['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'brac', '--traj', 'medium', '--seed', '1', '--data', '100000']
3091.3929548106125
episode: 0 training return: tensor(-9.6442e+18, device='cuda:0')
episode: 1 training return: tensor(-6.7300e+14, device='cuda:0')
episode: 2 training return: tensor(-4.6333e+21, device='cuda:0')
episode: 3 training return: tensor(-1.1037e+21, device='cuda:0')
epoch: 1 test_true_pfm: 46.1269043162177
episode: 4 training return: tensor(-2.3831e+21, device='cuda:0')
episode: 5 training return: tensor(-5.9217e+21, device='cuda:0')
episode: 6 training return: tensor(-1.5929e+21, device='cuda:0')
episode: 7 training return: tensor(-2.7776e+21, device='cuda:0')
epoch: 2 test_true_pfm: 44.680975905428774
episode: 8 training return: tensor(-4.2518e+21, device='cuda:0')
episode: 9 training return: tensor(-2.6111e+21, device='cuda:0')
episode: 10 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 11 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 3 test_true_pfm: 44.73331842456563
episode: 12 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 13 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 14 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 15 training return: tensor(-2.0893e+22, device='cuda:0')
epoch: 4 test_true_pfm: 45.046468751125296
episode: 16 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 17 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 18 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 19 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 5 test_true_pfm: 45.57283050310019
episode: 20 training return: tensor(-2.0908e+22, device='cuda:0')
episode: 21 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 22 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 23 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 6 test_true_pfm: 45.58399451418136
episode: 24 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 25 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 26 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 27 training return: tensor(-2.0895e+22, device='cuda:0')
epoch: 7 test_true_pfm: 45.69251727635776
episode: 28 training return: tensor(-2.0892e+22, device='cuda:0')
episode: 29 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 30 training return: tensor(-2.0893e+22, device='cuda:0')
episode: 31 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 8 test_true_pfm: 42.56259177299018
episode: 32 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 33 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 34 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 35 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 9 test_true_pfm: 44.73779863616522
episode: 36 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 37 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 38 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 39 training return: tensor(-2.0896e+22, device='cuda:0')
epoch: 10 test_true_pfm: 44.515965140440876
episode: 40 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 41 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 42 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 43 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 11 test_true_pfm: 47.03161885967845
episode: 44 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 45 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 46 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 47 training return: tensor(-2.0903e+22, device='cuda:0')
epoch: 12 test_true_pfm: 46.009924043749805
episode: 48 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 49 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 50 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 51 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 13 test_true_pfm: 46.62307863787171
episode: 52 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 53 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 54 training return: tensor(-2.0908e+22, device='cuda:0')
episode: 55 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 14 test_true_pfm: 45.226599348282775
episode: 56 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 57 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 58 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 59 training return: tensor(-2.0904e+22, device='cuda:0')
epoch: 15 test_true_pfm: 45.5571835461788
episode: 60 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 61 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 62 training return: tensor(-2.0893e+22, device='cuda:0')
episode: 63 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 16 test_true_pfm: 45.593466560710205
episode: 64 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 65 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 66 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 67 training return: tensor(-2.0896e+22, device='cuda:0')
epoch: 17 test_true_pfm: 45.44110953479619
episode: 68 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 69 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 70 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 71 training return: tensor(-2.0907e+22, device='cuda:0')
epoch: 18 test_true_pfm: 44.61143786563278
episode: 72 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 73 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 74 training return: tensor(-2.0894e+22, device='cuda:0')
episode: 75 training return: tensor(-2.0904e+22, device='cuda:0')
epoch: 19 test_true_pfm: 44.58657379659854
episode: 76 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 77 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 78 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 79 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 20 test_true_pfm: 45.04553207647373
episode: 80 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 81 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 82 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 83 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 21 test_true_pfm: 45.63329021524388
episode: 84 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 85 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 86 training return: tensor(-2.0908e+22, device='cuda:0')
episode: 87 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 22 test_true_pfm: 44.65024524055854
episode: 88 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 89 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 90 training return: tensor(-2.0893e+22, device='cuda:0')
episode: 91 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 23 test_true_pfm: 44.71825751512545
episode: 92 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 93 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 94 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 95 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 24 test_true_pfm: 45.21817081499727
episode: 96 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 97 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 98 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 99 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 25 test_true_pfm: 43.99257299998391
episode: 100 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 101 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 102 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 103 training return: tensor(-2.0905e+22, device='cuda:0')
epoch: 26 test_true_pfm: 44.78920884823149
episode: 104 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 105 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 106 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 107 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 27 test_true_pfm: 44.72842872218704
episode: 108 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 109 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 110 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 111 training return: tensor(-2.0895e+22, device='cuda:0')
epoch: 28 test_true_pfm: 45.035876916452644
episode: 112 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 113 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 114 training return: tensor(-2.0893e+22, device='cuda:0')
episode: 115 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 29 test_true_pfm: 45.80812234068254
episode: 116 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 117 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 118 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 119 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 30 test_true_pfm: 47.041195950634346
episode: 120 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 121 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 122 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 123 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 31 test_true_pfm: 46.442402435615016
episode: 124 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 125 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 126 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 127 training return: tensor(-2.0904e+22, device='cuda:0')
epoch: 32 test_true_pfm: 47.66692711734245
episode: 128 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 129 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 130 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 131 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 33 test_true_pfm: 44.330614381035566
episode: 132 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 133 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 134 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 135 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 34 test_true_pfm: 46.86888438173268
episode: 136 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 137 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 138 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 139 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 35 test_true_pfm: 45.1184107261476
episode: 140 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 141 training return: tensor(-2.0894e+22, device='cuda:0')
episode: 142 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 143 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 36 test_true_pfm: 45.53097815594248
episode: 144 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 145 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 146 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 147 training return: tensor(-2.0903e+22, device='cuda:0')
epoch: 37 test_true_pfm: 46.26549905416786
episode: 148 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 149 training return: tensor(-2.0893e+22, device='cuda:0')
episode: 150 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 151 training return: tensor(-2.0894e+22, device='cuda:0')
epoch: 38 test_true_pfm: 43.51365220448685
episode: 152 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 153 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 154 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 155 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 39 test_true_pfm: 45.08945132841356
episode: 156 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 157 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 158 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 159 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 40 test_true_pfm: 46.358242174421754
episode: 160 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 161 training return: tensor(-2.0892e+22, device='cuda:0')
episode: 162 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 163 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 41 test_true_pfm: 44.827832823520474
episode: 164 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 165 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 166 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 167 training return: tensor(-2.0894e+22, device='cuda:0')
epoch: 42 test_true_pfm: 45.77348921606768
episode: 168 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 169 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 170 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 171 training return: tensor(-2.0896e+22, device='cuda:0')
epoch: 43 test_true_pfm: 43.54161326561723
episode: 172 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 173 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 174 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 175 training return: tensor(-2.0903e+22, device='cuda:0')
epoch: 44 test_true_pfm: 45.43314650440636
episode: 176 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 177 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 178 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 179 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 45 test_true_pfm: 47.53007051774559
episode: 180 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 181 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 182 training return: tensor(-2.0894e+22, device='cuda:0')
episode: 183 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 46 test_true_pfm: 45.98958081870139
episode: 184 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 185 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 186 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 187 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 47 test_true_pfm: 46.196568090576505
episode: 188 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 189 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 190 training return: tensor(-2.0892e+22, device='cuda:0')
episode: 191 training return: tensor(-2.0892e+22, device='cuda:0')
epoch: 48 test_true_pfm: 45.26944849391276
episode: 192 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 193 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 194 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 195 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 49 test_true_pfm: 46.10934762176231
episode: 196 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 197 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 198 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 199 training return: tensor(-2.0896e+22, device='cuda:0')
epoch: 50 test_true_pfm: 45.77492095702339
episode: 200 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 201 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 202 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 203 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 51 test_true_pfm: 43.51801965725799
episode: 204 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 205 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 206 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 207 training return: tensor(-2.0894e+22, device='cuda:0')
epoch: 52 test_true_pfm: 46.52926904650363
episode: 208 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 209 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 210 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 211 training return: tensor(-2.0894e+22, device='cuda:0')
epoch: 53 test_true_pfm: 44.249938009891444
episode: 212 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 213 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 214 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 215 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 54 test_true_pfm: 45.8858659751891
episode: 216 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 217 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 218 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 219 training return: tensor(-2.0896e+22, device='cuda:0')
epoch: 55 test_true_pfm: 45.80173604230284
episode: 220 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 221 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 222 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 223 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 56 test_true_pfm: 45.04345225546792
episode: 224 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 225 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 226 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 227 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 57 test_true_pfm: 46.13243603098374
episode: 228 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 229 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 230 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 231 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 58 test_true_pfm: 44.82202757685824
episode: 232 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 233 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 234 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 235 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 59 test_true_pfm: 44.552603631446175
episode: 236 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 237 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 238 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 239 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 60 test_true_pfm: 46.21127411515215
episode: 240 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 241 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 242 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 243 training return: tensor(-2.0895e+22, device='cuda:0')
epoch: 61 test_true_pfm: 45.8238272662727
episode: 244 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 245 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 246 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 247 training return: tensor(-2.0903e+22, device='cuda:0')
epoch: 62 test_true_pfm: 44.727572011914795
episode: 248 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 249 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 250 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 251 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 63 test_true_pfm: 44.89913293313177
episode: 252 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 253 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 254 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 255 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 64 test_true_pfm: 46.501352126782734
episode: 256 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 257 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 258 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 259 training return: tensor(-2.0908e+22, device='cuda:0')
epoch: 65 test_true_pfm: 45.92060882453171
episode: 260 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 261 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 262 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 263 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 66 test_true_pfm: 45.507098585746355
episode: 264 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 265 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 266 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 267 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 67 test_true_pfm: 45.337468433658195
episode: 268 training return: tensor(-2.0893e+22, device='cuda:0')
episode: 269 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 270 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 271 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 68 test_true_pfm: 45.32359793060533
episode: 272 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 273 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 274 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 275 training return: tensor(-2.0904e+22, device='cuda:0')
epoch: 69 test_true_pfm: 45.78043489034798
episode: 276 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 277 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 278 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 279 training return: tensor(-2.0906e+22, device='cuda:0')
epoch: 70 test_true_pfm: 44.0517441737613
episode: 280 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 281 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 282 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 283 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 71 test_true_pfm: 45.57330605907456
episode: 284 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 285 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 286 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 287 training return: tensor(-2.0892e+22, device='cuda:0')
epoch: 72 test_true_pfm: 45.82112704407512
episode: 288 training return: tensor(-2.0894e+22, device='cuda:0')
episode: 289 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 290 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 291 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 73 test_true_pfm: 44.61731786371755
episode: 292 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 293 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 294 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 295 training return: tensor(-2.0904e+22, device='cuda:0')
epoch: 74 test_true_pfm: 45.62169068974149
episode: 296 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 297 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 298 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 299 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 75 test_true_pfm: 46.025087278926655
episode: 300 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 301 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 302 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 303 training return: tensor(-2.0895e+22, device='cuda:0')
epoch: 76 test_true_pfm: 44.995930549741125
episode: 304 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 305 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 306 training return: tensor(-2.0894e+22, device='cuda:0')
episode: 307 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 77 test_true_pfm: 46.46132951428202
episode: 308 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 309 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 310 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 311 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 78 test_true_pfm: 45.45877684455161
episode: 312 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 313 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 314 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 315 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 79 test_true_pfm: 46.2272950917675
episode: 316 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 317 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 318 training return: tensor(-2.0891e+22, device='cuda:0')
episode: 319 training return: tensor(-2.0904e+22, device='cuda:0')
epoch: 80 test_true_pfm: 44.257340783840625
episode: 320 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 321 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 322 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 323 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 81 test_true_pfm: 45.5102453617835
episode: 324 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 325 training return: tensor(-2.0893e+22, device='cuda:0')
episode: 326 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 327 training return: tensor(-2.0895e+22, device='cuda:0')
epoch: 82 test_true_pfm: 45.29033001229485
episode: 328 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 329 training return: tensor(-2.0911e+22, device='cuda:0')
episode: 330 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 331 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 83 test_true_pfm: 44.68784663170325
episode: 332 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 333 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 334 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 335 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 84 test_true_pfm: 45.29661629185477
episode: 336 training return: tensor(-2.0894e+22, device='cuda:0')
episode: 337 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 338 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 339 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 85 test_true_pfm: 44.66833634113516
episode: 340 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 341 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 342 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 343 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 86 test_true_pfm: 45.25009655770952
episode: 344 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 345 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 346 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 347 training return: tensor(-2.0895e+22, device='cuda:0')
epoch: 87 test_true_pfm: 46.343488683733234
episode: 348 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 349 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 350 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 351 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 88 test_true_pfm: 45.7808421495132
episode: 352 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 353 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 354 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 355 training return: tensor(-2.0903e+22, device='cuda:0')
epoch: 89 test_true_pfm: 45.23385145879635
episode: 356 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 357 training return: tensor(-2.0893e+22, device='cuda:0')
episode: 358 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 359 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 90 test_true_pfm: 46.797790541083124
episode: 360 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 361 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 362 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 363 training return: tensor(-2.0895e+22, device='cuda:0')
epoch: 91 test_true_pfm: 45.628092689040734
episode: 364 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 365 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 366 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 367 training return: tensor(-2.0903e+22, device='cuda:0')
epoch: 92 test_true_pfm: 45.17462644359137
episode: 368 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 369 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 370 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 371 training return: tensor(-2.0906e+22, device='cuda:0')
epoch: 93 test_true_pfm: 43.24069250834153
episode: 372 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 373 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 374 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 375 training return: tensor(-2.0895e+22, device='cuda:0')
epoch: 94 test_true_pfm: 45.86708646566785
episode: 376 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 377 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 378 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 379 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 95 test_true_pfm: 45.819803889338495
episode: 380 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 381 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 382 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 383 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 96 test_true_pfm: 47.55615728871968
episode: 384 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 385 training return: tensor(-2.0894e+22, device='cuda:0')
episode: 386 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 387 training return: tensor(-2.0903e+22, device='cuda:0')
epoch: 97 test_true_pfm: 45.51455000152573
episode: 388 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 389 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 390 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 391 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 98 test_true_pfm: 46.11697473756132
episode: 392 training return: tensor(-2.0890e+22, device='cuda:0')
episode: 393 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 394 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 395 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 99 test_true_pfm: 46.603498352509376
episode: 396 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 397 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 398 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 399 training return: tensor(-2.0906e+22, device='cuda:0')
epoch: 100 test_true_pfm: 45.028557376738696
episode: 400 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 401 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 402 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 403 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 101 test_true_pfm: 44.80337372514085
episode: 404 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 405 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 406 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 407 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 102 test_true_pfm: 43.39202705007414
episode: 408 training return: tensor(-2.0894e+22, device='cuda:0')
episode: 409 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 410 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 411 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 103 test_true_pfm: 46.66508027471699
episode: 412 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 413 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 414 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 415 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 104 test_true_pfm: 46.5276127988195
episode: 416 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 417 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 418 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 419 training return: tensor(-2.0896e+22, device='cuda:0')
epoch: 105 test_true_pfm: 45.66108352232053
episode: 420 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 421 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 422 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 423 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 106 test_true_pfm: 43.664842380573496
episode: 424 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 425 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 426 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 427 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 107 test_true_pfm: 46.2051511376503
episode: 428 training return: tensor(-2.0909e+22, device='cuda:0')
episode: 429 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 430 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 431 training return: tensor(-2.0896e+22, device='cuda:0')
epoch: 108 test_true_pfm: 46.06090769904847
episode: 432 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 433 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 434 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 435 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 109 test_true_pfm: 46.06471065218336
episode: 436 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 437 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 438 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 439 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 110 test_true_pfm: 45.39979288383702
episode: 440 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 441 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 442 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 443 training return: tensor(-2.0893e+22, device='cuda:0')
epoch: 111 test_true_pfm: 47.28024965865211
episode: 444 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 445 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 446 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 447 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 112 test_true_pfm: 47.5451181810999
episode: 448 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 449 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 450 training return: tensor(-2.0907e+22, device='cuda:0')
episode: 451 training return: tensor(-2.0896e+22, device='cuda:0')
epoch: 113 test_true_pfm: 46.56827901681397
episode: 452 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 453 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 454 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 455 training return: tensor(-2.0896e+22, device='cuda:0')
epoch: 114 test_true_pfm: 45.89479956806675
episode: 456 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 457 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 458 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 459 training return: tensor(-2.0898e+22, device='cuda:0')
epoch: 115 test_true_pfm: 44.14399780001332
episode: 460 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 461 training return: tensor(-2.0908e+22, device='cuda:0')
episode: 462 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 463 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 116 test_true_pfm: 46.136073263886665
episode: 464 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 465 training return: tensor(-2.0907e+22, device='cuda:0')
episode: 466 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 467 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 117 test_true_pfm: 43.11820093147463
episode: 468 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 469 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 470 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 471 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 118 test_true_pfm: 45.72690258516777
episode: 472 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 473 training return: tensor(-2.0892e+22, device='cuda:0')
episode: 474 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 475 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 119 test_true_pfm: 46.198514778207006
episode: 476 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 477 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 478 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 479 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 120 test_true_pfm: 46.12042758847881
episode: 480 training return: tensor(-2.0894e+22, device='cuda:0')
episode: 481 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 482 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 483 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 121 test_true_pfm: 44.75306081617325
episode: 484 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 485 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 486 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 487 training return: tensor(-2.0895e+22, device='cuda:0')
epoch: 122 test_true_pfm: 46.84610153734557
episode: 488 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 489 training return: tensor(-2.0907e+22, device='cuda:0')
episode: 490 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 491 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 123 test_true_pfm: 46.218368447041975
episode: 492 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 493 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 494 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 495 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 124 test_true_pfm: 43.61888776717416
episode: 496 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 497 training return: tensor(-2.0895e+22, device='cuda:0')
episode: 498 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 499 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 125 test_true_pfm: 46.35855848633665
episode: 500 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 501 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 502 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 503 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 126 test_true_pfm: 44.967576651808116
episode: 504 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 505 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 506 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 507 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 127 test_true_pfm: 43.574044355759895
episode: 508 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 509 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 510 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 511 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 128 test_true_pfm: 44.99459908014675
episode: 512 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 513 training return: tensor(-2.0893e+22, device='cuda:0')
episode: 514 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 515 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 129 test_true_pfm: 45.28195455485868
episode: 516 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 517 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 518 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 519 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 130 test_true_pfm: 43.39581789173161
episode: 520 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 521 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 522 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 523 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 131 test_true_pfm: 45.54128236305968
episode: 524 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 525 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 526 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 527 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 132 test_true_pfm: 45.80709071075978
episode: 528 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 529 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 530 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 531 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 133 test_true_pfm: 46.12069209730768
episode: 532 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 533 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 534 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 535 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 134 test_true_pfm: 45.735165340115095
episode: 536 training return: tensor(-2.0896e+22, device='cuda:0')
episode: 537 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 538 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 539 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 135 test_true_pfm: 45.24236757415871
episode: 540 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 541 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 542 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 543 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 136 test_true_pfm: 45.26487029949838
episode: 544 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 545 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 546 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 547 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 137 test_true_pfm: 45.36727453837718
episode: 548 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 549 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 550 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 551 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 138 test_true_pfm: 43.407856847481185
episode: 552 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 553 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 554 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 555 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 139 test_true_pfm: 46.17712267778331
episode: 556 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 557 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 558 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 559 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 140 test_true_pfm: 44.993929863414344
episode: 560 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 561 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 562 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 563 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 141 test_true_pfm: 47.303059451876855
episode: 564 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 565 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 566 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 567 training return: tensor(-2.0903e+22, device='cuda:0')
epoch: 142 test_true_pfm: 44.76990000390078
episode: 568 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 569 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 570 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 571 training return: tensor(-2.0904e+22, device='cuda:0')
epoch: 143 test_true_pfm: 44.18187150994513
episode: 572 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 573 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 574 training return: tensor(-2.0903e+22, device='cuda:0')
episode: 575 training return: tensor(-2.0901e+22, device='cuda:0')
epoch: 144 test_true_pfm: 45.662623792174195
episode: 576 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 577 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 578 training return: tensor(-2.0899e+22, device='cuda:0')
episode: 579 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 145 test_true_pfm: 45.272771765462316
episode: 580 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 581 training return: tensor(-2.0905e+22, device='cuda:0')
episode: 582 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 583 training return: tensor(-2.0902e+22, device='cuda:0')
epoch: 146 test_true_pfm: 46.784495685604575
episode: 584 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 585 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 586 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 587 training return: tensor(-2.0899e+22, device='cuda:0')
epoch: 147 test_true_pfm: 44.310715148559716
episode: 588 training return: tensor(-2.0901e+22, device='cuda:0')
episode: 589 training return: tensor(-2.0906e+22, device='cuda:0')
episode: 590 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 591 training return: tensor(-2.0897e+22, device='cuda:0')
epoch: 148 test_true_pfm: 46.03343622149239
episode: 592 training return: tensor(-2.0897e+22, device='cuda:0')
episode: 593 training return: tensor(-2.0904e+22, device='cuda:0')
episode: 594 training return: tensor(-2.0900e+22, device='cuda:0')
episode: 595 training return: tensor(-2.0903e+22, device='cuda:0')
epoch: 149 test_true_pfm: 44.317459122787454
episode: 596 training return: tensor(-2.0902e+22, device='cuda:0')
episode: 597 training return: tensor(-2.0908e+22, device='cuda:0')
episode: 598 training return: tensor(-2.0898e+22, device='cuda:0')
episode: 599 training return: tensor(-2.0900e+22, device='cuda:0')
epoch: 150 test_true_pfm: 46.299340846897934
