['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'baseline', '--traj', 'expert', '--seed', '3']
episode: 0 training return: tensor(-999.9999, device='cuda:0')
episode: 1 training return: tensor(-999.9999, device='cuda:0')
episode: 2 training return: tensor(-999.9992, device='cuda:0')
episode: 3 training return: tensor(-999.9997, device='cuda:0')
epoch: 1 test_true_pfm: 0.0013931396955008484 sim_pfm: -999.9010509053866
episode: 4 training return: tensor(-999.9987, device='cuda:0')
episode: 5 training return: tensor(-999.9997, device='cuda:0')
episode: 6 training return: tensor(-999.9995, device='cuda:0')
episode: 7 training return: tensor(-999.9992, device='cuda:0')
epoch: 2 test_true_pfm: -0.40574233903046864 sim_pfm: -999.9013234178225
episode: 8 training return: tensor(-999.9996, device='cuda:0')
episode: 9 training return: tensor(-999.9999, device='cuda:0')
episode: 10 training return: tensor(-999.9998, device='cuda:0')
episode: 11 training return: tensor(-999.9997, device='cuda:0')
epoch: 3 test_true_pfm: -1.1390241076534096 sim_pfm: -999.9019348025322
episode: 12 training return: tensor(-999.9999, device='cuda:0')
episode: 13 training return: tensor(-1000., device='cuda:0')
episode: 14 training return: tensor(-999.9998, device='cuda:0')
episode: 15 training return: tensor(-999.9998, device='cuda:0')
epoch: 4 test_true_pfm: -0.6676975270314646 sim_pfm: -999.9000892043114
episode: 16 training return: tensor(-999.9998, device='cuda:0')
episode: 17 training return: tensor(-999.9997, device='cuda:0')
episode: 18 training return: tensor(-999.9999, device='cuda:0')
episode: 19 training return: tensor(-999.9999, device='cuda:0')
epoch: 5 test_true_pfm: 0.21511386729958967 sim_pfm: -999.9022545814514
episode: 20 training return: tensor(-999.9999, device='cuda:0')
episode: 21 training return: tensor(-999.9998, device='cuda:0')
episode: 22 training return: tensor(-999.9999, device='cuda:0')
episode: 23 training return: tensor(-999.9998, device='cuda:0')
epoch: 6 test_true_pfm: -0.3901334631918502 sim_pfm: -999.9015452663103
episode: 24 training return: tensor(-1000., device='cuda:0')
episode: 25 training return: tensor(-999.9998, device='cuda:0')
episode: 26 training return: tensor(-999.9992, device='cuda:0')
episode: 27 training return: tensor(-999.9997, device='cuda:0')
epoch: 7 test_true_pfm: 0.03860223882608649 sim_pfm: -999.9012611707052
episode: 28 training return: tensor(-999.9997, device='cuda:0')
episode: 29 training return: tensor(-1000., device='cuda:0')
episode: 30 training return: tensor(-999.9998, device='cuda:0')
episode: 31 training return: tensor(-999.9999, device='cuda:0')
epoch: 8 test_true_pfm: -0.5029356548136007 sim_pfm: -999.9020041028658
episode: 32 training return: tensor(-999.9999, device='cuda:0')
episode: 33 training return: tensor(-999.9999, device='cuda:0')
episode: 34 training return: tensor(-999.9999, device='cuda:0')
episode: 35 training return: tensor(-999.9999, device='cuda:0')
epoch: 9 test_true_pfm: 0.07063767262808326 sim_pfm: -999.9002317587534
episode: 36 training return: tensor(-999.9998, device='cuda:0')
episode: 37 training return: tensor(-999.9999, device='cuda:0')
episode: 38 training return: tensor(-999.9999, device='cuda:0')
episode: 39 training return: tensor(-999.9999, device='cuda:0')
epoch: 10 test_true_pfm: -0.04881440934183449 sim_pfm: -999.9015925327936
episode: 40 training return: tensor(-999.9998, device='cuda:0')
episode: 41 training return: tensor(-999.9999, device='cuda:0')
episode: 42 training return: tensor(-999.9998, device='cuda:0')
episode: 43 training return: tensor(-999.9995, device='cuda:0')
epoch: 11 test_true_pfm: -0.22403191021331512 sim_pfm: -999.90104530255
episode: 44 training return: tensor(-999.9998, device='cuda:0')
episode: 45 training return: tensor(-999.9998, device='cuda:0')
episode: 46 training return: tensor(-999.9980, device='cuda:0')
episode: 47 training return: tensor(-999.9999, device='cuda:0')
epoch: 12 test_true_pfm: -0.3138091006436778 sim_pfm: -999.901847978433
episode: 48 training return: tensor(-999.9998, device='cuda:0')
episode: 49 training return: tensor(-999.9996, device='cuda:0')
episode: 50 training return: tensor(-999.9999, device='cuda:0')
episode: 51 training return: tensor(-999.9998, device='cuda:0')
epoch: 13 test_true_pfm: -1.1187081878426361 sim_pfm: -999.900766213735
episode: 52 training return: tensor(-999.9999, device='cuda:0')
episode: 53 training return: tensor(-999.9999, device='cuda:0')
episode: 54 training return: tensor(-999.9997, device='cuda:0')
episode: 55 training return: tensor(-999.9999, device='cuda:0')
epoch: 14 test_true_pfm: -0.6984164116135636 sim_pfm: -999.9010866085688
episode: 56 training return: tensor(-999.9999, 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(-999.9999, device='cuda:0')
epoch: 15 test_true_pfm: -0.5092178542540653 sim_pfm: -999.901881714662
episode: 60 training return: tensor(-999.9998, device='cuda:0')
episode: 61 training return: tensor(-999.9998, device='cuda:0')
episode: 62 training return: tensor(-999.9999, device='cuda:0')
episode: 63 training return: tensor(-999.9997, device='cuda:0')
epoch: 16 test_true_pfm: -0.06573741731524667 sim_pfm: -999.9000607132912
episode: 64 training return: tensor(-999.9996, device='cuda:0')
episode: 65 training return: tensor(-999.9999, device='cuda:0')
episode: 66 training return: tensor(-999.9998, device='cuda:0')
episode: 67 training return: tensor(-999.9965, device='cuda:0')
epoch: 17 test_true_pfm: -0.9165888883222834 sim_pfm: -999.9000461697578
episode: 68 training return: tensor(-999.9998, device='cuda:0')
episode: 69 training return: tensor(-999.9987, device='cuda:0')
episode: 70 training return: tensor(-999.9999, device='cuda:0')
episode: 71 training return: tensor(-1000., device='cuda:0')
epoch: 18 test_true_pfm: -0.2737419569752421 sim_pfm: -999.9009614189466
episode: 72 training return: tensor(-999.9999, device='cuda:0')
episode: 73 training return: tensor(-999.9998, device='cuda:0')
episode: 74 training return: tensor(-999.9999, device='cuda:0')
episode: 75 training return: tensor(-999.9999, device='cuda:0')
epoch: 19 test_true_pfm: -0.16840685203192493 sim_pfm: -999.9010513822237
episode: 76 training return: tensor(-999.9998, device='cuda:0')
episode: 77 training return: tensor(-999.9998, device='cuda:0')
episode: 78 training return: tensor(-999.9998, device='cuda:0')
episode: 79 training return: tensor(-999.9998, device='cuda:0')
epoch: 20 test_true_pfm: -0.3413242948752533 sim_pfm: -999.9016130963961
episode: 80 training return: tensor(-999.9999, device='cuda:0')
episode: 81 training return: tensor(-999.9999, device='cuda:0')
episode: 82 training return: tensor(-999.9997, device='cuda:0')
episode: 83 training return: tensor(-999.9999, device='cuda:0')
epoch: 21 test_true_pfm: 0.09963543448984667 sim_pfm: -999.9012926419576
episode: 84 training return: tensor(-1000., device='cuda:0')
episode: 85 training return: tensor(-999.9999, device='cuda:0')
episode: 86 training return: tensor(-999.9998, device='cuda:0')
episode: 87 training return: tensor(-999.9991, device='cuda:0')
epoch: 22 test_true_pfm: -0.6706305449289972 sim_pfm: -999.9017039736112
episode: 88 training return: tensor(-999.9999, device='cuda:0')
episode: 89 training return: tensor(-999.9998, device='cuda:0')
episode: 90 training return: tensor(-999.9991, device='cuda:0')
episode: 91 training return: tensor(-999.9998, device='cuda:0')
epoch: 23 test_true_pfm: 0.07537850944427808 sim_pfm: -999.9017506043116
episode: 92 training return: tensor(-999.9999, device='cuda:0')
episode: 93 training return: tensor(-999.9997, device='cuda:0')
episode: 94 training return: tensor(-999.9999, device='cuda:0')
episode: 95 training return: tensor(-999.9997, device='cuda:0')
epoch: 24 test_true_pfm: 0.46975020173232834 sim_pfm: -999.9012504220009
episode: 96 training return: tensor(-999.9999, device='cuda:0')
episode: 97 training return: tensor(-999.9999, device='cuda:0')
episode: 98 training return: tensor(-999.9999, device='cuda:0')
episode: 99 training return: tensor(-999.9978, device='cuda:0')
epoch: 25 test_true_pfm: -0.8339754136240969 sim_pfm: -999.9012757142385
episode: 100 training return: tensor(-999.9999, device='cuda:0')
episode: 101 training return: tensor(-999.9997, device='cuda:0')
episode: 102 training return: tensor(-999.9998, device='cuda:0')
episode: 103 training return: tensor(-999.9999, device='cuda:0')
epoch: 26 test_true_pfm: -0.047052102371908024 sim_pfm: -999.9007890423139
episode: 104 training return: tensor(-999.9998, device='cuda:0')
episode: 105 training return: tensor(-999.9999, device='cuda:0')
episode: 106 training return: tensor(-999.9997, device='cuda:0')
episode: 107 training return: tensor(-999.9999, device='cuda:0')
epoch: 27 test_true_pfm: 0.24479371354612645 sim_pfm: -999.900270541509
episode: 108 training return: tensor(-999.9996, device='cuda:0')
episode: 109 training return: tensor(-999.9999, device='cuda:0')
episode: 110 training return: tensor(-999.9993, device='cuda:0')
episode: 111 training return: tensor(-999.9998, device='cuda:0')
epoch: 28 test_true_pfm: -0.15124959406139496 sim_pfm: -999.9025627772013
episode: 112 training return: tensor(-999.9993, device='cuda:0')
episode: 113 training return: tensor(-999.9993, device='cuda:0')
episode: 114 training return: tensor(-999.9996, device='cuda:0')
episode: 115 training return: tensor(-999.9999, device='cuda:0')
epoch: 29 test_true_pfm: 0.0483862698595147 sim_pfm: -999.900244752566
episode: 116 training return: tensor(-999.9999, device='cuda:0')
episode: 117 training return: tensor(-999.9998, device='cuda:0')
episode: 118 training return: tensor(-999.9927, device='cuda:0')
episode: 119 training return: tensor(-999.9996, device='cuda:0')
epoch: 30 test_true_pfm: -0.4204488630062875 sim_pfm: -999.9014933904012
episode: 120 training return: tensor(-999.9998, device='cuda:0')
episode: 121 training return: tensor(-999.9999, device='cuda:0')
episode: 122 training return: tensor(-999.9999, device='cuda:0')
episode: 123 training return: tensor(-999.9996, device='cuda:0')
epoch: 31 test_true_pfm: 0.42803670045020564 sim_pfm: -999.9007919828097
episode: 124 training return: tensor(-1000., device='cuda:0')
episode: 125 training return: tensor(-999.9998, device='cuda:0')
episode: 126 training return: tensor(-999.9999, device='cuda:0')
episode: 127 training return: tensor(-999.9999, device='cuda:0')
epoch: 32 test_true_pfm: -0.31755851431880655 sim_pfm: -999.9022009571394
episode: 128 training return: tensor(-999.9999, device='cuda:0')
episode: 129 training return: tensor(-999.9991, device='cuda:0')
episode: 130 training return: tensor(-999.9986, device='cuda:0')
episode: 131 training return: tensor(-999.9999, device='cuda:0')
epoch: 33 test_true_pfm: 0.33397940306807566 sim_pfm: -999.901027003924
episode: 132 training return: tensor(-999.9995, device='cuda:0')
episode: 133 training return: tensor(-999.9999, device='cuda:0')
episode: 134 training return: tensor(-999.9998, device='cuda:0')
episode: 135 training return: tensor(-999.9996, device='cuda:0')
epoch: 34 test_true_pfm: -0.6256814866597039 sim_pfm: -999.9011949499449
episode: 136 training return: tensor(-999.9996, device='cuda:0')
episode: 137 training return: tensor(-999.9999, device='cuda:0')
episode: 138 training return: tensor(-999.9996, device='cuda:0')
episode: 139 training return: tensor(-999.9999, device='cuda:0')
epoch: 35 test_true_pfm: -0.42604182521086753 sim_pfm: -999.9019061724345
episode: 140 training return: tensor(-999.9999, device='cuda:0')
episode: 141 training return: tensor(-999.9997, device='cuda:0')
episode: 142 training return: tensor(-999.9999, device='cuda:0')
episode: 143 training return: tensor(-1000., device='cuda:0')
epoch: 36 test_true_pfm: -0.23969645521487382 sim_pfm: -999.901280005773
episode: 144 training return: tensor(-1000., device='cuda:0')
episode: 145 training return: tensor(-999.9998, device='cuda:0')
episode: 146 training return: tensor(-999.9998, device='cuda:0')
episode: 147 training return: tensor(-1000., device='cuda:0')
epoch: 37 test_true_pfm: -0.06097399347830124 sim_pfm: -999.9012563228607
episode: 148 training return: tensor(-999.9999, device='cuda:0')
episode: 149 training return: tensor(-1000., device='cuda:0')
episode: 150 training return: tensor(-999.9999, device='cuda:0')
episode: 151 training return: tensor(-999.9999, device='cuda:0')
epoch: 38 test_true_pfm: -0.3410071991796367 sim_pfm: -999.9009820421537
episode: 152 training return: tensor(-999.9996, device='cuda:0')
episode: 153 training return: tensor(-999.9996, device='cuda:0')
episode: 154 training return: tensor(-999.9998, device='cuda:0')
episode: 155 training return: tensor(-999.9995, device='cuda:0')
epoch: 39 test_true_pfm: 0.3225147253306545 sim_pfm: -999.8995848298073
episode: 156 training return: tensor(-999.9999, device='cuda:0')
episode: 157 training return: tensor(-999.9992, device='cuda:0')
episode: 158 training return: tensor(-999.9998, device='cuda:0')
episode: 159 training return: tensor(-999.9998, device='cuda:0')
epoch: 40 test_true_pfm: -0.6086229198801473 sim_pfm: -999.9007876316706
episode: 160 training return: tensor(-999.9998, device='cuda:0')
episode: 161 training return: tensor(-999.9998, device='cuda:0')
episode: 162 training return: tensor(-999.9998, device='cuda:0')
episode: 163 training return: tensor(-999.9996, device='cuda:0')
epoch: 41 test_true_pfm: -0.5866916541774206 sim_pfm: -999.9023446440697
episode: 164 training return: tensor(-999.9998, device='cuda:0')
episode: 165 training return: tensor(-999.9999, device='cuda:0')
episode: 166 training return: tensor(-999.9986, device='cuda:0')
episode: 167 training return: tensor(-999.9999, device='cuda:0')
epoch: 42 test_true_pfm: -0.04821850589072663 sim_pfm: -999.901493648688
episode: 168 training return: tensor(-999.9997, device='cuda:0')
episode: 169 training return: tensor(-999.9998, device='cuda:0')
episode: 170 training return: tensor(-999.9696, device='cuda:0')
episode: 171 training return: tensor(-999.9999, device='cuda:0')
epoch: 43 test_true_pfm: -0.3190157221213283 sim_pfm: -999.9021308024725
episode: 172 training return: tensor(-999.9999, device='cuda:0')
episode: 173 training return: tensor(-999.9998, device='cuda:0')
episode: 174 training return: tensor(-999.9997, device='cuda:0')
episode: 175 training return: tensor(-999.9999, device='cuda:0')
epoch: 44 test_true_pfm: -0.675185801005588 sim_pfm: -999.901510477066
episode: 176 training return: tensor(-1000., device='cuda:0')
episode: 177 training return: tensor(-999.9999, device='cuda:0')
episode: 178 training return: tensor(-999.9995, device='cuda:0')
episode: 179 training return: tensor(-999.9998, device='cuda:0')
epoch: 45 test_true_pfm: -0.1156207530348465 sim_pfm: -999.9008547862371
episode: 180 training return: tensor(-999.9996, device='cuda:0')
episode: 181 training return: tensor(-999.9997, device='cuda:0')
episode: 182 training return: tensor(-999.9996, device='cuda:0')
episode: 183 training return: tensor(-999.9999, device='cuda:0')
epoch: 46 test_true_pfm: 0.06925904288091046 sim_pfm: -999.9016086061796
episode: 184 training return: tensor(-999.9998, device='cuda:0')
episode: 185 training return: tensor(-999.9998, device='cuda:0')
episode: 186 training return: tensor(-999.9998, device='cuda:0')
episode: 187 training return: tensor(-999.9997, device='cuda:0')
epoch: 47 test_true_pfm: 0.7634597955526795 sim_pfm: -999.9018657604853
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(-999.9999, device='cuda:0')
episode: 191 training return: tensor(-999.9996, device='cuda:0')
epoch: 48 test_true_pfm: -0.11358429047943587 sim_pfm: -999.9016836682955
episode: 192 training return: tensor(-999.9985, device='cuda:0')
episode: 193 training return: tensor(-999.9996, device='cuda:0')
episode: 194 training return: tensor(-999.9996, device='cuda:0')
episode: 195 training return: tensor(-999.9998, device='cuda:0')
epoch: 49 test_true_pfm: -0.5393483093032256 sim_pfm: -999.9004874825478
episode: 196 training return: tensor(-999.9999, device='cuda:0')
episode: 197 training return: tensor(-999.9999, device='cuda:0')
episode: 198 training return: tensor(-999.9998, device='cuda:0')
episode: 199 training return: tensor(-999.9999, device='cuda:0')
epoch: 50 test_true_pfm: -0.8580304598845759 sim_pfm: -999.9001437226931
episode: 200 training return: tensor(-999.9999, device='cuda:0')
episode: 201 training return: tensor(-999.9993, device='cuda:0')
episode: 202 training return: tensor(-1000., device='cuda:0')
episode: 203 training return: tensor(-1000., device='cuda:0')
epoch: 51 test_true_pfm: -0.31209884924416237 sim_pfm: -999.9023952682813
episode: 204 training return: tensor(-999.9998, device='cuda:0')
episode: 205 training return: tensor(-999.9999, device='cuda:0')
episode: 206 training return: tensor(-1000., device='cuda:0')
episode: 207 training return: tensor(-999.9997, device='cuda:0')
epoch: 52 test_true_pfm: -0.5234340529525956 sim_pfm: -999.9003147482872
episode: 208 training return: tensor(-999.9999, device='cuda:0')
episode: 209 training return: tensor(-999.9997, device='cuda:0')
episode: 210 training return: tensor(-999.9998, device='cuda:0')
episode: 211 training return: tensor(-999.9998, device='cuda:0')
epoch: 53 test_true_pfm: -0.6963305715584011 sim_pfm: -999.9019880692164
episode: 212 training return: tensor(-999.9999, device='cuda:0')
episode: 213 training return: tensor(-999.9997, device='cuda:0')
episode: 214 training return: tensor(-999.9999, device='cuda:0')
episode: 215 training return: tensor(-999.9999, device='cuda:0')
epoch: 54 test_true_pfm: -0.6045762155979243 sim_pfm: -999.9008584022522
episode: 216 training return: tensor(-999.9999, device='cuda:0')
episode: 217 training return: tensor(-999.9998, device='cuda:0')
episode: 218 training return: tensor(-999.9957, device='cuda:0')
episode: 219 training return: tensor(-999.9996, device='cuda:0')
epoch: 55 test_true_pfm: -0.3193314944256294 sim_pfm: -999.9011554718018
episode: 220 training return: tensor(-999.9999, device='cuda:0')
episode: 221 training return: tensor(-999.9996, device='cuda:0')
episode: 222 training return: tensor(-999.9999, device='cuda:0')
episode: 223 training return: tensor(-999.9999, device='cuda:0')
epoch: 56 test_true_pfm: 0.19721473825722638 sim_pfm: -999.9011046687762
episode: 224 training return: tensor(-999.9779, device='cuda:0')
episode: 225 training return: tensor(-999.9992, device='cuda:0')
episode: 226 training return: tensor(-1000., device='cuda:0')
episode: 227 training return: tensor(-999.9998, device='cuda:0')
epoch: 57 test_true_pfm: -0.5866168010739398 sim_pfm: -999.9020160039266
episode: 228 training return: tensor(-999.9998, device='cuda:0')
episode: 229 training return: tensor(-1000., device='cuda:0')
episode: 230 training return: tensor(-999.9998, device='cuda:0')
episode: 231 training return: tensor(-999.9999, device='cuda:0')
epoch: 58 test_true_pfm: 0.15578355387307932 sim_pfm: -999.9008807738622
episode: 232 training return: tensor(-999.9997, device='cuda:0')
episode: 233 training return: tensor(-999.9999, device='cuda:0')
episode: 234 training return: tensor(-999.9999, device='cuda:0')
episode: 235 training return: tensor(-999.9999, device='cuda:0')
epoch: 59 test_true_pfm: 0.6659729213574469 sim_pfm: -999.901285370191
episode: 236 training return: tensor(-999.9999, device='cuda:0')
episode: 237 training return: tensor(-999.9999, device='cuda:0')
episode: 238 training return: tensor(-999.9999, device='cuda:0')
episode: 239 training return: tensor(-999.9998, device='cuda:0')
epoch: 60 test_true_pfm: -0.09092361532309405 sim_pfm: -999.9012455940247
episode: 240 training return: tensor(-999.9995, device='cuda:0')
episode: 241 training return: tensor(-999.9998, device='cuda:0')
episode: 242 training return: tensor(-999.9999, device='cuda:0')
episode: 243 training return: tensor(-999.9998, device='cuda:0')
epoch: 61 test_true_pfm: 0.38505862426016835 sim_pfm: -999.9020795822144
episode: 244 training return: tensor(-999.9998, device='cuda:0')
episode: 245 training return: tensor(-999.9998, device='cuda:0')
episode: 246 training return: tensor(-999.9999, device='cuda:0')
episode: 247 training return: tensor(-999.9995, device='cuda:0')
epoch: 62 test_true_pfm: -0.4989038940712152 sim_pfm: -999.9001428087553
episode: 248 training return: tensor(-999.9999, device='cuda:0')
episode: 249 training return: tensor(-1000., device='cuda:0')
episode: 250 training return: tensor(-999.9997, device='cuda:0')
episode: 251 training return: tensor(-999.9999, device='cuda:0')
epoch: 63 test_true_pfm: 0.20027322933708 sim_pfm: -999.9008736213049
episode: 252 training return: tensor(-999.9996, device='cuda:0')
episode: 253 training return: tensor(-999.9998, device='cuda:0')
episode: 254 training return: tensor(-999.9996, device='cuda:0')
episode: 255 training return: tensor(-999.9996, device='cuda:0')
epoch: 64 test_true_pfm: -0.46839310420386165 sim_pfm: -999.9022959470749
episode: 256 training return: tensor(-999.9996, device='cuda:0')
episode: 257 training return: tensor(-999.9998, device='cuda:0')
episode: 258 training return: tensor(-999.9997, device='cuda:0')
episode: 259 training return: tensor(-999.9998, device='cuda:0')
epoch: 65 test_true_pfm: 0.4305471171563047 sim_pfm: -999.9014746944109
episode: 260 training return: tensor(-999.9997, device='cuda:0')
episode: 261 training return: tensor(-999.9999, device='cuda:0')
episode: 262 training return: tensor(-1000., device='cuda:0')
episode: 263 training return: tensor(-999.9998, device='cuda:0')
epoch: 66 test_true_pfm: -0.29667395876869 sim_pfm: -999.9011226495107
episode: 264 training return: tensor(-1000., device='cuda:0')
episode: 265 training return: tensor(-999.9998, device='cuda:0')
episode: 266 training return: tensor(-1000., device='cuda:0')
episode: 267 training return: tensor(-999.9998, device='cuda:0')
epoch: 67 test_true_pfm: -0.03802312300128927 sim_pfm: -999.901202181975
episode: 268 training return: tensor(-999.9996, device='cuda:0')
episode: 269 training return: tensor(-999.9990, device='cuda:0')
episode: 270 training return: tensor(-999.9998, device='cuda:0')
episode: 271 training return: tensor(-999.9999, device='cuda:0')
epoch: 68 test_true_pfm: -0.43827542351504284 sim_pfm: -999.9000480771065
episode: 272 training return: tensor(-999.9999, device='cuda:0')
episode: 273 training return: tensor(-999.9999, device='cuda:0')
episode: 274 training return: tensor(-999.9991, device='cuda:0')
episode: 275 training return: tensor(-999.9998, device='cuda:0')
epoch: 69 test_true_pfm: -0.421582318290026 sim_pfm: -999.9018341898918
episode: 276 training return: tensor(-1000., device='cuda:0')
episode: 277 training return: tensor(-999.9999, device='cuda:0')
episode: 278 training return: tensor(-999.9998, device='cuda:0')
episode: 279 training return: tensor(-999.9998, device='cuda:0')
epoch: 70 test_true_pfm: 0.189655006695805 sim_pfm: -999.9016335209211
episode: 280 training return: tensor(-999.9997, device='cuda:0')
episode: 281 training return: tensor(-999.9996, device='cuda:0')
episode: 282 training return: tensor(-999.9995, device='cuda:0')
episode: 283 training return: tensor(-999.9986, device='cuda:0')
epoch: 71 test_true_pfm: -0.21863954502005264 sim_pfm: -999.9010164141655
episode: 284 training return: tensor(-999.9997, device='cuda:0')
episode: 285 training return: tensor(-999.9998, device='cuda:0')
episode: 286 training return: tensor(-999.9999, device='cuda:0')
episode: 287 training return: tensor(-999.9999, device='cuda:0')
epoch: 72 test_true_pfm: -0.6217534207557703 sim_pfm: -999.9019842147827
episode: 288 training return: tensor(-1000., device='cuda:0')
episode: 289 training return: tensor(-999.9998, device='cuda:0')
episode: 290 training return: tensor(-999.9999, device='cuda:0')
episode: 291 training return: tensor(-999.9991, device='cuda:0')
epoch: 73 test_true_pfm: -0.21603515966950845 sim_pfm: -999.9022955695788
episode: 292 training return: tensor(-999.9997, device='cuda:0')
episode: 293 training return: tensor(-999.9998, device='cuda:0')
episode: 294 training return: tensor(-1000., device='cuda:0')
episode: 295 training return: tensor(-999.9999, device='cuda:0')
epoch: 74 test_true_pfm: 0.09481754358526205 sim_pfm: -999.8998724023501
episode: 296 training return: tensor(-999.9998, device='cuda:0')
episode: 297 training return: tensor(-999.9996, device='cuda:0')
episode: 298 training return: tensor(-1000., device='cuda:0')
episode: 299 training return: tensor(-999.9996, device='cuda:0')
epoch: 75 test_true_pfm: 0.6321535355488095 sim_pfm: -999.9014329115549
episode: 300 training return: tensor(-999.9974, device='cuda:0')
episode: 301 training return: tensor(-999.9997, device='cuda:0')
episode: 302 training return: tensor(-999.9997, device='cuda:0')
episode: 303 training return: tensor(-999.9997, device='cuda:0')
epoch: 76 test_true_pfm: -0.49024146876774943 sim_pfm: -999.9006389180819
episode: 304 training return: tensor(-999.9999, device='cuda:0')
episode: 305 training return: tensor(-999.9999, device='cuda:0')
episode: 306 training return: tensor(-999.9998, device='cuda:0')
episode: 307 training return: tensor(-999.9996, device='cuda:0')
epoch: 77 test_true_pfm: 0.21368022175401916 sim_pfm: -999.901853521665
episode: 308 training return: tensor(-999.9996, device='cuda:0')
episode: 309 training return: tensor(-999.9999, device='cuda:0')
episode: 310 training return: tensor(-999.9999, device='cuda:0')
episode: 311 training return: tensor(-1000., device='cuda:0')
epoch: 78 test_true_pfm: -0.482963778043602 sim_pfm: -999.9021690885226
episode: 312 training return: tensor(-999.9999, device='cuda:0')
episode: 313 training return: tensor(-999.9998, device='cuda:0')
episode: 314 training return: tensor(-999.9999, device='cuda:0')
episode: 315 training return: tensor(-999.9998, device='cuda:0')
epoch: 79 test_true_pfm: -0.6117014200426295 sim_pfm: -999.9010690251986
episode: 316 training return: tensor(-999.9995, device='cuda:0')
episode: 317 training return: tensor(-999.9998, device='cuda:0')
episode: 318 training return: tensor(-999.9998, device='cuda:0')
episode: 319 training return: tensor(-999.9993, device='cuda:0')
epoch: 80 test_true_pfm: 0.36005449980056586 sim_pfm: -999.9020943840345
episode: 320 training return: tensor(-999.9987, device='cuda:0')
episode: 321 training return: tensor(-999.9998, device='cuda:0')
episode: 322 training return: tensor(-999.9999, device='cuda:0')
episode: 323 training return: tensor(-999.9996, device='cuda:0')
epoch: 81 test_true_pfm: -1.368931008716492 sim_pfm: -999.9003028273582
episode: 324 training return: tensor(-1000., device='cuda:0')
episode: 325 training return: tensor(-999.9992, device='cuda:0')
episode: 326 training return: tensor(-1000., device='cuda:0')
episode: 327 training return: tensor(-999.9998, device='cuda:0')
epoch: 82 test_true_pfm: -0.4908860607184918 sim_pfm: -999.9002583821615
episode: 328 training return: tensor(-1000., device='cuda:0')
episode: 329 training return: tensor(-999.9996, device='cuda:0')
episode: 330 training return: tensor(-999.9693, device='cuda:0')
episode: 331 training return: tensor(-999.9999, device='cuda:0')
epoch: 83 test_true_pfm: -0.9495108583013717 sim_pfm: -999.9015062053999
episode: 332 training return: tensor(-999.9999, device='cuda:0')
episode: 333 training return: tensor(-999.9999, device='cuda:0')
episode: 334 training return: tensor(-999.9999, device='cuda:0')
episode: 335 training return: tensor(-999.9996, device='cuda:0')
epoch: 84 test_true_pfm: -0.3979160624957352 sim_pfm: -999.9005604187647
episode: 336 training return: tensor(-999.9999, device='cuda:0')
episode: 337 training return: tensor(-1000., device='cuda:0')
episode: 338 training return: tensor(-999.9998, device='cuda:0')
episode: 339 training return: tensor(-999.9996, device='cuda:0')
epoch: 85 test_true_pfm: -0.7315037662628999 sim_pfm: -999.9003156423569
episode: 340 training return: tensor(-999.9995, device='cuda:0')
episode: 341 training return: tensor(-999.9998, device='cuda:0')
episode: 342 training return: tensor(-999.9999, device='cuda:0')
episode: 343 training return: tensor(-999.9984, device='cuda:0')
epoch: 86 test_true_pfm: -1.0494861138635627 sim_pfm: -999.9011061588923
episode: 344 training return: tensor(-999.9998, device='cuda:0')
episode: 345 training return: tensor(-999.9998, device='cuda:0')
episode: 346 training return: tensor(-999.9998, device='cuda:0')
episode: 347 training return: tensor(-999.9994, device='cuda:0')
epoch: 87 test_true_pfm: -0.9760592856182194 sim_pfm: -999.9009678165118
episode: 348 training return: tensor(-999.9999, device='cuda:0')
episode: 349 training return: tensor(-999.9993, device='cuda:0')
episode: 350 training return: tensor(-999.9991, device='cuda:0')
episode: 351 training return: tensor(-999.9999, device='cuda:0')
epoch: 88 test_true_pfm: -0.5236934245813549 sim_pfm: -999.9006689985594
episode: 352 training return: tensor(-1000., device='cuda:0')
episode: 353 training return: tensor(-999.9999, device='cuda:0')
episode: 354 training return: tensor(-999.9997, device='cuda:0')
episode: 355 training return: tensor(-999.9999, device='cuda:0')
epoch: 89 test_true_pfm: 0.030367113405552315 sim_pfm: -999.9017631610235
episode: 356 training return: tensor(-999.9998, device='cuda:0')
episode: 357 training return: tensor(-999.9997, device='cuda:0')
episode: 358 training return: tensor(-999.9996, device='cuda:0')
episode: 359 training return: tensor(-999.9991, device='cuda:0')
epoch: 90 test_true_pfm: -0.4012883084103019 sim_pfm: -999.901488006115
episode: 360 training return: tensor(-999.9999, device='cuda:0')
episode: 361 training return: tensor(-999.9999, device='cuda:0')
episode: 362 training return: tensor(-999.9996, device='cuda:0')
episode: 363 training return: tensor(-999.9995, device='cuda:0')
epoch: 91 test_true_pfm: -1.5796427163777225 sim_pfm: -999.9007761478424
episode: 364 training return: tensor(-999.9999, device='cuda:0')
episode: 365 training return: tensor(-999.9999, device='cuda:0')
episode: 366 training return: tensor(-999.9999, device='cuda:0')
episode: 367 training return: tensor(-1000., device='cuda:0')
epoch: 92 test_true_pfm: -0.006849373526608397 sim_pfm: -999.9014425873756
episode: 368 training return: tensor(-999.9999, device='cuda:0')
episode: 369 training return: tensor(-999.9997, device='cuda:0')
episode: 370 training return: tensor(-999.9996, device='cuda:0')
episode: 371 training return: tensor(-1000., device='cuda:0')
epoch: 93 test_true_pfm: -0.7269004694348591 sim_pfm: -999.9017222523689
episode: 372 training return: tensor(-999.9997, device='cuda:0')
episode: 373 training return: tensor(-999.9999, device='cuda:0')
episode: 374 training return: tensor(-999.9999, device='cuda:0')
episode: 375 training return: tensor(-999.9999, device='cuda:0')
epoch: 94 test_true_pfm: -0.5144170982696649 sim_pfm: -999.9023284912109
episode: 376 training return: tensor(-999.9999, device='cuda:0')
episode: 377 training return: tensor(-999.9993, device='cuda:0')
episode: 378 training return: tensor(-999.9999, device='cuda:0')
episode: 379 training return: tensor(-999.9993, device='cuda:0')
epoch: 95 test_true_pfm: -0.9631836633010181 sim_pfm: -999.9009686311086
episode: 380 training return: tensor(-999.9999, device='cuda:0')
episode: 381 training return: tensor(-999.9994, device='cuda:0')
episode: 382 training return: tensor(-999.9996, device='cuda:0')
episode: 383 training return: tensor(-999.9999, device='cuda:0')
epoch: 96 test_true_pfm: -0.2809217939150251 sim_pfm: -999.902262032032
episode: 384 training return: tensor(-999.9999, device='cuda:0')
episode: 385 training return: tensor(-1000., device='cuda:0')
episode: 386 training return: tensor(-999.9984, device='cuda:0')
episode: 387 training return: tensor(-1000., device='cuda:0')
epoch: 97 test_true_pfm: -0.3444381838420354 sim_pfm: -999.9007312456766
episode: 388 training return: tensor(-999.9993, device='cuda:0')
episode: 389 training return: tensor(-999.9989, device='cuda:0')
episode: 390 training return: tensor(-999.9998, device='cuda:0')
episode: 391 training return: tensor(-999.9999, device='cuda:0')
epoch: 98 test_true_pfm: -1.0085902997487777 sim_pfm: -999.9015571276346
episode: 392 training return: tensor(-999.9985, device='cuda:0')
episode: 393 training return: tensor(-999.9999, device='cuda:0')
episode: 394 training return: tensor(-999.9998, device='cuda:0')
episode: 395 training return: tensor(-999.9999, device='cuda:0')
epoch: 99 test_true_pfm: -0.4727246025270495 sim_pfm: -999.9031972885132
episode: 396 training return: tensor(-999.9998, device='cuda:0')
episode: 397 training return: tensor(-999.9999, device='cuda:0')
episode: 398 training return: tensor(-999.9996, device='cuda:0')
episode: 399 training return: tensor(-999.9999, device='cuda:0')
epoch: 100 test_true_pfm: -0.45802143086982694 sim_pfm: -999.9017173250517
episode: 400 training return: tensor(-999.9997, device='cuda:0')
episode: 401 training return: tensor(-999.9998, device='cuda:0')
episode: 402 training return: tensor(-1000., device='cuda:0')
episode: 403 training return: tensor(-999.9823, device='cuda:0')
epoch: 101 test_true_pfm: 0.4709181406761836 sim_pfm: -999.9002476135889
episode: 404 training return: tensor(-999.9996, device='cuda:0')
episode: 405 training return: tensor(-1000., device='cuda:0')
episode: 406 training return: tensor(-999.9995, device='cuda:0')
episode: 407 training return: tensor(-999.9999, device='cuda:0')
epoch: 102 test_true_pfm: -0.1314739284312112 sim_pfm: -999.8998434146246
episode: 408 training return: tensor(-999.9999, device='cuda:0')
episode: 409 training return: tensor(-999.9998, device='cuda:0')
episode: 410 training return: tensor(-999.9999, device='cuda:0')
episode: 411 training return: tensor(-999.9999, device='cuda:0')
epoch: 103 test_true_pfm: -0.9529792556640024 sim_pfm: -999.9023887912432
episode: 412 training return: tensor(-999.9999, device='cuda:0')
episode: 413 training return: tensor(-999.9999, device='cuda:0')
episode: 414 training return: tensor(-999.9995, device='cuda:0')
episode: 415 training return: tensor(-999.9996, device='cuda:0')
epoch: 104 test_true_pfm: -0.05925302115772893 sim_pfm: -999.9021724462509
episode: 416 training return: tensor(-999.9616, device='cuda:0')
episode: 417 training return: tensor(-999.9983, device='cuda:0')
episode: 418 training return: tensor(-999.9999, device='cuda:0')
episode: 419 training return: tensor(-999.9996, device='cuda:0')
epoch: 105 test_true_pfm: -0.34229871877160417 sim_pfm: -999.9017766515414
episode: 420 training return: tensor(-999.9999, device='cuda:0')
episode: 421 training return: tensor(-999.9996, device='cuda:0')
episode: 422 training return: tensor(-999.9999, device='cuda:0')
episode: 423 training return: tensor(-999.9998, device='cuda:0')
epoch: 106 test_true_pfm: -0.242462832515975 sim_pfm: -999.9013659556707
episode: 424 training return: tensor(-999.9995, device='cuda:0')
episode: 425 training return: tensor(-999.9999, device='cuda:0')
episode: 426 training return: tensor(-999.9999, device='cuda:0')
episode: 427 training return: tensor(-999.9999, device='cuda:0')
epoch: 107 test_true_pfm: 0.227147408749906 sim_pfm: -999.9007867574692
episode: 428 training return: tensor(-999.9999, device='cuda:0')
episode: 429 training return: tensor(-999.9996, device='cuda:0')
episode: 430 training return: tensor(-999.9998, device='cuda:0')
episode: 431 training return: tensor(-999.9998, device='cuda:0')
epoch: 108 test_true_pfm: -0.004620045101989619 sim_pfm: -999.9027098019918
episode: 432 training return: tensor(-999.9998, device='cuda:0')
episode: 433 training return: tensor(-999.9998, device='cuda:0')
episode: 434 training return: tensor(-999.9999, device='cuda:0')
episode: 435 training return: tensor(-1000., device='cuda:0')
epoch: 109 test_true_pfm: -0.4457025354712394 sim_pfm: -999.9014636278152
episode: 436 training return: tensor(-999.9998, device='cuda:0')
episode: 437 training return: tensor(-1000., device='cuda:0')
episode: 438 training return: tensor(-999.9976, device='cuda:0')
episode: 439 training return: tensor(-999.9999, device='cuda:0')
epoch: 110 test_true_pfm: -0.9881426519674802 sim_pfm: -999.9007663925489
episode: 440 training return: tensor(-999.9999, device='cuda:0')
episode: 441 training return: tensor(-1000., device='cuda:0')
episode: 442 training return: tensor(-999.9999, device='cuda:0')
episode: 443 training return: tensor(-999.9986, device='cuda:0')
epoch: 111 test_true_pfm: -0.7303306336914889 sim_pfm: -999.9003582398096
episode: 444 training return: tensor(-999.9999, device='cuda:0')
episode: 445 training return: tensor(-1000., device='cuda:0')
episode: 446 training return: tensor(-999.9886, device='cuda:0')
episode: 447 training return: tensor(-999.9998, device='cuda:0')
epoch: 112 test_true_pfm: -0.4425173130149959 sim_pfm: -999.9007691144943
episode: 448 training return: tensor(-999.9998, device='cuda:0')
episode: 449 training return: tensor(-999.9987, device='cuda:0')
episode: 450 training return: tensor(-999.9988, device='cuda:0')
episode: 451 training return: tensor(-999.9998, device='cuda:0')
epoch: 113 test_true_pfm: -0.1155997841565411 sim_pfm: -999.9016298254331
episode: 452 training return: tensor(-999.9999, device='cuda:0')
episode: 453 training return: tensor(-999.9933, device='cuda:0')
episode: 454 training return: tensor(-999.9997, device='cuda:0')
episode: 455 training return: tensor(-999.9999, device='cuda:0')
epoch: 114 test_true_pfm: -0.33980010550626033 sim_pfm: -999.900818725427
episode: 456 training return: tensor(-999.9998, device='cuda:0')
episode: 457 training return: tensor(-999.9996, device='cuda:0')
episode: 458 training return: tensor(-1000., device='cuda:0')
episode: 459 training return: tensor(-999.9993, device='cuda:0')
epoch: 115 test_true_pfm: -0.26017017502505607 sim_pfm: -999.9012122154236
episode: 460 training return: tensor(-999.9999, device='cuda:0')
episode: 461 training return: tensor(-999.9999, device='cuda:0')
episode: 462 training return: tensor(-999.9996, device='cuda:0')
episode: 463 training return: tensor(-999.9996, device='cuda:0')
epoch: 116 test_true_pfm: 0.13057650140457674 sim_pfm: -999.9014035860697
episode: 464 training return: tensor(-999.9999, device='cuda:0')
episode: 465 training return: tensor(-999.9999, device='cuda:0')
episode: 466 training return: tensor(-999.9998, device='cuda:0')
episode: 467 training return: tensor(-999.9998, device='cuda:0')
epoch: 117 test_true_pfm: 0.13494667003325622 sim_pfm: -999.9016194740931
episode: 468 training return: tensor(-999.9995, device='cuda:0')
episode: 469 training return: tensor(-999.9981, device='cuda:0')
episode: 470 training return: tensor(-999.9995, device='cuda:0')
episode: 471 training return: tensor(-999.9996, device='cuda:0')
epoch: 118 test_true_pfm: 0.2797242237116249 sim_pfm: -999.9007399280866
episode: 472 training return: tensor(-999.9999, device='cuda:0')
episode: 473 training return: tensor(-999.9998, device='cuda:0')
episode: 474 training return: tensor(-1000., device='cuda:0')
episode: 475 training return: tensor(-999.9999, device='cuda:0')
epoch: 119 test_true_pfm: -0.36056574723468743 sim_pfm: -999.9021250406901
episode: 476 training return: tensor(-999.9997, device='cuda:0')
episode: 477 training return: tensor(-999.9996, device='cuda:0')
episode: 478 training return: tensor(-999.9995, device='cuda:0')
episode: 479 training return: tensor(-999.9999, device='cuda:0')
epoch: 120 test_true_pfm: -0.018846409710578344 sim_pfm: -999.9022811849912
episode: 480 training return: tensor(-999.9999, device='cuda:0')
episode: 481 training return: tensor(-999.9999, device='cuda:0')
episode: 482 training return: tensor(-999.9996, device='cuda:0')
episode: 483 training return: tensor(-999.9998, device='cuda:0')
epoch: 121 test_true_pfm: 0.16354016090792856 sim_pfm: -999.9006604154905
episode: 484 training return: tensor(-999.9992, device='cuda:0')
episode: 485 training return: tensor(-999.9998, device='cuda:0')
episode: 486 training return: tensor(-999.9997, device='cuda:0')
episode: 487 training return: tensor(-999.9998, device='cuda:0')
epoch: 122 test_true_pfm: -0.6576787368792151 sim_pfm: -999.9015462398529
episode: 488 training return: tensor(-999.9999, device='cuda:0')
episode: 489 training return: tensor(-999.9996, device='cuda:0')
episode: 490 training return: tensor(-999.9980, device='cuda:0')
episode: 491 training return: tensor(-999.9997, device='cuda:0')
epoch: 123 test_true_pfm: -0.6060329396701315 sim_pfm: -999.9021672407786
episode: 492 training return: tensor(-999.9999, device='cuda:0')
episode: 493 training return: tensor(-999.9997, device='cuda:0')
episode: 494 training return: tensor(-999.9997, device='cuda:0')
episode: 495 training return: tensor(-999.9999, device='cuda:0')
epoch: 124 test_true_pfm: -0.7132532382506932 sim_pfm: -999.9019715189934
episode: 496 training return: tensor(-999.9999, device='cuda:0')
episode: 497 training return: tensor(-999.9997, device='cuda:0')
episode: 498 training return: tensor(-999.9999, device='cuda:0')
episode: 499 training return: tensor(-999.9998, device='cuda:0')
epoch: 125 test_true_pfm: -0.031596803703632305 sim_pfm: -999.9022851983706
episode: 500 training return: tensor(-999.9999, device='cuda:0')
episode: 501 training return: tensor(-999.9998, device='cuda:0')
episode: 502 training return: tensor(-999.9998, device='cuda:0')
episode: 503 training return: tensor(-999.9998, device='cuda:0')
epoch: 126 test_true_pfm: -0.16798091885333877 sim_pfm: -999.9023153583208
episode: 504 training return: tensor(-1000., device='cuda:0')
episode: 505 training return: tensor(-999.9999, device='cuda:0')
episode: 506 training return: tensor(-999.9999, device='cuda:0')
episode: 507 training return: tensor(-999.9862, device='cuda:0')
epoch: 127 test_true_pfm: -0.060519850336126314 sim_pfm: -999.9016378919283
episode: 508 training return: tensor(-999.9999, device='cuda:0')
episode: 509 training return: tensor(-999.9999, device='cuda:0')
episode: 510 training return: tensor(-999.9999, device='cuda:0')
episode: 511 training return: tensor(-999.9994, device='cuda:0')
epoch: 128 test_true_pfm: 0.25709464686464595 sim_pfm: -999.9011014898618
episode: 512 training return: tensor(-999.9998, device='cuda:0')
episode: 513 training return: tensor(-999.9999, device='cuda:0')
episode: 514 training return: tensor(-999.9999, device='cuda:0')
episode: 515 training return: tensor(-1000., device='cuda:0')
epoch: 129 test_true_pfm: -1.2528523247383123 sim_pfm: -999.9017569820086
episode: 516 training return: tensor(-999.9998, device='cuda:0')
episode: 517 training return: tensor(-999.9998, device='cuda:0')
episode: 518 training return: tensor(-999.9998, device='cuda:0')
episode: 519 training return: tensor(-999.9999, device='cuda:0')
epoch: 130 test_true_pfm: -0.5503251305829923 sim_pfm: -999.9016122817993
episode: 520 training return: tensor(-999.9443, device='cuda:0')
episode: 521 training return: tensor(-999.9999, device='cuda:0')
episode: 522 training return: tensor(-999.9998, device='cuda:0')
episode: 523 training return: tensor(-999.9987, device='cuda:0')
epoch: 131 test_true_pfm: -0.5046149925228116 sim_pfm: -999.900694767634
episode: 524 training return: tensor(-999.9999, device='cuda:0')
episode: 525 training return: tensor(-999.9991, device='cuda:0')
episode: 526 training return: tensor(-999.9998, device='cuda:0')
episode: 527 training return: tensor(-999.9999, device='cuda:0')
epoch: 132 test_true_pfm: 0.4197265391155119 sim_pfm: -999.9018295009931
episode: 528 training return: tensor(-999.9997, device='cuda:0')
episode: 529 training return: tensor(-999.9999, device='cuda:0')
episode: 530 training return: tensor(-999.9998, device='cuda:0')
episode: 531 training return: tensor(-999.9999, device='cuda:0')
epoch: 133 test_true_pfm: -0.920548588852116 sim_pfm: -999.9015202919642
episode: 532 training return: tensor(-999.9998, device='cuda:0')
episode: 533 training return: tensor(-999.9999, device='cuda:0')
episode: 534 training return: tensor(-999.9998, device='cuda:0')
episode: 535 training return: tensor(-1000., device='cuda:0')
epoch: 134 test_true_pfm: 0.17098322265833218 sim_pfm: -999.900458574295
episode: 536 training return: tensor(-1000., device='cuda:0')
episode: 537 training return: tensor(-999.9997, device='cuda:0')
episode: 538 training return: tensor(-999.9997, device='cuda:0')
episode: 539 training return: tensor(-999.9999, device='cuda:0')
epoch: 135 test_true_pfm: -0.9396173317251683 sim_pfm: -999.8994680841764
episode: 540 training return: tensor(-999.9998, device='cuda:0')
episode: 541 training return: tensor(-999.9999, device='cuda:0')
episode: 542 training return: tensor(-999.9998, device='cuda:0')
episode: 543 training return: tensor(-999.9998, device='cuda:0')
epoch: 136 test_true_pfm: -0.018532951494740102 sim_pfm: -999.9013161063194
episode: 544 training return: tensor(-1000., device='cuda:0')
episode: 545 training return: tensor(-999.9999, device='cuda:0')
episode: 546 training return: tensor(-999.9999, device='cuda:0')
episode: 547 training return: tensor(-999.9996, device='cuda:0')
epoch: 137 test_true_pfm: -0.6041946935360815 sim_pfm: -999.902579387029
episode: 548 training return: tensor(-999.9999, device='cuda:0')
episode: 549 training return: tensor(-999.9999, device='cuda:0')
episode: 550 training return: tensor(-999.9999, device='cuda:0')
episode: 551 training return: tensor(-999.9997, device='cuda:0')
epoch: 138 test_true_pfm: 0.22018104597454946 sim_pfm: -999.9017637968063
episode: 552 training return: tensor(-999.9999, device='cuda:0')
episode: 553 training return: tensor(-1000., device='cuda:0')
episode: 554 training return: tensor(-999.9995, device='cuda:0')
episode: 555 training return: tensor(-999.9968, device='cuda:0')
epoch: 139 test_true_pfm: -0.9726290932334444 sim_pfm: -999.9030217727026
episode: 556 training return: tensor(-999.9998, device='cuda:0')
episode: 557 training return: tensor(-999.9998, device='cuda:0')
episode: 558 training return: tensor(-999.9999, device='cuda:0')
episode: 559 training return: tensor(-999.9999, device='cuda:0')
epoch: 140 test_true_pfm: -0.2540635598670964 sim_pfm: -999.9012938141823
episode: 560 training return: tensor(-1000., device='cuda:0')
episode: 561 training return: tensor(-999.9999, device='cuda:0')
episode: 562 training return: tensor(-999.9998, device='cuda:0')
episode: 563 training return: tensor(-1000., device='cuda:0')
epoch: 141 test_true_pfm: 0.1932254284388656 sim_pfm: -999.9014318585396
episode: 564 training return: tensor(-999.9998, device='cuda:0')
episode: 565 training return: tensor(-999.9998, device='cuda:0')
episode: 566 training return: tensor(-999.9969, device='cuda:0')
episode: 567 training return: tensor(-999.9990, device='cuda:0')
epoch: 142 test_true_pfm: 0.19929755397834648 sim_pfm: -999.9021859765053
episode: 568 training return: tensor(-999.9999, device='cuda:0')
episode: 569 training return: tensor(-999.9995, device='cuda:0')
episode: 570 training return: tensor(-999.9998, device='cuda:0')
episode: 571 training return: tensor(-999.9997, device='cuda:0')
epoch: 143 test_true_pfm: -0.25753878184952134 sim_pfm: -999.9017742474874
episode: 572 training return: tensor(-999.9997, device='cuda:0')
episode: 573 training return: tensor(-999.9999, device='cuda:0')
episode: 574 training return: tensor(-999.9999, device='cuda:0')
episode: 575 training return: tensor(-999.9999, device='cuda:0')
epoch: 144 test_true_pfm: -0.09837627901212496 sim_pfm: -999.9013077616692
episode: 576 training return: tensor(-999.9994, device='cuda:0')
episode: 577 training return: tensor(-999.9999, device='cuda:0')
episode: 578 training return: tensor(-999.9998, device='cuda:0')
episode: 579 training return: tensor(-999.9999, device='cuda:0')
epoch: 145 test_true_pfm: -0.15016041693474583 sim_pfm: -999.9015778899193
episode: 580 training return: tensor(-999.9999, device='cuda:0')
episode: 581 training return: tensor(-999.9999, device='cuda:0')
episode: 582 training return: tensor(-999.9999, device='cuda:0')
episode: 583 training return: tensor(-999.9993, device='cuda:0')
epoch: 146 test_true_pfm: -0.648024018302865 sim_pfm: -999.9011115034422
episode: 584 training return: tensor(-999.9999, device='cuda:0')
episode: 585 training return: tensor(-999.9999, device='cuda:0')
episode: 586 training return: tensor(-999.9999, device='cuda:0')
episode: 587 training return: tensor(-999.9998, device='cuda:0')
epoch: 147 test_true_pfm: -0.0842271935745499 sim_pfm: -999.9020559191704
episode: 588 training return: tensor(-999.9999, device='cuda:0')
episode: 589 training return: tensor(-999.9995, device='cuda:0')
episode: 590 training return: tensor(-1000., device='cuda:0')
episode: 591 training return: tensor(-999.9998, device='cuda:0')
epoch: 148 test_true_pfm: -0.011699723872905679 sim_pfm: -999.900865316391
episode: 592 training return: tensor(-999.9998, device='cuda:0')
episode: 593 training return: tensor(-999.9998, device='cuda:0')
episode: 594 training return: tensor(-999.9999, device='cuda:0')
episode: 595 training return: tensor(-999.9999, device='cuda:0')
epoch: 149 test_true_pfm: 0.08376113183882127 sim_pfm: -999.9006216923395
episode: 596 training return: tensor(-1000., device='cuda:0')
episode: 597 training return: tensor(-999.9999, device='cuda:0')
episode: 598 training return: tensor(-999.9998, device='cuda:0')
episode: 599 training return: tensor(-999.9999, device='cuda:0')
epoch: 150 test_true_pfm: -1.1735253918939619 sim_pfm: -999.9018716812134
