['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'brac', '--traj', 'medium', '--seed', '1', '--data', '100000']
4991.992902170758
episode: 0 training return: tensor(-4404.4761, device='cuda:0')
episode: 1 training return: tensor(-4751.9146, device='cuda:0')
episode: 2 training return: tensor(-5210.9595, device='cuda:0')
episode: 3 training return: tensor(-4209.1465, device='cuda:0')
epoch: 1 test_true_pfm: 714.5431764338135
episode: 4 training return: tensor(-2738.6667, device='cuda:0')
episode: 5 training return: tensor(-5791.9028, device='cuda:0')
episode: 6 training return: tensor(-3796.7241, device='cuda:0')
episode: 7 training return: tensor(-4177.5654, device='cuda:0')
epoch: 2 test_true_pfm: 728.3275344261791
episode: 8 training return: tensor(-5470.0278, device='cuda:0')
episode: 9 training return: tensor(-5044.0674, device='cuda:0')
episode: 10 training return: tensor(-2910.7749, device='cuda:0')
episode: 11 training return: tensor(-1597.8149, device='cuda:0')
epoch: 3 test_true_pfm: 28.188779590760685
episode: 12 training return: tensor(-1742.0916, device='cuda:0')
episode: 13 training return: tensor(-1651.6498, device='cuda:0')
episode: 14 training return: tensor(-1671.3899, device='cuda:0')
episode: 15 training return: tensor(-1649.8398, device='cuda:0')
epoch: 4 test_true_pfm: -5.212716908267567
episode: 16 training return: tensor(-1842.7623, device='cuda:0')
episode: 17 training return: tensor(-1888.8257, device='cuda:0')
episode: 18 training return: tensor(-1699.0426, device='cuda:0')
episode: 19 training return: tensor(-1668.9034, device='cuda:0')
epoch: 5 test_true_pfm: 0.7582356995649876
episode: 20 training return: tensor(-1873.1368, device='cuda:0')
episode: 21 training return: tensor(-1671.4307, device='cuda:0')
episode: 22 training return: tensor(-1658.7700, device='cuda:0')
episode: 23 training return: tensor(-1682.1398, device='cuda:0')
epoch: 6 test_true_pfm: -18.022861593569974
episode: 24 training return: tensor(-1651.7909, device='cuda:0')
episode: 25 training return: tensor(-1663.9146, device='cuda:0')
episode: 26 training return: tensor(-1680.5897, device='cuda:0')
episode: 27 training return: tensor(-1664.6522, device='cuda:0')
epoch: 7 test_true_pfm: -6.589255618216554
episode: 28 training return: tensor(-1653.8569, device='cuda:0')
episode: 29 training return: tensor(-1642.7847, device='cuda:0')
episode: 30 training return: tensor(-1642.7141, device='cuda:0')
episode: 31 training return: tensor(-1651.9399, device='cuda:0')
epoch: 8 test_true_pfm: -15.909269451345766
episode: 32 training return: tensor(-1668.2545, device='cuda:0')
episode: 33 training return: tensor(-1639.6753, device='cuda:0')
episode: 34 training return: tensor(-1635.3749, device='cuda:0')
episode: 35 training return: tensor(-1636.6388, device='cuda:0')
epoch: 9 test_true_pfm: -21.67383123202308
episode: 36 training return: tensor(-1650.4817, device='cuda:0')
episode: 37 training return: tensor(-1626.1267, device='cuda:0')
episode: 38 training return: tensor(-1631.7235, device='cuda:0')
episode: 39 training return: tensor(-1647.9570, device='cuda:0')
epoch: 10 test_true_pfm: -19.655254283506036
episode: 40 training return: tensor(-1658.4315, device='cuda:0')
episode: 41 training return: tensor(-1627.3550, device='cuda:0')
episode: 42 training return: tensor(-1675.3121, device='cuda:0')
episode: 43 training return: tensor(-1637.2003, device='cuda:0')
epoch: 11 test_true_pfm: -28.937609295825087
episode: 44 training return: tensor(-1680.1572, device='cuda:0')
episode: 45 training return: tensor(-1638.8330, device='cuda:0')
episode: 46 training return: tensor(-1637.4580, device='cuda:0')
episode: 47 training return: tensor(-1632.0109, device='cuda:0')
epoch: 12 test_true_pfm: -17.76711047286086
episode: 48 training return: tensor(-1754.3906, device='cuda:0')
episode: 49 training return: tensor(-1647.7916, device='cuda:0')
episode: 50 training return: tensor(-1652.0680, device='cuda:0')
episode: 51 training return: tensor(-1651.8861, device='cuda:0')
epoch: 13 test_true_pfm: -17.414747574323403
episode: 52 training return: tensor(-1648.7709, device='cuda:0')
episode: 53 training return: tensor(-1656.0654, device='cuda:0')
episode: 54 training return: tensor(-1673.1281, device='cuda:0')
episode: 55 training return: tensor(-1659.8488, device='cuda:0')
epoch: 14 test_true_pfm: -3.55073716546914
episode: 56 training return: tensor(-1651.6726, device='cuda:0')
episode: 57 training return: tensor(-1643.6494, device='cuda:0')
episode: 58 training return: tensor(-1653.2059, device='cuda:0')
episode: 59 training return: tensor(-1649.5663, device='cuda:0')
epoch: 15 test_true_pfm: -11.032117507080189
episode: 60 training return: tensor(-1665.0854, device='cuda:0')
episode: 61 training return: tensor(-1653.3593, device='cuda:0')
episode: 62 training return: tensor(-1660.9994, device='cuda:0')
episode: 63 training return: tensor(-1652.5056, device='cuda:0')
epoch: 16 test_true_pfm: 0.17645998831446508
episode: 64 training return: tensor(-1665.8496, device='cuda:0')
episode: 65 training return: tensor(-1641.6647, device='cuda:0')
episode: 66 training return: tensor(-1650.6096, device='cuda:0')
episode: 67 training return: tensor(-1652.2477, device='cuda:0')
epoch: 17 test_true_pfm: -11.886816039964948
episode: 68 training return: tensor(-1641.6730, device='cuda:0')
episode: 69 training return: tensor(-1661.2512, device='cuda:0')
episode: 70 training return: tensor(-1677.9568, device='cuda:0')
episode: 71 training return: tensor(-1660.8353, device='cuda:0')
epoch: 18 test_true_pfm: -8.772699885113395
episode: 72 training return: tensor(-1670.9119, device='cuda:0')
episode: 73 training return: tensor(-1671.6925, device='cuda:0')
episode: 74 training return: tensor(-1666.3110, device='cuda:0')
episode: 75 training return: tensor(-1667.2935, device='cuda:0')
epoch: 19 test_true_pfm: -2.8530694273117554
episode: 76 training return: tensor(-1652.2386, device='cuda:0')
episode: 77 training return: tensor(-1669.8688, device='cuda:0')
episode: 78 training return: tensor(-1668.1951, device='cuda:0')
episode: 79 training return: tensor(-1650.6481, device='cuda:0')
epoch: 20 test_true_pfm: -3.283772447401527
episode: 80 training return: tensor(-1669.2382, device='cuda:0')
episode: 81 training return: tensor(-1647.9922, device='cuda:0')
episode: 82 training return: tensor(-1651.9181, device='cuda:0')
episode: 83 training return: tensor(-1668.7367, device='cuda:0')
epoch: 21 test_true_pfm: -7.185530480067842
episode: 84 training return: tensor(-1654.7490, device='cuda:0')
episode: 85 training return: tensor(-1660.4194, device='cuda:0')
episode: 86 training return: tensor(-1656.1614, device='cuda:0')
episode: 87 training return: tensor(-1641.3721, device='cuda:0')
epoch: 22 test_true_pfm: -6.285671272959521
episode: 88 training return: tensor(-1662.7333, device='cuda:0')
episode: 89 training return: tensor(-1643.3474, device='cuda:0')
episode: 90 training return: tensor(-1671.8527, device='cuda:0')
episode: 91 training return: tensor(-1649.3876, device='cuda:0')
epoch: 23 test_true_pfm: -16.056404704913557
episode: 92 training return: tensor(-1670.8851, device='cuda:0')
episode: 93 training return: tensor(-1667.8802, device='cuda:0')
episode: 94 training return: tensor(-1652.2781, device='cuda:0')
episode: 95 training return: tensor(-1658.5977, device='cuda:0')
epoch: 24 test_true_pfm: -9.928038135897227
episode: 96 training return: tensor(-1678.1238, device='cuda:0')
episode: 97 training return: tensor(-1667.0493, device='cuda:0')
episode: 98 training return: tensor(-1641.7468, device='cuda:0')
episode: 99 training return: tensor(-1660.1553, device='cuda:0')
epoch: 25 test_true_pfm: -16.27252446781944
episode: 100 training return: tensor(-1667.0504, device='cuda:0')
episode: 101 training return: tensor(-1639.9550, device='cuda:0')
episode: 102 training return: tensor(-1671.1013, device='cuda:0')
episode: 103 training return: tensor(-1675.5269, device='cuda:0')
epoch: 26 test_true_pfm: 0.31259928178607127
episode: 104 training return: tensor(-1663.0347, device='cuda:0')
episode: 105 training return: tensor(-1656.1119, device='cuda:0')
episode: 106 training return: tensor(-1657.0671, device='cuda:0')
episode: 107 training return: tensor(-1670.5768, device='cuda:0')
epoch: 27 test_true_pfm: -2.365780612234347
episode: 108 training return: tensor(-1654.9912, device='cuda:0')
episode: 109 training return: tensor(-1672.3442, device='cuda:0')
episode: 110 training return: tensor(-1651.0082, device='cuda:0')
episode: 111 training return: tensor(-1658.0024, device='cuda:0')
epoch: 28 test_true_pfm: -6.072013290440981
episode: 112 training return: tensor(-1625.1124, device='cuda:0')
episode: 113 training return: tensor(-1667.0149, device='cuda:0')
episode: 114 training return: tensor(-1648.7788, device='cuda:0')
episode: 115 training return: tensor(-1653.6624, device='cuda:0')
epoch: 29 test_true_pfm: -4.104932092857954
episode: 116 training return: tensor(-1667.6152, device='cuda:0')
episode: 117 training return: tensor(-1624.8021, device='cuda:0')
episode: 118 training return: tensor(-1657.4309, device='cuda:0')
episode: 119 training return: tensor(-1669.5471, device='cuda:0')
epoch: 30 test_true_pfm: -1.6900139518915946
episode: 120 training return: tensor(-1639.9611, device='cuda:0')
episode: 121 training return: tensor(-1649.6826, device='cuda:0')
episode: 122 training return: tensor(-1644.1425, device='cuda:0')
episode: 123 training return: tensor(-1664.0609, device='cuda:0')
epoch: 31 test_true_pfm: -3.9601330114401976
episode: 124 training return: tensor(-1689.3976, device='cuda:0')
episode: 125 training return: tensor(-1636.4078, device='cuda:0')
episode: 126 training return: tensor(-1670.5577, device='cuda:0')
episode: 127 training return: tensor(-1666.2693, device='cuda:0')
epoch: 32 test_true_pfm: -2.7676240405893218
episode: 128 training return: tensor(-1665.1417, device='cuda:0')
episode: 129 training return: tensor(-1637.0876, device='cuda:0')
episode: 130 training return: tensor(-1655.8181, device='cuda:0')
episode: 131 training return: tensor(-1639.9451, device='cuda:0')
epoch: 33 test_true_pfm: 1.2244660719075593
episode: 132 training return: tensor(-1650.0206, device='cuda:0')
episode: 133 training return: tensor(-1640.9187, device='cuda:0')
episode: 134 training return: tensor(-1654.0106, device='cuda:0')
episode: 135 training return: tensor(-1651.6477, device='cuda:0')
epoch: 34 test_true_pfm: -0.4459316920839927
episode: 136 training return: tensor(-1630.8175, device='cuda:0')
episode: 137 training return: tensor(-1629.9968, device='cuda:0')
episode: 138 training return: tensor(-1656.2749, device='cuda:0')
episode: 139 training return: tensor(-1636.5597, device='cuda:0')
epoch: 35 test_true_pfm: -3.7245715529770287
episode: 140 training return: tensor(-1640.2656, device='cuda:0')
episode: 141 training return: tensor(-1666.1228, device='cuda:0')
episode: 142 training return: tensor(-1633.0970, device='cuda:0')
episode: 143 training return: tensor(-1631.2719, device='cuda:0')
epoch: 36 test_true_pfm: -6.124479401500648
episode: 144 training return: tensor(-1637.5692, device='cuda:0')
episode: 145 training return: tensor(-1650.8606, device='cuda:0')
episode: 146 training return: tensor(-1643.6658, device='cuda:0')
episode: 147 training return: tensor(-1645.8232, device='cuda:0')
epoch: 37 test_true_pfm: -3.2821555631167083
episode: 148 training return: tensor(-1641.7233, device='cuda:0')
episode: 149 training return: tensor(-1643.8831, device='cuda:0')
episode: 150 training return: tensor(-1643.1432, device='cuda:0')
episode: 151 training return: tensor(-1638.4399, device='cuda:0')
epoch: 38 test_true_pfm: -11.54585163796223
episode: 152 training return: tensor(-1653.7626, device='cuda:0')
episode: 153 training return: tensor(-1637.2396, device='cuda:0')
episode: 154 training return: tensor(-1652.8918, device='cuda:0')
episode: 155 training return: tensor(-1659.5377, device='cuda:0')
epoch: 39 test_true_pfm: -4.866077075241175
episode: 156 training return: tensor(-1653.0284, device='cuda:0')
episode: 157 training return: tensor(-1651.3082, device='cuda:0')
episode: 158 training return: tensor(-1656.1002, device='cuda:0')
episode: 159 training return: tensor(-1651.2615, device='cuda:0')
epoch: 40 test_true_pfm: -1.0775149945711517
episode: 160 training return: tensor(-1652.3080, device='cuda:0')
episode: 161 training return: tensor(-1650.1746, device='cuda:0')
episode: 162 training return: tensor(-1675.9501, device='cuda:0')
episode: 163 training return: tensor(-1647.5466, device='cuda:0')
epoch: 41 test_true_pfm: -5.20887348032282
episode: 164 training return: tensor(-1638.6039, device='cuda:0')
episode: 165 training return: tensor(-1624.8969, device='cuda:0')
episode: 166 training return: tensor(-1626.7849, device='cuda:0')
episode: 167 training return: tensor(-1664.7273, device='cuda:0')
epoch: 42 test_true_pfm: -8.967036752815625
episode: 168 training return: tensor(-1634.4620, device='cuda:0')
episode: 169 training return: tensor(-1654.1981, device='cuda:0')
episode: 170 training return: tensor(-1644.0917, device='cuda:0')
episode: 171 training return: tensor(-1633.1624, device='cuda:0')
epoch: 43 test_true_pfm: -7.188145710246413
episode: 172 training return: tensor(-1642.2751, device='cuda:0')
episode: 173 training return: tensor(-1634.7308, device='cuda:0')
episode: 174 training return: tensor(-1636.4553, device='cuda:0')
episode: 175 training return: tensor(-1621.9017, device='cuda:0')
epoch: 44 test_true_pfm: -5.680263351539865
episode: 176 training return: tensor(-1640.5590, device='cuda:0')
episode: 177 training return: tensor(-1650.3629, device='cuda:0')
episode: 178 training return: tensor(-1637.0365, device='cuda:0')
episode: 179 training return: tensor(-1633.5874, device='cuda:0')
epoch: 45 test_true_pfm: -5.745081996378001
episode: 180 training return: tensor(-1626.8475, device='cuda:0')
episode: 181 training return: tensor(-1629.2842, device='cuda:0')
episode: 182 training return: tensor(-1644.4263, device='cuda:0')
episode: 183 training return: tensor(-1645.9766, device='cuda:0')
epoch: 46 test_true_pfm: -5.3480855680568835
episode: 184 training return: tensor(-1628.7482, device='cuda:0')
episode: 185 training return: tensor(-1650.8420, device='cuda:0')
episode: 186 training return: tensor(-1649.6140, device='cuda:0')
episode: 187 training return: tensor(-1642.0653, device='cuda:0')
epoch: 47 test_true_pfm: -3.905265184909384
episode: 188 training return: tensor(-1622.7941, device='cuda:0')
episode: 189 training return: tensor(-1642.0524, device='cuda:0')
episode: 190 training return: tensor(-1625.2924, device='cuda:0')
episode: 191 training return: tensor(-1617.0530, device='cuda:0')
epoch: 48 test_true_pfm: -2.679827802494888
episode: 192 training return: tensor(-1634.5184, device='cuda:0')
episode: 193 training return: tensor(-1645.1954, device='cuda:0')
episode: 194 training return: tensor(-1621.3051, device='cuda:0')
episode: 195 training return: tensor(-1618.0026, device='cuda:0')
epoch: 49 test_true_pfm: -5.790287461098135
episode: 196 training return: tensor(-1634.1895, device='cuda:0')
episode: 197 training return: tensor(-1635.7410, device='cuda:0')
episode: 198 training return: tensor(-1629.4011, device='cuda:0')
episode: 199 training return: tensor(-1635.6783, device='cuda:0')
epoch: 50 test_true_pfm: -4.932995228994191
episode: 200 training return: tensor(-1645.3806, device='cuda:0')
episode: 201 training return: tensor(-1634.8927, device='cuda:0')
episode: 202 training return: tensor(-1643.7258, device='cuda:0')
episode: 203 training return: tensor(-1647.3975, device='cuda:0')
epoch: 51 test_true_pfm: -5.44828589492802
episode: 204 training return: tensor(-1646.4138, device='cuda:0')
episode: 205 training return: tensor(-1637.8860, device='cuda:0')
episode: 206 training return: tensor(-1626.2581, device='cuda:0')
episode: 207 training return: tensor(-1629.7003, device='cuda:0')
epoch: 52 test_true_pfm: -3.5270373433427125
episode: 208 training return: tensor(-1635.0317, device='cuda:0')
episode: 209 training return: tensor(-1644.3322, device='cuda:0')
episode: 210 training return: tensor(-1636.7958, device='cuda:0')
episode: 211 training return: tensor(-1634.7500, device='cuda:0')
epoch: 53 test_true_pfm: 0.24922008458200673
episode: 212 training return: tensor(-1640.1417, device='cuda:0')
episode: 213 training return: tensor(-1633.8223, device='cuda:0')
episode: 214 training return: tensor(-1652.1552, device='cuda:0')
episode: 215 training return: tensor(-1654.8580, device='cuda:0')
epoch: 54 test_true_pfm: -1.7820260856049688
episode: 216 training return: tensor(-1644.4067, device='cuda:0')
episode: 217 training return: tensor(-1633.2927, device='cuda:0')
episode: 218 training return: tensor(-1629.5598, device='cuda:0')
episode: 219 training return: tensor(-1635.3910, device='cuda:0')
epoch: 55 test_true_pfm: -5.550254899272357
episode: 220 training return: tensor(-1634.4858, device='cuda:0')
episode: 221 training return: tensor(-1628.6018, device='cuda:0')
episode: 222 training return: tensor(-1640.9438, device='cuda:0')
episode: 223 training return: tensor(-1643.1682, device='cuda:0')
epoch: 56 test_true_pfm: -7.371873307560741
episode: 224 training return: tensor(-1635.8293, device='cuda:0')
episode: 225 training return: tensor(-1639.7046, device='cuda:0')
episode: 226 training return: tensor(-1620.5385, device='cuda:0')
episode: 227 training return: tensor(-1626.5559, device='cuda:0')
epoch: 57 test_true_pfm: -4.397422558168812
episode: 228 training return: tensor(-1633.1968, device='cuda:0')
episode: 229 training return: tensor(-1625.3312, device='cuda:0')
episode: 230 training return: tensor(-1634.7433, device='cuda:0')
episode: 231 training return: tensor(-1634.4890, device='cuda:0')
epoch: 58 test_true_pfm: -1.2108650601124618
episode: 232 training return: tensor(-1619.5305, device='cuda:0')
episode: 233 training return: tensor(-1628.3656, device='cuda:0')
episode: 234 training return: tensor(-1638.2114, device='cuda:0')
episode: 235 training return: tensor(-1632.4855, device='cuda:0')
epoch: 59 test_true_pfm: -5.349863656636285
episode: 236 training return: tensor(-1640.9987, device='cuda:0')
episode: 237 training return: tensor(-1628.2809, device='cuda:0')
episode: 238 training return: tensor(-1635.2719, device='cuda:0')
episode: 239 training return: tensor(-1636.7512, device='cuda:0')
epoch: 60 test_true_pfm: -10.915730240535844
episode: 240 training return: tensor(-1624.2485, device='cuda:0')
episode: 241 training return: tensor(-1617.1952, device='cuda:0')
episode: 242 training return: tensor(-1626.4865, device='cuda:0')
episode: 243 training return: tensor(-1650.7268, device='cuda:0')
epoch: 61 test_true_pfm: -2.671457698581151
episode: 244 training return: tensor(-1629.2480, device='cuda:0')
episode: 245 training return: tensor(-1623.6752, device='cuda:0')
episode: 246 training return: tensor(-1635.9165, device='cuda:0')
episode: 247 training return: tensor(-1628.4313, device='cuda:0')
epoch: 62 test_true_pfm: -6.260783677037124
episode: 248 training return: tensor(-1623.5510, device='cuda:0')
episode: 249 training return: tensor(-1622.7524, device='cuda:0')
episode: 250 training return: tensor(-1644.0809, device='cuda:0')
episode: 251 training return: tensor(-1633.5403, device='cuda:0')
epoch: 63 test_true_pfm: -2.884856684867353
episode: 252 training return: tensor(-1621.4264, device='cuda:0')
episode: 253 training return: tensor(-1628.5187, device='cuda:0')
episode: 254 training return: tensor(-1652.6460, device='cuda:0')
episode: 255 training return: tensor(-1646.5370, device='cuda:0')
epoch: 64 test_true_pfm: -3.3168984443359135
episode: 256 training return: tensor(-1629.8849, device='cuda:0')
episode: 257 training return: tensor(-1632.5747, device='cuda:0')
episode: 258 training return: tensor(-1648.7831, device='cuda:0')
episode: 259 training return: tensor(-1634.3041, device='cuda:0')
epoch: 65 test_true_pfm: -9.402676289019839
episode: 260 training return: tensor(-1636.8837, device='cuda:0')
episode: 261 training return: tensor(-1621.7965, device='cuda:0')
episode: 262 training return: tensor(-1623.0887, device='cuda:0')
episode: 263 training return: tensor(-1620.9902, device='cuda:0')
epoch: 66 test_true_pfm: -1.8086029348178085
episode: 264 training return: tensor(-1636.1157, device='cuda:0')
episode: 265 training return: tensor(-1612.1289, device='cuda:0')
episode: 266 training return: tensor(-1639.6851, device='cuda:0')
episode: 267 training return: tensor(-1635.0134, device='cuda:0')
epoch: 67 test_true_pfm: -8.53393860141537
episode: 268 training return: tensor(-1622.8326, device='cuda:0')
episode: 269 training return: tensor(-1631.1576, device='cuda:0')
episode: 270 training return: tensor(-1641.9106, device='cuda:0')
episode: 271 training return: tensor(-1634.5088, device='cuda:0')
epoch: 68 test_true_pfm: -0.10386457531361215
episode: 272 training return: tensor(-1620.4569, device='cuda:0')
episode: 273 training return: tensor(-1633.4629, device='cuda:0')
episode: 274 training return: tensor(-1646.0760, device='cuda:0')
episode: 275 training return: tensor(-1634.6826, device='cuda:0')
epoch: 69 test_true_pfm: -4.302174477722349
episode: 276 training return: tensor(-1615.5923, device='cuda:0')
episode: 277 training return: tensor(-1626.6920, device='cuda:0')
episode: 278 training return: tensor(-1616.7236, device='cuda:0')
episode: 279 training return: tensor(-1623.0768, device='cuda:0')
epoch: 70 test_true_pfm: -2.7872417022136644
episode: 280 training return: tensor(-1618.1350, device='cuda:0')
episode: 281 training return: tensor(-1622.9895, device='cuda:0')
episode: 282 training return: tensor(-1639.2523, device='cuda:0')
episode: 283 training return: tensor(-1637.3344, device='cuda:0')
epoch: 71 test_true_pfm: -11.822120840661517
episode: 284 training return: tensor(-1627.9713, device='cuda:0')
episode: 285 training return: tensor(-1624.2731, device='cuda:0')
episode: 286 training return: tensor(-1642.6403, device='cuda:0')
episode: 287 training return: tensor(-1621.3206, device='cuda:0')
epoch: 72 test_true_pfm: -3.665593513084449
episode: 288 training return: tensor(-1629.7729, device='cuda:0')
episode: 289 training return: tensor(-1633.1465, device='cuda:0')
episode: 290 training return: tensor(-1620.6281, device='cuda:0')
episode: 291 training return: tensor(-1621.0049, device='cuda:0')
epoch: 73 test_true_pfm: -4.967505842297031
episode: 292 training return: tensor(-1616.2301, device='cuda:0')
episode: 293 training return: tensor(-1616.3542, device='cuda:0')
episode: 294 training return: tensor(-1632.5474, device='cuda:0')
episode: 295 training return: tensor(-1619.6453, device='cuda:0')
epoch: 74 test_true_pfm: -11.503507871018563
episode: 296 training return: tensor(-1612.7719, device='cuda:0')
episode: 297 training return: tensor(-1629.8694, device='cuda:0')
episode: 298 training return: tensor(-1640.5250, device='cuda:0')
episode: 299 training return: tensor(-1625.9150, device='cuda:0')
epoch: 75 test_true_pfm: -3.2908111785758707
episode: 300 training return: tensor(-1622.2959, device='cuda:0')
episode: 301 training return: tensor(-1635.4730, device='cuda:0')
episode: 302 training return: tensor(-1620.8236, device='cuda:0')
episode: 303 training return: tensor(-1637.4875, device='cuda:0')
epoch: 76 test_true_pfm: -1.7968496011271418
episode: 304 training return: tensor(-1624.5756, device='cuda:0')
episode: 305 training return: tensor(-1621.7502, device='cuda:0')
episode: 306 training return: tensor(-1619.6439, device='cuda:0')
episode: 307 training return: tensor(-1640.7725, device='cuda:0')
epoch: 77 test_true_pfm: 0.40779760424143857
episode: 308 training return: tensor(-1615.2163, device='cuda:0')
episode: 309 training return: tensor(-1626.6722, device='cuda:0')
episode: 310 training return: tensor(-1630.8152, device='cuda:0')
episode: 311 training return: tensor(-1632.8885, device='cuda:0')
epoch: 78 test_true_pfm: -2.117957857455368
episode: 312 training return: tensor(-1617.4987, device='cuda:0')
episode: 313 training return: tensor(-1638.5336, device='cuda:0')
episode: 314 training return: tensor(-1615.0913, device='cuda:0')
episode: 315 training return: tensor(-1611.0935, device='cuda:0')
epoch: 79 test_true_pfm: -3.9400926547642343
episode: 316 training return: tensor(-1615.6335, device='cuda:0')
episode: 317 training return: tensor(-1613.5874, device='cuda:0')
episode: 318 training return: tensor(-1617.9696, device='cuda:0')
episode: 319 training return: tensor(-1625.3934, device='cuda:0')
epoch: 80 test_true_pfm: -5.125233652424874
episode: 320 training return: tensor(-1633.3613, device='cuda:0')
episode: 321 training return: tensor(-1621.0574, device='cuda:0')
episode: 322 training return: tensor(-1636.9011, device='cuda:0')
episode: 323 training return: tensor(-1613.0757, device='cuda:0')
epoch: 81 test_true_pfm: -8.186816418063263
episode: 324 training return: tensor(-1621.5074, device='cuda:0')
episode: 325 training return: tensor(-1625.2961, device='cuda:0')
episode: 326 training return: tensor(-1617.2367, device='cuda:0')
episode: 327 training return: tensor(-1630.4344, device='cuda:0')
epoch: 82 test_true_pfm: -3.7943316167069576
episode: 328 training return: tensor(-1621.7880, device='cuda:0')
episode: 329 training return: tensor(-1635.2460, device='cuda:0')
episode: 330 training return: tensor(-1613.3035, device='cuda:0')
episode: 331 training return: tensor(-1631.0040, device='cuda:0')
epoch: 83 test_true_pfm: -5.784398340362817
episode: 332 training return: tensor(-1625.8329, device='cuda:0')
episode: 333 training return: tensor(-1613.2654, device='cuda:0')
episode: 334 training return: tensor(-1623.0927, device='cuda:0')
episode: 335 training return: tensor(-1610.0349, device='cuda:0')
epoch: 84 test_true_pfm: -1.8375995400009835
episode: 336 training return: tensor(-1617.8380, device='cuda:0')
episode: 337 training return: tensor(-1623.5510, device='cuda:0')
episode: 338 training return: tensor(-1629.2642, device='cuda:0')
episode: 339 training return: tensor(-1601.5645, device='cuda:0')
epoch: 85 test_true_pfm: -0.5158862087686306
episode: 340 training return: tensor(-1635.3428, device='cuda:0')
episode: 341 training return: tensor(-1610.1312, device='cuda:0')
episode: 342 training return: tensor(-1646.6819, device='cuda:0')
episode: 343 training return: tensor(-1630.2065, device='cuda:0')
epoch: 86 test_true_pfm: 1.613375887449193
episode: 344 training return: tensor(-1614.0070, device='cuda:0')
episode: 345 training return: tensor(-1628.3884, device='cuda:0')
episode: 346 training return: tensor(-1614.7952, device='cuda:0')
episode: 347 training return: tensor(-1622.0072, device='cuda:0')
epoch: 87 test_true_pfm: -2.522412838706301
episode: 348 training return: tensor(-1616.8411, device='cuda:0')
episode: 349 training return: tensor(-1625.1187, device='cuda:0')
episode: 350 training return: tensor(-1622.3016, device='cuda:0')
episode: 351 training return: tensor(-1621.4353, device='cuda:0')
epoch: 88 test_true_pfm: -1.201433351133231
episode: 352 training return: tensor(-1617.8516, device='cuda:0')
episode: 353 training return: tensor(-1606.3875, device='cuda:0')
episode: 354 training return: tensor(-1631.4996, device='cuda:0')
episode: 355 training return: tensor(-1650.9941, device='cuda:0')
epoch: 89 test_true_pfm: -4.7780561208236385
episode: 356 training return: tensor(-1621.9867, device='cuda:0')
episode: 357 training return: tensor(-1622.2078, device='cuda:0')
episode: 358 training return: tensor(-1599.5468, device='cuda:0')
episode: 359 training return: tensor(-1626.0033, device='cuda:0')
epoch: 90 test_true_pfm: -3.6274731341200215
episode: 360 training return: tensor(-1638.8468, device='cuda:0')
episode: 361 training return: tensor(-1623.2587, device='cuda:0')
episode: 362 training return: tensor(-1617.3954, device='cuda:0')
episode: 363 training return: tensor(-1624.6489, device='cuda:0')
epoch: 91 test_true_pfm: -2.510132053050062
episode: 364 training return: tensor(-1625.0065, device='cuda:0')
episode: 365 training return: tensor(-1615.6052, device='cuda:0')
episode: 366 training return: tensor(-1619.5889, device='cuda:0')
episode: 367 training return: tensor(-1641.3571, device='cuda:0')
epoch: 92 test_true_pfm: -4.716156974925223
episode: 368 training return: tensor(-1631.3457, device='cuda:0')
episode: 369 training return: tensor(-1644.7384, device='cuda:0')
episode: 370 training return: tensor(-1613.8732, device='cuda:0')
episode: 371 training return: tensor(-1625.0891, device='cuda:0')
epoch: 93 test_true_pfm: -5.6694996250299345
episode: 372 training return: tensor(-1613.9808, device='cuda:0')
episode: 373 training return: tensor(-1622.0388, device='cuda:0')
episode: 374 training return: tensor(-1631.1824, device='cuda:0')
episode: 375 training return: tensor(-1624.7834, device='cuda:0')
epoch: 94 test_true_pfm: -3.0457441395291567
episode: 376 training return: tensor(-1621.0125, device='cuda:0')
episode: 377 training return: tensor(-1630.0983, device='cuda:0')
episode: 378 training return: tensor(-1609.9032, device='cuda:0')
episode: 379 training return: tensor(-1613.8628, device='cuda:0')
epoch: 95 test_true_pfm: -1.4685541110018654
episode: 380 training return: tensor(-1621.7341, device='cuda:0')
episode: 381 training return: tensor(-1625.4739, device='cuda:0')
episode: 382 training return: tensor(-1644.8582, device='cuda:0')
episode: 383 training return: tensor(-1611.1184, device='cuda:0')
epoch: 96 test_true_pfm: -7.472679210355049
episode: 384 training return: tensor(-1605.8785, device='cuda:0')
episode: 385 training return: tensor(-1627.5234, device='cuda:0')
episode: 386 training return: tensor(-1619.7634, device='cuda:0')
episode: 387 training return: tensor(-1619.8577, device='cuda:0')
epoch: 97 test_true_pfm: -8.112664237463678
episode: 388 training return: tensor(-1616.7317, device='cuda:0')
episode: 389 training return: tensor(-1629.7917, device='cuda:0')
episode: 390 training return: tensor(-1620.0768, device='cuda:0')
episode: 391 training return: tensor(-1610.8170, device='cuda:0')
epoch: 98 test_true_pfm: -10.621113930404151
episode: 392 training return: tensor(-1616.4025, device='cuda:0')
episode: 393 training return: tensor(-1617.2939, device='cuda:0')
episode: 394 training return: tensor(-1635.3038, device='cuda:0')
episode: 395 training return: tensor(-1631.4137, device='cuda:0')
epoch: 99 test_true_pfm: -7.650301817272276
episode: 396 training return: tensor(-1625.9542, device='cuda:0')
episode: 397 training return: tensor(-1621.7765, device='cuda:0')
episode: 398 training return: tensor(-1622.9706, device='cuda:0')
episode: 399 training return: tensor(-1626.4669, device='cuda:0')
epoch: 100 test_true_pfm: -7.082634867252224
episode: 400 training return: tensor(-1608.0765, device='cuda:0')
episode: 401 training return: tensor(-1612.4365, device='cuda:0')
episode: 402 training return: tensor(-1606.0643, device='cuda:0')
episode: 403 training return: tensor(-1606.4419, device='cuda:0')
epoch: 101 test_true_pfm: -8.135489921423023
episode: 404 training return: tensor(-1620.2435, device='cuda:0')
episode: 405 training return: tensor(-1611.1315, device='cuda:0')
episode: 406 training return: tensor(-1624.8525, device='cuda:0')
episode: 407 training return: tensor(-1629.1090, device='cuda:0')
epoch: 102 test_true_pfm: -7.452529579347023
episode: 408 training return: tensor(-1629.5333, device='cuda:0')
episode: 409 training return: tensor(-1610.9136, device='cuda:0')
episode: 410 training return: tensor(-1639.0453, device='cuda:0')
episode: 411 training return: tensor(-1615.3756, device='cuda:0')
epoch: 103 test_true_pfm: -4.115965692116777
episode: 412 training return: tensor(-1623.4469, device='cuda:0')
episode: 413 training return: tensor(-1623.3759, device='cuda:0')
episode: 414 training return: tensor(-1618.9626, device='cuda:0')
episode: 415 training return: tensor(-1600.9341, device='cuda:0')
epoch: 104 test_true_pfm: -1.3533955587970363
episode: 416 training return: tensor(-1627.7943, device='cuda:0')
episode: 417 training return: tensor(-1620.4097, device='cuda:0')
episode: 418 training return: tensor(-1623.2336, device='cuda:0')
episode: 419 training return: tensor(-1626.7683, device='cuda:0')
epoch: 105 test_true_pfm: -8.09876122488904
episode: 420 training return: tensor(-1614.5460, device='cuda:0')
episode: 421 training return: tensor(-1632.0621, device='cuda:0')
episode: 422 training return: tensor(-1616.9962, device='cuda:0')
episode: 423 training return: tensor(-1628.2573, device='cuda:0')
epoch: 106 test_true_pfm: -0.3719374435998068
episode: 424 training return: tensor(-1619.3058, device='cuda:0')
episode: 425 training return: tensor(-1629.0535, device='cuda:0')
episode: 426 training return: tensor(-1606.9010, device='cuda:0')
episode: 427 training return: tensor(-1606.0125, device='cuda:0')
epoch: 107 test_true_pfm: -2.227067964062146
episode: 428 training return: tensor(-1626.7988, device='cuda:0')
episode: 429 training return: tensor(-1625.1763, device='cuda:0')
episode: 430 training return: tensor(-1624.9292, device='cuda:0')
episode: 431 training return: tensor(-1631.6865, device='cuda:0')
epoch: 108 test_true_pfm: -1.6811130189033194
episode: 432 training return: tensor(-1612.6602, device='cuda:0')
episode: 433 training return: tensor(-1621.9575, device='cuda:0')
episode: 434 training return: tensor(-1624.7516, device='cuda:0')
episode: 435 training return: tensor(-1612.3652, device='cuda:0')
epoch: 109 test_true_pfm: -1.4842233324961638
episode: 436 training return: tensor(-1600.1692, device='cuda:0')
episode: 437 training return: tensor(-1622.0859, device='cuda:0')
episode: 438 training return: tensor(-1609.3546, device='cuda:0')
episode: 439 training return: tensor(-1617.3596, device='cuda:0')
epoch: 110 test_true_pfm: -2.3126051100146436
episode: 440 training return: tensor(-1628.0247, device='cuda:0')
episode: 441 training return: tensor(-1623.0446, device='cuda:0')
episode: 442 training return: tensor(-1628.8025, device='cuda:0')
episode: 443 training return: tensor(-1612.2775, device='cuda:0')
epoch: 111 test_true_pfm: -2.6769043309156095
episode: 444 training return: tensor(-1617.5742, device='cuda:0')
episode: 445 training return: tensor(-1617.0353, device='cuda:0')
episode: 446 training return: tensor(-1627.5215, device='cuda:0')
episode: 447 training return: tensor(-1623.6504, device='cuda:0')
epoch: 112 test_true_pfm: -4.763587066722268
episode: 448 training return: tensor(-1626.8289, device='cuda:0')
episode: 449 training return: tensor(-1615.6046, device='cuda:0')
episode: 450 training return: tensor(-1617.1288, device='cuda:0')
episode: 451 training return: tensor(-1614.0455, device='cuda:0')
epoch: 113 test_true_pfm: -8.393981650727804
episode: 452 training return: tensor(-1616.2671, device='cuda:0')
episode: 453 training return: tensor(-1621.8777, device='cuda:0')
episode: 454 training return: tensor(-1619.5725, device='cuda:0')
episode: 455 training return: tensor(-1609.7134, device='cuda:0')
epoch: 114 test_true_pfm: -0.06830764434663772
episode: 456 training return: tensor(-1635.6854, device='cuda:0')
episode: 457 training return: tensor(-1624.8257, device='cuda:0')
episode: 458 training return: tensor(-1625.1106, device='cuda:0')
episode: 459 training return: tensor(-1619.9711, device='cuda:0')
epoch: 115 test_true_pfm: -8.502612012568138
episode: 460 training return: tensor(-1623.0396, device='cuda:0')
episode: 461 training return: tensor(-1630.5482, device='cuda:0')
episode: 462 training return: tensor(-1640.1277, device='cuda:0')
episode: 463 training return: tensor(-1611.7732, device='cuda:0')
epoch: 116 test_true_pfm: 0.06808156572319206
episode: 464 training return: tensor(-1616.8936, device='cuda:0')
episode: 465 training return: tensor(-1624.4896, device='cuda:0')
episode: 466 training return: tensor(-1640.2971, device='cuda:0')
episode: 467 training return: tensor(-1625.0906, device='cuda:0')
epoch: 117 test_true_pfm: -5.085005011491792
episode: 468 training return: tensor(-1595.3212, device='cuda:0')
episode: 469 training return: tensor(-1620.9894, device='cuda:0')
episode: 470 training return: tensor(-1635.7543, device='cuda:0')
episode: 471 training return: tensor(-1620.9072, device='cuda:0')
epoch: 118 test_true_pfm: 0.9493709125618945
episode: 472 training return: tensor(-1616.8350, device='cuda:0')
episode: 473 training return: tensor(-1614.8810, device='cuda:0')
episode: 474 training return: tensor(-1609.7268, device='cuda:0')
episode: 475 training return: tensor(-1614.4647, device='cuda:0')
epoch: 119 test_true_pfm: -2.843408111807555
episode: 476 training return: tensor(-1620.8406, device='cuda:0')
episode: 477 training return: tensor(-1608.5951, device='cuda:0')
episode: 478 training return: tensor(-1622.7072, device='cuda:0')
episode: 479 training return: tensor(-1623.2086, device='cuda:0')
epoch: 120 test_true_pfm: -8.175721741662366
episode: 480 training return: tensor(-1606.3549, device='cuda:0')
episode: 481 training return: tensor(-1613.4283, device='cuda:0')
episode: 482 training return: tensor(-1611.5247, device='cuda:0')
episode: 483 training return: tensor(-1628.5260, device='cuda:0')
epoch: 121 test_true_pfm: -0.9527552332906398
episode: 484 training return: tensor(-1626.2871, device='cuda:0')
episode: 485 training return: tensor(-1610.5135, device='cuda:0')
episode: 486 training return: tensor(-1623.4723, device='cuda:0')
episode: 487 training return: tensor(-1626.3279, device='cuda:0')
epoch: 122 test_true_pfm: -2.9010228939066827
episode: 488 training return: tensor(-1609.2131, device='cuda:0')
episode: 489 training return: tensor(-1626.3146, device='cuda:0')
episode: 490 training return: tensor(-1613.6620, device='cuda:0')
episode: 491 training return: tensor(-1625.7040, device='cuda:0')
epoch: 123 test_true_pfm: -3.0853199116384133
episode: 492 training return: tensor(-1629.3561, device='cuda:0')
episode: 493 training return: tensor(-1610.4276, device='cuda:0')
episode: 494 training return: tensor(-1608.6879, device='cuda:0')
episode: 495 training return: tensor(-1626.1469, device='cuda:0')
epoch: 124 test_true_pfm: -6.614225822924261
episode: 496 training return: tensor(-1617.5741, device='cuda:0')
episode: 497 training return: tensor(-1605.6226, device='cuda:0')
episode: 498 training return: tensor(-1606.7482, device='cuda:0')
episode: 499 training return: tensor(-1615.3871, device='cuda:0')
epoch: 125 test_true_pfm: -4.714260274890429
episode: 500 training return: tensor(-1620.8717, device='cuda:0')
episode: 501 training return: tensor(-1638.3871, device='cuda:0')
episode: 502 training return: tensor(-1627.7131, device='cuda:0')
episode: 503 training return: tensor(-1616.9988, device='cuda:0')
epoch: 126 test_true_pfm: -9.582445655625351
episode: 504 training return: tensor(-1615.1437, device='cuda:0')
episode: 505 training return: tensor(-1619.2068, device='cuda:0')
episode: 506 training return: tensor(-1623.4720, device='cuda:0')
episode: 507 training return: tensor(-1618.9333, device='cuda:0')
epoch: 127 test_true_pfm: -4.474535086300918
episode: 508 training return: tensor(-1636.9180, device='cuda:0')
episode: 509 training return: tensor(-1626.0140, device='cuda:0')
episode: 510 training return: tensor(-1626.4902, device='cuda:0')
episode: 511 training return: tensor(-1625.0750, device='cuda:0')
epoch: 128 test_true_pfm: -0.8872492264692289
episode: 512 training return: tensor(-1601.7891, device='cuda:0')
episode: 513 training return: tensor(-1600.3960, device='cuda:0')
episode: 514 training return: tensor(-1616.3286, device='cuda:0')
episode: 515 training return: tensor(-1633.9833, device='cuda:0')
epoch: 129 test_true_pfm: -5.698430157606228
episode: 516 training return: tensor(-1619.8638, device='cuda:0')
episode: 517 training return: tensor(-1620.5265, device='cuda:0')
episode: 518 training return: tensor(-1616.5121, device='cuda:0')
episode: 519 training return: tensor(-1618.0149, device='cuda:0')
epoch: 130 test_true_pfm: -4.8146745589037225
episode: 520 training return: tensor(-1622.3234, device='cuda:0')
episode: 521 training return: tensor(-1623.2362, device='cuda:0')
episode: 522 training return: tensor(-1608.0464, device='cuda:0')
episode: 523 training return: tensor(-1628.9398, device='cuda:0')
epoch: 131 test_true_pfm: -3.0961829314917324
episode: 524 training return: tensor(-1623.0209, device='cuda:0')
episode: 525 training return: tensor(-1612.5347, device='cuda:0')
episode: 526 training return: tensor(-1624.9705, device='cuda:0')
episode: 527 training return: tensor(-1615.9547, device='cuda:0')
epoch: 132 test_true_pfm: -2.15689875657008
episode: 528 training return: tensor(-1639.0087, device='cuda:0')
episode: 529 training return: tensor(-1622.9960, device='cuda:0')
episode: 530 training return: tensor(-1629.8247, device='cuda:0')
episode: 531 training return: tensor(-1630.2661, device='cuda:0')
epoch: 133 test_true_pfm: -0.7585196435888507
episode: 532 training return: tensor(-1605.3589, device='cuda:0')
episode: 533 training return: tensor(-1616.7418, device='cuda:0')
episode: 534 training return: tensor(-1613.9427, device='cuda:0')
episode: 535 training return: tensor(-1594.3937, device='cuda:0')
epoch: 134 test_true_pfm: -11.006725660583605
episode: 536 training return: tensor(-1608.3240, device='cuda:0')
episode: 537 training return: tensor(-1624.1217, device='cuda:0')
episode: 538 training return: tensor(-1639.7189, device='cuda:0')
episode: 539 training return: tensor(-1625.2665, device='cuda:0')
epoch: 135 test_true_pfm: 0.7028979225111854
episode: 540 training return: tensor(-1622.0586, device='cuda:0')
episode: 541 training return: tensor(-1611.4644, device='cuda:0')
episode: 542 training return: tensor(-1606.2278, device='cuda:0')
episode: 543 training return: tensor(-1623.1639, device='cuda:0')
epoch: 136 test_true_pfm: -2.2739749599133496
episode: 544 training return: tensor(-1606.3652, device='cuda:0')
episode: 545 training return: tensor(-1614.6310, device='cuda:0')
episode: 546 training return: tensor(-1617.0726, device='cuda:0')
episode: 547 training return: tensor(-1613.0076, device='cuda:0')
epoch: 137 test_true_pfm: -6.555727815733879
episode: 548 training return: tensor(-1630.3105, device='cuda:0')
episode: 549 training return: tensor(-1610.6445, device='cuda:0')
episode: 550 training return: tensor(-1612.4880, device='cuda:0')
episode: 551 training return: tensor(-1619.3800, device='cuda:0')
epoch: 138 test_true_pfm: -5.895943893936881
episode: 552 training return: tensor(-1608.7303, device='cuda:0')
episode: 553 training return: tensor(-1602.9636, device='cuda:0')
episode: 554 training return: tensor(-1603.1161, device='cuda:0')
episode: 555 training return: tensor(-1627.0750, device='cuda:0')
epoch: 139 test_true_pfm: -6.86331077925625
episode: 556 training return: tensor(-1606.8744, device='cuda:0')
episode: 557 training return: tensor(-1613.0988, device='cuda:0')
episode: 558 training return: tensor(-1627.8262, device='cuda:0')
episode: 559 training return: tensor(-1615.7214, device='cuda:0')
epoch: 140 test_true_pfm: -3.61436066760357
episode: 560 training return: tensor(-1610.0319, device='cuda:0')
episode: 561 training return: tensor(-1607.7761, device='cuda:0')
episode: 562 training return: tensor(-1624.7638, device='cuda:0')
episode: 563 training return: tensor(-1629.6766, device='cuda:0')
epoch: 141 test_true_pfm: -6.310341188353864
episode: 564 training return: tensor(-1612.4308, device='cuda:0')
episode: 565 training return: tensor(-1623.3104, device='cuda:0')
episode: 566 training return: tensor(-1618.9102, device='cuda:0')
episode: 567 training return: tensor(-1614.2936, device='cuda:0')
epoch: 142 test_true_pfm: -6.779358988202332
episode: 568 training return: tensor(-1611.3295, device='cuda:0')
episode: 569 training return: tensor(-1637.8232, device='cuda:0')
episode: 570 training return: tensor(-1607.4625, device='cuda:0')
episode: 571 training return: tensor(-1616.1876, device='cuda:0')
epoch: 143 test_true_pfm: -7.936750894164256
episode: 572 training return: tensor(-1605.1204, device='cuda:0')
episode: 573 training return: tensor(-1619.9100, device='cuda:0')
episode: 574 training return: tensor(-1617.1758, device='cuda:0')
episode: 575 training return: tensor(-1620.0266, device='cuda:0')
epoch: 144 test_true_pfm: -7.333339189079311
episode: 576 training return: tensor(-1616.4272, device='cuda:0')
episode: 577 training return: tensor(-1617.1084, device='cuda:0')
episode: 578 training return: tensor(-1607.4071, device='cuda:0')
episode: 579 training return: tensor(-1609.5642, device='cuda:0')
epoch: 145 test_true_pfm: -9.184861303581027
episode: 580 training return: tensor(-1608.7288, device='cuda:0')
episode: 581 training return: tensor(-1626.3463, device='cuda:0')
episode: 582 training return: tensor(-1616.3564, device='cuda:0')
episode: 583 training return: tensor(-1601.7236, device='cuda:0')
epoch: 146 test_true_pfm: -9.573198533670825
episode: 584 training return: tensor(-1620.7930, device='cuda:0')
episode: 585 training return: tensor(-1615.3621, device='cuda:0')
episode: 586 training return: tensor(-1624.4746, device='cuda:0')
episode: 587 training return: tensor(-1611.8428, device='cuda:0')
epoch: 147 test_true_pfm: -4.801428686396119
episode: 588 training return: tensor(-1619.7074, device='cuda:0')
episode: 589 training return: tensor(-1625.7097, device='cuda:0')
episode: 590 training return: tensor(-1610.4043, device='cuda:0')
episode: 591 training return: tensor(-1637.9733, device='cuda:0')
epoch: 148 test_true_pfm: -5.55276399065784
episode: 592 training return: tensor(-1621.4462, device='cuda:0')
episode: 593 training return: tensor(-1617.8544, device='cuda:0')
episode: 594 training return: tensor(-1623.4215, device='cuda:0')
episode: 595 training return: tensor(-1603.0353, device='cuda:0')
epoch: 149 test_true_pfm: -8.583354446140126
episode: 596 training return: tensor(-1625.9922, device='cuda:0')
episode: 597 training return: tensor(-1610.2936, device='cuda:0')
episode: 598 training return: tensor(-1594.6073, device='cuda:0')
episode: 599 training return: tensor(-1600.8746, device='cuda:0')
epoch: 150 test_true_pfm: -8.053606990943516
