['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'baseline', '--traj', 'expert', '--seed', '2']
episode: 0 training return: tensor(-999.9998, device='cuda:0')
episode: 1 training return: tensor(-999.9996, device='cuda:0')
episode: 2 training return: tensor(-999.9994, device='cuda:0')
episode: 3 training return: tensor(-999.9999, device='cuda:0')
epoch: 1 test_true_pfm: -0.341388505100421 sim_pfm: -999.9560385346413
episode: 4 training return: tensor(-999.9997, device='cuda:0')
episode: 5 training return: tensor(-999.9996, device='cuda:0')
episode: 6 training return: tensor(-999.9998, device='cuda:0')
episode: 7 training return: tensor(-999.9995, device='cuda:0')
epoch: 2 test_true_pfm: -0.23638165889861504 sim_pfm: -999.9549770752589
episode: 8 training return: tensor(-999.9998, device='cuda:0')
episode: 9 training return: tensor(-999.9996, device='cuda:0')
episode: 10 training return: tensor(-999.9996, device='cuda:0')
episode: 11 training return: tensor(-999.9995, device='cuda:0')
epoch: 3 test_true_pfm: -0.3083222443788864 sim_pfm: -999.9548267324766
episode: 12 training return: tensor(-999.9998, device='cuda:0')
episode: 13 training return: tensor(-999.9995, device='cuda:0')
episode: 14 training return: tensor(-999.9998, device='cuda:0')
episode: 15 training return: tensor(-999.9996, device='cuda:0')
epoch: 4 test_true_pfm: 0.4557876184507335 sim_pfm: -999.9565228223801
episode: 16 training return: tensor(-999.9998, device='cuda:0')
episode: 17 training return: tensor(-999.9990, device='cuda:0')
episode: 18 training return: tensor(-999.9999, device='cuda:0')
episode: 19 training return: tensor(-999.9996, device='cuda:0')
epoch: 5 test_true_pfm: -0.18627666608596796 sim_pfm: -999.9561526179314
episode: 20 training return: tensor(-999.9997, device='cuda:0')
episode: 21 training return: tensor(-999.9990, device='cuda:0')
episode: 22 training return: tensor(-999.9998, device='cuda:0')
episode: 23 training return: tensor(-999.9998, device='cuda:0')
epoch: 6 test_true_pfm: 0.171984854369039 sim_pfm: -999.9549211859703
episode: 24 training return: tensor(-999.9996, device='cuda:0')
episode: 25 training return: tensor(-999.9997, device='cuda:0')
episode: 26 training return: tensor(-999.9997, device='cuda:0')
episode: 27 training return: tensor(-999.9976, device='cuda:0')
epoch: 7 test_true_pfm: -0.6523744261267613 sim_pfm: -999.9563274184862
episode: 28 training return: tensor(-999.9996, device='cuda:0')
episode: 29 training return: tensor(-999.9998, device='cuda:0')
episode: 30 training return: tensor(-999.9998, device='cuda:0')
episode: 31 training return: tensor(-999.9995, device='cuda:0')
epoch: 8 test_true_pfm: -0.7511774617986378 sim_pfm: -999.9568391839663
episode: 32 training return: tensor(-999.9999, device='cuda:0')
episode: 33 training return: tensor(-999.9998, 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: -0.31691649330641186 sim_pfm: -999.9557543992996
episode: 36 training return: tensor(-999.9998, device='cuda:0')
episode: 37 training return: tensor(-999.9994, device='cuda:0')
episode: 38 training return: tensor(-999.9996, device='cuda:0')
episode: 39 training return: tensor(-999.9994, device='cuda:0')
epoch: 10 test_true_pfm: 0.7656330833971273 sim_pfm: -999.9555923938751
episode: 40 training return: tensor(-999.9996, device='cuda:0')
episode: 41 training return: tensor(-999.9998, device='cuda:0')
episode: 42 training return: tensor(-999.9993, device='cuda:0')
episode: 43 training return: tensor(-999.9998, device='cuda:0')
epoch: 11 test_true_pfm: -0.6745332716300076 sim_pfm: -999.9547137816747
episode: 44 training return: tensor(-999.9996, device='cuda:0')
episode: 45 training return: tensor(-999.9998, device='cuda:0')
episode: 46 training return: tensor(-999.9998, device='cuda:0')
episode: 47 training return: tensor(-999.9995, device='cuda:0')
epoch: 12 test_true_pfm: -0.23238086819078838 sim_pfm: -999.9564221302668
episode: 48 training return: tensor(-999.9999, device='cuda:0')
episode: 49 training return: tensor(-999.9998, device='cuda:0')
episode: 50 training return: tensor(-999.9994, device='cuda:0')
episode: 51 training return: tensor(-999.9996, device='cuda:0')
epoch: 13 test_true_pfm: -0.7178350426298131 sim_pfm: -999.9579853812853
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(-999.9996, device='cuda:0')
episode: 55 training return: tensor(-999.9987, device='cuda:0')
epoch: 14 test_true_pfm: -0.8575836517783871 sim_pfm: -999.9562224149704
episode: 56 training return: tensor(-999.9999, device='cuda:0')
episode: 57 training return: tensor(-999.9996, device='cuda:0')
episode: 58 training return: tensor(-999.9995, device='cuda:0')
episode: 59 training return: tensor(-999.9994, device='cuda:0')
epoch: 15 test_true_pfm: -0.2713198748150904 sim_pfm: -999.9551400939623
episode: 60 training return: tensor(-999.9997, device='cuda:0')
episode: 61 training return: tensor(-999.9996, device='cuda:0')
episode: 62 training return: tensor(-999.9997, device='cuda:0')
episode: 63 training return: tensor(-999.9999, device='cuda:0')
epoch: 16 test_true_pfm: -0.0036228106844298593 sim_pfm: -999.9580796559652
episode: 64 training return: tensor(-999.9998, device='cuda:0')
episode: 65 training return: tensor(-999.9999, device='cuda:0')
episode: 66 training return: tensor(-999.9999, device='cuda:0')
episode: 67 training return: tensor(-999.9998, device='cuda:0')
epoch: 17 test_true_pfm: -0.3049693657516827 sim_pfm: -999.9563002983729
episode: 68 training return: tensor(-999.9995, device='cuda:0')
episode: 69 training return: tensor(-999.9998, device='cuda:0')
episode: 70 training return: tensor(-999.9995, device='cuda:0')
episode: 71 training return: tensor(-999.9999, device='cuda:0')
epoch: 18 test_true_pfm: -0.5403211917157559 sim_pfm: -999.955384850502
episode: 72 training return: tensor(-999.9997, device='cuda:0')
episode: 73 training return: tensor(-999.9997, device='cuda:0')
episode: 74 training return: tensor(-999.9996, device='cuda:0')
episode: 75 training return: tensor(-999.9999, device='cuda:0')
epoch: 19 test_true_pfm: -0.03981298239096646 sim_pfm: -999.9558895627657
episode: 76 training return: tensor(-999.9995, device='cuda:0')
episode: 77 training return: tensor(-999.9999, device='cuda:0')
episode: 78 training return: tensor(-999.9996, device='cuda:0')
episode: 79 training return: tensor(-999.9998, device='cuda:0')
epoch: 20 test_true_pfm: -0.6639659337939374 sim_pfm: -999.9563312927881
episode: 80 training return: tensor(-999.9998, device='cuda:0')
episode: 81 training return: tensor(-999.9998, 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: -0.0996526612746007 sim_pfm: -999.9561161200205
episode: 84 training return: tensor(-999.9997, device='cuda:0')
episode: 85 training return: tensor(-999.9995, device='cuda:0')
episode: 86 training return: tensor(-1000., device='cuda:0')
episode: 87 training return: tensor(-999.9999, device='cuda:0')
epoch: 22 test_true_pfm: -0.45295144107893953 sim_pfm: -999.9556127985319
episode: 88 training return: tensor(-999.9990, device='cuda:0')
episode: 89 training return: tensor(-999.9997, device='cuda:0')
episode: 90 training return: tensor(-999.9999, device='cuda:0')
episode: 91 training return: tensor(-999.9999, device='cuda:0')
epoch: 23 test_true_pfm: -0.03333374655146795 sim_pfm: -999.9559213519096
episode: 92 training return: tensor(-999.9996, device='cuda:0')
episode: 93 training return: tensor(-999.9998, device='cuda:0')
episode: 94 training return: tensor(-999.9988, device='cuda:0')
episode: 95 training return: tensor(-999.9998, device='cuda:0')
epoch: 24 test_true_pfm: 0.08637585874932048 sim_pfm: -999.9566029111544
episode: 96 training return: tensor(-999.9996, device='cuda:0')
episode: 97 training return: tensor(-999.9998, device='cuda:0')
episode: 98 training return: tensor(-999.9998, device='cuda:0')
episode: 99 training return: tensor(-999.9998, device='cuda:0')
epoch: 25 test_true_pfm: -0.9019680358391473 sim_pfm: -999.9566125075022
episode: 100 training return: tensor(-999.9993, device='cuda:0')
episode: 101 training return: tensor(-999.9997, device='cuda:0')
episode: 102 training return: tensor(-999.9996, device='cuda:0')
episode: 103 training return: tensor(-999.9996, device='cuda:0')
epoch: 26 test_true_pfm: -0.23014637028897492 sim_pfm: -999.9550758798918
episode: 104 training return: tensor(-999.9996, device='cuda:0')
episode: 105 training return: tensor(-999.9998, device='cuda:0')
episode: 106 training return: tensor(-999.9998, device='cuda:0')
episode: 107 training return: tensor(-999.9999, device='cuda:0')
epoch: 27 test_true_pfm: -0.14599287314174492 sim_pfm: -999.9565354983012
episode: 108 training return: tensor(-999.9998, device='cuda:0')
episode: 109 training return: tensor(-999.9999, device='cuda:0')
episode: 110 training return: tensor(-999.9986, device='cuda:0')
episode: 111 training return: tensor(-999.9996, device='cuda:0')
epoch: 28 test_true_pfm: 0.058975255695899474 sim_pfm: -999.9555430412292
episode: 112 training return: tensor(-999.9998, device='cuda:0')
episode: 113 training return: tensor(-999.9998, device='cuda:0')
episode: 114 training return: tensor(-999.9996, device='cuda:0')
episode: 115 training return: tensor(-999.9995, device='cuda:0')
epoch: 29 test_true_pfm: -0.9015586004462114 sim_pfm: -999.9567383329073
episode: 116 training return: tensor(-999.9999, device='cuda:0')
episode: 117 training return: tensor(-999.9997, device='cuda:0')
episode: 118 training return: tensor(-999.9997, device='cuda:0')
episode: 119 training return: tensor(-1000., device='cuda:0')
epoch: 30 test_true_pfm: -0.9651725627897726 sim_pfm: -999.9570717215538
episode: 120 training return: tensor(-999.9996, device='cuda:0')
episode: 121 training return: tensor(-999.9995, device='cuda:0')
episode: 122 training return: tensor(-999.9996, device='cuda:0')
episode: 123 training return: tensor(-999.9998, device='cuda:0')
epoch: 31 test_true_pfm: 0.03937880632651858 sim_pfm: -999.9573282599449
episode: 124 training return: tensor(-999.9996, device='cuda:0')
episode: 125 training return: tensor(-999.9999, device='cuda:0')
episode: 126 training return: tensor(-999.9997, device='cuda:0')
episode: 127 training return: tensor(-999.9998, device='cuda:0')
epoch: 32 test_true_pfm: 0.41313879441048845 sim_pfm: -999.9556573232015
episode: 128 training return: tensor(-999.9998, device='cuda:0')
episode: 129 training return: tensor(-999.9996, device='cuda:0')
episode: 130 training return: tensor(-999.9999, device='cuda:0')
episode: 131 training return: tensor(-999.9997, device='cuda:0')
epoch: 33 test_true_pfm: -0.2953180630756587 sim_pfm: -999.9567195574442
episode: 132 training return: tensor(-999.9996, device='cuda:0')
episode: 133 training return: tensor(-999.9998, device='cuda:0')
episode: 134 training return: tensor(-999.9995, device='cuda:0')
episode: 135 training return: tensor(-999.9999, device='cuda:0')
epoch: 34 test_true_pfm: 0.233309425580413 sim_pfm: -999.9560849666595
episode: 136 training return: tensor(-999.9999, device='cuda:0')
episode: 137 training return: tensor(-999.9994, device='cuda:0')
episode: 138 training return: tensor(-999.9996, device='cuda:0')
episode: 139 training return: tensor(-999.9998, device='cuda:0')
epoch: 35 test_true_pfm: -0.5710131141429918 sim_pfm: -999.9539744853973
episode: 140 training return: tensor(-999.9996, device='cuda:0')
episode: 141 training return: tensor(-999.9998, device='cuda:0')
episode: 142 training return: tensor(-999.9998, device='cuda:0')
episode: 143 training return: tensor(-999.9997, device='cuda:0')
epoch: 36 test_true_pfm: 0.06904911575508281 sim_pfm: -999.9574410120646
episode: 144 training return: tensor(-999.9997, device='cuda:0')
episode: 145 training return: tensor(-999.9993, device='cuda:0')
episode: 146 training return: tensor(-999.9996, device='cuda:0')
episode: 147 training return: tensor(-999.9996, device='cuda:0')
epoch: 37 test_true_pfm: -0.19823927255953847 sim_pfm: -999.9575910170873
episode: 148 training return: tensor(-999.9996, device='cuda:0')
episode: 149 training return: tensor(-999.9998, device='cuda:0')
episode: 150 training return: tensor(-999.9996, device='cuda:0')
episode: 151 training return: tensor(-999.9993, device='cuda:0')
epoch: 38 test_true_pfm: 0.05927449722877439 sim_pfm: -999.957071085771
episode: 152 training return: tensor(-999.9998, device='cuda:0')
episode: 153 training return: tensor(-999.9995, device='cuda:0')
episode: 154 training return: tensor(-999.9996, device='cuda:0')
episode: 155 training return: tensor(-999.9988, device='cuda:0')
epoch: 39 test_true_pfm: 0.284422533926677 sim_pfm: -999.9555554588636
episode: 156 training return: tensor(-999.9998, device='cuda:0')
episode: 157 training return: tensor(-999.9997, device='cuda:0')
episode: 158 training return: tensor(-999.9998, device='cuda:0')
episode: 159 training return: tensor(-999.9995, device='cuda:0')
epoch: 40 test_true_pfm: 0.14287879005529017 sim_pfm: -999.9550530910492
episode: 160 training return: tensor(-999.9997, device='cuda:0')
episode: 161 training return: tensor(-999.9994, 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: -0.06390311733018457 sim_pfm: -999.9550999005636
episode: 164 training return: tensor(-999.9977, device='cuda:0')
episode: 165 training return: tensor(-999.9997, device='cuda:0')
episode: 166 training return: tensor(-999.9999, device='cuda:0')
episode: 167 training return: tensor(-999.9999, device='cuda:0')
epoch: 42 test_true_pfm: -0.08104680885018496 sim_pfm: -999.9567324916521
episode: 168 training return: tensor(-999.9996, device='cuda:0')
episode: 169 training return: tensor(-999.9996, device='cuda:0')
episode: 170 training return: tensor(-999.9998, device='cuda:0')
episode: 171 training return: tensor(-999.9990, device='cuda:0')
epoch: 43 test_true_pfm: 0.5740079813255242 sim_pfm: -999.9560165405273
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(-999.9999, device='cuda:0')
episode: 175 training return: tensor(-999.9995, device='cuda:0')
epoch: 44 test_true_pfm: -0.622566641112955 sim_pfm: -999.9561684727669
episode: 176 training return: tensor(-999.9997, device='cuda:0')
episode: 177 training return: tensor(-999.9996, device='cuda:0')
episode: 178 training return: tensor(-999.9993, device='cuda:0')
episode: 179 training return: tensor(-999.9999, device='cuda:0')
epoch: 45 test_true_pfm: -0.1596419750582002 sim_pfm: -999.956814289093
episode: 180 training return: tensor(-999.9997, device='cuda:0')
episode: 181 training return: tensor(-999.9999, device='cuda:0')
episode: 182 training return: tensor(-999.9998, device='cuda:0')
episode: 183 training return: tensor(-999.9998, device='cuda:0')
epoch: 46 test_true_pfm: -0.35617653577572916 sim_pfm: -999.9558677077293
episode: 184 training return: tensor(-999.9996, device='cuda:0')
episode: 185 training return: tensor(-999.9998, device='cuda:0')
episode: 186 training return: tensor(-999.9999, device='cuda:0')
episode: 187 training return: tensor(-999.9997, device='cuda:0')
epoch: 47 test_true_pfm: -0.5559171121990856 sim_pfm: -999.9547308087349
episode: 188 training return: tensor(-999.9996, device='cuda:0')
episode: 189 training return: tensor(-999.9998, device='cuda:0')
episode: 190 training return: tensor(-999.9997, device='cuda:0')
episode: 191 training return: tensor(-999.9999, device='cuda:0')
epoch: 48 test_true_pfm: -0.7404773338890922 sim_pfm: -999.954407453537
episode: 192 training return: tensor(-999.9996, device='cuda:0')
episode: 193 training return: tensor(-999.9999, device='cuda:0')
episode: 194 training return: tensor(-999.9996, device='cuda:0')
episode: 195 training return: tensor(-999.9994, device='cuda:0')
epoch: 49 test_true_pfm: -0.7917697626776857 sim_pfm: -999.954418182373
episode: 196 training return: tensor(-999.9998, device='cuda:0')
episode: 197 training return: tensor(-999.9996, 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: -0.6722302499737761 sim_pfm: -999.9575294653574
episode: 200 training return: tensor(-999.9995, 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(-999.9988, device='cuda:0')
epoch: 51 test_true_pfm: -0.4241838278313699 sim_pfm: -999.9574786424637
episode: 204 training return: tensor(-999.9996, device='cuda:0')
episode: 205 training return: tensor(-999.9998, device='cuda:0')
episode: 206 training return: tensor(-999.9997, device='cuda:0')
episode: 207 training return: tensor(-999.9996, device='cuda:0')
epoch: 52 test_true_pfm: -1.0618071359765395 sim_pfm: -999.9557925462723
episode: 208 training return: tensor(-999.9996, device='cuda:0')
episode: 209 training return: tensor(-999.9998, device='cuda:0')
episode: 210 training return: tensor(-999.9993, device='cuda:0')
episode: 211 training return: tensor(-999.9996, device='cuda:0')
epoch: 53 test_true_pfm: -0.32046007394158954 sim_pfm: -999.9561648766199
episode: 212 training return: tensor(-999.9995, device='cuda:0')
episode: 213 training return: tensor(-999.9991, device='cuda:0')
episode: 214 training return: tensor(-999.9996, device='cuda:0')
episode: 215 training return: tensor(-999.9997, device='cuda:0')
epoch: 54 test_true_pfm: 0.01587449320896948 sim_pfm: -999.9571843743324
episode: 216 training return: tensor(-999.9998, device='cuda:0')
episode: 217 training return: tensor(-999.9998, device='cuda:0')
episode: 218 training return: tensor(-999.9992, device='cuda:0')
episode: 219 training return: tensor(-999.9999, device='cuda:0')
epoch: 55 test_true_pfm: -0.5280794614389025 sim_pfm: -999.9556897878647
episode: 220 training return: tensor(-999.9995, device='cuda:0')
episode: 221 training return: tensor(-999.9997, device='cuda:0')
episode: 222 training return: tensor(-999.9997, device='cuda:0')
episode: 223 training return: tensor(-999.9996, device='cuda:0')
epoch: 56 test_true_pfm: -0.05262378418910429 sim_pfm: -999.9564283291498
episode: 224 training return: tensor(-999.9995, device='cuda:0')
episode: 225 training return: tensor(-999.9996, device='cuda:0')
episode: 226 training return: tensor(-999.9999, device='cuda:0')
episode: 227 training return: tensor(-999.9996, device='cuda:0')
epoch: 57 test_true_pfm: -0.1951753213054844 sim_pfm: -999.9547686179479
episode: 228 training return: tensor(-999.9999, device='cuda:0')
episode: 229 training return: tensor(-999.9998, device='cuda:0')
episode: 230 training return: tensor(-999.9990, device='cuda:0')
episode: 231 training return: tensor(-999.9996, device='cuda:0')
epoch: 58 test_true_pfm: 0.0007928048704117044 sim_pfm: -999.9557905991873
episode: 232 training return: tensor(-999.9997, device='cuda:0')
episode: 233 training return: tensor(-999.9998, device='cuda:0')
episode: 234 training return: tensor(-999.9999, device='cuda:0')
episode: 235 training return: tensor(-999.9997, device='cuda:0')
epoch: 59 test_true_pfm: -0.6011798173244761 sim_pfm: -999.9569831887881
episode: 236 training return: tensor(-999.9990, device='cuda:0')
episode: 237 training return: tensor(-999.9996, device='cuda:0')
episode: 238 training return: tensor(-999.9993, device='cuda:0')
episode: 239 training return: tensor(-999.9998, device='cuda:0')
epoch: 60 test_true_pfm: -0.8493412937711867 sim_pfm: -999.9562214811643
episode: 240 training return: tensor(-999.9996, device='cuda:0')
episode: 241 training return: tensor(-999.9993, device='cuda:0')
episode: 242 training return: tensor(-999.9998, device='cuda:0')
episode: 243 training return: tensor(-999.9996, device='cuda:0')
epoch: 61 test_true_pfm: -0.4150191831725621 sim_pfm: -999.9561930894852
episode: 244 training return: tensor(-999.9997, device='cuda:0')
episode: 245 training return: tensor(-999.9996, device='cuda:0')
episode: 246 training return: tensor(-999.9993, device='cuda:0')
episode: 247 training return: tensor(-999.9997, device='cuda:0')
epoch: 62 test_true_pfm: -0.7215778751500901 sim_pfm: -999.9546580314636
episode: 248 training return: tensor(-999.9998, device='cuda:0')
episode: 249 training return: tensor(-999.9996, device='cuda:0')
episode: 250 training return: tensor(-999.9996, device='cuda:0')
episode: 251 training return: tensor(-999.9993, device='cuda:0')
epoch: 63 test_true_pfm: 0.2641549322816643 sim_pfm: -999.9550824960073
episode: 252 training return: tensor(-999.9995, device='cuda:0')
episode: 253 training return: tensor(-999.9989, device='cuda:0')
episode: 254 training return: tensor(-999.9999, device='cuda:0')
episode: 255 training return: tensor(-999.9999, device='cuda:0')
epoch: 64 test_true_pfm: -0.9769430006408047 sim_pfm: -999.9565018812815
episode: 256 training return: tensor(-999.9997, device='cuda:0')
episode: 257 training return: tensor(-999.9995, device='cuda:0')
episode: 258 training return: tensor(-999.9997, device='cuda:0')
episode: 259 training return: tensor(-999.9995, device='cuda:0')
epoch: 65 test_true_pfm: -0.4211057746887937 sim_pfm: -999.955671052138
episode: 260 training return: tensor(-999.9995, device='cuda:0')
episode: 261 training return: tensor(-999.9994, device='cuda:0')
episode: 262 training return: tensor(-999.9995, device='cuda:0')
episode: 263 training return: tensor(-999.9996, device='cuda:0')
epoch: 66 test_true_pfm: -0.8659791553742715 sim_pfm: -999.9557893872261
episode: 264 training return: tensor(-999.9999, device='cuda:0')
episode: 265 training return: tensor(-999.9997, device='cuda:0')
episode: 266 training return: tensor(-999.9994, device='cuda:0')
episode: 267 training return: tensor(-999.9998, device='cuda:0')
epoch: 67 test_true_pfm: -0.14176340107572089 sim_pfm: -999.9570290446281
episode: 268 training return: tensor(-999.9996, device='cuda:0')
episode: 269 training return: tensor(-999.9997, device='cuda:0')
episode: 270 training return: tensor(-999.9996, device='cuda:0')
episode: 271 training return: tensor(-999.9997, device='cuda:0')
epoch: 68 test_true_pfm: 0.5927774513051421 sim_pfm: -999.9568373362223
episode: 272 training return: tensor(-999.9997, device='cuda:0')
episode: 273 training return: tensor(-999.9997, device='cuda:0')
episode: 274 training return: tensor(-999.9999, device='cuda:0')
episode: 275 training return: tensor(-999.9993, device='cuda:0')
epoch: 69 test_true_pfm: -1.221278266559436 sim_pfm: -999.957589328289
episode: 276 training return: tensor(-999.9997, device='cuda:0')
episode: 277 training return: tensor(-999.9995, device='cuda:0')
episode: 278 training return: tensor(-999.9999, device='cuda:0')
episode: 279 training return: tensor(-999.9999, device='cuda:0')
epoch: 70 test_true_pfm: -0.25200228415349757 sim_pfm: -999.9556402564049
episode: 280 training return: tensor(-999.9998, device='cuda:0')
episode: 281 training return: tensor(-999.9999, device='cuda:0')
episode: 282 training return: tensor(-999.9996, device='cuda:0')
episode: 283 training return: tensor(-999.9998, device='cuda:0')
epoch: 71 test_true_pfm: 0.06752271796867965 sim_pfm: -999.9549109737078
episode: 284 training return: tensor(-999.9999, device='cuda:0')
episode: 285 training return: tensor(-999.9997, device='cuda:0')
episode: 286 training return: tensor(-999.9997, device='cuda:0')
episode: 287 training return: tensor(-999.9996, device='cuda:0')
epoch: 72 test_true_pfm: -0.23861766086050443 sim_pfm: -999.956454873085
episode: 288 training return: tensor(-999.9999, device='cuda:0')
episode: 289 training return: tensor(-999.9988, device='cuda:0')
episode: 290 training return: tensor(-999.9995, device='cuda:0')
episode: 291 training return: tensor(-999.9997, device='cuda:0')
epoch: 73 test_true_pfm: -0.49610394123781926 sim_pfm: -999.955543577671
episode: 292 training return: tensor(-999.9995, device='cuda:0')
episode: 293 training return: tensor(-999.9996, device='cuda:0')
episode: 294 training return: tensor(-999.9998, device='cuda:0')
episode: 295 training return: tensor(-999.9998, device='cuda:0')
epoch: 74 test_true_pfm: 0.3066976947493613 sim_pfm: -999.9550474087397
episode: 296 training return: tensor(-999.9996, device='cuda:0')
episode: 297 training return: tensor(-999.9998, device='cuda:0')
episode: 298 training return: tensor(-999.9996, device='cuda:0')
episode: 299 training return: tensor(-999.9997, device='cuda:0')
epoch: 75 test_true_pfm: -1.2583654277468037 sim_pfm: -999.9572764635086
episode: 300 training return: tensor(-999.9998, device='cuda:0')
episode: 301 training return: tensor(-999.9990, device='cuda:0')
episode: 302 training return: tensor(-999.9998, device='cuda:0')
episode: 303 training return: tensor(-999.9997, device='cuda:0')
epoch: 76 test_true_pfm: 0.4428720653380222 sim_pfm: -999.9553927779198
episode: 304 training return: tensor(-999.9998, device='cuda:0')
episode: 305 training return: tensor(-999.9996, device='cuda:0')
episode: 306 training return: tensor(-999.9998, device='cuda:0')
episode: 307 training return: tensor(-999.9998, device='cuda:0')
epoch: 77 test_true_pfm: 0.5031107811625523 sim_pfm: -999.9554663101832
episode: 308 training return: tensor(-999.9998, device='cuda:0')
episode: 309 training return: tensor(-999.9985, device='cuda:0')
episode: 310 training return: tensor(-999.9996, device='cuda:0')
episode: 311 training return: tensor(-999.9997, device='cuda:0')
epoch: 78 test_true_pfm: -0.6503849618979887 sim_pfm: -999.9566075801849
episode: 312 training return: tensor(-999.9998, device='cuda:0')
episode: 313 training return: tensor(-999.9999, device='cuda:0')
episode: 314 training return: tensor(-999.9998, device='cuda:0')
episode: 315 training return: tensor(-999.9996, device='cuda:0')
epoch: 79 test_true_pfm: -0.3901459359427267 sim_pfm: -999.9561796784401
episode: 316 training return: tensor(-999.9999, device='cuda:0')
episode: 317 training return: tensor(-999.9996, device='cuda:0')
episode: 318 training return: tensor(-999.9998, device='cuda:0')
episode: 319 training return: tensor(-999.9996, device='cuda:0')
epoch: 80 test_true_pfm: -0.2067580046320189 sim_pfm: -999.9558103680611
episode: 320 training return: tensor(-999.9996, device='cuda:0')
episode: 321 training return: tensor(-999.9995, device='cuda:0')
episode: 322 training return: tensor(-999.9999, device='cuda:0')
episode: 323 training return: tensor(-999.9997, device='cuda:0')
epoch: 81 test_true_pfm: -0.7066769173858692 sim_pfm: -999.9563790361086
episode: 324 training return: tensor(-999.9995, device='cuda:0')
episode: 325 training return: tensor(-999.9997, device='cuda:0')
episode: 326 training return: tensor(-999.9998, device='cuda:0')
episode: 327 training return: tensor(-999.9998, device='cuda:0')
epoch: 82 test_true_pfm: -0.36123215904918554 sim_pfm: -999.9562374750773
episode: 328 training return: tensor(-999.9998, device='cuda:0')
episode: 329 training return: tensor(-999.9997, device='cuda:0')
episode: 330 training return: tensor(-999.9996, device='cuda:0')
episode: 331 training return: tensor(-999.9998, device='cuda:0')
epoch: 83 test_true_pfm: -0.11444760583512777 sim_pfm: -999.9561071793238
episode: 332 training return: tensor(-999.9996, device='cuda:0')
episode: 333 training return: tensor(-999.9997, device='cuda:0')
episode: 334 training return: tensor(-999.9997, device='cuda:0')
episode: 335 training return: tensor(-999.9998, device='cuda:0')
epoch: 84 test_true_pfm: -0.806715060636029 sim_pfm: -999.9572986165682
episode: 336 training return: tensor(-999.9999, device='cuda:0')
episode: 337 training return: tensor(-999.9996, device='cuda:0')
episode: 338 training return: tensor(-999.9998, device='cuda:0')
episode: 339 training return: tensor(-999.9998, device='cuda:0')
epoch: 85 test_true_pfm: -1.0157215278013547 sim_pfm: -999.9570630987486
episode: 340 training return: tensor(-999.9998, device='cuda:0')
episode: 341 training return: tensor(-999.9998, device='cuda:0')
episode: 342 training return: tensor(-999.9998, device='cuda:0')
episode: 343 training return: tensor(-999.9998, device='cuda:0')
epoch: 86 test_true_pfm: -0.5304215016808481 sim_pfm: -999.9554021954536
episode: 344 training return: tensor(-999.9997, device='cuda:0')
episode: 345 training return: tensor(-999.9996, device='cuda:0')
episode: 346 training return: tensor(-999.9996, device='cuda:0')
episode: 347 training return: tensor(-999.9996, device='cuda:0')
epoch: 87 test_true_pfm: -0.19156069817054497 sim_pfm: -999.955868502458
episode: 348 training return: tensor(-999.9998, device='cuda:0')
episode: 349 training return: tensor(-999.9998, device='cuda:0')
episode: 350 training return: tensor(-999.9994, device='cuda:0')
episode: 351 training return: tensor(-999.9998, device='cuda:0')
epoch: 88 test_true_pfm: 0.018849414404139304 sim_pfm: -999.9558285474777
episode: 352 training return: tensor(-999.9996, device='cuda:0')
episode: 353 training return: tensor(-999.9999, device='cuda:0')
episode: 354 training return: tensor(-999.9985, device='cuda:0')
episode: 355 training return: tensor(-999.9999, device='cuda:0')
epoch: 89 test_true_pfm: -0.5616605039457133 sim_pfm: -999.9562440315882
episode: 356 training return: tensor(-999.9997, device='cuda:0')
episode: 357 training return: tensor(-999.9999, device='cuda:0')
episode: 358 training return: tensor(-999.9998, device='cuda:0')
episode: 359 training return: tensor(-999.9998, device='cuda:0')
epoch: 90 test_true_pfm: -1.1670849163320332 sim_pfm: -999.9547741611799
episode: 360 training return: tensor(-999.9996, device='cuda:0')
episode: 361 training return: tensor(-999.9997, device='cuda:0')
episode: 362 training return: tensor(-999.9996, device='cuda:0')
episode: 363 training return: tensor(-999.9994, device='cuda:0')
epoch: 91 test_true_pfm: 0.0937038400438815 sim_pfm: -999.9574029445648
episode: 364 training return: tensor(-999.9997, device='cuda:0')
episode: 365 training return: tensor(-999.9998, device='cuda:0')
episode: 366 training return: tensor(-999.9998, device='cuda:0')
episode: 367 training return: tensor(-999.9985, device='cuda:0')
epoch: 92 test_true_pfm: -0.043613335536998206 sim_pfm: -999.956886947155
episode: 368 training return: tensor(-999.9998, device='cuda:0')
episode: 369 training return: tensor(-999.9995, device='cuda:0')
episode: 370 training return: tensor(-999.9995, device='cuda:0')
episode: 371 training return: tensor(-999.9997, device='cuda:0')
epoch: 93 test_true_pfm: -0.2796762282775925 sim_pfm: -999.9566449920336
episode: 372 training return: tensor(-999.9997, device='cuda:0')
episode: 373 training return: tensor(-999.9993, device='cuda:0')
episode: 374 training return: tensor(-999.9997, device='cuda:0')
episode: 375 training return: tensor(-999.9996, device='cuda:0')
epoch: 94 test_true_pfm: -0.3831060859450453 sim_pfm: -999.9576317270597
episode: 376 training return: tensor(-999.9995, device='cuda:0')
episode: 377 training return: tensor(-999.9996, device='cuda:0')
episode: 378 training return: tensor(-999.9998, device='cuda:0')
episode: 379 training return: tensor(-999.9998, device='cuda:0')
epoch: 95 test_true_pfm: -0.7049332732466397 sim_pfm: -999.95703013738
episode: 380 training return: tensor(-999.9996, device='cuda:0')
episode: 381 training return: tensor(-999.9998, device='cuda:0')
episode: 382 training return: tensor(-999.9995, device='cuda:0')
episode: 383 training return: tensor(-999.9992, device='cuda:0')
epoch: 96 test_true_pfm: -0.5159597484928994 sim_pfm: -999.9559488097826
episode: 384 training return: tensor(-999.9995, device='cuda:0')
episode: 385 training return: tensor(-1000., device='cuda:0')
episode: 386 training return: tensor(-999.9996, device='cuda:0')
episode: 387 training return: tensor(-999.9993, device='cuda:0')
epoch: 97 test_true_pfm: -0.8002468923405178 sim_pfm: -999.9546818137169
episode: 388 training return: tensor(-999.9803, device='cuda:0')
episode: 389 training return: tensor(-999.9997, device='cuda:0')
episode: 390 training return: tensor(-999.9993, device='cuda:0')
episode: 391 training return: tensor(-999.9998, device='cuda:0')
epoch: 98 test_true_pfm: -0.3762804964813158 sim_pfm: -999.9554274479548
episode: 392 training return: tensor(-999.9997, device='cuda:0')
episode: 393 training return: tensor(-999.9999, device='cuda:0')
episode: 394 training return: tensor(-999.9980, device='cuda:0')
episode: 395 training return: tensor(-999.9998, device='cuda:0')
epoch: 99 test_true_pfm: -0.9616682162910175 sim_pfm: -999.9570202231407
episode: 396 training return: tensor(-999.9996, device='cuda:0')
episode: 397 training return: tensor(-999.9995, device='cuda:0')
episode: 398 training return: tensor(-999.9996, device='cuda:0')
episode: 399 training return: tensor(-999.9996, device='cuda:0')
epoch: 100 test_true_pfm: -0.2293119061959175 sim_pfm: -999.9547872145971
episode: 400 training return: tensor(-999.9998, device='cuda:0')
episode: 401 training return: tensor(-999.9998, device='cuda:0')
episode: 402 training return: tensor(-999.9998, device='cuda:0')
episode: 403 training return: tensor(-999.9998, device='cuda:0')
epoch: 101 test_true_pfm: -0.24552623737432686 sim_pfm: -999.9545806050301
episode: 404 training return: tensor(-999.9996, device='cuda:0')
episode: 405 training return: tensor(-999.9999, device='cuda:0')
episode: 406 training return: tensor(-999.9997, device='cuda:0')
episode: 407 training return: tensor(-999.9986, device='cuda:0')
epoch: 102 test_true_pfm: -0.3454131683953044 sim_pfm: -999.9558739066124
episode: 408 training return: tensor(-999.9999, device='cuda:0')
episode: 409 training return: tensor(-999.9996, device='cuda:0')
episode: 410 training return: tensor(-999.9997, device='cuda:0')
episode: 411 training return: tensor(-999.9998, device='cuda:0')
epoch: 103 test_true_pfm: -0.4121136044198585 sim_pfm: -999.9566708008448
episode: 412 training return: tensor(-999.9996, device='cuda:0')
episode: 413 training return: tensor(-999.9999, device='cuda:0')
episode: 414 training return: tensor(-999.9998, device='cuda:0')
episode: 415 training return: tensor(-999.9998, device='cuda:0')
epoch: 104 test_true_pfm: -0.4562494045621384 sim_pfm: -999.9556822180748
episode: 416 training return: tensor(-999.9998, device='cuda:0')
episode: 417 training return: tensor(-999.9998, device='cuda:0')
episode: 418 training return: tensor(-999.9991, device='cuda:0')
episode: 419 training return: tensor(-999.9998, device='cuda:0')
epoch: 105 test_true_pfm: 0.4951821532622643 sim_pfm: -999.9580776294073
episode: 420 training return: tensor(-999.9996, device='cuda:0')
episode: 421 training return: tensor(-999.9996, device='cuda:0')
episode: 422 training return: tensor(-999.9996, device='cuda:0')
episode: 423 training return: tensor(-999.9999, device='cuda:0')
epoch: 106 test_true_pfm: 0.24810136808940939 sim_pfm: -999.9572850863138
episode: 424 training return: tensor(-999.9993, device='cuda:0')
episode: 425 training return: tensor(-999.9997, device='cuda:0')
episode: 426 training return: tensor(-999.9998, device='cuda:0')
episode: 427 training return: tensor(-999.9996, device='cuda:0')
epoch: 107 test_true_pfm: -0.527947556110794 sim_pfm: -999.957383275032
episode: 428 training return: tensor(-999.9996, device='cuda:0')
episode: 429 training return: tensor(-999.9997, device='cuda:0')
episode: 430 training return: tensor(-1000., device='cuda:0')
episode: 431 training return: tensor(-999.9998, device='cuda:0')
epoch: 108 test_true_pfm: -0.3218708104810219 sim_pfm: -999.9561011791229
episode: 432 training return: tensor(-999.9998, device='cuda:0')
episode: 433 training return: tensor(-999.9996, device='cuda:0')
episode: 434 training return: tensor(-999.9997, device='cuda:0')
episode: 435 training return: tensor(-999.9999, device='cuda:0')
epoch: 109 test_true_pfm: -0.048002309409272 sim_pfm: -999.9555749495825
episode: 436 training return: tensor(-999.9994, device='cuda:0')
episode: 437 training return: tensor(-999.9996, device='cuda:0')
episode: 438 training return: tensor(-999.9985, device='cuda:0')
episode: 439 training return: tensor(-999.9998, device='cuda:0')
epoch: 110 test_true_pfm: -0.3052211844957937 sim_pfm: -999.956910610199
episode: 440 training return: tensor(-999.9998, device='cuda:0')
episode: 441 training return: tensor(-999.9995, device='cuda:0')
episode: 442 training return: tensor(-999.9997, device='cuda:0')
episode: 443 training return: tensor(-999.9995, device='cuda:0')
epoch: 111 test_true_pfm: -0.46260564108594626 sim_pfm: -999.9563018083572
episode: 444 training return: tensor(-999.9996, device='cuda:0')
episode: 445 training return: tensor(-999.9996, device='cuda:0')
episode: 446 training return: tensor(-999.9997, device='cuda:0')
episode: 447 training return: tensor(-999.9998, device='cuda:0')
epoch: 112 test_true_pfm: -0.018969193060669503 sim_pfm: -999.9551589290301
episode: 448 training return: tensor(-999.9996, device='cuda:0')
episode: 449 training return: tensor(-999.9998, device='cuda:0')
episode: 450 training return: tensor(-999.9999, device='cuda:0')
episode: 451 training return: tensor(-999.9998, device='cuda:0')
epoch: 113 test_true_pfm: -0.6355669079020232 sim_pfm: -999.9587947328886
episode: 452 training return: tensor(-999.9996, device='cuda:0')
episode: 453 training return: tensor(-999.9999, device='cuda:0')
episode: 454 training return: tensor(-999.9996, device='cuda:0')
episode: 455 training return: tensor(-999.9998, device='cuda:0')
epoch: 114 test_true_pfm: -0.19339897740044307 sim_pfm: -999.9566366871198
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(-999.9995, device='cuda:0')
episode: 459 training return: tensor(-999.9998, device='cuda:0')
epoch: 115 test_true_pfm: 0.20616404371148586 sim_pfm: -999.9575799703598
episode: 460 training return: tensor(-999.9998, device='cuda:0')
episode: 461 training return: tensor(-999.9999, device='cuda:0')
episode: 462 training return: tensor(-999.9997, device='cuda:0')
episode: 463 training return: tensor(-999.9999, device='cuda:0')
epoch: 116 test_true_pfm: -1.0836761197968647 sim_pfm: -999.9553201595942
episode: 464 training return: tensor(-999.9998, device='cuda:0')
episode: 465 training return: tensor(-999.9997, device='cuda:0')
episode: 466 training return: tensor(-999.9991, device='cuda:0')
episode: 467 training return: tensor(-999.9995, device='cuda:0')
epoch: 117 test_true_pfm: -0.18278057443795512 sim_pfm: -999.9569229880968
episode: 468 training return: tensor(-999.9996, device='cuda:0')
episode: 469 training return: tensor(-999.9992, device='cuda:0')
episode: 470 training return: tensor(-999.9998, device='cuda:0')
episode: 471 training return: tensor(-999.9999, device='cuda:0')
epoch: 118 test_true_pfm: -0.2014714649352665 sim_pfm: -999.9561129411062
episode: 472 training return: tensor(-999.9997, device='cuda:0')
episode: 473 training return: tensor(-999.9996, device='cuda:0')
episode: 474 training return: tensor(-999.9998, device='cuda:0')
episode: 475 training return: tensor(-999.9997, device='cuda:0')
epoch: 119 test_true_pfm: -0.27815747264496476 sim_pfm: -999.9570226867994
episode: 476 training return: tensor(-999.9998, device='cuda:0')
episode: 477 training return: tensor(-999.9998, device='cuda:0')
episode: 478 training return: tensor(-999.9996, device='cuda:0')
episode: 479 training return: tensor(-999.9995, device='cuda:0')
epoch: 120 test_true_pfm: -0.14099543300832143 sim_pfm: -999.9568588137627
episode: 480 training return: tensor(-999.9999, device='cuda:0')
episode: 481 training return: tensor(-999.9996, device='cuda:0')
episode: 482 training return: tensor(-999.9999, device='cuda:0')
episode: 483 training return: tensor(-999.9996, device='cuda:0')
epoch: 121 test_true_pfm: -0.6715017119939798 sim_pfm: -999.9543150464693
episode: 484 training return: tensor(-999.9994, device='cuda:0')
episode: 485 training return: tensor(-999.9997, 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: -0.39183626117234166 sim_pfm: -999.9561533729235
episode: 488 training return: tensor(-999.9997, device='cuda:0')
episode: 489 training return: tensor(-999.9997, device='cuda:0')
episode: 490 training return: tensor(-999.9995, device='cuda:0')
episode: 491 training return: tensor(-999.9995, device='cuda:0')
epoch: 123 test_true_pfm: -0.5931478886837002 sim_pfm: -999.9554296930631
episode: 492 training return: tensor(-999.9997, device='cuda:0')
episode: 493 training return: tensor(-999.9974, device='cuda:0')
episode: 494 training return: tensor(-999.9998, device='cuda:0')
episode: 495 training return: tensor(-999.9998, device='cuda:0')
epoch: 124 test_true_pfm: -0.10291028729705166 sim_pfm: -999.9567950169245
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(-999.9991, device='cuda:0')
episode: 499 training return: tensor(-999.9996, device='cuda:0')
epoch: 125 test_true_pfm: -0.1646336066911828 sim_pfm: -999.9555376172066
episode: 500 training return: tensor(-999.9998, device='cuda:0')
episode: 501 training return: tensor(-999.9998, device='cuda:0')
episode: 502 training return: tensor(-999.9996, device='cuda:0')
episode: 503 training return: tensor(-999.9999, device='cuda:0')
epoch: 126 test_true_pfm: -0.26130232075726934 sim_pfm: -999.9560065070788
episode: 504 training return: tensor(-999.9996, 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(-999.9991, device='cuda:0')
epoch: 127 test_true_pfm: -0.4241662780554399 sim_pfm: -999.9575218955675
episode: 508 training return: tensor(-999.9998, device='cuda:0')
episode: 509 training return: tensor(-999.9998, device='cuda:0')
episode: 510 training return: tensor(-999.9996, device='cuda:0')
episode: 511 training return: tensor(-999.9998, device='cuda:0')
epoch: 128 test_true_pfm: 0.203844563123644 sim_pfm: -999.9542651573817
episode: 512 training return: tensor(-999.9997, device='cuda:0')
episode: 513 training return: tensor(-999.9998, device='cuda:0')
episode: 514 training return: tensor(-999.9998, device='cuda:0')
episode: 515 training return: tensor(-999.9999, device='cuda:0')
epoch: 129 test_true_pfm: -0.03258923637143576 sim_pfm: -999.9565715789795
episode: 516 training return: tensor(-999.9997, 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(-999.9995, device='cuda:0')
epoch: 130 test_true_pfm: -0.13380493861927767 sim_pfm: -999.9565000931422
episode: 520 training return: tensor(-999.9998, device='cuda:0')
episode: 521 training return: tensor(-999.9995, device='cuda:0')
episode: 522 training return: tensor(-999.9997, device='cuda:0')
episode: 523 training return: tensor(-999.9995, device='cuda:0')
epoch: 131 test_true_pfm: -0.400462933588622 sim_pfm: -999.955284456412
episode: 524 training return: tensor(-999.9998, device='cuda:0')
episode: 525 training return: tensor(-999.9996, device='cuda:0')
episode: 526 training return: tensor(-999.9998, device='cuda:0')
episode: 527 training return: tensor(-999.9997, device='cuda:0')
epoch: 132 test_true_pfm: -0.8027661156705564 sim_pfm: -999.9583020210266
episode: 528 training return: tensor(-999.9998, device='cuda:0')
episode: 529 training return: tensor(-999.9998, device='cuda:0')
episode: 530 training return: tensor(-999.9996, device='cuda:0')
episode: 531 training return: tensor(-999.9998, device='cuda:0')
epoch: 133 test_true_pfm: -0.47160156035924744 sim_pfm: -999.9549990097681
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(-999.9874, device='cuda:0')
episode: 535 training return: tensor(-999.9998, device='cuda:0')
epoch: 134 test_true_pfm: -0.3213156382602475 sim_pfm: -999.9556757211685
episode: 536 training return: tensor(-999.9994, device='cuda:0')
episode: 537 training return: tensor(-999.9996, device='cuda:0')
episode: 538 training return: tensor(-999.9577, device='cuda:0')
episode: 539 training return: tensor(-999.9996, device='cuda:0')
epoch: 135 test_true_pfm: -0.8649681540325301 sim_pfm: -999.956854323546
episode: 540 training return: tensor(-999.9999, device='cuda:0')
episode: 541 training return: tensor(-999.9990, device='cuda:0')
episode: 542 training return: tensor(-999.9998, device='cuda:0')
episode: 543 training return: tensor(-999.9996, device='cuda:0')
epoch: 136 test_true_pfm: 0.32400480378425356 sim_pfm: -999.9568434755007
episode: 544 training return: tensor(-999.9997, device='cuda:0')
episode: 545 training return: tensor(-999.9992, device='cuda:0')
episode: 546 training return: tensor(-999.9998, device='cuda:0')
episode: 547 training return: tensor(-999.9999, device='cuda:0')
epoch: 137 test_true_pfm: -0.7657662409400917 sim_pfm: -999.9585340420405
episode: 548 training return: tensor(-999.9996, device='cuda:0')
episode: 549 training return: tensor(-999.9996, device='cuda:0')
episode: 550 training return: tensor(-999.9998, device='cuda:0')
episode: 551 training return: tensor(-999.9998, device='cuda:0')
epoch: 138 test_true_pfm: -1.2115754263444927 sim_pfm: -999.9567175507545
episode: 552 training return: tensor(-999.9998, device='cuda:0')
episode: 553 training return: tensor(-999.9998, device='cuda:0')
episode: 554 training return: tensor(-999.9993, device='cuda:0')
episode: 555 training return: tensor(-999.9998, device='cuda:0')
epoch: 139 test_true_pfm: -0.2676446179898802 sim_pfm: -999.9563422997793
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(-999.9998, device='cuda:0')
episode: 559 training return: tensor(-999.9996, device='cuda:0')
epoch: 140 test_true_pfm: -0.41106484705939644 sim_pfm: -999.9549691478411
episode: 560 training return: tensor(-999.9995, device='cuda:0')
episode: 561 training return: tensor(-999.9994, device='cuda:0')
episode: 562 training return: tensor(-999.9994, device='cuda:0')
episode: 563 training return: tensor(-999.9998, device='cuda:0')
epoch: 141 test_true_pfm: -0.5308104320183409 sim_pfm: -999.956673403581
episode: 564 training return: tensor(-999.9998, device='cuda:0')
episode: 565 training return: tensor(-999.9996, device='cuda:0')
episode: 566 training return: tensor(-999.9998, device='cuda:0')
episode: 567 training return: tensor(-999.9996, device='cuda:0')
epoch: 142 test_true_pfm: -0.11624374602179317 sim_pfm: -999.9568355679512
episode: 568 training return: tensor(-999.9996, device='cuda:0')
episode: 569 training return: tensor(-999.9998, device='cuda:0')
episode: 570 training return: tensor(-999.9996, device='cuda:0')
episode: 571 training return: tensor(-999.9999, device='cuda:0')
epoch: 143 test_true_pfm: 0.35181229336769687 sim_pfm: -999.9558005134264
episode: 572 training return: tensor(-999.9992, device='cuda:0')
episode: 573 training return: tensor(-999.9994, device='cuda:0')
episode: 574 training return: tensor(-999.9996, device='cuda:0')
episode: 575 training return: tensor(-999.9998, device='cuda:0')
epoch: 144 test_true_pfm: -0.41003653561770653 sim_pfm: -999.9556122422218
episode: 576 training return: tensor(-999.9996, device='cuda:0')
episode: 577 training return: tensor(-999.9999, device='cuda:0')
episode: 578 training return: tensor(-999.9997, device='cuda:0')
episode: 579 training return: tensor(-999.9999, device='cuda:0')
epoch: 145 test_true_pfm: -0.5260280967306953 sim_pfm: -999.9555831948916
episode: 580 training return: tensor(-999.9998, device='cuda:0')
episode: 581 training return: tensor(-999.9996, device='cuda:0')
episode: 582 training return: tensor(-999.9998, device='cuda:0')
episode: 583 training return: tensor(-999.9998, device='cuda:0')
epoch: 146 test_true_pfm: -0.536377460112652 sim_pfm: -999.9545501271883
episode: 584 training return: tensor(-999.9998, device='cuda:0')
episode: 585 training return: tensor(-999.9995, device='cuda:0')
episode: 586 training return: tensor(-999.9998, device='cuda:0')
episode: 587 training return: tensor(-999.9998, device='cuda:0')
epoch: 147 test_true_pfm: -0.27364615757042715 sim_pfm: -999.9562931656837
episode: 588 training return: tensor(-999.9996, device='cuda:0')
episode: 589 training return: tensor(-999.9995, device='cuda:0')
episode: 590 training return: tensor(-999.9995, device='cuda:0')
episode: 591 training return: tensor(-999.9998, device='cuda:0')
epoch: 148 test_true_pfm: -0.22224150207123924 sim_pfm: -999.9548390309016
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(-999.9991, device='cuda:0')
epoch: 149 test_true_pfm: -0.047662185701565885 sim_pfm: -999.9562370181084
episode: 596 training return: tensor(-999.9997, device='cuda:0')
episode: 597 training return: tensor(-999.9996, device='cuda:0')
episode: 598 training return: tensor(-999.9998, device='cuda:0')
episode: 599 training return: tensor(-999.9988, device='cuda:0')
epoch: 150 test_true_pfm: -0.1218653432906142 sim_pfm: -999.956667582194
