['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '1']
episode: 0 training return: tensor(-377.6504, device='cuda:0')
episode: 1 training return: tensor(-344.0197, device='cuda:0')
episode: 2 training return: tensor(-684.0792, device='cuda:0')
episode: 3 training return: tensor(-183.0686, device='cuda:0')
epoch: 1 test_true_pfm: 186.97993753437785 sim_pfm: -877.1749994770313
episode: 4 training return: tensor(-501.0119, device='cuda:0')
episode: 5 training return: tensor(-701.5925, device='cuda:0')
episode: 6 training return: tensor(-274.6881, device='cuda:0')
episode: 7 training return: tensor(-502.3400, device='cuda:0')
epoch: 2 test_true_pfm: 346.7637607788153 sim_pfm: -737.7382747985733
episode: 8 training return: tensor(-425.9434, device='cuda:0')
episode: 9 training return: tensor(-426.1454, device='cuda:0')
episode: 10 training return: tensor(-441.5354, device='cuda:0')
episode: 11 training return: tensor(-768.3952, device='cuda:0')
epoch: 3 test_true_pfm: 197.98015400182763 sim_pfm: -824.4473848291673
episode: 12 training return: tensor(-715.3655, device='cuda:0')
episode: 13 training return: tensor(-726.0149, device='cuda:0')
episode: 14 training return: tensor(-597.6285, device='cuda:0')
episode: 15 training return: tensor(-19.7228, device='cuda:0')
epoch: 4 test_true_pfm: 21.26221225977966 sim_pfm: -441.1725139169721
episode: 16 training return: tensor(-231.1348, device='cuda:0')
episode: 17 training return: tensor(-225.3404, device='cuda:0')
episode: 18 training return: tensor(-570.5297, device='cuda:0')
episode: 19 training return: tensor(-63.0730, device='cuda:0')
epoch: 5 test_true_pfm: 68.12292527115036 sim_pfm: -603.8276094474519
episode: 20 training return: tensor(-574.8246, device='cuda:0')
episode: 21 training return: tensor(-476.5043, device='cuda:0')
episode: 22 training return: tensor(-434.4256, device='cuda:0')
episode: 23 training return: tensor(-365.5122, device='cuda:0')
epoch: 6 test_true_pfm: -141.5267095544697 sim_pfm: -499.8411029743341
episode: 24 training return: tensor(-492.4655, device='cuda:0')
episode: 25 training return: tensor(-474.0178, device='cuda:0')
episode: 26 training return: tensor(-550.3589, device='cuda:0')
episode: 27 training return: tensor(-540.7453, device='cuda:0')
epoch: 7 test_true_pfm: -26.895370324011235 sim_pfm: -287.6507179039957
episode: 28 training return: tensor(-511.7809, device='cuda:0')
episode: 29 training return: tensor(-482.1240, device='cuda:0')
episode: 30 training return: tensor(-488.9001, device='cuda:0')
episode: 31 training return: tensor(-465.9010, device='cuda:0')
epoch: 8 test_true_pfm: -31.868902322095376 sim_pfm: -438.31676399707794
episode: 32 training return: tensor(-513.0362, device='cuda:0')
episode: 33 training return: tensor(-581.3352, device='cuda:0')
episode: 34 training return: tensor(-675.4570, device='cuda:0')
episode: 35 training return: tensor(-719.5472, device='cuda:0')
epoch: 9 test_true_pfm: 222.7230533618321 sim_pfm: -763.7110091588305
episode: 36 training return: tensor(-715.1928, device='cuda:0')
episode: 37 training return: tensor(-753.3477, device='cuda:0')
episode: 38 training return: tensor(-748.2063, device='cuda:0')
episode: 39 training return: tensor(-645.0303, device='cuda:0')
epoch: 10 test_true_pfm: 303.0386915782185 sim_pfm: -735.8679872983388
episode: 40 training return: tensor(-572.0556, device='cuda:0')
episode: 41 training return: tensor(-543.4790, device='cuda:0')
episode: 42 training return: tensor(-510.6001, device='cuda:0')
episode: 43 training return: tensor(-513.8218, device='cuda:0')
epoch: 11 test_true_pfm: 266.80814152074146 sim_pfm: -490.7385564471285
episode: 44 training return: tensor(-523.1013, device='cuda:0')
episode: 45 training return: tensor(-577.6857, device='cuda:0')
episode: 46 training return: tensor(-564.5145, device='cuda:0')
episode: 47 training return: tensor(-591.3840, device='cuda:0')
epoch: 12 test_true_pfm: 283.1360754276762 sim_pfm: -512.324659854387
episode: 48 training return: tensor(-532.3310, device='cuda:0')
episode: 49 training return: tensor(-495.5439, device='cuda:0')
episode: 50 training return: tensor(-547.6176, device='cuda:0')
episode: 51 training return: tensor(-533.8892, device='cuda:0')
epoch: 13 test_true_pfm: 225.0517113691336 sim_pfm: -504.1031030997013
episode: 52 training return: tensor(-540.7910, device='cuda:0')
episode: 53 training return: tensor(-546.3100, device='cuda:0')
episode: 54 training return: tensor(-523.0111, device='cuda:0')
episode: 55 training return: tensor(-499.6142, device='cuda:0')
epoch: 14 test_true_pfm: 192.29869203653269 sim_pfm: -467.91066988402355
episode: 56 training return: tensor(-522.0987, device='cuda:0')
episode: 57 training return: tensor(-523.3753, device='cuda:0')
episode: 58 training return: tensor(-506.2334, device='cuda:0')
episode: 59 training return: tensor(-509.7433, device='cuda:0')
epoch: 15 test_true_pfm: 256.6716647275352 sim_pfm: -458.0298317341367
episode: 60 training return: tensor(-526.9352, device='cuda:0')
episode: 61 training return: tensor(-511.4820, device='cuda:0')
episode: 62 training return: tensor(-486.3981, device='cuda:0')
episode: 63 training return: tensor(-492.7138, device='cuda:0')
epoch: 16 test_true_pfm: 275.394775367751 sim_pfm: -414.9609521854824
episode: 64 training return: tensor(-490.0457, device='cuda:0')
episode: 65 training return: tensor(-721.6272, device='cuda:0')
episode: 66 training return: tensor(-749.2335, device='cuda:0')
episode: 67 training return: tensor(-748.2634, device='cuda:0')
epoch: 17 test_true_pfm: 261.52571049793227 sim_pfm: -423.2908859947153
episode: 68 training return: tensor(-463.2671, device='cuda:0')
episode: 69 training return: tensor(-479.5450, device='cuda:0')
episode: 70 training return: tensor(-476.7277, device='cuda:0')
episode: 71 training return: tensor(-495.3604, device='cuda:0')
epoch: 18 test_true_pfm: 277.4007662015781 sim_pfm: -418.30748736633296
episode: 72 training return: tensor(-477.6028, device='cuda:0')
episode: 73 training return: tensor(-475.1462, device='cuda:0')
episode: 74 training return: tensor(-478.9853, device='cuda:0')
episode: 75 training return: tensor(-482.6078, device='cuda:0')
epoch: 19 test_true_pfm: 283.16462012100015 sim_pfm: -419.5980650125227
episode: 76 training return: tensor(-476.6742, device='cuda:0')
episode: 77 training return: tensor(-482.3563, device='cuda:0')
episode: 78 training return: tensor(-481.3709, device='cuda:0')
episode: 79 training return: tensor(-465.2219, device='cuda:0')
epoch: 20 test_true_pfm: 277.4369304962599 sim_pfm: -413.0612773204145
episode: 80 training return: tensor(-463.7454, device='cuda:0')
episode: 81 training return: tensor(-468.2466, device='cuda:0')
episode: 82 training return: tensor(-459.4056, device='cuda:0')
episode: 83 training return: tensor(-490.5759, device='cuda:0')
epoch: 21 test_true_pfm: 250.7330691057739 sim_pfm: -420.87006065746147
episode: 84 training return: tensor(-480.4238, device='cuda:0')
episode: 85 training return: tensor(-463.9231, device='cuda:0')
episode: 86 training return: tensor(-463.7663, device='cuda:0')
episode: 87 training return: tensor(-450.4281, device='cuda:0')
epoch: 22 test_true_pfm: 267.6719472160457 sim_pfm: -412.6248083358514
episode: 88 training return: tensor(-471.4742, device='cuda:0')
episode: 89 training return: tensor(-465.8936, device='cuda:0')
episode: 90 training return: tensor(-473.2441, device='cuda:0')
episode: 91 training return: tensor(-460.1755, device='cuda:0')
epoch: 23 test_true_pfm: 278.4573024882099 sim_pfm: -416.6638678019711
episode: 92 training return: tensor(-453.7912, device='cuda:0')
episode: 93 training return: tensor(-460.8840, device='cuda:0')
episode: 94 training return: tensor(-462.6800, device='cuda:0')
episode: 95 training return: tensor(-448.8459, device='cuda:0')
epoch: 24 test_true_pfm: 264.7389345151521 sim_pfm: -425.20938017452136
episode: 96 training return: tensor(-445.2401, device='cuda:0')
episode: 97 training return: tensor(-470.3928, device='cuda:0')
episode: 98 training return: tensor(-461.8802, device='cuda:0')
episode: 99 training return: tensor(-471.2933, device='cuda:0')
epoch: 25 test_true_pfm: 277.41088459769304 sim_pfm: -426.2231487648872
episode: 100 training return: tensor(-461.7675, device='cuda:0')
episode: 101 training return: tensor(-473.3230, device='cuda:0')
episode: 102 training return: tensor(-456.7281, device='cuda:0')
episode: 103 training return: tensor(-464.9008, device='cuda:0')
epoch: 26 test_true_pfm: 283.3761795776201 sim_pfm: -412.1505445222526
episode: 104 training return: tensor(-463.0599, device='cuda:0')
episode: 105 training return: tensor(-461.8112, device='cuda:0')
episode: 106 training return: tensor(-448.5471, device='cuda:0')
episode: 107 training return: tensor(-453.6524, device='cuda:0')
epoch: 27 test_true_pfm: 296.0152084649963 sim_pfm: -425.8235056413493
episode: 108 training return: tensor(-468.8679, device='cuda:0')
episode: 109 training return: tensor(-446.4327, device='cuda:0')
episode: 110 training return: tensor(-461.6119, device='cuda:0')
episode: 111 training return: tensor(-452.9613, device='cuda:0')
epoch: 28 test_true_pfm: 305.02162633774714 sim_pfm: -399.18411542890436
episode: 112 training return: tensor(-458.0659, device='cuda:0')
episode: 113 training return: tensor(-471.5844, device='cuda:0')
episode: 114 training return: tensor(-452.1675, device='cuda:0')
episode: 115 training return: tensor(-461.9029, device='cuda:0')
epoch: 29 test_true_pfm: 323.4176208468601 sim_pfm: -396.3989974245972
episode: 116 training return: tensor(-456.9832, device='cuda:0')
episode: 117 training return: tensor(-466.6865, device='cuda:0')
episode: 118 training return: tensor(-454.2166, device='cuda:0')
episode: 119 training return: tensor(-463.0042, device='cuda:0')
epoch: 30 test_true_pfm: 286.1784430377614 sim_pfm: -417.6687770119558
episode: 120 training return: tensor(-474.0578, device='cuda:0')
episode: 121 training return: tensor(-454.7769, device='cuda:0')
episode: 122 training return: tensor(-435.5651, device='cuda:0')
episode: 123 training return: tensor(-468.1794, device='cuda:0')
epoch: 31 test_true_pfm: 278.4756211689285 sim_pfm: -417.0169966899169
episode: 124 training return: tensor(-463.2335, device='cuda:0')
episode: 125 training return: tensor(-454.9030, device='cuda:0')
episode: 126 training return: tensor(-454.4218, device='cuda:0')
episode: 127 training return: tensor(-453.7664, device='cuda:0')
epoch: 32 test_true_pfm: 290.05912994118967 sim_pfm: -419.1984191293207
episode: 128 training return: tensor(-475.1842, device='cuda:0')
episode: 129 training return: tensor(-459.0989, device='cuda:0')
episode: 130 training return: tensor(-446.3087, device='cuda:0')
episode: 131 training return: tensor(-440.0344, device='cuda:0')
epoch: 33 test_true_pfm: 317.4082457491152 sim_pfm: -399.7353098151895
episode: 132 training return: tensor(-465.0111, device='cuda:0')
episode: 133 training return: tensor(-453.4264, device='cuda:0')
episode: 134 training return: tensor(-444.0313, device='cuda:0')
episode: 135 training return: tensor(-455.2988, device='cuda:0')
epoch: 34 test_true_pfm: 301.50494708384076 sim_pfm: -413.64497911084135
episode: 136 training return: tensor(-454.6565, device='cuda:0')
episode: 137 training return: tensor(-432.6601, device='cuda:0')
episode: 138 training return: tensor(-447.7194, device='cuda:0')
episode: 139 training return: tensor(-461.5223, device='cuda:0')
epoch: 35 test_true_pfm: 346.59689623022024 sim_pfm: -393.9967056089081
episode: 140 training return: tensor(-443.8990, device='cuda:0')
episode: 141 training return: tensor(-445.9020, device='cuda:0')
episode: 142 training return: tensor(-455.2873, device='cuda:0')
episode: 143 training return: tensor(-455.1602, device='cuda:0')
epoch: 36 test_true_pfm: 332.8445867937253 sim_pfm: -395.94052102397353
episode: 144 training return: tensor(-460.2805, device='cuda:0')
episode: 145 training return: tensor(-451.6472, device='cuda:0')
episode: 146 training return: tensor(-470.3558, device='cuda:0')
episode: 147 training return: tensor(-456.1097, device='cuda:0')
epoch: 37 test_true_pfm: 303.0287784793934 sim_pfm: -408.55480872808647
episode: 148 training return: tensor(-454.2560, device='cuda:0')
episode: 149 training return: tensor(-455.7542, device='cuda:0')
episode: 150 training return: tensor(-454.2855, device='cuda:0')
episode: 151 training return: tensor(-472.5457, device='cuda:0')
epoch: 38 test_true_pfm: 289.87856795510885 sim_pfm: -417.89070195068297
episode: 152 training return: tensor(-460.2517, device='cuda:0')
episode: 153 training return: tensor(-442.5464, device='cuda:0')
episode: 154 training return: tensor(-465.6685, device='cuda:0')
episode: 155 training return: tensor(-450.3601, device='cuda:0')
epoch: 39 test_true_pfm: 286.60120308691984 sim_pfm: -401.8081570050369
episode: 156 training return: tensor(-462.6481, device='cuda:0')
episode: 157 training return: tensor(-459.8076, device='cuda:0')
episode: 158 training return: tensor(-456.3532, device='cuda:0')
episode: 159 training return: tensor(-448.8221, device='cuda:0')
epoch: 40 test_true_pfm: 342.5118110478632 sim_pfm: -393.60043165887083
episode: 160 training return: tensor(-453.1625, device='cuda:0')
episode: 161 training return: tensor(-462.3136, device='cuda:0')
episode: 162 training return: tensor(-469.5769, device='cuda:0')
episode: 163 training return: tensor(-451.4167, device='cuda:0')
epoch: 41 test_true_pfm: 318.3927473512793 sim_pfm: -401.9557967471774
episode: 164 training return: tensor(-450.3700, device='cuda:0')
episode: 165 training return: tensor(-455.2292, device='cuda:0')
episode: 166 training return: tensor(-438.8622, device='cuda:0')
episode: 167 training return: tensor(-449.4841, device='cuda:0')
epoch: 42 test_true_pfm: 327.05170202273064 sim_pfm: -406.4675744151852
episode: 168 training return: tensor(-450.4015, device='cuda:0')
episode: 169 training return: tensor(-449.8267, device='cuda:0')
episode: 170 training return: tensor(-455.5617, device='cuda:0')
episode: 171 training return: tensor(-458.7681, device='cuda:0')
epoch: 43 test_true_pfm: 297.52587962504253 sim_pfm: -401.75330743775703
episode: 172 training return: tensor(-450.7520, device='cuda:0')
episode: 173 training return: tensor(-466.6446, device='cuda:0')
episode: 174 training return: tensor(-450.6328, device='cuda:0')
episode: 175 training return: tensor(-445.9462, device='cuda:0')
epoch: 44 test_true_pfm: 279.7077890274884 sim_pfm: -425.07279676074785
episode: 176 training return: tensor(-445.0409, device='cuda:0')
episode: 177 training return: tensor(-458.7420, device='cuda:0')
episode: 178 training return: tensor(-452.1126, device='cuda:0')
episode: 179 training return: tensor(-454.5825, device='cuda:0')
epoch: 45 test_true_pfm: 313.4314923683069 sim_pfm: -409.52107736177277
episode: 180 training return: tensor(-435.3055, device='cuda:0')
episode: 181 training return: tensor(-458.1725, device='cuda:0')
episode: 182 training return: tensor(-452.8293, device='cuda:0')
episode: 183 training return: tensor(-444.5951, device='cuda:0')
epoch: 46 test_true_pfm: 301.135162170616 sim_pfm: -410.95837618395063
episode: 184 training return: tensor(-450.2308, device='cuda:0')
episode: 185 training return: tensor(-450.4969, device='cuda:0')
episode: 186 training return: tensor(-443.1019, device='cuda:0')
episode: 187 training return: tensor(-463.9633, device='cuda:0')
epoch: 47 test_true_pfm: 355.61831023230496 sim_pfm: -388.33198270616896
episode: 188 training return: tensor(-436.4663, device='cuda:0')
episode: 189 training return: tensor(-434.8351, device='cuda:0')
episode: 190 training return: tensor(-448.4635, device='cuda:0')
episode: 191 training return: tensor(-439.3844, device='cuda:0')
epoch: 48 test_true_pfm: 296.87069444910435 sim_pfm: -408.39816654628765
episode: 192 training return: tensor(-450.9907, device='cuda:0')
episode: 193 training return: tensor(-444.7222, device='cuda:0')
episode: 194 training return: tensor(-434.8444, device='cuda:0')
episode: 195 training return: tensor(-451.7580, device='cuda:0')
epoch: 49 test_true_pfm: 312.1037190505411 sim_pfm: -402.7435490619391
episode: 196 training return: tensor(-447.8257, device='cuda:0')
episode: 197 training return: tensor(-434.1112, device='cuda:0')
episode: 198 training return: tensor(-449.3896, device='cuda:0')
episode: 199 training return: tensor(-427.7684, device='cuda:0')
epoch: 50 test_true_pfm: 317.61348381296654 sim_pfm: -407.25614063503843
episode: 200 training return: tensor(-451.8603, device='cuda:0')
episode: 201 training return: tensor(-438.7613, device='cuda:0')
episode: 202 training return: tensor(-449.7976, device='cuda:0')
episode: 203 training return: tensor(-447.6801, device='cuda:0')
epoch: 51 test_true_pfm: 339.10209264046745 sim_pfm: -390.93775327076827
episode: 204 training return: tensor(-445.3624, device='cuda:0')
episode: 205 training return: tensor(-448.9178, device='cuda:0')
episode: 206 training return: tensor(-446.3765, device='cuda:0')
episode: 207 training return: tensor(-451.8692, device='cuda:0')
epoch: 52 test_true_pfm: 338.4616366384002 sim_pfm: -394.1212810069167
episode: 208 training return: tensor(-440.0168, device='cuda:0')
episode: 209 training return: tensor(-436.2083, device='cuda:0')
episode: 210 training return: tensor(-444.9184, device='cuda:0')
episode: 211 training return: tensor(-437.2348, device='cuda:0')
epoch: 53 test_true_pfm: 350.1423221782176 sim_pfm: -387.1788399872991
episode: 212 training return: tensor(-460.4437, device='cuda:0')
episode: 213 training return: tensor(-438.5278, device='cuda:0')
episode: 214 training return: tensor(-431.4432, device='cuda:0')
episode: 215 training return: tensor(-427.6521, device='cuda:0')
epoch: 54 test_true_pfm: 345.39206116712813 sim_pfm: -406.31442424323177
episode: 216 training return: tensor(-444.8388, device='cuda:0')
episode: 217 training return: tensor(-437.5406, device='cuda:0')
episode: 218 training return: tensor(-453.9301, device='cuda:0')
episode: 219 training return: tensor(-449.3585, device='cuda:0')
epoch: 55 test_true_pfm: 315.05564925068916 sim_pfm: -399.32383881047525
episode: 220 training return: tensor(-434.4661, device='cuda:0')
episode: 221 training return: tensor(-457.2355, device='cuda:0')
episode: 222 training return: tensor(-441.6312, device='cuda:0')
episode: 223 training return: tensor(-430.8800, device='cuda:0')
epoch: 56 test_true_pfm: 336.54746938106433 sim_pfm: -391.2335978084399
episode: 224 training return: tensor(-454.0132, device='cuda:0')
episode: 225 training return: tensor(-440.9857, device='cuda:0')
episode: 226 training return: tensor(-457.8758, device='cuda:0')
episode: 227 training return: tensor(-448.1255, device='cuda:0')
epoch: 57 test_true_pfm: 360.00371088433366 sim_pfm: -384.39044912493165
episode: 228 training return: tensor(-437.5905, device='cuda:0')
episode: 229 training return: tensor(-453.1694, device='cuda:0')
episode: 230 training return: tensor(-444.2894, device='cuda:0')
episode: 231 training return: tensor(-450.3948, device='cuda:0')
epoch: 58 test_true_pfm: 360.4882871960064 sim_pfm: -383.867917887168
episode: 232 training return: tensor(-438.5304, device='cuda:0')
episode: 233 training return: tensor(-446.2044, device='cuda:0')
episode: 234 training return: tensor(-440.4885, device='cuda:0')
episode: 235 training return: tensor(-437.5626, device='cuda:0')
epoch: 59 test_true_pfm: 323.0332862135028 sim_pfm: -394.61981510991853
episode: 236 training return: tensor(-442.7005, device='cuda:0')
episode: 237 training return: tensor(-432.1469, device='cuda:0')
episode: 238 training return: tensor(-444.9144, device='cuda:0')
episode: 239 training return: tensor(-447.7036, device='cuda:0')
epoch: 60 test_true_pfm: 356.7365169888553 sim_pfm: -390.09683120033395
episode: 240 training return: tensor(-433.6283, device='cuda:0')
episode: 241 training return: tensor(-432.7625, device='cuda:0')
episode: 242 training return: tensor(-455.2878, device='cuda:0')
episode: 243 training return: tensor(-435.4265, device='cuda:0')
epoch: 61 test_true_pfm: 365.43655131560143 sim_pfm: -378.562112170582
episode: 244 training return: tensor(-447.0772, device='cuda:0')
episode: 245 training return: tensor(-433.4484, device='cuda:0')
episode: 246 training return: tensor(-431.1568, device='cuda:0')
episode: 247 training return: tensor(-443.8658, device='cuda:0')
epoch: 62 test_true_pfm: 351.1193250943147 sim_pfm: -388.2997061173276
episode: 248 training return: tensor(-446.0850, device='cuda:0')
episode: 249 training return: tensor(-421.8694, device='cuda:0')
episode: 250 training return: tensor(-434.2930, device='cuda:0')
episode: 251 training return: tensor(-439.7661, device='cuda:0')
epoch: 63 test_true_pfm: 369.4630643267157 sim_pfm: -377.255847225897
episode: 252 training return: tensor(-440.5594, device='cuda:0')
episode: 253 training return: tensor(-435.4908, device='cuda:0')
episode: 254 training return: tensor(-437.5967, device='cuda:0')
episode: 255 training return: tensor(-454.3708, device='cuda:0')
epoch: 64 test_true_pfm: 362.76035492915724 sim_pfm: -382.04329408099875
episode: 256 training return: tensor(-439.0690, device='cuda:0')
episode: 257 training return: tensor(-435.4533, device='cuda:0')
episode: 258 training return: tensor(-458.5095, device='cuda:0')
episode: 259 training return: tensor(-442.2592, device='cuda:0')
epoch: 65 test_true_pfm: 371.5845971614979 sim_pfm: -378.433573934366
episode: 260 training return: tensor(-438.8878, device='cuda:0')
episode: 261 training return: tensor(-433.6245, device='cuda:0')
episode: 262 training return: tensor(-442.7163, device='cuda:0')
episode: 263 training return: tensor(-433.8631, device='cuda:0')
epoch: 66 test_true_pfm: 342.5455216681778 sim_pfm: -390.39298770735815
episode: 264 training return: tensor(-437.4832, device='cuda:0')
episode: 265 training return: tensor(-421.3504, device='cuda:0')
episode: 266 training return: tensor(-431.9958, device='cuda:0')
episode: 267 training return: tensor(-438.6716, device='cuda:0')
epoch: 67 test_true_pfm: 351.5821643030394 sim_pfm: -392.6716749453141
episode: 268 training return: tensor(-445.7723, device='cuda:0')
episode: 269 training return: tensor(-438.5274, device='cuda:0')
episode: 270 training return: tensor(-437.5672, device='cuda:0')
episode: 271 training return: tensor(-438.2944, device='cuda:0')
epoch: 68 test_true_pfm: 385.70564571925394 sim_pfm: -370.0864108800112
episode: 272 training return: tensor(-426.1613, device='cuda:0')
episode: 273 training return: tensor(-445.7601, device='cuda:0')
episode: 274 training return: tensor(-435.4881, device='cuda:0')
episode: 275 training return: tensor(-419.5633, device='cuda:0')
epoch: 69 test_true_pfm: 369.40573843760757 sim_pfm: -382.33315496515326
episode: 276 training return: tensor(-425.6075, device='cuda:0')
episode: 277 training return: tensor(-436.7128, device='cuda:0')
episode: 278 training return: tensor(-437.1220, device='cuda:0')
episode: 279 training return: tensor(-431.5425, device='cuda:0')
epoch: 70 test_true_pfm: 345.3653635190354 sim_pfm: -395.6104439859434
episode: 280 training return: tensor(-441.0964, device='cuda:0')
episode: 281 training return: tensor(-425.8633, device='cuda:0')
episode: 282 training return: tensor(-414.6010, device='cuda:0')
episode: 283 training return: tensor(-423.9644, device='cuda:0')
epoch: 71 test_true_pfm: 394.4531676861246 sim_pfm: -369.45427939202636
episode: 284 training return: tensor(-417.3150, device='cuda:0')
episode: 285 training return: tensor(-426.4948, device='cuda:0')
episode: 286 training return: tensor(-427.9145, device='cuda:0')
episode: 287 training return: tensor(-418.4791, device='cuda:0')
epoch: 72 test_true_pfm: 394.5025496097789 sim_pfm: -369.02541725873016
episode: 288 training return: tensor(-424.5657, device='cuda:0')
episode: 289 training return: tensor(-435.5363, device='cuda:0')
episode: 290 training return: tensor(-438.6573, device='cuda:0')
episode: 291 training return: tensor(-434.2698, device='cuda:0')
epoch: 73 test_true_pfm: 363.9285387448117 sim_pfm: -372.72620818779495
episode: 292 training return: tensor(-410.5013, device='cuda:0')
episode: 293 training return: tensor(-416.9301, device='cuda:0')
episode: 294 training return: tensor(-443.6111, device='cuda:0')
episode: 295 training return: tensor(-423.2607, device='cuda:0')
epoch: 74 test_true_pfm: 390.7644991656566 sim_pfm: -376.6093699404349
episode: 296 training return: tensor(-449.1969, device='cuda:0')
episode: 297 training return: tensor(-454.5953, device='cuda:0')
episode: 298 training return: tensor(-435.1516, device='cuda:0')
episode: 299 training return: tensor(-419.0797, device='cuda:0')
epoch: 75 test_true_pfm: 382.69112457934096 sim_pfm: -379.9053190379248
episode: 300 training return: tensor(-422.4521, device='cuda:0')
episode: 301 training return: tensor(-409.1560, device='cuda:0')
episode: 302 training return: tensor(-417.9413, device='cuda:0')
episode: 303 training return: tensor(-430.8051, device='cuda:0')
epoch: 76 test_true_pfm: 414.9741522777479 sim_pfm: -365.72025120042963
episode: 304 training return: tensor(-443.4078, device='cuda:0')
episode: 305 training return: tensor(-420.7692, device='cuda:0')
episode: 306 training return: tensor(-423.0948, device='cuda:0')
episode: 307 training return: tensor(-434.5170, device='cuda:0')
epoch: 77 test_true_pfm: 375.5233876727852 sim_pfm: -375.43320177549805
episode: 308 training return: tensor(-418.7512, device='cuda:0')
episode: 309 training return: tensor(-425.7384, device='cuda:0')
episode: 310 training return: tensor(-428.1337, device='cuda:0')
episode: 311 training return: tensor(-437.8186, device='cuda:0')
epoch: 78 test_true_pfm: 373.59918952416893 sim_pfm: -384.3505084781985
episode: 312 training return: tensor(-424.6920, device='cuda:0')
episode: 313 training return: tensor(-415.0034, device='cuda:0')
episode: 314 training return: tensor(-421.0633, device='cuda:0')
episode: 315 training return: tensor(-413.7796, device='cuda:0')
epoch: 79 test_true_pfm: 362.0731883086601 sim_pfm: -378.985390400708
episode: 316 training return: tensor(-430.4615, device='cuda:0')
episode: 317 training return: tensor(-421.0854, device='cuda:0')
episode: 318 training return: tensor(-415.2845, device='cuda:0')
episode: 319 training return: tensor(-431.6022, device='cuda:0')
epoch: 80 test_true_pfm: 410.5842625557873 sim_pfm: -364.5652248654903
episode: 320 training return: tensor(-434.1879, device='cuda:0')
episode: 321 training return: tensor(-436.3971, device='cuda:0')
episode: 322 training return: tensor(-421.6029, device='cuda:0')
episode: 323 training return: tensor(-450.9839, device='cuda:0')
epoch: 81 test_true_pfm: 356.381199987964 sim_pfm: -383.07806870465475
episode: 324 training return: tensor(-421.0911, device='cuda:0')
episode: 325 training return: tensor(-444.0280, device='cuda:0')
episode: 326 training return: tensor(-415.2991, device='cuda:0')
episode: 327 training return: tensor(-435.1427, device='cuda:0')
epoch: 82 test_true_pfm: 379.8465153630189 sim_pfm: -369.24212307319976
episode: 328 training return: tensor(-415.6462, device='cuda:0')
episode: 329 training return: tensor(-442.9208, device='cuda:0')
episode: 330 training return: tensor(-416.0311, device='cuda:0')
episode: 331 training return: tensor(-420.9050, device='cuda:0')
epoch: 83 test_true_pfm: 351.6012978771082 sim_pfm: -384.76217404314474
episode: 332 training return: tensor(-409.5950, device='cuda:0')
episode: 333 training return: tensor(-424.2049, device='cuda:0')
episode: 334 training return: tensor(-408.4516, device='cuda:0')
episode: 335 training return: tensor(-428.4136, device='cuda:0')
epoch: 84 test_true_pfm: 420.5887663652074 sim_pfm: -366.38709119256237
episode: 336 training return: tensor(-435.9256, device='cuda:0')
episode: 337 training return: tensor(-418.3385, device='cuda:0')
episode: 338 training return: tensor(-419.3537, device='cuda:0')
episode: 339 training return: tensor(-414.4649, device='cuda:0')
epoch: 85 test_true_pfm: 370.70895908466235 sim_pfm: -385.34346158111777
episode: 340 training return: tensor(-420.9010, device='cuda:0')
episode: 341 training return: tensor(-418.3570, device='cuda:0')
episode: 342 training return: tensor(-408.5129, device='cuda:0')
episode: 343 training return: tensor(-427.9431, device='cuda:0')
epoch: 86 test_true_pfm: 379.1329292929806 sim_pfm: -369.82964663766325
episode: 344 training return: tensor(-408.0630, device='cuda:0')
episode: 345 training return: tensor(-454.4853, device='cuda:0')
episode: 346 training return: tensor(-406.8629, device='cuda:0')
episode: 347 training return: tensor(-423.2334, device='cuda:0')
epoch: 87 test_true_pfm: 385.93930697233037 sim_pfm: -367.76493711142876
episode: 348 training return: tensor(-427.9955, device='cuda:0')
episode: 349 training return: tensor(-424.3301, device='cuda:0')
episode: 350 training return: tensor(-403.6289, device='cuda:0')
episode: 351 training return: tensor(-424.7850, device='cuda:0')
epoch: 88 test_true_pfm: 344.90744154890416 sim_pfm: -385.08921672803507
episode: 352 training return: tensor(-425.5932, device='cuda:0')
episode: 353 training return: tensor(-412.5272, device='cuda:0')
episode: 354 training return: tensor(-425.9569, device='cuda:0')
episode: 355 training return: tensor(-403.1570, device='cuda:0')
epoch: 89 test_true_pfm: 380.3729790336186 sim_pfm: -372.77164125970256
episode: 356 training return: tensor(-417.5948, device='cuda:0')
episode: 357 training return: tensor(-432.4227, device='cuda:0')
episode: 358 training return: tensor(-416.3319, device='cuda:0')
episode: 359 training return: tensor(-424.3220, device='cuda:0')
epoch: 90 test_true_pfm: 384.42375402366815 sim_pfm: -371.6858123477238
episode: 360 training return: tensor(-412.6916, device='cuda:0')
episode: 361 training return: tensor(-374.3838, device='cuda:0')
episode: 362 training return: tensor(-409.6523, device='cuda:0')
episode: 363 training return: tensor(-411.6152, device='cuda:0')
epoch: 91 test_true_pfm: 344.0636640784442 sim_pfm: -379.17224075629684
episode: 364 training return: tensor(-428.3632, device='cuda:0')
episode: 365 training return: tensor(-412.5056, device='cuda:0')
episode: 366 training return: tensor(-410.0975, device='cuda:0')
episode: 367 training return: tensor(-394.8053, device='cuda:0')
epoch: 92 test_true_pfm: 340.0016352199655 sim_pfm: -387.86000903170014
episode: 368 training return: tensor(-425.6272, device='cuda:0')
episode: 369 training return: tensor(-397.7825, device='cuda:0')
episode: 370 training return: tensor(-416.3835, device='cuda:0')
episode: 371 training return: tensor(-400.3259, device='cuda:0')
epoch: 93 test_true_pfm: 450.1382231046368 sim_pfm: -356.6748219621756
episode: 372 training return: tensor(-447.3068, device='cuda:0')
episode: 373 training return: tensor(-435.9809, device='cuda:0')
episode: 374 training return: tensor(-423.1421, device='cuda:0')
episode: 375 training return: tensor(-400.1440, device='cuda:0')
epoch: 94 test_true_pfm: 469.82523978263544 sim_pfm: -346.0062249558978
episode: 376 training return: tensor(-397.3122, device='cuda:0')
episode: 377 training return: tensor(-382.7386, device='cuda:0')
episode: 378 training return: tensor(-408.6794, device='cuda:0')
episode: 379 training return: tensor(-354.6976, device='cuda:0')
epoch: 95 test_true_pfm: 1110.3799737148854 sim_pfm: -183.53741260889606
episode: 380 training return: tensor(-383.4083, device='cuda:0')
episode: 381 training return: tensor(-387.0687, device='cuda:0')
episode: 382 training return: tensor(-306.7256, device='cuda:0')
episode: 383 training return: tensor(-436.3414, device='cuda:0')
epoch: 96 test_true_pfm: 380.3409631183674 sim_pfm: -367.7210995174634
episode: 384 training return: tensor(-416.5339, device='cuda:0')
episode: 385 training return: tensor(-381.8945, device='cuda:0')
episode: 386 training return: tensor(-363.0897, device='cuda:0')
episode: 387 training return: tensor(-427.2434, device='cuda:0')
epoch: 97 test_true_pfm: 361.93164687089444 sim_pfm: -371.49654338186764
episode: 388 training return: tensor(-436.6812, device='cuda:0')
episode: 389 training return: tensor(-427.2656, device='cuda:0')
episode: 390 training return: tensor(-379.1409, device='cuda:0')
episode: 391 training return: tensor(-427.3593, device='cuda:0')
epoch: 98 test_true_pfm: 423.74164562491137 sim_pfm: -369.1608557033275
episode: 392 training return: tensor(-416.7128, device='cuda:0')
episode: 393 training return: tensor(-424.4167, device='cuda:0')
episode: 394 training return: tensor(-412.2074, device='cuda:0')
episode: 395 training return: tensor(-393.5749, device='cuda:0')
epoch: 99 test_true_pfm: 396.0663681403705 sim_pfm: -367.65731326971826
episode: 396 training return: tensor(-375.1252, device='cuda:0')
episode: 397 training return: tensor(-402.3943, device='cuda:0')
episode: 398 training return: tensor(-427.8796, device='cuda:0')
episode: 399 training return: tensor(-419.9134, device='cuda:0')
epoch: 100 test_true_pfm: 395.6350130448529 sim_pfm: -361.2513992962583
episode: 400 training return: tensor(-410.4407, device='cuda:0')
episode: 401 training return: tensor(-369.0866, device='cuda:0')
episode: 402 training return: tensor(-419.6326, device='cuda:0')
episode: 403 training return: tensor(-403.0249, device='cuda:0')
epoch: 101 test_true_pfm: 388.6624967092533 sim_pfm: -372.3340438987846
episode: 404 training return: tensor(-407.6537, device='cuda:0')
episode: 405 training return: tensor(-404.1919, device='cuda:0')
episode: 406 training return: tensor(-413.1309, device='cuda:0')
episode: 407 training return: tensor(-388.8315, device='cuda:0')
epoch: 102 test_true_pfm: 347.35048744730784 sim_pfm: -384.0125190134083
episode: 408 training return: tensor(-319.7734, device='cuda:0')
episode: 409 training return: tensor(-401.9672, device='cuda:0')
episode: 410 training return: tensor(-417.9027, device='cuda:0')
episode: 411 training return: tensor(-404.1769, device='cuda:0')
epoch: 103 test_true_pfm: 361.4512849401082 sim_pfm: -377.97912673900527
episode: 412 training return: tensor(-284.3517, device='cuda:0')
episode: 413 training return: tensor(-315.2840, device='cuda:0')
episode: 414 training return: tensor(-354.0961, device='cuda:0')
episode: 415 training return: tensor(-420.4261, device='cuda:0')
epoch: 104 test_true_pfm: 715.1875818235212 sim_pfm: -188.85252353552883
episode: 416 training return: tensor(-355.2618, device='cuda:0')
episode: 417 training return: tensor(-382.5737, device='cuda:0')
episode: 418 training return: tensor(-378.1523, device='cuda:0')
episode: 419 training return: tensor(-423.1446, device='cuda:0')
epoch: 105 test_true_pfm: 391.502030769306 sim_pfm: -377.4862688725504
episode: 420 training return: tensor(-427.2086, device='cuda:0')
episode: 421 training return: tensor(-403.0694, device='cuda:0')
episode: 422 training return: tensor(-406.6378, device='cuda:0')
episode: 423 training return: tensor(-379.0901, device='cuda:0')
epoch: 106 test_true_pfm: 516.0042474224317 sim_pfm: -326.5321870437765
episode: 424 training return: tensor(-329.4743, device='cuda:0')
episode: 425 training return: tensor(-313.8623, device='cuda:0')
episode: 426 training return: tensor(-370.7075, device='cuda:0')
episode: 427 training return: tensor(-367.0635, device='cuda:0')
epoch: 107 test_true_pfm: 528.7974402545243 sim_pfm: -262.72173559617175
episode: 428 training return: tensor(-413.4973, device='cuda:0')
episode: 429 training return: tensor(-339.5126, device='cuda:0')
episode: 430 training return: tensor(-279.0140, device='cuda:0')
episode: 431 training return: tensor(-227.9887, device='cuda:0')
epoch: 108 test_true_pfm: 1052.3797772752398 sim_pfm: -181.6537855110946
episode: 432 training return: tensor(-339.2716, device='cuda:0')
episode: 433 training return: tensor(-394.8524, device='cuda:0')
episode: 434 training return: tensor(-408.7671, device='cuda:0')
episode: 435 training return: tensor(-399.0194, device='cuda:0')
epoch: 109 test_true_pfm: 354.1125819222495 sim_pfm: -386.14205863776925
episode: 436 training return: tensor(-405.7235, device='cuda:0')
episode: 437 training return: tensor(-324.7912, device='cuda:0')
episode: 438 training return: tensor(-368.4191, device='cuda:0')
episode: 439 training return: tensor(-275.4295, device='cuda:0')
epoch: 110 test_true_pfm: 378.65177276521945 sim_pfm: -369.2702403771691
episode: 440 training return: tensor(-375.9514, device='cuda:0')
episode: 441 training return: tensor(-322.7247, device='cuda:0')
episode: 442 training return: tensor(-372.7397, device='cuda:0')
episode: 443 training return: tensor(-310.2795, device='cuda:0')
epoch: 111 test_true_pfm: 334.31123190122605 sim_pfm: -385.37416223677184
episode: 444 training return: tensor(-268.0483, device='cuda:0')
episode: 445 training return: tensor(-262.6017, device='cuda:0')
episode: 446 training return: tensor(-361.4918, device='cuda:0')
episode: 447 training return: tensor(-373.2489, device='cuda:0')
epoch: 112 test_true_pfm: 637.2461954314323 sim_pfm: -258.5844204775058
episode: 448 training return: tensor(-262.2000, device='cuda:0')
episode: 449 training return: tensor(-271.7490, device='cuda:0')
episode: 450 training return: tensor(-326.8476, device='cuda:0')
episode: 451 training return: tensor(-258.4257, device='cuda:0')
epoch: 113 test_true_pfm: 850.058681154805 sim_pfm: -218.37795549164488
episode: 452 training return: tensor(-271.4759, device='cuda:0')
episode: 453 training return: tensor(-288.5475, device='cuda:0')
episode: 454 training return: tensor(-249.3909, device='cuda:0')
episode: 455 training return: tensor(-305.2928, device='cuda:0')
epoch: 114 test_true_pfm: 731.0457230999976 sim_pfm: -256.0875315798524
episode: 456 training return: tensor(-265.7312, device='cuda:0')
episode: 457 training return: tensor(-293.5694, device='cuda:0')
episode: 458 training return: tensor(-268.9514, device='cuda:0')
episode: 459 training return: tensor(-266.5481, device='cuda:0')
epoch: 115 test_true_pfm: 821.9387354853867 sim_pfm: -237.44492388343983
episode: 460 training return: tensor(-244.2151, device='cuda:0')
episode: 461 training return: tensor(-272.3224, device='cuda:0')
episode: 462 training return: tensor(-239.5001, device='cuda:0')
episode: 463 training return: tensor(-248.6634, device='cuda:0')
epoch: 116 test_true_pfm: 817.4058868546216 sim_pfm: -229.43322513679354
episode: 464 training return: tensor(-261.7436, device='cuda:0')
episode: 465 training return: tensor(-236.0896, device='cuda:0')
episode: 466 training return: tensor(-263.6298, device='cuda:0')
episode: 467 training return: tensor(-258.3107, device='cuda:0')
epoch: 117 test_true_pfm: 839.415039516723 sim_pfm: -234.18822461429713
episode: 468 training return: tensor(-272.2576, device='cuda:0')
episode: 469 training return: tensor(-292.5491, device='cuda:0')
episode: 470 training return: tensor(-268.6673, device='cuda:0')
episode: 471 training return: tensor(-259.5573, device='cuda:0')
epoch: 118 test_true_pfm: 813.783855812896 sim_pfm: -236.48829588515218
episode: 472 training return: tensor(-254.5266, device='cuda:0')
episode: 473 training return: tensor(-258.7522, device='cuda:0')
episode: 474 training return: tensor(-270.5711, device='cuda:0')
episode: 475 training return: tensor(-261.6152, device='cuda:0')
epoch: 119 test_true_pfm: 833.0727300270213 sim_pfm: -220.9819724689005
episode: 476 training return: tensor(-250.0801, device='cuda:0')
episode: 477 training return: tensor(-290.9989, device='cuda:0')
episode: 478 training return: tensor(-227.9673, device='cuda:0')
episode: 479 training return: tensor(-240.9300, device='cuda:0')
epoch: 120 test_true_pfm: 744.0797272476552 sim_pfm: -264.261901255503
episode: 480 training return: tensor(-277.4084, device='cuda:0')
episode: 481 training return: tensor(-257.6777, device='cuda:0')
episode: 482 training return: tensor(-260.4370, device='cuda:0')
episode: 483 training return: tensor(-235.6780, device='cuda:0')
epoch: 121 test_true_pfm: 993.6340128070383 sim_pfm: -181.10671979084145
episode: 484 training return: tensor(-249.1928, device='cuda:0')
episode: 485 training return: tensor(-245.0139, device='cuda:0')
episode: 486 training return: tensor(-230.3021, device='cuda:0')
episode: 487 training return: tensor(-217.2076, device='cuda:0')
epoch: 122 test_true_pfm: 871.1324637245853 sim_pfm: -212.8164258604132
episode: 488 training return: tensor(-229.5961, device='cuda:0')
episode: 489 training return: tensor(-233.1273, device='cuda:0')
episode: 490 training return: tensor(-227.9289, device='cuda:0')
episode: 491 training return: tensor(-236.9663, device='cuda:0')
epoch: 123 test_true_pfm: 996.9794926060963 sim_pfm: -148.4182791321849
episode: 492 training return: tensor(-245.7583, device='cuda:0')
episode: 493 training return: tensor(-248.5264, device='cuda:0')
episode: 494 training return: tensor(-252.7445, device='cuda:0')
episode: 495 training return: tensor(-242.9498, device='cuda:0')
epoch: 124 test_true_pfm: 876.9956989250578 sim_pfm: -219.90682175999973
episode: 496 training return: tensor(-254.7119, device='cuda:0')
episode: 497 training return: tensor(-248.1098, device='cuda:0')
episode: 498 training return: tensor(-231.3839, device='cuda:0')
episode: 499 training return: tensor(-253.6063, device='cuda:0')
epoch: 125 test_true_pfm: 820.3645301761952 sim_pfm: -224.8185455946174
episode: 500 training return: tensor(-253.1528, device='cuda:0')
episode: 501 training return: tensor(-229.6947, device='cuda:0')
episode: 502 training return: tensor(-237.7609, device='cuda:0')
episode: 503 training return: tensor(-221.4716, device='cuda:0')
epoch: 126 test_true_pfm: 933.7456879872883 sim_pfm: -170.7199146577817
episode: 504 training return: tensor(-213.7146, device='cuda:0')
episode: 505 training return: tensor(-230.4279, device='cuda:0')
episode: 506 training return: tensor(-212.0545, device='cuda:0')
episode: 507 training return: tensor(-267.1481, device='cuda:0')
epoch: 127 test_true_pfm: 899.8993868552197 sim_pfm: -209.68719653378744
episode: 508 training return: tensor(-228.8533, device='cuda:0')
episode: 509 training return: tensor(-240.8222, device='cuda:0')
episode: 510 training return: tensor(-233.8872, device='cuda:0')
episode: 511 training return: tensor(-214.0617, device='cuda:0')
epoch: 128 test_true_pfm: 834.3618552282147 sim_pfm: -221.27025469509923
episode: 512 training return: tensor(-251.8425, device='cuda:0')
episode: 513 training return: tensor(-212.8779, device='cuda:0')
episode: 514 training return: tensor(-237.4646, device='cuda:0')
episode: 515 training return: tensor(-206.0194, device='cuda:0')
epoch: 129 test_true_pfm: 847.357000957191 sim_pfm: -225.57093860354507
episode: 516 training return: tensor(-242.7492, device='cuda:0')
episode: 517 training return: tensor(-224.1151, device='cuda:0')
episode: 518 training return: tensor(-231.0373, device='cuda:0')
episode: 519 training return: tensor(-258.0625, device='cuda:0')
epoch: 130 test_true_pfm: 905.0946414096317 sim_pfm: -204.9995098420671
episode: 520 training return: tensor(-249.1162, device='cuda:0')
episode: 521 training return: tensor(-228.5283, device='cuda:0')
episode: 522 training return: tensor(-226.4965, device='cuda:0')
episode: 523 training return: tensor(-222.9976, device='cuda:0')
epoch: 131 test_true_pfm: 887.8639008893618 sim_pfm: -206.58997307589743
episode: 524 training return: tensor(-247.6495, device='cuda:0')
episode: 525 training return: tensor(-233.7888, device='cuda:0')
episode: 526 training return: tensor(-209.7500, device='cuda:0')
episode: 527 training return: tensor(-231.9421, device='cuda:0')
epoch: 132 test_true_pfm: 870.2116733956003 sim_pfm: -221.1522490871721
episode: 528 training return: tensor(-250.6632, device='cuda:0')
episode: 529 training return: tensor(-234.1521, device='cuda:0')
episode: 530 training return: tensor(-255.8081, device='cuda:0')
episode: 531 training return: tensor(-232.1352, device='cuda:0')
epoch: 133 test_true_pfm: 814.1034697325017 sim_pfm: -240.912064761195
episode: 532 training return: tensor(-239.9849, device='cuda:0')
episode: 533 training return: tensor(-220.4327, device='cuda:0')
episode: 534 training return: tensor(-249.1702, device='cuda:0')
episode: 535 training return: tensor(-260.3663, device='cuda:0')
epoch: 134 test_true_pfm: 897.5119196394929 sim_pfm: -212.62251109791882
episode: 536 training return: tensor(-223.9758, device='cuda:0')
episode: 537 training return: tensor(-215.0066, device='cuda:0')
episode: 538 training return: tensor(-243.7116, device='cuda:0')
episode: 539 training return: tensor(-208.4653, device='cuda:0')
epoch: 135 test_true_pfm: 979.770136911732 sim_pfm: -178.3243088188659
episode: 540 training return: tensor(-245.9981, device='cuda:0')
episode: 541 training return: tensor(-221.3228, device='cuda:0')
episode: 542 training return: tensor(-208.0792, device='cuda:0')
episode: 543 training return: tensor(-196.1215, device='cuda:0')
epoch: 136 test_true_pfm: 862.0906079872134 sim_pfm: -219.26198799572498
episode: 544 training return: tensor(-225.8633, device='cuda:0')
episode: 545 training return: tensor(-243.2617, device='cuda:0')
episode: 546 training return: tensor(-211.2695, device='cuda:0')
episode: 547 training return: tensor(-220.8667, device='cuda:0')
epoch: 137 test_true_pfm: 915.1210853169114 sim_pfm: -190.2350035731797
episode: 548 training return: tensor(-216.8251, device='cuda:0')
episode: 549 training return: tensor(-227.6051, device='cuda:0')
episode: 550 training return: tensor(-206.3080, device='cuda:0')
episode: 551 training return: tensor(-207.4051, device='cuda:0')
epoch: 138 test_true_pfm: 870.7734292670676 sim_pfm: -215.24285166422487
episode: 552 training return: tensor(-226.3511, device='cuda:0')
episode: 553 training return: tensor(-216.6885, device='cuda:0')
episode: 554 training return: tensor(-226.5305, device='cuda:0')
episode: 555 training return: tensor(-209.1800, device='cuda:0')
epoch: 139 test_true_pfm: 955.780727463169 sim_pfm: -186.634362130649
episode: 556 training return: tensor(-218.5990, device='cuda:0')
episode: 557 training return: tensor(-224.2973, device='cuda:0')
episode: 558 training return: tensor(-237.0037, device='cuda:0')
episode: 559 training return: tensor(-214.6302, device='cuda:0')
epoch: 140 test_true_pfm: 818.9426284825744 sim_pfm: -239.85276669213394
episode: 560 training return: tensor(-226.6112, device='cuda:0')
episode: 561 training return: tensor(-213.3210, device='cuda:0')
episode: 562 training return: tensor(-262.4469, device='cuda:0')
episode: 563 training return: tensor(-212.8238, device='cuda:0')
epoch: 141 test_true_pfm: 883.5653620320376 sim_pfm: -214.10996925438909
episode: 564 training return: tensor(-219.9536, device='cuda:0')
episode: 565 training return: tensor(-224.9534, device='cuda:0')
episode: 566 training return: tensor(-226.1012, device='cuda:0')
episode: 567 training return: tensor(-245.7193, device='cuda:0')
epoch: 142 test_true_pfm: 893.9310344940345 sim_pfm: -191.02649465509845
episode: 568 training return: tensor(-211.7345, device='cuda:0')
episode: 569 training return: tensor(-193.5646, device='cuda:0')
episode: 570 training return: tensor(-217.0255, device='cuda:0')
episode: 571 training return: tensor(-239.3657, device='cuda:0')
epoch: 143 test_true_pfm: 965.087357119092 sim_pfm: -179.080776966856
episode: 572 training return: tensor(-219.2363, device='cuda:0')
episode: 573 training return: tensor(-214.2308, device='cuda:0')
episode: 574 training return: tensor(-207.1554, device='cuda:0')
episode: 575 training return: tensor(-221.6475, device='cuda:0')
epoch: 144 test_true_pfm: 910.3059370499931 sim_pfm: -206.25991140760016
episode: 576 training return: tensor(-213.4451, device='cuda:0')
episode: 577 training return: tensor(-219.8398, device='cuda:0')
episode: 578 training return: tensor(-236.9116, device='cuda:0')
episode: 579 training return: tensor(-221.4778, device='cuda:0')
epoch: 145 test_true_pfm: 976.0492397504836 sim_pfm: -167.25705716978214
episode: 580 training return: tensor(-196.3065, device='cuda:0')
episode: 581 training return: tensor(-223.6287, device='cuda:0')
episode: 582 training return: tensor(-216.1256, device='cuda:0')
episode: 583 training return: tensor(-216.3183, device='cuda:0')
epoch: 146 test_true_pfm: 917.0244082823789 sim_pfm: -193.3720501899952
episode: 584 training return: tensor(-185.2118, device='cuda:0')
episode: 585 training return: tensor(-209.7360, device='cuda:0')
episode: 586 training return: tensor(-202.9966, device='cuda:0')
episode: 587 training return: tensor(-191.0605, device='cuda:0')
epoch: 147 test_true_pfm: 944.5186187187859 sim_pfm: -182.8314895752798
episode: 588 training return: tensor(-199.1264, device='cuda:0')
episode: 589 training return: tensor(-206.8056, device='cuda:0')
episode: 590 training return: tensor(-227.0379, device='cuda:0')
episode: 591 training return: tensor(-230.0320, device='cuda:0')
epoch: 148 test_true_pfm: 924.5449015272461 sim_pfm: -199.8025923583967
episode: 592 training return: tensor(-237.1173, device='cuda:0')
episode: 593 training return: tensor(-213.8755, device='cuda:0')
episode: 594 training return: tensor(-199.4487, device='cuda:0')
episode: 595 training return: tensor(-226.3214, device='cuda:0')
epoch: 149 test_true_pfm: 1023.5077697882776 sim_pfm: -159.56043050121903
episode: 596 training return: tensor(-212.5352, device='cuda:0')
episode: 597 training return: tensor(-213.2786, device='cuda:0')
episode: 598 training return: tensor(-239.7669, device='cuda:0')
episode: 599 training return: tensor(-228.3043, device='cuda:0')
epoch: 150 test_true_pfm: 966.0539025306288 sim_pfm: -178.03422656694116
