return: tensor(-848.6393, device='cuda:0')
episode: 267 training return: tensor(-841.2747, device='cuda:0')
epoch: 67 test_true_pfm: 354.49787646974164 sim_pfm: -839.8619475724796
episode: 268 training return: tensor(-844.6439, device='cuda:0')
episode: 269 training return: tensor(-834.5432, device='cuda:0')
episode: 270 training return: tensor(-845.9156, device='cuda:0')
episode: 271 training return: tensor(-848.6037, device='cuda:0')
epoch: 68 test_true_pfm: 361.2458648817292 sim_pfm: -838.036987182335
episode: 272 training return: tensor(-842.0912, device='cuda:0')
episode: 273 training return: tensor(-840.3174, device='cuda:0')
episode: 274 training return: tensor(-846.5284, device='cuda:0')
episode: 275 training return: tensor(-839.9901, device='cuda:0')
epoch: 69 test_true_pfm: 351.3763037169152 sim_pfm: -838.5987094469989
episode: 276 training return: tensor(-851.9481, device='cuda:0')
episode: 277 training return: tensor(-837.8857, device='cuda:0')
episode: 278 training return: tensor(-836.2311, device='cuda:0')
episode: 279 training return: tensor(-846.5596, device='cuda:0')
epoch: 70 test_true_pfm: 352.3768816795857 sim_pfm: -837.5909022393947
episode: 280 training return: tensor(-841.7583, device='cuda:0')
episode: 281 training return: tensor(-841.2671, device='cuda:0')
episode: 282 training return: tensor(-836.7744, device='cuda:0')
episode: 283 training return: tensor(-840.6790, device='cuda:0')
epoch: 71 test_true_pfm: 354.4384373662854 sim_pfm: -836.9233605116606
episode: 284 training return: tensor(-848.1426, device='cuda:0')
episode: 285 training return: tensor(-838.5624, device='cuda:0')
episode: 286 training return: tensor(-840.9062, device='cuda:0')
episode: 287 training return: tensor(-841.5080, device='cuda:0')
epoch: 72 test_true_pfm: 354.03327310875784 sim_pfm: -836.7941885938247
episode: 288 training return: tensor(-842.7040, device='cuda:0')
episode: 289 training return: tensor(-839.5964, device='cuda:0')
episode: 290 training return: tensor(-848.3275, device='cuda:0')
episode: 291 training return: tensor(-842.4719, device='cuda:0')
epoch: 73 test_true_pfm: 360.4560472918549 sim_pfm: -834.6035835732085
episode: 292 training return: tensor(-844.5404, device='cuda:0')
episode: 293 training return: tensor(-843.4995, device='cuda:0')
episode: 294 training return: tensor(-848.8719, device='cuda:0')
episode: 295 training return: tensor(-839.9392, device='cuda:0')
epoch: 74 test_true_pfm: 361.18396241342157 sim_pfm: -836.5974381615719
episode: 296 training return: tensor(-845.7653, device='cuda:0')
episode: 297 training return: tensor(-846.6236, device='cuda:0')
episode: 298 training return: tensor(-847.0505, device='cuda:0')
episode: 299 training return: tensor(-845.5698, device='cuda:0')
epoch: 75 test_true_pfm: 355.96066130404216 sim_pfm: -836.0396079662411
episode: 300 training return: tensor(-846.2186, device='cuda:0')
episode: 301 training return: tensor(-849.6983, device='cuda:0')
episode: 302 training return: tensor(-840.7466, device='cuda:0')
episode: 303 training return: tensor(-835.7838, device='cuda:0')
epoch: 76 test_true_pfm: 346.1527102643275 sim_pfm: -839.196807222208
episode: 304 training return: tensor(-841.8976, device='cuda:0')
episode: 305 training return: tensor(-833.8931, device='cuda:0')
episode: 306 training return: tensor(-851.8201, device='cuda:0')
episode: 307 training return: tensor(-846.4005, device='cuda:0')
epoch: 77 test_true_pfm: 355.8717366616581 sim_pfm: -839.4678202899328
episode: 308 training return: tensor(-842.5774, device='cuda:0')
episode: 309 training return: tensor(-850.6897, device='cuda:0')
episode: 310 training return: tensor(-839.5041, device='cuda:0')
episode: 311 training return: tensor(-843.5208, device='cuda:0')
epoch: 78 test_true_pfm: 357.09918700996315 sim_pfm: -834.4205706686092
episode: 312 training return: tensor(-834.9404, device='cuda:0')
episode: 313 training return: tensor(-844.0261, device='cuda:0')
episode: 314 training return: tensor(-839.0858, device='cuda:0')
episode: 315 training return: tensor(-840.0370, device='cuda:0')
epoch: 79 test_true_pfm: 358.9289854828498 sim_pfm: -834.3794474669363
episode: 316 training return: tensor(-841.4906, device='cuda:0')
episode: 317 training return: tensor(-845.5893, device='cuda:0')
episode: 318 training return: tensor(-849.2510, device='cuda:0')
episode: 319 training return: tensor(-847.8476, device='cuda:0')
epoch: 80 test_true_pfm: 346.65894161666273 sim_pfm: -844.5778161525183
episode: 320 training return: tensor(-841.0202, device='cuda:0')
episode: 321 training return: tensor(-846.9193, device='cuda:0')
episode: 322 training return: tensor(-838.6993, device='cuda:0')
episode: 323 training return: tensor(-848.9700, device='cuda:0')
epoch: 81 test_true_pfm: 349.2919683531281 sim_pfm: -838.2088916433471
episode: 324 training return: tensor(-845.6222, device='cuda:0')
episode: 325 training return: tensor(-854.1754, device='cuda:0')
episode: 326 training return: tensor(-844.2978, device='cuda:0')
episode: 327 training return: tensor(-839.9620, device='cuda:0')
epoch: 82 test_true_pfm: 357.0471476311406 sim_pfm: -834.8486877496276
episode: 328 training return: tensor(-839.3083, device='cuda:0')
episode: 329 training return: tensor(-836.9005, device='cuda:0')
episode: 330 training return: tensor(-843.6477, device='cuda:0')
episode: 331 training return: tensor(-840.1965, device='cuda:0')
epoch: 83 test_true_pfm: 346.9353166204687 sim_pfm: -837.4086583394868
episode: 332 training return: tensor(-851.0107, device='cuda:0')
episode: 333 training return: tensor(-839.2369, device='cuda:0')
episode: 334 training return: tensor(-842.5561, device='cuda:0')
episode: 335 training return: tensor(-845.5910, device='cuda:0')
epoch: 84 test_true_pfm: 339.22667931642746 sim_pfm: -838.9318458992833
episode: 336 training return: tensor(-837.3585, device='cuda:0')
episode: 337 training return: tensor(-836.9168, device='cuda:0')
episode: 338 training return: tensor(-840.7262, device='cuda:0')
episode: 339 training return: tensor(-840.1171, device='cuda:0')
epoch: 85 test_true_pfm: 344.84021917624324 sim_pfm: -834.8548823728537
episode: 340 training return: tensor(-839.8927, device='cuda:0')
episode: 341 training return: tensor(-837.7767, device='cuda:0')
episode: 342 training return: tensor(-844.6459, device='cuda:0')
episode: 343 training return: tensor(-842.6663, device='cuda:0')
epoch: 86 test_true_pfm: 351.41724890812947 sim_pfm: -836.3643279732205
episode: 344 training return: tensor(-847.9969, device='cuda:0')
episode: 345 training return: tensor(-843.6125, device='cuda:0')
episode: 346 training return: tensor(-844.4981, device='cuda:0')
episode: 347 training return: tensor(-836.3521, device='cuda:0')
epoch: 87 test_true_pfm: 357.2801413633758 sim_pfm: -839.6992118194079
episode: 348 training return: tensor(-845.9233, device='cuda:0')
episode: 349 training return: tensor(-847.2695, device='cuda:0')
episode: 350 training return: tensor(-845.3246, device='cuda:0')
episode: 351 training return: tensor(-845.6655, device='cuda:0')
epoch: 88 test_true_pfm: 353.0360276936492 sim_pfm: -836.6011794591128
episode: 352 training return: tensor(-844.3975, device='cuda:0')
episode: 353 training return: tensor(-842.5193, device='cuda:0')
episode: 354 training return: tensor(-842.9653, device='cuda:0')
episode: 355 training return: tensor(-842.7753, device='cuda:0')
epoch: 89 test_true_pfm: 347.00383716968025 sim_pfm: -837.2697399838362
episode: 356 training return: tensor(-838.7268, device='cuda:0')
episode: 357 training return: tensor(-841.6181, device='cuda:0')
episode: 358 training return: tensor(-836.9122, device='cuda:0')
episode: 359 training return: tensor(-840.5903, device='cuda:0')
epoch: 90 test_true_pfm: 348.8856561330837 sim_pfm: -836.33463458258
episode: 360 training return: tensor(-837.5275, device='cuda:0')
episode: 361 training return: tensor(-837.3760, device='cuda:0')
episode: 362 training return: tensor(-840.2258, device='cuda:0')
episode: 363 training return: tensor(-840.1097, device='cuda:0')
epoch: 91 test_true_pfm: 344.5990485745474 sim_pfm: -836.0631589175513
episode: 364 training return: tensor(-844.4040, device='cuda:0')
episode: 365 training return: tensor(-840.6468, device='cuda:0')
episode: 366 training return: tensor(-843.9312, device='cuda:0')
episode: 367 training return: tensor(-842.1051, device='cuda:0')
epoch: 92 test_true_pfm: 352.8346238780029 sim_pfm: -835.3308413064418
episode: 368 training return: tensor(-845.8171, device='cuda:0')
episode: 369 training return: tensor(-840.2999, device='cuda:0')
episode: 370 training return: tensor(-840.4092, device='cuda:0')
episode: 371 training return: tensor(-842.3679, device='cuda:0')
epoch: 93 test_true_pfm: 342.3130763268302 sim_pfm: -838.6560976195615
episode: 372 training return: tensor(-843.4595, device='cuda:0')
episode: 373 training return: tensor(-838.7064, device='cuda:0')
episode: 374 training return: tensor(-848.6503, device='cuda:0')
episode: 375 training return: tensor(-857.5397, device='cuda:0')
epoch: 94 test_true_pfm: 345.7334598132168 sim_pfm: -843.4426584797911
episode: 376 training return: tensor(-839.8528, device='cuda:0')
episode: 377 training return: tensor(-835.9692, device='cuda:0')
episode: 378 training return: tensor(-856.5151, device='cuda:0')
episode: 379 training return: tensor(-844.1989, device='cuda:0')
epoch: 95 test_true_pfm: 343.9845130019576 sim_pfm: -836.7556105307303
episode: 380 training return: tensor(-841.1947, device='cuda:0')
episode: 381 training return: tensor(-847.8413, device='cuda:0')
episode: 382 training return: tensor(-835.7967, device='cuda:0')
episode: 383 training return: tensor(-844.4615, device='cuda:0')
epoch: 96 test_true_pfm: 348.24826245861567 sim_pfm: -840.0191983648887
episode: 384 training return: tensor(-844.7587, device='cuda:0')
episode: 385 training return: tensor(-844.0724, device='cuda:0')
episode: 386 training return: tensor(-842.2374, device='cuda:0')
episode: 387 training return: tensor(-847.6100, device='cuda:0')
epoch: 97 test_true_pfm: 342.58727474875235 sim_pfm: -840.2181025286749
episode: 388 training return: tensor(-842.2822, device='cuda:0')
episode: 389 training return: tensor(-844.0248, device='cuda:0')
episode: 390 training return: tensor(-840.8706, device='cuda:0')
episode: 391 training return: tensor(-845.7737, device='cuda:0')
epoch: 98 test_true_pfm: 348.8496003656898 sim_pfm: -834.7240690079052
episode: 392 training return: tensor(-841.3226, device='cuda:0')
episode: 393 training return: tensor(-843.0377, device='cuda:0')
episode: 394 training return: tensor(-839.4999, device='cuda:0')
episode: 395 training return: tensor(-835.6563, device='cuda:0')
epoch: 99 test_true_pfm: 348.8506385165611 sim_pfm: -835.0872268599342
episode: 396 training return: tensor(-841.1273, device='cuda:0')
episode: 397 training return: tensor(-843.0311, device='cuda:0')
episode: 398 training return: tensor(-837.9224, device='cuda:0')
episode: 399 training return: tensor(-853.1714, device='cuda:0')
epoch: 100 test_true_pfm: 338.32832666777426 sim_pfm: -837.8439863874033
episode: 400 training return: tensor(-848.1699, device='cuda:0')
episode: 401 training return: tensor(-844.3797, device='cuda:0')
episode: 402 training return: tensor(-846.8545, device='cuda:0')
episode: 403 training return: tensor(-840.2592, device='cuda:0')
epoch: 101 test_true_pfm: 345.3664196946418 sim_pfm: -836.9819641869204
episode: 404 training return: tensor(-839.4810, device='cuda:0')
episode: 405 training return: tensor(-838.9563, device='cuda:0')
episode: 406 training return: tensor(-845.6529, device='cuda:0')
episode: 407 training return: tensor(-842.4367, device='cuda:0')
epoch: 102 test_true_pfm: 344.17334242971924 sim_pfm: -839.7406568285078
episode: 408 training return: tensor(-841.7190, device='cuda:0')
episode: 409 training return: tensor(-846.6561, device='cuda:0')
episode: 410 training return: tensor(-848.8220, device='cuda:0')
episode: 411 training return: tensor(-846.0164, device='cuda:0')
epoch: 103 test_true_pfm: 348.7059613782399 sim_pfm: -835.6267558116427
episode: 412 training return: tensor(-840.7950, device='cuda:0')
episode: 413 training return: tensor(-842.1961, device='cuda:0')
episode: 414 training return: tensor(-845.7221, device='cuda:0')
episode: 415 training return: tensor(-842.1956, device='cuda:0')
epoch: 104 test_true_pfm: 353.1081884674442 sim_pfm: -836.1713521280326
episode: 416 training return: tensor(-846.2864, device='cuda:0')
episode: 417 training return: tensor(-839.5298, device='cuda:0')
episode: 418 training return: tensor(-852.6139, device='cuda:0')
episode: 419 training return: tensor(-842.8431, device='cuda:0')
epoch: 105 test_true_pfm: 342.4508867853959 sim_pfm: -839.2005079311784
episode: 420 training return: tensor(-844.2626, device='cuda:0')
episode: 421 training return: tensor(-839.3386, device='cuda:0')
episode: 422 training return: tensor(-842.7042, device='cuda:0')
episode: 423 training return: tensor(-850.1196, device='cuda:0')
epoch: 106 test_true_pfm: 341.12835443783473 sim_pfm: -841.8693227697319
episode: 424 training return: tensor(-845.4260, device='cuda:0')
episode: 425 training return: tensor(-840.2256, device='cuda:0')
episode: 426 training return: tensor(-847.6711, device='cuda:0')
episode: 427 training return: tensor(-844.0310, device='cuda:0')
epoch: 107 test_true_pfm: 339.2950006201574 sim_pfm: -840.767526157666
episode: 428 training return: tensor(-847.0331, device='cuda:0')
episode: 429 training return: tensor(-845.3513, device='cuda:0')
episode: 430 training return: tensor(-840.4241, device='cuda:0')
episode: 431 training return: tensor(-841.3130, device='cuda:0')
epoch: 108 test_true_pfm: 348.1567498608969 sim_pfm: -837.978066174003
episode: 432 training return: tensor(-845.6015, device='cuda:0')
episode: 433 training return: tensor(-842.8746, device='cuda:0')
episode: 434 training return: tensor(-839.5426, device='cuda:0')
episode: 435 training return: tensor(-838.3859, device='cuda:0')
epoch: 109 test_true_pfm: 344.0292100963799 sim_pfm: -842.2272971198059
episode: 436 training return: tensor(-841.9123, device='cuda:0')
episode: 437 training return: tensor(-844.2992, device='cuda:0')
episode: 438 training return: tensor(-844.9705, device='cuda:0')
episode: 439 training return: tensor(-841.3293, device='cuda:0')
epoch: 110 test_true_pfm: 334.15491144245425 sim_pfm: -842.7896361176972
episode: 440 training return: tensor(-844.9405, device='cuda:0')
episode: 441 training return: tensor(-847.1646, device='cuda:0')
episode: 442 training return: tensor(-841.9780, device='cuda:0')
episode: 443 training return: tensor(-840.1161, device='cuda:0')
epoch: 111 test_true_pfm: 347.3245864637841 sim_pfm: -836.2507519616823
episode: 444 training return: tensor(-848.0628, device='cuda:0')
episode: 445 training return: tensor(-836.1820, device='cuda:0')
episode: 446 training return: tensor(-838.1558, device='cuda:0')
episode: 447 training return: tensor(-840.6002, device='cuda:0')
epoch: 112 test_true_pfm: 344.9011327976985 sim_pfm: -838.2564757136473
episode: 448 training return: tensor(-837.3741, device='cuda:0')
episode: 449 training return: tensor(-846.9379, device='cuda:0')
episode: 450 training return: tensor(-851.3925, device='cuda:0')
episode: 451 training return: tensor(-845.1226, device='cuda:0')
epoch: 113 test_true_pfm: 342.484270566498 sim_pfm: -843.3310881288102
episode: 452 training return: tensor(-847.2264, device='cuda:0')
episode: 453 training return: tensor(-855.6161, device='cuda:0')
episode: 454 training return: tensor(-849.5457, device='cuda:0')
episode: 455 training return: tensor(-840.6453, device='cuda:0')
epoch: 114 test_true_pfm: 345.7992935120831 sim_pfm: -839.1491712721763
episode: 456 training return: tensor(-848.0126, device='cuda:0')
episode: 457 training return: tensor(-841.7697, device='cuda:0')
episode: 458 training return: tensor(-836.6668, device='cuda:0')
episode: 459 training return: tensor(-853.8542, device='cuda:0')
epoch: 115 test_true_pfm: 339.8408486481665 sim_pfm: -843.0830096782689
episode: 460 training return: tensor(-843.4227, device='cuda:0')
episode: 461 training return: tensor(-847.5828, device='cuda:0')
episode: 462 training return: tensor(-844.4138, device='cuda:0')
episode: 463 training return: tensor(-842.6811, device='cuda:0')
epoch: 116 test_true_pfm: 350.2178200442701 sim_pfm: -837.7724932665782
episode: 464 training return: tensor(-845.1078, device='cuda:0')
episode: 465 training return: tensor(-839.3976, device='cuda:0')
episode: 466 training return: tensor(-844.1821, device='cuda:0')
episode: 467 training return: tensor(-850.8470, device='cuda:0')
epoch: 117 test_true_pfm: 337.0606776221682 sim_pfm: -840.8671836528616
episode: 468 training return: tensor(-845.5201, device='cuda:0')
episode: 469 training return: tensor(-845.4438, device='cuda:0')
episode: 470 training return: tensor(-843.0899, device='cuda:0')
episode: 471 training return: tensor(-846.9293, device='cuda:0')
epoch: 118 test_true_pfm: 340.0851878203786 sim_pfm: -840.8016942209409
episode: 472 training return: tensor(-845.4863, device='cuda:0')
episode: 473 training return: tensor(-840.8832, device='cuda:0')
episode: 474 training return: tensor(-840.8480, device='cuda:0')
episode: 475 training return: tensor(-853.6887, device='cuda:0')
epoch: 119 test_true_pfm: 342.5194498702237 sim_pfm: -839.9295976633827
episode: 476 training return: tensor(-845.3171, device='cuda:0')
episode: 477 training return: tensor(-844.5261, device='cuda:0')
episode: 478 training return: tensor(-841.3329, device='cuda:0')
episode: 479 training return: tensor(-841.7448, device='cuda:0')
epoch: 120 test_true_pfm: 346.94358855148135 sim_pfm: -836.0615508536188
episode: 480 training return: tensor(-849.8612, device='cuda:0')
episode: 481 training return: tensor(-841.6270, device='cuda:0')
episode: 482 training return: tensor(-842.6412, device='cuda:0')
episode: 483 training return: tensor(-841.0170, device='cuda:0')
epoch: 121 test_true_pfm: 340.7414677726908 sim_pfm: -843.4480847635617
episode: 484 training return: tensor(-844.8119, device='cuda:0')
episode: 485 training return: tensor(-848.5563, device='cuda:0')
episode: 486 training return: tensor(-842.6537, device='cuda:0')
episode: 487 training return: tensor(-845.6993, device='cuda:0')
epoch: 122 test_true_pfm: 351.22979808304746 sim_pfm: -835.6466393784309
episode: 488 training return: tensor(-842.7308, device='cuda:0')
episode: 489 training return: tensor(-842.1942, device='cuda:0')
episode: 490 training return: tensor(-849.0237, device='cuda:0')
episode: 491 training return: tensor(-840.4166, device='cuda:0')
epoch: 123 test_true_pfm: 337.16558637970394 sim_pfm: -837.0058208432359
episode: 492 training return: tensor(-838.0956, device='cuda:0')
episode: 493 training return: tensor(-843.7974, device='cuda:0')
episode: 494 training return: tensor(-843.9995, device='cuda:0')
episode: 495 training return: tensor(-840.2014, device='cuda:0')
epoch: 124 test_true_pfm: 341.97616803407226 sim_pfm: -839.2649771556607
episode: 496 training return: tensor(-848.4794, device='cuda:0')
episode: 497 training return: tensor(-848.8096, device='cuda:0')
episode: 498 training return: tensor(-838.0074, device='cuda:0')
episode: 499 training return: tensor(-852.0408, device='cuda:0')
epoch: 125 test_true_pfm: 341.11426301055695 sim_pfm: -842.3759300500775
episode: 500 training return: tensor(-843.6525, device='cuda:0')
episode: 501 training return: tensor(-848.4692, device='cuda:0')
episode: 502 training return: tensor(-839.1257, device='cuda:0')
episode: 503 training return: tensor(-848.0016, device='cuda:0')
epoch: 126 test_true_pfm: 342.14287984167 sim_pfm: -841.0385002298281
episode: 504 training return: tensor(-843.1974, device='cuda:0')
episode: 505 training return: tensor(-841.5372, device='cuda:0')
episode: 506 training return: tensor(-842.7126, device='cuda:0')
episode: 507 training return: tensor(-837.1166, device='cuda:0')
epoch: 127 test_true_pfm: 348.86555284523524 sim_pfm: -839.1613808333253
episode: 508 training return: tensor(-838.9111, device='cuda:0')
episode: 509 training return: tensor(-837.9575, device='cuda:0')
episode: 510 training return: tensor(-845.3985, device='cuda:0')
episode: 511 training return: tensor(-839.6982, device='cuda:0')
epoch: 128 test_true_pfm: 338.17566662305353 sim_pfm: -843.6323503829577
episode: 512 training return: tensor(-837.1182, device='cuda:0')
episode: 513 training return: tensor(-852.3614, device='cuda:0')
episode: 514 training return: tensor(-846.1345, device='cuda:0')
episode: 515 training return: tensor(-847.4471, device='cuda:0')
epoch: 129 test_true_pfm: 346.1086740948811 sim_pfm: -841.0790403011875
episode: 516 training return: tensor(-840.0520, device='cuda:0')
episode: 517 training return: tensor(-843.9034, device='cuda:0')
episode: 518 training return: tensor(-854.3419, device='cuda:0')
episode: 519 training return: tensor(-843.9576, device='cuda:0')
epoch: 130 test_true_pfm: 348.3383904485797 sim_pfm: -836.7642087473845
episode: 520 training return: tensor(-838.8173, device='cuda:0')
episode: 521 training return: tensor(-840.0363, device='cuda:0')
episode: 522 training return: tensor(-846.6281, device='cuda:0')
episode: 523 training return: tensor(-840.8503, device='cuda:0')
epoch: 131 test_true_pfm: 347.3234717485248 sim_pfm: -838.2157577998005
episode: 524 training return: tensor(-841.3461, device='cuda:0')
episode: 525 training return: tensor(-848.7140, device='cuda:0')
episode: 526 training return: tensor(-839.2759, device='cuda:0')
episode: 527 training return: tensor(-840.3119, device='cuda:0')
epoch: 132 test_true_pfm: 340.23646981905677 sim_pfm: -841.0175228473576
episode: 528 training return: tensor(-843.7547, device='cuda:0')
episode: 529 training return: tensor(-841.3420, device='cuda:0')
episode: 530 training return: tensor(-848.5966, device='cuda:0')
episode: 531 training return: tensor(-841.3526, device='cuda:0')
epoch: 133 test_true_pfm: 340.7745635602533 sim_pfm: -839.7951525039583
episode: 532 training return: tensor(-839.6841, device='cuda:0')
episode: 533 training return: tensor(-838.0015, device='cuda:0')
episode: 534 training return: tensor(-840.6108, device='cuda:0')
episode: 535 training return: tensor(-845.8563, device='cuda:0')
epoch: 134 test_true_pfm: 343.6674150934626 sim_pfm: -841.1341576780542
episode: 536 training return: tensor(-849.9557, device='cuda:0')
episode: 537 training return: tensor(-842.8470, device='cuda:0')
episode: 538 training return: tensor(-840.0155, device='cuda:0')
episode: 539 training return: tensor(-841.8309, device='cuda:0')
epoch: 135 test_true_pfm: 346.2350889727416 sim_pfm: -837.0760753607998
episode: 540 training return: tensor(-834.2968, device='cuda:0')
episode: 541 training return: tensor(-835.6066, device='cuda:0')
episode: 542 training return: tensor(-839.9464, device='cuda:0')
episode: 543 training return: tensor(-845.3554, device='cuda:0')
epoch: 136 test_true_pfm: 343.35785130567206 sim_pfm: -837.139614792075
episode: 544 training return: tensor(-842.8304, device='cuda:0')
episode: 545 training return: tensor(-840.8083, device='cuda:0')
episode: 546 training return: tensor(-843.8609, device='cuda:0')
episode: 547 training return: tensor(-843.3511, device='cuda:0')
epoch: 137 test_true_pfm: 342.9419520464767 sim_pfm: -839.4840506032924
episode: 548 training return: tensor(-841.7737, device='cuda:0')
episode: 549 training return: tensor(-839.6088, device='cuda:0')
episode: 550 training return: tensor(-837.0276, device='cuda:0')
episode: 551 training return: tensor(-843.6586, device='cuda:0')
epoch: 138 test_true_pfm: 347.554314279812 sim_pfm: -836.0026522395201
episode: 552 training return: tensor(-840.9448, device='cuda:0')
episode: 553 training return: tensor(-841.5409, device='cuda:0')
episode: 554 training return: tensor(-846.7638, device='cuda:0')
episode: 555 training return: tensor(-839.5519, device='cuda:0')
epoch: 139 test_true_pfm: 344.3393689760317 sim_pfm: -833.8471416635439
episode: 556 training return: tensor(-839.1285, device='cuda:0')
episode: 557 training return: tensor(-834.6783, device='cuda:0')
episode: 558 training return: tensor(-843.7837, device='cuda:0')
episode: 559 training return: tensor(-840.2888, device='cuda:0')
epoch: 140 test_true_pfm: 346.7407100072907 sim_pfm: -837.4391637718072
episode: 560 training return: tensor(-844.7625, device='cuda:0')
episode: 561 training return: tensor(-843.0176, device='cuda:0')
episode: 562 training return: tensor(-843.4521, device='cuda:0')
episode: 563 training return: tensor(-849.3913, device='cuda:0')
epoch: 141 test_true_pfm: 337.70779303885257 sim_pfm: -840.1977808756443
episode: 564 training return: tensor(-843.2530, device='cuda:0')
episode: 565 training return: tensor(-842.2767, device='cuda:0')
episode: 566 training return: tensor(-838.1661, device='cuda:0')
episode: 567 training return: tensor(-844.5823, device='cuda:0')
epoch: 142 test_true_pfm: 337.02719518069745 sim_pfm: -842.5617047223108
episode: 568 training return: tensor(-845.3158, device='cuda:0')
episode: 569 training return: tensor(-836.3905, device='cuda:0')
episode: 570 training return: tensor(-835.7317, device='cuda:0')
episode: 571 training return: tensor(-841.9494, device='cuda:0')
epoch: 143 test_true_pfm: 340.2408505626142 sim_pfm: -839.7523236389194
episode: 572 training return: tensor(-840.3713, device='cuda:0')
episode: 573 training return: tensor(-843.0696, device='cuda:0')
episode: 574 training return: tensor(-838.9591, device='cuda:0')
episode: 575 training return: tensor(-837.9391, device='cuda:0')
epoch: 144 test_true_pfm: 349.7085037514237 sim_pfm: -836.0340814024676
episode: 576 training return: tensor(-843.1985, device='cuda:0')
episode: 577 training return: tensor(-844.1595, device='cuda:0')
episode: 578 training return: tensor(-841.1434, device='cuda:0')
episode: 579 training return: tensor(-846.6788, device='cuda:0')
epoch: 145 test_true_pfm: 343.4075294756556 sim_pfm: -840.1869980582075
episode: 580 training return: tensor(-849.3138, device='cuda:0')
episode: 581 training return: tensor(-845.4936, device='cuda:0')
episode: 582 training return: tensor(-844.6983, device='cuda:0')
episode: 583 training return: tensor(-843.3851, device='cuda:0')
epoch: 146 test_true_pfm: 345.0776930186084 sim_pfm: -837.4671142671335
episode: 584 training return: tensor(-839.6223, device='cuda:0')
episode: 585 training return: tensor(-848.8019, device='cuda:0')
episode: 586 training return: tensor(-846.5505, device='cuda:0')
episode: 587 training return: tensor(-839.1309, device='cuda:0')
epoch: 147 test_true_pfm: 336.8556432608677 sim_pfm: -842.6126232090561
episode: 588 training return: tensor(-846.9890, device='cuda:0')
episode: 589 training return: tensor(-838.9128, device='cuda:0')
episode: 590 training return: tensor(-844.5675, device='cuda:0')
episode: 591 training return: tensor(-843.5396, device='cuda:0')
epoch: 148 test_true_pfm: 346.6455019634048 sim_pfm: -835.3611153280557
episode: 592 training return: tensor(-843.3691, device='cuda:0')
episode: 593 training return: tensor(-841.4318, device='cuda:0')
episode: 594 training return: tensor(-849.5921, device='cuda:0')
episode: 595 training return: tensor(-839.1298, device='cuda:0')
epoch: 149 test_true_pfm: 342.4009776939827 sim_pfm: -835.9367340658791
episode: 596 training return: tensor(-838.0939, device='cuda:0')
episode: 597 training return: tensor(-836.6035, device='cuda:0')
episode: 598 training return: tensor(-838.5685, device='cuda:0')
episode: 599 training return: tensor(-839.2451, device='cuda:0')
epoch: 150 test_true_pfm: 344.2627617488422 sim_pfm: -841.2555144149034
