['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'baseline', '--traj', 'medium', '--seed', '3']
episode: 0 training return: tensor(-999.9991, device='cuda:0')
episode: 1 training return: tensor(-999.9987, device='cuda:0')
episode: 2 training return: tensor(-999.9940, device='cuda:0')
episode: 3 training return: tensor(-999.9984, device='cuda:0')
epoch: 1 test_true_pfm: 0.5184570485403912 sim_pfm: -999.993955274423
episode: 4 training return: tensor(-999.9990, device='cuda:0')
episode: 5 training return: tensor(-999.9981, device='cuda:0')
episode: 6 training return: tensor(-999.9978, device='cuda:0')
episode: 7 training return: tensor(-999.9952, device='cuda:0')
epoch: 2 test_true_pfm: 0.10667251166314985 sim_pfm: -999.9938923319181
episode: 8 training return: tensor(-999.9960, device='cuda:0')
episode: 9 training return: tensor(-999.9976, device='cuda:0')
episode: 10 training return: tensor(-999.9995, device='cuda:0')
episode: 11 training return: tensor(-999.9962, device='cuda:0')
epoch: 3 test_true_pfm: 0.05613679110494866 sim_pfm: -999.9940066734949
episode: 12 training return: tensor(-999.9968, device='cuda:0')
episode: 13 training return: tensor(-999.9963, device='cuda:0')
episode: 14 training return: tensor(-999.9945, device='cuda:0')
episode: 15 training return: tensor(-999.9934, device='cuda:0')
epoch: 4 test_true_pfm: -0.010766052176221674 sim_pfm: -999.993839542071
episode: 16 training return: tensor(-999.9984, device='cuda:0')
episode: 17 training return: tensor(-999.9982, device='cuda:0')
episode: 18 training return: tensor(-999.9985, device='cuda:0')
episode: 19 training return: tensor(-999.9949, device='cuda:0')
epoch: 5 test_true_pfm: 0.05482305147985792 sim_pfm: -999.9941358566284
episode: 20 training return: tensor(-999.9964, device='cuda:0')
episode: 21 training return: tensor(-999.9978, device='cuda:0')
episode: 22 training return: tensor(-999.9782, device='cuda:0')
episode: 23 training return: tensor(-999.9965, device='cuda:0')
epoch: 6 test_true_pfm: 0.15161521018119664 sim_pfm: -999.9938957293829
episode: 24 training return: tensor(-999.9968, device='cuda:0')
episode: 25 training return: tensor(-999.9989, device='cuda:0')
episode: 26 training return: tensor(-999.9998, device='cuda:0')
episode: 27 training return: tensor(-999.9974, device='cuda:0')
epoch: 7 test_true_pfm: -0.3153291813053424 sim_pfm: -999.993955274423
episode: 28 training return: tensor(-999.9980, device='cuda:0')
episode: 29 training return: tensor(-999.9982, device='cuda:0')
episode: 30 training return: tensor(-999.9959, device='cuda:0')
episode: 31 training return: tensor(-999.9965, device='cuda:0')
epoch: 8 test_true_pfm: -0.4030418173892038 sim_pfm: -999.9940156539282
episode: 32 training return: tensor(-999.9958, device='cuda:0')
episode: 33 training return: tensor(-999.9954, device='cuda:0')
episode: 34 training return: tensor(-999.9989, device='cuda:0')
episode: 35 training return: tensor(-999.9968, device='cuda:0')
epoch: 9 test_true_pfm: 0.037717962750464164 sim_pfm: -999.9937739372253
episode: 36 training return: tensor(-999.9817, device='cuda:0')
episode: 37 training return: tensor(-999.9965, device='cuda:0')
episode: 38 training return: tensor(-999.9948, device='cuda:0')
episode: 39 training return: tensor(-999.9981, device='cuda:0')
epoch: 10 test_true_pfm: -1.115546845960606 sim_pfm: -999.9941324591637
episode: 40 training return: tensor(-999.9958, device='cuda:0')
episode: 41 training return: tensor(-999.9977, device='cuda:0')
episode: 42 training return: tensor(-999.9979, device='cuda:0')
episode: 43 training return: tensor(-999.9959, device='cuda:0')
epoch: 11 test_true_pfm: -1.2091947344829732 sim_pfm: -999.9940699934959
episode: 44 training return: tensor(-999.9980, device='cuda:0')
episode: 45 training return: tensor(-999.9985, device='cuda:0')
episode: 46 training return: tensor(-999.9966, device='cuda:0')
episode: 47 training return: tensor(-999.9976, device='cuda:0')
epoch: 12 test_true_pfm: -0.3210810917373641 sim_pfm: -999.9938871860504
episode: 48 training return: tensor(-999.9982, device='cuda:0')
episode: 49 training return: tensor(-999.9979, device='cuda:0')
episode: 50 training return: tensor(-999.9973, device='cuda:0')
episode: 51 training return: tensor(-999.9948, device='cuda:0')
epoch: 13 test_true_pfm: -0.27800841193529635 sim_pfm: -999.9939577778181
episode: 52 training return: tensor(-999.9974, device='cuda:0')
episode: 53 training return: tensor(-999.9966, device='cuda:0')
episode: 54 training return: tensor(-999.9984, device='cuda:0')
episode: 55 training return: tensor(-999.9966, device='cuda:0')
epoch: 14 test_true_pfm: -0.18206470077030387 sim_pfm: -999.9939541220665
episode: 56 training return: tensor(-999.9940, device='cuda:0')
episode: 57 training return: tensor(-999.9958, device='cuda:0')
episode: 58 training return: tensor(-999.9976, device='cuda:0')
episode: 59 training return: tensor(-999.9985, device='cuda:0')
epoch: 15 test_true_pfm: -1.008591013573322 sim_pfm: -999.9940084218979
episode: 60 training return: tensor(-999.9957, device='cuda:0')
episode: 61 training return: tensor(-999.9944, device='cuda:0')
episode: 62 training return: tensor(-999.9938, device='cuda:0')
episode: 63 training return: tensor(-999.9975, device='cuda:0')
epoch: 16 test_true_pfm: -0.2670334270859757 sim_pfm: -999.9938346147537
episode: 64 training return: tensor(-999.9986, device='cuda:0')
episode: 65 training return: tensor(-999.9970, device='cuda:0')
episode: 66 training return: tensor(-999.9974, device='cuda:0')
episode: 67 training return: tensor(-999.9962, device='cuda:0')
epoch: 17 test_true_pfm: -0.4660761685396142 sim_pfm: -999.9940642913183
episode: 68 training return: tensor(-999.9972, device='cuda:0')
episode: 69 training return: tensor(-999.9988, device='cuda:0')
episode: 70 training return: tensor(-999.9995, device='cuda:0')
episode: 71 training return: tensor(-999.9976, device='cuda:0')
epoch: 18 test_true_pfm: -0.6235655971100713 sim_pfm: -999.9940133690834
episode: 72 training return: tensor(-999.9967, device='cuda:0')
episode: 73 training return: tensor(-999.9926, device='cuda:0')
episode: 74 training return: tensor(-999.9985, device='cuda:0')
episode: 75 training return: tensor(-999.9965, device='cuda:0')
epoch: 19 test_true_pfm: -0.43779486728391803 sim_pfm: -999.9940749406815
episode: 76 training return: tensor(-999.9937, device='cuda:0')
episode: 77 training return: tensor(-999.9978, device='cuda:0')
episode: 78 training return: tensor(-999.9944, device='cuda:0')
episode: 79 training return: tensor(-999.9965, device='cuda:0')
epoch: 20 test_true_pfm: 0.35404738330054925 sim_pfm: -999.9940060774485
episode: 80 training return: tensor(-999.9973, device='cuda:0')
episode: 81 training return: tensor(-999.9977, device='cuda:0')
episode: 82 training return: tensor(-999.9954, device='cuda:0')
episode: 83 training return: tensor(-999.9958, device='cuda:0')
epoch: 21 test_true_pfm: -0.4892693097212398 sim_pfm: -999.9940137664477
episode: 84 training return: tensor(-999.9964, device='cuda:0')
episode: 85 training return: tensor(-999.9981, device='cuda:0')
episode: 86 training return: tensor(-999.9978, device='cuda:0')
episode: 87 training return: tensor(-999.9959, device='cuda:0')
epoch: 22 test_true_pfm: -0.0006306387476454992 sim_pfm: -999.993898332119
episode: 88 training return: tensor(-999.9965, device='cuda:0')
episode: 89 training return: tensor(-999.9948, device='cuda:0')
episode: 90 training return: tensor(-999.9966, device='cuda:0')
episode: 91 training return: tensor(-999.9949, device='cuda:0')
epoch: 23 test_true_pfm: 0.030393388204569532 sim_pfm: -999.9940129121145
episode: 92 training return: tensor(-999.9985, device='cuda:0')
episode: 93 training return: tensor(-999.9978, device='cuda:0')
episode: 94 training return: tensor(-999.9972, device='cuda:0')
episode: 95 training return: tensor(-999.9885, device='cuda:0')
epoch: 24 test_true_pfm: -0.30990038876765064 sim_pfm: -999.9939564466476
episode: 96 training return: tensor(-999.9969, device='cuda:0')
episode: 97 training return: tensor(-999.9973, device='cuda:0')
episode: 98 training return: tensor(-999.9973, device='cuda:0')
episode: 99 training return: tensor(-999.9960, device='cuda:0')
epoch: 25 test_true_pfm: -0.5825146856639898 sim_pfm: -999.9940130114555
episode: 100 training return: tensor(-999.9963, device='cuda:0')
episode: 101 training return: tensor(-999.9992, device='cuda:0')
episode: 102 training return: tensor(-999.9948, device='cuda:0')
episode: 103 training return: tensor(-999.9977, device='cuda:0')
epoch: 26 test_true_pfm: -0.29756951048333447 sim_pfm: -999.994072775046
episode: 104 training return: tensor(-999.9957, device='cuda:0')
episode: 105 training return: tensor(-999.9963, device='cuda:0')
episode: 106 training return: tensor(-999.9976, device='cuda:0')
episode: 107 training return: tensor(-999.9973, device='cuda:0')
epoch: 27 test_true_pfm: -0.15455560824440315 sim_pfm: -999.9940107266108
episode: 108 training return: tensor(-999.9973, device='cuda:0')
episode: 109 training return: tensor(-999.9984, device='cuda:0')
episode: 110 training return: tensor(-999.9977, device='cuda:0')
episode: 111 training return: tensor(-999.9992, device='cuda:0')
epoch: 28 test_true_pfm: 0.052784342176262156 sim_pfm: -999.9938913583755
episode: 112 training return: tensor(-999.9972, device='cuda:0')
episode: 113 training return: tensor(-999.9990, device='cuda:0')
episode: 114 training return: tensor(-999.9977, device='cuda:0')
episode: 115 training return: tensor(-999.9960, device='cuda:0')
epoch: 29 test_true_pfm: 0.00862979268329099 sim_pfm: -999.9939485987028
episode: 116 training return: tensor(-999.9996, device='cuda:0')
episode: 117 training return: tensor(-999.9980, device='cuda:0')
episode: 118 training return: tensor(-999.9978, device='cuda:0')
episode: 119 training return: tensor(-999.9980, device='cuda:0')
epoch: 30 test_true_pfm: 0.06379338778276733 sim_pfm: -999.9938947558403
episode: 120 training return: tensor(-999.9984, device='cuda:0')
episode: 121 training return: tensor(-999.9974, device='cuda:0')
episode: 122 training return: tensor(-999.9977, device='cuda:0')
episode: 123 training return: tensor(-999.9951, device='cuda:0')
epoch: 31 test_true_pfm: -0.6829810438680944 sim_pfm: -999.9940156539282
episode: 124 training return: tensor(-999.9973, device='cuda:0')
episode: 125 training return: tensor(-999.9988, device='cuda:0')
episode: 126 training return: tensor(-999.9979, device='cuda:0')
episode: 127 training return: tensor(-999.9955, device='cuda:0')
epoch: 32 test_true_pfm: -0.5405536244597585 sim_pfm: -999.9938398798307
episode: 128 training return: tensor(-999.9982, device='cuda:0')
episode: 129 training return: tensor(-999.9969, device='cuda:0')
episode: 130 training return: tensor(-999.9962, device='cuda:0')
episode: 131 training return: tensor(-999.9972, device='cuda:0')
epoch: 33 test_true_pfm: -0.3978586078046014 sim_pfm: -999.9940216342608
episode: 132 training return: tensor(-999.9973, device='cuda:0')
episode: 133 training return: tensor(-999.9955, device='cuda:0')
episode: 134 training return: tensor(-999.9973, device='cuda:0')
episode: 135 training return: tensor(-999.9972, device='cuda:0')
epoch: 34 test_true_pfm: -0.0800048692370751 sim_pfm: -999.993952592214
episode: 136 training return: tensor(-999.9972, device='cuda:0')
episode: 137 training return: tensor(-999.9979, device='cuda:0')
episode: 138 training return: tensor(-999.9991, device='cuda:0')
episode: 139 training return: tensor(-999.9978, device='cuda:0')
epoch: 35 test_true_pfm: -0.058904250245555866 sim_pfm: -999.9938897689184
episode: 140 training return: tensor(-999.9966, device='cuda:0')
episode: 141 training return: tensor(-999.9954, device='cuda:0')
episode: 142 training return: tensor(-999.9968, device='cuda:0')
episode: 143 training return: tensor(-999.9971, device='cuda:0')
epoch: 36 test_true_pfm: -0.3182158672926815 sim_pfm: -999.9938965439796
episode: 144 training return: tensor(-999.9971, device='cuda:0')
episode: 145 training return: tensor(-999.9972, device='cuda:0')
episode: 146 training return: tensor(-999.9975, device='cuda:0')
episode: 147 training return: tensor(-999.9983, device='cuda:0')
epoch: 37 test_true_pfm: -0.6539951615622797 sim_pfm: -999.9937753280004
episode: 148 training return: tensor(-999.9977, device='cuda:0')
episode: 149 training return: tensor(-999.9991, device='cuda:0')
episode: 150 training return: tensor(-999.9976, device='cuda:0')
episode: 151 training return: tensor(-999.9977, device='cuda:0')
epoch: 38 test_true_pfm: -0.9270140580346716 sim_pfm: -999.993951757749
episode: 152 training return: tensor(-999.9971, device='cuda:0')
episode: 153 training return: tensor(-999.9965, device='cuda:0')
episode: 154 training return: tensor(-999.9966, device='cuda:0')
episode: 155 training return: tensor(-999.9974, device='cuda:0')
epoch: 39 test_true_pfm: -0.6769222547686259 sim_pfm: -999.993955830733
episode: 156 training return: tensor(-999.9973, device='cuda:0')
episode: 157 training return: tensor(-999.9973, device='cuda:0')
episode: 158 training return: tensor(-999.9986, device='cuda:0')
episode: 159 training return: tensor(-999.9931, device='cuda:0')
epoch: 40 test_true_pfm: -0.20087111836817972 sim_pfm: -999.994011859099
episode: 160 training return: tensor(-999.9957, device='cuda:0')
episode: 161 training return: tensor(-999.9958, device='cuda:0')
episode: 162 training return: tensor(-999.9988, device='cuda:0')
episode: 163 training return: tensor(-999.9949, device='cuda:0')
epoch: 41 test_true_pfm: 0.0338023646741488 sim_pfm: -999.9938361446062
episode: 164 training return: tensor(-999.9979, device='cuda:0')
episode: 165 training return: tensor(-999.9984, device='cuda:0')
episode: 166 training return: tensor(-999.9958, device='cuda:0')
episode: 167 training return: tensor(-999.9957, device='cuda:0')
epoch: 42 test_true_pfm: 0.45635631054690995 sim_pfm: -999.9937782088915
episode: 168 training return: tensor(-999.9962, device='cuda:0')
episode: 169 training return: tensor(-999.9982, device='cuda:0')
episode: 170 training return: tensor(-999.9930, device='cuda:0')
episode: 171 training return: tensor(-999.9926, device='cuda:0')
epoch: 43 test_true_pfm: -0.2935498221726028 sim_pfm: -999.9938354094824
episode: 172 training return: tensor(-999.9971, device='cuda:0')
episode: 173 training return: tensor(-999.9941, device='cuda:0')
episode: 174 training return: tensor(-999.9984, device='cuda:0')
episode: 175 training return: tensor(-999.9987, device='cuda:0')
epoch: 44 test_true_pfm: -0.41008374487116755 sim_pfm: -999.9940747618675
episode: 176 training return: tensor(-999.9946, device='cuda:0')
episode: 177 training return: tensor(-999.9909, device='cuda:0')
episode: 178 training return: tensor(-999.9985, device='cuda:0')
episode: 179 training return: tensor(-999.9958, device='cuda:0')
epoch: 45 test_true_pfm: -0.9812395167814739 sim_pfm: -999.9940754373869
episode: 180 training return: tensor(-999.9966, device='cuda:0')
episode: 181 training return: tensor(-999.9968, device='cuda:0')
episode: 182 training return: tensor(-999.9980, device='cuda:0')
episode: 183 training return: tensor(-999.9954, device='cuda:0')
epoch: 46 test_true_pfm: -0.26812606779309794 sim_pfm: -999.9940721392632
episode: 184 training return: tensor(-999.9983, device='cuda:0')
episode: 185 training return: tensor(-999.9980, device='cuda:0')
episode: 186 training return: tensor(-999.9976, device='cuda:0')
episode: 187 training return: tensor(-999.9990, device='cuda:0')
epoch: 47 test_true_pfm: -0.19444834292548288 sim_pfm: -999.9940071105957
episode: 188 training return: tensor(-999.9966, device='cuda:0')
episode: 189 training return: tensor(-999.9961, device='cuda:0')
episode: 190 training return: tensor(-999.9976, device='cuda:0')
episode: 191 training return: tensor(-999.9972, device='cuda:0')
epoch: 48 test_true_pfm: -0.3289813176373824 sim_pfm: -999.9940150380135
episode: 192 training return: tensor(-999.9972, device='cuda:0')
episode: 193 training return: tensor(-999.9966, device='cuda:0')
episode: 194 training return: tensor(-999.9985, device='cuda:0')
episode: 195 training return: tensor(-999.9979, device='cuda:0')
epoch: 49 test_true_pfm: -0.5110031481577717 sim_pfm: -999.9939511418343
episode: 196 training return: tensor(-999.9976, device='cuda:0')
episode: 197 training return: tensor(-999.9971, device='cuda:0')
episode: 198 training return: tensor(-999.9969, device='cuda:0')
episode: 199 training return: tensor(-999.9966, device='cuda:0')
epoch: 50 test_true_pfm: 0.04210358470019102 sim_pfm: -999.9940069715182
episode: 200 training return: tensor(-999.9960, device='cuda:0')
episode: 201 training return: tensor(-999.9983, device='cuda:0')
episode: 202 training return: tensor(-999.9976, device='cuda:0')
episode: 203 training return: tensor(-999.9979, device='cuda:0')
epoch: 51 test_true_pfm: -0.5961101164029005 sim_pfm: -999.9938376347224
episode: 204 training return: tensor(-999.9973, device='cuda:0')
episode: 205 training return: tensor(-999.9906, device='cuda:0')
episode: 206 training return: tensor(-999.9973, device='cuda:0')
episode: 207 training return: tensor(-999.9933, device='cuda:0')
epoch: 52 test_true_pfm: -0.21151150313238118 sim_pfm: -999.9941864609718
episode: 208 training return: tensor(-999.9977, device='cuda:0')
episode: 209 training return: tensor(-999.9993, device='cuda:0')
episode: 210 training return: tensor(-999.9993, device='cuda:0')
episode: 211 training return: tensor(-999.9969, device='cuda:0')
epoch: 53 test_true_pfm: 0.19423275395424433 sim_pfm: -999.9940687417984
episode: 212 training return: tensor(-999.9985, device='cuda:0')
episode: 213 training return: tensor(-999.9943, device='cuda:0')
episode: 214 training return: tensor(-999.9993, device='cuda:0')
episode: 215 training return: tensor(-999.9960, device='cuda:0')
epoch: 54 test_true_pfm: -0.12758406250849297 sim_pfm: -999.9938344160715
episode: 216 training return: tensor(-999.9957, device='cuda:0')
episode: 217 training return: tensor(-999.9980, device='cuda:0')
episode: 218 training return: tensor(-999.9979, device='cuda:0')
episode: 219 training return: tensor(-999.9937, device='cuda:0')
epoch: 55 test_true_pfm: -0.1507800453302658 sim_pfm: -999.993954718113
episode: 220 training return: tensor(-999.9965, device='cuda:0')
episode: 221 training return: tensor(-999.9990, device='cuda:0')
episode: 222 training return: tensor(-999.9962, device='cuda:0')
episode: 223 training return: tensor(-999.9930, device='cuda:0')
epoch: 56 test_true_pfm: -0.022496792035476127 sim_pfm: -999.9940180182457
episode: 224 training return: tensor(-999.9976, device='cuda:0')
episode: 225 training return: tensor(-999.9976, device='cuda:0')
episode: 226 training return: tensor(-999.9993, device='cuda:0')
episode: 227 training return: tensor(-999.9967, device='cuda:0')
epoch: 57 test_true_pfm: -0.2568257507938581 sim_pfm: -999.9939645926157
episode: 228 training return: tensor(-999.9966, device='cuda:0')
episode: 229 training return: tensor(-999.9954, device='cuda:0')
episode: 230 training return: tensor(-999.9960, device='cuda:0')
episode: 231 training return: tensor(-999.9965, device='cuda:0')
epoch: 58 test_true_pfm: -0.20037222182475103 sim_pfm: -999.9939497709274
episode: 232 training return: tensor(-999.9982, device='cuda:0')
episode: 233 training return: tensor(-999.9944, device='cuda:0')
episode: 234 training return: tensor(-999.9976, device='cuda:0')
episode: 235 training return: tensor(-999.9962, device='cuda:0')
epoch: 59 test_true_pfm: 0.4541457929129522 sim_pfm: -999.9937783082327
episode: 236 training return: tensor(-999.9960, device='cuda:0')
episode: 237 training return: tensor(-999.9971, device='cuda:0')
episode: 238 training return: tensor(-999.9990, device='cuda:0')
episode: 239 training return: tensor(-999.9963, device='cuda:0')
epoch: 60 test_true_pfm: -0.6714890222548697 sim_pfm: -999.9939514398575
episode: 240 training return: tensor(-999.9957, device='cuda:0')
episode: 241 training return: tensor(-999.9965, device='cuda:0')
episode: 242 training return: tensor(-999.9977, device='cuda:0')
episode: 243 training return: tensor(-999.9954, device='cuda:0')
epoch: 61 test_true_pfm: -0.3087932451006705 sim_pfm: -999.9938405950865
episode: 244 training return: tensor(-999.9977, device='cuda:0')
episode: 245 training return: tensor(-999.9957, device='cuda:0')
episode: 246 training return: tensor(-999.9973, device='cuda:0')
episode: 247 training return: tensor(-999.9924, device='cuda:0')
epoch: 62 test_true_pfm: 0.3519573188278204 sim_pfm: -999.9941267371178
episode: 248 training return: tensor(-999.9984, device='cuda:0')
episode: 249 training return: tensor(-999.9986, device='cuda:0')
episode: 250 training return: tensor(-999.9988, device='cuda:0')
episode: 251 training return: tensor(-999.9952, device='cuda:0')
epoch: 63 test_true_pfm: 0.07172347550418819 sim_pfm: -999.9937161405882
episode: 252 training return: tensor(-999.9995, device='cuda:0')
episode: 253 training return: tensor(-999.9998, device='cuda:0')
episode: 254 training return: tensor(-999.9975, device='cuda:0')
episode: 255 training return: tensor(-999.9974, device='cuda:0')
epoch: 64 test_true_pfm: -0.5387337456510721 sim_pfm: -999.9938961466154
episode: 256 training return: tensor(-999.9968, device='cuda:0')
episode: 257 training return: tensor(-999.9958, device='cuda:0')
episode: 258 training return: tensor(-999.9989, device='cuda:0')
episode: 259 training return: tensor(-999.9973, device='cuda:0')
epoch: 65 test_true_pfm: -0.31026172011219827 sim_pfm: -999.9938963452975
episode: 260 training return: tensor(-999.9977, device='cuda:0')
episode: 261 training return: tensor(-999.9972, device='cuda:0')
episode: 262 training return: tensor(-999.9942, device='cuda:0')
episode: 263 training return: tensor(-999.9977, device='cuda:0')
epoch: 66 test_true_pfm: -0.37351538124355727 sim_pfm: -999.9939558108648
episode: 264 training return: tensor(-999.9969, device='cuda:0')
episode: 265 training return: tensor(-999.9968, device='cuda:0')
episode: 266 training return: tensor(-999.9968, device='cuda:0')
episode: 267 training return: tensor(-999.9988, device='cuda:0')
epoch: 67 test_true_pfm: 0.08456134266444125 sim_pfm: -999.9939565062523
episode: 268 training return: tensor(-999.9988, device='cuda:0')
episode: 269 training return: tensor(-999.9981, device='cuda:0')
episode: 270 training return: tensor(-999.9984, device='cuda:0')
episode: 271 training return: tensor(-999.9941, device='cuda:0')
epoch: 68 test_true_pfm: 0.035846278944338915 sim_pfm: -999.9940725763639
episode: 272 training return: tensor(-999.9963, device='cuda:0')
episode: 273 training return: tensor(-999.9971, device='cuda:0')
episode: 274 training return: tensor(-999.9908, device='cuda:0')
episode: 275 training return: tensor(-999.9965, device='cuda:0')
epoch: 69 test_true_pfm: -0.3585608955953945 sim_pfm: -999.9939539432526
episode: 276 training return: tensor(-999.9983, device='cuda:0')
episode: 277 training return: tensor(-999.9976, device='cuda:0')
episode: 278 training return: tensor(-999.9974, device='cuda:0')
episode: 279 training return: tensor(-999.9991, device='cuda:0')
epoch: 70 test_true_pfm: 0.24339090864792745 sim_pfm: -999.9938387274742
episode: 280 training return: tensor(-999.9978, device='cuda:0')
episode: 281 training return: tensor(-999.9962, device='cuda:0')
episode: 282 training return: tensor(-999.9938, device='cuda:0')
episode: 283 training return: tensor(-999.9958, device='cuda:0')
epoch: 71 test_true_pfm: -0.7665421806320915 sim_pfm: -999.9940122167269
episode: 284 training return: tensor(-999.9968, device='cuda:0')
episode: 285 training return: tensor(-999.9974, device='cuda:0')
episode: 286 training return: tensor(-999.9977, device='cuda:0')
episode: 287 training return: tensor(-999.9974, device='cuda:0')
epoch: 72 test_true_pfm: -0.2192076130851183 sim_pfm: -999.9938978354136
episode: 288 training return: tensor(-999.9990, device='cuda:0')
episode: 289 training return: tensor(-999.9967, device='cuda:0')
episode: 290 training return: tensor(-999.9947, device='cuda:0')
episode: 291 training return: tensor(-999.9953, device='cuda:0')
epoch: 73 test_true_pfm: -0.04736853446251086 sim_pfm: -999.9938339392344
episode: 292 training return: tensor(-999.9993, device='cuda:0')
episode: 293 training return: tensor(-999.9983, device='cuda:0')
episode: 294 training return: tensor(-999.9958, device='cuda:0')
episode: 295 training return: tensor(-999.9960, device='cuda:0')
epoch: 74 test_true_pfm: -1.2323717672927588 sim_pfm: -999.9938346743584
episode: 296 training return: tensor(-999.9973, device='cuda:0')
episode: 297 training return: tensor(-999.9964, device='cuda:0')
episode: 298 training return: tensor(-999.9975, device='cuda:0')
episode: 299 training return: tensor(-999.9973, device='cuda:0')
epoch: 75 test_true_pfm: -0.3376420905591327 sim_pfm: -999.9940149982771
episode: 300 training return: tensor(-999.9997, device='cuda:0')
episode: 301 training return: tensor(-999.9963, device='cuda:0')
episode: 302 training return: tensor(-999.9965, device='cuda:0')
episode: 303 training return: tensor(-999.9977, device='cuda:0')
epoch: 76 test_true_pfm: -0.18527654238262956 sim_pfm: -999.9938929080963
episode: 304 training return: tensor(-999.9971, device='cuda:0')
episode: 305 training return: tensor(-999.9963, device='cuda:0')
episode: 306 training return: tensor(-999.9957, device='cuda:0')
episode: 307 training return: tensor(-999.9958, device='cuda:0')
epoch: 77 test_true_pfm: -0.19331117944792023 sim_pfm: -999.9937780102094
episode: 308 training return: tensor(-999.9955, device='cuda:0')
episode: 309 training return: tensor(-999.9968, device='cuda:0')
episode: 310 training return: tensor(-999.9963, device='cuda:0')
episode: 311 training return: tensor(-999.9977, device='cuda:0')
epoch: 78 test_true_pfm: -0.2942808928940322 sim_pfm: -999.9938365022341
episode: 312 training return: tensor(-999.9984, device='cuda:0')
episode: 313 training return: tensor(-999.9936, device='cuda:0')
episode: 314 training return: tensor(-999.9987, device='cuda:0')
episode: 315 training return: tensor(-999.9977, device='cuda:0')
epoch: 79 test_true_pfm: 0.7349925457486588 sim_pfm: -999.9940060575803
episode: 316 training return: tensor(-999.9988, device='cuda:0')
episode: 317 training return: tensor(-999.9972, device='cuda:0')
episode: 318 training return: tensor(-999.9959, device='cuda:0')
episode: 319 training return: tensor(-999.9968, device='cuda:0')
epoch: 80 test_true_pfm: 0.192130552205385 sim_pfm: -999.9939551949501
episode: 320 training return: tensor(-999.9975, device='cuda:0')
episode: 321 training return: tensor(-999.9973, device='cuda:0')
episode: 322 training return: tensor(-999.9973, device='cuda:0')
episode: 323 training return: tensor(-999.9982, device='cuda:0')
epoch: 81 test_true_pfm: 0.2393218581151122 sim_pfm: -999.9939563671747
episode: 324 training return: tensor(-999.9998, device='cuda:0')
episode: 325 training return: tensor(-999.9936, device='cuda:0')
episode: 326 training return: tensor(-999.9982, device='cuda:0')
episode: 327 training return: tensor(-999.9994, device='cuda:0')
epoch: 82 test_true_pfm: -0.7699355619984839 sim_pfm: -999.9940754373869
episode: 328 training return: tensor(-999.9995, device='cuda:0')
episode: 329 training return: tensor(-999.9982, device='cuda:0')
episode: 330 training return: tensor(-999.9968, device='cuda:0')
episode: 331 training return: tensor(-999.9968, device='cuda:0')
epoch: 83 test_true_pfm: 0.651750297891903 sim_pfm: -999.9939521551132
episode: 332 training return: tensor(-999.9969, device='cuda:0')
episode: 333 training return: tensor(-999.9991, device='cuda:0')
episode: 334 training return: tensor(-999.9938, device='cuda:0')
episode: 335 training return: tensor(-999.9971, device='cuda:0')
epoch: 84 test_true_pfm: -0.5565873433374152 sim_pfm: -999.9939517378807
episode: 336 training return: tensor(-999.9988, device='cuda:0')
episode: 337 training return: tensor(-999.9987, device='cuda:0')
episode: 338 training return: tensor(-999.9959, device='cuda:0')
episode: 339 training return: tensor(-999.9964, device='cuda:0')
epoch: 85 test_true_pfm: 0.23365033158618984 sim_pfm: -999.9938313563665
episode: 340 training return: tensor(-999.9982, device='cuda:0')
episode: 341 training return: tensor(-999.9974, device='cuda:0')
episode: 342 training return: tensor(-999.9977, device='cuda:0')
episode: 343 training return: tensor(-999.9942, device='cuda:0')
epoch: 86 test_true_pfm: -0.6567837512314669 sim_pfm: -999.993956108888
episode: 344 training return: tensor(-999.9969, device='cuda:0')
episode: 345 training return: tensor(-999.9993, device='cuda:0')
episode: 346 training return: tensor(-999.9971, device='cuda:0')
episode: 347 training return: tensor(-999.9966, device='cuda:0')
epoch: 87 test_true_pfm: 0.2979156754953965 sim_pfm: -999.9938338398933
episode: 348 training return: tensor(-999.9941, device='cuda:0')
episode: 349 training return: tensor(-999.9972, device='cuda:0')
episode: 350 training return: tensor(-999.9983, device='cuda:0')
episode: 351 training return: tensor(-999.9977, device='cuda:0')
epoch: 88 test_true_pfm: 0.18025475547430145 sim_pfm: -999.993654290835
episode: 352 training return: tensor(-999.9968, device='cuda:0')
episode: 353 training return: tensor(-999.9940, device='cuda:0')
episode: 354 training return: tensor(-999.9987, device='cuda:0')
episode: 355 training return: tensor(-999.9957, device='cuda:0')
epoch: 89 test_true_pfm: -0.9344561035023502 sim_pfm: -999.993954817454
episode: 356 training return: tensor(-999.9949, device='cuda:0')
episode: 357 training return: tensor(-999.9976, device='cuda:0')
episode: 358 training return: tensor(-999.9978, device='cuda:0')
episode: 359 training return: tensor(-999.9987, device='cuda:0')
epoch: 90 test_true_pfm: -0.07586215816985832 sim_pfm: -999.9939496914545
episode: 360 training return: tensor(-999.9966, device='cuda:0')
episode: 361 training return: tensor(-999.9973, device='cuda:0')
episode: 362 training return: tensor(-999.9993, device='cuda:0')
episode: 363 training return: tensor(-999.9983, device='cuda:0')
epoch: 91 test_true_pfm: -0.40795252924577485 sim_pfm: -999.9939491351446
episode: 364 training return: tensor(-999.9976, device='cuda:0')
episode: 365 training return: tensor(-999.9982, device='cuda:0')
episode: 366 training return: tensor(-999.9959, device='cuda:0')
episode: 367 training return: tensor(-999.9961, device='cuda:0')
epoch: 92 test_true_pfm: -0.7767790114544931 sim_pfm: -999.9938276608785
episode: 368 training return: tensor(-999.9976, device='cuda:0')
episode: 369 training return: tensor(-999.9971, device='cuda:0')
episode: 370 training return: tensor(-999.9983, device='cuda:0')
episode: 371 training return: tensor(-999.9954, device='cuda:0')
epoch: 93 test_true_pfm: -0.46989714932185334 sim_pfm: -999.9938885966936
episode: 372 training return: tensor(-999.9966, device='cuda:0')
episode: 373 training return: tensor(-999.9957, device='cuda:0')
episode: 374 training return: tensor(-999.9975, device='cuda:0')
episode: 375 training return: tensor(-999.9963, device='cuda:0')
epoch: 94 test_true_pfm: -0.43016764772819654 sim_pfm: -999.9940185149511
episode: 376 training return: tensor(-999.9470, device='cuda:0')
episode: 377 training return: tensor(-999.9988, device='cuda:0')
episode: 378 training return: tensor(-999.9987, device='cuda:0')
episode: 379 training return: tensor(-999.9955, device='cuda:0')
epoch: 95 test_true_pfm: -0.23689943193338547 sim_pfm: -999.9938389658928
episode: 380 training return: tensor(-999.9959, device='cuda:0')
episode: 381 training return: tensor(-999.9976, device='cuda:0')
episode: 382 training return: tensor(-999.9930, device='cuda:0')
episode: 383 training return: tensor(-999.9989, device='cuda:0')
epoch: 96 test_true_pfm: -0.7225081340879506 sim_pfm: -999.9938334226608
episode: 384 training return: tensor(-999.9993, device='cuda:0')
episode: 385 training return: tensor(-999.9991, device='cuda:0')
episode: 386 training return: tensor(-999.9977, device='cuda:0')
episode: 387 training return: tensor(-999.9968, device='cuda:0')
epoch: 97 test_true_pfm: -0.05420270095853993 sim_pfm: -999.9940097928047
episode: 388 training return: tensor(-999.9992, device='cuda:0')
episode: 389 training return: tensor(-999.9958, device='cuda:0')
episode: 390 training return: tensor(-999.9908, device='cuda:0')
episode: 391 training return: tensor(-999.9965, device='cuda:0')
epoch: 98 test_true_pfm: 0.08329755538385834 sim_pfm: -999.9939546585083
episode: 392 training return: tensor(-999.9973, device='cuda:0')
episode: 393 training return: tensor(-999.9990, device='cuda:0')
episode: 394 training return: tensor(-999.9985, device='cuda:0')
episode: 395 training return: tensor(-999.9977, device='cuda:0')
epoch: 99 test_true_pfm: 0.5231924176983156 sim_pfm: -999.9940111637115
episode: 396 training return: tensor(-999.9971, device='cuda:0')
episode: 397 training return: tensor(-999.9957, device='cuda:0')
episode: 398 training return: tensor(-999.9984, device='cuda:0')
episode: 399 training return: tensor(-999.9985, device='cuda:0')
epoch: 100 test_true_pfm: -0.6810116646017423 sim_pfm: -999.994013607502
episode: 400 training return: tensor(-999.9959, device='cuda:0')
episode: 401 training return: tensor(-999.9973, device='cuda:0')
episode: 402 training return: tensor(-999.9978, device='cuda:0')
episode: 403 training return: tensor(-999.9976, device='cuda:0')
epoch: 101 test_true_pfm: -0.9285116484438877 sim_pfm: -999.9938925504684
episode: 404 training return: tensor(-999.9943, device='cuda:0')
episode: 405 training return: tensor(-999.9989, device='cuda:0')
episode: 406 training return: tensor(-999.9955, device='cuda:0')
episode: 407 training return: tensor(-999.9966, device='cuda:0')
epoch: 102 test_true_pfm: 0.044199453658771294 sim_pfm: -999.9940119584402
episode: 408 training return: tensor(-999.9977, device='cuda:0')
episode: 409 training return: tensor(-999.9980, device='cuda:0')
episode: 410 training return: tensor(-999.9990, device='cuda:0')
episode: 411 training return: tensor(-999.9971, device='cuda:0')
epoch: 103 test_true_pfm: -0.19885584589843128 sim_pfm: -999.9938392241796
episode: 412 training return: tensor(-999.9995, device='cuda:0')
episode: 413 training return: tensor(-999.9866, device='cuda:0')
episode: 414 training return: tensor(-999.9946, device='cuda:0')
episode: 415 training return: tensor(-999.9966, device='cuda:0')
epoch: 104 test_true_pfm: 0.20665794597005682 sim_pfm: -999.993825395902
episode: 416 training return: tensor(-999.9979, device='cuda:0')
episode: 417 training return: tensor(-999.9980, device='cuda:0')
episode: 418 training return: tensor(-999.9985, device='cuda:0')
episode: 419 training return: tensor(-999.9958, device='cuda:0')
epoch: 105 test_true_pfm: 0.1579201879855582 sim_pfm: -999.9938353697459
episode: 420 training return: tensor(-999.9980, device='cuda:0')
episode: 421 training return: tensor(-999.9985, device='cuda:0')
episode: 422 training return: tensor(-999.9964, device='cuda:0')
episode: 423 training return: tensor(-999.9959, device='cuda:0')
epoch: 106 test_true_pfm: -0.2780356033312308 sim_pfm: -999.9940632780393
episode: 424 training return: tensor(-999.9951, device='cuda:0')
episode: 425 training return: tensor(-999.9982, device='cuda:0')
episode: 426 training return: tensor(-999.9951, device='cuda:0')
episode: 427 training return: tensor(-999.9982, device='cuda:0')
epoch: 107 test_true_pfm: -0.8201604252178641 sim_pfm: -999.993947426478
episode: 428 training return: tensor(-999.9954, device='cuda:0')
episode: 429 training return: tensor(-999.9988, device='cuda:0')
episode: 430 training return: tensor(-999.9973, device='cuda:0')
episode: 431 training return: tensor(-999.9988, device='cuda:0')
epoch: 108 test_true_pfm: -0.3029516689977801 sim_pfm: -999.9938329656919
episode: 432 training return: tensor(-999.9996, device='cuda:0')
episode: 433 training return: tensor(-999.9967, device='cuda:0')
episode: 434 training return: tensor(-999.9935, device='cuda:0')
episode: 435 training return: tensor(-999.9941, device='cuda:0')
epoch: 109 test_true_pfm: -0.2718173885739069 sim_pfm: -999.9939500292143
episode: 436 training return: tensor(-999.9976, device='cuda:0')
episode: 437 training return: tensor(-999.9954, device='cuda:0')
episode: 438 training return: tensor(-999.9988, device='cuda:0')
episode: 439 training return: tensor(-999.9982, device='cuda:0')
epoch: 110 test_true_pfm: -0.6721650842835651 sim_pfm: -999.9939022262892
episode: 440 training return: tensor(-999.9995, device='cuda:0')
episode: 441 training return: tensor(-999.9991, device='cuda:0')
episode: 442 training return: tensor(-999.9982, device='cuda:0')
episode: 443 training return: tensor(-999.9989, device='cuda:0')
epoch: 111 test_true_pfm: -0.6303117034887928 sim_pfm: -999.9940178195635
episode: 444 training return: tensor(-999.9986, device='cuda:0')
episode: 445 training return: tensor(-999.9990, device='cuda:0')
episode: 446 training return: tensor(-999.9883, device='cuda:0')
episode: 447 training return: tensor(-999.9974, device='cuda:0')
epoch: 112 test_true_pfm: -0.5770794514851533 sim_pfm: -999.9939527908961
episode: 448 training return: tensor(-999.9973, device='cuda:0')
episode: 449 training return: tensor(-999.9978, device='cuda:0')
episode: 450 training return: tensor(-999.9984, device='cuda:0')
episode: 451 training return: tensor(-999.9990, device='cuda:0')
epoch: 113 test_true_pfm: -0.7186695464606218 sim_pfm: -999.9939540425936
episode: 452 training return: tensor(-999.9983, device='cuda:0')
episode: 453 training return: tensor(-999.9987, device='cuda:0')
episode: 454 training return: tensor(-999.9987, device='cuda:0')
episode: 455 training return: tensor(-999.9960, device='cuda:0')
epoch: 114 test_true_pfm: -0.5741922456411314 sim_pfm: -999.9940103093783
episode: 456 training return: tensor(-999.9945, device='cuda:0')
episode: 457 training return: tensor(-999.9963, device='cuda:0')
episode: 458 training return: tensor(-999.9988, device='cuda:0')
episode: 459 training return: tensor(-999.9972, device='cuda:0')
epoch: 115 test_true_pfm: -0.30406337338724687 sim_pfm: -999.9941280086836
episode: 460 training return: tensor(-999.9988, device='cuda:0')
episode: 461 training return: tensor(-999.9982, device='cuda:0')
episode: 462 training return: tensor(-999.9968, device='cuda:0')
episode: 463 training return: tensor(-999.9971, device='cuda:0')
epoch: 116 test_true_pfm: -0.6050894594124222 sim_pfm: -999.9939555327097
episode: 464 training return: tensor(-999.9974, device='cuda:0')
episode: 465 training return: tensor(-999.9966, device='cuda:0')
episode: 466 training return: tensor(-999.9995, device='cuda:0')
episode: 467 training return: tensor(-999.9952, device='cuda:0')
epoch: 117 test_true_pfm: -0.49097330337054323 sim_pfm: -999.9938324491183
episode: 468 training return: tensor(-999.9988, device='cuda:0')
episode: 469 training return: tensor(-999.9989, device='cuda:0')
episode: 470 training return: tensor(-999.9993, device='cuda:0')
episode: 471 training return: tensor(-999.9970, device='cuda:0')
epoch: 118 test_true_pfm: 0.12138869128775626 sim_pfm: -999.9941939711571
episode: 472 training return: tensor(-999.9958, device='cuda:0')
episode: 473 training return: tensor(-999.9979, device='cuda:0')
episode: 474 training return: tensor(-999.9974, device='cuda:0')
episode: 475 training return: tensor(-999.9992, device='cuda:0')
epoch: 119 test_true_pfm: -0.2635482493136878 sim_pfm: -999.9940123955408
episode: 476 training return: tensor(-999.9996, device='cuda:0')
episode: 477 training return: tensor(-999.9961, device='cuda:0')
episode: 478 training return: tensor(-999.9966, device='cuda:0')
episode: 479 training return: tensor(-999.9922, device='cuda:0')
epoch: 120 test_true_pfm: -0.7033057588281878 sim_pfm: -999.9940714041392
episode: 480 training return: tensor(-999.9958, device='cuda:0')
episode: 481 training return: tensor(-999.9960, device='cuda:0')
episode: 482 training return: tensor(-999.9962, device='cuda:0')
episode: 483 training return: tensor(-999.9968, device='cuda:0')
epoch: 121 test_true_pfm: -0.1900368819307696 sim_pfm: -999.9937683145205
episode: 484 training return: tensor(-999.9962, device='cuda:0')
episode: 485 training return: tensor(-999.9968, device='cuda:0')
episode: 486 training return: tensor(-999.9958, device='cuda:0')
episode: 487 training return: tensor(-999.9970, device='cuda:0')
epoch: 122 test_true_pfm: 0.05916864823603652 sim_pfm: -999.9939455986023
episode: 488 training return: tensor(-999.9984, device='cuda:0')
episode: 489 training return: tensor(-999.9981, device='cuda:0')
episode: 490 training return: tensor(-999.9982, device='cuda:0')
episode: 491 training return: tensor(-999.9984, device='cuda:0')
epoch: 123 test_true_pfm: -0.4182340684365333 sim_pfm: -999.9940092960993
episode: 492 training return: tensor(-999.9982, device='cuda:0')
episode: 493 training return: tensor(-999.9989, device='cuda:0')
episode: 494 training return: tensor(-999.9996, device='cuda:0')
episode: 495 training return: tensor(-999.9966, device='cuda:0')
epoch: 124 test_true_pfm: 0.09299045015434652 sim_pfm: -999.9939581751823
episode: 496 training return: tensor(-999.9979, device='cuda:0')
episode: 497 training return: tensor(-999.9960, device='cuda:0')
episode: 498 training return: tensor(-999.9979, device='cuda:0')
episode: 499 training return: tensor(-999.9972, device='cuda:0')
epoch: 125 test_true_pfm: -0.25437735541020573 sim_pfm: -999.9940153956413
episode: 500 training return: tensor(-999.9985, device='cuda:0')
episode: 501 training return: tensor(-999.9970, device='cuda:0')
episode: 502 training return: tensor(-999.9975, device='cuda:0')
episode: 503 training return: tensor(-999.9976, device='cuda:0')
epoch: 126 test_true_pfm: -0.9204196466778866 sim_pfm: -999.9940011501312
episode: 504 training return: tensor(-999.9951, device='cuda:0')
episode: 505 training return: tensor(-999.9954, device='cuda:0')
episode: 506 training return: tensor(-999.9973, device='cuda:0')
episode: 507 training return: tensor(-999.9965, device='cuda:0')
epoch: 127 test_true_pfm: -0.5465619306257694 sim_pfm: -999.9939525127411
episode: 508 training return: tensor(-999.9971, device='cuda:0')
episode: 509 training return: tensor(-999.9979, device='cuda:0')
episode: 510 training return: tensor(-999.9965, device='cuda:0')
episode: 511 training return: tensor(-999.9966, device='cuda:0')
epoch: 128 test_true_pfm: 0.3913118129138933 sim_pfm: -999.9940172036489
episode: 512 training return: tensor(-999.9912, device='cuda:0')
episode: 513 training return: tensor(-999.9972, device='cuda:0')
episode: 514 training return: tensor(-999.9983, device='cuda:0')
episode: 515 training return: tensor(-999.9971, device='cuda:0')
epoch: 129 test_true_pfm: 0.13462487547140856 sim_pfm: -999.9940046866735
episode: 516 training return: tensor(-999.9960, device='cuda:0')
episode: 517 training return: tensor(-999.9977, device='cuda:0')
episode: 518 training return: tensor(-999.9974, device='cuda:0')
episode: 519 training return: tensor(-999.9946, device='cuda:0')
epoch: 130 test_true_pfm: 0.08139712896974827 sim_pfm: -999.9938957691193
episode: 520 training return: tensor(-999.9983, device='cuda:0')
episode: 521 training return: tensor(-999.9964, device='cuda:0')
episode: 522 training return: tensor(-999.9966, device='cuda:0')
episode: 523 training return: tensor(-999.9955, device='cuda:0')
epoch: 131 test_true_pfm: 0.09778762769211635 sim_pfm: -999.9938975572586
episode: 524 training return: tensor(-999.9968, device='cuda:0')
episode: 525 training return: tensor(-999.9993, device='cuda:0')
episode: 526 training return: tensor(-999.9981, device='cuda:0')
episode: 527 training return: tensor(-999.9956, device='cuda:0')
epoch: 132 test_true_pfm: -0.25809455304707174 sim_pfm: -999.9938886761665
episode: 528 training return: tensor(-999.9959, device='cuda:0')
episode: 529 training return: tensor(-999.9951, device='cuda:0')
episode: 530 training return: tensor(-999.9973, device='cuda:0')
episode: 531 training return: tensor(-999.9985, device='cuda:0')
epoch: 133 test_true_pfm: -0.9796481835129324 sim_pfm: -999.9938318928083
episode: 532 training return: tensor(-999.9974, device='cuda:0')
episode: 533 training return: tensor(-999.9958, device='cuda:0')
episode: 534 training return: tensor(-999.9939, device='cuda:0')
episode: 535 training return: tensor(-999.9973, device='cuda:0')
epoch: 134 test_true_pfm: 0.24944769243397028 sim_pfm: -999.9939463535944
episode: 536 training return: tensor(-999.9991, device='cuda:0')
episode: 537 training return: tensor(-999.9991, device='cuda:0')
episode: 538 training return: tensor(-999.9977, device='cuda:0')
episode: 539 training return: tensor(-999.9968, device='cuda:0')
epoch: 135 test_true_pfm: -0.039921071554313646 sim_pfm: -999.9939441482226
episode: 540 training return: tensor(-999.9967, device='cuda:0')
episode: 541 training return: tensor(-999.9981, device='cuda:0')
episode: 542 training return: tensor(-999.9927, device='cuda:0')
episode: 543 training return: tensor(-999.9982, device='cuda:0')
epoch: 136 test_true_pfm: -0.17158018105705933 sim_pfm: -999.9938324292501
episode: 544 training return: tensor(-999.9984, device='cuda:0')
episode: 545 training return: tensor(-999.9949, device='cuda:0')
episode: 546 training return: tensor(-999.9995, device='cuda:0')
episode: 547 training return: tensor(-999.9973, device='cuda:0')
epoch: 137 test_true_pfm: -0.28897451252145884 sim_pfm: -999.9938966433207
episode: 548 training return: tensor(-999.9965, device='cuda:0')
episode: 549 training return: tensor(-999.9973, device='cuda:0')
episode: 550 training return: tensor(-999.9988, device='cuda:0')
episode: 551 training return: tensor(-999.9963, device='cuda:0')
epoch: 138 test_true_pfm: -0.002986975825069016 sim_pfm: -999.9940721392632
episode: 552 training return: tensor(-999.9981, device='cuda:0')
episode: 553 training return: tensor(-999.9959, device='cuda:0')
episode: 554 training return: tensor(-999.9973, device='cuda:0')
episode: 555 training return: tensor(-999.9971, device='cuda:0')
epoch: 139 test_true_pfm: -0.21480133329747006 sim_pfm: -999.9940173824629
episode: 556 training return: tensor(-999.9950, device='cuda:0')
episode: 557 training return: tensor(-999.9954, device='cuda:0')
episode: 558 training return: tensor(-999.9959, device='cuda:0')
episode: 559 training return: tensor(-999.9976, device='cuda:0')
epoch: 140 test_true_pfm: -0.18306307846668615 sim_pfm: -999.9938870469729
episode: 560 training return: tensor(-999.9976, device='cuda:0')
episode: 561 training return: tensor(-999.9989, device='cuda:0')
episode: 562 training return: tensor(-999.9969, device='cuda:0')
episode: 563 training return: tensor(-999.9957, device='cuda:0')
epoch: 141 test_true_pfm: -0.773326809703807 sim_pfm: -999.9941298762957
episode: 564 training return: tensor(-999.9980, device='cuda:0')
episode: 565 training return: tensor(-999.9965, device='cuda:0')
episode: 566 training return: tensor(-999.9985, device='cuda:0')
episode: 567 training return: tensor(-999.9976, device='cuda:0')
epoch: 142 test_true_pfm: -0.26017279533011006 sim_pfm: -999.9939537843069
episode: 568 training return: tensor(-999.9974, device='cuda:0')
episode: 569 training return: tensor(-999.9981, device='cuda:0')
episode: 570 training return: tensor(-999.9986, device='cuda:0')
episode: 571 training return: tensor(-999.9976, device='cuda:0')
epoch: 143 test_true_pfm: 0.44624404159933356 sim_pfm: -999.9940715034803
episode: 572 training return: tensor(-999.9973, device='cuda:0')
episode: 573 training return: tensor(-999.9984, device='cuda:0')
episode: 574 training return: tensor(-999.9980, device='cuda:0')
episode: 575 training return: tensor(-999.9979, device='cuda:0')
epoch: 144 test_true_pfm: -1.1437058158829065 sim_pfm: -999.9939526120821
episode: 576 training return: tensor(-999.9981, device='cuda:0')
episode: 577 training return: tensor(-999.9976, device='cuda:0')
episode: 578 training return: tensor(-999.9973, device='cuda:0')
episode: 579 training return: tensor(-999.9993, device='cuda:0')
epoch: 145 test_true_pfm: -0.6736783047528055 sim_pfm: -999.993956387043
episode: 580 training return: tensor(-999.9988, device='cuda:0')
episode: 581 training return: tensor(-999.9967, device='cuda:0')
episode: 582 training return: tensor(-999.9982, device='cuda:0')
episode: 583 training return: tensor(-999.9943, device='cuda:0')
epoch: 146 test_true_pfm: 0.6107599204426878 sim_pfm: -999.9938971201578
episode: 584 training return: tensor(-999.9982, device='cuda:0')
episode: 585 training return: tensor(-999.9983, device='cuda:0')
episode: 586 training return: tensor(-999.9958, device='cuda:0')
episode: 587 training return: tensor(-999.9966, device='cuda:0')
epoch: 147 test_true_pfm: 0.3096344790645585 sim_pfm: -999.9939502278963
episode: 588 training return: tensor(-999.9978, device='cuda:0')
episode: 589 training return: tensor(-999.9980, device='cuda:0')
episode: 590 training return: tensor(-999.9990, device='cuda:0')
episode: 591 training return: tensor(-999.9976, device='cuda:0')
epoch: 148 test_true_pfm: -0.6658937443842102 sim_pfm: -999.9940085411072
episode: 592 training return: tensor(-999.9951, device='cuda:0')
episode: 593 training return: tensor(-999.9995, device='cuda:0')
episode: 594 training return: tensor(-999.9972, device='cuda:0')
episode: 595 training return: tensor(-999.9952, device='cuda:0')
epoch: 149 test_true_pfm: 0.3799076819895375 sim_pfm: -999.9938961664835
episode: 596 training return: tensor(-999.9979, device='cuda:0')
episode: 597 training return: tensor(-999.9973, device='cuda:0')
episode: 598 training return: tensor(-999.9973, device='cuda:0')
episode: 599 training return: tensor(-999.9968, device='cuda:0')
epoch: 150 test_true_pfm: -0.045673851937959586 sim_pfm: -999.9939553538958
