['--alg', 'sac', '--env', 'HalfCheetah-v2', '--learn', 'brac', '--traj', 'medium', '--seed', '2', '--data', '100000']
5059.843029351587
episode: 0 training return: tensor(-4075.9810, device='cuda:0')
episode: 1 training return: tensor(-4880.3560, device='cuda:0')
episode: 2 training return: tensor(-3504.0007, device='cuda:0')
episode: 3 training return: tensor(-4361.1787, device='cuda:0')
epoch: 1 test_true_pfm: 197.90835868457063
episode: 4 training return: tensor(-4882.0981, device='cuda:0')
episode: 5 training return: tensor(-4534.0508, device='cuda:0')
episode: 6 training return: tensor(-4626.9800, device='cuda:0')
episode: 7 training return: tensor(-2753.3311, device='cuda:0')
epoch: 2 test_true_pfm: -241.14431491436258
episode: 8 training return: tensor(-4934.1470, device='cuda:0')
episode: 9 training return: tensor(-4868.3179, device='cuda:0')
episode: 10 training return: tensor(-1979.1829, device='cuda:0')
episode: 11 training return: tensor(-1866.4132, device='cuda:0')
epoch: 3 test_true_pfm: -80.66169448750578
episode: 12 training return: tensor(-1788.7219, device='cuda:0')
episode: 13 training return: tensor(-1714.5817, device='cuda:0')
episode: 14 training return: tensor(-1664.5720, device='cuda:0')
episode: 15 training return: tensor(-1681.4302, device='cuda:0')
epoch: 4 test_true_pfm: -148.25862353255857
episode: 16 training return: tensor(-1613.7194, device='cuda:0')
episode: 17 training return: tensor(-1579.3007, device='cuda:0')
episode: 18 training return: tensor(-1543.0311, device='cuda:0')
episode: 19 training return: tensor(-1552.3356, device='cuda:0')
epoch: 5 test_true_pfm: -180.60291841878836
episode: 20 training return: tensor(-1559.1984, device='cuda:0')
episode: 21 training return: tensor(-1552.6312, device='cuda:0')
episode: 22 training return: tensor(-1513.1145, device='cuda:0')
episode: 23 training return: tensor(-1503.9526, device='cuda:0')
epoch: 6 test_true_pfm: -157.1922878868883
episode: 24 training return: tensor(-1480.9855, device='cuda:0')
episode: 25 training return: tensor(-1500.4113, device='cuda:0')
episode: 26 training return: tensor(-1497.8517, device='cuda:0')
episode: 27 training return: tensor(-1471.6765, device='cuda:0')
epoch: 7 test_true_pfm: -196.6535391933812
episode: 28 training return: tensor(-1501.7745, device='cuda:0')
episode: 29 training return: tensor(-1502.0156, device='cuda:0')
episode: 30 training return: tensor(-1497.7428, device='cuda:0')
episode: 31 training return: tensor(-1542.0842, device='cuda:0')
epoch: 8 test_true_pfm: -170.75934519624582
episode: 32 training return: tensor(-1513.8236, device='cuda:0')
episode: 33 training return: tensor(-1542.4298, device='cuda:0')
episode: 34 training return: tensor(-1571.3036, device='cuda:0')
episode: 35 training return: tensor(-1627.8765, device='cuda:0')
epoch: 9 test_true_pfm: -158.97762519803055
episode: 36 training return: tensor(-1737.5212, device='cuda:0')
episode: 37 training return: tensor(-1772.9399, device='cuda:0')
episode: 38 training return: tensor(-1588.7883, device='cuda:0')
episode: 39 training return: tensor(-1530.1708, device='cuda:0')
epoch: 10 test_true_pfm: -135.85743789497425
episode: 40 training return: tensor(-1469.9874, device='cuda:0')
episode: 41 training return: tensor(-1482.6715, device='cuda:0')
episode: 42 training return: tensor(-1483.9851, device='cuda:0')
episode: 43 training return: tensor(-1464.6196, device='cuda:0')
epoch: 11 test_true_pfm: -147.07183282282628
episode: 44 training return: tensor(-1455.4111, device='cuda:0')
episode: 45 training return: tensor(-1457.0972, device='cuda:0')
episode: 46 training return: tensor(-1446.5542, device='cuda:0')
episode: 47 training return: tensor(-1460.6389, device='cuda:0')
epoch: 12 test_true_pfm: -168.8247968785289
episode: 48 training return: tensor(-1460.6704, device='cuda:0')
episode: 49 training return: tensor(-1466.0562, device='cuda:0')
episode: 50 training return: tensor(-1476.2118, device='cuda:0')
episode: 51 training return: tensor(-1462.2397, device='cuda:0')
epoch: 13 test_true_pfm: -172.24950466964864
episode: 52 training return: tensor(-1490.4595, device='cuda:0')
episode: 53 training return: tensor(-1643.3090, device='cuda:0')
episode: 54 training return: tensor(-1497.0795, device='cuda:0')
episode: 55 training return: tensor(-1453.1290, device='cuda:0')
epoch: 14 test_true_pfm: -191.23741154455493
episode: 56 training return: tensor(-1485.9454, device='cuda:0')
episode: 57 training return: tensor(-1455.5972, device='cuda:0')
episode: 58 training return: tensor(-1449.7052, device='cuda:0')
episode: 59 training return: tensor(-1445.8005, device='cuda:0')
epoch: 15 test_true_pfm: -162.86963840723328
episode: 60 training return: tensor(-1477.7550, device='cuda:0')
episode: 61 training return: tensor(-1455.9510, device='cuda:0')
episode: 62 training return: tensor(-1480.1515, device='cuda:0')
episode: 63 training return: tensor(-1560.4475, device='cuda:0')
epoch: 16 test_true_pfm: -177.0676694218716
episode: 64 training return: tensor(-1491.7279, device='cuda:0')
episode: 65 training return: tensor(-1642.0643, device='cuda:0')
episode: 66 training return: tensor(-1764.0894, device='cuda:0')
episode: 67 training return: tensor(-1665.7709, device='cuda:0')
epoch: 17 test_true_pfm: -114.84449587619076
episode: 68 training return: tensor(-1579.5273, device='cuda:0')
episode: 69 training return: tensor(-1747.0022, device='cuda:0')
episode: 70 training return: tensor(-1702.3345, device='cuda:0')
episode: 71 training return: tensor(-1745.1429, device='cuda:0')
epoch: 18 test_true_pfm: 18.65586392805334
episode: 72 training return: tensor(-1723.8990, device='cuda:0')
episode: 73 training return: tensor(-1762.5793, device='cuda:0')
episode: 74 training return: tensor(-1742.9893, device='cuda:0')
episode: 75 training return: tensor(-1754.1326, device='cuda:0')
epoch: 19 test_true_pfm: -47.736675572551746
episode: 76 training return: tensor(-1738.0881, device='cuda:0')
episode: 77 training return: tensor(-1744.3197, device='cuda:0')
episode: 78 training return: tensor(-1757.1896, device='cuda:0')
episode: 79 training return: tensor(-1775.7095, device='cuda:0')
epoch: 20 test_true_pfm: -44.34606510375346
episode: 80 training return: tensor(-1696.6425, device='cuda:0')
episode: 81 training return: tensor(-1758.7008, device='cuda:0')
episode: 82 training return: tensor(-1764.3777, device='cuda:0')
episode: 83 training return: tensor(-1754.4058, device='cuda:0')
epoch: 21 test_true_pfm: 14.194455535159738
episode: 84 training return: tensor(-1778.2190, device='cuda:0')
episode: 85 training return: tensor(-1738.0555, device='cuda:0')
episode: 86 training return: tensor(-1754.9802, device='cuda:0')
episode: 87 training return: tensor(-1747.7925, device='cuda:0')
epoch: 22 test_true_pfm: -55.42903563465078
episode: 88 training return: tensor(-1650.6599, device='cuda:0')
episode: 89 training return: tensor(-1770.2063, device='cuda:0')
episode: 90 training return: tensor(-1747.5143, device='cuda:0')
episode: 91 training return: tensor(-1767.0216, device='cuda:0')
epoch: 23 test_true_pfm: -54.42378826238795
episode: 92 training return: tensor(-1768.5914, device='cuda:0')
episode: 93 training return: tensor(-1760.2705, device='cuda:0')
episode: 94 training return: tensor(-1774.9193, device='cuda:0')
episode: 95 training return: tensor(-1760.1051, device='cuda:0')
epoch: 24 test_true_pfm: -40.39049951024517
episode: 96 training return: tensor(-1787.1520, device='cuda:0')
episode: 97 training return: tensor(-1714.9574, device='cuda:0')
episode: 98 training return: tensor(-1774.6484, device='cuda:0')
episode: 99 training return: tensor(-1766.5312, device='cuda:0')
epoch: 25 test_true_pfm: -63.61375955031349
episode: 100 training return: tensor(-1776.7797, device='cuda:0')
episode: 101 training return: tensor(-1777.3683, device='cuda:0')
episode: 102 training return: tensor(-1779.4160, device='cuda:0')
episode: 103 training return: tensor(-1746.4102, device='cuda:0')
epoch: 26 test_true_pfm: -52.85125968051427
episode: 104 training return: tensor(-1765.8986, device='cuda:0')
episode: 105 training return: tensor(-1758.9049, device='cuda:0')
episode: 106 training return: tensor(-1794.8677, device='cuda:0')
episode: 107 training return: tensor(-1766.8627, device='cuda:0')
epoch: 27 test_true_pfm: -33.266129821521254
episode: 108 training return: tensor(-1764.9113, device='cuda:0')
episode: 109 training return: tensor(-1773.6393, device='cuda:0')
episode: 110 training return: tensor(-1777.0181, device='cuda:0')
episode: 111 training return: tensor(-1766.6228, device='cuda:0')
epoch: 28 test_true_pfm: -56.842276102082415
episode: 112 training return: tensor(-1707.1843, device='cuda:0')
episode: 113 training return: tensor(-1757.2711, device='cuda:0')
episode: 114 training return: tensor(-1765.9849, device='cuda:0')
episode: 115 training return: tensor(-1760.7351, device='cuda:0')
epoch: 29 test_true_pfm: -34.06966792834594
episode: 116 training return: tensor(-1770.7535, device='cuda:0')
episode: 117 training return: tensor(-1696.1218, device='cuda:0')
episode: 118 training return: tensor(-1694.4240, device='cuda:0')
episode: 119 training return: tensor(-1754.8627, device='cuda:0')
epoch: 30 test_true_pfm: -51.995409901972955
episode: 120 training return: tensor(-1770.7878, device='cuda:0')
episode: 121 training return: tensor(-1777.8915, device='cuda:0')
episode: 122 training return: tensor(-1769.3955, device='cuda:0')
episode: 123 training return: tensor(-1756.6660, device='cuda:0')
epoch: 31 test_true_pfm: -39.57271276167623
episode: 124 training return: tensor(-1757.6814, device='cuda:0')
episode: 125 training return: tensor(-1784.5822, device='cuda:0')
episode: 126 training return: tensor(-1765.9031, device='cuda:0')
episode: 127 training return: tensor(-1770.6198, device='cuda:0')
epoch: 32 test_true_pfm: -47.36663844809461
episode: 128 training return: tensor(-1754.0072, device='cuda:0')
episode: 129 training return: tensor(-1740.8802, device='cuda:0')
episode: 130 training return: tensor(-1767.9587, device='cuda:0')
episode: 131 training return: tensor(-1761.0044, device='cuda:0')
epoch: 33 test_true_pfm: 24.027830902420458
episode: 132 training return: tensor(-1777.7522, device='cuda:0')
episode: 133 training return: tensor(-1764.6772, device='cuda:0')
episode: 134 training return: tensor(-1727.9037, device='cuda:0')
episode: 135 training return: tensor(-1772.2646, device='cuda:0')
epoch: 34 test_true_pfm: -37.34621672013239
episode: 136 training return: tensor(-1768.3878, device='cuda:0')
episode: 137 training return: tensor(-1762.4032, device='cuda:0')
episode: 138 training return: tensor(-1763.4823, device='cuda:0')
episode: 139 training return: tensor(-1773.0048, device='cuda:0')
epoch: 35 test_true_pfm: -43.342562387258795
episode: 140 training return: tensor(-1712.3625, device='cuda:0')
episode: 141 training return: tensor(-1749.0118, device='cuda:0')
episode: 142 training return: tensor(-1757.0682, device='cuda:0')
episode: 143 training return: tensor(-1730.6923, device='cuda:0')
epoch: 36 test_true_pfm: -40.09039949784983
episode: 144 training return: tensor(-1782.3557, device='cuda:0')
episode: 145 training return: tensor(-1715.7036, device='cuda:0')
episode: 146 training return: tensor(-1767.1863, device='cuda:0')
episode: 147 training return: tensor(-1724.5740, device='cuda:0')
epoch: 37 test_true_pfm: -12.76662103241466
episode: 148 training return: tensor(-1774.3818, device='cuda:0')
episode: 149 training return: tensor(-1755.3083, device='cuda:0')
episode: 150 training return: tensor(-1764.7766, device='cuda:0')
episode: 151 training return: tensor(-1764.4569, device='cuda:0')
epoch: 38 test_true_pfm: -34.93921440844202
episode: 152 training return: tensor(-1775.3770, device='cuda:0')
episode: 153 training return: tensor(-1753.1462, device='cuda:0')
episode: 154 training return: tensor(-1757.1438, device='cuda:0')
episode: 155 training return: tensor(-1744.6584, device='cuda:0')
epoch: 39 test_true_pfm: -36.290131793662034
episode: 156 training return: tensor(-1768.6083, device='cuda:0')
episode: 157 training return: tensor(-1762.4285, device='cuda:0')
episode: 158 training return: tensor(-1751.6543, device='cuda:0')
episode: 159 training return: tensor(-1738.3292, device='cuda:0')
epoch: 40 test_true_pfm: -29.914851156743254
episode: 160 training return: tensor(-1758.9553, device='cuda:0')
episode: 161 training return: tensor(-1749.5912, device='cuda:0')
episode: 162 training return: tensor(-1739.3701, device='cuda:0')
episode: 163 training return: tensor(-1761.8118, device='cuda:0')
epoch: 41 test_true_pfm: -28.533989419079145
episode: 164 training return: tensor(-1763.3334, device='cuda:0')
episode: 165 training return: tensor(-1747.5172, device='cuda:0')
episode: 166 training return: tensor(-1755.7227, device='cuda:0')
episode: 167 training return: tensor(-1779.0685, device='cuda:0')
epoch: 42 test_true_pfm: 22.687553611948022
episode: 168 training return: tensor(-1762.8253, device='cuda:0')
episode: 169 training return: tensor(-1777.4796, device='cuda:0')
episode: 170 training return: tensor(-1763.9709, device='cuda:0')
episode: 171 training return: tensor(-1751.9886, device='cuda:0')
epoch: 43 test_true_pfm: -8.818010400587008
episode: 172 training return: tensor(-1750.7225, device='cuda:0')
episode: 173 training return: tensor(-1755.1484, device='cuda:0')
episode: 174 training return: tensor(-1775.9546, device='cuda:0')
episode: 175 training return: tensor(-1772.0499, device='cuda:0')
epoch: 44 test_true_pfm: 5.568239482293773
episode: 176 training return: tensor(-1761.3418, device='cuda:0')
episode: 177 training return: tensor(-1746.6073, device='cuda:0')
episode: 178 training return: tensor(-1761.5754, device='cuda:0')
episode: 179 training return: tensor(-1765.1403, device='cuda:0')
epoch: 45 test_true_pfm: -39.800529548246416
episode: 180 training return: tensor(-1758.7343, device='cuda:0')
episode: 181 training return: tensor(-1747.7659, device='cuda:0')
episode: 182 training return: tensor(-1755.1921, device='cuda:0')
episode: 183 training return: tensor(-1759.2206, device='cuda:0')
epoch: 46 test_true_pfm: 22.698672751893273
episode: 184 training return: tensor(-1755.7401, device='cuda:0')
episode: 185 training return: tensor(-1735.1886, device='cuda:0')
episode: 186 training return: tensor(-1756.3723, device='cuda:0')
episode: 187 training return: tensor(-1764.1882, device='cuda:0')
epoch: 47 test_true_pfm: -35.49696650026049
episode: 188 training return: tensor(-1759.1974, device='cuda:0')
episode: 189 training return: tensor(-1752.5950, device='cuda:0')
episode: 190 training return: tensor(-1759.6765, device='cuda:0')
episode: 191 training return: tensor(-1757.0521, device='cuda:0')
epoch: 48 test_true_pfm: 22.255315245650934
episode: 192 training return: tensor(-1753.4659, device='cuda:0')
episode: 193 training return: tensor(-1753.0687, device='cuda:0')
episode: 194 training return: tensor(-1758.0458, device='cuda:0')
episode: 195 training return: tensor(-1712.9423, device='cuda:0')
epoch: 49 test_true_pfm: 25.207820855648944
episode: 196 training return: tensor(-1754.9160, device='cuda:0')
episode: 197 training return: tensor(-1747.2188, device='cuda:0')
episode: 198 training return: tensor(-1751.9594, device='cuda:0')
episode: 199 training return: tensor(-1753.9701, device='cuda:0')
epoch: 50 test_true_pfm: -30.859755634849023
episode: 200 training return: tensor(-1759.9838, device='cuda:0')
episode: 201 training return: tensor(-1758.2769, device='cuda:0')
episode: 202 training return: tensor(-1744.3934, device='cuda:0')
episode: 203 training return: tensor(-1757.8597, device='cuda:0')
epoch: 51 test_true_pfm: -28.314568005247793
episode: 204 training return: tensor(-1745.6998, device='cuda:0')
episode: 205 training return: tensor(-1753.1237, device='cuda:0')
episode: 206 training return: tensor(-1768.5774, device='cuda:0')
episode: 207 training return: tensor(-1737.1492, device='cuda:0')
epoch: 52 test_true_pfm: -13.985205521515455
episode: 208 training return: tensor(-1760.3595, device='cuda:0')
episode: 209 training return: tensor(-1772.5045, device='cuda:0')
episode: 210 training return: tensor(-1759.3020, device='cuda:0')
episode: 211 training return: tensor(-1747.1754, device='cuda:0')
epoch: 53 test_true_pfm: -17.801637447345158
episode: 212 training return: tensor(-1715.2897, device='cuda:0')
episode: 213 training return: tensor(-1744.1128, device='cuda:0')
episode: 214 training return: tensor(-1758.7297, device='cuda:0')
episode: 215 training return: tensor(-1742.7913, device='cuda:0')
epoch: 54 test_true_pfm: -32.14007169303913
episode: 216 training return: tensor(-1720.7784, device='cuda:0')
episode: 217 training return: tensor(-1756.2389, device='cuda:0')
episode: 218 training return: tensor(-1764.6464, device='cuda:0')
episode: 219 training return: tensor(-1743.6241, device='cuda:0')
epoch: 55 test_true_pfm: -25.118546762034214
episode: 220 training return: tensor(-1753.0858, device='cuda:0')
episode: 221 training return: tensor(-1743.8296, device='cuda:0')
episode: 222 training return: tensor(-1749.4993, device='cuda:0')
episode: 223 training return: tensor(-1727.9058, device='cuda:0')
epoch: 56 test_true_pfm: -32.8883426818655
episode: 224 training return: tensor(-1756.8314, device='cuda:0')
episode: 225 training return: tensor(-1772.9629, device='cuda:0')
episode: 226 training return: tensor(-1761.7673, device='cuda:0')
episode: 227 training return: tensor(-1738.0353, device='cuda:0')
epoch: 57 test_true_pfm: -29.65759967172615
episode: 228 training return: tensor(-1748.4110, device='cuda:0')
episode: 229 training return: tensor(-1746.7582, device='cuda:0')
episode: 230 training return: tensor(-1685.0059, device='cuda:0')
episode: 231 training return: tensor(-1739.0503, device='cuda:0')
epoch: 58 test_true_pfm: -35.59128352372587
episode: 232 training return: tensor(-1756.4272, device='cuda:0')
episode: 233 training return: tensor(-1729.3402, device='cuda:0')
episode: 234 training return: tensor(-1761.5594, device='cuda:0')
episode: 235 training return: tensor(-1750.8134, device='cuda:0')
epoch: 59 test_true_pfm: -19.384506190851734
episode: 236 training return: tensor(-1753.9377, device='cuda:0')
episode: 237 training return: tensor(-1761.9464, device='cuda:0')
episode: 238 training return: tensor(-1762.0179, device='cuda:0')
episode: 239 training return: tensor(-1663.7648, device='cuda:0')
epoch: 60 test_true_pfm: -23.135199717213265
episode: 240 training return: tensor(-1744.2675, device='cuda:0')
episode: 241 training return: tensor(-1741.3517, device='cuda:0')
episode: 242 training return: tensor(-1744.6813, device='cuda:0')
episode: 243 training return: tensor(-1747.6158, device='cuda:0')
epoch: 61 test_true_pfm: -14.834549711777806
episode: 244 training return: tensor(-1767.6538, device='cuda:0')
episode: 245 training return: tensor(-1751.7703, device='cuda:0')
episode: 246 training return: tensor(-1759.3103, device='cuda:0')
episode: 247 training return: tensor(-1746.0665, device='cuda:0')
epoch: 62 test_true_pfm: -20.53447957236151
episode: 248 training return: tensor(-1708.2474, device='cuda:0')
episode: 249 training return: tensor(-1754.3254, device='cuda:0')
episode: 250 training return: tensor(-1758.3707, device='cuda:0')
episode: 251 training return: tensor(-1754.6078, device='cuda:0')
epoch: 63 test_true_pfm: -12.034413475792539
episode: 252 training return: tensor(-1696.3319, device='cuda:0')
episode: 253 training return: tensor(-1734.0332, device='cuda:0')
episode: 254 training return: tensor(-1749.1776, device='cuda:0')
episode: 255 training return: tensor(-1733.5956, device='cuda:0')
epoch: 64 test_true_pfm: -10.607392440286555
episode: 256 training return: tensor(-1690.8837, device='cuda:0')
episode: 257 training return: tensor(-1700.3120, device='cuda:0')
episode: 258 training return: tensor(-1738.3951, device='cuda:0')
episode: 259 training return: tensor(-1746.3322, device='cuda:0')
epoch: 65 test_true_pfm: -20.175253950421567
episode: 260 training return: tensor(-1728.2534, device='cuda:0')
episode: 261 training return: tensor(-1742.6665, device='cuda:0')
episode: 262 training return: tensor(-1680.2394, device='cuda:0')
episode: 263 training return: tensor(-1737.5677, device='cuda:0')
epoch: 66 test_true_pfm: -13.766720877408831
episode: 264 training return: tensor(-1695.5618, device='cuda:0')
episode: 265 training return: tensor(-1756.5112, device='cuda:0')
episode: 266 training return: tensor(-1724.6410, device='cuda:0')
episode: 267 training return: tensor(-1759.3199, device='cuda:0')
epoch: 67 test_true_pfm: -19.785094006006272
episode: 268 training return: tensor(-1737.2308, device='cuda:0')
episode: 269 training return: tensor(-1699.4659, device='cuda:0')
episode: 270 training return: tensor(-1645.5668, device='cuda:0')
episode: 271 training return: tensor(-1755.1483, device='cuda:0')
epoch: 68 test_true_pfm: -8.943256276796175
episode: 272 training return: tensor(-1764.6831, device='cuda:0')
episode: 273 training return: tensor(-1709.1740, device='cuda:0')
episode: 274 training return: tensor(-1752.7334, device='cuda:0')
episode: 275 training return: tensor(-1699.3353, device='cuda:0')
epoch: 69 test_true_pfm: -15.49197542713948
episode: 276 training return: tensor(-1698.7085, device='cuda:0')
episode: 277 training return: tensor(-1752.5588, device='cuda:0')
episode: 278 training return: tensor(-1737.7930, device='cuda:0')
episode: 279 training return: tensor(-1728.3430, device='cuda:0')
epoch: 70 test_true_pfm: -11.955863901620967
episode: 280 training return: tensor(-1748.1066, device='cuda:0')
episode: 281 training return: tensor(-1736.1879, device='cuda:0')
episode: 282 training return: tensor(-1659.6730, device='cuda:0')
episode: 283 training return: tensor(-1702.9503, device='cuda:0')
epoch: 71 test_true_pfm: -7.407385803705565
episode: 284 training return: tensor(-1648.2493, device='cuda:0')
episode: 285 training return: tensor(-1670.6527, device='cuda:0')
episode: 286 training return: tensor(-1676.7375, device='cuda:0')
episode: 287 training return: tensor(-1747.5356, device='cuda:0')
epoch: 72 test_true_pfm: -8.534994083396972
episode: 288 training return: tensor(-1741.0911, device='cuda:0')
episode: 289 training return: tensor(-1741.0232, device='cuda:0')
episode: 290 training return: tensor(-1690.4202, device='cuda:0')
episode: 291 training return: tensor(-1746.7257, device='cuda:0')
epoch: 73 test_true_pfm: -7.614243682532842
episode: 292 training return: tensor(-1706.7833, device='cuda:0')
episode: 293 training return: tensor(-1751.3721, device='cuda:0')
episode: 294 training return: tensor(-1669.6516, device='cuda:0')
episode: 295 training return: tensor(-1702.9092, device='cuda:0')
epoch: 74 test_true_pfm: -6.5037113082005185
episode: 296 training return: tensor(-1628.9879, device='cuda:0')
episode: 297 training return: tensor(-1668.5643, device='cuda:0')
episode: 298 training return: tensor(-1717.8523, device='cuda:0')
episode: 299 training return: tensor(-1739.2253, device='cuda:0')
epoch: 75 test_true_pfm: -3.832491527687688
episode: 300 training return: tensor(-1736.3693, device='cuda:0')
episode: 301 training return: tensor(-1659.3230, device='cuda:0')
episode: 302 training return: tensor(-1744.9139, device='cuda:0')
episode: 303 training return: tensor(-1694.2704, device='cuda:0')
epoch: 76 test_true_pfm: 0.21278046544973825
episode: 304 training return: tensor(-1664.1650, device='cuda:0')
episode: 305 training return: tensor(-1684.7982, device='cuda:0')
episode: 306 training return: tensor(-1745.6990, device='cuda:0')
episode: 307 training return: tensor(-1687.6298, device='cuda:0')
epoch: 77 test_true_pfm: -5.832011406365177
episode: 308 training return: tensor(-1649.5720, device='cuda:0')
episode: 309 training return: tensor(-1702.3201, device='cuda:0')
episode: 310 training return: tensor(-1743.9844, device='cuda:0')
episode: 311 training return: tensor(-1683.0676, device='cuda:0')
epoch: 78 test_true_pfm: -2.0385826550732715
episode: 312 training return: tensor(-1728.9351, device='cuda:0')
episode: 313 training return: tensor(-1737.8071, device='cuda:0')
episode: 314 training return: tensor(-1739.0242, device='cuda:0')
episode: 315 training return: tensor(-1730.3339, device='cuda:0')
epoch: 79 test_true_pfm: 0.5447015294521376
episode: 316 training return: tensor(-1655.9612, device='cuda:0')
episode: 317 training return: tensor(-1636.5688, device='cuda:0')
episode: 318 training return: tensor(-1649.2799, device='cuda:0')
episode: 319 training return: tensor(-1627.8334, device='cuda:0')
epoch: 80 test_true_pfm: -0.4409571129716354
episode: 320 training return: tensor(-1728.5178, device='cuda:0')
episode: 321 training return: tensor(-1709.6368, device='cuda:0')
episode: 322 training return: tensor(-1740.5798, device='cuda:0')
episode: 323 training return: tensor(-1741.6433, device='cuda:0')
epoch: 81 test_true_pfm: -4.535207554056306
episode: 324 training return: tensor(-1625.5653, device='cuda:0')
episode: 325 training return: tensor(-1747.3842, device='cuda:0')
episode: 326 training return: tensor(-1666.1312, device='cuda:0')
episode: 327 training return: tensor(-1604.2954, device='cuda:0')
epoch: 82 test_true_pfm: 0.7654294473947658
episode: 328 training return: tensor(-1740.1804, device='cuda:0')
episode: 329 training return: tensor(-1646.7426, device='cuda:0')
episode: 330 training return: tensor(-1664.9105, device='cuda:0')
episode: 331 training return: tensor(-1747.0116, device='cuda:0')
epoch: 83 test_true_pfm: -1.5561181704363316
episode: 332 training return: tensor(-1643.2814, device='cuda:0')
episode: 333 training return: tensor(-1738.4612, device='cuda:0')
episode: 334 training return: tensor(-1684.0166, device='cuda:0')
episode: 335 training return: tensor(-1696.9178, device='cuda:0')
epoch: 84 test_true_pfm: -4.49168362096422
episode: 336 training return: tensor(-1752.5542, device='cuda:0')
episode: 337 training return: tensor(-1740.1803, device='cuda:0')
episode: 338 training return: tensor(-1697.4146, device='cuda:0')
episode: 339 training return: tensor(-1654.8970, device='cuda:0')
epoch: 85 test_true_pfm: 1.2383547184549484
episode: 340 training return: tensor(-1637.4614, device='cuda:0')
episode: 341 training return: tensor(-1614.0023, device='cuda:0')
episode: 342 training return: tensor(-1744.0026, device='cuda:0')
episode: 343 training return: tensor(-1635.0841, device='cuda:0')
epoch: 86 test_true_pfm: -10.911514868882563
episode: 344 training return: tensor(-1754.8500, device='cuda:0')
episode: 345 training return: tensor(-1640.7831, device='cuda:0')
episode: 346 training return: tensor(-1718.1509, device='cuda:0')
episode: 347 training return: tensor(-1740.9454, device='cuda:0')
epoch: 87 test_true_pfm: -1.971108277372271
episode: 348 training return: tensor(-1649.6051, device='cuda:0')
episode: 349 training return: tensor(-1715.8486, device='cuda:0')
episode: 350 training return: tensor(-1642.0009, device='cuda:0')
episode: 351 training return: tensor(-1656.3284, device='cuda:0')
epoch: 88 test_true_pfm: -4.011748250176308
episode: 352 training return: tensor(-1690.2960, device='cuda:0')
episode: 353 training return: tensor(-1705.9764, device='cuda:0')
episode: 354 training return: tensor(-1621.2919, device='cuda:0')
episode: 355 training return: tensor(-1614.1792, device='cuda:0')
epoch: 89 test_true_pfm: -1.7016392421819806
episode: 356 training return: tensor(-1660.6110, device='cuda:0')
episode: 357 training return: tensor(-1633.4478, device='cuda:0')
episode: 358 training return: tensor(-1734.4982, device='cuda:0')
episode: 359 training return: tensor(-1665.4666, device='cuda:0')
epoch: 90 test_true_pfm: 4.383147294443783
episode: 360 training return: tensor(-1623.8170, device='cuda:0')
episode: 361 training return: tensor(-1631.5836, device='cuda:0')
episode: 362 training return: tensor(-1740.0278, device='cuda:0')
episode: 363 training return: tensor(-1691.6925, device='cuda:0')
epoch: 91 test_true_pfm: -13.011516418578802
episode: 364 training return: tensor(-1613.9034, device='cuda:0')
episode: 365 training return: tensor(-1708.6265, device='cuda:0')
episode: 366 training return: tensor(-1650.1042, device='cuda:0')
episode: 367 training return: tensor(-1619.1033, device='cuda:0')
epoch: 92 test_true_pfm: 1.057673987552268
episode: 368 training return: tensor(-1744.4792, device='cuda:0')
episode: 369 training return: tensor(-1637.0798, device='cuda:0')
episode: 370 training return: tensor(-1757.0159, device='cuda:0')
episode: 371 training return: tensor(-1729.3595, device='cuda:0')
epoch: 93 test_true_pfm: -1.8332306760178947
episode: 372 training return: tensor(-1630.3590, device='cuda:0')
episode: 373 training return: tensor(-1634.1990, device='cuda:0')
episode: 374 training return: tensor(-1639.3179, device='cuda:0')
episode: 375 training return: tensor(-1649.8617, device='cuda:0')
epoch: 94 test_true_pfm: -2.3859355823142443
episode: 376 training return: tensor(-1737.6897, device='cuda:0')
episode: 377 training return: tensor(-1654.8499, device='cuda:0')
episode: 378 training return: tensor(-1633.7356, device='cuda:0')
episode: 379 training return: tensor(-1619.0676, device='cuda:0')
epoch: 95 test_true_pfm: 3.6257475943472333
episode: 380 training return: tensor(-1688.2618, device='cuda:0')
episode: 381 training return: tensor(-1625.0602, device='cuda:0')
episode: 382 training return: tensor(-1620.7681, device='cuda:0')
episode: 383 training return: tensor(-1662.9476, device='cuda:0')
epoch: 96 test_true_pfm: -4.5379592341243455
episode: 384 training return: tensor(-1693.5563, device='cuda:0')
episode: 385 training return: tensor(-1621.0935, device='cuda:0')
episode: 386 training return: tensor(-1683.0355, device='cuda:0')
episode: 387 training return: tensor(-1650.1475, device='cuda:0')
epoch: 97 test_true_pfm: 2.4652952817928164
episode: 388 training return: tensor(-1680.7086, device='cuda:0')
episode: 389 training return: tensor(-1723.9781, device='cuda:0')
episode: 390 training return: tensor(-1723.6575, device='cuda:0')
episode: 391 training return: tensor(-1615.9927, device='cuda:0')
epoch: 98 test_true_pfm: -0.3209234635832798
episode: 392 training return: tensor(-1621.2819, device='cuda:0')
episode: 393 training return: tensor(-1635.8593, device='cuda:0')
episode: 394 training return: tensor(-1621.3781, device='cuda:0')
episode: 395 training return: tensor(-1634.0685, device='cuda:0')
epoch: 99 test_true_pfm: -2.5488059331451773
episode: 396 training return: tensor(-1735.0153, device='cuda:0')
episode: 397 training return: tensor(-1636.0660, device='cuda:0')
episode: 398 training return: tensor(-1616.3865, device='cuda:0')
episode: 399 training return: tensor(-1609.5062, device='cuda:0')
epoch: 100 test_true_pfm: 0.13530989449519742
episode: 400 training return: tensor(-1703.6687, device='cuda:0')
episode: 401 training return: tensor(-1641.0424, device='cuda:0')
episode: 402 training return: tensor(-1630.2689, device='cuda:0')
episode: 403 training return: tensor(-1617.9219, device='cuda:0')
epoch: 101 test_true_pfm: -3.2424093085993335
episode: 404 training return: tensor(-1627.0735, device='cuda:0')
episode: 405 training return: tensor(-1633.3109, device='cuda:0')
episode: 406 training return: tensor(-1630.7933, device='cuda:0')
episode: 407 training return: tensor(-1616.9413, device='cuda:0')
epoch: 102 test_true_pfm: -6.081452569271144
episode: 408 training return: tensor(-1628.6069, device='cuda:0')
episode: 409 training return: tensor(-1636.6725, device='cuda:0')
episode: 410 training return: tensor(-1645.6624, device='cuda:0')
episode: 411 training return: tensor(-1635.2605, device='cuda:0')
epoch: 103 test_true_pfm: -4.4776023722695335
episode: 412 training return: tensor(-1627.0168, device='cuda:0')
episode: 413 training return: tensor(-1678.4244, device='cuda:0')
episode: 414 training return: tensor(-1622.0657, device='cuda:0')
episode: 415 training return: tensor(-1618.1302, device='cuda:0')
epoch: 104 test_true_pfm: 1.3931803664997513
episode: 416 training return: tensor(-1731.9397, device='cuda:0')
episode: 417 training return: tensor(-1625.6714, device='cuda:0')
episode: 418 training return: tensor(-1634.3905, device='cuda:0')
episode: 419 training return: tensor(-1626.5742, device='cuda:0')
epoch: 105 test_true_pfm: -0.9291764598215364
episode: 420 training return: tensor(-1636.7598, device='cuda:0')
episode: 421 training return: tensor(-1658.3077, device='cuda:0')
episode: 422 training return: tensor(-1670.8199, device='cuda:0')
episode: 423 training return: tensor(-1628.9044, device='cuda:0')
epoch: 106 test_true_pfm: -3.4489088990533427
episode: 424 training return: tensor(-1639.5770, device='cuda:0')
episode: 425 training return: tensor(-1698.3419, device='cuda:0')
episode: 426 training return: tensor(-1625.4202, device='cuda:0')
episode: 427 training return: tensor(-1699.1979, device='cuda:0')
epoch: 107 test_true_pfm: -0.49287705985255686
episode: 428 training return: tensor(-1639.1254, device='cuda:0')
episode: 429 training return: tensor(-1653.3627, device='cuda:0')
episode: 430 training return: tensor(-1734.2212, device='cuda:0')
episode: 431 training return: tensor(-1692.2606, device='cuda:0')
epoch: 108 test_true_pfm: -2.657118204268329
episode: 432 training return: tensor(-1630.8539, device='cuda:0')
episode: 433 training return: tensor(-1642.5334, device='cuda:0')
episode: 434 training return: tensor(-1696.6068, device='cuda:0')
episode: 435 training return: tensor(-1650.7567, device='cuda:0')
epoch: 109 test_true_pfm: -11.59322365391994
episode: 436 training return: tensor(-1713.0397, device='cuda:0')
episode: 437 training return: tensor(-1612.9612, device='cuda:0')
episode: 438 training return: tensor(-1615.6577, device='cuda:0')
episode: 439 training return: tensor(-1634.6296, device='cuda:0')
epoch: 110 test_true_pfm: -3.6576176976890813
episode: 440 training return: tensor(-1695.7251, device='cuda:0')
episode: 441 training return: tensor(-1626.9438, device='cuda:0')
episode: 442 training return: tensor(-1627.4790, device='cuda:0')
episode: 443 training return: tensor(-1707.3428, device='cuda:0')
epoch: 111 test_true_pfm: -2.085715945471233
episode: 444 training return: tensor(-1675.0145, device='cuda:0')
episode: 445 training return: tensor(-1616.4537, device='cuda:0')
episode: 446 training return: tensor(-1736.7906, device='cuda:0')
episode: 447 training return: tensor(-1740.2103, device='cuda:0')
epoch: 112 test_true_pfm: -0.9617860825437622
episode: 448 training return: tensor(-1670.4171, device='cuda:0')
episode: 449 training return: tensor(-1616.8779, device='cuda:0')
episode: 450 training return: tensor(-1628.2395, device='cuda:0')
episode: 451 training return: tensor(-1603.8823, device='cuda:0')
epoch: 113 test_true_pfm: 0.44341396518150694
episode: 452 training return: tensor(-1632.9836, device='cuda:0')
episode: 453 training return: tensor(-1626.6248, device='cuda:0')
episode: 454 training return: tensor(-1618.1310, device='cuda:0')
episode: 455 training return: tensor(-1646.1233, device='cuda:0')
epoch: 114 test_true_pfm: 0.2721342111002269
episode: 456 training return: tensor(-1616.4382, device='cuda:0')
episode: 457 training return: tensor(-1617.1423, device='cuda:0')
episode: 458 training return: tensor(-1668.0542, device='cuda:0')
episode: 459 training return: tensor(-1626.8301, device='cuda:0')
epoch: 115 test_true_pfm: -0.8620162118746834
episode: 460 training return: tensor(-1625.6343, device='cuda:0')
episode: 461 training return: tensor(-1629.6870, device='cuda:0')
episode: 462 training return: tensor(-1629.1842, device='cuda:0')
episode: 463 training return: tensor(-1734.0161, device='cuda:0')
epoch: 116 test_true_pfm: -8.117126020855835
episode: 464 training return: tensor(-1703.2040, device='cuda:0')
episode: 465 training return: tensor(-1617.5715, device='cuda:0')
episode: 466 training return: tensor(-1637.5530, device='cuda:0')
episode: 467 training return: tensor(-1630.5696, device='cuda:0')
epoch: 117 test_true_pfm: -1.938613852758792
episode: 468 training return: tensor(-1622.3488, device='cuda:0')
episode: 469 training return: tensor(-1622.2450, device='cuda:0')
episode: 470 training return: tensor(-1734.4966, device='cuda:0')
episode: 471 training return: tensor(-1622.8870, device='cuda:0')
epoch: 118 test_true_pfm: -5.2771627244485835
episode: 472 training return: tensor(-1605.0006, device='cuda:0')
episode: 473 training return: tensor(-1705.8792, device='cuda:0')
episode: 474 training return: tensor(-1690.3796, device='cuda:0')
episode: 475 training return: tensor(-1638.7871, device='cuda:0')
epoch: 119 test_true_pfm: -1.5328425041475218
episode: 476 training return: tensor(-1611.7091, device='cuda:0')
episode: 477 training return: tensor(-1615.3782, device='cuda:0')
episode: 478 training return: tensor(-1637.2628, device='cuda:0')
episode: 479 training return: tensor(-1632.5793, device='cuda:0')
epoch: 120 test_true_pfm: -5.550735305155331
episode: 480 training return: tensor(-1715.1666, device='cuda:0')
episode: 481 training return: tensor(-1613.7487, device='cuda:0')
episode: 482 training return: tensor(-1645.3027, device='cuda:0')
episode: 483 training return: tensor(-1667.3579, device='cuda:0')
epoch: 121 test_true_pfm: -1.6637173791880866
episode: 484 training return: tensor(-1616.2715, device='cuda:0')
episode: 485 training return: tensor(-1606.5049, device='cuda:0')
episode: 486 training return: tensor(-1605.6609, device='cuda:0')
episode: 487 training return: tensor(-1636.8898, device='cuda:0')
epoch: 122 test_true_pfm: -7.904530031100141
episode: 488 training return: tensor(-1740.3822, device='cuda:0')
episode: 489 training return: tensor(-1701.3777, device='cuda:0')
episode: 490 training return: tensor(-1609.6769, device='cuda:0')
episode: 491 training return: tensor(-1635.6768, device='cuda:0')
epoch: 123 test_true_pfm: -7.737157268425281
episode: 492 training return: tensor(-1599.9733, device='cuda:0')
episode: 493 training return: tensor(-1659.6010, device='cuda:0')
episode: 494 training return: tensor(-1658.5693, device='cuda:0')
episode: 495 training return: tensor(-1688.0247, device='cuda:0')
epoch: 124 test_true_pfm: -9.929786901474587
episode: 496 training return: tensor(-1604.9720, device='cuda:0')
episode: 497 training return: tensor(-1598.5468, device='cuda:0')
episode: 498 training return: tensor(-1634.8463, device='cuda:0')
episode: 499 training return: tensor(-1617.8591, device='cuda:0')
epoch: 125 test_true_pfm: -13.292702814659878
episode: 500 training return: tensor(-1605.2273, device='cuda:0')
episode: 501 training return: tensor(-1609.0685, device='cuda:0')
episode: 502 training return: tensor(-1672.6038, device='cuda:0')
episode: 503 training return: tensor(-1616.5420, device='cuda:0')
epoch: 126 test_true_pfm: -12.015848927565097
episode: 504 training return: tensor(-1631.6024, device='cuda:0')
episode: 505 training return: tensor(-1631.7031, device='cuda:0')
episode: 506 training return: tensor(-1617.1747, device='cuda:0')
episode: 507 training return: tensor(-1615.9261, device='cuda:0')
epoch: 127 test_true_pfm: -4.817643348671325
episode: 508 training return: tensor(-1657.9677, device='cuda:0')
episode: 509 training return: tensor(-1616.2717, device='cuda:0')
episode: 510 training return: tensor(-1666.3213, device='cuda:0')
episode: 511 training return: tensor(-1611.0688, device='cuda:0')
epoch: 128 test_true_pfm: -15.287422310577563
episode: 512 training return: tensor(-1598.8641, device='cuda:0')
episode: 513 training return: tensor(-1596.0605, device='cuda:0')
episode: 514 training return: tensor(-1605.7013, device='cuda:0')
episode: 515 training return: tensor(-1627.6506, device='cuda:0')
epoch: 129 test_true_pfm: -14.725321728974038
episode: 516 training return: tensor(-1631.5930, device='cuda:0')
episode: 517 training return: tensor(-1623.4493, device='cuda:0')
episode: 518 training return: tensor(-1624.0219, device='cuda:0')
episode: 519 training return: tensor(-1606.5597, device='cuda:0')
epoch: 130 test_true_pfm: -17.346776758327668
episode: 520 training return: tensor(-1613.0868, device='cuda:0')
episode: 521 training return: tensor(-1709.1992, device='cuda:0')
episode: 522 training return: tensor(-1594.5284, device='cuda:0')
episode: 523 training return: tensor(-1611.7390, device='cuda:0')
epoch: 131 test_true_pfm: -22.061556664597685
episode: 524 training return: tensor(-1608.5184, device='cuda:0')
episode: 525 training return: tensor(-1601.9545, device='cuda:0')
episode: 526 training return: tensor(-1608.6509, device='cuda:0')
episode: 527 training return: tensor(-1620.8434, device='cuda:0')
epoch: 132 test_true_pfm: -14.716148807652173
episode: 528 training return: tensor(-1599.3298, device='cuda:0')
episode: 529 training return: tensor(-1607.4849, device='cuda:0')
episode: 530 training return: tensor(-1580.6256, device='cuda:0')
episode: 531 training return: tensor(-1621.2222, device='cuda:0')
epoch: 133 test_true_pfm: -13.264328902040374
episode: 532 training return: tensor(-1600.1766, device='cuda:0')
episode: 533 training return: tensor(-1617.6267, device='cuda:0')
episode: 534 training return: tensor(-1614.6892, device='cuda:0')
episode: 535 training return: tensor(-1597.5984, device='cuda:0')
epoch: 134 test_true_pfm: -10.286536109818856
episode: 536 training return: tensor(-1593.5271, device='cuda:0')
episode: 537 training return: tensor(-1589.2001, device='cuda:0')
episode: 538 training return: tensor(-1592.0337, device='cuda:0')
episode: 539 training return: tensor(-1593.5951, device='cuda:0')
epoch: 135 test_true_pfm: -14.579818357273362
episode: 540 training return: tensor(-1603.4045, device='cuda:0')
episode: 541 training return: tensor(-1606.3267, device='cuda:0')
episode: 542 training return: tensor(-1642.8191, device='cuda:0')
episode: 543 training return: tensor(-1606.3203, device='cuda:0')
epoch: 136 test_true_pfm: -10.91641585265284
episode: 544 training return: tensor(-1609.0070, device='cuda:0')
episode: 545 training return: tensor(-1615.9744, device='cuda:0')
episode: 546 training return: tensor(-1678.9996, device='cuda:0')
episode: 547 training return: tensor(-1606.2732, device='cuda:0')
epoch: 137 test_true_pfm: -10.645760453430398
episode: 548 training return: tensor(-1594.7812, device='cuda:0')
episode: 549 training return: tensor(-1608.4757, device='cuda:0')
episode: 550 training return: tensor(-1604.4106, device='cuda:0')
episode: 551 training return: tensor(-1595.3500, device='cuda:0')
epoch: 138 test_true_pfm: -11.236324736227635
episode: 552 training return: tensor(-1596.7428, device='cuda:0')
episode: 553 training return: tensor(-1608.5444, device='cuda:0')
episode: 554 training return: tensor(-1597.2693, device='cuda:0')
episode: 555 training return: tensor(-1588.7446, device='cuda:0')
epoch: 139 test_true_pfm: -11.803097602844645
episode: 556 training return: tensor(-1603.5892, device='cuda:0')
episode: 557 training return: tensor(-1611.6073, device='cuda:0')
episode: 558 training return: tensor(-1624.0562, device='cuda:0')
episode: 559 training return: tensor(-1614.4753, device='cuda:0')
epoch: 140 test_true_pfm: -14.801653583111483
episode: 560 training return: tensor(-1601.3130, device='cuda:0')
episode: 561 training return: tensor(-1607.4541, device='cuda:0')
episode: 562 training return: tensor(-1597.7059, device='cuda:0')
episode: 563 training return: tensor(-1616.1034, device='cuda:0')
epoch: 141 test_true_pfm: -15.633148230125707
episode: 564 training return: tensor(-1598.6022, device='cuda:0')
episode: 565 training return: tensor(-1597.8605, device='cuda:0')
episode: 566 training return: tensor(-1597.6024, device='cuda:0')
episode: 567 training return: tensor(-1603.8630, device='cuda:0')
epoch: 142 test_true_pfm: -17.02034864793522
episode: 568 training return: tensor(-1593.4520, device='cuda:0')
episode: 569 training return: tensor(-1596.6168, device='cuda:0')
episode: 570 training return: tensor(-1610.0505, device='cuda:0')
episode: 571 training return: tensor(-1599.5006, device='cuda:0')
epoch: 143 test_true_pfm: -13.218894767318028
episode: 572 training return: tensor(-1742.4883, device='cuda:0')
episode: 573 training return: tensor(-1612.6716, device='cuda:0')
episode: 574 training return: tensor(-1618.9445, device='cuda:0')
episode: 575 training return: tensor(-1589.9320, device='cuda:0')
epoch: 144 test_true_pfm: -17.303107309004393
episode: 576 training return: tensor(-1610.1064, device='cuda:0')
episode: 577 training return: tensor(-1606.1858, device='cuda:0')
episode: 578 training return: tensor(-1732.5610, device='cuda:0')
episode: 579 training return: tensor(-1587.6162, device='cuda:0')
epoch: 145 test_true_pfm: -15.63849639850195
episode: 580 training return: tensor(-1600.8092, device='cuda:0')
episode: 581 training return: tensor(-1608.3330, device='cuda:0')
episode: 582 training return: tensor(-1609.7764, device='cuda:0')
episode: 583 training return: tensor(-1619.7123, device='cuda:0')
epoch: 146 test_true_pfm: -12.73230903065397
episode: 584 training return: tensor(-1597.9100, device='cuda:0')
episode: 585 training return: tensor(-1605.3754, device='cuda:0')
episode: 586 training return: tensor(-1599.4871, device='cuda:0')
episode: 587 training return: tensor(-1603.2948, device='cuda:0')
epoch: 147 test_true_pfm: -11.035356902948417
episode: 588 training return: tensor(-1602.7123, device='cuda:0')
episode: 589 training return: tensor(-1596.5826, device='cuda:0')
episode: 590 training return: tensor(-1606.4698, device='cuda:0')
episode: 591 training return: tensor(-1600.2965, device='cuda:0')
epoch: 148 test_true_pfm: -7.297353992809846
episode: 592 training return: tensor(-1607.0688, device='cuda:0')
episode: 593 training return: tensor(-1595.2854, device='cuda:0')
episode: 594 training return: tensor(-1623.7515, device='cuda:0')
episode: 595 training return: tensor(-1636.3162, device='cuda:0')
epoch: 149 test_true_pfm: -10.245247613723114
episode: 596 training return: tensor(-1606.9564, device='cuda:0')
episode: 597 training return: tensor(-1617.9998, device='cuda:0')
episode: 598 training return: tensor(-1594.7725, device='cuda:0')
episode: 599 training return: tensor(-1597.8569, device='cuda:0')
epoch: 150 test_true_pfm: -8.16966589175074
