['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'baseline', '--traj', 'medium', '--seed', '2']
episode: 0 training return: tensor(-999.9741, device='cuda:0')
episode: 1 training return: tensor(-999.9174, device='cuda:0')
episode: 2 training return: tensor(-999.9830, device='cuda:0')
episode: 3 training return: tensor(-999.9801, device='cuda:0')
epoch: 1 test_true_pfm: -0.05102802443794996 sim_pfm: -999.8926821351051
episode: 4 training return: tensor(-999.9792, device='cuda:0')
episode: 5 training return: tensor(-999.9733, device='cuda:0')
episode: 6 training return: tensor(-999.9823, device='cuda:0')
episode: 7 training return: tensor(-999.8055, device='cuda:0')
epoch: 2 test_true_pfm: -0.015717520897908805 sim_pfm: -999.8914224505424
episode: 8 training return: tensor(-999.9569, device='cuda:0')
episode: 9 training return: tensor(-999.9684, device='cuda:0')
episode: 10 training return: tensor(-999.9584, device='cuda:0')
episode: 11 training return: tensor(-999.9846, device='cuda:0')
epoch: 3 test_true_pfm: -0.164589267438001 sim_pfm: -999.8920531074206
episode: 12 training return: tensor(-999.9808, device='cuda:0')
episode: 13 training return: tensor(-999.9808, device='cuda:0')
episode: 14 training return: tensor(-999.9752, device='cuda:0')
episode: 15 training return: tensor(-999.9486, device='cuda:0')
epoch: 4 test_true_pfm: -0.9033365748560401 sim_pfm: -999.8919754823049
episode: 16 training return: tensor(-999.9787, device='cuda:0')
episode: 17 training return: tensor(-999.9672, device='cuda:0')
episode: 18 training return: tensor(-999.9775, device='cuda:0')
episode: 19 training return: tensor(-999.9753, device='cuda:0')
epoch: 5 test_true_pfm: -0.3297063532859626 sim_pfm: -999.892587284247
episode: 20 training return: tensor(-999.9755, device='cuda:0')
episode: 21 training return: tensor(-999.9774, device='cuda:0')
episode: 22 training return: tensor(-999.9778, device='cuda:0')
episode: 23 training return: tensor(-999.9779, device='cuda:0')
epoch: 6 test_true_pfm: 0.34924935560818 sim_pfm: -999.892412106196
episode: 24 training return: tensor(-999.9850, device='cuda:0')
episode: 25 training return: tensor(-999.9798, device='cuda:0')
episode: 26 training return: tensor(-999.9855, device='cuda:0')
episode: 27 training return: tensor(-999.9681, device='cuda:0')
epoch: 7 test_true_pfm: -0.5610089801844456 sim_pfm: -999.8908424973488
episode: 28 training return: tensor(-999.9681, device='cuda:0')
episode: 29 training return: tensor(-999.9788, device='cuda:0')
episode: 30 training return: tensor(-999.9653, device='cuda:0')
episode: 31 training return: tensor(-999.9800, device='cuda:0')
epoch: 8 test_true_pfm: -0.8011063139436388 sim_pfm: -999.8911324540774
episode: 32 training return: tensor(-999.9747, device='cuda:0')
episode: 33 training return: tensor(-999.9787, device='cuda:0')
episode: 34 training return: tensor(-999.9830, device='cuda:0')
episode: 35 training return: tensor(-999.9571, device='cuda:0')
epoch: 9 test_true_pfm: -0.8080989302439349 sim_pfm: -999.8912193775177
episode: 36 training return: tensor(-999.9688, device='cuda:0')
episode: 37 training return: tensor(-999.9584, device='cuda:0')
episode: 38 training return: tensor(-999.9484, device='cuda:0')
episode: 39 training return: tensor(-999.9727, device='cuda:0')
epoch: 10 test_true_pfm: -0.23014257222434187 sim_pfm: -999.8919896284739
episode: 40 training return: tensor(-999.9840, device='cuda:0')
episode: 41 training return: tensor(-999.9753, device='cuda:0')
episode: 42 training return: tensor(-999.9766, device='cuda:0')
episode: 43 training return: tensor(-999.9839, device='cuda:0')
epoch: 11 test_true_pfm: -0.4533019500587831 sim_pfm: -999.8925242821375
episode: 44 training return: tensor(-999.9751, device='cuda:0')
episode: 45 training return: tensor(-999.9747, device='cuda:0')
episode: 46 training return: tensor(-999.9783, device='cuda:0')
episode: 47 training return: tensor(-999.9768, device='cuda:0')
epoch: 12 test_true_pfm: -0.21777777073459595 sim_pfm: -999.8916666905085
episode: 48 training return: tensor(-999.9831, device='cuda:0')
episode: 49 training return: tensor(-999.9624, device='cuda:0')
episode: 50 training return: tensor(-999.9791, device='cuda:0')
episode: 51 training return: tensor(-999.9779, device='cuda:0')
epoch: 13 test_true_pfm: -0.28730380655243987 sim_pfm: -999.8928767641386
episode: 52 training return: tensor(-999.9801, device='cuda:0')
episode: 53 training return: tensor(-999.9852, device='cuda:0')
episode: 54 training return: tensor(-999.9508, device='cuda:0')
episode: 55 training return: tensor(-999.9648, device='cuda:0')
epoch: 14 test_true_pfm: -0.11610666456667862 sim_pfm: -999.8911822636923
episode: 56 training return: tensor(-999.9731, device='cuda:0')
episode: 57 training return: tensor(-999.9702, device='cuda:0')
episode: 58 training return: tensor(-999.9684, device='cuda:0')
episode: 59 training return: tensor(-999.9350, device='cuda:0')
epoch: 15 test_true_pfm: -0.7030524716400933 sim_pfm: -999.8916576902071
episode: 60 training return: tensor(-999.9527, device='cuda:0')
episode: 61 training return: tensor(-999.9837, device='cuda:0')
episode: 62 training return: tensor(-999.9529, device='cuda:0')
episode: 63 training return: tensor(-999.9806, device='cuda:0')
epoch: 16 test_true_pfm: -0.4050577793200136 sim_pfm: -999.8916979233423
episode: 64 training return: tensor(-999.9566, device='cuda:0')
episode: 65 training return: tensor(-999.9714, device='cuda:0')
episode: 66 training return: tensor(-999.9795, device='cuda:0')
episode: 67 training return: tensor(-999.9621, device='cuda:0')
epoch: 17 test_true_pfm: -0.37854177577889153 sim_pfm: -999.8920421799024
episode: 68 training return: tensor(-999.9728, device='cuda:0')
episode: 69 training return: tensor(-999.9852, device='cuda:0')
episode: 70 training return: tensor(-999.9737, device='cuda:0')
episode: 71 training return: tensor(-999.9818, device='cuda:0')
epoch: 18 test_true_pfm: -0.24148161562280235 sim_pfm: -999.8907492955526
episode: 72 training return: tensor(-999.9865, device='cuda:0')
episode: 73 training return: tensor(-999.9755, device='cuda:0')
episode: 74 training return: tensor(-999.9850, device='cuda:0')
episode: 75 training return: tensor(-999.9876, device='cuda:0')
epoch: 19 test_true_pfm: -0.9139334988012995 sim_pfm: -999.8914647102356
episode: 76 training return: tensor(-999.9752, device='cuda:0')
episode: 77 training return: tensor(-999.9838, device='cuda:0')
episode: 78 training return: tensor(-999.9800, device='cuda:0')
episode: 79 training return: tensor(-999.9537, device='cuda:0')
epoch: 20 test_true_pfm: -0.008901520033337065 sim_pfm: -999.8925857941309
episode: 80 training return: tensor(-999.9811, device='cuda:0')
episode: 81 training return: tensor(-999.9725, device='cuda:0')
episode: 82 training return: tensor(-999.9688, device='cuda:0')
episode: 83 training return: tensor(-999.9810, device='cuda:0')
epoch: 21 test_true_pfm: 0.21141107395739334 sim_pfm: -999.8914068937302
episode: 84 training return: tensor(-999.9818, device='cuda:0')
episode: 85 training return: tensor(-999.9769, device='cuda:0')
episode: 86 training return: tensor(-999.9758, device='cuda:0')
episode: 87 training return: tensor(-999.9775, device='cuda:0')
epoch: 22 test_true_pfm: 0.5302660523939714 sim_pfm: -999.8903577526411
episode: 88 training return: tensor(-999.9744, device='cuda:0')
episode: 89 training return: tensor(-999.9811, device='cuda:0')
episode: 90 training return: tensor(-999.9741, device='cuda:0')
episode: 91 training return: tensor(-999.9831, device='cuda:0')
epoch: 23 test_true_pfm: -0.17120349596818019 sim_pfm: -999.8917609850565
episode: 92 training return: tensor(-999.9642, device='cuda:0')
episode: 93 training return: tensor(-999.9746, device='cuda:0')
episode: 94 training return: tensor(-999.9465, device='cuda:0')
episode: 95 training return: tensor(-999.9797, device='cuda:0')
epoch: 24 test_true_pfm: -0.005334165375815307 sim_pfm: -999.891925017039
episode: 96 training return: tensor(-999.9815, device='cuda:0')
episode: 97 training return: tensor(-999.9813, device='cuda:0')
episode: 98 training return: tensor(-999.9823, device='cuda:0')
episode: 99 training return: tensor(-999.9811, device='cuda:0')
epoch: 25 test_true_pfm: -0.4674195945533827 sim_pfm: -999.8918937643369
episode: 100 training return: tensor(-999.9768, device='cuda:0')
episode: 101 training return: tensor(-999.9849, device='cuda:0')
episode: 102 training return: tensor(-999.9542, device='cuda:0')
episode: 103 training return: tensor(-999.9465, device='cuda:0')
epoch: 26 test_true_pfm: -1.2166667812355767 sim_pfm: -999.8922463456789
episode: 104 training return: tensor(-999.9726, device='cuda:0')
episode: 105 training return: tensor(-999.9376, device='cuda:0')
episode: 106 training return: tensor(-999.9797, device='cuda:0')
episode: 107 training return: tensor(-999.9640, device='cuda:0')
epoch: 27 test_true_pfm: -0.4612328542871278 sim_pfm: -999.8899590969086
episode: 108 training return: tensor(-999.9762, device='cuda:0')
episode: 109 training return: tensor(-999.9861, device='cuda:0')
episode: 110 training return: tensor(-999.9749, device='cuda:0')
episode: 111 training return: tensor(-999.9464, device='cuda:0')
epoch: 28 test_true_pfm: -1.1006202438874029 sim_pfm: -999.8913449645042
episode: 112 training return: tensor(-999.9391, device='cuda:0')
episode: 113 training return: tensor(-999.9733, device='cuda:0')
episode: 114 training return: tensor(-999.9774, device='cuda:0')
episode: 115 training return: tensor(-999.9583, device='cuda:0')
epoch: 29 test_true_pfm: -0.1922235754492337 sim_pfm: -999.8922989567121
episode: 116 training return: tensor(-999.9786, device='cuda:0')
episode: 117 training return: tensor(-999.9536, device='cuda:0')
episode: 118 training return: tensor(-999.9791, device='cuda:0')
episode: 119 training return: tensor(-999.9769, device='cuda:0')
epoch: 30 test_true_pfm: -0.23337490604876884 sim_pfm: -999.8912594517072
episode: 120 training return: tensor(-999.9631, device='cuda:0')
episode: 121 training return: tensor(-999.9731, device='cuda:0')
episode: 122 training return: tensor(-999.9813, device='cuda:0')
episode: 123 training return: tensor(-999.9769, device='cuda:0')
epoch: 31 test_true_pfm: 0.40122381923280265 sim_pfm: -999.8912355701128
episode: 124 training return: tensor(-999.9554, device='cuda:0')
episode: 125 training return: tensor(-999.9818, device='cuda:0')
episode: 126 training return: tensor(-999.9468, device='cuda:0')
episode: 127 training return: tensor(-999.9693, device='cuda:0')
epoch: 32 test_true_pfm: -0.18396128915862808 sim_pfm: -999.8910770018896
episode: 128 training return: tensor(-999.9677, device='cuda:0')
episode: 129 training return: tensor(-999.9626, device='cuda:0')
episode: 130 training return: tensor(-999.9730, device='cuda:0')
episode: 131 training return: tensor(-999.9424, device='cuda:0')
epoch: 33 test_true_pfm: -0.5060621917228842 sim_pfm: -999.8933517535528
episode: 132 training return: tensor(-999.9745, device='cuda:0')
episode: 133 training return: tensor(-999.9606, device='cuda:0')
episode: 134 training return: tensor(-999.9517, device='cuda:0')
episode: 135 training return: tensor(-999.9819, device='cuda:0')
epoch: 34 test_true_pfm: 0.29330740235692243 sim_pfm: -999.8917370239893
episode: 136 training return: tensor(-999.9868, device='cuda:0')
episode: 137 training return: tensor(-999.9807, device='cuda:0')
episode: 138 training return: tensor(-999.9808, device='cuda:0')
episode: 139 training return: tensor(-999.9773, device='cuda:0')
epoch: 35 test_true_pfm: -0.0882867731239464 sim_pfm: -999.8915050228437
episode: 140 training return: tensor(-999.9633, device='cuda:0')
episode: 141 training return: tensor(-999.9673, device='cuda:0')
episode: 142 training return: tensor(-999.9277, device='cuda:0')
episode: 143 training return: tensor(-999.9791, device='cuda:0')
epoch: 36 test_true_pfm: 0.3158850164860963 sim_pfm: -999.8922592798868
episode: 144 training return: tensor(-999.9878, device='cuda:0')
episode: 145 training return: tensor(-999.9674, device='cuda:0')
episode: 146 training return: tensor(-999.9738, device='cuda:0')
episode: 147 training return: tensor(-999.9431, device='cuda:0')
epoch: 37 test_true_pfm: -0.1339101566683705 sim_pfm: -999.8919579188029
episode: 148 training return: tensor(-999.9752, device='cuda:0')
episode: 149 training return: tensor(-999.9723, device='cuda:0')
episode: 150 training return: tensor(-999.9771, device='cuda:0')
episode: 151 training return: tensor(-999.9824, device='cuda:0')
epoch: 38 test_true_pfm: -0.047301297455272985 sim_pfm: -999.8917051355044
episode: 152 training return: tensor(-999.9454, device='cuda:0')
episode: 153 training return: tensor(-999.9695, device='cuda:0')
episode: 154 training return: tensor(-999.9520, device='cuda:0')
episode: 155 training return: tensor(-999.9361, device='cuda:0')
epoch: 39 test_true_pfm: 0.18139503275529456 sim_pfm: -999.8923025925955
episode: 156 training return: tensor(-999.9755, device='cuda:0')
episode: 157 training return: tensor(-999.9819, device='cuda:0')
episode: 158 training return: tensor(-999.9734, device='cuda:0')
episode: 159 training return: tensor(-999.9807, device='cuda:0')
epoch: 40 test_true_pfm: -0.1939787237285813 sim_pfm: -999.8917402426401
episode: 160 training return: tensor(-999.9764, device='cuda:0')
episode: 161 training return: tensor(-999.9780, device='cuda:0')
episode: 162 training return: tensor(-999.9659, device='cuda:0')
episode: 163 training return: tensor(-999.9752, device='cuda:0')
epoch: 41 test_true_pfm: -0.3561518486251652 sim_pfm: -999.8923444549242
episode: 164 training return: tensor(-999.9673, device='cuda:0')
episode: 165 training return: tensor(-999.9767, device='cuda:0')
episode: 166 training return: tensor(-999.9712, device='cuda:0')
episode: 167 training return: tensor(-999.9825, device='cuda:0')
epoch: 42 test_true_pfm: -0.5796817728133514 sim_pfm: -999.8918744723002
episode: 168 training return: tensor(-999.9296, device='cuda:0')
episode: 169 training return: tensor(-999.9805, device='cuda:0')
episode: 170 training return: tensor(-999.9852, device='cuda:0')
episode: 171 training return: tensor(-999.9799, device='cuda:0')
epoch: 43 test_true_pfm: -0.33724120784770034 sim_pfm: -999.8926930427551
episode: 172 training return: tensor(-999.9716, device='cuda:0')
episode: 173 training return: tensor(-999.9835, device='cuda:0')
episode: 174 training return: tensor(-999.9470, device='cuda:0')
episode: 175 training return: tensor(-999.9789, device='cuda:0')
epoch: 44 test_true_pfm: -0.5763442945141323 sim_pfm: -999.8928819894791
episode: 176 training return: tensor(-999.9702, device='cuda:0')
episode: 177 training return: tensor(-999.9537, device='cuda:0')
episode: 178 training return: tensor(-999.9777, device='cuda:0')
episode: 179 training return: tensor(-999.9783, device='cuda:0')
epoch: 45 test_true_pfm: -0.2878901597899853 sim_pfm: -999.891631325086
episode: 180 training return: tensor(-999.9786, device='cuda:0')
episode: 181 training return: tensor(-999.9753, device='cuda:0')
episode: 182 training return: tensor(-999.9841, device='cuda:0')
episode: 183 training return: tensor(-999.9867, device='cuda:0')
epoch: 46 test_true_pfm: -0.06538870058392765 sim_pfm: -999.8930532534918
episode: 184 training return: tensor(-999.9540, device='cuda:0')
episode: 185 training return: tensor(-999.9815, device='cuda:0')
episode: 186 training return: tensor(-999.9640, device='cuda:0')
episode: 187 training return: tensor(-999.9449, device='cuda:0')
epoch: 47 test_true_pfm: 0.42841039004338394 sim_pfm: -999.8918434381485
episode: 188 training return: tensor(-999.9827, device='cuda:0')
episode: 189 training return: tensor(-999.9755, device='cuda:0')
episode: 190 training return: tensor(-999.9750, device='cuda:0')
episode: 191 training return: tensor(-999.9827, device='cuda:0')
epoch: 48 test_true_pfm: -0.11969293478615789 sim_pfm: -999.890693406264
episode: 192 training return: tensor(-999.9826, device='cuda:0')
episode: 193 training return: tensor(-999.9734, device='cuda:0')
episode: 194 training return: tensor(-999.9576, device='cuda:0')
episode: 195 training return: tensor(-999.9810, device='cuda:0')
epoch: 49 test_true_pfm: -0.3487266754112359 sim_pfm: -999.891343096892
episode: 196 training return: tensor(-999.9692, device='cuda:0')
episode: 197 training return: tensor(-999.9847, device='cuda:0')
episode: 198 training return: tensor(-999.9308, device='cuda:0')
episode: 199 training return: tensor(-999.9592, device='cuda:0')
epoch: 50 test_true_pfm: -0.2929219614860175 sim_pfm: -999.892119983832
episode: 200 training return: tensor(-999.9766, device='cuda:0')
episode: 201 training return: tensor(-999.9769, device='cuda:0')
episode: 202 training return: tensor(-999.9765, device='cuda:0')
episode: 203 training return: tensor(-999.9369, device='cuda:0')
epoch: 51 test_true_pfm: -0.4253164327948748 sim_pfm: -999.890225370725
episode: 204 training return: tensor(-999.9487, device='cuda:0')
episode: 205 training return: tensor(-999.9818, device='cuda:0')
episode: 206 training return: tensor(-999.9673, device='cuda:0')
episode: 207 training return: tensor(-999.9797, device='cuda:0')
epoch: 52 test_true_pfm: -0.2350707519225593 sim_pfm: -999.8915169636408
episode: 208 training return: tensor(-999.9805, device='cuda:0')
episode: 209 training return: tensor(-999.9850, device='cuda:0')
episode: 210 training return: tensor(-999.9709, device='cuda:0')
episode: 211 training return: tensor(-999.9658, device='cuda:0')
epoch: 53 test_true_pfm: -0.14356448876944014 sim_pfm: -999.8915189703306
episode: 212 training return: tensor(-999.9705, device='cuda:0')
episode: 213 training return: tensor(-999.9837, device='cuda:0')
episode: 214 training return: tensor(-999.9734, device='cuda:0')
episode: 215 training return: tensor(-999.9698, device='cuda:0')
epoch: 54 test_true_pfm: -0.14271341634055076 sim_pfm: -999.8914175232252
episode: 216 training return: tensor(-999.9774, device='cuda:0')
episode: 217 training return: tensor(-999.9830, device='cuda:0')
episode: 218 training return: tensor(-999.9324, device='cuda:0')
episode: 219 training return: tensor(-999.9845, device='cuda:0')
epoch: 55 test_true_pfm: -0.04079796721235429 sim_pfm: -999.8917156259218
episode: 220 training return: tensor(-999.9805, device='cuda:0')
episode: 221 training return: tensor(-999.9417, device='cuda:0')
episode: 222 training return: tensor(-999.9370, device='cuda:0')
episode: 223 training return: tensor(-999.9732, device='cuda:0')
epoch: 56 test_true_pfm: 0.3215370483386999 sim_pfm: -999.8910030523936
episode: 224 training return: tensor(-999.9885, device='cuda:0')
episode: 225 training return: tensor(-999.9835, device='cuda:0')
episode: 226 training return: tensor(-999.9789, device='cuda:0')
episode: 227 training return: tensor(-999.9814, device='cuda:0')
epoch: 57 test_true_pfm: 0.03243257251803885 sim_pfm: -999.891944527626
episode: 228 training return: tensor(-999.9810, device='cuda:0')
episode: 229 training return: tensor(-999.9482, device='cuda:0')
episode: 230 training return: tensor(-999.9836, device='cuda:0')
episode: 231 training return: tensor(-999.9802, device='cuda:0')
epoch: 58 test_true_pfm: -0.1982911081651225 sim_pfm: -999.890136440595
episode: 232 training return: tensor(-999.9844, device='cuda:0')
episode: 233 training return: tensor(-999.9888, device='cuda:0')
episode: 234 training return: tensor(-999.9667, device='cuda:0')
episode: 235 training return: tensor(-999.9835, device='cuda:0')
epoch: 59 test_true_pfm: -0.5722118152119373 sim_pfm: -999.8927291433016
episode: 236 training return: tensor(-999.9098, device='cuda:0')
episode: 237 training return: tensor(-999.9645, device='cuda:0')
episode: 238 training return: tensor(-999.9788, device='cuda:0')
episode: 239 training return: tensor(-999.9840, device='cuda:0')
epoch: 60 test_true_pfm: -0.4499287422305698 sim_pfm: -999.8925068775812
episode: 240 training return: tensor(-999.9765, device='cuda:0')
episode: 241 training return: tensor(-999.9703, device='cuda:0')
episode: 242 training return: tensor(-999.9640, device='cuda:0')
episode: 243 training return: tensor(-999.9713, device='cuda:0')
epoch: 61 test_true_pfm: 0.20406700906967748 sim_pfm: -999.8911455074946
episode: 244 training return: tensor(-999.9857, device='cuda:0')
episode: 245 training return: tensor(-999.9530, device='cuda:0')
episode: 246 training return: tensor(-999.9850, device='cuda:0')
episode: 247 training return: tensor(-999.9645, device='cuda:0')
epoch: 62 test_true_pfm: -1.1712408785335588 sim_pfm: -999.8911782701811
episode: 248 training return: tensor(-999.9459, device='cuda:0')
episode: 249 training return: tensor(-999.9771, device='cuda:0')
episode: 250 training return: tensor(-999.9611, device='cuda:0')
episode: 251 training return: tensor(-999.9548, device='cuda:0')
epoch: 63 test_true_pfm: -0.6003867636744732 sim_pfm: -999.8904882470766
episode: 252 training return: tensor(-999.9848, device='cuda:0')
episode: 253 training return: tensor(-999.9669, device='cuda:0')
episode: 254 training return: tensor(-999.9650, device='cuda:0')
episode: 255 training return: tensor(-999.9632, device='cuda:0')
epoch: 64 test_true_pfm: -0.3635889999142905 sim_pfm: -999.8920065760612
episode: 256 training return: tensor(-999.9800, device='cuda:0')
episode: 257 training return: tensor(-999.9846, device='cuda:0')
episode: 258 training return: tensor(-999.9490, device='cuda:0')
episode: 259 training return: tensor(-999.9817, device='cuda:0')
epoch: 65 test_true_pfm: -0.8798926782920824 sim_pfm: -999.8908340930939
episode: 260 training return: tensor(-999.9750, device='cuda:0')
episode: 261 training return: tensor(-999.9725, device='cuda:0')
episode: 262 training return: tensor(-999.9452, device='cuda:0')
episode: 263 training return: tensor(-999.9844, device='cuda:0')
epoch: 66 test_true_pfm: -0.08062019456988771 sim_pfm: -999.8918830752373
episode: 264 training return: tensor(-999.9758, device='cuda:0')
episode: 265 training return: tensor(-999.9698, device='cuda:0')
episode: 266 training return: tensor(-999.9782, device='cuda:0')
episode: 267 training return: tensor(-999.9868, device='cuda:0')
epoch: 67 test_true_pfm: -0.419778319741166 sim_pfm: -999.892603357633
episode: 268 training return: tensor(-999.9822, device='cuda:0')
episode: 269 training return: tensor(-999.9628, device='cuda:0')
episode: 270 training return: tensor(-999.9791, device='cuda:0')
episode: 271 training return: tensor(-999.9814, device='cuda:0')
epoch: 68 test_true_pfm: -1.0209666476852581 sim_pfm: -999.890102048715
episode: 272 training return: tensor(-999.9758, device='cuda:0')
episode: 273 training return: tensor(-999.9832, device='cuda:0')
episode: 274 training return: tensor(-999.9839, device='cuda:0')
episode: 275 training return: tensor(-999.9750, device='cuda:0')
epoch: 69 test_true_pfm: 0.0482517472909747 sim_pfm: -999.8929413159689
episode: 276 training return: tensor(-999.9788, device='cuda:0')
episode: 277 training return: tensor(-999.9470, device='cuda:0')
episode: 278 training return: tensor(-999.9838, device='cuda:0')
episode: 279 training return: tensor(-999.9754, device='cuda:0')
epoch: 70 test_true_pfm: 0.28246863212089895 sim_pfm: -999.8924123048782
episode: 280 training return: tensor(-999.9827, device='cuda:0')
episode: 281 training return: tensor(-999.9385, device='cuda:0')
episode: 282 training return: tensor(-999.9791, device='cuda:0')
episode: 283 training return: tensor(-999.9738, device='cuda:0')
epoch: 71 test_true_pfm: 0.19165865972698745 sim_pfm: -999.8917381167412
episode: 284 training return: tensor(-999.9781, device='cuda:0')
episode: 285 training return: tensor(-999.9713, device='cuda:0')
episode: 286 training return: tensor(-999.9771, device='cuda:0')
episode: 287 training return: tensor(-999.9799, device='cuda:0')
epoch: 72 test_true_pfm: -0.4712172407282145 sim_pfm: -999.8909784158071
episode: 288 training return: tensor(-999.9782, device='cuda:0')
episode: 289 training return: tensor(-999.9818, device='cuda:0')
episode: 290 training return: tensor(-999.9771, device='cuda:0')
episode: 291 training return: tensor(-999.9629, device='cuda:0')
epoch: 73 test_true_pfm: -0.10172754671363642 sim_pfm: -999.8912478486697
episode: 292 training return: tensor(-999.9628, device='cuda:0')
episode: 293 training return: tensor(-999.9726, device='cuda:0')
episode: 294 training return: tensor(-999.9785, device='cuda:0')
episode: 295 training return: tensor(-999.9758, device='cuda:0')
epoch: 74 test_true_pfm: -0.1494158070478157 sim_pfm: -999.8909660577774
episode: 296 training return: tensor(-999.9809, device='cuda:0')
episode: 297 training return: tensor(-999.9785, device='cuda:0')
episode: 298 training return: tensor(-999.9838, device='cuda:0')
episode: 299 training return: tensor(-999.9803, device='cuda:0')
epoch: 75 test_true_pfm: 0.3741392305074415 sim_pfm: -999.8913771708807
episode: 300 training return: tensor(-999.9800, device='cuda:0')
episode: 301 training return: tensor(-999.9821, device='cuda:0')
episode: 302 training return: tensor(-999.9718, device='cuda:0')
episode: 303 training return: tensor(-999.9661, device='cuda:0')
epoch: 76 test_true_pfm: -0.4919337739852863 sim_pfm: -999.8927854895592
episode: 304 training return: tensor(-999.9646, device='cuda:0')
episode: 305 training return: tensor(-999.9821, device='cuda:0')
episode: 306 training return: tensor(-999.9805, device='cuda:0')
episode: 307 training return: tensor(-999.9504, device='cuda:0')
epoch: 77 test_true_pfm: -0.2676768110267562 sim_pfm: -999.8921691974004
episode: 308 training return: tensor(-999.9714, device='cuda:0')
episode: 309 training return: tensor(-999.9860, device='cuda:0')
episode: 310 training return: tensor(-999.8814, device='cuda:0')
episode: 311 training return: tensor(-999.9718, device='cuda:0')
epoch: 78 test_true_pfm: -0.07946717816317146 sim_pfm: -999.8912959694862
episode: 312 training return: tensor(-999.9832, device='cuda:0')
episode: 313 training return: tensor(-999.9581, device='cuda:0')
episode: 314 training return: tensor(-999.9788, device='cuda:0')
episode: 315 training return: tensor(-999.9734, device='cuda:0')
epoch: 79 test_true_pfm: 0.2397702334874706 sim_pfm: -999.8912733793259
episode: 316 training return: tensor(-999.9494, device='cuda:0')
episode: 317 training return: tensor(-999.9774, device='cuda:0')
episode: 318 training return: tensor(-999.9725, device='cuda:0')
episode: 319 training return: tensor(-999.9841, device='cuda:0')
epoch: 80 test_true_pfm: -0.5579761911865834 sim_pfm: -999.8917565743128
episode: 320 training return: tensor(-999.9486, device='cuda:0')
episode: 321 training return: tensor(-999.9822, device='cuda:0')
episode: 322 training return: tensor(-999.9777, device='cuda:0')
episode: 323 training return: tensor(-999.9795, device='cuda:0')
epoch: 81 test_true_pfm: -0.4311543612074223 sim_pfm: -999.8903162678083
episode: 324 training return: tensor(-999.9579, device='cuda:0')
episode: 325 training return: tensor(-999.9720, device='cuda:0')
episode: 326 training return: tensor(-999.9741, device='cuda:0')
episode: 327 training return: tensor(-999.9815, device='cuda:0')
epoch: 82 test_true_pfm: 0.05694697024685021 sim_pfm: -999.8915191292763
episode: 328 training return: tensor(-999.9753, device='cuda:0')
episode: 329 training return: tensor(-999.9438, device='cuda:0')
episode: 330 training return: tensor(-999.9791, device='cuda:0')
episode: 331 training return: tensor(-999.9773, device='cuda:0')
epoch: 83 test_true_pfm: -0.3522452475850157 sim_pfm: -999.8927553296089
episode: 332 training return: tensor(-999.9780, device='cuda:0')
episode: 333 training return: tensor(-999.9825, device='cuda:0')
episode: 334 training return: tensor(-999.9830, device='cuda:0')
episode: 335 training return: tensor(-999.9669, device='cuda:0')
epoch: 84 test_true_pfm: -0.3780921444856946 sim_pfm: -999.8914983669916
episode: 336 training return: tensor(-999.9808, device='cuda:0')
episode: 337 training return: tensor(-999.9777, device='cuda:0')
episode: 338 training return: tensor(-999.9553, device='cuda:0')
episode: 339 training return: tensor(-999.9753, device='cuda:0')
epoch: 85 test_true_pfm: -0.149303759754283 sim_pfm: -999.8913658459982
episode: 340 training return: tensor(-999.9852, device='cuda:0')
episode: 341 training return: tensor(-999.9778, device='cuda:0')
episode: 342 training return: tensor(-999.9688, device='cuda:0')
episode: 343 training return: tensor(-999.9659, device='cuda:0')
epoch: 86 test_true_pfm: 0.40772483891829353 sim_pfm: -999.8917921384176
episode: 344 training return: tensor(-999.9695, device='cuda:0')
episode: 345 training return: tensor(-999.9688, device='cuda:0')
episode: 346 training return: tensor(-999.9802, device='cuda:0')
episode: 347 training return: tensor(-999.9733, device='cuda:0')
epoch: 87 test_true_pfm: 0.030200230678716206 sim_pfm: -999.8927414615949
episode: 348 training return: tensor(-999.9775, device='cuda:0')
episode: 349 training return: tensor(-999.9536, device='cuda:0')
episode: 350 training return: tensor(-999.9520, device='cuda:0')
episode: 351 training return: tensor(-999.9655, device='cuda:0')
epoch: 88 test_true_pfm: -0.5421358189002169 sim_pfm: -999.8927326798439
episode: 352 training return: tensor(-999.9570, device='cuda:0')
episode: 353 training return: tensor(-999.9756, device='cuda:0')
episode: 354 training return: tensor(-999.9767, device='cuda:0')
episode: 355 training return: tensor(-999.9736, device='cuda:0')
epoch: 89 test_true_pfm: -0.49609090421915863 sim_pfm: -999.8904889424642
episode: 356 training return: tensor(-999.9808, device='cuda:0')
episode: 357 training return: tensor(-999.9799, device='cuda:0')
episode: 358 training return: tensor(-999.9745, device='cuda:0')
episode: 359 training return: tensor(-999.9744, device='cuda:0')
epoch: 90 test_true_pfm: -0.4929695013495441 sim_pfm: -999.892640610536
episode: 360 training return: tensor(-999.9767, device='cuda:0')
episode: 361 training return: tensor(-999.9835, device='cuda:0')
episode: 362 training return: tensor(-999.9850, device='cuda:0')
episode: 363 training return: tensor(-999.9762, device='cuda:0')
epoch: 91 test_true_pfm: 0.0039649849829844624 sim_pfm: -999.8920076886812
episode: 364 training return: tensor(-999.9825, device='cuda:0')
episode: 365 training return: tensor(-999.9829, device='cuda:0')
episode: 366 training return: tensor(-999.9692, device='cuda:0')
episode: 367 training return: tensor(-999.9639, device='cuda:0')
epoch: 92 test_true_pfm: -0.2326436502750574 sim_pfm: -999.8912723263105
episode: 368 training return: tensor(-999.9721, device='cuda:0')
episode: 369 training return: tensor(-999.9777, device='cuda:0')
episode: 370 training return: tensor(-999.9561, device='cuda:0')
episode: 371 training return: tensor(-999.9595, device='cuda:0')
epoch: 93 test_true_pfm: -0.5197224095562901 sim_pfm: -999.892244319121
episode: 372 training return: tensor(-999.9828, device='cuda:0')
episode: 373 training return: tensor(-999.9768, device='cuda:0')
episode: 374 training return: tensor(-999.9629, device='cuda:0')
episode: 375 training return: tensor(-999.9834, device='cuda:0')
epoch: 94 test_true_pfm: -0.667955424942236 sim_pfm: -999.891994436582
episode: 376 training return: tensor(-999.9764, device='cuda:0')
episode: 377 training return: tensor(-999.9846, device='cuda:0')
episode: 378 training return: tensor(-999.9653, device='cuda:0')
episode: 379 training return: tensor(-999.9815, device='cuda:0')
epoch: 95 test_true_pfm: -0.04154309605975567 sim_pfm: -999.8909060955048
episode: 380 training return: tensor(-999.9769, device='cuda:0')
episode: 381 training return: tensor(-999.9792, device='cuda:0')
episode: 382 training return: tensor(-999.9781, device='cuda:0')
episode: 383 training return: tensor(-999.9821, device='cuda:0')
epoch: 96 test_true_pfm: 0.16110011897118007 sim_pfm: -999.8910232186317
episode: 384 training return: tensor(-999.9751, device='cuda:0')
episode: 385 training return: tensor(-999.9845, device='cuda:0')
episode: 386 training return: tensor(-999.9725, device='cuda:0')
episode: 387 training return: tensor(-999.9623, device='cuda:0')
epoch: 97 test_true_pfm: -0.29686123917314106 sim_pfm: -999.8928754130999
episode: 388 training return: tensor(-999.9637, device='cuda:0')
episode: 389 training return: tensor(-999.9796, device='cuda:0')
episode: 390 training return: tensor(-999.9799, device='cuda:0')
episode: 391 training return: tensor(-999.9783, device='cuda:0')
epoch: 98 test_true_pfm: -0.2512137740893388 sim_pfm: -999.8924177885056
episode: 392 training return: tensor(-999.9806, device='cuda:0')
episode: 393 training return: tensor(-999.9827, device='cuda:0')
episode: 394 training return: tensor(-999.9822, device='cuda:0')
episode: 395 training return: tensor(-999.9703, device='cuda:0')
epoch: 99 test_true_pfm: -0.2897206444633051 sim_pfm: -999.8921216527621
episode: 396 training return: tensor(-999.9771, device='cuda:0')
episode: 397 training return: tensor(-999.9722, device='cuda:0')
episode: 398 training return: tensor(-999.9756, device='cuda:0')
episode: 399 training return: tensor(-999.9772, device='cuda:0')
epoch: 100 test_true_pfm: -0.6457050854496657 sim_pfm: -999.8924613992373
episode: 400 training return: tensor(-999.9834, device='cuda:0')
episode: 401 training return: tensor(-999.9337, device='cuda:0')
episode: 402 training return: tensor(-999.9705, device='cuda:0')
episode: 403 training return: tensor(-999.9625, device='cuda:0')
epoch: 101 test_true_pfm: -0.6034099668242598 sim_pfm: -999.89098072052
episode: 404 training return: tensor(-999.9599, device='cuda:0')
episode: 405 training return: tensor(-999.9734, device='cuda:0')
episode: 406 training return: tensor(-999.9689, device='cuda:0')
episode: 407 training return: tensor(-999.9431, device='cuda:0')
epoch: 102 test_true_pfm: -0.2406938154638113 sim_pfm: -999.8920121391615
episode: 408 training return: tensor(-999.9554, device='cuda:0')
episode: 409 training return: tensor(-999.9847, device='cuda:0')
episode: 410 training return: tensor(-999.9841, device='cuda:0')
episode: 411 training return: tensor(-999.9758, device='cuda:0')
epoch: 103 test_true_pfm: 0.3964641031749037 sim_pfm: -999.8921155333519
episode: 412 training return: tensor(-999.9847, device='cuda:0')
episode: 413 training return: tensor(-999.9716, device='cuda:0')
episode: 414 training return: tensor(-999.9465, device='cuda:0')
episode: 415 training return: tensor(-999.9467, device='cuda:0')
epoch: 104 test_true_pfm: 0.21095422241528095 sim_pfm: -999.8921333948771
episode: 416 training return: tensor(-999.9780, device='cuda:0')
episode: 417 training return: tensor(-999.9763, device='cuda:0')
episode: 418 training return: tensor(-999.9809, device='cuda:0')
episode: 419 training return: tensor(-999.9816, device='cuda:0')
epoch: 105 test_true_pfm: -0.06882060714854109 sim_pfm: -999.8928974668185
episode: 420 training return: tensor(-999.9805, device='cuda:0')
episode: 421 training return: tensor(-999.9803, device='cuda:0')
episode: 422 training return: tensor(-999.9299, device='cuda:0')
episode: 423 training return: tensor(-999.8863, device='cuda:0')
epoch: 106 test_true_pfm: -0.770924527181573 sim_pfm: -999.8896975914637
episode: 424 training return: tensor(-999.9783, device='cuda:0')
episode: 425 training return: tensor(-999.9799, device='cuda:0')
episode: 426 training return: tensor(-999.7258, device='cuda:0')
episode: 427 training return: tensor(-999.9637, device='cuda:0')
epoch: 107 test_true_pfm: -0.4685476319357806 sim_pfm: -999.891575217247
episode: 428 training return: tensor(-999.9789, device='cuda:0')
episode: 429 training return: tensor(-999.9627, device='cuda:0')
episode: 430 training return: tensor(-999.9794, device='cuda:0')
episode: 431 training return: tensor(-999.9561, device='cuda:0')
epoch: 108 test_true_pfm: -0.9746676928704446 sim_pfm: -999.891557653745
episode: 432 training return: tensor(-999.9664, device='cuda:0')
episode: 433 training return: tensor(-999.9330, device='cuda:0')
episode: 434 training return: tensor(-999.9720, device='cuda:0')
episode: 435 training return: tensor(-999.9763, device='cuda:0')
epoch: 109 test_true_pfm: -1.2815524507398417 sim_pfm: -999.8903021613756
episode: 436 training return: tensor(-999.9720, device='cuda:0')
episode: 437 training return: tensor(-999.9832, device='cuda:0')
episode: 438 training return: tensor(-999.9618, device='cuda:0')
episode: 439 training return: tensor(-999.9777, device='cuda:0')
epoch: 110 test_true_pfm: -0.3355953217865331 sim_pfm: -999.8912096222242
episode: 440 training return: tensor(-999.9819, device='cuda:0')
episode: 441 training return: tensor(-999.9677, device='cuda:0')
episode: 442 training return: tensor(-999.9734, device='cuda:0')
episode: 443 training return: tensor(-999.9333, device='cuda:0')
epoch: 111 test_true_pfm: -0.10902647839024639 sim_pfm: -999.8919291694959
episode: 444 training return: tensor(-999.9683, device='cuda:0')
episode: 445 training return: tensor(-999.9866, device='cuda:0')
episode: 446 training return: tensor(-999.9746, device='cuda:0')
episode: 447 training return: tensor(-999.9844, device='cuda:0')
epoch: 112 test_true_pfm: -0.4604713443517629 sim_pfm: -999.89337793986
episode: 448 training return: tensor(-999.9826, device='cuda:0')
episode: 449 training return: tensor(-999.9722, device='cuda:0')
episode: 450 training return: tensor(-999.9759, device='cuda:0')
episode: 451 training return: tensor(-999.9839, device='cuda:0')
epoch: 113 test_true_pfm: -0.3232966126477889 sim_pfm: -999.8916007876396
episode: 452 training return: tensor(-999.9305, device='cuda:0')
episode: 453 training return: tensor(-999.9706, device='cuda:0')
episode: 454 training return: tensor(-999.9870, device='cuda:0')
episode: 455 training return: tensor(-999.9810, device='cuda:0')
epoch: 114 test_true_pfm: -0.6632183141039736 sim_pfm: -999.8913639585177
episode: 456 training return: tensor(-999.9799, device='cuda:0')
episode: 457 training return: tensor(-999.9788, device='cuda:0')
episode: 458 training return: tensor(-999.9624, device='cuda:0')
episode: 459 training return: tensor(-999.9794, device='cuda:0')
epoch: 115 test_true_pfm: -1.1903961245246493 sim_pfm: -999.8921816945076
episode: 460 training return: tensor(-999.9275, device='cuda:0')
episode: 461 training return: tensor(-999.9731, device='cuda:0')
episode: 462 training return: tensor(-999.9450, device='cuda:0')
episode: 463 training return: tensor(-999.9855, device='cuda:0')
epoch: 116 test_true_pfm: -0.22435407276221944 sim_pfm: -999.892999390761
episode: 464 training return: tensor(-999.9671, device='cuda:0')
episode: 465 training return: tensor(-999.9811, device='cuda:0')
episode: 466 training return: tensor(-999.9791, device='cuda:0')
episode: 467 training return: tensor(-999.9824, device='cuda:0')
epoch: 117 test_true_pfm: -0.38469471944185357 sim_pfm: -999.892768839995
episode: 468 training return: tensor(-999.9736, device='cuda:0')
episode: 469 training return: tensor(-999.9507, device='cuda:0')
episode: 470 training return: tensor(-999.9792, device='cuda:0')
episode: 471 training return: tensor(-999.9685, device='cuda:0')
epoch: 118 test_true_pfm: -0.6181862337674113 sim_pfm: -999.8917986154556
episode: 472 training return: tensor(-999.9238, device='cuda:0')
episode: 473 training return: tensor(-999.9796, device='cuda:0')
episode: 474 training return: tensor(-999.9839, device='cuda:0')
episode: 475 training return: tensor(-999.9447, device='cuda:0')
epoch: 119 test_true_pfm: -0.4644870641934218 sim_pfm: -999.8919204076132
episode: 476 training return: tensor(-999.9772, device='cuda:0')
episode: 477 training return: tensor(-999.9588, device='cuda:0')
episode: 478 training return: tensor(-999.9139, device='cuda:0')
episode: 479 training return: tensor(-999.9801, device='cuda:0')
epoch: 120 test_true_pfm: -0.024544308510664026 sim_pfm: -999.8930584192276
episode: 480 training return: tensor(-999.9204, device='cuda:0')
episode: 481 training return: tensor(-999.9791, device='cuda:0')
episode: 482 training return: tensor(-999.9805, device='cuda:0')
episode: 483 training return: tensor(-999.9786, device='cuda:0')
epoch: 121 test_true_pfm: -0.6054832538325992 sim_pfm: -999.8906476895014
episode: 484 training return: tensor(-999.9557, device='cuda:0')
episode: 485 training return: tensor(-999.9659, device='cuda:0')
episode: 486 training return: tensor(-999.9722, device='cuda:0')
episode: 487 training return: tensor(-999.9723, device='cuda:0')
epoch: 122 test_true_pfm: -0.3449700974410126 sim_pfm: -999.8926668564478
episode: 488 training return: tensor(-999.9401, device='cuda:0')
episode: 489 training return: tensor(-999.9756, device='cuda:0')
episode: 490 training return: tensor(-999.9771, device='cuda:0')
episode: 491 training return: tensor(-999.9808, device='cuda:0')
epoch: 123 test_true_pfm: -0.20341996848401936 sim_pfm: -999.8915875355402
episode: 492 training return: tensor(-999.9758, device='cuda:0')
episode: 493 training return: tensor(-999.9776, device='cuda:0')
episode: 494 training return: tensor(-999.9835, device='cuda:0')
episode: 495 training return: tensor(-999.9695, device='cuda:0')
epoch: 124 test_true_pfm: 0.10936642726902644 sim_pfm: -999.8931813637415
episode: 496 training return: tensor(-999.9709, device='cuda:0')
episode: 497 training return: tensor(-999.9698, device='cuda:0')
episode: 498 training return: tensor(-999.9653, device='cuda:0')
episode: 499 training return: tensor(-999.9853, device='cuda:0')
epoch: 125 test_true_pfm: -0.3315047088008312 sim_pfm: -999.8921276926994
episode: 500 training return: tensor(-999.9258, device='cuda:0')
episode: 501 training return: tensor(-999.9780, device='cuda:0')
episode: 502 training return: tensor(-999.9878, device='cuda:0')
episode: 503 training return: tensor(-999.9587, device='cuda:0')
epoch: 126 test_true_pfm: -0.20371256220302236 sim_pfm: -999.8917591373125
episode: 504 training return: tensor(-999.9548, device='cuda:0')
episode: 505 training return: tensor(-999.9883, device='cuda:0')
episode: 506 training return: tensor(-999.9667, device='cuda:0')
episode: 507 training return: tensor(-999.9622, device='cuda:0')
epoch: 127 test_true_pfm: 0.05071588275742837 sim_pfm: -999.8908634583155
episode: 508 training return: tensor(-999.9575, device='cuda:0')
episode: 509 training return: tensor(-999.9849, device='cuda:0')
episode: 510 training return: tensor(-999.9345, device='cuda:0')
episode: 511 training return: tensor(-999.9509, device='cuda:0')
epoch: 128 test_true_pfm: 0.24195414356398817 sim_pfm: -999.8914525707563
episode: 512 training return: tensor(-999.9213, device='cuda:0')
episode: 513 training return: tensor(-999.9777, device='cuda:0')
episode: 514 training return: tensor(-999.9724, device='cuda:0')
episode: 515 training return: tensor(-999.9437, device='cuda:0')
epoch: 129 test_true_pfm: 0.13756806503734706 sim_pfm: -999.8922609885534
episode: 516 training return: tensor(-999.9606, device='cuda:0')
episode: 517 training return: tensor(-999.9778, device='cuda:0')
episode: 518 training return: tensor(-999.9802, device='cuda:0')
episode: 519 training return: tensor(-999.9833, device='cuda:0')
epoch: 130 test_true_pfm: -0.14186316532529275 sim_pfm: -999.8913286129633
episode: 520 training return: tensor(-999.9746, device='cuda:0')
episode: 521 training return: tensor(-999.9850, device='cuda:0')
episode: 522 training return: tensor(-999.9745, device='cuda:0')
episode: 523 training return: tensor(-999.9557, device='cuda:0')
epoch: 131 test_true_pfm: -0.51264164196518 sim_pfm: -999.8914679288864
episode: 524 training return: tensor(-999.9749, device='cuda:0')
episode: 525 training return: tensor(-999.9739, device='cuda:0')
episode: 526 training return: tensor(-999.9803, device='cuda:0')
episode: 527 training return: tensor(-999.9802, device='cuda:0')
epoch: 132 test_true_pfm: -0.3894850767925955 sim_pfm: -999.8918889760971
episode: 528 training return: tensor(-999.9785, device='cuda:0')
episode: 529 training return: tensor(-999.9705, device='cuda:0')
episode: 530 training return: tensor(-999.9827, device='cuda:0')
episode: 531 training return: tensor(-999.9845, device='cuda:0')
epoch: 133 test_true_pfm: 0.23928172858834285 sim_pfm: -999.8925670584043
episode: 532 training return: tensor(-999.9586, device='cuda:0')
episode: 533 training return: tensor(-999.9838, device='cuda:0')
episode: 534 training return: tensor(-999.9510, device='cuda:0')
episode: 535 training return: tensor(-999.9725, device='cuda:0')
epoch: 134 test_true_pfm: -0.09651654154302884 sim_pfm: -999.8927648464838
episode: 536 training return: tensor(-999.9487, device='cuda:0')
episode: 537 training return: tensor(-999.9841, device='cuda:0')
episode: 538 training return: tensor(-999.9174, device='cuda:0')
episode: 539 training return: tensor(-999.9624, device='cuda:0')
epoch: 135 test_true_pfm: -0.4209811375874648 sim_pfm: -999.8918104767799
episode: 540 training return: tensor(-999.9771, device='cuda:0')
episode: 541 training return: tensor(-999.9730, device='cuda:0')
episode: 542 training return: tensor(-999.9784, device='cuda:0')
episode: 543 training return: tensor(-999.9742, device='cuda:0')
epoch: 136 test_true_pfm: -0.10425125373734805 sim_pfm: -999.8912932872772
episode: 544 training return: tensor(-999.9709, device='cuda:0')
episode: 545 training return: tensor(-999.9840, device='cuda:0')
episode: 546 training return: tensor(-999.9769, device='cuda:0')
episode: 547 training return: tensor(-999.9799, device='cuda:0')
epoch: 137 test_true_pfm: -0.05204060017818124 sim_pfm: -999.8925874233246
episode: 548 training return: tensor(-999.9164, device='cuda:0')
episode: 549 training return: tensor(-999.9686, device='cuda:0')
episode: 550 training return: tensor(-999.9818, device='cuda:0')
episode: 551 training return: tensor(-999.9706, device='cuda:0')
epoch: 138 test_true_pfm: -0.22122913797903024 sim_pfm: -999.8908328016599
episode: 552 training return: tensor(-999.9872, device='cuda:0')
episode: 553 training return: tensor(-999.9682, device='cuda:0')
episode: 554 training return: tensor(-999.9790, device='cuda:0')
episode: 555 training return: tensor(-999.9730, device='cuda:0')
epoch: 139 test_true_pfm: -0.16805686317627044 sim_pfm: -999.891910970211
episode: 556 training return: tensor(-999.9604, device='cuda:0')
episode: 557 training return: tensor(-999.9568, device='cuda:0')
episode: 558 training return: tensor(-999.9808, device='cuda:0')
episode: 559 training return: tensor(-999.9829, device='cuda:0')
epoch: 140 test_true_pfm: -0.3358378465271388 sim_pfm: -999.8910418351492
episode: 560 training return: tensor(-999.9719, device='cuda:0')
episode: 561 training return: tensor(-999.9741, device='cuda:0')
episode: 562 training return: tensor(-999.9692, device='cuda:0')
episode: 563 training return: tensor(-999.9668, device='cuda:0')
epoch: 141 test_true_pfm: -0.04241829017306248 sim_pfm: -999.8927257855734
episode: 564 training return: tensor(-999.9808, device='cuda:0')
episode: 565 training return: tensor(-999.9698, device='cuda:0')
episode: 566 training return: tensor(-999.9789, device='cuda:0')
episode: 567 training return: tensor(-999.9567, device='cuda:0')
epoch: 142 test_true_pfm: -0.8545818957728132 sim_pfm: -999.8922601342201
episode: 568 training return: tensor(-999.9268, device='cuda:0')
episode: 569 training return: tensor(-999.9455, device='cuda:0')
episode: 570 training return: tensor(-999.9536, device='cuda:0')
episode: 571 training return: tensor(-999.9792, device='cuda:0')
epoch: 143 test_true_pfm: -0.2811804351716165 sim_pfm: -999.891199251016
episode: 572 training return: tensor(-999.9747, device='cuda:0')
episode: 573 training return: tensor(-999.9769, device='cuda:0')
episode: 574 training return: tensor(-999.9802, device='cuda:0')
episode: 575 training return: tensor(-999.7950, device='cuda:0')
epoch: 144 test_true_pfm: 0.20259699572266476 sim_pfm: -999.8914281725883
episode: 576 training return: tensor(-999.9761, device='cuda:0')
episode: 577 training return: tensor(-999.9852, device='cuda:0')
episode: 578 training return: tensor(-999.9781, device='cuda:0')
episode: 579 training return: tensor(-999.9842, device='cuda:0')
epoch: 145 test_true_pfm: -0.1856177154724715 sim_pfm: -999.8903688788414
episode: 580 training return: tensor(-999.9841, device='cuda:0')
episode: 581 training return: tensor(-999.9479, device='cuda:0')
episode: 582 training return: tensor(-999.9869, device='cuda:0')
episode: 583 training return: tensor(-999.9757, device='cuda:0')
epoch: 146 test_true_pfm: -0.1958075339002063 sim_pfm: -999.8920693000158
episode: 584 training return: tensor(-999.9715, device='cuda:0')
episode: 585 training return: tensor(-999.9818, device='cuda:0')
episode: 586 training return: tensor(-999.9784, device='cuda:0')
episode: 587 training return: tensor(-999.9807, device='cuda:0')
epoch: 147 test_true_pfm: -0.472942959952459 sim_pfm: -999.8917349974314
episode: 588 training return: tensor(-999.9718, device='cuda:0')
episode: 589 training return: tensor(-999.9458, device='cuda:0')
episode: 590 training return: tensor(-999.9645, device='cuda:0')
episode: 591 training return: tensor(-999.9696, device='cuda:0')
epoch: 148 test_true_pfm: -0.5109363021624396 sim_pfm: -999.8915470043818
episode: 592 training return: tensor(-999.9806, device='cuda:0')
episode: 593 training return: tensor(-999.9584, device='cuda:0')
episode: 594 training return: tensor(-999.9675, device='cuda:0')
episode: 595 training return: tensor(-999.9817, device='cuda:0')
epoch: 149 test_true_pfm: 0.10185082711065178 sim_pfm: -999.8919882376989
episode: 596 training return: tensor(-999.9608, device='cuda:0')
episode: 597 training return: tensor(-999.9856, device='cuda:0')
episode: 598 training return: tensor(-999.9616, device='cuda:0')
episode: 599 training return: tensor(-999.9733, device='cuda:0')
epoch: 150 test_true_pfm: -0.5017844648402586 sim_pfm: -999.8922117551168
