['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '1']
episode: 0 training return: tensor(-614.9269, device='cuda:0')
episode: 1 training return: tensor(-572.3304, device='cuda:0')
episode: 2 training return: tensor(-551.4202, device='cuda:0')
episode: 3 training return: tensor(-513.0956, device='cuda:0')
epoch: 1 test_true_pfm: 35.48539454874793 sim_pfm: -679.7922297120094
episode: 4 training return: tensor(-632.3658, device='cuda:0')
episode: 5 training return: tensor(-701.7815, device='cuda:0')
episode: 6 training return: tensor(-673.0518, device='cuda:0')
episode: 7 training return: tensor(-524.3759, device='cuda:0')
epoch: 2 test_true_pfm: -102.89476307551229 sim_pfm: -562.3561533987522
episode: 8 training return: tensor(-582.6927, device='cuda:0')
episode: 9 training return: tensor(-680.0209, device='cuda:0')
episode: 10 training return: tensor(-731.6739, device='cuda:0')
episode: 11 training return: tensor(-537.7449, device='cuda:0')
epoch: 3 test_true_pfm: -211.60567017384938 sim_pfm: -504.77257996145636
episode: 12 training return: tensor(-576.7346, device='cuda:0')
episode: 13 training return: tensor(-737.5485, device='cuda:0')
episode: 14 training return: tensor(-721.8270, device='cuda:0')
episode: 15 training return: tensor(-762.6996, device='cuda:0')
epoch: 4 test_true_pfm: -92.00731649161229 sim_pfm: -653.3601704786221
episode: 16 training return: tensor(-598.8328, device='cuda:0')
episode: 17 training return: tensor(-522.7245, device='cuda:0')
episode: 18 training return: tensor(-531.0725, device='cuda:0')
episode: 19 training return: tensor(-511.7612, device='cuda:0')
epoch: 5 test_true_pfm: 44.17035483608211 sim_pfm: -694.2006245062997
episode: 20 training return: tensor(-785.9362, device='cuda:0')
episode: 21 training return: tensor(-757.6097, device='cuda:0')
episode: 22 training return: tensor(-650.4585, device='cuda:0')
episode: 23 training return: tensor(-750.5606, device='cuda:0')
epoch: 6 test_true_pfm: 119.02267235935126 sim_pfm: -536.0760750671228
episode: 24 training return: tensor(-656.8339, device='cuda:0')
episode: 25 training return: tensor(-450.7433, device='cuda:0')
episode: 26 training return: tensor(-555.6120, device='cuda:0')
episode: 27 training return: tensor(-526.3190, device='cuda:0')
epoch: 7 test_true_pfm: -71.34961693970446 sim_pfm: -592.3112053188185
episode: 28 training return: tensor(-694.6971, device='cuda:0')
episode: 29 training return: tensor(-677.9760, device='cuda:0')
episode: 30 training return: tensor(-470.7946, device='cuda:0')
episode: 31 training return: tensor(-664.7237, device='cuda:0')
epoch: 8 test_true_pfm: 160.73889803860746 sim_pfm: -659.2806195636222
episode: 32 training return: tensor(-673.1244, device='cuda:0')
episode: 33 training return: tensor(-468.5861, device='cuda:0')
episode: 34 training return: tensor(-642.5209, device='cuda:0')
episode: 35 training return: tensor(-627.3105, device='cuda:0')
epoch: 9 test_true_pfm: 43.44290681007627 sim_pfm: -516.9365195901677
episode: 36 training return: tensor(-508.5327, device='cuda:0')
episode: 37 training return: tensor(-581.7833, device='cuda:0')
episode: 38 training return: tensor(-420.1895, device='cuda:0')
episode: 39 training return: tensor(-585.4163, device='cuda:0')
epoch: 10 test_true_pfm: 168.93520662954063 sim_pfm: -651.1904042027891
episode: 40 training return: tensor(-516.7666, device='cuda:0')
episode: 41 training return: tensor(-393.9530, device='cuda:0')
episode: 42 training return: tensor(-392.0221, device='cuda:0')
episode: 43 training return: tensor(-564.2237, device='cuda:0')
epoch: 11 test_true_pfm: 104.29332036955627 sim_pfm: -406.8464705723648
episode: 44 training return: tensor(-379.4637, device='cuda:0')
episode: 45 training return: tensor(-462.5765, device='cuda:0')
episode: 46 training return: tensor(-510.2912, device='cuda:0')
episode: 47 training return: tensor(-354.2032, device='cuda:0')
epoch: 12 test_true_pfm: 126.69292002302895 sim_pfm: -583.5025301724672
episode: 48 training return: tensor(-458.7507, device='cuda:0')
episode: 49 training return: tensor(-464.3560, device='cuda:0')
episode: 50 training return: tensor(-476.3817, device='cuda:0')
episode: 51 training return: tensor(-410.7346, device='cuda:0')
epoch: 13 test_true_pfm: 190.95932722811486 sim_pfm: -417.0044925871771
episode: 52 training return: tensor(-543.5732, device='cuda:0')
episode: 53 training return: tensor(-431.1143, device='cuda:0')
episode: 54 training return: tensor(-453.1695, device='cuda:0')
episode: 55 training return: tensor(-762.4081, device='cuda:0')
epoch: 14 test_true_pfm: 58.491086930436474 sim_pfm: -476.77512588935014
episode: 56 training return: tensor(-464.3506, device='cuda:0')
episode: 57 training return: tensor(-408.8504, device='cuda:0')
episode: 58 training return: tensor(-447.1216, device='cuda:0')
episode: 59 training return: tensor(-429.1046, device='cuda:0')
epoch: 15 test_true_pfm: 132.18690420409504 sim_pfm: -372.53027836282854
episode: 60 training return: tensor(-367.7933, device='cuda:0')
episode: 61 training return: tensor(-408.7377, device='cuda:0')
episode: 62 training return: tensor(-455.0719, device='cuda:0')
episode: 63 training return: tensor(-589.2682, device='cuda:0')
epoch: 16 test_true_pfm: 96.56918517136477 sim_pfm: -382.329325570104
episode: 64 training return: tensor(-453.2203, device='cuda:0')
episode: 65 training return: tensor(-423.0706, device='cuda:0')
episode: 66 training return: tensor(-418.3095, device='cuda:0')
episode: 67 training return: tensor(-410.4336, device='cuda:0')
epoch: 17 test_true_pfm: 36.189560426626564 sim_pfm: -393.86530942008056
episode: 68 training return: tensor(-393.1866, device='cuda:0')
episode: 69 training return: tensor(-332.4472, device='cuda:0')
episode: 70 training return: tensor(-374.2524, device='cuda:0')
episode: 71 training return: tensor(-427.0118, device='cuda:0')
epoch: 18 test_true_pfm: 117.64766784870574 sim_pfm: -382.8864002368161
episode: 72 training return: tensor(-439.1459, device='cuda:0')
episode: 73 training return: tensor(-385.7750, device='cuda:0')
episode: 74 training return: tensor(-457.8993, device='cuda:0')
episode: 75 training return: tensor(-387.7679, device='cuda:0')
epoch: 19 test_true_pfm: 111.96212428979983 sim_pfm: -395.879225694264
episode: 76 training return: tensor(-396.7013, device='cuda:0')
episode: 77 training return: tensor(-450.6301, device='cuda:0')
episode: 78 training return: tensor(-376.2976, device='cuda:0')
episode: 79 training return: tensor(-433.4816, device='cuda:0')
epoch: 20 test_true_pfm: 55.219070192299945 sim_pfm: -388.0489370099579
episode: 80 training return: tensor(-444.5312, device='cuda:0')
episode: 81 training return: tensor(-446.6258, device='cuda:0')
episode: 82 training return: tensor(-447.9161, device='cuda:0')
episode: 83 training return: tensor(-410.0345, device='cuda:0')
epoch: 21 test_true_pfm: 206.9639474416632 sim_pfm: -341.64189696269267
episode: 84 training return: tensor(-398.3260, device='cuda:0')
episode: 85 training return: tensor(-436.4122, device='cuda:0')
episode: 86 training return: tensor(-396.4506, device='cuda:0')
episode: 87 training return: tensor(-423.5963, device='cuda:0')
epoch: 22 test_true_pfm: 81.20576744539197 sim_pfm: -347.29661808970076
episode: 88 training return: tensor(-432.9622, device='cuda:0')
episode: 89 training return: tensor(-435.2217, device='cuda:0')
episode: 90 training return: tensor(-387.8781, device='cuda:0')
episode: 91 training return: tensor(-441.4601, device='cuda:0')
epoch: 23 test_true_pfm: 290.1366134955055 sim_pfm: -328.9027227717452
episode: 92 training return: tensor(-442.1743, device='cuda:0')
episode: 93 training return: tensor(-450.1271, device='cuda:0')
episode: 94 training return: tensor(-394.6121, device='cuda:0')
episode: 95 training return: tensor(-376.9223, device='cuda:0')
epoch: 24 test_true_pfm: 62.64550712717672 sim_pfm: -400.5697780516154
episode: 96 training return: tensor(-410.3298, device='cuda:0')
episode: 97 training return: tensor(-446.8381, device='cuda:0')
episode: 98 training return: tensor(-391.3271, device='cuda:0')
episode: 99 training return: tensor(-447.8025, device='cuda:0')
epoch: 25 test_true_pfm: 33.3440434178497 sim_pfm: -352.6857793557768
episode: 100 training return: tensor(-419.4131, device='cuda:0')
episode: 101 training return: tensor(-404.4368, device='cuda:0')
episode: 102 training return: tensor(-394.3938, device='cuda:0')
episode: 103 training return: tensor(-366.2197, device='cuda:0')
epoch: 26 test_true_pfm: 194.82031069272372 sim_pfm: -365.0931450273686
episode: 104 training return: tensor(-379.7720, device='cuda:0')
episode: 105 training return: tensor(-404.0927, device='cuda:0')
episode: 106 training return: tensor(-393.5886, device='cuda:0')
episode: 107 training return: tensor(-374.8454, device='cuda:0')
epoch: 27 test_true_pfm: 189.81953668453335 sim_pfm: -343.63685509308317
episode: 108 training return: tensor(-388.5386, device='cuda:0')
episode: 109 training return: tensor(-391.7838, device='cuda:0')
episode: 110 training return: tensor(-326.8633, device='cuda:0')
episode: 111 training return: tensor(-467.2804, device='cuda:0')
epoch: 28 test_true_pfm: 258.4482812857926 sim_pfm: -347.4178818327685
episode: 112 training return: tensor(-437.4526, device='cuda:0')
episode: 113 training return: tensor(-383.0283, device='cuda:0')
episode: 114 training return: tensor(-371.0190, device='cuda:0')
episode: 115 training return: tensor(-417.1957, device='cuda:0')
epoch: 29 test_true_pfm: 279.1931622728783 sim_pfm: -349.6296577908021
episode: 116 training return: tensor(-370.0253, device='cuda:0')
episode: 117 training return: tensor(-381.6285, device='cuda:0')
episode: 118 training return: tensor(-394.0462, device='cuda:0')
episode: 119 training return: tensor(-412.1547, device='cuda:0')
epoch: 30 test_true_pfm: 29.322742089463485 sim_pfm: -376.6197280938116
episode: 120 training return: tensor(-351.6105, device='cuda:0')
episode: 121 training return: tensor(-416.1556, device='cuda:0')
episode: 122 training return: tensor(-390.7573, device='cuda:0')
episode: 123 training return: tensor(-414.5793, device='cuda:0')
epoch: 31 test_true_pfm: 241.88392104891878 sim_pfm: -350.0181814053406
episode: 124 training return: tensor(-426.9753, device='cuda:0')
episode: 125 training return: tensor(-447.1590, device='cuda:0')
episode: 126 training return: tensor(-392.0674, device='cuda:0')
episode: 127 training return: tensor(-383.3556, device='cuda:0')
epoch: 32 test_true_pfm: 106.43231760194315 sim_pfm: -387.6233523764531
episode: 128 training return: tensor(-430.0844, device='cuda:0')
episode: 129 training return: tensor(-606.0923, device='cuda:0')
episode: 130 training return: tensor(-402.5191, device='cuda:0')
episode: 131 training return: tensor(-426.0977, device='cuda:0')
epoch: 33 test_true_pfm: 136.46144920553348 sim_pfm: -364.40188255448203
episode: 132 training return: tensor(-385.5317, device='cuda:0')
episode: 133 training return: tensor(-411.3254, device='cuda:0')
episode: 134 training return: tensor(-458.1738, device='cuda:0')
episode: 135 training return: tensor(-409.7253, device='cuda:0')
epoch: 34 test_true_pfm: 262.40585699740126 sim_pfm: -319.35488181588397
episode: 136 training return: tensor(-436.7101, device='cuda:0')
episode: 137 training return: tensor(-403.0326, device='cuda:0')
episode: 138 training return: tensor(-418.3881, device='cuda:0')
episode: 139 training return: tensor(-462.1398, device='cuda:0')
epoch: 35 test_true_pfm: 202.40994824707698 sim_pfm: -309.41986677318346
episode: 140 training return: tensor(-410.9142, device='cuda:0')
episode: 141 training return: tensor(-396.2684, device='cuda:0')
episode: 142 training return: tensor(-412.5987, device='cuda:0')
episode: 143 training return: tensor(-431.5054, device='cuda:0')
epoch: 36 test_true_pfm: 220.58908368786413 sim_pfm: -349.3474115265223
episode: 144 training return: tensor(-396.1961, device='cuda:0')
episode: 145 training return: tensor(-389.3477, device='cuda:0')
episode: 146 training return: tensor(-399.8547, device='cuda:0')
episode: 147 training return: tensor(-427.1621, device='cuda:0')
epoch: 37 test_true_pfm: 115.73473206702295 sim_pfm: -339.4302331792812
episode: 148 training return: tensor(-422.4365, device='cuda:0')
episode: 149 training return: tensor(-361.2679, device='cuda:0')
episode: 150 training return: tensor(-400.0842, device='cuda:0')
episode: 151 training return: tensor(-427.6877, device='cuda:0')
epoch: 38 test_true_pfm: 168.77645172341695 sim_pfm: -342.0726256052246
episode: 152 training return: tensor(-459.7024, device='cuda:0')
episode: 153 training return: tensor(-393.8114, device='cuda:0')
episode: 154 training return: tensor(-398.6607, device='cuda:0')
episode: 155 training return: tensor(-398.8862, device='cuda:0')
epoch: 39 test_true_pfm: 318.61087071493677 sim_pfm: -326.8891610659387
episode: 156 training return: tensor(-417.9558, device='cuda:0')
episode: 157 training return: tensor(-387.4709, device='cuda:0')
episode: 158 training return: tensor(-396.4185, device='cuda:0')
episode: 159 training return: tensor(-395.6856, device='cuda:0')
epoch: 40 test_true_pfm: 156.49721183726885 sim_pfm: -328.0197427323631
episode: 160 training return: tensor(-413.9525, device='cuda:0')
episode: 161 training return: tensor(-377.2916, device='cuda:0')
episode: 162 training return: tensor(-397.9490, device='cuda:0')
episode: 163 training return: tensor(-372.5768, device='cuda:0')
epoch: 41 test_true_pfm: 23.85959654635387 sim_pfm: -356.2709253008167
episode: 164 training return: tensor(-388.8553, device='cuda:0')
episode: 165 training return: tensor(-381.1640, device='cuda:0')
episode: 166 training return: tensor(-402.4838, device='cuda:0')
episode: 167 training return: tensor(-415.4861, device='cuda:0')
epoch: 42 test_true_pfm: 73.49925332544245 sim_pfm: -315.76951421741006
episode: 168 training return: tensor(-391.2696, device='cuda:0')
episode: 169 training return: tensor(-414.2904, device='cuda:0')
episode: 170 training return: tensor(-408.2669, device='cuda:0')
episode: 171 training return: tensor(-385.8074, device='cuda:0')
epoch: 43 test_true_pfm: 34.345920160680976 sim_pfm: -322.8082120240045
episode: 172 training return: tensor(-409.5787, device='cuda:0')
episode: 173 training return: tensor(-371.7205, device='cuda:0')
episode: 174 training return: tensor(-386.6619, device='cuda:0')
episode: 175 training return: tensor(-405.5232, device='cuda:0')
epoch: 44 test_true_pfm: -11.417147310678518 sim_pfm: -371.77352772063267
episode: 176 training return: tensor(-378.3213, device='cuda:0')
episode: 177 training return: tensor(-379.0007, device='cuda:0')
episode: 178 training return: tensor(-355.3026, device='cuda:0')
episode: 179 training return: tensor(-395.1395, device='cuda:0')
epoch: 45 test_true_pfm: 207.94123662832803 sim_pfm: -354.3742240741655
episode: 180 training return: tensor(-496.1334, device='cuda:0')
episode: 181 training return: tensor(-452.3780, device='cuda:0')
episode: 182 training return: tensor(-425.4746, device='cuda:0')
episode: 183 training return: tensor(-385.5852, device='cuda:0')
epoch: 46 test_true_pfm: 147.6225233858473 sim_pfm: -343.65709108750644
episode: 184 training return: tensor(-455.4996, device='cuda:0')
episode: 185 training return: tensor(-426.7747, device='cuda:0')
episode: 186 training return: tensor(-450.1667, device='cuda:0')
episode: 187 training return: tensor(-396.0894, device='cuda:0')
epoch: 47 test_true_pfm: 166.814677606978 sim_pfm: -362.18204232652596
episode: 188 training return: tensor(-401.5061, device='cuda:0')
episode: 189 training return: tensor(-436.5383, device='cuda:0')
episode: 190 training return: tensor(-406.0428, device='cuda:0')
episode: 191 training return: tensor(-410.9364, device='cuda:0')
epoch: 48 test_true_pfm: 21.26674464029359 sim_pfm: -351.5886805408906
episode: 192 training return: tensor(-369.4451, device='cuda:0')
episode: 193 training return: tensor(-409.1660, device='cuda:0')
episode: 194 training return: tensor(-422.0025, device='cuda:0')
episode: 195 training return: tensor(-384.0912, device='cuda:0')
epoch: 49 test_true_pfm: 220.33566393251726 sim_pfm: -342.00622002093587
episode: 196 training return: tensor(-426.6996, device='cuda:0')
episode: 197 training return: tensor(-402.3876, device='cuda:0')
episode: 198 training return: tensor(-458.9326, device='cuda:0')
episode: 199 training return: tensor(-398.9226, device='cuda:0')
epoch: 50 test_true_pfm: 279.28370837026654 sim_pfm: -358.31039377930574
episode: 200 training return: tensor(-394.5172, device='cuda:0')
episode: 201 training return: tensor(-396.3173, device='cuda:0')
episode: 202 training return: tensor(-384.0992, device='cuda:0')
episode: 203 training return: tensor(-399.6148, device='cuda:0')
epoch: 51 test_true_pfm: 34.685018888103876 sim_pfm: -342.0676903631732
episode: 204 training return: tensor(-375.7230, device='cuda:0')
episode: 205 training return: tensor(-406.5934, device='cuda:0')
episode: 206 training return: tensor(-461.1193, device='cuda:0')
episode: 207 training return: tensor(-425.9059, device='cuda:0')
epoch: 52 test_true_pfm: 153.67421059440937 sim_pfm: -346.6636966887163
episode: 208 training return: tensor(-407.7213, device='cuda:0')
episode: 209 training return: tensor(-415.5533, device='cuda:0')
episode: 210 training return: tensor(-397.1036, device='cuda:0')
episode: 211 training return: tensor(-416.3988, device='cuda:0')
epoch: 53 test_true_pfm: 121.79854519272529 sim_pfm: -387.523846997569
episode: 212 training return: tensor(-395.8134, device='cuda:0')
episode: 213 training return: tensor(-391.1039, device='cuda:0')
episode: 214 training return: tensor(-394.1865, device='cuda:0')
episode: 215 training return: tensor(-398.7591, device='cuda:0')
epoch: 54 test_true_pfm: 247.28461597739897 sim_pfm: -359.3145767946844
episode: 216 training return: tensor(-452.2935, device='cuda:0')
episode: 217 training return: tensor(-391.4370, device='cuda:0')
episode: 218 training return: tensor(-381.5464, device='cuda:0')
episode: 219 training return: tensor(-438.1283, device='cuda:0')
epoch: 55 test_true_pfm: 107.1000401256642 sim_pfm: -341.5522401702862
episode: 220 training return: tensor(-370.1973, device='cuda:0')
episode: 221 training return: tensor(-399.8765, device='cuda:0')
episode: 222 training return: tensor(-379.4580, device='cuda:0')
episode: 223 training return: tensor(-384.9112, device='cuda:0')
epoch: 56 test_true_pfm: 301.7485637469042 sim_pfm: -342.7553954415683
episode: 224 training return: tensor(-380.7227, device='cuda:0')
episode: 225 training return: tensor(-351.8230, device='cuda:0')
episode: 226 training return: tensor(-399.3391, device='cuda:0')
episode: 227 training return: tensor(-377.8335, device='cuda:0')
epoch: 57 test_true_pfm: 155.2414909355991 sim_pfm: -356.26363817338523
episode: 228 training return: tensor(-369.5764, device='cuda:0')
episode: 229 training return: tensor(-417.9283, device='cuda:0')
episode: 230 training return: tensor(-429.9981, device='cuda:0')
episode: 231 training return: tensor(-432.1456, device='cuda:0')
epoch: 58 test_true_pfm: 230.28637915582155 sim_pfm: -336.4824044502845
episode: 232 training return: tensor(-369.4445, device='cuda:0')
episode: 233 training return: tensor(-409.9203, device='cuda:0')
episode: 234 training return: tensor(-389.0919, device='cuda:0')
episode: 235 training return: tensor(-364.1653, device='cuda:0')
epoch: 59 test_true_pfm: 212.9618512743361 sim_pfm: -361.19522794685327
episode: 236 training return: tensor(-378.4927, device='cuda:0')
episode: 237 training return: tensor(-398.1591, device='cuda:0')
episode: 238 training return: tensor(-422.1671, device='cuda:0')
episode: 239 training return: tensor(-411.3093, device='cuda:0')
epoch: 60 test_true_pfm: 161.77064319858394 sim_pfm: -339.8513315783348
episode: 240 training return: tensor(-440.8474, device='cuda:0')
episode: 241 training return: tensor(-395.6842, device='cuda:0')
episode: 242 training return: tensor(-391.3855, device='cuda:0')
episode: 243 training return: tensor(-348.9439, device='cuda:0')
epoch: 61 test_true_pfm: 221.20181826804927 sim_pfm: -319.15074653341435
episode: 244 training return: tensor(-396.2731, device='cuda:0')
episode: 245 training return: tensor(-425.1526, device='cuda:0')
episode: 246 training return: tensor(-399.5430, device='cuda:0')
episode: 247 training return: tensor(-386.2227, device='cuda:0')
epoch: 62 test_true_pfm: -12.117471466068546 sim_pfm: -407.02452122992446
episode: 248 training return: tensor(-410.8976, device='cuda:0')
episode: 249 training return: tensor(-382.9870, device='cuda:0')
episode: 250 training return: tensor(-413.3519, device='cuda:0')
episode: 251 training return: tensor(-404.3962, device='cuda:0')
epoch: 63 test_true_pfm: 223.3365179896665 sim_pfm: -337.8103385242478
episode: 252 training return: tensor(-397.3285, device='cuda:0')
episode: 253 training return: tensor(-382.2497, device='cuda:0')
episode: 254 training return: tensor(-449.2217, device='cuda:0')
episode: 255 training return: tensor(-424.6889, device='cuda:0')
epoch: 64 test_true_pfm: 267.07802893675995 sim_pfm: -343.8705310477235
episode: 256 training return: tensor(-392.2522, device='cuda:0')
episode: 257 training return: tensor(-390.8351, device='cuda:0')
episode: 258 training return: tensor(-373.4664, device='cuda:0')
episode: 259 training return: tensor(-385.8462, device='cuda:0')
epoch: 65 test_true_pfm: 312.51399175124857 sim_pfm: -359.5488637148325
episode: 260 training return: tensor(-417.4989, device='cuda:0')
episode: 261 training return: tensor(-354.8099, device='cuda:0')
episode: 262 training return: tensor(-387.6635, device='cuda:0')
episode: 263 training return: tensor(-431.7878, device='cuda:0')
epoch: 66 test_true_pfm: 211.1640127244458 sim_pfm: -313.53071721975965
episode: 264 training return: tensor(-332.8154, device='cuda:0')
episode: 265 training return: tensor(-387.3492, device='cuda:0')
episode: 266 training return: tensor(-392.0325, device='cuda:0')
episode: 267 training return: tensor(-399.0993, device='cuda:0')
epoch: 67 test_true_pfm: 169.1066866057306 sim_pfm: -344.88070002174936
episode: 268 training return: tensor(-367.8055, device='cuda:0')
episode: 269 training return: tensor(-426.9302, device='cuda:0')
episode: 270 training return: tensor(-396.6980, device='cuda:0')
episode: 271 training return: tensor(-372.2683, device='cuda:0')
epoch: 68 test_true_pfm: 250.25731256014492 sim_pfm: -375.33567707341473
episode: 272 training return: tensor(-415.1245, device='cuda:0')
episode: 273 training return: tensor(-389.2520, device='cuda:0')
episode: 274 training return: tensor(-359.4668, device='cuda:0')
episode: 275 training return: tensor(-373.0656, device='cuda:0')
epoch: 69 test_true_pfm: 379.6669062311221 sim_pfm: -322.27488097703707
episode: 276 training return: tensor(-404.1599, device='cuda:0')
episode: 277 training return: tensor(-384.6865, device='cuda:0')
episode: 278 training return: tensor(-422.0768, device='cuda:0')
episode: 279 training return: tensor(-342.8758, device='cuda:0')
epoch: 70 test_true_pfm: 298.0507578437381 sim_pfm: -318.210480294462
episode: 280 training return: tensor(-431.5508, device='cuda:0')
episode: 281 training return: tensor(-357.4974, device='cuda:0')
episode: 282 training return: tensor(-397.7985, device='cuda:0')
episode: 283 training return: tensor(-397.7334, device='cuda:0')
epoch: 71 test_true_pfm: 253.68382088566014 sim_pfm: -344.22682365650934
episode: 284 training return: tensor(-411.3718, device='cuda:0')
episode: 285 training return: tensor(-385.8734, device='cuda:0')
episode: 286 training return: tensor(-353.8703, device='cuda:0')
episode: 287 training return: tensor(-359.7728, device='cuda:0')
epoch: 72 test_true_pfm: 302.4796511437577 sim_pfm: -333.2336932281032
episode: 288 training return: tensor(-354.9655, device='cuda:0')
episode: 289 training return: tensor(-344.9123, device='cuda:0')
episode: 290 training return: tensor(-354.0055, device='cuda:0')
episode: 291 training return: tensor(-357.1971, device='cuda:0')
epoch: 73 test_true_pfm: 290.9083114395957 sim_pfm: -323.8874612624447
episode: 292 training return: tensor(-411.3351, device='cuda:0')
episode: 293 training return: tensor(-374.3589, device='cuda:0')
episode: 294 training return: tensor(-398.5006, device='cuda:0')
episode: 295 training return: tensor(-372.6141, device='cuda:0')
epoch: 74 test_true_pfm: 308.2993888073661 sim_pfm: -344.0999982181238
episode: 296 training return: tensor(-373.3697, device='cuda:0')
episode: 297 training return: tensor(-382.3708, device='cuda:0')
episode: 298 training return: tensor(-386.7664, device='cuda:0')
episode: 299 training return: tensor(-371.3272, device='cuda:0')
epoch: 75 test_true_pfm: 237.31422972746267 sim_pfm: -336.8441319033348
episode: 300 training return: tensor(-372.4818, device='cuda:0')
episode: 301 training return: tensor(-389.4214, device='cuda:0')
episode: 302 training return: tensor(-360.6732, device='cuda:0')
episode: 303 training return: tensor(-385.9568, device='cuda:0')
epoch: 76 test_true_pfm: 268.81843011792057 sim_pfm: -326.3014940454547
episode: 304 training return: tensor(-402.0637, device='cuda:0')
episode: 305 training return: tensor(-431.9197, device='cuda:0')
episode: 306 training return: tensor(-320.6472, device='cuda:0')
episode: 307 training return: tensor(-385.4266, device='cuda:0')
epoch: 77 test_true_pfm: 254.38533826154503 sim_pfm: -321.8249904754048
episode: 308 training return: tensor(-417.5236, device='cuda:0')
episode: 309 training return: tensor(-366.7187, device='cuda:0')
episode: 310 training return: tensor(-345.1077, device='cuda:0')
episode: 311 training return: tensor(-379.9872, device='cuda:0')
epoch: 78 test_true_pfm: 274.32596243172424 sim_pfm: -337.36957079179894
episode: 312 training return: tensor(-380.7978, device='cuda:0')
episode: 313 training return: tensor(-393.7439, device='cuda:0')
episode: 314 training return: tensor(-417.0694, device='cuda:0')
episode: 315 training return: tensor(-371.8041, device='cuda:0')
epoch: 79 test_true_pfm: 193.7290094629092 sim_pfm: -350.38831404573284
episode: 316 training return: tensor(-409.7065, device='cuda:0')
episode: 317 training return: tensor(-413.0166, device='cuda:0')
episode: 318 training return: tensor(-345.7159, device='cuda:0')
episode: 319 training return: tensor(-429.3658, device='cuda:0')
epoch: 80 test_true_pfm: 185.79066182195757 sim_pfm: -362.63040856508695
episode: 320 training return: tensor(-396.8042, device='cuda:0')
episode: 321 training return: tensor(-392.5949, device='cuda:0')
episode: 322 training return: tensor(-343.1721, device='cuda:0')
episode: 323 training return: tensor(-367.3904, device='cuda:0')
epoch: 81 test_true_pfm: 245.20686956343056 sim_pfm: -353.9369688655327
episode: 324 training return: tensor(-401.0414, device='cuda:0')
episode: 325 training return: tensor(-409.5038, device='cuda:0')
episode: 326 training return: tensor(-373.2067, device='cuda:0')
episode: 327 training return: tensor(-431.2611, device='cuda:0')
epoch: 82 test_true_pfm: 343.7943279156996 sim_pfm: -321.2031204453281
episode: 328 training return: tensor(-441.4473, device='cuda:0')
episode: 329 training return: tensor(-410.9429, device='cuda:0')
episode: 330 training return: tensor(-375.1052, device='cuda:0')
episode: 331 training return: tensor(-396.4282, device='cuda:0')
epoch: 83 test_true_pfm: 219.9185147343912 sim_pfm: -334.01747111432877
episode: 332 training return: tensor(-365.1568, device='cuda:0')
episode: 333 training return: tensor(-351.3374, device='cuda:0')
episode: 334 training return: tensor(-426.8292, device='cuda:0')
episode: 335 training return: tensor(-404.5339, device='cuda:0')
epoch: 84 test_true_pfm: 265.5208791125819 sim_pfm: -364.1940391462219
episode: 336 training return: tensor(-358.9189, device='cuda:0')
episode: 337 training return: tensor(-357.6051, device='cuda:0')
episode: 338 training return: tensor(-441.5679, device='cuda:0')
episode: 339 training return: tensor(-339.0682, device='cuda:0')
epoch: 85 test_true_pfm: 125.11397190773312 sim_pfm: -336.0346466281917
episode: 340 training return: tensor(-394.2379, device='cuda:0')
episode: 341 training return: tensor(-364.9907, device='cuda:0')
episode: 342 training return: tensor(-364.2702, device='cuda:0')
episode: 343 training return: tensor(-369.9900, device='cuda:0')
epoch: 86 test_true_pfm: 356.97871549380005 sim_pfm: -344.9688877616524
episode: 344 training return: tensor(-430.1669, device='cuda:0')
episode: 345 training return: tensor(-353.5940, device='cuda:0')
episode: 346 training return: tensor(-381.0113, device='cuda:0')
episode: 347 training return: tensor(-394.9532, device='cuda:0')
epoch: 87 test_true_pfm: 117.50787881155162 sim_pfm: -311.11073795108433
episode: 348 training return: tensor(-356.4918, device='cuda:0')
episode: 349 training return: tensor(-391.8271, device='cuda:0')
episode: 350 training return: tensor(-386.9620, device='cuda:0')
episode: 351 training return: tensor(-355.5181, device='cuda:0')
epoch: 88 test_true_pfm: 303.7917176251607 sim_pfm: -354.4050075414901
episode: 352 training return: tensor(-378.7446, device='cuda:0')
episode: 353 training return: tensor(-352.4964, device='cuda:0')
episode: 354 training return: tensor(-459.4450, device='cuda:0')
episode: 355 training return: tensor(-416.0304, device='cuda:0')
epoch: 89 test_true_pfm: 322.75196690625916 sim_pfm: -354.921013562164
episode: 356 training return: tensor(-383.6618, device='cuda:0')
episode: 357 training return: tensor(-404.5608, device='cuda:0')
episode: 358 training return: tensor(-342.4460, device='cuda:0')
episode: 359 training return: tensor(-364.3134, device='cuda:0')
epoch: 90 test_true_pfm: 301.2324955510559 sim_pfm: -314.283446621402
episode: 360 training return: tensor(-427.2699, device='cuda:0')
episode: 361 training return: tensor(-413.7125, device='cuda:0')
episode: 362 training return: tensor(-374.1255, device='cuda:0')
episode: 363 training return: tensor(-359.6033, device='cuda:0')
epoch: 91 test_true_pfm: 340.44679645092936 sim_pfm: -340.69225273631554
episode: 364 training return: tensor(-370.0508, device='cuda:0')
episode: 365 training return: tensor(-438.5143, device='cuda:0')
episode: 366 training return: tensor(-358.0477, device='cuda:0')
episode: 367 training return: tensor(-434.1577, device='cuda:0')
epoch: 92 test_true_pfm: 283.80728957421746 sim_pfm: -340.38143256745144
episode: 368 training return: tensor(-375.0056, device='cuda:0')
episode: 369 training return: tensor(-381.3782, device='cuda:0')
episode: 370 training return: tensor(-374.4646, device='cuda:0')
episode: 371 training return: tensor(-399.0442, device='cuda:0')
epoch: 93 test_true_pfm: 201.39512226195654 sim_pfm: -318.8243413895834
episode: 372 training return: tensor(-411.6483, device='cuda:0')
episode: 373 training return: tensor(-389.8795, device='cuda:0')
episode: 374 training return: tensor(-403.8109, device='cuda:0')
episode: 375 training return: tensor(-405.3773, device='cuda:0')
epoch: 94 test_true_pfm: 358.2490351557656 sim_pfm: -342.45541744671453
episode: 376 training return: tensor(-388.5352, device='cuda:0')
episode: 377 training return: tensor(-383.3673, device='cuda:0')
episode: 378 training return: tensor(-398.6087, device='cuda:0')
episode: 379 training return: tensor(-325.7976, device='cuda:0')
epoch: 95 test_true_pfm: 411.5666853286034 sim_pfm: -343.4595695410001
episode: 380 training return: tensor(-418.2749, device='cuda:0')
episode: 381 training return: tensor(-401.7186, device='cuda:0')
episode: 382 training return: tensor(-360.3448, device='cuda:0')
episode: 383 training return: tensor(-379.3536, device='cuda:0')
epoch: 96 test_true_pfm: 483.4732101635597 sim_pfm: -341.02289224031847
episode: 384 training return: tensor(-366.3746, device='cuda:0')
episode: 385 training return: tensor(-373.0762, device='cuda:0')
episode: 386 training return: tensor(-350.2052, device='cuda:0')
episode: 387 training return: tensor(-366.2523, device='cuda:0')
epoch: 97 test_true_pfm: 327.88379412700255 sim_pfm: -314.11960224888753
episode: 388 training return: tensor(-463.1826, device='cuda:0')
episode: 389 training return: tensor(-382.2781, device='cuda:0')
episode: 390 training return: tensor(-389.6620, device='cuda:0')
episode: 391 training return: tensor(-343.6114, device='cuda:0')
epoch: 98 test_true_pfm: 129.58095977253967 sim_pfm: -321.5107289448691
episode: 392 training return: tensor(-374.1264, device='cuda:0')
episode: 393 training return: tensor(-334.8522, device='cuda:0')
episode: 394 training return: tensor(-394.4422, device='cuda:0')
episode: 395 training return: tensor(-383.9403, device='cuda:0')
epoch: 99 test_true_pfm: 199.87605161731452 sim_pfm: -327.40711612541537
episode: 396 training return: tensor(-376.0655, device='cuda:0')
episode: 397 training return: tensor(-376.1189, device='cuda:0')
episode: 398 training return: tensor(-340.5227, device='cuda:0')
episode: 399 training return: tensor(-362.6750, device='cuda:0')
epoch: 100 test_true_pfm: 394.0208593416855 sim_pfm: -325.47230998347123
episode: 400 training return: tensor(-396.4388, device='cuda:0')
episode: 401 training return: tensor(-366.2361, device='cuda:0')
episode: 402 training return: tensor(-367.9781, device='cuda:0')
episode: 403 training return: tensor(-378.5246, device='cuda:0')
epoch: 101 test_true_pfm: 316.9984651799506 sim_pfm: -311.95246218148776
episode: 404 training return: tensor(-398.7516, device='cuda:0')
episode: 405 training return: tensor(-412.8798, device='cuda:0')
episode: 406 training return: tensor(-380.6682, device='cuda:0')
episode: 407 training return: tensor(-409.6628, device='cuda:0')
epoch: 102 test_true_pfm: 416.26015487417163 sim_pfm: -351.3522193911097
episode: 408 training return: tensor(-356.9801, device='cuda:0')
episode: 409 training return: tensor(-368.1345, device='cuda:0')
episode: 410 training return: tensor(-308.5220, device='cuda:0')
episode: 411 training return: tensor(-416.1222, device='cuda:0')
epoch: 103 test_true_pfm: 346.8967246469836 sim_pfm: -298.17557897159713
episode: 412 training return: tensor(-375.7425, device='cuda:0')
episode: 413 training return: tensor(-414.5082, device='cuda:0')
episode: 414 training return: tensor(-393.6417, device='cuda:0')
episode: 415 training return: tensor(-362.5039, device='cuda:0')
epoch: 104 test_true_pfm: 270.44182156545054 sim_pfm: -321.1373629628409
episode: 416 training return: tensor(-393.2164, device='cuda:0')
episode: 417 training return: tensor(-393.8806, device='cuda:0')
episode: 418 training return: tensor(-398.0997, device='cuda:0')
episode: 419 training return: tensor(-384.9858, device='cuda:0')
epoch: 105 test_true_pfm: 314.2879719118754 sim_pfm: -336.20115652593086
episode: 420 training return: tensor(-387.4488, device='cuda:0')
episode: 421 training return: tensor(-324.1352, device='cuda:0')
episode: 422 training return: tensor(-320.0413, device='cuda:0')
episode: 423 training return: tensor(-330.4843, device='cuda:0')
epoch: 106 test_true_pfm: 377.19739794420184 sim_pfm: -329.03820932252955
episode: 424 training return: tensor(-368.3883, device='cuda:0')
episode: 425 training return: tensor(-398.7022, device='cuda:0')
episode: 426 training return: tensor(-395.6233, device='cuda:0')
episode: 427 training return: tensor(-380.0455, device='cuda:0')
epoch: 107 test_true_pfm: 307.2444334482894 sim_pfm: -306.97451759387815
episode: 428 training return: tensor(-400.5246, device='cuda:0')
episode: 429 training return: tensor(-327.9722, device='cuda:0')
episode: 430 training return: tensor(-454.5175, device='cuda:0')
episode: 431 training return: tensor(-391.2022, device='cuda:0')
epoch: 108 test_true_pfm: 305.49275448470206 sim_pfm: -339.83328697651933
episode: 432 training return: tensor(-383.9370, device='cuda:0')
episode: 433 training return: tensor(-360.4633, device='cuda:0')
episode: 434 training return: tensor(-381.1222, device='cuda:0')
episode: 435 training return: tensor(-379.4978, device='cuda:0')
epoch: 109 test_true_pfm: 244.99361936179517 sim_pfm: -310.85749726044014
episode: 436 training return: tensor(-399.2564, device='cuda:0')
episode: 437 training return: tensor(-353.9372, device='cuda:0')
episode: 438 training return: tensor(-373.5951, device='cuda:0')
episode: 439 training return: tensor(-394.5689, device='cuda:0')
epoch: 110 test_true_pfm: 299.6426127556563 sim_pfm: -342.6843360803032
episode: 440 training return: tensor(-374.4066, device='cuda:0')
episode: 441 training return: tensor(-395.8341, device='cuda:0')
episode: 442 training return: tensor(-375.6765, device='cuda:0')
episode: 443 training return: tensor(-374.4916, device='cuda:0')
epoch: 111 test_true_pfm: 336.8891468580309 sim_pfm: -350.74490623315796
episode: 444 training return: tensor(-345.6658, device='cuda:0')
episode: 445 training return: tensor(-357.1508, device='cuda:0')
episode: 446 training return: tensor(-375.5535, device='cuda:0')
episode: 447 training return: tensor(-368.6419, device='cuda:0')
epoch: 112 test_true_pfm: 233.76798378546098 sim_pfm: -338.2412652130006
episode: 448 training return: tensor(-358.8156, device='cuda:0')
episode: 449 training return: tensor(-397.2272, device='cuda:0')
episode: 450 training return: tensor(-406.2569, device='cuda:0')
episode: 451 training return: tensor(-431.3381, device='cuda:0')
epoch: 113 test_true_pfm: 329.6832424799611 sim_pfm: -317.05407844835037
episode: 452 training return: tensor(-351.8497, device='cuda:0')
episode: 453 training return: tensor(-352.6180, device='cuda:0')
episode: 454 training return: tensor(-409.1611, device='cuda:0')
episode: 455 training return: tensor(-393.5908, device='cuda:0')
epoch: 114 test_true_pfm: 251.46729084960404 sim_pfm: -335.40321288347087
episode: 456 training return: tensor(-365.8450, device='cuda:0')
episode: 457 training return: tensor(-390.4284, device='cuda:0')
episode: 458 training return: tensor(-371.3288, device='cuda:0')
episode: 459 training return: tensor(-378.2262, device='cuda:0')
epoch: 115 test_true_pfm: 364.49709610190786 sim_pfm: -327.5123391451004
episode: 460 training return: tensor(-368.7023, device='cuda:0')
episode: 461 training return: tensor(-462.0620, device='cuda:0')
episode: 462 training return: tensor(-387.4480, device='cuda:0')
episode: 463 training return: tensor(-385.4153, device='cuda:0')
epoch: 116 test_true_pfm: 267.93550618944374 sim_pfm: -314.5114546752302
episode: 464 training return: tensor(-327.5295, device='cuda:0')
episode: 465 training return: tensor(-399.2003, device='cuda:0')
episode: 466 training return: tensor(-363.7512, device='cuda:0')
episode: 467 training return: tensor(-375.5340, device='cuda:0')
epoch: 117 test_true_pfm: 307.0678250732913 sim_pfm: -326.7484848505895
episode: 468 training return: tensor(-360.8358, device='cuda:0')
episode: 469 training return: tensor(-387.9134, device='cuda:0')
episode: 470 training return: tensor(-373.3027, device='cuda:0')
episode: 471 training return: tensor(-377.2958, device='cuda:0')
epoch: 118 test_true_pfm: 382.2731817190955 sim_pfm: -323.1246028651173
episode: 472 training return: tensor(-365.7839, device='cuda:0')
episode: 473 training return: tensor(-446.1909, device='cuda:0')
episode: 474 training return: tensor(-355.0034, device='cuda:0')
episode: 475 training return: tensor(-373.9084, device='cuda:0')
epoch: 119 test_true_pfm: 264.92120489509364 sim_pfm: -364.0514174892257
episode: 476 training return: tensor(-380.3561, device='cuda:0')
episode: 477 training return: tensor(-397.1818, device='cuda:0')
episode: 478 training return: tensor(-397.4595, device='cuda:0')
episode: 479 training return: tensor(-378.0215, device='cuda:0')
epoch: 120 test_true_pfm: 310.76463036898826 sim_pfm: -339.55170352885034
episode: 480 training return: tensor(-365.2301, device='cuda:0')
episode: 481 training return: tensor(-367.4968, device='cuda:0')
episode: 482 training return: tensor(-412.8919, device='cuda:0')
episode: 483 training return: tensor(-409.0345, device='cuda:0')
epoch: 121 test_true_pfm: 326.5416907511115 sim_pfm: -327.6984315026396
episode: 484 training return: tensor(-407.3490, device='cuda:0')
episode: 485 training return: tensor(-348.3534, device='cuda:0')
episode: 486 training return: tensor(-396.6484, device='cuda:0')
episode: 487 training return: tensor(-377.8719, device='cuda:0')
epoch: 122 test_true_pfm: 213.55552949018406 sim_pfm: -344.9182893416728
episode: 488 training return: tensor(-330.2366, device='cuda:0')
episode: 489 training return: tensor(-410.0797, device='cuda:0')
episode: 490 training return: tensor(-425.0506, device='cuda:0')
episode: 491 training return: tensor(-375.1617, device='cuda:0')
epoch: 123 test_true_pfm: 335.22152455140764 sim_pfm: -300.79533734209446
episode: 492 training return: tensor(-376.9365, device='cuda:0')
episode: 493 training return: tensor(-410.5155, device='cuda:0')
episode: 494 training return: tensor(-412.3181, device='cuda:0')
episode: 495 training return: tensor(-416.2914, device='cuda:0')
epoch: 124 test_true_pfm: 367.8930338692021 sim_pfm: -355.63188163144514
episode: 496 training return: tensor(-372.9499, device='cuda:0')
episode: 497 training return: tensor(-395.4651, device='cuda:0')
episode: 498 training return: tensor(-414.1119, device='cuda:0')
episode: 499 training return: tensor(-374.9027, device='cuda:0')
epoch: 125 test_true_pfm: 266.49062924035866 sim_pfm: -343.2826152962516
episode: 500 training return: tensor(-348.3837, device='cuda:0')
episode: 501 training return: tensor(-398.9741, device='cuda:0')
episode: 502 training return: tensor(-417.9100, device='cuda:0')
episode: 503 training return: tensor(-399.5455, device='cuda:0')
epoch: 126 test_true_pfm: 304.039342698589 sim_pfm: -329.68632562303293
episode: 504 training return: tensor(-364.8048, device='cuda:0')
episode: 505 training return: tensor(-385.6368, device='cuda:0')
episode: 506 training return: tensor(-383.6899, device='cuda:0')
episode: 507 training return: tensor(-402.9908, device='cuda:0')
epoch: 127 test_true_pfm: 186.96277228859074 sim_pfm: -329.7647835096286
episode: 508 training return: tensor(-374.0625, device='cuda:0')
episode: 509 training return: tensor(-413.5530, device='cuda:0')
episode: 510 training return: tensor(-363.8099, device='cuda:0')
episode: 511 training return: tensor(-394.2454, device='cuda:0')
epoch: 128 test_true_pfm: 262.58041050031846 sim_pfm: -325.3761837355657
episode: 512 training return: tensor(-343.8901, device='cuda:0')
episode: 513 training return: tensor(-353.2180, device='cuda:0')
episode: 514 training return: tensor(-390.7672, device='cuda:0')
episode: 515 training return: tensor(-385.5509, device='cuda:0')
epoch: 129 test_true_pfm: 358.20751420064767 sim_pfm: -323.7943209815421
episode: 516 training return: tensor(-332.9180, device='cuda:0')
episode: 517 training return: tensor(-350.6525, device='cuda:0')
episode: 518 training return: tensor(-378.9407, device='cuda:0')
episode: 519 training return: tensor(-363.3733, device='cuda:0')
epoch: 130 test_true_pfm: 432.9665068876972 sim_pfm: -297.9194554916273
episode: 520 training return: tensor(-396.8639, device='cuda:0')
episode: 521 training return: tensor(-381.9937, device='cuda:0')
episode: 522 training return: tensor(-415.9955, device='cuda:0')
episode: 523 training return: tensor(-374.8975, device='cuda:0')
epoch: 131 test_true_pfm: 413.7691385792453 sim_pfm: -310.5556929354013
episode: 524 training return: tensor(-378.0658, device='cuda:0')
episode: 525 training return: tensor(-397.4615, device='cuda:0')
episode: 526 training return: tensor(-388.2601, device='cuda:0')
episode: 527 training return: tensor(-343.8898, device='cuda:0')
epoch: 132 test_true_pfm: 387.1023842038803 sim_pfm: -275.49524462176487
episode: 528 training return: tensor(-398.7852, device='cuda:0')
episode: 529 training return: tensor(-388.8314, device='cuda:0')
episode: 530 training return: tensor(-348.6489, device='cuda:0')
episode: 531 training return: tensor(-389.9760, device='cuda:0')
epoch: 133 test_true_pfm: 265.8830180386191 sim_pfm: -331.62783265307854
episode: 532 training return: tensor(-403.8980, device='cuda:0')
episode: 533 training return: tensor(-398.3601, device='cuda:0')
episode: 534 training return: tensor(-396.5876, device='cuda:0')
episode: 535 training return: tensor(-395.1883, device='cuda:0')
epoch: 134 test_true_pfm: 291.53622837988286 sim_pfm: -314.8869674426581
episode: 536 training return: tensor(-379.9162, device='cuda:0')
episode: 537 training return: tensor(-397.8669, device='cuda:0')
episode: 538 training return: tensor(-380.2238, device='cuda:0')
episode: 539 training return: tensor(-350.8813, device='cuda:0')
epoch: 135 test_true_pfm: 297.9248131966001 sim_pfm: -311.815839733618
episode: 540 training return: tensor(-354.8022, device='cuda:0')
episode: 541 training return: tensor(-371.3431, device='cuda:0')
episode: 542 training return: tensor(-371.3139, device='cuda:0')
episode: 543 training return: tensor(-362.5791, device='cuda:0')
epoch: 136 test_true_pfm: 405.6991960868545 sim_pfm: -328.2137607541129
episode: 544 training return: tensor(-415.5199, device='cuda:0')
episode: 545 training return: tensor(-416.5205, device='cuda:0')
episode: 546 training return: tensor(-380.9732, device='cuda:0')
episode: 547 training return: tensor(-382.6720, device='cuda:0')
epoch: 137 test_true_pfm: 274.79214516810924 sim_pfm: -319.9981778485235
episode: 548 training return: tensor(-408.6257, device='cuda:0')
episode: 549 training return: tensor(-390.6610, device='cuda:0')
episode: 550 training return: tensor(-414.6081, device='cuda:0')
episode: 551 training return: tensor(-356.2981, device='cuda:0')
epoch: 138 test_true_pfm: 393.98704753935516 sim_pfm: -316.34309533789445
episode: 552 training return: tensor(-351.4481, device='cuda:0')
episode: 553 training return: tensor(-380.2850, device='cuda:0')
episode: 554 training return: tensor(-361.8672, device='cuda:0')
episode: 555 training return: tensor(-405.8942, device='cuda:0')
epoch: 139 test_true_pfm: 300.3104852959371 sim_pfm: -335.48178374022245
episode: 556 training return: tensor(-385.4925, device='cuda:0')
episode: 557 training return: tensor(-370.2977, device='cuda:0')
episode: 558 training return: tensor(-401.6753, device='cuda:0')
episode: 559 training return: tensor(-387.7858, device='cuda:0')
epoch: 140 test_true_pfm: 328.9131085643283 sim_pfm: -334.6225376135553
episode: 560 training return: tensor(-358.1162, device='cuda:0')
episode: 561 training return: tensor(-339.5147, device='cuda:0')
episode: 562 training return: tensor(-426.3888, device='cuda:0')
episode: 563 training return: tensor(-379.3141, device='cuda:0')
epoch: 141 test_true_pfm: 297.3930125052506 sim_pfm: -318.655619048106
episode: 564 training return: tensor(-406.1668, device='cuda:0')
episode: 565 training return: tensor(-370.9871, device='cuda:0')
episode: 566 training return: tensor(-326.9839, device='cuda:0')
episode: 567 training return: tensor(-410.4532, device='cuda:0')
epoch: 142 test_true_pfm: 344.7472510466382 sim_pfm: -291.4054427112763
episode: 568 training return: tensor(-360.0884, device='cuda:0')
episode: 569 training return: tensor(-398.5984, device='cuda:0')
episode: 570 training return: tensor(-330.1199, device='cuda:0')
episode: 571 training return: tensor(-369.6150, device='cuda:0')
epoch: 143 test_true_pfm: 287.6289895058077 sim_pfm: -358.7938269234631
episode: 572 training return: tensor(-383.2277, device='cuda:0')
episode: 573 training return: tensor(-413.7305, device='cuda:0')
episode: 574 training return: tensor(-411.9927, device='cuda:0')
episode: 575 training return: tensor(-423.8910, device='cuda:0')
epoch: 144 test_true_pfm: 412.95803089280145 sim_pfm: -319.9935519361558
episode: 576 training return: tensor(-379.0242, device='cuda:0')
episode: 577 training return: tensor(-414.6393, device='cuda:0')
episode: 578 training return: tensor(-454.5594, device='cuda:0')
episode: 579 training return: tensor(-394.6943, device='cuda:0')
epoch: 145 test_true_pfm: 355.17985242653714 sim_pfm: -345.8979077623614
episode: 580 training return: tensor(-349.7273, device='cuda:0')
episode: 581 training return: tensor(-336.9176, device='cuda:0')
episode: 582 training return: tensor(-410.1657, device='cuda:0')
episode: 583 training return: tensor(-360.4961, device='cuda:0')
epoch: 146 test_true_pfm: 386.6349603382801 sim_pfm: -282.7496776485738
episode: 584 training return: tensor(-368.6665, device='cuda:0')
episode: 585 training return: tensor(-329.0996, device='cuda:0')
episode: 586 training return: tensor(-376.7117, device='cuda:0')
episode: 587 training return: tensor(-384.2932, device='cuda:0')
epoch: 147 test_true_pfm: 188.6592755143936 sim_pfm: -317.342228450502
episode: 588 training return: tensor(-383.5711, device='cuda:0')
episode: 589 training return: tensor(-353.9467, device='cuda:0')
episode: 590 training return: tensor(-362.6305, device='cuda:0')
episode: 591 training return: tensor(-375.9529, device='cuda:0')
epoch: 148 test_true_pfm: 172.8163090446683 sim_pfm: -337.93449079140555
episode: 592 training return: tensor(-401.4772, device='cuda:0')
episode: 593 training return: tensor(-384.2340, device='cuda:0')
episode: 594 training return: tensor(-343.1367, device='cuda:0')
episode: 595 training return: tensor(-381.6248, device='cuda:0')
epoch: 149 test_true_pfm: 313.17767509220806 sim_pfm: -305.9507530546592
episode: 596 training return: tensor(-400.4728, device='cuda:0')
episode: 597 training return: tensor(-402.6563, device='cuda:0')
episode: 598 training return: tensor(-410.4448, device='cuda:0')
episode: 599 training return: tensor(-357.0041, device='cuda:0')
epoch: 150 test_true_pfm: 330.1167577689784 sim_pfm: -301.0308783872363
