['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'baseline', '--traj', 'medium', '--seed', '1']
episode: 0 training return: tensor(-999.9987, device='cuda:0')
episode: 1 training return: tensor(-999.9929, device='cuda:0')
episode: 2 training return: tensor(-999.9977, device='cuda:0')
episode: 3 training return: tensor(-999.9985, device='cuda:0')
epoch: 1 test_true_pfm: 0.5035542043090661 sim_pfm: -999.9866109291712
episode: 4 training return: tensor(-999.9974, device='cuda:0')
episode: 5 training return: tensor(-999.9981, device='cuda:0')
episode: 6 training return: tensor(-999.9927, device='cuda:0')
episode: 7 training return: tensor(-999.9988, device='cuda:0')
epoch: 2 test_true_pfm: -0.20237742966401032 sim_pfm: -999.9864921371142
episode: 8 training return: tensor(-999.9946, device='cuda:0')
episode: 9 training return: tensor(-999.9987, device='cuda:0')
episode: 10 training return: tensor(-999.9813, device='cuda:0')
episode: 11 training return: tensor(-999.9966, device='cuda:0')
epoch: 3 test_true_pfm: -0.12557226310439581 sim_pfm: -999.9866071542104
episode: 12 training return: tensor(-999.9930, device='cuda:0')
episode: 13 training return: tensor(-999.9861, device='cuda:0')
episode: 14 training return: tensor(-999.9879, device='cuda:0')
episode: 15 training return: tensor(-999.9930, device='cuda:0')
epoch: 4 test_true_pfm: 0.21407826696025986 sim_pfm: -999.9866223533949
episode: 16 training return: tensor(-999.9962, device='cuda:0')
episode: 17 training return: tensor(-999.9985, device='cuda:0')
episode: 18 training return: tensor(-999.9960, device='cuda:0')
episode: 19 training return: tensor(-999.9913, device='cuda:0')
epoch: 5 test_true_pfm: 0.08262607003480417 sim_pfm: -999.9865512053171
episode: 20 training return: tensor(-999.9946, device='cuda:0')
episode: 21 training return: tensor(-999.9929, device='cuda:0')
episode: 22 training return: tensor(-999.9929, device='cuda:0')
episode: 23 training return: tensor(-999.9980, device='cuda:0')
epoch: 6 test_true_pfm: -0.4444787989858487 sim_pfm: -999.9866951505343
episode: 24 training return: tensor(-999.9986, device='cuda:0')
episode: 25 training return: tensor(-999.9975, device='cuda:0')
episode: 26 training return: tensor(-999.9980, device='cuda:0')
episode: 27 training return: tensor(-999.9957, device='cuda:0')
epoch: 7 test_true_pfm: -1.3044692946162897 sim_pfm: -999.9865102569262
episode: 28 training return: tensor(-999.9879, device='cuda:0')
episode: 29 training return: tensor(-999.9962, device='cuda:0')
episode: 30 training return: tensor(-999.9993, device='cuda:0')
episode: 31 training return: tensor(-999.9993, device='cuda:0')
epoch: 8 test_true_pfm: -0.3841001255387841 sim_pfm: -999.9865544637045
episode: 32 training return: tensor(-999.9913, device='cuda:0')
episode: 33 training return: tensor(-999.9973, device='cuda:0')
episode: 34 training return: tensor(-999.9894, device='cuda:0')
episode: 35 training return: tensor(-999.9927, device='cuda:0')
epoch: 9 test_true_pfm: -0.3653402766673027 sim_pfm: -999.9865481257439
episode: 36 training return: tensor(-999.9973, device='cuda:0')
episode: 37 training return: tensor(-999.9966, device='cuda:0')
episode: 38 training return: tensor(-999.9943, device='cuda:0')
episode: 39 training return: tensor(-999.9986, device='cuda:0')
epoch: 10 test_true_pfm: -0.6452251036310683 sim_pfm: -999.9865455230077
episode: 40 training return: tensor(-999.9971, device='cuda:0')
episode: 41 training return: tensor(-999.9977, device='cuda:0')
episode: 42 training return: tensor(-999.9987, device='cuda:0')
episode: 43 training return: tensor(-999.9985, device='cuda:0')
epoch: 11 test_true_pfm: 0.09266804427435127 sim_pfm: -999.9864782094955
episode: 44 training return: tensor(-999.9984, device='cuda:0')
episode: 45 training return: tensor(-999.9988, device='cuda:0')
episode: 46 training return: tensor(-999.9912, device='cuda:0')
episode: 47 training return: tensor(-999.9972, device='cuda:0')
epoch: 12 test_true_pfm: -0.14366949591083444 sim_pfm: -999.9865553975105
episode: 48 training return: tensor(-999.9962, device='cuda:0')
episode: 49 training return: tensor(-999.9945, device='cuda:0')
episode: 50 training return: tensor(-999.9982, device='cuda:0')
episode: 51 training return: tensor(-999.9966, device='cuda:0')
epoch: 13 test_true_pfm: -0.29402946195542506 sim_pfm: -999.9864395459493
episode: 52 training return: tensor(-999.9980, device='cuda:0')
episode: 53 training return: tensor(-999.9941, device='cuda:0')
episode: 54 training return: tensor(-999.9917, device='cuda:0')
episode: 55 training return: tensor(-999.9977, device='cuda:0')
epoch: 14 test_true_pfm: -0.9482346673926069 sim_pfm: -999.9866323669752
episode: 56 training return: tensor(-999.9967, device='cuda:0')
episode: 57 training return: tensor(-999.9941, device='cuda:0')
episode: 58 training return: tensor(-999.9990, device='cuda:0')
episode: 59 training return: tensor(-999.9943, device='cuda:0')
epoch: 15 test_true_pfm: -0.5530385566499276 sim_pfm: -999.9865817626318
episode: 60 training return: tensor(-999.9951, device='cuda:0')
episode: 61 training return: tensor(-999.9985, device='cuda:0')
episode: 62 training return: tensor(-999.9875, device='cuda:0')
episode: 63 training return: tensor(-999.9986, device='cuda:0')
epoch: 16 test_true_pfm: 0.11492247176536198 sim_pfm: -999.986487587293
episode: 64 training return: tensor(-999.9943, device='cuda:0')
episode: 65 training return: tensor(-999.9986, device='cuda:0')
episode: 66 training return: tensor(-999.9935, device='cuda:0')
episode: 67 training return: tensor(-999.9946, device='cuda:0')
epoch: 17 test_true_pfm: 0.30768492436959605 sim_pfm: -999.9865513046583
episode: 68 training return: tensor(-999.9963, device='cuda:0')
episode: 69 training return: tensor(-999.9979, device='cuda:0')
episode: 70 training return: tensor(-999.9971, device='cuda:0')
episode: 71 training return: tensor(-999.9981, device='cuda:0')
epoch: 18 test_true_pfm: 0.042861403808844255 sim_pfm: -999.9865982929865
episode: 72 training return: tensor(-999.9894, device='cuda:0')
episode: 73 training return: tensor(-999.9988, device='cuda:0')
episode: 74 training return: tensor(-999.9984, device='cuda:0')
episode: 75 training return: tensor(-999.9988, device='cuda:0')
epoch: 19 test_true_pfm: 0.5539830560052934 sim_pfm: -999.986490825812
episode: 76 training return: tensor(-999.9968, device='cuda:0')
episode: 77 training return: tensor(-999.9980, device='cuda:0')
episode: 78 training return: tensor(-999.9963, device='cuda:0')
episode: 79 training return: tensor(-999.9926, device='cuda:0')
epoch: 20 test_true_pfm: -0.0807052312030841 sim_pfm: -999.9865579803785
episode: 80 training return: tensor(-999.9938, device='cuda:0')
episode: 81 training return: tensor(-999.9914, device='cuda:0')
episode: 82 training return: tensor(-999.9918, device='cuda:0')
episode: 83 training return: tensor(-999.9910, device='cuda:0')
epoch: 21 test_true_pfm: -0.09178015287373849 sim_pfm: -999.9865484833717
episode: 84 training return: tensor(-999.9977, device='cuda:0')
episode: 85 training return: tensor(-999.9879, device='cuda:0')
episode: 86 training return: tensor(-999.9985, device='cuda:0')
episode: 87 training return: tensor(-999.9986, device='cuda:0')
epoch: 22 test_true_pfm: -0.5814181705150102 sim_pfm: -999.9864947398504
episode: 88 training return: tensor(-999.9946, device='cuda:0')
episode: 89 training return: tensor(-999.9977, device='cuda:0')
episode: 90 training return: tensor(-999.9952, device='cuda:0')
episode: 91 training return: tensor(-999.9984, device='cuda:0')
epoch: 23 test_true_pfm: -0.8630910213818997 sim_pfm: -999.9864357709885
episode: 92 training return: tensor(-999.9915, device='cuda:0')
episode: 93 training return: tensor(-999.9983, device='cuda:0')
episode: 94 training return: tensor(-999.9958, device='cuda:0')
episode: 95 training return: tensor(-999.9974, device='cuda:0')
epoch: 24 test_true_pfm: -1.2105189690425753 sim_pfm: -999.9867260654768
episode: 96 training return: tensor(-999.9979, device='cuda:0')
episode: 97 training return: tensor(-999.9976, device='cuda:0')
episode: 98 training return: tensor(-999.9988, device='cuda:0')
episode: 99 training return: tensor(-999.9902, device='cuda:0')
epoch: 25 test_true_pfm: -0.9621377039035829 sim_pfm: -999.9864863355955
episode: 100 training return: tensor(-999.9994, device='cuda:0')
episode: 101 training return: tensor(-999.9943, device='cuda:0')
episode: 102 training return: tensor(-999.9993, device='cuda:0')
episode: 103 training return: tensor(-999.9982, device='cuda:0')
epoch: 26 test_true_pfm: -0.5050057106115988 sim_pfm: -999.986560344696
episode: 104 training return: tensor(-999.9985, device='cuda:0')
episode: 105 training return: tensor(-999.9943, device='cuda:0')
episode: 106 training return: tensor(-999.9913, device='cuda:0')
episode: 107 training return: tensor(-999.9988, device='cuda:0')
epoch: 27 test_true_pfm: -0.16737158067015587 sim_pfm: -999.9865493178368
episode: 108 training return: tensor(-999.9979, device='cuda:0')
episode: 109 training return: tensor(-999.9946, device='cuda:0')
episode: 110 training return: tensor(-999.9962, device='cuda:0')
episode: 111 training return: tensor(-999.9962, device='cuda:0')
epoch: 28 test_true_pfm: -0.7739013399421047 sim_pfm: -999.9865532120069
episode: 112 training return: tensor(-999.9982, device='cuda:0')
episode: 113 training return: tensor(-999.9914, device='cuda:0')
episode: 114 training return: tensor(-999.9882, device='cuda:0')
episode: 115 training return: tensor(-999.9987, device='cuda:0')
epoch: 29 test_true_pfm: -0.14300201392834214 sim_pfm: -999.9865823586782
episode: 116 training return: tensor(-999.9858, device='cuda:0')
episode: 117 training return: tensor(-999.9987, device='cuda:0')
episode: 118 training return: tensor(-999.9881, device='cuda:0')
episode: 119 training return: tensor(-999.9904, device='cuda:0')
epoch: 30 test_true_pfm: 0.274741580519706 sim_pfm: -999.9865589936575
episode: 120 training return: tensor(-999.9987, device='cuda:0')
episode: 121 training return: tensor(-999.9977, device='cuda:0')
episode: 122 training return: tensor(-999.9933, device='cuda:0')
episode: 123 training return: tensor(-999.9963, device='cuda:0')
epoch: 31 test_true_pfm: -0.9188661382668992 sim_pfm: -999.9866618116697
episode: 124 training return: tensor(-999.9887, device='cuda:0')
episode: 125 training return: tensor(-999.9890, device='cuda:0')
episode: 126 training return: tensor(-999.9926, device='cuda:0')
episode: 127 training return: tensor(-999.9979, device='cuda:0')
epoch: 32 test_true_pfm: -0.6430519218478827 sim_pfm: -999.9864873091379
episode: 128 training return: tensor(-999.9984, device='cuda:0')
episode: 129 training return: tensor(-999.9982, device='cuda:0')
episode: 130 training return: tensor(-999.9992, device='cuda:0')
episode: 131 training return: tensor(-999.9973, device='cuda:0')
epoch: 33 test_true_pfm: -0.8425558955027936 sim_pfm: -999.9865331252416
episode: 132 training return: tensor(-999.9874, device='cuda:0')
episode: 133 training return: tensor(-999.9879, device='cuda:0')
episode: 134 training return: tensor(-999.9928, device='cuda:0')
episode: 135 training return: tensor(-999.9967, device='cuda:0')
epoch: 34 test_true_pfm: -0.8073079918496417 sim_pfm: -999.9866642753283
episode: 136 training return: tensor(-999.9979, device='cuda:0')
episode: 137 training return: tensor(-999.9957, device='cuda:0')
episode: 138 training return: tensor(-999.9983, device='cuda:0')
episode: 139 training return: tensor(-999.9897, device='cuda:0')
epoch: 35 test_true_pfm: -0.24583937100148254 sim_pfm: -999.9864734013876
episode: 140 training return: tensor(-999.9868, device='cuda:0')
episode: 141 training return: tensor(-999.9932, device='cuda:0')
episode: 142 training return: tensor(-999.9954, device='cuda:0')
episode: 143 training return: tensor(-999.9941, device='cuda:0')
epoch: 36 test_true_pfm: -0.05514039569588972 sim_pfm: -999.9865169127783
episode: 144 training return: tensor(-999.9958, device='cuda:0')
episode: 145 training return: tensor(-999.9980, device='cuda:0')
episode: 146 training return: tensor(-999.9982, device='cuda:0')
episode: 147 training return: tensor(-999.9976, device='cuda:0')
epoch: 37 test_true_pfm: -0.14327354081579816 sim_pfm: -999.9865539272627
episode: 148 training return: tensor(-999.9832, device='cuda:0')
episode: 149 training return: tensor(-999.9976, device='cuda:0')
episode: 150 training return: tensor(-999.9966, device='cuda:0')
episode: 151 training return: tensor(-999.9937, device='cuda:0')
epoch: 38 test_true_pfm: -0.5245475583915467 sim_pfm: -999.9865401983261
episode: 152 training return: tensor(-999.9989, device='cuda:0')
episode: 153 training return: tensor(-999.9979, device='cuda:0')
episode: 154 training return: tensor(-999.9925, device='cuda:0')
episode: 155 training return: tensor(-999.9882, device='cuda:0')
epoch: 39 test_true_pfm: -0.04172052571130117 sim_pfm: -999.9864921569824
episode: 156 training return: tensor(-999.9963, device='cuda:0')
episode: 157 training return: tensor(-999.9993, device='cuda:0')
episode: 158 training return: tensor(-999.9964, device='cuda:0')
episode: 159 training return: tensor(-999.9934, device='cuda:0')
epoch: 40 test_true_pfm: -0.04221892311649178 sim_pfm: -999.9866055250168
episode: 160 training return: tensor(-999.9970, device='cuda:0')
episode: 161 training return: tensor(-999.9866, device='cuda:0')
episode: 162 training return: tensor(-999.9973, device='cuda:0')
episode: 163 training return: tensor(-999.9816, device='cuda:0')
epoch: 41 test_true_pfm: -0.32736998685709634 sim_pfm: -999.9864875078201
episode: 164 training return: tensor(-999.9966, device='cuda:0')
episode: 165 training return: tensor(-999.9949, device='cuda:0')
episode: 166 training return: tensor(-999.9987, device='cuda:0')
episode: 167 training return: tensor(-999.9984, device='cuda:0')
epoch: 42 test_true_pfm: -0.320001677498653 sim_pfm: -999.9864844083786
episode: 168 training return: tensor(-999.9984, device='cuda:0')
episode: 169 training return: tensor(-999.9932, device='cuda:0')
episode: 170 training return: tensor(-999.9980, device='cuda:0')
episode: 171 training return: tensor(-999.9955, device='cuda:0')
epoch: 43 test_true_pfm: -0.11462420825097419 sim_pfm: -999.9866062800089
episode: 172 training return: tensor(-999.9973, device='cuda:0')
episode: 173 training return: tensor(-999.9991, device='cuda:0')
episode: 174 training return: tensor(-999.9964, device='cuda:0')
episode: 175 training return: tensor(-999.9974, device='cuda:0')
epoch: 44 test_true_pfm: 0.49713461705958806 sim_pfm: -999.9866166114807
episode: 176 training return: tensor(-999.9990, device='cuda:0')
episode: 177 training return: tensor(-999.9977, device='cuda:0')
episode: 178 training return: tensor(-999.9989, device='cuda:0')
episode: 179 training return: tensor(-999.9984, device='cuda:0')
epoch: 45 test_true_pfm: -0.332708001154127 sim_pfm: -999.9865973989168
episode: 180 training return: tensor(-999.9987, device='cuda:0')
episode: 181 training return: tensor(-999.9956, device='cuda:0')
episode: 182 training return: tensor(-999.9982, device='cuda:0')
episode: 183 training return: tensor(-999.9828, device='cuda:0')
epoch: 46 test_true_pfm: 0.05694270087035874 sim_pfm: -999.9867120583853
episode: 184 training return: tensor(-999.9975, device='cuda:0')
episode: 185 training return: tensor(-999.9984, device='cuda:0')
episode: 186 training return: tensor(-999.9929, device='cuda:0')
episode: 187 training return: tensor(-999.9993, device='cuda:0')
epoch: 47 test_true_pfm: -0.642278768236665 sim_pfm: -999.9865329265594
episode: 188 training return: tensor(-999.9975, device='cuda:0')
episode: 189 training return: tensor(-999.9919, device='cuda:0')
episode: 190 training return: tensor(-999.9983, device='cuda:0')
episode: 191 training return: tensor(-999.9902, device='cuda:0')
epoch: 48 test_true_pfm: -0.4543794436266315 sim_pfm: -999.9866079688072
episode: 192 training return: tensor(-999.9982, device='cuda:0')
episode: 193 training return: tensor(-999.9943, device='cuda:0')
episode: 194 training return: tensor(-999.9861, device='cuda:0')
episode: 195 training return: tensor(-999.9991, device='cuda:0')
epoch: 49 test_true_pfm: -0.08248724229771465 sim_pfm: -999.9865281979243
episode: 196 training return: tensor(-999.9838, device='cuda:0')
episode: 197 training return: tensor(-999.9980, device='cuda:0')
episode: 198 training return: tensor(-999.9957, device='cuda:0')
episode: 199 training return: tensor(-999.9978, device='cuda:0')
epoch: 50 test_true_pfm: -0.5895690953069265 sim_pfm: -999.9866040349007
episode: 200 training return: tensor(-999.9985, device='cuda:0')
episode: 201 training return: tensor(-999.9979, device='cuda:0')
episode: 202 training return: tensor(-999.9958, device='cuda:0')
episode: 203 training return: tensor(-999.9990, device='cuda:0')
epoch: 51 test_true_pfm: 0.34476321556732864 sim_pfm: -999.9865635832151
episode: 204 training return: tensor(-999.9974, device='cuda:0')
episode: 205 training return: tensor(-999.9940, device='cuda:0')
episode: 206 training return: tensor(-999.9960, device='cuda:0')
episode: 207 training return: tensor(-999.9900, device='cuda:0')
epoch: 52 test_true_pfm: -0.460020803509916 sim_pfm: -999.9865373969078
episode: 208 training return: tensor(-999.9905, device='cuda:0')
episode: 209 training return: tensor(-999.9986, device='cuda:0')
episode: 210 training return: tensor(-999.9988, device='cuda:0')
episode: 211 training return: tensor(-999.9927, device='cuda:0')
epoch: 53 test_true_pfm: 0.358597471625846 sim_pfm: -999.9865694642067
episode: 212 training return: tensor(-999.9994, device='cuda:0')
episode: 213 training return: tensor(-999.9955, device='cuda:0')
episode: 214 training return: tensor(-999.9977, device='cuda:0')
episode: 215 training return: tensor(-999.9984, device='cuda:0')
epoch: 54 test_true_pfm: -1.5700747449683832 sim_pfm: -999.9864893953005
episode: 216 training return: tensor(-999.9880, device='cuda:0')
episode: 217 training return: tensor(-999.9882, device='cuda:0')
episode: 218 training return: tensor(-999.9833, device='cuda:0')
episode: 219 training return: tensor(-999.9968, device='cuda:0')
epoch: 55 test_true_pfm: -1.1416802690543113 sim_pfm: -999.9864086111387
episode: 220 training return: tensor(-999.9990, device='cuda:0')
episode: 221 training return: tensor(-999.9983, device='cuda:0')
episode: 222 training return: tensor(-999.9985, device='cuda:0')
episode: 223 training return: tensor(-999.9819, device='cuda:0')
epoch: 56 test_true_pfm: 0.051968845264119344 sim_pfm: -999.9865423838297
episode: 224 training return: tensor(-999.9981, device='cuda:0')
episode: 225 training return: tensor(-999.9969, device='cuda:0')
episode: 226 training return: tensor(-999.9987, device='cuda:0')
episode: 227 training return: tensor(-999.9969, device='cuda:0')
epoch: 57 test_true_pfm: -0.4250614258616497 sim_pfm: -999.9866812030474
episode: 228 training return: tensor(-999.9979, device='cuda:0')
episode: 229 training return: tensor(-999.9979, device='cuda:0')
episode: 230 training return: tensor(-999.9962, device='cuda:0')
episode: 231 training return: tensor(-999.9984, device='cuda:0')
epoch: 58 test_true_pfm: -0.658128164663744 sim_pfm: -999.9865967432657
episode: 232 training return: tensor(-999.9979, device='cuda:0')
episode: 233 training return: tensor(-999.9968, device='cuda:0')
episode: 234 training return: tensor(-999.9987, device='cuda:0')
episode: 235 training return: tensor(-999.9985, device='cuda:0')
epoch: 59 test_true_pfm: 0.11381047511797941 sim_pfm: -999.9865289330482
episode: 236 training return: tensor(-999.9991, device='cuda:0')
episode: 237 training return: tensor(-999.9941, device='cuda:0')
episode: 238 training return: tensor(-999.9978, device='cuda:0')
episode: 239 training return: tensor(-999.9976, device='cuda:0')
epoch: 60 test_true_pfm: -0.30301995956317873 sim_pfm: -999.9865348339081
episode: 240 training return: tensor(-999.9965, device='cuda:0')
episode: 241 training return: tensor(-999.9919, device='cuda:0')
episode: 242 training return: tensor(-999.9911, device='cuda:0')
episode: 243 training return: tensor(-999.9986, device='cuda:0')
epoch: 61 test_true_pfm: 0.11384057774931393 sim_pfm: -999.9866731762886
episode: 244 training return: tensor(-999.9986, device='cuda:0')
episode: 245 training return: tensor(-999.9980, device='cuda:0')
episode: 246 training return: tensor(-999.9969, device='cuda:0')
episode: 247 training return: tensor(-999.9996, device='cuda:0')
epoch: 62 test_true_pfm: -0.08779586978211325 sim_pfm: -999.9865633249283
episode: 248 training return: tensor(-999.9901, device='cuda:0')
episode: 249 training return: tensor(-999.9998, device='cuda:0')
episode: 250 training return: tensor(-999.9981, device='cuda:0')
episode: 251 training return: tensor(-999.9993, device='cuda:0')
epoch: 63 test_true_pfm: 0.010469676367926764 sim_pfm: -999.9866744478544
episode: 252 training return: tensor(-999.9948, device='cuda:0')
episode: 253 training return: tensor(-999.9976, device='cuda:0')
episode: 254 training return: tensor(-999.9944, device='cuda:0')
episode: 255 training return: tensor(-999.9974, device='cuda:0')
epoch: 64 test_true_pfm: 0.633568901869959 sim_pfm: -999.9865012168884
episode: 256 training return: tensor(-999.9971, device='cuda:0')
episode: 257 training return: tensor(-999.9984, device='cuda:0')
episode: 258 training return: tensor(-999.9986, device='cuda:0')
episode: 259 training return: tensor(-999.9977, device='cuda:0')
epoch: 65 test_true_pfm: -0.547381354822913 sim_pfm: -999.9864742159843
episode: 260 training return: tensor(-999.9976, device='cuda:0')
episode: 261 training return: tensor(-999.9903, device='cuda:0')
episode: 262 training return: tensor(-999.9963, device='cuda:0')
episode: 263 training return: tensor(-999.9987, device='cuda:0')
epoch: 66 test_true_pfm: -0.22460188427915004 sim_pfm: -999.9866072734197
episode: 264 training return: tensor(-999.9996, device='cuda:0')
episode: 265 training return: tensor(-999.9990, device='cuda:0')
episode: 266 training return: tensor(-999.9984, device='cuda:0')
episode: 267 training return: tensor(-999.9980, device='cuda:0')
epoch: 67 test_true_pfm: -0.4005060653840369 sim_pfm: -999.9865318735441
episode: 268 training return: tensor(-999.9957, device='cuda:0')
episode: 269 training return: tensor(-999.9899, device='cuda:0')
episode: 270 training return: tensor(-999.9973, device='cuda:0')
episode: 271 training return: tensor(-999.9963, device='cuda:0')
epoch: 68 test_true_pfm: -0.6606017148364817 sim_pfm: -999.9866188367208
episode: 272 training return: tensor(-999.9980, device='cuda:0')
episode: 273 training return: tensor(-999.9908, device='cuda:0')
episode: 274 training return: tensor(-999.9990, device='cuda:0')
episode: 275 training return: tensor(-999.9841, device='cuda:0')
epoch: 69 test_true_pfm: 0.03549386940950431 sim_pfm: -999.9865871866544
episode: 276 training return: tensor(-999.9982, device='cuda:0')
episode: 277 training return: tensor(-999.9981, device='cuda:0')
episode: 278 training return: tensor(-999.9965, device='cuda:0')
episode: 279 training return: tensor(-999.9966, device='cuda:0')
epoch: 70 test_true_pfm: -0.4202596912405752 sim_pfm: -999.9865444103876
episode: 280 training return: tensor(-999.9927, device='cuda:0')
episode: 281 training return: tensor(-999.9953, device='cuda:0')
episode: 282 training return: tensor(-999.9982, device='cuda:0')
episode: 283 training return: tensor(-999.9979, device='cuda:0')
epoch: 71 test_true_pfm: -0.33765636678352157 sim_pfm: -999.9865497748057
episode: 284 training return: tensor(-999.9982, device='cuda:0')
episode: 285 training return: tensor(-999.9956, device='cuda:0')
episode: 286 training return: tensor(-999.9962, device='cuda:0')
episode: 287 training return: tensor(-999.9948, device='cuda:0')
epoch: 72 test_true_pfm: -0.6863003467479948 sim_pfm: -999.9863610267639
episode: 288 training return: tensor(-999.9965, device='cuda:0')
episode: 289 training return: tensor(-999.9952, device='cuda:0')
episode: 290 training return: tensor(-999.9949, device='cuda:0')
episode: 291 training return: tensor(-999.9969, device='cuda:0')
epoch: 73 test_true_pfm: 0.19983433874186476 sim_pfm: -999.9866528312365
episode: 292 training return: tensor(-999.9976, device='cuda:0')
episode: 293 training return: tensor(-999.9970, device='cuda:0')
episode: 294 training return: tensor(-999.9913, device='cuda:0')
episode: 295 training return: tensor(-999.9972, device='cuda:0')
epoch: 74 test_true_pfm: 0.11894923164209943 sim_pfm: -999.9865956306458
episode: 296 training return: tensor(-999.9960, device='cuda:0')
episode: 297 training return: tensor(-999.9974, device='cuda:0')
episode: 298 training return: tensor(-999.9954, device='cuda:0')
episode: 299 training return: tensor(-999.9908, device='cuda:0')
epoch: 75 test_true_pfm: -0.4625832225601028 sim_pfm: -999.9865401387215
episode: 300 training return: tensor(-999.9955, device='cuda:0')
episode: 301 training return: tensor(-999.9978, device='cuda:0')
episode: 302 training return: tensor(-999.9978, device='cuda:0')
episode: 303 training return: tensor(-999.9977, device='cuda:0')
epoch: 76 test_true_pfm: -0.6906445922246158 sim_pfm: -999.9864954153696
episode: 304 training return: tensor(-999.9988, device='cuda:0')
episode: 305 training return: tensor(-999.9946, device='cuda:0')
episode: 306 training return: tensor(-999.9980, device='cuda:0')
episode: 307 training return: tensor(-999.9975, device='cuda:0')
epoch: 77 test_true_pfm: -0.3511695418927287 sim_pfm: -999.9864898324013
episode: 308 training return: tensor(-999.9988, device='cuda:0')
episode: 309 training return: tensor(-999.9897, device='cuda:0')
episode: 310 training return: tensor(-999.9952, device='cuda:0')
episode: 311 training return: tensor(-999.9931, device='cuda:0')
epoch: 78 test_true_pfm: -0.5628392938465684 sim_pfm: -999.9866799513499
episode: 312 training return: tensor(-999.9987, device='cuda:0')
episode: 313 training return: tensor(-999.9968, device='cuda:0')
episode: 314 training return: tensor(-999.9957, device='cuda:0')
episode: 315 training return: tensor(-999.9955, device='cuda:0')
epoch: 79 test_true_pfm: 0.0405397348060789 sim_pfm: -999.9865982532501
episode: 316 training return: tensor(-999.9988, device='cuda:0')
episode: 317 training return: tensor(-999.9930, device='cuda:0')
episode: 318 training return: tensor(-999.9951, device='cuda:0')
episode: 319 training return: tensor(-999.9982, device='cuda:0')
epoch: 80 test_true_pfm: -0.5639385093646848 sim_pfm: -999.986653705438
episode: 320 training return: tensor(-999.9977, device='cuda:0')
episode: 321 training return: tensor(-999.9980, device='cuda:0')
episode: 322 training return: tensor(-999.9907, device='cuda:0')
episode: 323 training return: tensor(-999.9982, device='cuda:0')
epoch: 81 test_true_pfm: -0.6226925030596312 sim_pfm: -999.9865578015646
episode: 324 training return: tensor(-999.9985, device='cuda:0')
episode: 325 training return: tensor(-999.9890, device='cuda:0')
episode: 326 training return: tensor(-999.9964, device='cuda:0')
episode: 327 training return: tensor(-999.9966, device='cuda:0')
epoch: 82 test_true_pfm: -0.8624622305471422 sim_pfm: -999.9865497549375
episode: 328 training return: tensor(-999.9984, device='cuda:0')
episode: 329 training return: tensor(-999.9985, device='cuda:0')
episode: 330 training return: tensor(-999.9978, device='cuda:0')
episode: 331 training return: tensor(-999.9955, device='cuda:0')
epoch: 83 test_true_pfm: -0.5444172002885576 sim_pfm: -999.9864283800125
episode: 332 training return: tensor(-999.9882, device='cuda:0')
episode: 333 training return: tensor(-999.9992, device='cuda:0')
episode: 334 training return: tensor(-999.9983, device='cuda:0')
episode: 335 training return: tensor(-999.9970, device='cuda:0')
epoch: 84 test_true_pfm: -1.0633996479107772 sim_pfm: -999.9865731994311
episode: 336 training return: tensor(-999.9995, device='cuda:0')
episode: 337 training return: tensor(-999.9927, device='cuda:0')
episode: 338 training return: tensor(-999.9985, device='cuda:0')
episode: 339 training return: tensor(-999.9968, device='cuda:0')
epoch: 85 test_true_pfm: -0.3748271766297253 sim_pfm: -999.986550629139
episode: 340 training return: tensor(-999.9953, device='cuda:0')
episode: 341 training return: tensor(-999.9986, device='cuda:0')
episode: 342 training return: tensor(-999.9954, device='cuda:0')
episode: 343 training return: tensor(-999.9921, device='cuda:0')
epoch: 86 test_true_pfm: 0.28609043388385597 sim_pfm: -999.9864448706309
episode: 344 training return: tensor(-999.9989, device='cuda:0')
episode: 345 training return: tensor(-999.9969, device='cuda:0')
episode: 346 training return: tensor(-999.9991, device='cuda:0')
episode: 347 training return: tensor(-999.9971, device='cuda:0')
epoch: 87 test_true_pfm: -0.43926914736707573 sim_pfm: -999.9864901502928
episode: 348 training return: tensor(-999.9983, device='cuda:0')
episode: 349 training return: tensor(-999.9963, device='cuda:0')
episode: 350 training return: tensor(-999.9986, device='cuda:0')
episode: 351 training return: tensor(-999.9893, device='cuda:0')
epoch: 88 test_true_pfm: -0.1475938916304148 sim_pfm: -999.9864472349485
episode: 352 training return: tensor(-999.9747, device='cuda:0')
episode: 353 training return: tensor(-999.9957, device='cuda:0')
episode: 354 training return: tensor(-999.9890, device='cuda:0')
episode: 355 training return: tensor(-999.9978, device='cuda:0')
epoch: 89 test_true_pfm: -0.6876273210781325 sim_pfm: -999.98666203022
episode: 356 training return: tensor(-999.9967, device='cuda:0')
episode: 357 training return: tensor(-999.9985, device='cuda:0')
episode: 358 training return: tensor(-999.9992, device='cuda:0')
episode: 359 training return: tensor(-999.9801, device='cuda:0')
epoch: 90 test_true_pfm: 0.3882899894947642 sim_pfm: -999.9865461786588
episode: 360 training return: tensor(-999.9982, device='cuda:0')
episode: 361 training return: tensor(-999.9990, device='cuda:0')
episode: 362 training return: tensor(-999.9881, device='cuda:0')
episode: 363 training return: tensor(-999.9891, device='cuda:0')
epoch: 91 test_true_pfm: 0.005047738536027598 sim_pfm: -999.9865995844206
episode: 364 training return: tensor(-999.9980, device='cuda:0')
episode: 365 training return: tensor(-999.9961, device='cuda:0')
episode: 366 training return: tensor(-999.9980, device='cuda:0')
episode: 367 training return: tensor(-999.9968, device='cuda:0')
epoch: 92 test_true_pfm: -0.5021956889349072 sim_pfm: -999.98650320371
episode: 368 training return: tensor(-999.9973, device='cuda:0')
episode: 369 training return: tensor(-999.9964, device='cuda:0')
episode: 370 training return: tensor(-999.9985, device='cuda:0')
episode: 371 training return: tensor(-999.9970, device='cuda:0')
epoch: 93 test_true_pfm: -0.5972655086129743 sim_pfm: -999.9866643945376
episode: 372 training return: tensor(-999.9885, device='cuda:0')
episode: 373 training return: tensor(-999.9958, device='cuda:0')
episode: 374 training return: tensor(-999.9974, device='cuda:0')
episode: 375 training return: tensor(-999.9788, device='cuda:0')
epoch: 94 test_true_pfm: 0.05298799028315301 sim_pfm: -999.98652780056
episode: 376 training return: tensor(-999.9830, device='cuda:0')
episode: 377 training return: tensor(-999.9966, device='cuda:0')
episode: 378 training return: tensor(-999.9991, device='cuda:0')
episode: 379 training return: tensor(-999.9927, device='cuda:0')
epoch: 95 test_true_pfm: -0.3772934083384178 sim_pfm: -999.9865441322327
episode: 380 training return: tensor(-999.9937, device='cuda:0')
episode: 381 training return: tensor(-999.9988, device='cuda:0')
episode: 382 training return: tensor(-999.9975, device='cuda:0')
episode: 383 training return: tensor(-999.9915, device='cuda:0')
epoch: 96 test_true_pfm: 0.040649649555787426 sim_pfm: -999.9866016904513
episode: 384 training return: tensor(-999.9987, device='cuda:0')
episode: 385 training return: tensor(-999.9986, device='cuda:0')
episode: 386 training return: tensor(-999.9967, device='cuda:0')
episode: 387 training return: tensor(-999.9944, device='cuda:0')
epoch: 97 test_true_pfm: -0.795666421184693 sim_pfm: -999.9866058627764
episode: 388 training return: tensor(-999.9943, device='cuda:0')
episode: 389 training return: tensor(-999.9926, device='cuda:0')
episode: 390 training return: tensor(-999.9979, device='cuda:0')
episode: 391 training return: tensor(-999.9961, device='cuda:0')
epoch: 98 test_true_pfm: 0.5057480909443247 sim_pfm: -999.986583729585
episode: 392 training return: tensor(-999.9955, device='cuda:0')
episode: 393 training return: tensor(-999.9985, device='cuda:0')
episode: 394 training return: tensor(-999.9879, device='cuda:0')
episode: 395 training return: tensor(-999.9954, device='cuda:0')
epoch: 99 test_true_pfm: -0.7588252074899229 sim_pfm: -999.9865526159605
episode: 396 training return: tensor(-999.9969, device='cuda:0')
episode: 397 training return: tensor(-999.9979, device='cuda:0')
episode: 398 training return: tensor(-999.9948, device='cuda:0')
episode: 399 training return: tensor(-999.9986, device='cuda:0')
epoch: 100 test_true_pfm: 0.12401497988915026 sim_pfm: -999.9864966869354
episode: 400 training return: tensor(-999.9969, device='cuda:0')
episode: 401 training return: tensor(-999.9970, device='cuda:0')
episode: 402 training return: tensor(-999.9965, device='cuda:0')
episode: 403 training return: tensor(-999.9933, device='cuda:0')
epoch: 101 test_true_pfm: -0.23807964025559827 sim_pfm: -999.9865517218908
episode: 404 training return: tensor(-999.9914, device='cuda:0')
episode: 405 training return: tensor(-999.9893, device='cuda:0')
episode: 406 training return: tensor(-999.9981, device='cuda:0')
episode: 407 training return: tensor(-999.9964, device='cuda:0')
epoch: 102 test_true_pfm: -0.3576628333861551 sim_pfm: -999.9865446289381
episode: 408 training return: tensor(-999.9989, device='cuda:0')
episode: 409 training return: tensor(-999.9971, device='cuda:0')
episode: 410 training return: tensor(-999.9930, device='cuda:0')
episode: 411 training return: tensor(-999.9982, device='cuda:0')
epoch: 103 test_true_pfm: 0.009290766515202978 sim_pfm: -999.9864946007729
episode: 412 training return: tensor(-999.9888, device='cuda:0')
episode: 413 training return: tensor(-999.9983, device='cuda:0')
episode: 414 training return: tensor(-999.9942, device='cuda:0')
episode: 415 training return: tensor(-999.9936, device='cuda:0')
epoch: 104 test_true_pfm: -0.04720162491277289 sim_pfm: -999.9865271051725
episode: 416 training return: tensor(-999.9888, device='cuda:0')
episode: 417 training return: tensor(-999.9880, device='cuda:0')
episode: 418 training return: tensor(-999.9923, device='cuda:0')
episode: 419 training return: tensor(-999.9976, device='cuda:0')
epoch: 105 test_true_pfm: -0.9533122743480337 sim_pfm: -999.986553410689
episode: 420 training return: tensor(-999.9990, device='cuda:0')
episode: 421 training return: tensor(-999.9977, device='cuda:0')
episode: 422 training return: tensor(-999.9879, device='cuda:0')
episode: 423 training return: tensor(-999.9863, device='cuda:0')
epoch: 106 test_true_pfm: -0.5766078165088201 sim_pfm: -999.9865875840187
episode: 424 training return: tensor(-999.9984, device='cuda:0')
episode: 425 training return: tensor(-999.9935, device='cuda:0')
episode: 426 training return: tensor(-999.9899, device='cuda:0')
episode: 427 training return: tensor(-999.9871, device='cuda:0')
epoch: 107 test_true_pfm: -0.3267663306793452 sim_pfm: -999.9865163962046
episode: 428 training return: tensor(-999.9985, device='cuda:0')
episode: 429 training return: tensor(-999.9973, device='cuda:0')
episode: 430 training return: tensor(-999.9971, device='cuda:0')
episode: 431 training return: tensor(-999.9906, device='cuda:0')
epoch: 108 test_true_pfm: -0.03263847196617679 sim_pfm: -999.9865754445394
episode: 432 training return: tensor(-999.9984, device='cuda:0')
episode: 433 training return: tensor(-999.9985, device='cuda:0')
episode: 434 training return: tensor(-999.9978, device='cuda:0')
episode: 435 training return: tensor(-999.9977, device='cuda:0')
epoch: 109 test_true_pfm: 0.333920174137051 sim_pfm: -999.9866420030594
episode: 436 training return: tensor(-999.9985, device='cuda:0')
episode: 437 training return: tensor(-999.9984, device='cuda:0')
episode: 438 training return: tensor(-999.9987, device='cuda:0')
episode: 439 training return: tensor(-999.9976, device='cuda:0')
epoch: 110 test_true_pfm: 0.03325035239909565 sim_pfm: -999.9866428971291
episode: 440 training return: tensor(-999.9986, device='cuda:0')
episode: 441 training return: tensor(-999.9867, device='cuda:0')
episode: 442 training return: tensor(-999.9938, device='cuda:0')
episode: 443 training return: tensor(-999.9952, device='cuda:0')
epoch: 111 test_true_pfm: -0.11497825232768379 sim_pfm: -999.986557841301
episode: 444 training return: tensor(-999.9918, device='cuda:0')
episode: 445 training return: tensor(-999.9976, device='cuda:0')
episode: 446 training return: tensor(-999.9985, device='cuda:0')
episode: 447 training return: tensor(-999.9916, device='cuda:0')
epoch: 112 test_true_pfm: -0.29763813641878456 sim_pfm: -999.986545185248
episode: 448 training return: tensor(-999.9891, device='cuda:0')
episode: 449 training return: tensor(-999.9993, device='cuda:0')
episode: 450 training return: tensor(-999.9988, device='cuda:0')
episode: 451 training return: tensor(-999.9982, device='cuda:0')
epoch: 113 test_true_pfm: 0.5654980057517759 sim_pfm: -999.9865801334381
episode: 452 training return: tensor(-999.9985, device='cuda:0')
episode: 453 training return: tensor(-999.9929, device='cuda:0')
episode: 454 training return: tensor(-999.9981, device='cuda:0')
episode: 455 training return: tensor(-999.9993, device='cuda:0')
epoch: 114 test_true_pfm: -0.8423132310845896 sim_pfm: -999.9865700999895
episode: 456 training return: tensor(-999.9986, device='cuda:0')
episode: 457 training return: tensor(-999.9978, device='cuda:0')
episode: 458 training return: tensor(-999.9987, device='cuda:0')
episode: 459 training return: tensor(-999.9965, device='cuda:0')
epoch: 115 test_true_pfm: -0.3311702816938378 sim_pfm: -999.986531317234
episode: 460 training return: tensor(-999.9959, device='cuda:0')
episode: 461 training return: tensor(-999.9980, device='cuda:0')
episode: 462 training return: tensor(-999.9944, device='cuda:0')
episode: 463 training return: tensor(-999.9992, device='cuda:0')
epoch: 116 test_true_pfm: -0.44933199679671193 sim_pfm: -999.9865445295969
episode: 464 training return: tensor(-999.9983, device='cuda:0')
episode: 465 training return: tensor(-999.9843, device='cuda:0')
episode: 466 training return: tensor(-999.9978, device='cuda:0')
episode: 467 training return: tensor(-999.9985, device='cuda:0')
epoch: 117 test_true_pfm: -0.4510079364016517 sim_pfm: -999.9865507483482
episode: 468 training return: tensor(-999.9915, device='cuda:0')
episode: 469 training return: tensor(-999.9974, device='cuda:0')
episode: 470 training return: tensor(-999.9963, device='cuda:0')
episode: 471 training return: tensor(-999.9912, device='cuda:0')
epoch: 118 test_true_pfm: -1.1164517352025942 sim_pfm: -999.9866001605988
episode: 472 training return: tensor(-999.9974, device='cuda:0')
episode: 473 training return: tensor(-999.9988, device='cuda:0')
episode: 474 training return: tensor(-999.9976, device='cuda:0')
episode: 475 training return: tensor(-999.9968, device='cuda:0')
epoch: 119 test_true_pfm: -0.9844218008744031 sim_pfm: -999.9864959915479
episode: 476 training return: tensor(-999.9974, device='cuda:0')
episode: 477 training return: tensor(-999.9987, device='cuda:0')
episode: 478 training return: tensor(-999.9985, device='cuda:0')
episode: 479 training return: tensor(-999.9921, device='cuda:0')
epoch: 120 test_true_pfm: -0.04553249733242178 sim_pfm: -999.9864809513092
episode: 480 training return: tensor(-999.9917, device='cuda:0')
episode: 481 training return: tensor(-999.9953, device='cuda:0')
episode: 482 training return: tensor(-999.9990, device='cuda:0')
episode: 483 training return: tensor(-999.9980, device='cuda:0')
epoch: 121 test_true_pfm: 0.3505595871370124 sim_pfm: -999.9864867925644
episode: 484 training return: tensor(-999.9988, device='cuda:0')
episode: 485 training return: tensor(-999.9980, device='cuda:0')
episode: 486 training return: tensor(-999.9964, device='cuda:0')
episode: 487 training return: tensor(-999.9986, device='cuda:0')
epoch: 122 test_true_pfm: -0.13999793594128707 sim_pfm: -999.9864750703176
episode: 488 training return: tensor(-999.9987, device='cuda:0')
episode: 489 training return: tensor(-999.9987, device='cuda:0')
episode: 490 training return: tensor(-999.9977, device='cuda:0')
episode: 491 training return: tensor(-999.9965, device='cuda:0')
epoch: 123 test_true_pfm: -0.2520058646873388 sim_pfm: -999.9866174260775
episode: 492 training return: tensor(-999.9931, device='cuda:0')
episode: 493 training return: tensor(-999.9974, device='cuda:0')
episode: 494 training return: tensor(-999.9968, device='cuda:0')
episode: 495 training return: tensor(-999.9966, device='cuda:0')
epoch: 124 test_true_pfm: -0.3507556995164798 sim_pfm: -999.9866713881493
episode: 496 training return: tensor(-999.9923, device='cuda:0')
episode: 497 training return: tensor(-999.9932, device='cuda:0')
episode: 498 training return: tensor(-999.9984, device='cuda:0')
episode: 499 training return: tensor(-999.9975, device='cuda:0')
epoch: 125 test_true_pfm: 0.7295653146376595 sim_pfm: -999.986552019914
episode: 500 training return: tensor(-999.9905, device='cuda:0')
episode: 501 training return: tensor(-999.9983, device='cuda:0')
episode: 502 training return: tensor(-999.9969, device='cuda:0')
episode: 503 training return: tensor(-999.9972, device='cuda:0')
epoch: 126 test_true_pfm: -0.273986088831683 sim_pfm: -999.9865893522898
episode: 504 training return: tensor(-999.9948, device='cuda:0')
episode: 505 training return: tensor(-999.9993, device='cuda:0')
episode: 506 training return: tensor(-999.9972, device='cuda:0')
episode: 507 training return: tensor(-999.9976, device='cuda:0')
epoch: 127 test_true_pfm: -0.5688762039140219 sim_pfm: -999.9866071144739
episode: 508 training return: tensor(-999.9943, device='cuda:0')
episode: 509 training return: tensor(-999.9961, device='cuda:0')
episode: 510 training return: tensor(-999.9993, device='cuda:0')
episode: 511 training return: tensor(-999.9990, device='cuda:0')
epoch: 128 test_true_pfm: -0.9762802725659224 sim_pfm: -999.9866224527359
episode: 512 training return: tensor(-999.9935, device='cuda:0')
episode: 513 training return: tensor(-999.9971, device='cuda:0')
episode: 514 training return: tensor(-999.9985, device='cuda:0')
episode: 515 training return: tensor(-999.9977, device='cuda:0')
epoch: 129 test_true_pfm: -0.41928489855263745 sim_pfm: -999.9864755471548
episode: 516 training return: tensor(-999.9950, device='cuda:0')
episode: 517 training return: tensor(-999.9990, device='cuda:0')
episode: 518 training return: tensor(-999.9976, device='cuda:0')
episode: 519 training return: tensor(-999.9911, device='cuda:0')
epoch: 130 test_true_pfm: -0.15847958227521022 sim_pfm: -999.9865496953329
episode: 520 training return: tensor(-999.9977, device='cuda:0')
episode: 521 training return: tensor(-999.9952, device='cuda:0')
episode: 522 training return: tensor(-999.9980, device='cuda:0')
episode: 523 training return: tensor(-999.9983, device='cuda:0')
epoch: 131 test_true_pfm: -0.4899335552861778 sim_pfm: -999.9865390459696
episode: 524 training return: tensor(-999.9926, device='cuda:0')
episode: 525 training return: tensor(-999.9985, device='cuda:0')
episode: 526 training return: tensor(-999.9988, device='cuda:0')
episode: 527 training return: tensor(-999.9910, device='cuda:0')
epoch: 132 test_true_pfm: -0.8507885330308147 sim_pfm: -999.9866135319074
episode: 528 training return: tensor(-999.9970, device='cuda:0')
episode: 529 training return: tensor(-999.9984, device='cuda:0')
episode: 530 training return: tensor(-999.9985, device='cuda:0')
episode: 531 training return: tensor(-999.9982, device='cuda:0')
epoch: 133 test_true_pfm: 0.08456301801316625 sim_pfm: -999.9866144855818
episode: 532 training return: tensor(-999.9974, device='cuda:0')
episode: 533 training return: tensor(-999.9983, device='cuda:0')
episode: 534 training return: tensor(-999.9937, device='cuda:0')
episode: 535 training return: tensor(-999.9975, device='cuda:0')
epoch: 134 test_true_pfm: 0.9433970979361689 sim_pfm: -999.9864080548286
episode: 536 training return: tensor(-999.9959, device='cuda:0')
episode: 537 training return: tensor(-999.9970, device='cuda:0')
episode: 538 training return: tensor(-999.9963, device='cuda:0')
episode: 539 training return: tensor(-999.9982, device='cuda:0')
epoch: 135 test_true_pfm: -0.539473376684729 sim_pfm: -999.9865502317747
episode: 540 training return: tensor(-999.9940, device='cuda:0')
episode: 541 training return: tensor(-999.9988, device='cuda:0')
episode: 542 training return: tensor(-999.9982, device='cuda:0')
episode: 543 training return: tensor(-999.9948, device='cuda:0')
epoch: 136 test_true_pfm: -0.9870523471252753 sim_pfm: -999.9865831335386
episode: 544 training return: tensor(-999.9974, device='cuda:0')
episode: 545 training return: tensor(-999.9980, device='cuda:0')
episode: 546 training return: tensor(-999.9985, device='cuda:0')
episode: 547 training return: tensor(-999.9988, device='cuda:0')
epoch: 137 test_true_pfm: -0.31187726905928875 sim_pfm: -999.9867173234621
episode: 548 training return: tensor(-999.9927, device='cuda:0')
episode: 549 training return: tensor(-999.9898, device='cuda:0')
episode: 550 training return: tensor(-999.9985, device='cuda:0')
episode: 551 training return: tensor(-999.9985, device='cuda:0')
epoch: 138 test_true_pfm: -0.2252994239910818 sim_pfm: -999.9865511258444
episode: 552 training return: tensor(-999.9986, device='cuda:0')
episode: 553 training return: tensor(-999.9970, device='cuda:0')
episode: 554 training return: tensor(-999.9986, device='cuda:0')
episode: 555 training return: tensor(-999.9949, device='cuda:0')
epoch: 139 test_true_pfm: 0.6098947364584052 sim_pfm: -999.9865962266922
episode: 556 training return: tensor(-999.9948, device='cuda:0')
episode: 557 training return: tensor(-999.9919, device='cuda:0')
episode: 558 training return: tensor(-999.9990, device='cuda:0')
episode: 559 training return: tensor(-999.9905, device='cuda:0')
epoch: 140 test_true_pfm: 0.2735111888788612 sim_pfm: -999.986634751161
episode: 560 training return: tensor(-999.9977, device='cuda:0')
episode: 561 training return: tensor(-999.9993, device='cuda:0')
episode: 562 training return: tensor(-999.9880, device='cuda:0')
episode: 563 training return: tensor(-999.9957, device='cuda:0')
epoch: 141 test_true_pfm: -0.1608421210168263 sim_pfm: -999.9865891138712
episode: 564 training return: tensor(-999.9987, device='cuda:0')
episode: 565 training return: tensor(-999.9980, device='cuda:0')
episode: 566 training return: tensor(-999.9974, device='cuda:0')
episode: 567 training return: tensor(-999.9974, device='cuda:0')
epoch: 142 test_true_pfm: -0.6798383005529 sim_pfm: -999.9864949584007
episode: 568 training return: tensor(-999.9944, device='cuda:0')
episode: 569 training return: tensor(-999.9986, device='cuda:0')
episode: 570 training return: tensor(-999.9971, device='cuda:0')
episode: 571 training return: tensor(-999.9928, device='cuda:0')
epoch: 143 test_true_pfm: 0.4272461564258357 sim_pfm: -999.9865920146307
episode: 572 training return: tensor(-999.9960, device='cuda:0')
episode: 573 training return: tensor(-999.9905, device='cuda:0')
episode: 574 training return: tensor(-999.9940, device='cuda:0')
episode: 575 training return: tensor(-999.9926, device='cuda:0')
epoch: 144 test_true_pfm: -0.16586986193753891 sim_pfm: -999.9865434368452
episode: 576 training return: tensor(-999.9941, device='cuda:0')
episode: 577 training return: tensor(-999.9952, device='cuda:0')
episode: 578 training return: tensor(-999.9953, device='cuda:0')
episode: 579 training return: tensor(-999.9988, device='cuda:0')
epoch: 145 test_true_pfm: 0.41041471149044884 sim_pfm: -999.9864756464958
episode: 580 training return: tensor(-999.9967, device='cuda:0')
episode: 581 training return: tensor(-999.9886, device='cuda:0')
episode: 582 training return: tensor(-999.9917, device='cuda:0')
episode: 583 training return: tensor(-999.9976, device='cuda:0')
epoch: 146 test_true_pfm: 0.01898357251525214 sim_pfm: -999.9865402579308
episode: 584 training return: tensor(-999.9948, device='cuda:0')
episode: 585 training return: tensor(-999.9993, device='cuda:0')
episode: 586 training return: tensor(-999.9971, device='cuda:0')
episode: 587 training return: tensor(-999.9984, device='cuda:0')
epoch: 147 test_true_pfm: -0.32698793383679114 sim_pfm: -999.9865835706393
episode: 588 training return: tensor(-999.9833, device='cuda:0')
episode: 589 training return: tensor(-999.9982, device='cuda:0')
episode: 590 training return: tensor(-999.9890, device='cuda:0')
episode: 591 training return: tensor(-999.9985, device='cuda:0')
epoch: 148 test_true_pfm: -0.4407221006223055 sim_pfm: -999.9865377545357
episode: 592 training return: tensor(-999.9988, device='cuda:0')
episode: 593 training return: tensor(-999.9888, device='cuda:0')
episode: 594 training return: tensor(-999.9978, device='cuda:0')
episode: 595 training return: tensor(-999.9867, device='cuda:0')
epoch: 149 test_true_pfm: 0.029154384928992177 sim_pfm: -999.986582159996
episode: 596 training return: tensor(-999.9987, device='cuda:0')
episode: 597 training return: tensor(-999.9963, device='cuda:0')
episode: 598 training return: tensor(-999.9931, device='cuda:0')
episode: 599 training return: tensor(-999.9983, device='cuda:0')
epoch: 150 test_true_pfm: -0.8508168076776806 sim_pfm: -999.9865814050039
