['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'brac', '--traj', 'medium', '--seed', '0', '--data', '100000']
4992.343096075699
episode: 0 training return: tensor(-4983.7373, device='cuda:0')
episode: 1 training return: tensor(-4356.4873, device='cuda:0')
episode: 2 training return: tensor(-4910.7100, device='cuda:0')
episode: 3 training return: tensor(-2043.6759, device='cuda:0')
epoch: 1 test_true_pfm: 557.0473165350104
episode: 4 training return: tensor(-2901.8225, device='cuda:0')
episode: 5 training return: tensor(-2303.6528, device='cuda:0')
episode: 6 training return: tensor(-5362.3877, device='cuda:0')
episode: 7 training return: tensor(-5229.8921, device='cuda:0')
epoch: 2 test_true_pfm: -180.03457515801483
episode: 8 training return: tensor(-2787.0256, device='cuda:0')
episode: 9 training return: tensor(-5002.7339, device='cuda:0')
episode: 10 training return: tensor(-2575.2666, device='cuda:0')
episode: 11 training return: tensor(-2351.1375, device='cuda:0')
epoch: 3 test_true_pfm: 18.484273501011398
episode: 12 training return: tensor(-1914.2249, device='cuda:0')
episode: 13 training return: tensor(-1965.8296, device='cuda:0')
episode: 14 training return: tensor(-1729.2517, device='cuda:0')
episode: 15 training return: tensor(-1608.4664, device='cuda:0')
epoch: 4 test_true_pfm: -153.18008320788203
episode: 16 training return: tensor(-1816.2651, device='cuda:0')
episode: 17 training return: tensor(-1857.0018, device='cuda:0')
episode: 18 training return: tensor(-1658.1764, device='cuda:0')
episode: 19 training return: tensor(-1657.9978, device='cuda:0')
epoch: 5 test_true_pfm: -60.60712444736199
episode: 20 training return: tensor(-1719.1399, device='cuda:0')
episode: 21 training return: tensor(-1639.1255, device='cuda:0')
episode: 22 training return: tensor(-1661.3330, device='cuda:0')
episode: 23 training return: tensor(-1688.0243, device='cuda:0')
epoch: 6 test_true_pfm: -50.870651036607605
episode: 24 training return: tensor(-1657.6112, device='cuda:0')
episode: 25 training return: tensor(-1659.5903, device='cuda:0')
episode: 26 training return: tensor(-1873.0598, device='cuda:0')
episode: 27 training return: tensor(-1765.9042, device='cuda:0')
epoch: 7 test_true_pfm: -36.38501926458916
episode: 28 training return: tensor(-1717.3395, device='cuda:0')
episode: 29 training return: tensor(-1857.5714, device='cuda:0')
episode: 30 training return: tensor(-1674.4070, device='cuda:0')
episode: 31 training return: tensor(-1666.5652, device='cuda:0')
epoch: 8 test_true_pfm: -35.28311704954742
episode: 32 training return: tensor(-1639.6552, device='cuda:0')
episode: 33 training return: tensor(-1682.5140, device='cuda:0')
episode: 34 training return: tensor(-1856.0166, device='cuda:0')
episode: 35 training return: tensor(-1867.2545, device='cuda:0')
epoch: 9 test_true_pfm: -40.15319510626808
episode: 36 training return: tensor(-1648.6653, device='cuda:0')
episode: 37 training return: tensor(-1847.1334, device='cuda:0')
episode: 38 training return: tensor(-1735.0480, device='cuda:0')
episode: 39 training return: tensor(-1742.8250, device='cuda:0')
epoch: 10 test_true_pfm: -27.915432958178883
episode: 40 training return: tensor(-1666.8777, device='cuda:0')
episode: 41 training return: tensor(-1835.1136, device='cuda:0')
episode: 42 training return: tensor(-1837.4758, device='cuda:0')
episode: 43 training return: tensor(-1644.5460, device='cuda:0')
epoch: 11 test_true_pfm: -26.558764013776784
episode: 44 training return: tensor(-1616.9012, device='cuda:0')
episode: 45 training return: tensor(-1653.2893, device='cuda:0')
episode: 46 training return: tensor(-1619.7347, device='cuda:0')
episode: 47 training return: tensor(-1647.6979, device='cuda:0')
epoch: 12 test_true_pfm: -24.41928695872404
episode: 48 training return: tensor(-1620.9363, device='cuda:0')
episode: 49 training return: tensor(-1639.6035, device='cuda:0')
episode: 50 training return: tensor(-1627.9119, device='cuda:0')
episode: 51 training return: tensor(-1702.6919, device='cuda:0')
epoch: 13 test_true_pfm: -26.788826164948933
episode: 52 training return: tensor(-1634.8376, device='cuda:0')
episode: 53 training return: tensor(-1610.6649, device='cuda:0')
episode: 54 training return: tensor(-1637.4600, device='cuda:0')
episode: 55 training return: tensor(-1634.1216, device='cuda:0')
epoch: 14 test_true_pfm: -23.48640018040828
episode: 56 training return: tensor(-1687.0189, device='cuda:0')
episode: 57 training return: tensor(-1627.0402, device='cuda:0')
episode: 58 training return: tensor(-1653.3104, device='cuda:0')
episode: 59 training return: tensor(-1609.6492, device='cuda:0')
epoch: 15 test_true_pfm: -20.900753968530577
episode: 60 training return: tensor(-1625.1735, device='cuda:0')
episode: 61 training return: tensor(-1642.6143, device='cuda:0')
episode: 62 training return: tensor(-1617.9271, device='cuda:0')
episode: 63 training return: tensor(-1619.0458, device='cuda:0')
epoch: 16 test_true_pfm: -22.78047440707535
episode: 64 training return: tensor(-1629.5498, device='cuda:0')
episode: 65 training return: tensor(-1637.3158, device='cuda:0')
episode: 66 training return: tensor(-1631.0304, device='cuda:0')
episode: 67 training return: tensor(-1641.8055, device='cuda:0')
epoch: 17 test_true_pfm: -19.18494590529438
episode: 68 training return: tensor(-1644.4996, device='cuda:0')
episode: 69 training return: tensor(-1630.9111, device='cuda:0')
episode: 70 training return: tensor(-1632.8641, device='cuda:0')
episode: 71 training return: tensor(-1620.1727, device='cuda:0')
epoch: 18 test_true_pfm: -22.528254725334733
episode: 72 training return: tensor(-1643.2639, device='cuda:0')
episode: 73 training return: tensor(-1636.9048, device='cuda:0')
episode: 74 training return: tensor(-1664.9403, device='cuda:0')
episode: 75 training return: tensor(-1613.7701, device='cuda:0')
epoch: 19 test_true_pfm: -17.87422928180005
episode: 76 training return: tensor(-1645.2900, device='cuda:0')
episode: 77 training return: tensor(-1621.9041, device='cuda:0')
episode: 78 training return: tensor(-1638.1027, device='cuda:0')
episode: 79 training return: tensor(-1638.8572, device='cuda:0')
epoch: 20 test_true_pfm: -11.83414425348677
episode: 80 training return: tensor(-1650.9725, device='cuda:0')
episode: 81 training return: tensor(-1627.8207, device='cuda:0')
episode: 82 training return: tensor(-1662.3156, device='cuda:0')
episode: 83 training return: tensor(-1634.4111, device='cuda:0')
epoch: 21 test_true_pfm: -20.007083693286287
episode: 84 training return: tensor(-1647.5565, device='cuda:0')
episode: 85 training return: tensor(-1635.4248, device='cuda:0')
episode: 86 training return: tensor(-1608.7539, device='cuda:0')
episode: 87 training return: tensor(-1618.5143, device='cuda:0')
epoch: 22 test_true_pfm: -14.308648796474664
episode: 88 training return: tensor(-1626.3644, device='cuda:0')
episode: 89 training return: tensor(-1645.0167, device='cuda:0')
episode: 90 training return: tensor(-1655.3375, device='cuda:0')
episode: 91 training return: tensor(-1624.5331, device='cuda:0')
epoch: 23 test_true_pfm: -12.353658460344342
episode: 92 training return: tensor(-1824.8373, device='cuda:0')
episode: 93 training return: tensor(-1651.8557, device='cuda:0')
episode: 94 training return: tensor(-1632.6469, device='cuda:0')
episode: 95 training return: tensor(-1650.2372, device='cuda:0')
epoch: 24 test_true_pfm: -13.006865399069914
episode: 96 training return: tensor(-1627.6755, device='cuda:0')
episode: 97 training return: tensor(-1633.1681, device='cuda:0')
episode: 98 training return: tensor(-1634.1389, device='cuda:0')
episode: 99 training return: tensor(-1641.1483, device='cuda:0')
epoch: 25 test_true_pfm: -12.303122304735956
episode: 100 training return: tensor(-1612.2526, device='cuda:0')
episode: 101 training return: tensor(-1619.1438, device='cuda:0')
episode: 102 training return: tensor(-1650.6371, device='cuda:0')
episode: 103 training return: tensor(-1652.8446, device='cuda:0')
epoch: 26 test_true_pfm: -19.25153015502453
episode: 104 training return: tensor(-1639.9419, device='cuda:0')
episode: 105 training return: tensor(-1631.9181, device='cuda:0')
episode: 106 training return: tensor(-1628.2058, device='cuda:0')
episode: 107 training return: tensor(-1650.3593, device='cuda:0')
epoch: 27 test_true_pfm: -17.266209535670125
episode: 108 training return: tensor(-1639.5394, device='cuda:0')
episode: 109 training return: tensor(-1637.5649, device='cuda:0')
episode: 110 training return: tensor(-1647.5504, device='cuda:0')
episode: 111 training return: tensor(-1666.6572, device='cuda:0')
epoch: 28 test_true_pfm: -16.017132872700927
episode: 112 training return: tensor(-1639.6589, device='cuda:0')
episode: 113 training return: tensor(-1679.8290, device='cuda:0')
episode: 114 training return: tensor(-1647.9086, device='cuda:0')
episode: 115 training return: tensor(-1617.9303, device='cuda:0')
epoch: 29 test_true_pfm: -14.90153492388506
episode: 116 training return: tensor(-1634.1949, device='cuda:0')
episode: 117 training return: tensor(-1628.2151, device='cuda:0')
episode: 118 training return: tensor(-1633.7959, device='cuda:0')
episode: 119 training return: tensor(-1629.4929, device='cuda:0')
epoch: 30 test_true_pfm: -21.477347467827897
episode: 120 training return: tensor(-1641.9489, device='cuda:0')
episode: 121 training return: tensor(-1636.6161, device='cuda:0')
episode: 122 training return: tensor(-1651.7013, device='cuda:0')
episode: 123 training return: tensor(-1638.1906, device='cuda:0')
epoch: 31 test_true_pfm: -24.425799044281078
episode: 124 training return: tensor(-1641.1073, device='cuda:0')
episode: 125 training return: tensor(-1636.7378, device='cuda:0')
episode: 126 training return: tensor(-1636.6755, device='cuda:0')
episode: 127 training return: tensor(-1628.2036, device='cuda:0')
epoch: 32 test_true_pfm: -15.111051856403298
episode: 128 training return: tensor(-1652.1570, device='cuda:0')
episode: 129 training return: tensor(-1633.6893, device='cuda:0')
episode: 130 training return: tensor(-1639.2362, device='cuda:0')
episode: 131 training return: tensor(-1612.8601, device='cuda:0')
epoch: 33 test_true_pfm: -14.147699551899153
episode: 132 training return: tensor(-1632.4695, device='cuda:0')
episode: 133 training return: tensor(-1604.2388, device='cuda:0')
episode: 134 training return: tensor(-1624.3121, device='cuda:0')
episode: 135 training return: tensor(-1617.2322, device='cuda:0')
epoch: 34 test_true_pfm: -16.56047653764545
episode: 136 training return: tensor(-1620.3234, device='cuda:0')
episode: 137 training return: tensor(-1624.7543, device='cuda:0')
episode: 138 training return: tensor(-1640.1166, device='cuda:0')
episode: 139 training return: tensor(-1642.6211, device='cuda:0')
epoch: 35 test_true_pfm: -19.058014636168
episode: 140 training return: tensor(-1623.9197, device='cuda:0')
episode: 141 training return: tensor(-1623.2178, device='cuda:0')
episode: 142 training return: tensor(-1627.0150, device='cuda:0')
episode: 143 training return: tensor(-1625.2000, device='cuda:0')
epoch: 36 test_true_pfm: -18.581707349665706
episode: 144 training return: tensor(-1612.6058, device='cuda:0')
episode: 145 training return: tensor(-1615.3846, device='cuda:0')
episode: 146 training return: tensor(-1613.1903, device='cuda:0')
episode: 147 training return: tensor(-1613.9445, device='cuda:0')
epoch: 37 test_true_pfm: -13.61829340224312
episode: 148 training return: tensor(-1622.9479, device='cuda:0')
episode: 149 training return: tensor(-1644.5724, device='cuda:0')
episode: 150 training return: tensor(-1630.5629, device='cuda:0')
episode: 151 training return: tensor(-1632.4436, device='cuda:0')
epoch: 38 test_true_pfm: -16.251980478082924
episode: 152 training return: tensor(-1636.2357, device='cuda:0')
episode: 153 training return: tensor(-1614.1722, device='cuda:0')
episode: 154 training return: tensor(-1645.8551, device='cuda:0')
episode: 155 training return: tensor(-1627.4489, device='cuda:0')
epoch: 39 test_true_pfm: -16.28391941666678
episode: 156 training return: tensor(-1629.7271, device='cuda:0')
episode: 157 training return: tensor(-1635.2041, device='cuda:0')
episode: 158 training return: tensor(-1634.1693, device='cuda:0')
episode: 159 training return: tensor(-1643.5209, device='cuda:0')
epoch: 40 test_true_pfm: -18.267338085722784
episode: 160 training return: tensor(-1637.4972, device='cuda:0')
episode: 161 training return: tensor(-1634.5280, device='cuda:0')
episode: 162 training return: tensor(-1626.4709, device='cuda:0')
episode: 163 training return: tensor(-1616.0616, device='cuda:0')
epoch: 41 test_true_pfm: -17.74343579882787
episode: 164 training return: tensor(-1612.2190, device='cuda:0')
episode: 165 training return: tensor(-1851.9200, device='cuda:0')
episode: 166 training return: tensor(-1650.2714, device='cuda:0')
episode: 167 training return: tensor(-1640.6571, device='cuda:0')
epoch: 42 test_true_pfm: -10.027663129751351
episode: 168 training return: tensor(-1618.0096, device='cuda:0')
episode: 169 training return: tensor(-1616.1387, device='cuda:0')
episode: 170 training return: tensor(-1626.3903, device='cuda:0')
episode: 171 training return: tensor(-1618.3915, device='cuda:0')
epoch: 43 test_true_pfm: -17.388784946764833
episode: 172 training return: tensor(-1650.0026, device='cuda:0')
episode: 173 training return: tensor(-1624.3123, device='cuda:0')
episode: 174 training return: tensor(-1626.0903, device='cuda:0')
episode: 175 training return: tensor(-1624.8776, device='cuda:0')
epoch: 44 test_true_pfm: -19.550248184733263
episode: 176 training return: tensor(-1625.0854, device='cuda:0')
episode: 177 training return: tensor(-1638.1285, device='cuda:0')
episode: 178 training return: tensor(-1623.7656, device='cuda:0')
episode: 179 training return: tensor(-1611.6667, device='cuda:0')
epoch: 45 test_true_pfm: -17.894980347688602
episode: 180 training return: tensor(-1642.6425, device='cuda:0')
episode: 181 training return: tensor(-1600.3322, device='cuda:0')
episode: 182 training return: tensor(-1617.6246, device='cuda:0')
episode: 183 training return: tensor(-1638.0548, device='cuda:0')
epoch: 46 test_true_pfm: -20.533574621745306
episode: 184 training return: tensor(-1630.5321, device='cuda:0')
episode: 185 training return: tensor(-1629.7229, device='cuda:0')
episode: 186 training return: tensor(-1649.7299, device='cuda:0')
episode: 187 training return: tensor(-1612.9263, device='cuda:0')
epoch: 47 test_true_pfm: -12.871480405954074
episode: 188 training return: tensor(-1644.4224, device='cuda:0')
episode: 189 training return: tensor(-1619.5367, device='cuda:0')
episode: 190 training return: tensor(-1626.2341, device='cuda:0')
episode: 191 training return: tensor(-1625.8115, device='cuda:0')
epoch: 48 test_true_pfm: -15.04726530226032
episode: 192 training return: tensor(-1635.8401, device='cuda:0')
episode: 193 training return: tensor(-1616.6577, device='cuda:0')
episode: 194 training return: tensor(-1623.3024, device='cuda:0')
episode: 195 training return: tensor(-1629.0864, device='cuda:0')
epoch: 49 test_true_pfm: -22.251878541195524
episode: 196 training return: tensor(-1613.3859, device='cuda:0')
episode: 197 training return: tensor(-1621.8232, device='cuda:0')
episode: 198 training return: tensor(-1627.0687, device='cuda:0')
episode: 199 training return: tensor(-1619.5980, device='cuda:0')
epoch: 50 test_true_pfm: -19.88074380618952
episode: 200 training return: tensor(-1629.6276, device='cuda:0')
episode: 201 training return: tensor(-1619.0360, device='cuda:0')
episode: 202 training return: tensor(-1615.4766, device='cuda:0')
episode: 203 training return: tensor(-1607.4464, device='cuda:0')
epoch: 51 test_true_pfm: -15.264251516778463
episode: 204 training return: tensor(-1637.4048, device='cuda:0')
episode: 205 training return: tensor(-1641.7086, device='cuda:0')
episode: 206 training return: tensor(-1629.6566, device='cuda:0')
episode: 207 training return: tensor(-1623.3976, device='cuda:0')
epoch: 52 test_true_pfm: -20.166933633910478
episode: 208 training return: tensor(-1627.3698, device='cuda:0')
episode: 209 training return: tensor(-1612.8046, device='cuda:0')
episode: 210 training return: tensor(-1609.6565, device='cuda:0')
episode: 211 training return: tensor(-1615.4738, device='cuda:0')
epoch: 53 test_true_pfm: -18.67649496960424
episode: 212 training return: tensor(-1645.4258, device='cuda:0')
episode: 213 training return: tensor(-1639.0681, device='cuda:0')
episode: 214 training return: tensor(-1641.6581, device='cuda:0')
episode: 215 training return: tensor(-1612.5115, device='cuda:0')
epoch: 54 test_true_pfm: -13.391282929461076
episode: 216 training return: tensor(-1621.1023, device='cuda:0')
episode: 217 training return: tensor(-1609.2954, device='cuda:0')
episode: 218 training return: tensor(-1616.5726, device='cuda:0')
episode: 219 training return: tensor(-1619.6271, device='cuda:0')
epoch: 55 test_true_pfm: -13.722392091335534
episode: 220 training return: tensor(-1625.9220, device='cuda:0')
episode: 221 training return: tensor(-1622.6858, device='cuda:0')
episode: 222 training return: tensor(-1610.5544, device='cuda:0')
episode: 223 training return: tensor(-1651.3035, device='cuda:0')
epoch: 56 test_true_pfm: -16.813657745917943
episode: 224 training return: tensor(-1645.0756, device='cuda:0')
episode: 225 training return: tensor(-1621.6995, device='cuda:0')
episode: 226 training return: tensor(-1633.1903, device='cuda:0')
episode: 227 training return: tensor(-1617.4806, device='cuda:0')
epoch: 57 test_true_pfm: -19.07765278516602
episode: 228 training return: tensor(-1633.0511, device='cuda:0')
episode: 229 training return: tensor(-1641.1276, device='cuda:0')
episode: 230 training return: tensor(-1629.9187, device='cuda:0')
episode: 231 training return: tensor(-1632.7830, device='cuda:0')
epoch: 58 test_true_pfm: -14.031724530383107
episode: 232 training return: tensor(-1634.8723, device='cuda:0')
episode: 233 training return: tensor(-1626.5532, device='cuda:0')
episode: 234 training return: tensor(-1630.7660, device='cuda:0')
episode: 235 training return: tensor(-1609.2587, device='cuda:0')
epoch: 59 test_true_pfm: -14.266592710235434
episode: 236 training return: tensor(-1624.8353, device='cuda:0')
episode: 237 training return: tensor(-1623.9990, device='cuda:0')
episode: 238 training return: tensor(-1615.3805, device='cuda:0')
episode: 239 training return: tensor(-1631.3450, device='cuda:0')
epoch: 60 test_true_pfm: -14.972242832416542
episode: 240 training return: tensor(-1626.8745, device='cuda:0')
episode: 241 training return: tensor(-1630.1549, device='cuda:0')
episode: 242 training return: tensor(-1632.2145, device='cuda:0')
episode: 243 training return: tensor(-1620.1329, device='cuda:0')
epoch: 61 test_true_pfm: -23.10667453162651
episode: 244 training return: tensor(-1610.0898, device='cuda:0')
episode: 245 training return: tensor(-1627.5717, device='cuda:0')
episode: 246 training return: tensor(-1619.4957, device='cuda:0')
episode: 247 training return: tensor(-1618.0570, device='cuda:0')
epoch: 62 test_true_pfm: -19.707339164182887
episode: 248 training return: tensor(-1616.8877, device='cuda:0')
episode: 249 training return: tensor(-1610.6838, device='cuda:0')
episode: 250 training return: tensor(-1616.4692, device='cuda:0')
episode: 251 training return: tensor(-1636.3931, device='cuda:0')
epoch: 63 test_true_pfm: -15.994068904193199
episode: 252 training return: tensor(-1628.4475, device='cuda:0')
episode: 253 training return: tensor(-1622.4637, device='cuda:0')
episode: 254 training return: tensor(-1627.0802, device='cuda:0')
episode: 255 training return: tensor(-1623.3418, device='cuda:0')
epoch: 64 test_true_pfm: -12.93010556164547
episode: 256 training return: tensor(-1626.6809, device='cuda:0')
episode: 257 training return: tensor(-1623.5394, device='cuda:0')
episode: 258 training return: tensor(-1615.8376, device='cuda:0')
episode: 259 training return: tensor(-1644.1465, device='cuda:0')
epoch: 65 test_true_pfm: -13.053894578737058
episode: 260 training return: tensor(-1616.3209, device='cuda:0')
episode: 261 training return: tensor(-1618.7690, device='cuda:0')
episode: 262 training return: tensor(-1609.9739, device='cuda:0')
episode: 263 training return: tensor(-1630.2615, device='cuda:0')
epoch: 66 test_true_pfm: -14.688189030709395
episode: 264 training return: tensor(-1629.2225, device='cuda:0')
episode: 265 training return: tensor(-1616.9867, device='cuda:0')
episode: 266 training return: tensor(-1623.0165, device='cuda:0')
episode: 267 training return: tensor(-1628.9406, device='cuda:0')
epoch: 67 test_true_pfm: -10.689293041833443
episode: 268 training return: tensor(-1632.0411, device='cuda:0')
episode: 269 training return: tensor(-1597.2601, device='cuda:0')
episode: 270 training return: tensor(-1635.1438, device='cuda:0')
episode: 271 training return: tensor(-1605.2400, device='cuda:0')
epoch: 68 test_true_pfm: -15.487158751077736
episode: 272 training return: tensor(-1613.5000, device='cuda:0')
episode: 273 training return: tensor(-1637.9447, device='cuda:0')
episode: 274 training return: tensor(-1613.3248, device='cuda:0')
episode: 275 training return: tensor(-1632.9436, device='cuda:0')
epoch: 69 test_true_pfm: -16.317989194654928
episode: 276 training return: tensor(-1621.9484, device='cuda:0')
episode: 277 training return: tensor(-1621.0640, device='cuda:0')
episode: 278 training return: tensor(-1608.7860, device='cuda:0')
episode: 279 training return: tensor(-1613.0577, device='cuda:0')
epoch: 70 test_true_pfm: -18.503349313266096
episode: 280 training return: tensor(-1619.9856, device='cuda:0')
episode: 281 training return: tensor(-1610.0403, device='cuda:0')
episode: 282 training return: tensor(-1615.2417, device='cuda:0')
episode: 283 training return: tensor(-1608.4767, device='cuda:0')
epoch: 71 test_true_pfm: -13.24757095189515
episode: 284 training return: tensor(-1638.9481, device='cuda:0')
episode: 285 training return: tensor(-1620.3064, device='cuda:0')
episode: 286 training return: tensor(-1620.6786, device='cuda:0')
episode: 287 training return: tensor(-1622.1487, device='cuda:0')
epoch: 72 test_true_pfm: -13.244666552316525
episode: 288 training return: tensor(-1608.7205, device='cuda:0')
episode: 289 training return: tensor(-1592.7639, device='cuda:0')
episode: 290 training return: tensor(-1631.7893, device='cuda:0')
episode: 291 training return: tensor(-1613.2550, device='cuda:0')
epoch: 73 test_true_pfm: -16.989245136803337
episode: 292 training return: tensor(-1612.8508, device='cuda:0')
episode: 293 training return: tensor(-1605.9772, device='cuda:0')
episode: 294 training return: tensor(-1621.4192, device='cuda:0')
episode: 295 training return: tensor(-1629.4415, device='cuda:0')
epoch: 74 test_true_pfm: -17.155709430992168
episode: 296 training return: tensor(-1634.2465, device='cuda:0')
episode: 297 training return: tensor(-1624.2585, device='cuda:0')
episode: 298 training return: tensor(-1609.2885, device='cuda:0')
episode: 299 training return: tensor(-1625.6975, device='cuda:0')
epoch: 75 test_true_pfm: -15.962301440532846
episode: 300 training return: tensor(-1621.2506, device='cuda:0')
episode: 301 training return: tensor(-1601.5298, device='cuda:0')
episode: 302 training return: tensor(-1641.5671, device='cuda:0')
episode: 303 training return: tensor(-1614.1686, device='cuda:0')
epoch: 76 test_true_pfm: -12.141968078356305
episode: 304 training return: tensor(-1611.8488, device='cuda:0')
episode: 305 training return: tensor(-1613.8444, device='cuda:0')
episode: 306 training return: tensor(-1622.8513, device='cuda:0')
episode: 307 training return: tensor(-1617.2478, device='cuda:0')
epoch: 77 test_true_pfm: -14.584878001126702
episode: 308 training return: tensor(-1625.9208, device='cuda:0')
episode: 309 training return: tensor(-1607.6373, device='cuda:0')
episode: 310 training return: tensor(-1606.0616, device='cuda:0')
episode: 311 training return: tensor(-1611.8776, device='cuda:0')
epoch: 78 test_true_pfm: -12.75870776723868
episode: 312 training return: tensor(-1621.2999, device='cuda:0')
episode: 313 training return: tensor(-1611.9775, device='cuda:0')
episode: 314 training return: tensor(-1599.5863, device='cuda:0')
episode: 315 training return: tensor(-1609.3833, device='cuda:0')
epoch: 79 test_true_pfm: -16.139385304227492
episode: 316 training return: tensor(-1615.0828, device='cuda:0')
episode: 317 training return: tensor(-1623.5708, device='cuda:0')
episode: 318 training return: tensor(-1605.4857, device='cuda:0')
episode: 319 training return: tensor(-1626.4165, device='cuda:0')
epoch: 80 test_true_pfm: -15.13472202691601
episode: 320 training return: tensor(-1622.0554, device='cuda:0')
episode: 321 training return: tensor(-1624.6614, device='cuda:0')
episode: 322 training return: tensor(-1618.5239, device='cuda:0')
episode: 323 training return: tensor(-1604.9613, device='cuda:0')
epoch: 81 test_true_pfm: -13.43251169988097
episode: 324 training return: tensor(-1597.3405, device='cuda:0')
episode: 325 training return: tensor(-1597.0693, device='cuda:0')
episode: 326 training return: tensor(-1608.6514, device='cuda:0')
episode: 327 training return: tensor(-1637.2673, device='cuda:0')
epoch: 82 test_true_pfm: -13.175018845037123
episode: 328 training return: tensor(-1619.7360, device='cuda:0')
episode: 329 training return: tensor(-1623.3013, device='cuda:0')
episode: 330 training return: tensor(-1613.6130, device='cuda:0')
episode: 331 training return: tensor(-1624.9578, device='cuda:0')
epoch: 83 test_true_pfm: -12.45549902466653
episode: 332 training return: tensor(-1608.5537, device='cuda:0')
episode: 333 training return: tensor(-1608.5767, device='cuda:0')
episode: 334 training return: tensor(-1621.4187, device='cuda:0')
episode: 335 training return: tensor(-1599.7028, device='cuda:0')
epoch: 84 test_true_pfm: -18.383319939068194
episode: 336 training return: tensor(-1615.6783, device='cuda:0')
episode: 337 training return: tensor(-1603.7626, device='cuda:0')
episode: 338 training return: tensor(-1602.1145, device='cuda:0')
episode: 339 training return: tensor(-1595.5811, device='cuda:0')
epoch: 85 test_true_pfm: -14.92967781909475
episode: 340 training return: tensor(-1617.6493, device='cuda:0')
episode: 341 training return: tensor(-1618.5118, device='cuda:0')
episode: 342 training return: tensor(-1609.5068, device='cuda:0')
episode: 343 training return: tensor(-1633.0176, device='cuda:0')
epoch: 86 test_true_pfm: -13.227512221621126
episode: 344 training return: tensor(-1622.2698, device='cuda:0')
episode: 345 training return: tensor(-1612.1238, device='cuda:0')
episode: 346 training return: tensor(-1622.6071, device='cuda:0')
episode: 347 training return: tensor(-1611.5671, device='cuda:0')
epoch: 87 test_true_pfm: -11.66333681694475
episode: 348 training return: tensor(-1599.5671, device='cuda:0')
episode: 349 training return: tensor(-1606.6053, device='cuda:0')
episode: 350 training return: tensor(-1605.4072, device='cuda:0')
episode: 351 training return: tensor(-1603.7433, device='cuda:0')
epoch: 88 test_true_pfm: -12.897381490168732
episode: 352 training return: tensor(-1604.5024, device='cuda:0')
episode: 353 training return: tensor(-1618.2161, device='cuda:0')
episode: 354 training return: tensor(-1617.3583, device='cuda:0')
episode: 355 training return: tensor(-1620.9733, device='cuda:0')
epoch: 89 test_true_pfm: -14.473970787778939
episode: 356 training return: tensor(-1618.9620, device='cuda:0')
episode: 357 training return: tensor(-1604.8733, device='cuda:0')
episode: 358 training return: tensor(-1617.2878, device='cuda:0')
episode: 359 training return: tensor(-1613.1331, device='cuda:0')
epoch: 90 test_true_pfm: -12.53885769580421
episode: 360 training return: tensor(-1620.7566, device='cuda:0')
episode: 361 training return: tensor(-1615.2581, device='cuda:0')
episode: 362 training return: tensor(-1609.0762, device='cuda:0')
episode: 363 training return: tensor(-1631.5648, device='cuda:0')
epoch: 91 test_true_pfm: -14.456213039747391
episode: 364 training return: tensor(-1612.9426, device='cuda:0')
episode: 365 training return: tensor(-1609.1790, device='cuda:0')
episode: 366 training return: tensor(-1606.5977, device='cuda:0')
episode: 367 training return: tensor(-1618.0667, device='cuda:0')
epoch: 92 test_true_pfm: -16.014088456301575
episode: 368 training return: tensor(-1616.8018, device='cuda:0')
episode: 369 training return: tensor(-1611.7716, device='cuda:0')
episode: 370 training return: tensor(-1607.6271, device='cuda:0')
episode: 371 training return: tensor(-1612.4489, device='cuda:0')
epoch: 93 test_true_pfm: -11.216381760341058
episode: 372 training return: tensor(-1631.0767, device='cuda:0')
episode: 373 training return: tensor(-1605.3925, device='cuda:0')
episode: 374 training return: tensor(-1594.2382, device='cuda:0')
episode: 375 training return: tensor(-1620.2515, device='cuda:0')
epoch: 94 test_true_pfm: -10.537356706432046
episode: 376 training return: tensor(-1592.6365, device='cuda:0')
episode: 377 training return: tensor(-1603.0706, device='cuda:0')
episode: 378 training return: tensor(-1609.8213, device='cuda:0')
episode: 379 training return: tensor(-1623.9147, device='cuda:0')
epoch: 95 test_true_pfm: -10.73371222610759
episode: 380 training return: tensor(-1627.7983, device='cuda:0')
episode: 381 training return: tensor(-1612.2433, device='cuda:0')
episode: 382 training return: tensor(-1603.4154, device='cuda:0')
episode: 383 training return: tensor(-1603.7726, device='cuda:0')
epoch: 96 test_true_pfm: -9.672048348347971
episode: 384 training return: tensor(-1598.3765, device='cuda:0')
episode: 385 training return: tensor(-1621.6925, device='cuda:0')
episode: 386 training return: tensor(-1604.5670, device='cuda:0')
episode: 387 training return: tensor(-1610.5659, device='cuda:0')
epoch: 97 test_true_pfm: -15.692648381158191
episode: 388 training return: tensor(-1602.3195, device='cuda:0')
episode: 389 training return: tensor(-1622.4004, device='cuda:0')
episode: 390 training return: tensor(-1619.6576, device='cuda:0')
episode: 391 training return: tensor(-1608.6233, device='cuda:0')
epoch: 98 test_true_pfm: -13.477688343181605
episode: 392 training return: tensor(-1611.0908, device='cuda:0')
episode: 393 training return: tensor(-1601.6365, device='cuda:0')
episode: 394 training return: tensor(-1589.9928, device='cuda:0')
episode: 395 training return: tensor(-1610.4910, device='cuda:0')
epoch: 99 test_true_pfm: -14.287152968136548
episode: 396 training return: tensor(-1588.8967, device='cuda:0')
episode: 397 training return: tensor(-1611.4746, device='cuda:0')
episode: 398 training return: tensor(-1596.9724, device='cuda:0')
episode: 399 training return: tensor(-1598.2010, device='cuda:0')
epoch: 100 test_true_pfm: -13.427653247425459
episode: 400 training return: tensor(-1612.2865, device='cuda:0')
episode: 401 training return: tensor(-1611.9960, device='cuda:0')
episode: 402 training return: tensor(-1596.0685, device='cuda:0')
episode: 403 training return: tensor(-1613.6747, device='cuda:0')
epoch: 101 test_true_pfm: -15.216548331807624
episode: 404 training return: tensor(-1625.7689, device='cuda:0')
episode: 405 training return: tensor(-1618.5850, device='cuda:0')
episode: 406 training return: tensor(-1611.3185, device='cuda:0')
episode: 407 training return: tensor(-1607.2961, device='cuda:0')
epoch: 102 test_true_pfm: -12.928466146350003
episode: 408 training return: tensor(-1628.3198, device='cuda:0')
episode: 409 training return: tensor(-1607.7408, device='cuda:0')
episode: 410 training return: tensor(-1604.6520, device='cuda:0')
episode: 411 training return: tensor(-1590.2003, device='cuda:0')
epoch: 103 test_true_pfm: -11.782039077138892
episode: 412 training return: tensor(-1598.6796, device='cuda:0')
episode: 413 training return: tensor(-1620.8163, device='cuda:0')
episode: 414 training return: tensor(-1593.6124, device='cuda:0')
episode: 415 training return: tensor(-1609.6444, device='cuda:0')
epoch: 104 test_true_pfm: -12.846471422581429
episode: 416 training return: tensor(-1608.9908, device='cuda:0')
episode: 417 training return: tensor(-1610.6370, device='cuda:0')
episode: 418 training return: tensor(-1615.5959, device='cuda:0')
episode: 419 training return: tensor(-1618.9402, device='cuda:0')
epoch: 105 test_true_pfm: -12.615102970115805
episode: 420 training return: tensor(-1611.0608, device='cuda:0')
episode: 421 training return: tensor(-1615.9152, device='cuda:0')
episode: 422 training return: tensor(-1613.1071, device='cuda:0')
episode: 423 training return: tensor(-1621.0436, device='cuda:0')
epoch: 106 test_true_pfm: -13.99714074788075
episode: 424 training return: tensor(-1585.5659, device='cuda:0')
episode: 425 training return: tensor(-1613.1060, device='cuda:0')
episode: 426 training return: tensor(-1605.0896, device='cuda:0')
episode: 427 training return: tensor(-1599.5596, device='cuda:0')
epoch: 107 test_true_pfm: -15.728463319131384
episode: 428 training return: tensor(-1626.0137, device='cuda:0')
episode: 429 training return: tensor(-1600.2151, device='cuda:0')
episode: 430 training return: tensor(-1622.1796, device='cuda:0')
episode: 431 training return: tensor(-1603.3435, device='cuda:0')
epoch: 108 test_true_pfm: -18.017302564717127
episode: 432 training return: tensor(-1611.5074, device='cuda:0')
episode: 433 training return: tensor(-1598.9258, device='cuda:0')
episode: 434 training return: tensor(-1596.1667, device='cuda:0')
episode: 435 training return: tensor(-1605.9115, device='cuda:0')
epoch: 109 test_true_pfm: -16.814457503451965
episode: 436 training return: tensor(-1600.0200, device='cuda:0')
episode: 437 training return: tensor(-1594.4918, device='cuda:0')
episode: 438 training return: tensor(-1590.7311, device='cuda:0')
episode: 439 training return: tensor(-1596.9883, device='cuda:0')
epoch: 110 test_true_pfm: -14.085652125963158
episode: 440 training return: tensor(-1599.4274, device='cuda:0')
episode: 441 training return: tensor(-1600.9015, device='cuda:0')
episode: 442 training return: tensor(-1612.3591, device='cuda:0')
episode: 443 training return: tensor(-1595.9329, device='cuda:0')
epoch: 111 test_true_pfm: -14.330124976725985
episode: 444 training return: tensor(-1613.2139, device='cuda:0')
episode: 445 training return: tensor(-1607.6422, device='cuda:0')
episode: 446 training return: tensor(-1614.1025, device='cuda:0')
episode: 447 training return: tensor(-1609.6740, device='cuda:0')
epoch: 112 test_true_pfm: -12.790271641205797
episode: 448 training return: tensor(-1593.2524, device='cuda:0')
episode: 449 training return: tensor(-1620.2026, device='cuda:0')
episode: 450 training return: tensor(-1622.7783, device='cuda:0')
episode: 451 training return: tensor(-1610.0029, device='cuda:0')
epoch: 113 test_true_pfm: -10.667111605621836
episode: 452 training return: tensor(-1604.4229, device='cuda:0')
episode: 453 training return: tensor(-1621.1927, device='cuda:0')
episode: 454 training return: tensor(-1605.0538, device='cuda:0')
episode: 455 training return: tensor(-1611.6748, device='cuda:0')
epoch: 114 test_true_pfm: -6.910856290450657
episode: 456 training return: tensor(-1603.2179, device='cuda:0')
episode: 457 training return: tensor(-1609.7203, device='cuda:0')
episode: 458 training return: tensor(-1601.7015, device='cuda:0')
episode: 459 training return: tensor(-1625.8175, device='cuda:0')
epoch: 115 test_true_pfm: -11.58914139314273
episode: 460 training return: tensor(-1613.3857, device='cuda:0')
episode: 461 training return: tensor(-1596.0139, device='cuda:0')
episode: 462 training return: tensor(-1606.5216, device='cuda:0')
episode: 463 training return: tensor(-1607.3184, device='cuda:0')
epoch: 116 test_true_pfm: -11.77279505818626
episode: 464 training return: tensor(-1612.5459, device='cuda:0')
episode: 465 training return: tensor(-1599.7219, device='cuda:0')
episode: 466 training return: tensor(-1581.9041, device='cuda:0')
episode: 467 training return: tensor(-1598.9353, device='cuda:0')
epoch: 117 test_true_pfm: -13.986564976812064
episode: 468 training return: tensor(-1603.9619, device='cuda:0')
episode: 469 training return: tensor(-1602.4941, device='cuda:0')
episode: 470 training return: tensor(-1593.9104, device='cuda:0')
episode: 471 training return: tensor(-1613.6093, device='cuda:0')
epoch: 118 test_true_pfm: -14.804392585054961
episode: 472 training return: tensor(-1622.1179, device='cuda:0')
episode: 473 training return: tensor(-1596.2189, device='cuda:0')
episode: 474 training return: tensor(-1588.3751, device='cuda:0')
episode: 475 training return: tensor(-1608.0171, device='cuda:0')
epoch: 119 test_true_pfm: -13.228643084290207
episode: 476 training return: tensor(-1588.0955, device='cuda:0')
episode: 477 training return: tensor(-1611.7964, device='cuda:0')
episode: 478 training return: tensor(-1604.2101, device='cuda:0')
episode: 479 training return: tensor(-1603.1931, device='cuda:0')
epoch: 120 test_true_pfm: -14.201539022145262
episode: 480 training return: tensor(-1603.5404, device='cuda:0')
episode: 481 training return: tensor(-1594.3501, device='cuda:0')
episode: 482 training return: tensor(-1594.8477, device='cuda:0')
episode: 483 training return: tensor(-1606.2311, device='cuda:0')
epoch: 121 test_true_pfm: -7.709995633744193
episode: 484 training return: tensor(-1606.9159, device='cuda:0')
episode: 485 training return: tensor(-1599.5117, device='cuda:0')
episode: 486 training return: tensor(-1598.3583, device='cuda:0')
episode: 487 training return: tensor(-1603.1290, device='cuda:0')
epoch: 122 test_true_pfm: -16.012703204589144
episode: 488 training return: tensor(-1609.9080, device='cuda:0')
episode: 489 training return: tensor(-1604.2085, device='cuda:0')
episode: 490 training return: tensor(-1595.5496, device='cuda:0')
episode: 491 training return: tensor(-1608.8784, device='cuda:0')
epoch: 123 test_true_pfm: -13.428200256152957
episode: 492 training return: tensor(-1594.2633, device='cuda:0')
episode: 493 training return: tensor(-1590.5939, device='cuda:0')
episode: 494 training return: tensor(-1604.1847, device='cuda:0')
episode: 495 training return: tensor(-1597.3816, device='cuda:0')
epoch: 124 test_true_pfm: -11.553172905879146
episode: 496 training return: tensor(-1603.1063, device='cuda:0')
episode: 497 training return: tensor(-1595.2861, device='cuda:0')
episode: 498 training return: tensor(-1607.8612, device='cuda:0')
episode: 499 training return: tensor(-1609.8933, device='cuda:0')
epoch: 125 test_true_pfm: -13.73340063851409
episode: 500 training return: tensor(-1606.0565, device='cuda:0')
episode: 501 training return: tensor(-1594.3198, device='cuda:0')
episode: 502 training return: tensor(-1602.1844, device='cuda:0')
episode: 503 training return: tensor(-1593.5833, device='cuda:0')
epoch: 126 test_true_pfm: -9.11616580990083
episode: 504 training return: tensor(-1588.3380, device='cuda:0')
episode: 505 training return: tensor(-1600.7740, device='cuda:0')
episode: 506 training return: tensor(-1602.0919, device='cuda:0')
episode: 507 training return: tensor(-1595.2699, device='cuda:0')
epoch: 127 test_true_pfm: -14.218915438100504
episode: 508 training return: tensor(-1595.9454, device='cuda:0')
episode: 509 training return: tensor(-1598.0931, device='cuda:0')
episode: 510 training return: tensor(-1577.8748, device='cuda:0')
episode: 511 training return: tensor(-1599.0063, device='cuda:0')
epoch: 128 test_true_pfm: -11.646461842877862
episode: 512 training return: tensor(-1608.8054, device='cuda:0')
episode: 513 training return: tensor(-1607.2056, device='cuda:0')
episode: 514 training return: tensor(-1595.8973, device='cuda:0')
episode: 515 training return: tensor(-1583.9562, device='cuda:0')
epoch: 129 test_true_pfm: -12.014568395387847
episode: 516 training return: tensor(-1594.1011, device='cuda:0')
episode: 517 training return: tensor(-1609.7856, device='cuda:0')
episode: 518 training return: tensor(-1600.9922, device='cuda:0')
episode: 519 training return: tensor(-1596.1631, device='cuda:0')
epoch: 130 test_true_pfm: -11.029649565258268
episode: 520 training return: tensor(-1591.1809, device='cuda:0')
episode: 521 training return: tensor(-1614.1462, device='cuda:0')
episode: 522 training return: tensor(-1613.4258, device='cuda:0')
episode: 523 training return: tensor(-1570.4292, device='cuda:0')
epoch: 131 test_true_pfm: -9.786366079100878
episode: 524 training return: tensor(-1603.1868, device='cuda:0')
episode: 525 training return: tensor(-1605.6699, device='cuda:0')
episode: 526 training return: tensor(-1595.5321, device='cuda:0')
episode: 527 training return: tensor(-1596.2413, device='cuda:0')
epoch: 132 test_true_pfm: -12.404282542694984
episode: 528 training return: tensor(-1592.2192, device='cuda:0')
episode: 529 training return: tensor(-1600.2902, device='cuda:0')
episode: 530 training return: tensor(-1590.7627, device='cuda:0')
episode: 531 training return: tensor(-1604.2269, device='cuda:0')
epoch: 133 test_true_pfm: -14.633782749131905
episode: 532 training return: tensor(-1582.9741, device='cuda:0')
episode: 533 training return: tensor(-1591.5171, device='cuda:0')
episode: 534 training return: tensor(-1597.0991, device='cuda:0')
episode: 535 training return: tensor(-1593.3120, device='cuda:0')
epoch: 134 test_true_pfm: -12.819336402330533
episode: 536 training return: tensor(-1602.1681, device='cuda:0')
episode: 537 training return: tensor(-1594.1337, device='cuda:0')
episode: 538 training return: tensor(-1606.1505, device='cuda:0')
episode: 539 training return: tensor(-1597.9812, device='cuda:0')
epoch: 135 test_true_pfm: -17.30235764059299
episode: 540 training return: tensor(-1583.5333, device='cuda:0')
episode: 541 training return: tensor(-1572.3674, device='cuda:0')
episode: 542 training return: tensor(-1586.9003, device='cuda:0')
episode: 543 training return: tensor(-1600.1207, device='cuda:0')
epoch: 136 test_true_pfm: -12.8942934547089
episode: 544 training return: tensor(-1595.2274, device='cuda:0')
episode: 545 training return: tensor(-1579.2417, device='cuda:0')
episode: 546 training return: tensor(-1593.8422, device='cuda:0')
episode: 547 training return: tensor(-1588.5460, device='cuda:0')
epoch: 137 test_true_pfm: -10.8829364643509
episode: 548 training return: tensor(-1601.5070, device='cuda:0')
episode: 549 training return: tensor(-1600.9186, device='cuda:0')
episode: 550 training return: tensor(-1586.0748, device='cuda:0')
episode: 551 training return: tensor(-1604.7825, device='cuda:0')
epoch: 138 test_true_pfm: -16.393762638362173
episode: 552 training return: tensor(-1598.9514, device='cuda:0')
episode: 553 training return: tensor(-1592.5712, device='cuda:0')
episode: 554 training return: tensor(-1589.1466, device='cuda:0')
episode: 555 training return: tensor(-1595.5034, device='cuda:0')
epoch: 139 test_true_pfm: -12.977415810899677
episode: 556 training return: tensor(-1607.5353, device='cuda:0')
episode: 557 training return: tensor(-1573.4109, device='cuda:0')
episode: 558 training return: tensor(-1590.6963, device='cuda:0')
episode: 559 training return: tensor(-1582.6373, device='cuda:0')
epoch: 140 test_true_pfm: -14.666119243138242
episode: 560 training return: tensor(-1583.9938, device='cuda:0')
episode: 561 training return: tensor(-1589.9463, device='cuda:0')
episode: 562 training return: tensor(-1601.4240, device='cuda:0')
episode: 563 training return: tensor(-1591.4774, device='cuda:0')
epoch: 141 test_true_pfm: -15.194818534305417
episode: 564 training return: tensor(-1578.8563, device='cuda:0')
episode: 565 training return: tensor(-1592.6216, device='cuda:0')
episode: 566 training return: tensor(-1585.4611, device='cuda:0')
episode: 567 training return: tensor(-1590.5679, device='cuda:0')
epoch: 142 test_true_pfm: -14.248389795016331
episode: 568 training return: tensor(-1591.6326, device='cuda:0')
episode: 569 training return: tensor(-1597.3588, device='cuda:0')
episode: 570 training return: tensor(-1571.4651, device='cuda:0')
episode: 571 training return: tensor(-1580.7607, device='cuda:0')
epoch: 143 test_true_pfm: -17.32246757294457
episode: 572 training return: tensor(-1588.5215, device='cuda:0')
episode: 573 training return: tensor(-1586.3129, device='cuda:0')
episode: 574 training return: tensor(-1580.1241, device='cuda:0')
episode: 575 training return: tensor(-1586.2100, device='cuda:0')
epoch: 144 test_true_pfm: -20.10837969557844
episode: 576 training return: tensor(-1591.1621, device='cuda:0')
episode: 577 training return: tensor(-1590.4258, device='cuda:0')
episode: 578 training return: tensor(-1579.9542, device='cuda:0')
episode: 579 training return: tensor(-1606.0128, device='cuda:0')
epoch: 145 test_true_pfm: -15.866892630263164
episode: 580 training return: tensor(-1588.0853, device='cuda:0')
episode: 581 training return: tensor(-1605.8978, device='cuda:0')
episode: 582 training return: tensor(-1598.9073, device='cuda:0')
episode: 583 training return: tensor(-1589.0995, device='cuda:0')
epoch: 146 test_true_pfm: -12.651305689819539
episode: 584 training return: tensor(-1589.1936, device='cuda:0')
episode: 585 training return: tensor(-1588.5929, device='cuda:0')
episode: 586 training return: tensor(-1589.8779, device='cuda:0')
episode: 587 training return: tensor(-1583.5927, device='cuda:0')
epoch: 147 test_true_pfm: -11.240037795313578
episode: 588 training return: tensor(-1603.8267, device='cuda:0')
episode: 589 training return: tensor(-1599.4901, device='cuda:0')
episode: 590 training return: tensor(-1605.8673, device='cuda:0')
episode: 591 training return: tensor(-1598.5613, device='cuda:0')
epoch: 148 test_true_pfm: -14.95531765616363
episode: 592 training return: tensor(-1590.0809, device='cuda:0')
episode: 593 training return: tensor(-1586.3956, device='cuda:0')
episode: 594 training return: tensor(-1597.7380, device='cuda:0')
episode: 595 training return: tensor(-1595.9164, device='cuda:0')
epoch: 149 test_true_pfm: -12.451738193039235
episode: 596 training return: tensor(-1584.0089, device='cuda:0')
episode: 597 training return: tensor(-1584.6562, device='cuda:0')
episode: 598 training return: tensor(-1596.0701, device='cuda:0')
episode: 599 training return: tensor(-1576.5387, device='cuda:0')
epoch: 150 test_true_pfm: -12.487544814956301
