['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '3', '--data', '100000', '--regu', '0.3']
1988.2637992991138
episode: 0 training return: tensor(-419.9146, device='cuda:0')
episode: 1 training return: tensor(-339.8582, device='cuda:0')
episode: 2 training return: tensor(-336.5051, device='cuda:0')
episode: 3 training return: tensor(-361.1297, device='cuda:0')
epoch: 1 test_true_pfm: 1347.8724287527011 sim_pfm: -374.6774923778915
episode: 4 training return: tensor(-178.8181, device='cuda:0')
episode: 5 training return: tensor(-322.6223, device='cuda:0')
episode: 6 training return: tensor(-450.7577, device='cuda:0')
episode: 7 training return: tensor(-402.7535, device='cuda:0')
epoch: 2 test_true_pfm: 3108.224346927042 sim_pfm: 10.00017883827483
episode: 8 training return: tensor(-98.5097, device='cuda:0')
episode: 9 training return: tensor(-179.3295, device='cuda:0')
episode: 10 training return: tensor(-330.8813, device='cuda:0')
episode: 11 training return: tensor(-281.5770, device='cuda:0')
epoch: 3 test_true_pfm: 1201.4473364947364 sim_pfm: -389.4461157967259
episode: 12 training return: tensor(178.7151, device='cuda:0')
episode: 13 training return: tensor(-453.8068, device='cuda:0')
episode: 14 training return: tensor(-273.9028, device='cuda:0')
episode: 15 training return: tensor(-522.6490, device='cuda:0')
epoch: 4 test_true_pfm: 1648.8974659346413 sim_pfm: -382.89848590514157
episode: 16 training return: tensor(-356.3256, device='cuda:0')
episode: 17 training return: tensor(-514.9852, device='cuda:0')
episode: 18 training return: tensor(-453.8064, device='cuda:0')
episode: 19 training return: tensor(-438.8861, device='cuda:0')
epoch: 5 test_true_pfm: 1719.965318993216 sim_pfm: -350.19409717755235
episode: 20 training return: tensor(-462.8496, device='cuda:0')
episode: 21 training return: tensor(-440.9525, device='cuda:0')
episode: 22 training return: tensor(-410.3458, device='cuda:0')
episode: 23 training return: tensor(-359.3278, device='cuda:0')
epoch: 6 test_true_pfm: 1001.0463385812183 sim_pfm: -499.5639695727829
episode: 24 training return: tensor(-515.8683, device='cuda:0')
episode: 25 training return: tensor(-351.5991, device='cuda:0')
episode: 26 training return: tensor(-276.5496, device='cuda:0')
episode: 27 training return: tensor(-519.8002, device='cuda:0')
epoch: 7 test_true_pfm: 1181.8941213985406 sim_pfm: -439.1112759015523
episode: 28 training return: tensor(-437.5771, device='cuda:0')
episode: 29 training return: tensor(-345.0889, device='cuda:0')
episode: 30 training return: tensor(-521.5906, device='cuda:0')
episode: 31 training return: tensor(-450.4259, device='cuda:0')
epoch: 8 test_true_pfm: 909.4940426605502 sim_pfm: -529.7249251023944
episode: 32 training return: tensor(-491.2220, device='cuda:0')
episode: 33 training return: tensor(-331.4214, device='cuda:0')
episode: 34 training return: tensor(-556.9885, device='cuda:0')
episode: 35 training return: tensor(-511.1581, device='cuda:0')
epoch: 9 test_true_pfm: 985.358019406487 sim_pfm: -518.0749441949496
episode: 36 training return: tensor(-358.1501, device='cuda:0')
episode: 37 training return: tensor(-329.1475, device='cuda:0')
episode: 38 training return: tensor(-351.6172, device='cuda:0')
episode: 39 training return: tensor(-528.2082, device='cuda:0')
epoch: 10 test_true_pfm: 1719.1744877461776 sim_pfm: -257.6300115078532
episode: 40 training return: tensor(-499.1136, device='cuda:0')
episode: 41 training return: tensor(-431.2150, device='cuda:0')
episode: 42 training return: tensor(-551.5772, device='cuda:0')
episode: 43 training return: tensor(-452.0446, device='cuda:0')
epoch: 11 test_true_pfm: 1390.0924753053612 sim_pfm: -397.4988871421083
episode: 44 training return: tensor(-344.4157, device='cuda:0')
episode: 45 training return: tensor(-341.0219, device='cuda:0')
episode: 46 training return: tensor(-79.1792, device='cuda:0')
episode: 47 training return: tensor(-168.6431, device='cuda:0')
epoch: 12 test_true_pfm: 1907.8081119829433 sim_pfm: -218.49076633721901
episode: 48 training return: tensor(-73.4130, device='cuda:0')
episode: 49 training return: tensor(-401.3388, device='cuda:0')
episode: 50 training return: tensor(-58.3139, device='cuda:0')
episode: 51 training return: tensor(-407.4085, device='cuda:0')
epoch: 13 test_true_pfm: 1200.8605259633339 sim_pfm: -450.948711226801
episode: 52 training return: tensor(-385.6229, device='cuda:0')
episode: 53 training return: tensor(-428.6754, device='cuda:0')
episode: 54 training return: tensor(-445.1472, device='cuda:0')
episode: 55 training return: tensor(-137.6220, device='cuda:0')
epoch: 14 test_true_pfm: 2041.512834993818 sim_pfm: -2.9233950407554707
episode: 56 training return: tensor(-335.1817, device='cuda:0')
episode: 57 training return: tensor(-308.0065, device='cuda:0')
episode: 58 training return: tensor(-371.3750, device='cuda:0')
episode: 59 training return: tensor(-230.2294, device='cuda:0')
epoch: 15 test_true_pfm: 1925.4248877135724 sim_pfm: -311.6485799944494
episode: 60 training return: tensor(-280.6431, device='cuda:0')
episode: 61 training return: tensor(-216.5194, device='cuda:0')
episode: 62 training return: tensor(-403.5635, device='cuda:0')
episode: 63 training return: tensor(-430.0508, device='cuda:0')
epoch: 16 test_true_pfm: 2225.8661977215957 sim_pfm: -148.70801891518445
episode: 64 training return: tensor(290.8764, device='cuda:0')
episode: 65 training return: tensor(-311.7859, device='cuda:0')
episode: 66 training return: tensor(-433.2296, device='cuda:0')
episode: 67 training return: tensor(31.0610, device='cuda:0')
epoch: 17 test_true_pfm: 2817.732289021404 sim_pfm: -77.21361025896233
episode: 68 training return: tensor(-271.3343, device='cuda:0')
episode: 69 training return: tensor(-319.4667, device='cuda:0')
episode: 70 training return: tensor(-425.1566, device='cuda:0')
episode: 71 training return: tensor(183.4754, device='cuda:0')
epoch: 18 test_true_pfm: 1299.6287248525716 sim_pfm: -371.7534106379996
episode: 72 training return: tensor(23.3163, device='cuda:0')
episode: 73 training return: tensor(-141.1155, device='cuda:0')
episode: 74 training return: tensor(-413.1072, device='cuda:0')
episode: 75 training return: tensor(-153.5047, device='cuda:0')
epoch: 19 test_true_pfm: 2771.7050121880347 sim_pfm: 67.76927918425645
episode: 76 training return: tensor(-333.1003, device='cuda:0')
episode: 77 training return: tensor(-408.1153, device='cuda:0')
episode: 78 training return: tensor(281.2367, device='cuda:0')
episode: 79 training return: tensor(-250.1935, device='cuda:0')
epoch: 20 test_true_pfm: 1304.8692335169562 sim_pfm: -394.935052709848
episode: 80 training return: tensor(-307.6409, device='cuda:0')
episode: 81 training return: tensor(-116.2348, device='cuda:0')
episode: 82 training return: tensor(-412.1806, device='cuda:0')
episode: 83 training return: tensor(-327.2542, device='cuda:0')
epoch: 21 test_true_pfm: 2352.977673101302 sim_pfm: -188.20518250072686
episode: 84 training return: tensor(115.9467, device='cuda:0')
episode: 85 training return: tensor(-250.2200, device='cuda:0')
episode: 86 training return: tensor(-329.1258, device='cuda:0')
episode: 87 training return: tensor(-168.6053, device='cuda:0')
epoch: 22 test_true_pfm: 2246.2586386413473 sim_pfm: 4.0382959304067
episode: 88 training return: tensor(-325.8237, device='cuda:0')
episode: 89 training return: tensor(-31.6801, device='cuda:0')
episode: 90 training return: tensor(-455.0090, device='cuda:0')
episode: 91 training return: tensor(263.5553, device='cuda:0')
epoch: 23 test_true_pfm: 2817.487309176564 sim_pfm: 199.39533806199324
episode: 92 training return: tensor(-412.3196, device='cuda:0')
episode: 93 training return: tensor(-39.2852, device='cuda:0')
episode: 94 training return: tensor(-350.9569, device='cuda:0')
episode: 95 training return: tensor(-238.7348, device='cuda:0')
epoch: 24 test_true_pfm: 2602.841739967536 sim_pfm: 120.06826407303258
episode: 96 training return: tensor(57.1113, device='cuda:0')
episode: 97 training return: tensor(-389.6215, device='cuda:0')
episode: 98 training return: tensor(-240.2248, device='cuda:0')
episode: 99 training return: tensor(-252.0327, device='cuda:0')
epoch: 25 test_true_pfm: 2093.804379443654 sim_pfm: -157.89946804751526
episode: 100 training return: tensor(-236.9273, device='cuda:0')
episode: 101 training return: tensor(-522.3030, device='cuda:0')
episode: 102 training return: tensor(-406.1993, device='cuda:0')
episode: 103 training return: tensor(-426.2321, device='cuda:0')
epoch: 26 test_true_pfm: 2497.4011082491033 sim_pfm: 77.43970535166834
episode: 104 training return: tensor(-506.6105, device='cuda:0')
episode: 105 training return: tensor(33.9546, device='cuda:0')
episode: 106 training return: tensor(-396.3814, device='cuda:0')
episode: 107 training return: tensor(-425.9566, device='cuda:0')
epoch: 27 test_true_pfm: 2343.8596172947377 sim_pfm: 63.818648514008
episode: 108 training return: tensor(-74.6894, device='cuda:0')
episode: 109 training return: tensor(-498.2782, device='cuda:0')
episode: 110 training return: tensor(-276.5537, device='cuda:0')
episode: 111 training return: tensor(-467.3546, device='cuda:0')
epoch: 28 test_true_pfm: 1757.2801537233042 sim_pfm: -343.4579786629183
episode: 112 training return: tensor(-351.8691, device='cuda:0')
episode: 113 training return: tensor(-489.0935, device='cuda:0')
episode: 114 training return: tensor(-109.2126, device='cuda:0')
episode: 115 training return: tensor(200.3241, device='cuda:0')
epoch: 29 test_true_pfm: 1309.263027437051 sim_pfm: -397.4293545007434
episode: 116 training return: tensor(-331.4776, device='cuda:0')
episode: 117 training return: tensor(-515.2066, device='cuda:0')
episode: 118 training return: tensor(231.8087, device='cuda:0')
episode: 119 training return: tensor(-75.9631, device='cuda:0')
epoch: 30 test_true_pfm: 2375.6049343502855 sim_pfm: -205.14170625730185
episode: 120 training return: tensor(-314.9165, device='cuda:0')
episode: 121 training return: tensor(-412.5811, device='cuda:0')
episode: 122 training return: tensor(-435.7794, device='cuda:0')
episode: 123 training return: tensor(-440.9558, device='cuda:0')
epoch: 31 test_true_pfm: 2584.4245726677336 sim_pfm: -43.24153229724228
episode: 124 training return: tensor(46.5429, device='cuda:0')
episode: 125 training return: tensor(-326.5957, device='cuda:0')
episode: 126 training return: tensor(-268.5935, device='cuda:0')
episode: 127 training return: tensor(-249.1685, device='cuda:0')
epoch: 32 test_true_pfm: 2250.355312156904 sim_pfm: 43.11872169127067
episode: 128 training return: tensor(-178.9734, device='cuda:0')
episode: 129 training return: tensor(-156.3099, device='cuda:0')
episode: 130 training return: tensor(-395.4224, device='cuda:0')
episode: 131 training return: tensor(-70.6410, device='cuda:0')
epoch: 33 test_true_pfm: 2652.904390517675 sim_pfm: 154.510890672255
episode: 132 training return: tensor(-239.3950, device='cuda:0')
episode: 133 training return: tensor(-416.3271, device='cuda:0')
episode: 134 training return: tensor(-242.8176, device='cuda:0')
episode: 135 training return: tensor(-157.0028, device='cuda:0')
epoch: 34 test_true_pfm: 1309.4768278263944 sim_pfm: -390.0830628579327
episode: 136 training return: tensor(-398.1605, device='cuda:0')
episode: 137 training return: tensor(-412.6333, device='cuda:0')
episode: 138 training return: tensor(-424.2893, device='cuda:0')
episode: 139 training return: tensor(-326.8538, device='cuda:0')
epoch: 35 test_true_pfm: 2109.626944775527 sim_pfm: 12.59510514854143
episode: 140 training return: tensor(-115.4269, device='cuda:0')
episode: 141 training return: tensor(-468.9164, device='cuda:0')
episode: 142 training return: tensor(-68.7678, device='cuda:0')
episode: 143 training return: tensor(-441.7437, device='cuda:0')
epoch: 36 test_true_pfm: 2202.6325973016724 sim_pfm: -271.9033293543519
episode: 144 training return: tensor(-340.7312, device='cuda:0')
episode: 145 training return: tensor(-237.6889, device='cuda:0')
episode: 146 training return: tensor(-354.5984, device='cuda:0')
episode: 147 training return: tensor(-185.6333, device='cuda:0')
epoch: 37 test_true_pfm: 2282.501988755041 sim_pfm: -87.37701437432163
episode: 148 training return: tensor(-490.1596, device='cuda:0')
episode: 149 training return: tensor(-265.0965, device='cuda:0')
episode: 150 training return: tensor(-356.9941, device='cuda:0')
episode: 151 training return: tensor(-426.7730, device='cuda:0')
epoch: 38 test_true_pfm: 1921.2008777768199 sim_pfm: -311.64873330415384
episode: 152 training return: tensor(-308.3160, device='cuda:0')
episode: 153 training return: tensor(-272.9595, device='cuda:0')
episode: 154 training return: tensor(-451.5443, device='cuda:0')
episode: 155 training return: tensor(-181.8389, device='cuda:0')
epoch: 39 test_true_pfm: 2400.433338547276 sim_pfm: 13.845422793684216
episode: 156 training return: tensor(-181.1246, device='cuda:0')
episode: 157 training return: tensor(-332.7596, device='cuda:0')
episode: 158 training return: tensor(-419.2300, device='cuda:0')
episode: 159 training return: tensor(-326.4961, device='cuda:0')
epoch: 40 test_true_pfm: 3197.428814953848 sim_pfm: -94.65555944590596
episode: 160 training return: tensor(-464.3923, device='cuda:0')
episode: 161 training return: tensor(175.6613, device='cuda:0')
episode: 162 training return: tensor(-338.0298, device='cuda:0')
episode: 163 training return: tensor(-503.1622, device='cuda:0')
epoch: 41 test_true_pfm: 1311.7046332405237 sim_pfm: -398.8158471082958
episode: 164 training return: tensor(-521.0436, device='cuda:0')
episode: 165 training return: tensor(-276.0268, device='cuda:0')
episode: 166 training return: tensor(-272.4951, device='cuda:0')
episode: 167 training return: tensor(-333.9745, device='cuda:0')
epoch: 42 test_true_pfm: 1296.2317989807223 sim_pfm: -408.52653927041683
episode: 168 training return: tensor(-5.2183, device='cuda:0')
episode: 169 training return: tensor(-273.3145, device='cuda:0')
episode: 170 training return: tensor(-515.1297, device='cuda:0')
episode: 171 training return: tensor(-265.0973, device='cuda:0')
epoch: 43 test_true_pfm: 1913.6782871685227 sim_pfm: -183.21328233521976
episode: 172 training return: tensor(-331.1802, device='cuda:0')
episode: 173 training return: tensor(95.3258, device='cuda:0')
episode: 174 training return: tensor(-244.8065, device='cuda:0')
episode: 175 training return: tensor(-429.1708, device='cuda:0')
epoch: 44 test_true_pfm: 2032.0471965252138 sim_pfm: -13.82685315287866
episode: 176 training return: tensor(-66.8462, device='cuda:0')
episode: 177 training return: tensor(-239.4079, device='cuda:0')
episode: 178 training return: tensor(-272.0571, device='cuda:0')
episode: 179 training return: tensor(-207.0899, device='cuda:0')
epoch: 45 test_true_pfm: 2475.3018770639414 sim_pfm: -290.3585697180436
episode: 180 training return: tensor(-308.1220, device='cuda:0')
episode: 181 training return: tensor(-428.2055, device='cuda:0')
episode: 182 training return: tensor(-299.5673, device='cuda:0')
episode: 183 training return: tensor(-197.3204, device='cuda:0')
epoch: 46 test_true_pfm: 1373.512865097234 sim_pfm: -352.0013027626749
episode: 184 training return: tensor(-446.3716, device='cuda:0')
episode: 185 training return: tensor(-458.6759, device='cuda:0')
episode: 186 training return: tensor(-405.3245, device='cuda:0')
episode: 187 training return: tensor(-82.6327, device='cuda:0')
epoch: 47 test_true_pfm: 1342.7514511458978 sim_pfm: -373.5854834416629
episode: 188 training return: tensor(-416.0396, device='cuda:0')
episode: 189 training return: tensor(-459.1904, device='cuda:0')
episode: 190 training return: tensor(-252.9689, device='cuda:0')
episode: 191 training return: tensor(-437.7303, device='cuda:0')
epoch: 48 test_true_pfm: 1831.5294304898 sim_pfm: -3.233596305944957
episode: 192 training return: tensor(-160.3380, device='cuda:0')
episode: 193 training return: tensor(98.2629, device='cuda:0')
episode: 194 training return: tensor(-466.8947, device='cuda:0')
episode: 195 training return: tensor(-430.6823, device='cuda:0')
epoch: 49 test_true_pfm: 1304.8558819462426 sim_pfm: -361.2409349281418
episode: 196 training return: tensor(-474.2878, device='cuda:0')
episode: 197 training return: tensor(-7.7056, device='cuda:0')
episode: 198 training return: tensor(-330.7923, device='cuda:0')
episode: 199 training return: tensor(-317.9327, device='cuda:0')
epoch: 50 test_true_pfm: 2414.645429493386 sim_pfm: 283.95483934890945
episode: 200 training return: tensor(-525.8618, device='cuda:0')
episode: 201 training return: tensor(-278.8596, device='cuda:0')
episode: 202 training return: tensor(-430.1673, device='cuda:0')
episode: 203 training return: tensor(-515.6934, device='cuda:0')
epoch: 51 test_true_pfm: 2246.3883399992596 sim_pfm: 257.7881694865646
episode: 204 training return: tensor(-238.2300, device='cuda:0')
episode: 205 training return: tensor(-98.3144, device='cuda:0')
episode: 206 training return: tensor(-101.8887, device='cuda:0')
episode: 207 training return: tensor(-354.0133, device='cuda:0')
epoch: 52 test_true_pfm: 1580.7884301724373 sim_pfm: -300.4315681223525
episode: 208 training return: tensor(-442.5219, device='cuda:0')
episode: 209 training return: tensor(-460.3910, device='cuda:0')
episode: 210 training return: tensor(-417.5773, device='cuda:0')
episode: 211 training return: tensor(-255.7587, device='cuda:0')
epoch: 53 test_true_pfm: 2133.6452323752096 sim_pfm: -59.15892253579417
episode: 212 training return: tensor(-506.2816, device='cuda:0')
episode: 213 training return: tensor(-290.7197, device='cuda:0')
episode: 214 training return: tensor(-487.9886, device='cuda:0')
episode: 215 training return: tensor(-505.6241, device='cuda:0')
epoch: 54 test_true_pfm: 1918.7712089891502 sim_pfm: 165.37161172689716
episode: 216 training return: tensor(-523.0518, device='cuda:0')
episode: 217 training return: tensor(-170.1295, device='cuda:0')
episode: 218 training return: tensor(-429.4363, device='cuda:0')
episode: 219 training return: tensor(301.7442, device='cuda:0')
epoch: 55 test_true_pfm: 2447.21752039227 sim_pfm: 22.537792827002704
episode: 220 training return: tensor(-363.5080, device='cuda:0')
episode: 221 training return: tensor(-336.1740, device='cuda:0')
episode: 222 training return: tensor(-442.5569, device='cuda:0')
episode: 223 training return: tensor(-382.7363, device='cuda:0')
epoch: 56 test_true_pfm: 1387.015049746877 sim_pfm: -194.2438305944573
episode: 224 training return: tensor(-333.3030, device='cuda:0')
episode: 225 training return: tensor(-407.6710, device='cuda:0')
episode: 226 training return: tensor(-202.5532, device='cuda:0')
episode: 227 training return: tensor(-421.7314, device='cuda:0')
epoch: 57 test_true_pfm: 2290.6704697800174 sim_pfm: -163.31074172343747
episode: 228 training return: tensor(-482.5284, device='cuda:0')
episode: 229 training return: tensor(-83.1707, device='cuda:0')
episode: 230 training return: tensor(-365.3459, device='cuda:0')
episode: 231 training return: tensor(-301.3785, device='cuda:0')
epoch: 58 test_true_pfm: 2811.0939974403577 sim_pfm: 200.18799357422782
episode: 232 training return: tensor(-171.9244, device='cuda:0')
episode: 233 training return: tensor(-325.1965, device='cuda:0')
episode: 234 training return: tensor(-465.2905, device='cuda:0')
episode: 235 training return: tensor(-281.5082, device='cuda:0')
epoch: 59 test_true_pfm: 2686.3902611147732 sim_pfm: 116.91346776966627
episode: 236 training return: tensor(-454.4901, device='cuda:0')
episode: 237 training return: tensor(-141.0188, device='cuda:0')
episode: 238 training return: tensor(-96.2956, device='cuda:0')
episode: 239 training return: tensor(-431.7055, device='cuda:0')
epoch: 60 test_true_pfm: 2127.7508250542014 sim_pfm: -35.773050175824515
episode: 240 training return: tensor(-205.2102, device='cuda:0')
episode: 241 training return: tensor(-531.7983, device='cuda:0')
episode: 242 training return: tensor(-277.7997, device='cuda:0')
episode: 243 training return: tensor(-273.2927, device='cuda:0')
epoch: 61 test_true_pfm: 1303.2585600430857 sim_pfm: -391.9245079845229
episode: 244 training return: tensor(-240.9455, device='cuda:0')
episode: 245 training return: tensor(265.6665, device='cuda:0')
episode: 246 training return: tensor(-278.6131, device='cuda:0')
episode: 247 training return: tensor(-317.6451, device='cuda:0')
epoch: 62 test_true_pfm: 2789.141649794578 sim_pfm: 75.04006044169849
episode: 248 training return: tensor(-270.9513, device='cuda:0')
episode: 249 training return: tensor(-401.8264, device='cuda:0')
episode: 250 training return: tensor(-448.0467, device='cuda:0')
episode: 251 training return: tensor(-429.3907, device='cuda:0')
epoch: 63 test_true_pfm: 1955.3360261994003 sim_pfm: -325.47251375570585
episode: 252 training return: tensor(-249.3229, device='cuda:0')
episode: 253 training return: tensor(-18.6976, device='cuda:0')
episode: 254 training return: tensor(-421.1193, device='cuda:0')
episode: 255 training return: tensor(-467.5957, device='cuda:0')
epoch: 64 test_true_pfm: 2838.2345717189733 sim_pfm: -30.910454046175193
episode: 256 training return: tensor(-512.5236, device='cuda:0')
episode: 257 training return: tensor(-501.6425, device='cuda:0')
episode: 258 training return: tensor(-530.6438, device='cuda:0')
episode: 259 training return: tensor(-252.4606, device='cuda:0')
epoch: 65 test_true_pfm: 2851.0471945409213 sim_pfm: 82.28962822528167
episode: 260 training return: tensor(-333.7719, device='cuda:0')
episode: 261 training return: tensor(-458.9468, device='cuda:0')
episode: 262 training return: tensor(-379.2844, device='cuda:0')
episode: 263 training return: tensor(-10.6079, device='cuda:0')
epoch: 66 test_true_pfm: 1497.1667510218297 sim_pfm: -29.14252661294692
episode: 264 training return: tensor(-370.3580, device='cuda:0')
episode: 265 training return: tensor(-364.6282, device='cuda:0')
episode: 266 training return: tensor(-506.5417, device='cuda:0')
episode: 267 training return: tensor(-411.5037, device='cuda:0')
epoch: 67 test_true_pfm: 2992.1319960555934 sim_pfm: -12.432069222452506
episode: 268 training return: tensor(-510.2997, device='cuda:0')
episode: 269 training return: tensor(-330.0655, device='cuda:0')
episode: 270 training return: tensor(-352.9243, device='cuda:0')
episode: 271 training return: tensor(-402.4114, device='cuda:0')
epoch: 68 test_true_pfm: 3252.925237213451 sim_pfm: 257.39332672180416
episode: 272 training return: tensor(-432.9959, device='cuda:0')
episode: 273 training return: tensor(68.4488, device='cuda:0')
episode: 274 training return: tensor(-324.4213, device='cuda:0')
episode: 275 training return: tensor(-485.0317, device='cuda:0')
epoch: 69 test_true_pfm: 2813.235244550624 sim_pfm: 232.89354738903543
episode: 276 training return: tensor(-166.5321, device='cuda:0')
episode: 277 training return: tensor(-392.5685, device='cuda:0')
episode: 278 training return: tensor(-332.9496, device='cuda:0')
episode: 279 training return: tensor(-263.2257, device='cuda:0')
epoch: 70 test_true_pfm: 1426.739635449325 sim_pfm: -397.0239593075821
episode: 280 training return: tensor(-439.1922, device='cuda:0')
episode: 281 training return: tensor(-497.7602, device='cuda:0')
episode: 282 training return: tensor(-421.6230, device='cuda:0')
episode: 283 training return: tensor(-510.9195, device='cuda:0')
epoch: 71 test_true_pfm: 1553.5828083483277 sim_pfm: -103.2507939656789
episode: 284 training return: tensor(-443.0499, device='cuda:0')
episode: 285 training return: tensor(-261.8811, device='cuda:0')
episode: 286 training return: tensor(-242.4400, device='cuda:0')
episode: 287 training return: tensor(-442.4964, device='cuda:0')
epoch: 72 test_true_pfm: 2314.4964094489847 sim_pfm: 59.88127577165142
episode: 288 training return: tensor(-317.4101, device='cuda:0')
episode: 289 training return: tensor(-410.1836, device='cuda:0')
episode: 290 training return: tensor(-438.7953, device='cuda:0')
episode: 291 training return: tensor(-534.6558, device='cuda:0')
epoch: 73 test_true_pfm: 1974.73157116188 sim_pfm: -57.28044057496785
episode: 292 training return: tensor(7.1239, device='cuda:0')
episode: 293 training return: tensor(-469.7601, device='cuda:0')
episode: 294 training return: tensor(-402.7381, device='cuda:0')
episode: 295 training return: tensor(-470.5321, device='cuda:0')
epoch: 74 test_true_pfm: 2293.3232072075825 sim_pfm: 109.60867423923143
episode: 296 training return: tensor(-285.3875, device='cuda:0')
episode: 297 training return: tensor(-455.7134, device='cuda:0')
episode: 298 training return: tensor(-427.9315, device='cuda:0')
episode: 299 training return: tensor(-462.5023, device='cuda:0')
epoch: 75 test_true_pfm: 2347.750674886729 sim_pfm: -22.73363280230357
episode: 300 training return: tensor(-520.5724, device='cuda:0')
episode: 301 training return: tensor(-497.0839, device='cuda:0')
episode: 302 training return: tensor(-410.2784, device='cuda:0')
episode: 303 training return: tensor(-85.9634, device='cuda:0')
epoch: 76 test_true_pfm: 1474.2454455546588 sim_pfm: -332.74714343240095
episode: 304 training return: tensor(-452.4585, device='cuda:0')
episode: 305 training return: tensor(-522.7716, device='cuda:0')
episode: 306 training return: tensor(-122.7391, device='cuda:0')
episode: 307 training return: tensor(-379.8484, device='cuda:0')
epoch: 77 test_true_pfm: 1683.0632760004612 sim_pfm: -106.58325773658969
episode: 308 training return: tensor(-485.3108, device='cuda:0')
episode: 309 training return: tensor(-512.5540, device='cuda:0')
episode: 310 training return: tensor(-433.9748, device='cuda:0')
episode: 311 training return: tensor(-456.1639, device='cuda:0')
epoch: 78 test_true_pfm: 2377.1131227365204 sim_pfm: 156.11967205426967
episode: 312 training return: tensor(-507.6299, device='cuda:0')
episode: 313 training return: tensor(-505.1261, device='cuda:0')
episode: 314 training return: tensor(-469.2625, device='cuda:0')
episode: 315 training return: tensor(-344.4188, device='cuda:0')
epoch: 79 test_true_pfm: 1518.0220224648644 sim_pfm: -348.85142508756445
episode: 316 training return: tensor(-256.7861, device='cuda:0')
episode: 317 training return: tensor(-181.8900, device='cuda:0')
episode: 318 training return: tensor(-550.7588, device='cuda:0')
episode: 319 training return: tensor(-347.9891, device='cuda:0')
epoch: 80 test_true_pfm: 3325.332119832525 sim_pfm: 12.160505705154113
episode: 320 training return: tensor(-349.5323, device='cuda:0')
episode: 321 training return: tensor(-506.4045, device='cuda:0')
episode: 322 training return: tensor(-453.8707, device='cuda:0')
episode: 323 training return: tensor(-341.4765, device='cuda:0')
epoch: 81 test_true_pfm: 1693.8815270422722 sim_pfm: -101.59653101108658
episode: 324 training return: tensor(-284.5036, device='cuda:0')
episode: 325 training return: tensor(-459.6302, device='cuda:0')
episode: 326 training return: tensor(-420.4000, device='cuda:0')
episode: 327 training return: tensor(-351.6916, device='cuda:0')
epoch: 82 test_true_pfm: 2526.499889930386 sim_pfm: 42.52337570868743
episode: 328 training return: tensor(-482.1035, device='cuda:0')
episode: 329 training return: tensor(-348.7672, device='cuda:0')
episode: 330 training return: tensor(-39.2528, device='cuda:0')
episode: 331 training return: tensor(-344.2449, device='cuda:0')
epoch: 83 test_true_pfm: 3000.692777838571 sim_pfm: 97.67371188829809
episode: 332 training return: tensor(-384.0822, device='cuda:0')
episode: 333 training return: tensor(-266.7481, device='cuda:0')
episode: 334 training return: tensor(-469.8180, device='cuda:0')
episode: 335 training return: tensor(-452.1843, device='cuda:0')
epoch: 84 test_true_pfm: 2353.531406373488 sim_pfm: 249.85543058305242
episode: 336 training return: tensor(-443.9193, device='cuda:0')
episode: 337 training return: tensor(-508.3974, device='cuda:0')
episode: 338 training return: tensor(-364.3986, device='cuda:0')
episode: 339 training return: tensor(-290.1584, device='cuda:0')
epoch: 85 test_true_pfm: 2066.247554115191 sim_pfm: -173.45160253718495
episode: 340 training return: tensor(-520.5309, device='cuda:0')
episode: 341 training return: tensor(-358.7586, device='cuda:0')
episode: 342 training return: tensor(-504.2643, device='cuda:0')
episode: 343 training return: tensor(-398.2836, device='cuda:0')
epoch: 86 test_true_pfm: 2161.944125637308 sim_pfm: -369.7819929934728
episode: 344 training return: tensor(-82.5232, device='cuda:0')
episode: 345 training return: tensor(-511.0252, device='cuda:0')
episode: 346 training return: tensor(-524.2812, device='cuda:0')
episode: 347 training return: tensor(-468.0526, device='cuda:0')
epoch: 87 test_true_pfm: 2213.102897250024 sim_pfm: -98.49158514046576
episode: 348 training return: tensor(-423.8620, device='cuda:0')
episode: 349 training return: tensor(-407.5984, device='cuda:0')
episode: 350 training return: tensor(-357.0966, device='cuda:0')
episode: 351 training return: tensor(-438.5542, device='cuda:0')
epoch: 88 test_true_pfm: 1469.043932746188 sim_pfm: -284.59393166036654
episode: 352 training return: tensor(-444.4797, device='cuda:0')
episode: 353 training return: tensor(-513.7815, device='cuda:0')
episode: 354 training return: tensor(-527.7246, device='cuda:0')
episode: 355 training return: tensor(-429.0894, device='cuda:0')
epoch: 89 test_true_pfm: 1700.1473986230312 sim_pfm: -296.1703847889148
episode: 356 training return: tensor(-467.7204, device='cuda:0')
episode: 357 training return: tensor(-436.6052, device='cuda:0')
episode: 358 training return: tensor(-204.7575, device='cuda:0')
episode: 359 training return: tensor(-528.1643, device='cuda:0')
epoch: 90 test_true_pfm: 1370.0305069119902 sim_pfm: -397.64171446628944
episode: 360 training return: tensor(-470.0450, device='cuda:0')
episode: 361 training return: tensor(-504.4399, device='cuda:0')
episode: 362 training return: tensor(-449.7921, device='cuda:0')
episode: 363 training return: tensor(-260.0587, device='cuda:0')
epoch: 91 test_true_pfm: 2079.884503724677 sim_pfm: -376.48549814906437
episode: 364 training return: tensor(-291.0032, device='cuda:0')
episode: 365 training return: tensor(-514.0650, device='cuda:0')
episode: 366 training return: tensor(-526.5380, device='cuda:0')
episode: 367 training return: tensor(-455.9263, device='cuda:0')
epoch: 92 test_true_pfm: 3087.4242653517626 sim_pfm: 287.7522686436617
episode: 368 training return: tensor(-548.7100, device='cuda:0')
episode: 369 training return: tensor(-431.7152, device='cuda:0')
episode: 370 training return: tensor(-424.3564, device='cuda:0')
episode: 371 training return: tensor(-361.1533, device='cuda:0')
epoch: 93 test_true_pfm: 1805.1642749647117 sim_pfm: -62.18219158441449
episode: 372 training return: tensor(-346.3129, device='cuda:0')
episode: 373 training return: tensor(-524.8729, device='cuda:0')
episode: 374 training return: tensor(-545.6166, device='cuda:0')
episode: 375 training return: tensor(-467.3280, device='cuda:0')
epoch: 94 test_true_pfm: 1562.5457430965414 sim_pfm: -243.5271342798757
episode: 376 training return: tensor(-245.5378, device='cuda:0')
episode: 377 training return: tensor(-461.8159, device='cuda:0')
episode: 378 training return: tensor(-516.7996, device='cuda:0')
episode: 379 training return: tensor(-504.6335, device='cuda:0')
epoch: 95 test_true_pfm: 2786.103738821886 sim_pfm: -25.42066023692799
episode: 380 training return: tensor(-515.1738, device='cuda:0')
episode: 381 training return: tensor(-455.4658, device='cuda:0')
episode: 382 training return: tensor(-117.0224, device='cuda:0')
episode: 383 training return: tensor(-541.6452, device='cuda:0')
epoch: 96 test_true_pfm: 1375.8717589960277 sim_pfm: -358.3288201316609
episode: 384 training return: tensor(55.0130, device='cuda:0')
episode: 385 training return: tensor(-249.5227, device='cuda:0')
episode: 386 training return: tensor(-502.8170, device='cuda:0')
episode: 387 training return: tensor(-385.4939, device='cuda:0')
epoch: 97 test_true_pfm: 2551.4310504557966 sim_pfm: 275.9553798452641
episode: 388 training return: tensor(-406.5685, device='cuda:0')
episode: 389 training return: tensor(-421.9098, device='cuda:0')
episode: 390 training return: tensor(-568.4598, device='cuda:0')
episode: 391 training return: tensor(-452.5104, device='cuda:0')
epoch: 98 test_true_pfm: 2144.3741178991177 sim_pfm: -333.71915989004384
episode: 392 training return: tensor(-523.5809, device='cuda:0')
episode: 393 training return: tensor(-518.6866, device='cuda:0')
episode: 394 training return: tensor(-435.7411, device='cuda:0')
episode: 395 training return: tensor(-307.6828, device='cuda:0')
epoch: 99 test_true_pfm: 3073.7275212866602 sim_pfm: -128.20764614890018
episode: 396 training return: tensor(-278.4011, device='cuda:0')
episode: 397 training return: tensor(-449.1359, device='cuda:0')
episode: 398 training return: tensor(-453.8590, device='cuda:0')
episode: 399 training return: tensor(169.0463, device='cuda:0')
epoch: 100 test_true_pfm: 2737.8375886035506 sim_pfm: 200.40105899004266
episode: 400 training return: tensor(-419.0662, device='cuda:0')
episode: 401 training return: tensor(-446.2041, device='cuda:0')
episode: 402 training return: tensor(-519.9585, device='cuda:0')
episode: 403 training return: tensor(-507.9226, device='cuda:0')
epoch: 101 test_true_pfm: 2986.850762056274 sim_pfm: 67.98506455559982
episode: 404 training return: tensor(-340.0783, device='cuda:0')
episode: 405 training return: tensor(-456.7182, device='cuda:0')
episode: 406 training return: tensor(-266.8502, device='cuda:0')
episode: 407 training return: tensor(-389.1158, device='cuda:0')
epoch: 102 test_true_pfm: 2335.656846777607 sim_pfm: -68.03598834451986
episode: 408 training return: tensor(-69.1514, device='cuda:0')
episode: 409 training return: tensor(-340.7238, device='cuda:0')
episode: 410 training return: tensor(-459.0914, device='cuda:0')
episode: 411 training return: tensor(-508.0866, device='cuda:0')
epoch: 103 test_true_pfm: 1753.1896288126316 sim_pfm: 160.90788730837326
episode: 412 training return: tensor(-309.4654, device='cuda:0')
episode: 413 training return: tensor(-346.9001, device='cuda:0')
episode: 414 training return: tensor(-92.5299, device='cuda:0')
episode: 415 training return: tensor(-433.7163, device='cuda:0')
epoch: 104 test_true_pfm: 2562.914022131717 sim_pfm: 282.99223571910017
episode: 416 training return: tensor(-333.5494, device='cuda:0')
episode: 417 training return: tensor(-448.5225, device='cuda:0')
episode: 418 training return: tensor(-458.4306, device='cuda:0')
episode: 419 training return: tensor(-432.8188, device='cuda:0')
epoch: 105 test_true_pfm: 3014.469380925542 sim_pfm: 68.51798309886362
episode: 420 training return: tensor(-375.0024, device='cuda:0')
episode: 421 training return: tensor(-538.9123, device='cuda:0')
episode: 422 training return: tensor(-468.7155, device='cuda:0')
episode: 423 training return: tensor(-462.2255, device='cuda:0')
epoch: 106 test_true_pfm: 2874.1675836588965 sim_pfm: -24.661726031685248
episode: 424 training return: tensor(-283.4706, device='cuda:0')
episode: 425 training return: tensor(-339.2197, device='cuda:0')
episode: 426 training return: tensor(-513.8541, device='cuda:0')
episode: 427 training return: tensor(-9.5462, device='cuda:0')
epoch: 107 test_true_pfm: 2869.492758207938 sim_pfm: 103.15737818018533
episode: 428 training return: tensor(-422.3370, device='cuda:0')
episode: 429 training return: tensor(-56.9214, device='cuda:0')
episode: 430 training return: tensor(-432.5415, device='cuda:0')
episode: 431 training return: tensor(-458.8594, device='cuda:0')
epoch: 108 test_true_pfm: 1509.7815870724353 sim_pfm: -300.37152474254253
episode: 432 training return: tensor(-203.1689, device='cuda:0')
episode: 433 training return: tensor(-443.6850, device='cuda:0')
episode: 434 training return: tensor(-459.4453, device='cuda:0')
episode: 435 training return: tensor(178.8775, device='cuda:0')
epoch: 109 test_true_pfm: 2292.4903881263344 sim_pfm: 178.05604725199132
episode: 436 training return: tensor(-272.8144, device='cuda:0')
episode: 437 training return: tensor(-356.2362, device='cuda:0')
episode: 438 training return: tensor(-187.6541, device='cuda:0')
episode: 439 training return: tensor(223.7859, device='cuda:0')
epoch: 110 test_true_pfm: 3046.1270796237254 sim_pfm: 140.27219364312865
episode: 440 training return: tensor(-431.4955, device='cuda:0')
episode: 441 training return: tensor(-427.5778, device='cuda:0')
episode: 442 training return: tensor(-507.9625, device='cuda:0')
episode: 443 training return: tensor(-446.4492, device='cuda:0')
epoch: 111 test_true_pfm: 2804.1721305491556 sim_pfm: 103.50179503097509
episode: 444 training return: tensor(-423.2649, device='cuda:0')
episode: 445 training return: tensor(-390.2702, device='cuda:0')
episode: 446 training return: tensor(-418.4889, device='cuda:0')
episode: 447 training return: tensor(75.6621, device='cuda:0')
epoch: 112 test_true_pfm: 2517.728960386547 sim_pfm: 258.9539350034708
episode: 448 training return: tensor(-215.5009, device='cuda:0')
episode: 449 training return: tensor(-445.0086, device='cuda:0')
episode: 450 training return: tensor(-437.2916, device='cuda:0')
episode: 451 training return: tensor(-248.6643, device='cuda:0')
epoch: 113 test_true_pfm: 2914.57162910159 sim_pfm: 75.02671324560652
episode: 452 training return: tensor(-255.9915, device='cuda:0')
episode: 453 training return: tensor(-423.4012, device='cuda:0')
episode: 454 training return: tensor(-467.4799, device='cuda:0')
episode: 455 training return: tensor(-495.4298, device='cuda:0')
epoch: 114 test_true_pfm: 2913.139595390401 sim_pfm: 276.9345823237575
episode: 456 training return: tensor(-198.5980, device='cuda:0')
episode: 457 training return: tensor(-448.9723, device='cuda:0')
episode: 458 training return: tensor(-247.3670, device='cuda:0')
episode: 459 training return: tensor(-500.5742, device='cuda:0')
epoch: 115 test_true_pfm: 2910.607079572341 sim_pfm: 278.5363428105775
episode: 460 training return: tensor(-418.6299, device='cuda:0')
episode: 461 training return: tensor(-453.3355, device='cuda:0')
episode: 462 training return: tensor(-386.0791, device='cuda:0')
episode: 463 training return: tensor(-360.6466, device='cuda:0')
epoch: 116 test_true_pfm: 2592.9342456484696 sim_pfm: 160.6220957543895
episode: 464 training return: tensor(-89.5087, device='cuda:0')
episode: 465 training return: tensor(-342.1346, device='cuda:0')
episode: 466 training return: tensor(-466.2796, device='cuda:0')
episode: 467 training return: tensor(-438.5013, device='cuda:0')
epoch: 117 test_true_pfm: 3127.382662407932 sim_pfm: -120.65120816681883
episode: 468 training return: tensor(-284.1698, device='cuda:0')
episode: 469 training return: tensor(-353.1879, device='cuda:0')
episode: 470 training return: tensor(-522.0801, device='cuda:0')
episode: 471 training return: tensor(44.8162, device='cuda:0')
epoch: 118 test_true_pfm: 3305.985676392918 sim_pfm: 220.4378662992191
episode: 472 training return: tensor(-462.4151, device='cuda:0')
episode: 473 training return: tensor(-356.3005, device='cuda:0')
episode: 474 training return: tensor(-473.8061, device='cuda:0')
episode: 475 training return: tensor(-177.1597, device='cuda:0')
epoch: 119 test_true_pfm: 3305.6822218761336 sim_pfm: 208.74289775051875
episode: 476 training return: tensor(-262.0045, device='cuda:0')
episode: 477 training return: tensor(-437.5207, device='cuda:0')
episode: 478 training return: tensor(-458.1406, device='cuda:0')
episode: 479 training return: tensor(-253.0894, device='cuda:0')
epoch: 120 test_true_pfm: 2927.742379175428 sim_pfm: 172.97957654006314
episode: 480 training return: tensor(-424.4974, device='cuda:0')
episode: 481 training return: tensor(-456.2091, device='cuda:0')
episode: 482 training return: tensor(-513.0165, device='cuda:0')
episode: 483 training return: tensor(-197.2745, device='cuda:0')
epoch: 121 test_true_pfm: 3057.457673064677 sim_pfm: 282.58342496621964
episode: 484 training return: tensor(22.6097, device='cuda:0')
episode: 485 training return: tensor(-198.5043, device='cuda:0')
episode: 486 training return: tensor(-482.8385, device='cuda:0')
episode: 487 training return: tensor(-344.2194, device='cuda:0')
epoch: 122 test_true_pfm: 2850.1430455352106 sim_pfm: 253.65383806888713
episode: 488 training return: tensor(-350.7002, device='cuda:0')
episode: 489 training return: tensor(-172.3530, device='cuda:0')
episode: 490 training return: tensor(-348.1821, device='cuda:0')
episode: 491 training return: tensor(-387.9685, device='cuda:0')
epoch: 123 test_true_pfm: 3318.038424092642 sim_pfm: 286.6199703186576
episode: 492 training return: tensor(-178.8722, device='cuda:0')
episode: 493 training return: tensor(228.5690, device='cuda:0')
episode: 494 training return: tensor(-345.3264, device='cuda:0')
episode: 495 training return: tensor(-262.2080, device='cuda:0')
epoch: 124 test_true_pfm: 3299.2277135931295 sim_pfm: 260.68439864585525
episode: 496 training return: tensor(-429.9126, device='cuda:0')
episode: 497 training return: tensor(-364.6808, device='cuda:0')
episode: 498 training return: tensor(281.8633, device='cuda:0')
episode: 499 training return: tensor(-459.9868, device='cuda:0')
epoch: 125 test_true_pfm: 3314.607234086936 sim_pfm: 268.18248976468266
episode: 500 training return: tensor(-385.2722, device='cuda:0')
episode: 501 training return: tensor(-432.8848, device='cuda:0')
episode: 502 training return: tensor(-450.8367, device='cuda:0')
episode: 503 training return: tensor(-277.4366, device='cuda:0')
epoch: 126 test_true_pfm: 3302.0527037358333 sim_pfm: 244.53044253135644
episode: 504 training return: tensor(-461.3660, device='cuda:0')
episode: 505 training return: tensor(83.6642, device='cuda:0')
episode: 506 training return: tensor(-469.9091, device='cuda:0')
episode: 507 training return: tensor(-490.1694, device='cuda:0')
epoch: 127 test_true_pfm: 3089.1017505184595 sim_pfm: -80.44432619741808
episode: 508 training return: tensor(-436.8145, device='cuda:0')
episode: 509 training return: tensor(-525.0944, device='cuda:0')
episode: 510 training return: tensor(-249.6208, device='cuda:0')
episode: 511 training return: tensor(-271.6704, device='cuda:0')
epoch: 128 test_true_pfm: 2346.0673950857736 sim_pfm: 277.3040090085221
episode: 512 training return: tensor(-389.1427, device='cuda:0')
episode: 513 training return: tensor(-293.4257, device='cuda:0')
episode: 514 training return: tensor(-253.3677, device='cuda:0')
episode: 515 training return: tensor(-237.2661, device='cuda:0')
epoch: 129 test_true_pfm: 3304.544100328492 sim_pfm: 259.9323743012598
episode: 516 training return: tensor(-419.2700, device='cuda:0')
episode: 517 training return: tensor(-436.8559, device='cuda:0')
episode: 518 training return: tensor(-285.0340, device='cuda:0')
episode: 519 training return: tensor(-342.9375, device='cuda:0')
epoch: 130 test_true_pfm: 3263.772268522389 sim_pfm: 260.18828225587885
episode: 520 training return: tensor(-11.0330, device='cuda:0')
episode: 521 training return: tensor(-504.1347, device='cuda:0')
episode: 522 training return: tensor(-32.6107, device='cuda:0')
episode: 523 training return: tensor(-335.4406, device='cuda:0')
epoch: 131 test_true_pfm: 2653.285111851128 sim_pfm: -22.86352857731011
episode: 524 training return: tensor(-211.5265, device='cuda:0')
episode: 525 training return: tensor(-347.3334, device='cuda:0')
episode: 526 training return: tensor(-437.1603, device='cuda:0')
episode: 527 training return: tensor(-28.2836, device='cuda:0')
epoch: 132 test_true_pfm: 3316.8729302192255 sim_pfm: 257.000889073126
episode: 528 training return: tensor(-94.1092, device='cuda:0')
episode: 529 training return: tensor(276.8349, device='cuda:0')
episode: 530 training return: tensor(-468.9778, device='cuda:0')
episode: 531 training return: tensor(-317.9032, device='cuda:0')
epoch: 133 test_true_pfm: 2951.411273275689 sim_pfm: 220.50474625162315
episode: 532 training return: tensor(-333.8173, device='cuda:0')
episode: 533 training return: tensor(-426.6352, device='cuda:0')
episode: 534 training return: tensor(-339.9680, device='cuda:0')
episode: 535 training return: tensor(63.5918, device='cuda:0')
epoch: 134 test_true_pfm: 2211.899844882542 sim_pfm: 107.78694339539895
episode: 536 training return: tensor(-22.2318, device='cuda:0')
episode: 537 training return: tensor(-442.2542, device='cuda:0')
episode: 538 training return: tensor(-347.4765, device='cuda:0')
episode: 539 training return: tensor(-427.9512, device='cuda:0')
epoch: 135 test_true_pfm: 3297.8332216054673 sim_pfm: 255.95691656447403
episode: 540 training return: tensor(-278.9510, device='cuda:0')
episode: 541 training return: tensor(-443.1763, device='cuda:0')
episode: 542 training return: tensor(-292.2050, device='cuda:0')
episode: 543 training return: tensor(-179.1621, device='cuda:0')
epoch: 136 test_true_pfm: 3313.9036998774077 sim_pfm: 268.45587712400203
episode: 544 training return: tensor(-453.7202, device='cuda:0')
episode: 545 training return: tensor(-435.1693, device='cuda:0')
episode: 546 training return: tensor(-209.5092, device='cuda:0')
episode: 547 training return: tensor(-32.9906, device='cuda:0')
epoch: 137 test_true_pfm: 3298.9171317334963 sim_pfm: 263.05728348400834
episode: 548 training return: tensor(-211.5837, device='cuda:0')
episode: 549 training return: tensor(-91.6694, device='cuda:0')
episode: 550 training return: tensor(-454.7499, device='cuda:0')
episode: 551 training return: tensor(-433.4882, device='cuda:0')
epoch: 138 test_true_pfm: 3317.060918853613 sim_pfm: 282.3289679254619
episode: 552 training return: tensor(-341.6447, device='cuda:0')
episode: 553 training return: tensor(-325.9512, device='cuda:0')
episode: 554 training return: tensor(-447.5092, device='cuda:0')
episode: 555 training return: tensor(-352.0270, device='cuda:0')
epoch: 139 test_true_pfm: 3094.051147726767 sim_pfm: 270.1196636988316
episode: 556 training return: tensor(-347.6138, device='cuda:0')
episode: 557 training return: tensor(-450.6055, device='cuda:0')
episode: 558 training return: tensor(-434.9356, device='cuda:0')
episode: 559 training return: tensor(-87.3994, device='cuda:0')
epoch: 140 test_true_pfm: 3005.986147376568 sim_pfm: 258.1668335959548
episode: 560 training return: tensor(-337.7210, device='cuda:0')
episode: 561 training return: tensor(-449.0788, device='cuda:0')
episode: 562 training return: tensor(-258.6974, device='cuda:0')
episode: 563 training return: tensor(-272.8457, device='cuda:0')
epoch: 141 test_true_pfm: 2840.1256392473115 sim_pfm: 168.31689972938815
episode: 564 training return: tensor(-453.1757, device='cuda:0')
episode: 565 training return: tensor(91.7285, device='cuda:0')
episode: 566 training return: tensor(315.7409, device='cuda:0')
episode: 567 training return: tensor(240.4008, device='cuda:0')
epoch: 142 test_true_pfm: 3315.5890914473566 sim_pfm: 264.8911985784459
episode: 568 training return: tensor(201.4655, device='cuda:0')
episode: 569 training return: tensor(-392.9910, device='cuda:0')
episode: 570 training return: tensor(-404.6467, device='cuda:0')
episode: 571 training return: tensor(-341.1287, device='cuda:0')
epoch: 143 test_true_pfm: 3266.4596184235374 sim_pfm: 267.1311809923888
episode: 572 training return: tensor(-345.5975, device='cuda:0')
episode: 573 training return: tensor(-355.9642, device='cuda:0')
episode: 574 training return: tensor(-452.3487, device='cuda:0')
episode: 575 training return: tensor(-354.6389, device='cuda:0')
epoch: 144 test_true_pfm: 2598.527315555073 sim_pfm: 87.69013886332202
episode: 576 training return: tensor(-458.2276, device='cuda:0')
episode: 577 training return: tensor(-434.3569, device='cuda:0')
episode: 578 training return: tensor(-347.9283, device='cuda:0')
episode: 579 training return: tensor(-158.1871, device='cuda:0')
epoch: 145 test_true_pfm: 3317.1345578684763 sim_pfm: 200.0624750710946
episode: 580 training return: tensor(-439.7665, device='cuda:0')
episode: 581 training return: tensor(-454.6367, device='cuda:0')
episode: 582 training return: tensor(-458.6410, device='cuda:0')
episode: 583 training return: tensor(-295.3512, device='cuda:0')
epoch: 146 test_true_pfm: 3102.880915010022 sim_pfm: 262.8443165285959
episode: 584 training return: tensor(-436.0388, device='cuda:0')
episode: 585 training return: tensor(-429.8681, device='cuda:0')
episode: 586 training return: tensor(-451.7424, device='cuda:0')
episode: 587 training return: tensor(-341.0644, device='cuda:0')
epoch: 147 test_true_pfm: 2968.8435120766153 sim_pfm: 197.12786175999403
episode: 588 training return: tensor(-336.4753, device='cuda:0')
episode: 589 training return: tensor(-302.0422, device='cuda:0')
episode: 590 training return: tensor(-407.3585, device='cuda:0')
episode: 591 training return: tensor(-424.2874, device='cuda:0')
epoch: 148 test_true_pfm: 3106.9708210235403 sim_pfm: 77.74032825798106
episode: 592 training return: tensor(-76.5232, device='cuda:0')
episode: 593 training return: tensor(55.8928, device='cuda:0')
episode: 594 training return: tensor(-509.3655, device='cuda:0')
episode: 595 training return: tensor(-422.5507, device='cuda:0')
epoch: 149 test_true_pfm: 3317.895815068812 sim_pfm: 34.53238227575397
episode: 596 training return: tensor(-230.2490, device='cuda:0')
episode: 597 training return: tensor(-138.3911, device='cuda:0')
episode: 598 training return: tensor(-423.4500, device='cuda:0')
episode: 599 training return: tensor(-449.0835, device='cuda:0')
epoch: 150 test_true_pfm: 3305.1890420291725 sim_pfm: 264.32572678269935
