['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'baseline', '--traj', 'expert', '--seed', '1']
episode: 0 training return: tensor(-999.9971, device='cuda:0')
episode: 1 training return: tensor(-1000., device='cuda:0')
episode: 2 training return: tensor(-1000., device='cuda:0')
episode: 3 training return: tensor(-999.9980, device='cuda:0')
epoch: 1 test_true_pfm: 0.16828492977391496 sim_pfm: -999.9982170859972
episode: 4 training return: tensor(-999.9999, device='cuda:0')
episode: 5 training return: tensor(-1000., device='cuda:0')
episode: 6 training return: tensor(-999.9969, device='cuda:0')
episode: 7 training return: tensor(-1000., device='cuda:0')
epoch: 2 test_true_pfm: -0.4211374919733646 sim_pfm: -999.9982811013857
episode: 8 training return: tensor(-1000., device='cuda:0')
episode: 9 training return: tensor(-999.9971, device='cuda:0')
episode: 10 training return: tensor(-1000., device='cuda:0')
episode: 11 training return: tensor(-999.9980, device='cuda:0')
epoch: 3 test_true_pfm: -0.516692781604069 sim_pfm: -999.9981558918953
episode: 12 training return: tensor(-1000., device='cuda:0')
episode: 13 training return: tensor(-999.9995, device='cuda:0')
episode: 14 training return: tensor(-1000., device='cuda:0')
episode: 15 training return: tensor(-1000., device='cuda:0')
epoch: 4 test_true_pfm: -0.6225532888882642 sim_pfm: -999.9980878035227
episode: 16 training return: tensor(-1000., device='cuda:0')
episode: 17 training return: tensor(-999.9881, device='cuda:0')
episode: 18 training return: tensor(-999.9944, device='cuda:0')
episode: 19 training return: tensor(-999.9972, device='cuda:0')
epoch: 5 test_true_pfm: -0.32572139250202176 sim_pfm: -999.9982180595398
episode: 20 training return: tensor(-999.9992, device='cuda:0')
episode: 21 training return: tensor(-1000., device='cuda:0')
episode: 22 training return: tensor(-1000., device='cuda:0')
episode: 23 training return: tensor(-1000., device='cuda:0')
epoch: 6 test_true_pfm: 0.7081990541380505 sim_pfm: -999.9982103506724
episode: 24 training return: tensor(-1000., device='cuda:0')
episode: 25 training return: tensor(-999.9981, device='cuda:0')
episode: 26 training return: tensor(-1000., device='cuda:0')
episode: 27 training return: tensor(-999.9969, device='cuda:0')
epoch: 7 test_true_pfm: -0.1368516173231039 sim_pfm: -999.9980994462967
episode: 28 training return: tensor(-999.9984, device='cuda:0')
episode: 29 training return: tensor(-999.9995, device='cuda:0')
episode: 30 training return: tensor(-999.9999, device='cuda:0')
episode: 31 training return: tensor(-999.9977, device='cuda:0')
epoch: 8 test_true_pfm: -0.9829995744221232 sim_pfm: -999.9981552958488
episode: 32 training return: tensor(-999.9996, device='cuda:0')
episode: 33 training return: tensor(-1000., device='cuda:0')
episode: 34 training return: tensor(-1000., device='cuda:0')
episode: 35 training return: tensor(-1000., device='cuda:0')
epoch: 9 test_true_pfm: -0.1901792972109293 sim_pfm: -999.9982162117958
episode: 36 training return: tensor(-1000., device='cuda:0')
episode: 37 training return: tensor(-999.9970, device='cuda:0')
episode: 38 training return: tensor(-999.9999, device='cuda:0')
episode: 39 training return: tensor(-999.9993, device='cuda:0')
epoch: 10 test_true_pfm: 0.4245424973638645 sim_pfm: -999.9982754985491
episode: 40 training return: tensor(-999.9996, device='cuda:0')
episode: 41 training return: tensor(-999.9999, device='cuda:0')
episode: 42 training return: tensor(-1000., device='cuda:0')
episode: 43 training return: tensor(-1000., device='cuda:0')
epoch: 11 test_true_pfm: -0.25303792404310305 sim_pfm: -999.9981553951899
episode: 44 training return: tensor(-1000., device='cuda:0')
episode: 45 training return: tensor(-1000., device='cuda:0')
episode: 46 training return: tensor(-999.9987, device='cuda:0')
episode: 47 training return: tensor(-1000., device='cuda:0')
epoch: 12 test_true_pfm: 0.10617955584861642 sim_pfm: -999.9982191324234
episode: 48 training return: tensor(-999.9987, device='cuda:0')
episode: 49 training return: tensor(-999.9960, device='cuda:0')
episode: 50 training return: tensor(-999.9999, device='cuda:0')
episode: 51 training return: tensor(-1000., device='cuda:0')
epoch: 13 test_true_pfm: -0.8896902817888699 sim_pfm: -999.9982106486956
episode: 52 training return: tensor(-999.9994, device='cuda:0')
episode: 53 training return: tensor(-999.9997, device='cuda:0')
episode: 54 training return: tensor(-1000., device='cuda:0')
episode: 55 training return: tensor(-999.9989, device='cuda:0')
epoch: 14 test_true_pfm: 0.03853920490653873 sim_pfm: -999.9982141653696
episode: 56 training return: tensor(-1000., device='cuda:0')
episode: 57 training return: tensor(-999.9999, device='cuda:0')
episode: 58 training return: tensor(-1000., device='cuda:0')
episode: 59 training return: tensor(-999.9987, device='cuda:0')
epoch: 15 test_true_pfm: 0.16732166823973862 sim_pfm: -999.9982107281685
episode: 60 training return: tensor(-999.9943, device='cuda:0')
episode: 61 training return: tensor(-999.9999, device='cuda:0')
episode: 62 training return: tensor(-1000., device='cuda:0')
episode: 63 training return: tensor(-999.9991, device='cuda:0')
epoch: 16 test_true_pfm: 0.44648644433704016 sim_pfm: -999.9982170661291
episode: 64 training return: tensor(-999.9999, device='cuda:0')
episode: 65 training return: tensor(-999.9999, device='cuda:0')
episode: 66 training return: tensor(-1000., device='cuda:0')
episode: 67 training return: tensor(-1000., device='cuda:0')
epoch: 17 test_true_pfm: -0.5720014210130783 sim_pfm: -999.9982188542684
episode: 68 training return: tensor(-999.9999, device='cuda:0')
episode: 69 training return: tensor(-1000., device='cuda:0')
episode: 70 training return: tensor(-1000., device='cuda:0')
episode: 71 training return: tensor(-999.9918, device='cuda:0')
epoch: 18 test_true_pfm: -0.4936328811314213 sim_pfm: -999.9982155561447
episode: 72 training return: tensor(-999.9995, device='cuda:0')
episode: 73 training return: tensor(-1000., device='cuda:0')
episode: 74 training return: tensor(-1000., device='cuda:0')
episode: 75 training return: tensor(-999.9982, device='cuda:0')
epoch: 19 test_true_pfm: 0.046841845962696034 sim_pfm: -999.9981553951899
episode: 76 training return: tensor(-1000., device='cuda:0')
episode: 77 training return: tensor(-1000., device='cuda:0')
episode: 78 training return: tensor(-1000., device='cuda:0')
episode: 79 training return: tensor(-999.9932, device='cuda:0')
epoch: 20 test_true_pfm: -0.43414997329767746 sim_pfm: -999.9981543024381
episode: 80 training return: tensor(-1000., device='cuda:0')
episode: 81 training return: tensor(-999.9999, device='cuda:0')
episode: 82 training return: tensor(-1000., device='cuda:0')
episode: 83 training return: tensor(-999.9967, device='cuda:0')
epoch: 21 test_true_pfm: -0.6580527446281281 sim_pfm: -999.9981497526169
episode: 84 training return: tensor(-999.9944, device='cuda:0')
episode: 85 training return: tensor(-999.9999, device='cuda:0')
episode: 86 training return: tensor(-1000., device='cuda:0')
episode: 87 training return: tensor(-999.9975, device='cuda:0')
epoch: 22 test_true_pfm: -0.5061777569691402 sim_pfm: -999.9982121388117
episode: 88 training return: tensor(-999.9999, device='cuda:0')
episode: 89 training return: tensor(-1000., device='cuda:0')
episode: 90 training return: tensor(-999.9977, device='cuda:0')
episode: 91 training return: tensor(-1000., device='cuda:0')
epoch: 23 test_true_pfm: -0.14791307908695053 sim_pfm: -999.9980991284052
episode: 92 training return: tensor(-999.9957, device='cuda:0')
episode: 93 training return: tensor(-1000., device='cuda:0')
episode: 94 training return: tensor(-999.9998, device='cuda:0')
episode: 95 training return: tensor(-1000., device='cuda:0')
epoch: 24 test_true_pfm: -1.107989227318886 sim_pfm: -999.9982182780901
episode: 96 training return: tensor(-999.9965, device='cuda:0')
episode: 97 training return: tensor(-999.9975, device='cuda:0')
episode: 98 training return: tensor(-999.9954, device='cuda:0')
episode: 99 training return: tensor(-999.9999, device='cuda:0')
epoch: 25 test_true_pfm: -0.7457140259871066 sim_pfm: -999.9981587131819
episode: 100 training return: tensor(-1000., device='cuda:0')
episode: 101 training return: tensor(-1000., device='cuda:0')
episode: 102 training return: tensor(-999.9998, device='cuda:0')
episode: 103 training return: tensor(-999.9971, device='cuda:0')
epoch: 26 test_true_pfm: -0.519887290016564 sim_pfm: -999.9982153773308
episode: 104 training return: tensor(-999.9973, device='cuda:0')
episode: 105 training return: tensor(-1000., device='cuda:0')
episode: 106 training return: tensor(-1000., device='cuda:0')
episode: 107 training return: tensor(-999.9998, device='cuda:0')
epoch: 27 test_true_pfm: 0.19496240953467095 sim_pfm: -999.9981567263603
episode: 108 training return: tensor(-999.9999, device='cuda:0')
episode: 109 training return: tensor(-999.9980, device='cuda:0')
episode: 110 training return: tensor(-999.9986, device='cuda:0')
episode: 111 training return: tensor(-999.9976, device='cuda:0')
epoch: 28 test_true_pfm: -0.6094288050563748 sim_pfm: -999.9982113043467
episode: 112 training return: tensor(-999.9985, device='cuda:0')
episode: 113 training return: tensor(-1000., device='cuda:0')
episode: 114 training return: tensor(-999.9953, device='cuda:0')
episode: 115 training return: tensor(-1000., device='cuda:0')
epoch: 29 test_true_pfm: -1.1739510332433487 sim_pfm: -999.9981546401978
episode: 116 training return: tensor(-999.9988, device='cuda:0')
episode: 117 training return: tensor(-999.9999, device='cuda:0')
episode: 118 training return: tensor(-999.9960, device='cuda:0')
episode: 119 training return: tensor(-999.9976, device='cuda:0')
epoch: 30 test_true_pfm: 0.20916542632893206 sim_pfm: -999.9982737501463
episode: 120 training return: tensor(-1000., device='cuda:0')
episode: 121 training return: tensor(-999.9988, device='cuda:0')
episode: 122 training return: tensor(-1000., device='cuda:0')
episode: 123 training return: tensor(-1000., device='cuda:0')
epoch: 31 test_true_pfm: -1.2411348532698858 sim_pfm: -999.9982133706411
episode: 124 training return: tensor(-1000., device='cuda:0')
episode: 125 training return: tensor(-1000., device='cuda:0')
episode: 126 training return: tensor(-1000., device='cuda:0')
episode: 127 training return: tensor(-1000., device='cuda:0')
epoch: 32 test_true_pfm: -0.37847494411081883 sim_pfm: -999.9982176621755
episode: 128 training return: tensor(-999.9996, device='cuda:0')
episode: 129 training return: tensor(-999.9998, device='cuda:0')
episode: 130 training return: tensor(-999.9996, device='cuda:0')
episode: 131 training return: tensor(-1000., device='cuda:0')
epoch: 33 test_true_pfm: -0.44892757612221706 sim_pfm: -999.9981569647789
episode: 132 training return: tensor(-999.9994, device='cuda:0')
episode: 133 training return: tensor(-1000., device='cuda:0')
episode: 134 training return: tensor(-999.9987, device='cuda:0')
episode: 135 training return: tensor(-999.9957, device='cuda:0')
epoch: 34 test_true_pfm: -0.286781640914433 sim_pfm: -999.9981583356857
episode: 136 training return: tensor(-999.9969, device='cuda:0')
episode: 137 training return: tensor(-999.9973, device='cuda:0')
episode: 138 training return: tensor(-1000., device='cuda:0')
episode: 139 training return: tensor(-1000., device='cuda:0')
epoch: 35 test_true_pfm: 0.11482244438831797 sim_pfm: -999.9982116818428
episode: 140 training return: tensor(-999.9989, device='cuda:0')
episode: 141 training return: tensor(-1000., device='cuda:0')
episode: 142 training return: tensor(-999.9993, device='cuda:0')
episode: 143 training return: tensor(-999.9919, device='cuda:0')
epoch: 36 test_true_pfm: -0.9700789890240458 sim_pfm: -999.9982137878736
episode: 144 training return: tensor(-999.9985, device='cuda:0')
episode: 145 training return: tensor(-1000., device='cuda:0')
episode: 146 training return: tensor(-1000., device='cuda:0')
episode: 147 training return: tensor(-1000., device='cuda:0')
epoch: 37 test_true_pfm: 0.29775209198036506 sim_pfm: -999.9981522162756
episode: 148 training return: tensor(-999.9997, device='cuda:0')
episode: 149 training return: tensor(-999.9999, device='cuda:0')
episode: 150 training return: tensor(-999.9985, device='cuda:0')
episode: 151 training return: tensor(-999.9996, device='cuda:0')
epoch: 38 test_true_pfm: 0.12505990644230577 sim_pfm: -999.998154024283
episode: 152 training return: tensor(-999.9991, device='cuda:0')
episode: 153 training return: tensor(-1000., device='cuda:0')
episode: 154 training return: tensor(-999.9989, device='cuda:0')
episode: 155 training return: tensor(-1000., device='cuda:0')
epoch: 39 test_true_pfm: 0.28986405333123977 sim_pfm: -999.9981520573298
episode: 156 training return: tensor(-1000., device='cuda:0')
episode: 157 training return: tensor(-999.9999, device='cuda:0')
episode: 158 training return: tensor(-999.9999, device='cuda:0')
episode: 159 training return: tensor(-1000., device='cuda:0')
epoch: 40 test_true_pfm: -0.31852243158351445 sim_pfm: -999.9980973601341
episode: 160 training return: tensor(-1000., device='cuda:0')
episode: 161 training return: tensor(-999.9961, device='cuda:0')
episode: 162 training return: tensor(-999.9997, device='cuda:0')
episode: 163 training return: tensor(-999.9996, device='cuda:0')
epoch: 41 test_true_pfm: 0.33296191971960254 sim_pfm: -999.998208741347
episode: 164 training return: tensor(-999.9999, device='cuda:0')
episode: 165 training return: tensor(-999.9974, device='cuda:0')
episode: 166 training return: tensor(-1000., device='cuda:0')
episode: 167 training return: tensor(-999.9971, device='cuda:0')
epoch: 42 test_true_pfm: -0.21179399660320805 sim_pfm: -999.9982099135717
episode: 168 training return: tensor(-1000., device='cuda:0')
episode: 169 training return: tensor(-999.9996, device='cuda:0')
episode: 170 training return: tensor(-999.9930, device='cuda:0')
episode: 171 training return: tensor(-1000., device='cuda:0')
epoch: 43 test_true_pfm: -0.5764088909520947 sim_pfm: -999.9982152779897
episode: 172 training return: tensor(-1000., device='cuda:0')
episode: 173 training return: tensor(-1000., device='cuda:0')
episode: 174 training return: tensor(-1000., device='cuda:0')
episode: 175 training return: tensor(-1000., device='cuda:0')
epoch: 44 test_true_pfm: -0.13743700164453898 sim_pfm: -999.9982170462608
episode: 176 training return: tensor(-1000., device='cuda:0')
episode: 177 training return: tensor(-999.9999, device='cuda:0')
episode: 178 training return: tensor(-999.9999, device='cuda:0')
episode: 179 training return: tensor(-1000., device='cuda:0')
epoch: 45 test_true_pfm: -1.0035647528544216 sim_pfm: -999.9981571237246
episode: 180 training return: tensor(-1000., device='cuda:0')
episode: 181 training return: tensor(-1000., device='cuda:0')
episode: 182 training return: tensor(-999.9969, device='cuda:0')
episode: 183 training return: tensor(-999.9980, device='cuda:0')
epoch: 46 test_true_pfm: -1.2266510680109481 sim_pfm: -999.9981539646784
episode: 184 training return: tensor(-999.9977, device='cuda:0')
episode: 185 training return: tensor(-999.9995, device='cuda:0')
episode: 186 training return: tensor(-1000., device='cuda:0')
episode: 187 training return: tensor(-1000., device='cuda:0')
epoch: 47 test_true_pfm: -0.7175402510540131 sim_pfm: -999.9982155362765
episode: 188 training return: tensor(-999.9999, device='cuda:0')
episode: 189 training return: tensor(-999.9999, device='cuda:0')
episode: 190 training return: tensor(-1000., device='cuda:0')
episode: 191 training return: tensor(-999.9954, device='cuda:0')
epoch: 48 test_true_pfm: -0.13083649712125736 sim_pfm: -999.9982130527496
episode: 192 training return: tensor(-999.9999, device='cuda:0')
episode: 193 training return: tensor(-1000., device='cuda:0')
episode: 194 training return: tensor(-1000., device='cuda:0')
episode: 195 training return: tensor(-1000., device='cuda:0')
epoch: 49 test_true_pfm: -0.5338351061590235 sim_pfm: -999.9981590708097
episode: 196 training return: tensor(-999.9938, device='cuda:0')
episode: 197 training return: tensor(-999.9998, device='cuda:0')
episode: 198 training return: tensor(-999.9968, device='cuda:0')
episode: 199 training return: tensor(-1000., device='cuda:0')
epoch: 50 test_true_pfm: -0.3886782442910315 sim_pfm: -999.998208284378
episode: 200 training return: tensor(-999.9999, device='cuda:0')
episode: 201 training return: tensor(-999.9999, device='cuda:0')
episode: 202 training return: tensor(-999.9998, device='cuda:0')
episode: 203 training return: tensor(-999.9995, device='cuda:0')
epoch: 51 test_true_pfm: -0.6386963949346467 sim_pfm: -999.9981570243835
episode: 204 training return: tensor(-1000., device='cuda:0')
episode: 205 training return: tensor(-1000., device='cuda:0')
episode: 206 training return: tensor(-999.9988, device='cuda:0')
episode: 207 training return: tensor(-1000., device='cuda:0')
epoch: 52 test_true_pfm: -0.0356471777048821 sim_pfm: -999.9981595079104
episode: 208 training return: tensor(-999.9969, device='cuda:0')
episode: 209 training return: tensor(-1000., device='cuda:0')
episode: 210 training return: tensor(-1000., device='cuda:0')
episode: 211 training return: tensor(-1000., device='cuda:0')
epoch: 53 test_true_pfm: 0.09724627857892915 sim_pfm: -999.9982196887335
episode: 212 training return: tensor(-999.9996, device='cuda:0')
episode: 213 training return: tensor(-999.9990, device='cuda:0')
episode: 214 training return: tensor(-999.9947, device='cuda:0')
episode: 215 training return: tensor(-999.9996, device='cuda:0')
epoch: 54 test_true_pfm: 0.4647302996077407 sim_pfm: -999.9982186555862
episode: 216 training return: tensor(-1000., device='cuda:0')
episode: 217 training return: tensor(-1000., device='cuda:0')
episode: 218 training return: tensor(-1000., device='cuda:0')
episode: 219 training return: tensor(-1000., device='cuda:0')
epoch: 55 test_true_pfm: -0.13032334048682706 sim_pfm: -999.9981587926546
episode: 220 training return: tensor(-999.9999, device='cuda:0')
episode: 221 training return: tensor(-999.9972, device='cuda:0')
episode: 222 training return: tensor(-999.9982, device='cuda:0')
episode: 223 training return: tensor(-1000., device='cuda:0')
epoch: 56 test_true_pfm: -0.25875593686959536 sim_pfm: -999.9982133507729
episode: 224 training return: tensor(-999.9973, device='cuda:0')
episode: 225 training return: tensor(-1000., device='cuda:0')
episode: 226 training return: tensor(-1000., device='cuda:0')
episode: 227 training return: tensor(-1000., device='cuda:0')
epoch: 57 test_true_pfm: -0.48590996734675396 sim_pfm: -999.9982141256332
episode: 228 training return: tensor(-1000., device='cuda:0')
episode: 229 training return: tensor(-1000., device='cuda:0')
episode: 230 training return: tensor(-1000., device='cuda:0')
episode: 231 training return: tensor(-999.9993, device='cuda:0')
epoch: 58 test_true_pfm: 0.1029749338455005 sim_pfm: -999.9982169866562
episode: 232 training return: tensor(-999.9987, device='cuda:0')
episode: 233 training return: tensor(-1000., device='cuda:0')
episode: 234 training return: tensor(-999.9963, device='cuda:0')
episode: 235 training return: tensor(-999.9999, device='cuda:0')
epoch: 59 test_true_pfm: -0.25726718785659236 sim_pfm: -999.9982143243154
episode: 236 training return: tensor(-1000., device='cuda:0')
episode: 237 training return: tensor(-999.9999, device='cuda:0')
episode: 238 training return: tensor(-1000., device='cuda:0')
episode: 239 training return: tensor(-999.9974, device='cuda:0')
epoch: 60 test_true_pfm: -0.18062865816587284 sim_pfm: -999.9981536865234
episode: 240 training return: tensor(-999.9976, device='cuda:0')
episode: 241 training return: tensor(-1000., device='cuda:0')
episode: 242 training return: tensor(-1000., device='cuda:0')
episode: 243 training return: tensor(-999.9999, device='cuda:0')
epoch: 61 test_true_pfm: 0.3774745502444679 sim_pfm: -999.9982080459595
episode: 244 training return: tensor(-1000., device='cuda:0')
episode: 245 training return: tensor(-1000., device='cuda:0')
episode: 246 training return: tensor(-1000., device='cuda:0')
episode: 247 training return: tensor(-999.9973, device='cuda:0')
epoch: 62 test_true_pfm: 0.18620493373490818 sim_pfm: -999.9982098539671
episode: 248 training return: tensor(-999.9968, device='cuda:0')
episode: 249 training return: tensor(-1000., device='cuda:0')
episode: 250 training return: tensor(-999.9980, device='cuda:0')
episode: 251 training return: tensor(-999.9999, device='cuda:0')
epoch: 63 test_true_pfm: -0.2038917966371648 sim_pfm: -999.9982136090597
episode: 252 training return: tensor(-1000., device='cuda:0')
episode: 253 training return: tensor(-999.9998, device='cuda:0')
episode: 254 training return: tensor(-1000., device='cuda:0')
episode: 255 training return: tensor(-999.9982, device='cuda:0')
epoch: 64 test_true_pfm: -0.637236080592139 sim_pfm: -999.9981541236242
episode: 256 training return: tensor(-1000., device='cuda:0')
episode: 257 training return: tensor(-999.9995, device='cuda:0')
episode: 258 training return: tensor(-1000., device='cuda:0')
episode: 259 training return: tensor(-1000., device='cuda:0')
epoch: 65 test_true_pfm: -0.7988373466104249 sim_pfm: -999.9982180992762
episode: 260 training return: tensor(-1000., device='cuda:0')
episode: 261 training return: tensor(-999.9998, device='cuda:0')
episode: 262 training return: tensor(-999.9981, device='cuda:0')
episode: 263 training return: tensor(-999.9999, device='cuda:0')
epoch: 66 test_true_pfm: -0.7240571809048765 sim_pfm: -999.9981534481049
episode: 264 training return: tensor(-1000., device='cuda:0')
episode: 265 training return: tensor(-999.9976, device='cuda:0')
episode: 266 training return: tensor(-1000., device='cuda:0')
episode: 267 training return: tensor(-1000., device='cuda:0')
epoch: 67 test_true_pfm: -0.8410285384733595 sim_pfm: -999.9982180198034
episode: 268 training return: tensor(-999.9999, device='cuda:0')
episode: 269 training return: tensor(-1000., device='cuda:0')
episode: 270 training return: tensor(-1000., device='cuda:0')
episode: 271 training return: tensor(-999.9998, device='cuda:0')
epoch: 68 test_true_pfm: -0.8174525549345244 sim_pfm: -999.998215576013
episode: 272 training return: tensor(-1000., device='cuda:0')
episode: 273 training return: tensor(-999.9998, device='cuda:0')
episode: 274 training return: tensor(-999.9991, device='cuda:0')
episode: 275 training return: tensor(-999.9999, device='cuda:0')
epoch: 69 test_true_pfm: 0.5261278270083324 sim_pfm: -999.9982154170672
episode: 276 training return: tensor(-999.9975, device='cuda:0')
episode: 277 training return: tensor(-999.9999, device='cuda:0')
episode: 278 training return: tensor(-1000., device='cuda:0')
episode: 279 training return: tensor(-999.9999, device='cuda:0')
epoch: 70 test_true_pfm: 0.3559681988724086 sim_pfm: -999.9981582363447
episode: 280 training return: tensor(-1000., device='cuda:0')
episode: 281 training return: tensor(-999.9976, device='cuda:0')
episode: 282 training return: tensor(-999.9942, device='cuda:0')
episode: 283 training return: tensor(-999.9977, device='cuda:0')
epoch: 71 test_true_pfm: -0.09487882247932038 sim_pfm: -999.9981551170349
episode: 284 training return: tensor(-999.9999, device='cuda:0')
episode: 285 training return: tensor(-999.9998, device='cuda:0')
episode: 286 training return: tensor(-999.9977, device='cuda:0')
episode: 287 training return: tensor(-1000., device='cuda:0')
epoch: 72 test_true_pfm: -0.07000765342936426 sim_pfm: -999.9981553157171
episode: 288 training return: tensor(-999.9998, device='cuda:0')
episode: 289 training return: tensor(-999.9946, device='cuda:0')
episode: 290 training return: tensor(-1000., device='cuda:0')
episode: 291 training return: tensor(-1000., device='cuda:0')
epoch: 73 test_true_pfm: -1.6244980849488844 sim_pfm: -999.9982162714005
episode: 292 training return: tensor(-999.9997, device='cuda:0')
episode: 293 training return: tensor(-1000., device='cuda:0')
episode: 294 training return: tensor(-1000., device='cuda:0')
episode: 295 training return: tensor(-999.9974, device='cuda:0')
epoch: 74 test_true_pfm: -0.6783670786158917 sim_pfm: -999.998219092687
episode: 296 training return: tensor(-999.9995, device='cuda:0')
episode: 297 training return: tensor(-1000., device='cuda:0')
episode: 298 training return: tensor(-999.9998, device='cuda:0')
episode: 299 training return: tensor(-999.9973, device='cuda:0')
epoch: 75 test_true_pfm: -1.0705732780813104 sim_pfm: -999.9982161323229
episode: 300 training return: tensor(-1000., device='cuda:0')
episode: 301 training return: tensor(-999.9918, device='cuda:0')
episode: 302 training return: tensor(-999.9999, device='cuda:0')
episode: 303 training return: tensor(-1000., device='cuda:0')
epoch: 76 test_true_pfm: -0.5650424972673588 sim_pfm: -999.9981521964073
episode: 304 training return: tensor(-1000., device='cuda:0')
episode: 305 training return: tensor(-1000., device='cuda:0')
episode: 306 training return: tensor(-1000., device='cuda:0')
episode: 307 training return: tensor(-1000., device='cuda:0')
epoch: 77 test_true_pfm: -0.440311477232846 sim_pfm: -999.9982113440832
episode: 308 training return: tensor(-999.9999, device='cuda:0')
episode: 309 training return: tensor(-999.9998, device='cuda:0')
episode: 310 training return: tensor(-1000., device='cuda:0')
episode: 311 training return: tensor(-999.9993, device='cuda:0')
epoch: 78 test_true_pfm: -0.8406659016359693 sim_pfm: -999.9982159137726
episode: 312 training return: tensor(-999.9999, device='cuda:0')
episode: 313 training return: tensor(-999.9999, device='cuda:0')
episode: 314 training return: tensor(-1000., device='cuda:0')
episode: 315 training return: tensor(-999.9993, device='cuda:0')
epoch: 79 test_true_pfm: 0.21489487713210273 sim_pfm: -999.9980972409248
episode: 316 training return: tensor(-999.9908, device='cuda:0')
episode: 317 training return: tensor(-999.9991, device='cuda:0')
episode: 318 training return: tensor(-999.9998, device='cuda:0')
episode: 319 training return: tensor(-999.9981, device='cuda:0')
epoch: 80 test_true_pfm: -0.3256099987317116 sim_pfm: -999.9981510837873
episode: 320 training return: tensor(-999.9971, device='cuda:0')
episode: 321 training return: tensor(-1000., device='cuda:0')
episode: 322 training return: tensor(-999.9974, device='cuda:0')
episode: 323 training return: tensor(-999.9982, device='cuda:0')
epoch: 81 test_true_pfm: -0.3143877793381492 sim_pfm: -999.9982138872147
episode: 324 training return: tensor(-1000., device='cuda:0')
episode: 325 training return: tensor(-1000., device='cuda:0')
episode: 326 training return: tensor(-1000., device='cuda:0')
episode: 327 training return: tensor(-999.9999, device='cuda:0')
epoch: 82 test_true_pfm: -0.7910887799690837 sim_pfm: -999.9982158939043
episode: 328 training return: tensor(-1000., device='cuda:0')
episode: 329 training return: tensor(-1000., device='cuda:0')
episode: 330 training return: tensor(-999.9954, device='cuda:0')
episode: 331 training return: tensor(-1000., device='cuda:0')
epoch: 83 test_true_pfm: -0.06748302094930547 sim_pfm: -999.9981508851051
episode: 332 training return: tensor(-999.9993, device='cuda:0')
episode: 333 training return: tensor(-999.9977, device='cuda:0')
episode: 334 training return: tensor(-1000., device='cuda:0')
episode: 335 training return: tensor(-999.9999, device='cuda:0')
epoch: 84 test_true_pfm: -0.7795847269594193 sim_pfm: -999.9981544415156
episode: 336 training return: tensor(-1000., device='cuda:0')
episode: 337 training return: tensor(-1000., device='cuda:0')
episode: 338 training return: tensor(-1000., device='cuda:0')
episode: 339 training return: tensor(-1000., device='cuda:0')
epoch: 85 test_true_pfm: -0.276858025875723 sim_pfm: -999.9982171853384
episode: 340 training return: tensor(-1000., device='cuda:0')
episode: 341 training return: tensor(-1000., device='cuda:0')
episode: 342 training return: tensor(-999.9969, device='cuda:0')
episode: 343 training return: tensor(-999.9979, device='cuda:0')
epoch: 86 test_true_pfm: -0.13681981211959862 sim_pfm: -999.9981513818105
episode: 344 training return: tensor(-999.9991, device='cuda:0')
episode: 345 training return: tensor(-1000., device='cuda:0')
episode: 346 training return: tensor(-999.9999, device='cuda:0')
episode: 347 training return: tensor(-1000., device='cuda:0')
epoch: 87 test_true_pfm: -0.3068904263515704 sim_pfm: -999.9982739885648
episode: 348 training return: tensor(-1000., device='cuda:0')
episode: 349 training return: tensor(-999.9999, device='cuda:0')
episode: 350 training return: tensor(-999.9987, device='cuda:0')
episode: 351 training return: tensor(-999.9998, device='cuda:0')
epoch: 88 test_true_pfm: -0.21316369494605916 sim_pfm: -999.9982163111368
episode: 352 training return: tensor(-999.9999, device='cuda:0')
episode: 353 training return: tensor(-1000., device='cuda:0')
episode: 354 training return: tensor(-999.9994, device='cuda:0')
episode: 355 training return: tensor(-1000., device='cuda:0')
epoch: 89 test_true_pfm: -0.5093993627219867 sim_pfm: -999.998155216376
episode: 356 training return: tensor(-999.9978, device='cuda:0')
episode: 357 training return: tensor(-999.9969, device='cuda:0')
episode: 358 training return: tensor(-1000., device='cuda:0')
episode: 359 training return: tensor(-1000., device='cuda:0')
epoch: 90 test_true_pfm: -0.9955295516148991 sim_pfm: -999.9980995059013
episode: 360 training return: tensor(-1000., device='cuda:0')
episode: 361 training return: tensor(-1000., device='cuda:0')
episode: 362 training return: tensor(-999.9993, device='cuda:0')
episode: 363 training return: tensor(-999.9999, device='cuda:0')
epoch: 91 test_true_pfm: -0.9118616040996605 sim_pfm: -999.9982180992762
episode: 364 training return: tensor(-1000., device='cuda:0')
episode: 365 training return: tensor(-999.9973, device='cuda:0')
episode: 366 training return: tensor(-1000., device='cuda:0')
episode: 367 training return: tensor(-1000., device='cuda:0')
epoch: 92 test_true_pfm: 0.6312564276800275 sim_pfm: -999.9982148011526
episode: 368 training return: tensor(-1000., device='cuda:0')
episode: 369 training return: tensor(-999.9984, device='cuda:0')
episode: 370 training return: tensor(-999.9970, device='cuda:0')
episode: 371 training return: tensor(-999.9993, device='cuda:0')
epoch: 93 test_true_pfm: -0.4922945740303326 sim_pfm: -999.9982154170672
episode: 372 training return: tensor(-1000., device='cuda:0')
episode: 373 training return: tensor(-1000., device='cuda:0')
episode: 374 training return: tensor(-999.9974, device='cuda:0')
episode: 375 training return: tensor(-999.9999, device='cuda:0')
epoch: 94 test_true_pfm: -1.8057073561659582 sim_pfm: -999.9982196092606
episode: 376 training return: tensor(-999.9975, device='cuda:0')
episode: 377 training return: tensor(-999.9991, device='cuda:0')
episode: 378 training return: tensor(-999.9955, device='cuda:0')
episode: 379 training return: tensor(-999.9966, device='cuda:0')
epoch: 95 test_true_pfm: -0.29625407027781636 sim_pfm: -999.998093187809
episode: 380 training return: tensor(-1000., device='cuda:0')
episode: 381 training return: tensor(-1000., device='cuda:0')
episode: 382 training return: tensor(-999.9980, device='cuda:0')
episode: 383 training return: tensor(-1000., device='cuda:0')
epoch: 96 test_true_pfm: -0.5259644038950401 sim_pfm: -999.9982753992081
episode: 384 training return: tensor(-999.9997, device='cuda:0')
episode: 385 training return: tensor(-1000., device='cuda:0')
episode: 386 training return: tensor(-999.9964, device='cuda:0')
episode: 387 training return: tensor(-1000., device='cuda:0')
epoch: 97 test_true_pfm: -0.24764185849390738 sim_pfm: -999.998274564743
episode: 388 training return: tensor(-999.9990, device='cuda:0')
episode: 389 training return: tensor(-1000., device='cuda:0')
episode: 390 training return: tensor(-1000., device='cuda:0')
episode: 391 training return: tensor(-999.9951, device='cuda:0')
epoch: 98 test_true_pfm: -0.24140682704082353 sim_pfm: -999.9980962077776
episode: 392 training return: tensor(-999.9940, device='cuda:0')
episode: 393 training return: tensor(-999.9993, device='cuda:0')
episode: 394 training return: tensor(-1000., device='cuda:0')
episode: 395 training return: tensor(-1000., device='cuda:0')
epoch: 99 test_true_pfm: -0.46548719013315343 sim_pfm: -999.9982177416483
episode: 396 training return: tensor(-1000., device='cuda:0')
episode: 397 training return: tensor(-1000., device='cuda:0')
episode: 398 training return: tensor(-1000., device='cuda:0')
episode: 399 training return: tensor(-1000., device='cuda:0')
epoch: 100 test_true_pfm: -0.8981418338335959 sim_pfm: -999.9981520573298
episode: 400 training return: tensor(-1000., device='cuda:0')
episode: 401 training return: tensor(-1000., device='cuda:0')
episode: 402 training return: tensor(-1000., device='cuda:0')
episode: 403 training return: tensor(-999.9999, device='cuda:0')
epoch: 101 test_true_pfm: 0.3832301598637997 sim_pfm: -999.9981589516004
episode: 404 training return: tensor(-999.9971, device='cuda:0')
episode: 405 training return: tensor(-999.9989, device='cuda:0')
episode: 406 training return: tensor(-999.9971, device='cuda:0')
episode: 407 training return: tensor(-1000., device='cuda:0')
epoch: 102 test_true_pfm: -0.20175195079778038 sim_pfm: -999.9982684453329
episode: 408 training return: tensor(-1000., device='cuda:0')
episode: 409 training return: tensor(-999.9999, device='cuda:0')
episode: 410 training return: tensor(-1000., device='cuda:0')
episode: 411 training return: tensor(-999.9999, device='cuda:0')
epoch: 103 test_true_pfm: -0.7364084877846526 sim_pfm: -999.9982219735781
episode: 412 training return: tensor(-1000., device='cuda:0')
episode: 413 training return: tensor(-999.9996, device='cuda:0')
episode: 414 training return: tensor(-999.9969, device='cuda:0')
episode: 415 training return: tensor(-999.9990, device='cuda:0')
epoch: 104 test_true_pfm: -0.9163928685630712 sim_pfm: -999.998219927152
episode: 416 training return: tensor(-1000., device='cuda:0')
episode: 417 training return: tensor(-999.9998, device='cuda:0')
episode: 418 training return: tensor(-999.9981, device='cuda:0')
episode: 419 training return: tensor(-1000., device='cuda:0')
epoch: 105 test_true_pfm: 0.4966157598067719 sim_pfm: -999.9981596271197
episode: 420 training return: tensor(-999.9999, device='cuda:0')
episode: 421 training return: tensor(-999.9998, device='cuda:0')
episode: 422 training return: tensor(-1000., device='cuda:0')
episode: 423 training return: tensor(-999.9974, device='cuda:0')
epoch: 106 test_true_pfm: -0.43291623245759014 sim_pfm: -999.9980908632278
episode: 424 training return: tensor(-1000., device='cuda:0')
episode: 425 training return: tensor(-1000., device='cuda:0')
episode: 426 training return: tensor(-1000., device='cuda:0')
episode: 427 training return: tensor(-1000., device='cuda:0')
epoch: 107 test_true_pfm: -0.20003278019029244 sim_pfm: -999.9981589118639
episode: 428 training return: tensor(-1000., device='cuda:0')
episode: 429 training return: tensor(-1000., device='cuda:0')
episode: 430 training return: tensor(-999.9999, device='cuda:0')
episode: 431 training return: tensor(-999.9999, device='cuda:0')
epoch: 108 test_true_pfm: -0.39146421531502246 sim_pfm: -999.9982149799665
episode: 432 training return: tensor(-999.9999, device='cuda:0')
episode: 433 training return: tensor(-999.9999, device='cuda:0')
episode: 434 training return: tensor(-999.9999, device='cuda:0')
episode: 435 training return: tensor(-999.9925, device='cuda:0')
epoch: 109 test_true_pfm: -0.5863184188909513 sim_pfm: -999.9982188542684
episode: 436 training return: tensor(-999.9991, device='cuda:0')
episode: 437 training return: tensor(-1000., device='cuda:0')
episode: 438 training return: tensor(-1000., device='cuda:0')
episode: 439 training return: tensor(-1000., device='cuda:0')
epoch: 110 test_true_pfm: -0.30312792378084674 sim_pfm: -999.9981500903765
episode: 440 training return: tensor(-999.9982, device='cuda:0')
episode: 441 training return: tensor(-999.9969, device='cuda:0')
episode: 442 training return: tensor(-999.9999, device='cuda:0')
episode: 443 training return: tensor(-1000., device='cuda:0')
epoch: 111 test_true_pfm: -0.7255582488243175 sim_pfm: -999.99821494023
episode: 444 training return: tensor(-999.9998, device='cuda:0')
episode: 445 training return: tensor(-1000., device='cuda:0')
episode: 446 training return: tensor(-999.9996, device='cuda:0')
episode: 447 training return: tensor(-1000., device='cuda:0')
epoch: 112 test_true_pfm: -0.5655259036594128 sim_pfm: -999.9982762734095
episode: 448 training return: tensor(-1000., device='cuda:0')
episode: 449 training return: tensor(-999.9943, device='cuda:0')
episode: 450 training return: tensor(-999.9993, device='cuda:0')
episode: 451 training return: tensor(-999.9999, device='cuda:0')
epoch: 113 test_true_pfm: 0.3579695784719856 sim_pfm: -999.9981478850046
episode: 452 training return: tensor(-1000., device='cuda:0')
episode: 453 training return: tensor(-1000., device='cuda:0')
episode: 454 training return: tensor(-999.9983, device='cuda:0')
episode: 455 training return: tensor(-999.9999, device='cuda:0')
epoch: 114 test_true_pfm: -0.6319537858995369 sim_pfm: -999.9981557925543
episode: 456 training return: tensor(-999.9980, device='cuda:0')
episode: 457 training return: tensor(-1000., device='cuda:0')
episode: 458 training return: tensor(-999.9975, device='cuda:0')
episode: 459 training return: tensor(-1000., device='cuda:0')
epoch: 115 test_true_pfm: -1.5568886552810266 sim_pfm: -999.9982166488966
episode: 460 training return: tensor(-1000., device='cuda:0')
episode: 461 training return: tensor(-1000., device='cuda:0')
episode: 462 training return: tensor(-1000., device='cuda:0')
episode: 463 training return: tensor(-999.9995, device='cuda:0')
epoch: 116 test_true_pfm: -0.34383865696786303 sim_pfm: -999.9981480042139
episode: 464 training return: tensor(-1000., device='cuda:0')
episode: 465 training return: tensor(-999.9984, device='cuda:0')
episode: 466 training return: tensor(-999.9983, device='cuda:0')
episode: 467 training return: tensor(-999.9987, device='cuda:0')
epoch: 117 test_true_pfm: 0.7450204788240464 sim_pfm: -999.9982144435247
episode: 468 training return: tensor(-999.9940, device='cuda:0')
episode: 469 training return: tensor(-999.9951, device='cuda:0')
episode: 470 training return: tensor(-999.9910, device='cuda:0')
episode: 471 training return: tensor(-999.9965, device='cuda:0')
epoch: 118 test_true_pfm: -0.8330040131036038 sim_pfm: -999.9982129732767
episode: 472 training return: tensor(-999.9987, device='cuda:0')
episode: 473 training return: tensor(-1000., device='cuda:0')
episode: 474 training return: tensor(-999.9995, device='cuda:0')
episode: 475 training return: tensor(-999.9993, device='cuda:0')
epoch: 119 test_true_pfm: 0.06575458674208641 sim_pfm: -999.9981500307719
episode: 476 training return: tensor(-1000., device='cuda:0')
episode: 477 training return: tensor(-999.9994, device='cuda:0')
episode: 478 training return: tensor(-1000., device='cuda:0')
episode: 479 training return: tensor(-1000., device='cuda:0')
epoch: 120 test_true_pfm: 0.10127924761726292 sim_pfm: -999.9982173244158
episode: 480 training return: tensor(-1000., device='cuda:0')
episode: 481 training return: tensor(-999.9968, device='cuda:0')
episode: 482 training return: tensor(-999.9999, device='cuda:0')
episode: 483 training return: tensor(-1000., device='cuda:0')
epoch: 121 test_true_pfm: -0.17730853532377536 sim_pfm: -999.9981615344683
episode: 484 training return: tensor(-1000., device='cuda:0')
episode: 485 training return: tensor(-999.9991, device='cuda:0')
episode: 486 training return: tensor(-1000., device='cuda:0')
episode: 487 training return: tensor(-999.9999, device='cuda:0')
epoch: 122 test_true_pfm: 0.025268971340728513 sim_pfm: -999.9982161521912
episode: 488 training return: tensor(-999.9953, device='cuda:0')
episode: 489 training return: tensor(-999.9992, device='cuda:0')
episode: 490 training return: tensor(-1000., device='cuda:0')
episode: 491 training return: tensor(-999.9996, device='cuda:0')
epoch: 123 test_true_pfm: -0.12395436635325645 sim_pfm: -999.9982057611147
episode: 492 training return: tensor(-999.9954, device='cuda:0')
episode: 493 training return: tensor(-999.9985, device='cuda:0')
episode: 494 training return: tensor(-999.9999, device='cuda:0')
episode: 495 training return: tensor(-1000., device='cuda:0')
epoch: 124 test_true_pfm: -0.18146199543474814 sim_pfm: -999.9982767502466
episode: 496 training return: tensor(-1000., device='cuda:0')
episode: 497 training return: tensor(-999.9990, device='cuda:0')
episode: 498 training return: tensor(-1000., device='cuda:0')
episode: 499 training return: tensor(-1000., device='cuda:0')
epoch: 125 test_true_pfm: -0.1667277710463113 sim_pfm: -999.998270491759
episode: 500 training return: tensor(-999.9979, device='cuda:0')
episode: 501 training return: tensor(-1000., device='cuda:0')
episode: 502 training return: tensor(-1000., device='cuda:0')
episode: 503 training return: tensor(-1000., device='cuda:0')
epoch: 126 test_true_pfm: 0.15095920650755804 sim_pfm: -999.9982114831606
episode: 504 training return: tensor(-1000., device='cuda:0')
episode: 505 training return: tensor(-999.9987, device='cuda:0')
episode: 506 training return: tensor(-999.9964, device='cuda:0')
episode: 507 training return: tensor(-1000., device='cuda:0')
epoch: 127 test_true_pfm: 0.03267549020935336 sim_pfm: -999.9981536269188
episode: 508 training return: tensor(-999.9999, device='cuda:0')
episode: 509 training return: tensor(-1000., device='cuda:0')
episode: 510 training return: tensor(-1000., device='cuda:0')
episode: 511 training return: tensor(-999.9942, device='cuda:0')
epoch: 128 test_true_pfm: -0.41683539507198525 sim_pfm: -999.9982097347578
episode: 512 training return: tensor(-999.9990, device='cuda:0')
episode: 513 training return: tensor(-999.9988, device='cuda:0')
episode: 514 training return: tensor(-1000., device='cuda:0')
episode: 515 training return: tensor(-1000., device='cuda:0')
epoch: 129 test_true_pfm: 0.8103079907181208 sim_pfm: -999.9982114036878
episode: 516 training return: tensor(-999.9954, device='cuda:0')
episode: 517 training return: tensor(-1000., device='cuda:0')
episode: 518 training return: tensor(-1000., device='cuda:0')
episode: 519 training return: tensor(-1000., device='cuda:0')
epoch: 130 test_true_pfm: -0.3825200411406353 sim_pfm: -999.9982194503149
episode: 520 training return: tensor(-999.9999, device='cuda:0')
episode: 521 training return: tensor(-999.9988, device='cuda:0')
episode: 522 training return: tensor(-1000., device='cuda:0')
episode: 523 training return: tensor(-999.9971, device='cuda:0')
epoch: 131 test_true_pfm: -0.5254406398894355 sim_pfm: -999.9981532295545
episode: 524 training return: tensor(-1000., device='cuda:0')
episode: 525 training return: tensor(-999.9948, device='cuda:0')
episode: 526 training return: tensor(-1000., device='cuda:0')
episode: 527 training return: tensor(-999.9999, device='cuda:0')
epoch: 132 test_true_pfm: -0.7098288662425213 sim_pfm: -999.9982178409895
episode: 528 training return: tensor(-1000., device='cuda:0')
episode: 529 training return: tensor(-999.9999, device='cuda:0')
episode: 530 training return: tensor(-1000., device='cuda:0')
episode: 531 training return: tensor(-1000., device='cuda:0')
epoch: 133 test_true_pfm: -0.8269862936209664 sim_pfm: -999.9982157548269
episode: 532 training return: tensor(-999.9996, device='cuda:0')
episode: 533 training return: tensor(-1000., device='cuda:0')
episode: 534 training return: tensor(-999.9971, device='cuda:0')
episode: 535 training return: tensor(-1000., device='cuda:0')
epoch: 134 test_true_pfm: -0.9753567832345151 sim_pfm: -999.9982187151909
episode: 536 training return: tensor(-999.9991, device='cuda:0')
episode: 537 training return: tensor(-1000., device='cuda:0')
episode: 538 training return: tensor(-999.9949, device='cuda:0')
episode: 539 training return: tensor(-999.9999, device='cuda:0')
epoch: 135 test_true_pfm: 0.17548414951433725 sim_pfm: -999.9982161124548
episode: 540 training return: tensor(-999.9979, device='cuda:0')
episode: 541 training return: tensor(-999.9955, device='cuda:0')
episode: 542 training return: tensor(-1000., device='cuda:0')
episode: 543 training return: tensor(-1000., device='cuda:0')
epoch: 136 test_true_pfm: 0.12092397681756391 sim_pfm: -999.9982174833616
episode: 544 training return: tensor(-999.9959, device='cuda:0')
episode: 545 training return: tensor(-1000., device='cuda:0')
episode: 546 training return: tensor(-999.9969, device='cuda:0')
episode: 547 training return: tensor(-1000., device='cuda:0')
epoch: 137 test_true_pfm: -0.541630380666145 sim_pfm: -999.9982192317644
episode: 548 training return: tensor(-999.9988, device='cuda:0')
episode: 549 training return: tensor(-999.9978, device='cuda:0')
episode: 550 training return: tensor(-1000., device='cuda:0')
episode: 551 training return: tensor(-1000., device='cuda:0')
epoch: 138 test_true_pfm: -0.3262487792725994 sim_pfm: -999.9981549978256
episode: 552 training return: tensor(-999.9994, device='cuda:0')
episode: 553 training return: tensor(-1000., device='cuda:0')
episode: 554 training return: tensor(-1000., device='cuda:0')
episode: 555 training return: tensor(-999.9971, device='cuda:0')
epoch: 139 test_true_pfm: -0.1592728107391612 sim_pfm: -999.9982133507729
episode: 556 training return: tensor(-999.9999, device='cuda:0')
episode: 557 training return: tensor(-1000., device='cuda:0')
episode: 558 training return: tensor(-1000., device='cuda:0')
episode: 559 training return: tensor(-999.9999, device='cuda:0')
epoch: 140 test_true_pfm: -0.8739201496707155 sim_pfm: -999.9981535275778
episode: 560 training return: tensor(-999.9998, device='cuda:0')
episode: 561 training return: tensor(-1000., device='cuda:0')
episode: 562 training return: tensor(-1000., device='cuda:0')
episode: 563 training return: tensor(-999.9991, device='cuda:0')
epoch: 141 test_true_pfm: -0.4355468742143507 sim_pfm: -999.9982124368349
episode: 564 training return: tensor(-999.9991, device='cuda:0')
episode: 565 training return: tensor(-999.9999, device='cuda:0')
episode: 566 training return: tensor(-1000., device='cuda:0')
episode: 567 training return: tensor(-999.9996, device='cuda:0')
epoch: 142 test_true_pfm: -0.011516203683828496 sim_pfm: -999.9982164700826
episode: 568 training return: tensor(-1000., device='cuda:0')
episode: 569 training return: tensor(-999.9988, device='cuda:0')
episode: 570 training return: tensor(-999.9980, device='cuda:0')
episode: 571 training return: tensor(-999.9999, device='cuda:0')
epoch: 143 test_true_pfm: 0.020589177913543238 sim_pfm: -999.9981589913368
episode: 572 training return: tensor(-1000., device='cuda:0')
episode: 573 training return: tensor(-999.9999, device='cuda:0')
episode: 574 training return: tensor(-999.9973, device='cuda:0')
episode: 575 training return: tensor(-999.9993, device='cuda:0')
epoch: 144 test_true_pfm: 0.05153958096538943 sim_pfm: -999.9981516202291
episode: 576 training return: tensor(-999.9999, device='cuda:0')
episode: 577 training return: tensor(-999.9926, device='cuda:0')
episode: 578 training return: tensor(-1000., device='cuda:0')
episode: 579 training return: tensor(-1000., device='cuda:0')
epoch: 145 test_true_pfm: 0.1525846343729387 sim_pfm: -999.9982145229975
episode: 580 training return: tensor(-999.9957, device='cuda:0')
episode: 581 training return: tensor(-1000., device='cuda:0')
episode: 582 training return: tensor(-999.9977, device='cuda:0')
episode: 583 training return: tensor(-999.9999, device='cuda:0')
epoch: 146 test_true_pfm: -0.11548099833130893 sim_pfm: -999.998150507609
episode: 584 training return: tensor(-999.9986, device='cuda:0')
episode: 585 training return: tensor(-999.9994, device='cuda:0')
episode: 586 training return: tensor(-1000., device='cuda:0')
episode: 587 training return: tensor(-999.9993, device='cuda:0')
epoch: 147 test_true_pfm: 0.020469588245087822 sim_pfm: -999.9981580972672
episode: 588 training return: tensor(-999.9999, device='cuda:0')
episode: 589 training return: tensor(-1000., device='cuda:0')
episode: 590 training return: tensor(-1000., device='cuda:0')
episode: 591 training return: tensor(-1000., device='cuda:0')
epoch: 148 test_true_pfm: -0.5582474866308051 sim_pfm: -999.9981554547945
episode: 592 training return: tensor(-1000., device='cuda:0')
episode: 593 training return: tensor(-999.9996, device='cuda:0')
episode: 594 training return: tensor(-999.9993, device='cuda:0')
episode: 595 training return: tensor(-999.9985, device='cuda:0')
epoch: 149 test_true_pfm: 0.002008420823052748 sim_pfm: -999.9981569846472
episode: 596 training return: tensor(-999.9999, device='cuda:0')
episode: 597 training return: tensor(-1000., device='cuda:0')
episode: 598 training return: tensor(-999.9885, device='cuda:0')
episode: 599 training return: tensor(-999.9981, device='cuda:0')
epoch: 150 test_true_pfm: -0.6815343432715076 sim_pfm: -999.9982192516327
