['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '1', '--data', '100000', '--regu', '0.3']
2697.6309199457937
episode: 0 training return: tensor(-329.8670, device='cuda:0')
episode: 1 training return: tensor(-370.4860, device='cuda:0')
episode: 2 training return: tensor(227.4625, device='cuda:0')
episode: 3 training return: tensor(71.4962, device='cuda:0')
epoch: 1 test_true_pfm: 2866.1203064647866 sim_pfm: 251.16251025218904
episode: 4 training return: tensor(-279.9846, device='cuda:0')
episode: 5 training return: tensor(-364.7389, device='cuda:0')
episode: 6 training return: tensor(-194.4064, device='cuda:0')
episode: 7 training return: tensor(-362.0544, device='cuda:0')
epoch: 2 test_true_pfm: 1814.9240316796233 sim_pfm: -105.99146809132071
episode: 8 training return: tensor(-384.8565, device='cuda:0')
episode: 9 training return: tensor(-349.1595, device='cuda:0')
episode: 10 training return: tensor(-331.9110, device='cuda:0')
episode: 11 training return: tensor(-191.1143, device='cuda:0')
epoch: 3 test_true_pfm: 1700.1598739162418 sim_pfm: -336.1463143170113
episode: 12 training return: tensor(-422.2079, device='cuda:0')
episode: 13 training return: tensor(-441.2212, device='cuda:0')
episode: 14 training return: tensor(-275.0989, device='cuda:0')
episode: 15 training return: tensor(-443.4000, device='cuda:0')
epoch: 4 test_true_pfm: 1116.065130485427 sim_pfm: -471.52896696690004
episode: 16 training return: tensor(-347.0604, device='cuda:0')
episode: 17 training return: tensor(-284.9911, device='cuda:0')
episode: 18 training return: tensor(-511.9279, device='cuda:0')
episode: 19 training return: tensor(90.5801, device='cuda:0')
epoch: 5 test_true_pfm: 1178.8766504852447 sim_pfm: -439.3371243296424
episode: 20 training return: tensor(-456.8260, device='cuda:0')
episode: 21 training return: tensor(-424.2970, device='cuda:0')
episode: 22 training return: tensor(-248.9177, device='cuda:0')
episode: 23 training return: tensor(-393.7455, device='cuda:0')
epoch: 6 test_true_pfm: 1541.0317965596362 sim_pfm: -363.2311525130256
episode: 24 training return: tensor(-455.4700, device='cuda:0')
episode: 25 training return: tensor(-286.2256, device='cuda:0')
episode: 26 training return: tensor(-462.5453, device='cuda:0')
episode: 27 training return: tensor(-363.0863, device='cuda:0')
epoch: 7 test_true_pfm: 1259.4470435489131 sim_pfm: -419.1852695413788
episode: 28 training return: tensor(-532.3546, device='cuda:0')
episode: 29 training return: tensor(-268.1160, device='cuda:0')
episode: 30 training return: tensor(-465.9217, device='cuda:0')
episode: 31 training return: tensor(-286.9770, device='cuda:0')
epoch: 8 test_true_pfm: 1494.6419146645546 sim_pfm: -361.0428015680906
episode: 32 training return: tensor(-373.6555, device='cuda:0')
episode: 33 training return: tensor(196.2548, device='cuda:0')
episode: 34 training return: tensor(-394.4790, device='cuda:0')
episode: 35 training return: tensor(-217.9935, device='cuda:0')
epoch: 9 test_true_pfm: 1276.821098231688 sim_pfm: -435.276191075284
episode: 36 training return: tensor(-175.0454, device='cuda:0')
episode: 37 training return: tensor(-371.6702, device='cuda:0')
episode: 38 training return: tensor(-473.7152, device='cuda:0')
episode: 39 training return: tensor(-458.4126, device='cuda:0')
epoch: 10 test_true_pfm: 1263.696207809174 sim_pfm: -423.28325069635565
episode: 40 training return: tensor(-320.8055, device='cuda:0')
episode: 41 training return: tensor(-442.3939, device='cuda:0')
episode: 42 training return: tensor(-448.9650, device='cuda:0')
episode: 43 training return: tensor(-191.2228, device='cuda:0')
epoch: 11 test_true_pfm: 1375.2380124949716 sim_pfm: -381.2114241249025
episode: 44 training return: tensor(-334.3161, device='cuda:0')
episode: 45 training return: tensor(-343.4212, device='cuda:0')
episode: 46 training return: tensor(-501.1917, device='cuda:0')
episode: 47 training return: tensor(-452.4427, device='cuda:0')
epoch: 12 test_true_pfm: 2121.708144331456 sim_pfm: -26.484808184749756
episode: 48 training return: tensor(-311.2386, device='cuda:0')
episode: 49 training return: tensor(-421.2069, device='cuda:0')
episode: 50 training return: tensor(-406.9791, device='cuda:0')
episode: 51 training return: tensor(80.3273, device='cuda:0')
epoch: 13 test_true_pfm: 2297.0509524562 sim_pfm: -7.579899248162595
episode: 52 training return: tensor(-317.1510, device='cuda:0')
episode: 53 training return: tensor(-253.4537, device='cuda:0')
episode: 54 training return: tensor(-423.8338, device='cuda:0')
episode: 55 training return: tensor(-140.2959, device='cuda:0')
epoch: 14 test_true_pfm: 2111.7423574207983 sim_pfm: -207.85910431478018
episode: 56 training return: tensor(-338.5803, device='cuda:0')
episode: 57 training return: tensor(-403.7778, device='cuda:0')
episode: 58 training return: tensor(-152.5423, device='cuda:0')
episode: 59 training return: tensor(-416.5544, device='cuda:0')
epoch: 15 test_true_pfm: 2345.2575865465406 sim_pfm: -74.33967970391193
episode: 60 training return: tensor(-246.0917, device='cuda:0')
episode: 61 training return: tensor(-451.1673, device='cuda:0')
episode: 62 training return: tensor(-466.3892, device='cuda:0')
episode: 63 training return: tensor(-285.4236, device='cuda:0')
epoch: 16 test_true_pfm: 2158.688891462398 sim_pfm: -305.8755045893292
episode: 64 training return: tensor(-484.1962, device='cuda:0')
episode: 65 training return: tensor(90.6731, device='cuda:0')
episode: 66 training return: tensor(-407.8072, device='cuda:0')
episode: 67 training return: tensor(-373.8157, device='cuda:0')
epoch: 17 test_true_pfm: 1912.165790169039 sim_pfm: -67.00091084480907
episode: 68 training return: tensor(-487.4345, device='cuda:0')
episode: 69 training return: tensor(-408.2097, device='cuda:0')
episode: 70 training return: tensor(-385.4670, device='cuda:0')
episode: 71 training return: tensor(-400.2977, device='cuda:0')
epoch: 18 test_true_pfm: 1854.0868550243333 sim_pfm: -399.8203550252947
episode: 72 training return: tensor(-275.0868, device='cuda:0')
episode: 73 training return: tensor(-224.4072, device='cuda:0')
episode: 74 training return: tensor(-426.8891, device='cuda:0')
episode: 75 training return: tensor(-151.3675, device='cuda:0')
epoch: 19 test_true_pfm: 1873.7459901332124 sim_pfm: -69.21284745439577
episode: 76 training return: tensor(-356.6725, device='cuda:0')
episode: 77 training return: tensor(-358.7294, device='cuda:0')
episode: 78 training return: tensor(-316.0739, device='cuda:0')
episode: 79 training return: tensor(-396.1483, device='cuda:0')
epoch: 20 test_true_pfm: 2367.5868340710813 sim_pfm: -164.13867164436184
episode: 80 training return: tensor(-322.5721, device='cuda:0')
episode: 81 training return: tensor(-337.9747, device='cuda:0')
episode: 82 training return: tensor(-296.6738, device='cuda:0')
episode: 83 training return: tensor(-110.6390, device='cuda:0')
epoch: 21 test_true_pfm: 1562.561209163231 sim_pfm: -150.5395293114707
episode: 84 training return: tensor(-376.3681, device='cuda:0')
episode: 85 training return: tensor(-395.8881, device='cuda:0')
episode: 86 training return: tensor(-464.6727, device='cuda:0')
episode: 87 training return: tensor(-5.7666, device='cuda:0')
epoch: 22 test_true_pfm: 2150.6823651893887 sim_pfm: -98.93662230104867
episode: 88 training return: tensor(-410.6724, device='cuda:0')
episode: 89 training return: tensor(-232.0461, device='cuda:0')
episode: 90 training return: tensor(-137.5711, device='cuda:0')
episode: 91 training return: tensor(-308.3802, device='cuda:0')
epoch: 23 test_true_pfm: 2457.3430114092585 sim_pfm: -45.77488463957949
episode: 92 training return: tensor(-430.5881, device='cuda:0')
episode: 93 training return: tensor(106.0244, device='cuda:0')
episode: 94 training return: tensor(-26.7522, device='cuda:0')
episode: 95 training return: tensor(51.5539, device='cuda:0')
epoch: 24 test_true_pfm: 1758.658807410338 sim_pfm: -297.6980159704205
episode: 96 training return: tensor(-309.2002, device='cuda:0')
episode: 97 training return: tensor(-312.9239, device='cuda:0')
episode: 98 training return: tensor(-214.9816, device='cuda:0')
episode: 99 training return: tensor(-77.4899, device='cuda:0')
epoch: 25 test_true_pfm: 2537.8004331221955 sim_pfm: 76.02635590833961
episode: 100 training return: tensor(-309.0631, device='cuda:0')
episode: 101 training return: tensor(-385.1162, device='cuda:0')
episode: 102 training return: tensor(-386.3607, device='cuda:0')
episode: 103 training return: tensor(70.0733, device='cuda:0')
epoch: 26 test_true_pfm: 2247.222703508928 sim_pfm: 37.43043620553605
episode: 104 training return: tensor(-343.0810, device='cuda:0')
episode: 105 training return: tensor(-129.6003, device='cuda:0')
episode: 106 training return: tensor(-405.9450, device='cuda:0')
episode: 107 training return: tensor(-391.1794, device='cuda:0')
epoch: 27 test_true_pfm: 2794.690574270239 sim_pfm: 6.522295470019647
episode: 108 training return: tensor(-411.5505, device='cuda:0')
episode: 109 training return: tensor(-153.0456, device='cuda:0')
episode: 110 training return: tensor(-420.2050, device='cuda:0')
episode: 111 training return: tensor(-300.1582, device='cuda:0')
epoch: 28 test_true_pfm: 1675.135650275479 sim_pfm: -292.19588961661793
episode: 112 training return: tensor(-408.3459, device='cuda:0')
episode: 113 training return: tensor(-254.5638, device='cuda:0')
episode: 114 training return: tensor(277.6365, device='cuda:0')
episode: 115 training return: tensor(-402.1817, device='cuda:0')
epoch: 29 test_true_pfm: 2601.0395937710364 sim_pfm: -289.85886519703007
episode: 116 training return: tensor(-133.1766, device='cuda:0')
episode: 117 training return: tensor(-214.3699, device='cuda:0')
episode: 118 training return: tensor(-417.8138, device='cuda:0')
episode: 119 training return: tensor(-320.2866, device='cuda:0')
epoch: 30 test_true_pfm: 2761.006954228657 sim_pfm: -84.24904825247359
episode: 120 training return: tensor(-357.8052, device='cuda:0')
episode: 121 training return: tensor(94.2474, device='cuda:0')
episode: 122 training return: tensor(-397.0246, device='cuda:0')
episode: 123 training return: tensor(-224.3810, device='cuda:0')
epoch: 31 test_true_pfm: 1699.313919163875 sim_pfm: -275.57204622460995
episode: 124 training return: tensor(-349.3182, device='cuda:0')
episode: 125 training return: tensor(-313.5589, device='cuda:0')
episode: 126 training return: tensor(-216.8710, device='cuda:0')
episode: 127 training return: tensor(24.5874, device='cuda:0')
epoch: 32 test_true_pfm: 2184.9114332782806 sim_pfm: -55.7579955329032
episode: 128 training return: tensor(-223.1279, device='cuda:0')
episode: 129 training return: tensor(-199.8646, device='cuda:0')
episode: 130 training return: tensor(-213.9980, device='cuda:0')
episode: 131 training return: tensor(-1.6956, device='cuda:0')
epoch: 33 test_true_pfm: 1983.042324619765 sim_pfm: 21.85600886233927
episode: 132 training return: tensor(-412.7560, device='cuda:0')
episode: 133 training return: tensor(-326.7881, device='cuda:0')
episode: 134 training return: tensor(-376.8872, device='cuda:0')
episode: 135 training return: tensor(-412.1887, device='cuda:0')
epoch: 34 test_true_pfm: 2196.8128622279164 sim_pfm: -131.4268560471052
episode: 136 training return: tensor(-321.0852, device='cuda:0')
episode: 137 training return: tensor(-270.0278, device='cuda:0')
episode: 138 training return: tensor(-158.9362, device='cuda:0')
episode: 139 training return: tensor(-307.0704, device='cuda:0')
epoch: 35 test_true_pfm: 3231.3598398472604 sim_pfm: -35.32261260342784
episode: 140 training return: tensor(-336.9460, device='cuda:0')
episode: 141 training return: tensor(230.2545, device='cuda:0')
episode: 142 training return: tensor(-181.4793, device='cuda:0')
episode: 143 training return: tensor(-284.0040, device='cuda:0')
epoch: 36 test_true_pfm: 2652.8170612911395 sim_pfm: -122.69174735129734
episode: 144 training return: tensor(-121.9465, device='cuda:0')
episode: 145 training return: tensor(-389.8216, device='cuda:0')
episode: 146 training return: tensor(-227.9037, device='cuda:0')
episode: 147 training return: tensor(-401.1064, device='cuda:0')
epoch: 37 test_true_pfm: 2806.2339529609744 sim_pfm: -127.49604579878117
episode: 148 training return: tensor(-269.9292, device='cuda:0')
episode: 149 training return: tensor(-227.2928, device='cuda:0')
episode: 150 training return: tensor(-163.5302, device='cuda:0')
episode: 151 training return: tensor(-333.3201, device='cuda:0')
epoch: 38 test_true_pfm: 1737.6623690675685 sim_pfm: -87.11902224928296
episode: 152 training return: tensor(-88.7324, device='cuda:0')
episode: 153 training return: tensor(-390.7032, device='cuda:0')
episode: 154 training return: tensor(-211.3835, device='cuda:0')
episode: 155 training return: tensor(24.0373, device='cuda:0')
epoch: 39 test_true_pfm: 2476.25621827561 sim_pfm: 21.51976909672764
episode: 156 training return: tensor(276.3851, device='cuda:0')
episode: 157 training return: tensor(-80.2526, device='cuda:0')
episode: 158 training return: tensor(-314.7925, device='cuda:0')
episode: 159 training return: tensor(-210.7048, device='cuda:0')
epoch: 40 test_true_pfm: 1616.9120492290076 sim_pfm: -92.4777108670775
episode: 160 training return: tensor(-208.4184, device='cuda:0')
episode: 161 training return: tensor(86.2146, device='cuda:0')
episode: 162 training return: tensor(-134.2800, device='cuda:0')
episode: 163 training return: tensor(-439.7429, device='cuda:0')
epoch: 41 test_true_pfm: 2828.090671683436 sim_pfm: 50.865422340711426
episode: 164 training return: tensor(-221.7198, device='cuda:0')
episode: 165 training return: tensor(-246.6678, device='cuda:0')
episode: 166 training return: tensor(-93.1925, device='cuda:0')
episode: 167 training return: tensor(4.2631, device='cuda:0')
epoch: 42 test_true_pfm: 3251.6802329730413 sim_pfm: 280.2828589164225
episode: 168 training return: tensor(-271.1925, device='cuda:0')
episode: 169 training return: tensor(-150.0626, device='cuda:0')
episode: 170 training return: tensor(225.6270, device='cuda:0')
episode: 171 training return: tensor(-223.3840, device='cuda:0')
epoch: 43 test_true_pfm: 2620.2782153641856 sim_pfm: 222.72082685979936
episode: 172 training return: tensor(-174.6852, device='cuda:0')
episode: 173 training return: tensor(-349.6757, device='cuda:0')
episode: 174 training return: tensor(-463.4419, device='cuda:0')
episode: 175 training return: tensor(53.7965, device='cuda:0')
epoch: 44 test_true_pfm: 1882.500667098692 sim_pfm: -18.668377651638973
episode: 176 training return: tensor(-282.2370, device='cuda:0')
episode: 177 training return: tensor(-156.5133, device='cuda:0')
episode: 178 training return: tensor(-420.0346, device='cuda:0')
episode: 179 training return: tensor(206.3297, device='cuda:0')
epoch: 45 test_true_pfm: 2792.505641701369 sim_pfm: 25.00374085174796
episode: 180 training return: tensor(-374.1838, device='cuda:0')
episode: 181 training return: tensor(-442.2073, device='cuda:0')
episode: 182 training return: tensor(174.9878, device='cuda:0')
episode: 183 training return: tensor(-348.2861, device='cuda:0')
epoch: 46 test_true_pfm: 3051.6918900684627 sim_pfm: 201.92148633199395
episode: 184 training return: tensor(-84.5835, device='cuda:0')
episode: 185 training return: tensor(-437.8054, device='cuda:0')
episode: 186 training return: tensor(-290.4525, device='cuda:0')
episode: 187 training return: tensor(-81.4796, device='cuda:0')
epoch: 47 test_true_pfm: 2800.788425938334 sim_pfm: 145.66403817685205
episode: 188 training return: tensor(-82.8841, device='cuda:0')
episode: 189 training return: tensor(-327.5120, device='cuda:0')
episode: 190 training return: tensor(-419.4923, device='cuda:0')
episode: 191 training return: tensor(-345.5969, device='cuda:0')
epoch: 48 test_true_pfm: 2289.8567743964213 sim_pfm: 182.99172659214432
episode: 192 training return: tensor(-204.8963, device='cuda:0')
episode: 193 training return: tensor(-275.3263, device='cuda:0')
episode: 194 training return: tensor(262.6194, device='cuda:0')
episode: 195 training return: tensor(-153.1181, device='cuda:0')
epoch: 49 test_true_pfm: 2349.265986716429 sim_pfm: -78.17540853634516
episode: 196 training return: tensor(-189.1197, device='cuda:0')
episode: 197 training return: tensor(-71.0694, device='cuda:0')
episode: 198 training return: tensor(-338.0117, device='cuda:0')
episode: 199 training return: tensor(-62.8554, device='cuda:0')
epoch: 50 test_true_pfm: 2822.627515686258 sim_pfm: 168.45432089509754
episode: 200 training return: tensor(-303.5522, device='cuda:0')
episode: 201 training return: tensor(-226.3520, device='cuda:0')
episode: 202 training return: tensor(-160.9443, device='cuda:0')
episode: 203 training return: tensor(-170.6299, device='cuda:0')
epoch: 51 test_true_pfm: 1672.515068359496 sim_pfm: -302.4007528958027
episode: 204 training return: tensor(-92.5697, device='cuda:0')
episode: 205 training return: tensor(-248.0363, device='cuda:0')
episode: 206 training return: tensor(-399.0829, device='cuda:0')
episode: 207 training return: tensor(76.8444, device='cuda:0')
epoch: 52 test_true_pfm: 2890.1339424734565 sim_pfm: 161.65908020434048
episode: 208 training return: tensor(257.5764, device='cuda:0')
episode: 209 training return: tensor(-103.0556, device='cuda:0')
episode: 210 training return: tensor(-12.5401, device='cuda:0')
episode: 211 training return: tensor(-30.6712, device='cuda:0')
epoch: 53 test_true_pfm: 2936.1642435875124 sim_pfm: 289.7645503601719
episode: 212 training return: tensor(-511.8506, device='cuda:0')
episode: 213 training return: tensor(-133.4059, device='cuda:0')
episode: 214 training return: tensor(-247.7449, device='cuda:0')
episode: 215 training return: tensor(226.6648, device='cuda:0')
epoch: 54 test_true_pfm: 3162.458486544831 sim_pfm: 279.1226949149859
episode: 216 training return: tensor(-416.3417, device='cuda:0')
episode: 217 training return: tensor(-219.6989, device='cuda:0')
episode: 218 training return: tensor(-436.1486, device='cuda:0')
episode: 219 training return: tensor(-16.9923, device='cuda:0')
epoch: 55 test_true_pfm: 2496.815393415183 sim_pfm: 11.262670690193772
episode: 220 training return: tensor(-381.0587, device='cuda:0')
episode: 221 training return: tensor(-400.4677, device='cuda:0')
episode: 222 training return: tensor(-152.2605, device='cuda:0')
episode: 223 training return: tensor(-202.7343, device='cuda:0')
epoch: 56 test_true_pfm: 3273.423999231563 sim_pfm: 209.28167804939827
episode: 224 training return: tensor(-172.2539, device='cuda:0')
episode: 225 training return: tensor(-352.9026, device='cuda:0')
episode: 226 training return: tensor(-451.7619, device='cuda:0')
episode: 227 training return: tensor(-197.0474, device='cuda:0')
epoch: 57 test_true_pfm: 3289.8925545387815 sim_pfm: 166.93592770539303
episode: 228 training return: tensor(-434.9602, device='cuda:0')
episode: 229 training return: tensor(-421.1296, device='cuda:0')
episode: 230 training return: tensor(-491.4982, device='cuda:0')
episode: 231 training return: tensor(19.1970, device='cuda:0')
epoch: 58 test_true_pfm: 2977.936274254834 sim_pfm: 203.55752620549174
episode: 232 training return: tensor(117.6320, device='cuda:0')
episode: 233 training return: tensor(-284.2381, device='cuda:0')
episode: 234 training return: tensor(-361.1783, device='cuda:0')
episode: 235 training return: tensor(303.3306, device='cuda:0')
epoch: 59 test_true_pfm: 2901.541275313275 sim_pfm: 111.57168507574049
episode: 236 training return: tensor(-343.5532, device='cuda:0')
episode: 237 training return: tensor(-507.1985, device='cuda:0')
episode: 238 training return: tensor(-234.8746, device='cuda:0')
episode: 239 training return: tensor(-260.5620, device='cuda:0')
epoch: 60 test_true_pfm: 3299.5673183618833 sim_pfm: 287.20690402392455
episode: 240 training return: tensor(29.0397, device='cuda:0')
episode: 241 training return: tensor(-389.8741, device='cuda:0')
episode: 242 training return: tensor(-186.2433, device='cuda:0')
episode: 243 training return: tensor(-202.8454, device='cuda:0')
epoch: 61 test_true_pfm: 2303.3320205081486 sim_pfm: 91.11540667766046
episode: 244 training return: tensor(-329.1533, device='cuda:0')
episode: 245 training return: tensor(-450.5594, device='cuda:0')
episode: 246 training return: tensor(-269.4487, device='cuda:0')
episode: 247 training return: tensor(-445.4141, device='cuda:0')
epoch: 62 test_true_pfm: 2638.2869337188736 sim_pfm: 280.51783186515485
episode: 248 training return: tensor(-394.8477, device='cuda:0')
episode: 249 training return: tensor(-252.1389, device='cuda:0')
episode: 250 training return: tensor(-41.6036, device='cuda:0')
episode: 251 training return: tensor(-309.7109, device='cuda:0')
epoch: 63 test_true_pfm: 2850.102035167394 sim_pfm: -15.883180464773128
episode: 252 training return: tensor(-504.7050, device='cuda:0')
episode: 253 training return: tensor(-91.3056, device='cuda:0')
episode: 254 training return: tensor(-277.9328, device='cuda:0')
episode: 255 training return: tensor(-464.0062, device='cuda:0')
epoch: 64 test_true_pfm: 3295.772019439142 sim_pfm: 269.72708721151383
episode: 256 training return: tensor(-441.2319, device='cuda:0')
episode: 257 training return: tensor(-311.9493, device='cuda:0')
episode: 258 training return: tensor(-346.6184, device='cuda:0')
episode: 259 training return: tensor(-38.7798, device='cuda:0')
epoch: 65 test_true_pfm: 3314.675547623041 sim_pfm: 276.45993346578325
episode: 260 training return: tensor(-211.1140, device='cuda:0')
episode: 261 training return: tensor(-372.6252, device='cuda:0')
episode: 262 training return: tensor(-338.5450, device='cuda:0')
episode: 263 training return: tensor(-244.9067, device='cuda:0')
epoch: 66 test_true_pfm: 3321.25798823987 sim_pfm: 47.5575522617631
episode: 264 training return: tensor(26.2757, device='cuda:0')
episode: 265 training return: tensor(-224.2064, device='cuda:0')
episode: 266 training return: tensor(-85.3087, device='cuda:0')
episode: 267 training return: tensor(-456.2471, device='cuda:0')
epoch: 67 test_true_pfm: 2957.497426950898 sim_pfm: 291.16430553002283
episode: 268 training return: tensor(-206.9995, device='cuda:0')
episode: 269 training return: tensor(-272.8296, device='cuda:0')
episode: 270 training return: tensor(-478.6587, device='cuda:0')
episode: 271 training return: tensor(-149.4048, device='cuda:0')
epoch: 68 test_true_pfm: 3061.847785016922 sim_pfm: 281.4039278274674
episode: 272 training return: tensor(186.9591, device='cuda:0')
episode: 273 training return: tensor(-63.1061, device='cuda:0')
episode: 274 training return: tensor(-301.1844, device='cuda:0')
episode: 275 training return: tensor(-112.7686, device='cuda:0')
epoch: 69 test_true_pfm: 3167.535962339538 sim_pfm: 244.2331249739509
episode: 276 training return: tensor(-418.0770, device='cuda:0')
episode: 277 training return: tensor(-430.4061, device='cuda:0')
episode: 278 training return: tensor(-339.7790, device='cuda:0')
episode: 279 training return: tensor(-437.8584, device='cuda:0')
epoch: 70 test_true_pfm: 3129.4727358400246 sim_pfm: 195.07779794406574
episode: 280 training return: tensor(-208.0911, device='cuda:0')
episode: 281 training return: tensor(-375.0374, device='cuda:0')
episode: 282 training return: tensor(-341.4516, device='cuda:0')
episode: 283 training return: tensor(188.2634, device='cuda:0')
epoch: 71 test_true_pfm: 2724.088156488018 sim_pfm: 287.2726375248458
episode: 284 training return: tensor(-419.3911, device='cuda:0')
episode: 285 training return: tensor(103.5911, device='cuda:0')
episode: 286 training return: tensor(-416.8256, device='cuda:0')
episode: 287 training return: tensor(-499.7382, device='cuda:0')
epoch: 72 test_true_pfm: 3313.4206081951124 sim_pfm: 268.4900527735008
episode: 288 training return: tensor(-59.7928, device='cuda:0')
episode: 289 training return: tensor(-484.9658, device='cuda:0')
episode: 290 training return: tensor(-97.4613, device='cuda:0')
episode: 291 training return: tensor(-342.4396, device='cuda:0')
epoch: 73 test_true_pfm: 3118.543409090024 sim_pfm: 254.36206738170586
episode: 292 training return: tensor(-425.0627, device='cuda:0')
episode: 293 training return: tensor(-277.1358, device='cuda:0')
episode: 294 training return: tensor(-425.3807, device='cuda:0')
episode: 295 training return: tensor(-342.6918, device='cuda:0')
epoch: 74 test_true_pfm: 2933.3463219368264 sim_pfm: 262.3046437500355
episode: 296 training return: tensor(97.6174, device='cuda:0')
episode: 297 training return: tensor(-306.4936, device='cuda:0')
episode: 298 training return: tensor(-531.5773, device='cuda:0')
episode: 299 training return: tensor(-275.7487, device='cuda:0')
epoch: 75 test_true_pfm: 3136.1000125154765 sim_pfm: 283.25900730202557
episode: 300 training return: tensor(-450.8046, device='cuda:0')
episode: 301 training return: tensor(-241.7725, device='cuda:0')
episode: 302 training return: tensor(-432.0994, device='cuda:0')
episode: 303 training return: tensor(-259.1529, device='cuda:0')
epoch: 76 test_true_pfm: 3229.727279557373 sim_pfm: 273.4858196757268
episode: 304 training return: tensor(-380.8546, device='cuda:0')
episode: 305 training return: tensor(-138.1307, device='cuda:0')
episode: 306 training return: tensor(-532.9777, device='cuda:0')
episode: 307 training return: tensor(232.8058, device='cuda:0')
epoch: 77 test_true_pfm: 3247.7119196309 sim_pfm: 312.1646057088995
episode: 308 training return: tensor(-430.1027, device='cuda:0')
episode: 309 training return: tensor(-260.5678, device='cuda:0')
episode: 310 training return: tensor(-215.1617, device='cuda:0')
episode: 311 training return: tensor(-402.7654, device='cuda:0')
epoch: 78 test_true_pfm: 3309.20023746352 sim_pfm: 247.09865569203006
episode: 312 training return: tensor(-442.6150, device='cuda:0')
episode: 313 training return: tensor(-236.5459, device='cuda:0')
episode: 314 training return: tensor(-67.9214, device='cuda:0')
episode: 315 training return: tensor(272.3462, device='cuda:0')
epoch: 79 test_true_pfm: 3343.3036223025006 sim_pfm: 330.65085245746496
episode: 316 training return: tensor(-283.4536, device='cuda:0')
episode: 317 training return: tensor(-391.1105, device='cuda:0')
episode: 318 training return: tensor(-343.3779, device='cuda:0')
episode: 319 training return: tensor(-0.7514, device='cuda:0')
epoch: 80 test_true_pfm: 3344.5904114074124 sim_pfm: 303.99870046433836
episode: 320 training return: tensor(252.5854, device='cuda:0')
episode: 321 training return: tensor(-447.6039, device='cuda:0')
episode: 322 training return: tensor(-433.9307, device='cuda:0')
episode: 323 training return: tensor(-466.6048, device='cuda:0')
epoch: 81 test_true_pfm: 3325.478285686522 sim_pfm: 293.00843108362943
episode: 324 training return: tensor(-499.0413, device='cuda:0')
episode: 325 training return: tensor(-458.1831, device='cuda:0')
episode: 326 training return: tensor(-343.6282, device='cuda:0')
episode: 327 training return: tensor(-390.8667, device='cuda:0')
epoch: 82 test_true_pfm: 2648.24472301272 sim_pfm: -62.98357153967178
episode: 328 training return: tensor(-213.0673, device='cuda:0')
episode: 329 training return: tensor(-385.6871, device='cuda:0')
episode: 330 training return: tensor(-405.5281, device='cuda:0')
episode: 331 training return: tensor(-453.7359, device='cuda:0')
epoch: 83 test_true_pfm: 2976.803425330719 sim_pfm: 28.685721325629856
episode: 332 training return: tensor(-65.1215, device='cuda:0')
episode: 333 training return: tensor(-308.0449, device='cuda:0')
episode: 334 training return: tensor(-433.8558, device='cuda:0')
episode: 335 training return: tensor(-439.2865, device='cuda:0')
epoch: 84 test_true_pfm: 3325.5824323752618 sim_pfm: 290.3721136996949
episode: 336 training return: tensor(-334.3694, device='cuda:0')
episode: 337 training return: tensor(-301.1317, device='cuda:0')
episode: 338 training return: tensor(-412.2481, device='cuda:0')
episode: 339 training return: tensor(-255.1882, device='cuda:0')
epoch: 85 test_true_pfm: 3293.996997603402 sim_pfm: 166.9801986432673
episode: 340 training return: tensor(-441.6811, device='cuda:0')
episode: 341 training return: tensor(-332.1554, device='cuda:0')
episode: 342 training return: tensor(-433.5991, device='cuda:0')
episode: 343 training return: tensor(-88.5107, device='cuda:0')
epoch: 86 test_true_pfm: 2911.2742132841654 sim_pfm: 147.01524597381163
episode: 344 training return: tensor(-270.3298, device='cuda:0')
episode: 345 training return: tensor(148.2589, device='cuda:0')
episode: 346 training return: tensor(-122.7998, device='cuda:0')
episode: 347 training return: tensor(-61.3193, device='cuda:0')
epoch: 87 test_true_pfm: 2906.1283546281466 sim_pfm: 48.342670499327745
episode: 348 training return: tensor(-244.7665, device='cuda:0')
episode: 349 training return: tensor(-271.2146, device='cuda:0')
episode: 350 training return: tensor(324.7271, device='cuda:0')
episode: 351 training return: tensor(-429.0585, device='cuda:0')
epoch: 88 test_true_pfm: 3073.336933305383 sim_pfm: 297.05924156628316
episode: 352 training return: tensor(-215.2747, device='cuda:0')
episode: 353 training return: tensor(-380.8747, device='cuda:0')
episode: 354 training return: tensor(-462.4883, device='cuda:0')
episode: 355 training return: tensor(-84.1571, device='cuda:0')
epoch: 89 test_true_pfm: 2936.643468037522 sim_pfm: 300.69322945404565
episode: 356 training return: tensor(301.2094, device='cuda:0')
episode: 357 training return: tensor(-237.1855, device='cuda:0')
episode: 358 training return: tensor(-340.7066, device='cuda:0')
episode: 359 training return: tensor(-390.0910, device='cuda:0')
epoch: 90 test_true_pfm: 3135.7697685393264 sim_pfm: 155.18311736701676
episode: 360 training return: tensor(-425.9243, device='cuda:0')
episode: 361 training return: tensor(-459.7637, device='cuda:0')
episode: 362 training return: tensor(-340.2400, device='cuda:0')
episode: 363 training return: tensor(49.4556, device='cuda:0')
epoch: 91 test_true_pfm: 3327.2291168777506 sim_pfm: 239.9987640385128
episode: 364 training return: tensor(-430.2620, device='cuda:0')
episode: 365 training return: tensor(-160.1541, device='cuda:0')
episode: 366 training return: tensor(-427.9469, device='cuda:0')
episode: 367 training return: tensor(-459.0237, device='cuda:0')
epoch: 92 test_true_pfm: 3330.35023106366 sim_pfm: 188.27196726598777
episode: 368 training return: tensor(-503.6481, device='cuda:0')
episode: 369 training return: tensor(-394.2406, device='cuda:0')
episode: 370 training return: tensor(-256.8262, device='cuda:0')
episode: 371 training return: tensor(-219.6660, device='cuda:0')
epoch: 93 test_true_pfm: 3064.5955780293493 sim_pfm: 285.91442830552114
episode: 372 training return: tensor(-229.8028, device='cuda:0')
episode: 373 training return: tensor(-272.8561, device='cuda:0')
episode: 374 training return: tensor(-440.5725, device='cuda:0')
episode: 375 training return: tensor(-168.8222, device='cuda:0')
epoch: 94 test_true_pfm: 3313.3070111342736 sim_pfm: 299.76085869084153
episode: 376 training return: tensor(-295.4602, device='cuda:0')
episode: 377 training return: tensor(81.8636, device='cuda:0')
episode: 378 training return: tensor(-431.3444, device='cuda:0')
episode: 379 training return: tensor(-245.6788, device='cuda:0')
epoch: 95 test_true_pfm: 2975.844708263226 sim_pfm: 289.923817534281
episode: 380 training return: tensor(-229.3308, device='cuda:0')
episode: 381 training return: tensor(-362.3305, device='cuda:0')
episode: 382 training return: tensor(-449.1771, device='cuda:0')
episode: 383 training return: tensor(-162.4409, device='cuda:0')
epoch: 96 test_true_pfm: 2874.431731740609 sim_pfm: 267.54513270376873
episode: 384 training return: tensor(-361.9366, device='cuda:0')
episode: 385 training return: tensor(-429.8731, device='cuda:0')
episode: 386 training return: tensor(-440.1172, device='cuda:0')
episode: 387 training return: tensor(-374.0276, device='cuda:0')
epoch: 97 test_true_pfm: 2983.8596598320655 sim_pfm: 70.00955022151659
episode: 388 training return: tensor(-239.9413, device='cuda:0')
episode: 389 training return: tensor(-441.7106, device='cuda:0')
episode: 390 training return: tensor(-209.1134, device='cuda:0')
episode: 391 training return: tensor(-256.8264, device='cuda:0')
epoch: 98 test_true_pfm: 3326.1139941952133 sim_pfm: 154.5077296126207
episode: 392 training return: tensor(-252.6475, device='cuda:0')
episode: 393 training return: tensor(-449.9757, device='cuda:0')
episode: 394 training return: tensor(-15.4235, device='cuda:0')
episode: 395 training return: tensor(-366.5325, device='cuda:0')
epoch: 99 test_true_pfm: 2421.760152491487 sim_pfm: -52.838870720006526
episode: 396 training return: tensor(-445.6721, device='cuda:0')
episode: 397 training return: tensor(-385.2668, device='cuda:0')
episode: 398 training return: tensor(-124.0880, device='cuda:0')
episode: 399 training return: tensor(-207.2785, device='cuda:0')
epoch: 100 test_true_pfm: 3346.7720164039542 sim_pfm: 298.36304530481965
episode: 400 training return: tensor(-374.7095, device='cuda:0')
episode: 401 training return: tensor(-248.0602, device='cuda:0')
episode: 402 training return: tensor(-260.6808, device='cuda:0')
episode: 403 training return: tensor(-429.5838, device='cuda:0')
epoch: 101 test_true_pfm: 2638.443887863072 sim_pfm: 220.94301495029745
episode: 404 training return: tensor(-436.3992, device='cuda:0')
episode: 405 training return: tensor(-23.3276, device='cuda:0')
episode: 406 training return: tensor(-264.3288, device='cuda:0')
episode: 407 training return: tensor(-425.2512, device='cuda:0')
epoch: 102 test_true_pfm: 3318.748915310387 sim_pfm: 153.727629347326
episode: 408 training return: tensor(66.5849, device='cuda:0')
episode: 409 training return: tensor(-325.9254, device='cuda:0')
episode: 410 training return: tensor(-430.2284, device='cuda:0')
episode: 411 training return: tensor(-378.8486, device='cuda:0')
epoch: 103 test_true_pfm: 2452.9083463302118 sim_pfm: 292.8139350905549
episode: 412 training return: tensor(-422.3571, device='cuda:0')
episode: 413 training return: tensor(-477.8073, device='cuda:0')
episode: 414 training return: tensor(-463.2228, device='cuda:0')
episode: 415 training return: tensor(-425.0442, device='cuda:0')
epoch: 104 test_true_pfm: 1826.4254762090575 sim_pfm: -119.68577394052409
episode: 416 training return: tensor(-250.7221, device='cuda:0')
episode: 417 training return: tensor(-514.1273, device='cuda:0')
episode: 418 training return: tensor(-455.8065, device='cuda:0')
episode: 419 training return: tensor(-426.6649, device='cuda:0')
epoch: 105 test_true_pfm: 2970.0046026196164 sim_pfm: 177.81341165903723
episode: 420 training return: tensor(-461.9119, device='cuda:0')
episode: 421 training return: tensor(-367.9588, device='cuda:0')
episode: 422 training return: tensor(78.7562, device='cuda:0')
episode: 423 training return: tensor(-401.3911, device='cuda:0')
epoch: 106 test_true_pfm: 3231.1252725863064 sim_pfm: 176.43931117211469
episode: 424 training return: tensor(-440.3082, device='cuda:0')
episode: 425 training return: tensor(-388.9155, device='cuda:0')
episode: 426 training return: tensor(-385.9214, device='cuda:0')
episode: 427 training return: tensor(-301.2047, device='cuda:0')
epoch: 107 test_true_pfm: 3301.558600584091 sim_pfm: 303.7539325833495
episode: 428 training return: tensor(-388.8427, device='cuda:0')
episode: 429 training return: tensor(-408.9953, device='cuda:0')
episode: 430 training return: tensor(-361.6596, device='cuda:0')
episode: 431 training return: tensor(-349.2090, device='cuda:0')
epoch: 108 test_true_pfm: 3321.5975656924893 sim_pfm: 312.7882946195702
episode: 432 training return: tensor(-353.5285, device='cuda:0')
episode: 433 training return: tensor(-311.8536, device='cuda:0')
episode: 434 training return: tensor(-168.6974, device='cuda:0')
episode: 435 training return: tensor(-65.2319, device='cuda:0')
epoch: 109 test_true_pfm: 3193.602034699033 sim_pfm: 155.0855859472067
episode: 436 training return: tensor(-226.2386, device='cuda:0')
episode: 437 training return: tensor(-16.0937, device='cuda:0')
episode: 438 training return: tensor(-396.4155, device='cuda:0')
episode: 439 training return: tensor(-252.9699, device='cuda:0')
epoch: 110 test_true_pfm: 3308.6301295597755 sim_pfm: 44.106259412830696
episode: 440 training return: tensor(-447.6194, device='cuda:0')
episode: 441 training return: tensor(-252.6587, device='cuda:0')
episode: 442 training return: tensor(-460.8871, device='cuda:0')
episode: 443 training return: tensor(-375.1277, device='cuda:0')
epoch: 111 test_true_pfm: 3086.6663597285965 sim_pfm: -21.770942100323737
episode: 444 training return: tensor(-462.1048, device='cuda:0')
episode: 445 training return: tensor(-378.8842, device='cuda:0')
episode: 446 training return: tensor(-356.5139, device='cuda:0')
episode: 447 training return: tensor(-159.9033, device='cuda:0')
epoch: 112 test_true_pfm: 3121.4510026495395 sim_pfm: 217.68883509802012
episode: 448 training return: tensor(-427.6474, device='cuda:0')
episode: 449 training return: tensor(-455.9611, device='cuda:0')
episode: 450 training return: tensor(-327.7598, device='cuda:0')
episode: 451 training return: tensor(-464.1856, device='cuda:0')
epoch: 113 test_true_pfm: 3055.5810846297395 sim_pfm: 211.56399634837484
episode: 452 training return: tensor(-441.7284, device='cuda:0')
episode: 453 training return: tensor(-466.1589, device='cuda:0')
episode: 454 training return: tensor(-197.6783, device='cuda:0')
episode: 455 training return: tensor(-95.6680, device='cuda:0')
epoch: 114 test_true_pfm: 2021.0196681774032 sim_pfm: -211.85184159851633
episode: 456 training return: tensor(-447.4269, device='cuda:0')
episode: 457 training return: tensor(-224.5379, device='cuda:0')
episode: 458 training return: tensor(-427.4323, device='cuda:0')
episode: 459 training return: tensor(-442.9644, device='cuda:0')
epoch: 115 test_true_pfm: 2311.949378941689 sim_pfm: 123.54563882564737
episode: 460 training return: tensor(-451.6222, device='cuda:0')
episode: 461 training return: tensor(18.2144, device='cuda:0')
episode: 462 training return: tensor(-322.8524, device='cuda:0')
episode: 463 training return: tensor(-377.5990, device='cuda:0')
epoch: 116 test_true_pfm: 3032.77257696311 sim_pfm: 306.37655484400847
episode: 464 training return: tensor(-254.4376, device='cuda:0')
episode: 465 training return: tensor(-442.8504, device='cuda:0')
episode: 466 training return: tensor(-307.0628, device='cuda:0')
episode: 467 training return: tensor(-471.0075, device='cuda:0')
epoch: 117 test_true_pfm: 3060.8797654058058 sim_pfm: 180.04654968122486
episode: 468 training return: tensor(-391.3602, device='cuda:0')
episode: 469 training return: tensor(-476.6079, device='cuda:0')
episode: 470 training return: tensor(-66.8814, device='cuda:0')
episode: 471 training return: tensor(-426.4261, device='cuda:0')
epoch: 118 test_true_pfm: 2542.9078937883737 sim_pfm: -105.88073063191648
episode: 472 training return: tensor(-471.7376, device='cuda:0')
episode: 473 training return: tensor(-358.7954, device='cuda:0')
episode: 474 training return: tensor(-391.0144, device='cuda:0')
episode: 475 training return: tensor(-454.6127, device='cuda:0')
epoch: 119 test_true_pfm: 3303.9897384792243 sim_pfm: 299.18847135889035
episode: 476 training return: tensor(-435.4692, device='cuda:0')
episode: 477 training return: tensor(-441.5103, device='cuda:0')
episode: 478 training return: tensor(228.0086, device='cuda:0')
episode: 479 training return: tensor(-177.8257, device='cuda:0')
epoch: 120 test_true_pfm: 2825.931277633019 sim_pfm: -18.887776908309508
episode: 480 training return: tensor(-300.1001, device='cuda:0')
episode: 481 training return: tensor(59.4310, device='cuda:0')
episode: 482 training return: tensor(-459.0186, device='cuda:0')
episode: 483 training return: tensor(-457.7710, device='cuda:0')
epoch: 121 test_true_pfm: 3194.3950131584756 sim_pfm: 298.7837304385127
episode: 484 training return: tensor(-463.1929, device='cuda:0')
episode: 485 training return: tensor(-447.0091, device='cuda:0')
episode: 486 training return: tensor(-476.0121, device='cuda:0')
episode: 487 training return: tensor(-472.5393, device='cuda:0')
epoch: 122 test_true_pfm: 2986.0546802161975 sim_pfm: 299.0118457825544
episode: 488 training return: tensor(-254.8878, device='cuda:0')
episode: 489 training return: tensor(-97.5788, device='cuda:0')
episode: 490 training return: tensor(-199.9904, device='cuda:0')
episode: 491 training return: tensor(-527.7357, device='cuda:0')
epoch: 123 test_true_pfm: 2870.979316241514 sim_pfm: 192.8073476755526
episode: 492 training return: tensor(-417.0868, device='cuda:0')
episode: 493 training return: tensor(-383.5615, device='cuda:0')
episode: 494 training return: tensor(-235.1552, device='cuda:0')
episode: 495 training return: tensor(-436.3081, device='cuda:0')
epoch: 124 test_true_pfm: 3240.8224364796165 sim_pfm: 298.90804260394845
episode: 496 training return: tensor(-200.8960, device='cuda:0')
episode: 497 training return: tensor(-341.5654, device='cuda:0')
episode: 498 training return: tensor(-168.7721, device='cuda:0')
episode: 499 training return: tensor(-263.9567, device='cuda:0')
epoch: 125 test_true_pfm: 3354.1631690864415 sim_pfm: 204.93882512838658
episode: 500 training return: tensor(-427.9348, device='cuda:0')
episode: 501 training return: tensor(-445.1901, device='cuda:0')
episode: 502 training return: tensor(-344.5458, device='cuda:0')
episode: 503 training return: tensor(-393.3951, device='cuda:0')
epoch: 126 test_true_pfm: 3059.0444626263893 sim_pfm: 156.30158873298205
episode: 504 training return: tensor(-244.8846, device='cuda:0')
episode: 505 training return: tensor(-215.8385, device='cuda:0')
episode: 506 training return: tensor(-442.4207, device='cuda:0')
episode: 507 training return: tensor(-516.5059, device='cuda:0')
epoch: 127 test_true_pfm: 2565.87470664854 sim_pfm: 133.83748607861344
episode: 508 training return: tensor(-476.2855, device='cuda:0')
episode: 509 training return: tensor(-425.2200, device='cuda:0')
episode: 510 training return: tensor(-227.1275, device='cuda:0')
episode: 511 training return: tensor(-419.2357, device='cuda:0')
epoch: 128 test_true_pfm: 3317.4699024903653 sim_pfm: 105.00748143624514
episode: 512 training return: tensor(-388.5970, device='cuda:0')
episode: 513 training return: tensor(-437.5431, device='cuda:0')
episode: 514 training return: tensor(-471.1903, device='cuda:0')
episode: 515 training return: tensor(-448.7722, device='cuda:0')
epoch: 129 test_true_pfm: 2689.691839389814 sim_pfm: 58.302347949861236
episode: 516 training return: tensor(-252.6080, device='cuda:0')
episode: 517 training return: tensor(-391.8851, device='cuda:0')
episode: 518 training return: tensor(-434.5328, device='cuda:0')
episode: 519 training return: tensor(-27.2189, device='cuda:0')
epoch: 130 test_true_pfm: 3303.145336930704 sim_pfm: 309.5343472143868
episode: 520 training return: tensor(-440.5269, device='cuda:0')
episode: 521 training return: tensor(-408.6191, device='cuda:0')
episode: 522 training return: tensor(-470.3646, device='cuda:0')
episode: 523 training return: tensor(-433.5457, device='cuda:0')
epoch: 131 test_true_pfm: 3025.6127429019903 sim_pfm: 130.28638765464225
episode: 524 training return: tensor(-506.1249, device='cuda:0')
episode: 525 training return: tensor(302.9016, device='cuda:0')
episode: 526 training return: tensor(-455.9972, device='cuda:0')
episode: 527 training return: tensor(-424.7358, device='cuda:0')
epoch: 132 test_true_pfm: 2536.033906220058 sim_pfm: 40.21195519094666
episode: 528 training return: tensor(-438.4924, device='cuda:0')
episode: 529 training return: tensor(-447.9363, device='cuda:0')
episode: 530 training return: tensor(-429.9775, device='cuda:0')
episode: 531 training return: tensor(-371.0273, device='cuda:0')
epoch: 133 test_true_pfm: 3328.3172572676904 sim_pfm: 305.1252633058466
episode: 532 training return: tensor(-368.5339, device='cuda:0')
episode: 533 training return: tensor(-463.4268, device='cuda:0')
episode: 534 training return: tensor(-350.6454, device='cuda:0')
episode: 535 training return: tensor(-464.8993, device='cuda:0')
epoch: 134 test_true_pfm: 3215.0824881340286 sim_pfm: 147.36094332913248
episode: 536 training return: tensor(-387.6995, device='cuda:0')
episode: 537 training return: tensor(-308.9605, device='cuda:0')
episode: 538 training return: tensor(-449.6841, device='cuda:0')
episode: 539 training return: tensor(-442.2648, device='cuda:0')
epoch: 135 test_true_pfm: 3332.8816735425276 sim_pfm: 298.70659397993586
episode: 540 training return: tensor(-355.8982, device='cuda:0')
episode: 541 training return: tensor(-345.6426, device='cuda:0')
episode: 542 training return: tensor(95.8470, device='cuda:0')
episode: 543 training return: tensor(-416.3148, device='cuda:0')
epoch: 136 test_true_pfm: 1984.6515076014286 sim_pfm: 83.11753796188471
episode: 544 training return: tensor(0.6068, device='cuda:0')
episode: 545 training return: tensor(-443.5269, device='cuda:0')
episode: 546 training return: tensor(222.2831, device='cuda:0')
episode: 547 training return: tensor(-388.9483, device='cuda:0')
epoch: 137 test_true_pfm: 3077.120458952624 sim_pfm: 297.64247452422086
episode: 548 training return: tensor(-460.8079, device='cuda:0')
episode: 549 training return: tensor(-306.2268, device='cuda:0')
episode: 550 training return: tensor(-227.5828, device='cuda:0')
episode: 551 training return: tensor(-429.6873, device='cuda:0')
epoch: 138 test_true_pfm: 2725.599552286659 sim_pfm: -144.6893200665363
episode: 552 training return: tensor(-471.9631, device='cuda:0')
episode: 553 training return: tensor(-161.4615, device='cuda:0')
episode: 554 training return: tensor(-400.6161, device='cuda:0')
episode: 555 training return: tensor(-395.6527, device='cuda:0')
epoch: 139 test_true_pfm: 2186.9189214679423 sim_pfm: -30.916190977014292
episode: 556 training return: tensor(-387.0409, device='cuda:0')
episode: 557 training return: tensor(-435.5525, device='cuda:0')
episode: 558 training return: tensor(-530.3664, device='cuda:0')
episode: 559 training return: tensor(-388.4421, device='cuda:0')
epoch: 140 test_true_pfm: 3305.3594872579124 sim_pfm: 287.9655269375071
episode: 560 training return: tensor(-363.5206, device='cuda:0')
episode: 561 training return: tensor(-379.3715, device='cuda:0')
episode: 562 training return: tensor(-465.2287, device='cuda:0')
episode: 563 training return: tensor(-449.8965, device='cuda:0')
epoch: 141 test_true_pfm: 3163.9132232293196 sim_pfm: 223.00911771312045
episode: 564 training return: tensor(-502.6848, device='cuda:0')
episode: 565 training return: tensor(-369.0017, device='cuda:0')
episode: 566 training return: tensor(-429.3470, device='cuda:0')
episode: 567 training return: tensor(-257.1784, device='cuda:0')
epoch: 142 test_true_pfm: 3234.630301870698 sim_pfm: -65.86669853993226
episode: 568 training return: tensor(-267.5929, device='cuda:0')
episode: 569 training return: tensor(-442.1606, device='cuda:0')
episode: 570 training return: tensor(-378.6470, device='cuda:0')
episode: 571 training return: tensor(-443.0961, device='cuda:0')
epoch: 143 test_true_pfm: 2449.5477253093 sim_pfm: 3.9764928759541363
episode: 572 training return: tensor(-438.3342, device='cuda:0')
episode: 573 training return: tensor(-355.0297, device='cuda:0')
episode: 574 training return: tensor(-415.4993, device='cuda:0')
episode: 575 training return: tensor(-454.9023, device='cuda:0')
epoch: 144 test_true_pfm: 3320.643838777151 sim_pfm: 300.6762612436044
episode: 576 training return: tensor(86.9400, device='cuda:0')
episode: 577 training return: tensor(-370.3641, device='cuda:0')
episode: 578 training return: tensor(-462.0895, device='cuda:0')
episode: 579 training return: tensor(-285.4308, device='cuda:0')
epoch: 145 test_true_pfm: 3081.251844202028 sim_pfm: 210.8940918596539
episode: 580 training return: tensor(-313.6724, device='cuda:0')
episode: 581 training return: tensor(-454.9887, device='cuda:0')
episode: 582 training return: tensor(-405.6295, device='cuda:0')
episode: 583 training return: tensor(-431.4146, device='cuda:0')
epoch: 146 test_true_pfm: 3256.8388562510245 sim_pfm: 60.873442136663165
episode: 584 training return: tensor(-121.5785, device='cuda:0')
episode: 585 training return: tensor(-403.6072, device='cuda:0')
episode: 586 training return: tensor(-508.6090, device='cuda:0')
episode: 587 training return: tensor(-158.1355, device='cuda:0')
epoch: 147 test_true_pfm: 2132.5814693518782 sim_pfm: -209.2692971304059
episode: 588 training return: tensor(-458.6553, device='cuda:0')
episode: 589 training return: tensor(139.4132, device='cuda:0')
episode: 590 training return: tensor(-502.3472, device='cuda:0')
episode: 591 training return: tensor(-432.1745, device='cuda:0')
epoch: 148 test_true_pfm: 2582.28978846552 sim_pfm: -97.48940299426128
episode: 592 training return: tensor(-424.5042, device='cuda:0')
episode: 593 training return: tensor(-396.0677, device='cuda:0')
episode: 594 training return: tensor(-334.3550, device='cuda:0')
episode: 595 training return: tensor(-328.2317, device='cuda:0')
epoch: 149 test_true_pfm: 2918.2869309958555 sim_pfm: 275.6516399362202
episode: 596 training return: tensor(-375.2738, device='cuda:0')
episode: 597 training return: tensor(-392.8281, device='cuda:0')
episode: 598 training return: tensor(-447.8629, device='cuda:0')
episode: 599 training return: tensor(-500.7924, device='cuda:0')
epoch: 150 test_true_pfm: 3072.037233438532 sim_pfm: 115.6021374616151
