episode: 0 training return: tensor(-582.0548, device='cuda:0')
episode: 1 training return: tensor(-773.8674, device='cuda:0')
episode: 2 training return: tensor(-827.4810, device='cuda:0')
episode: 3 training return: tensor(-891.5975, device='cuda:0')
epoch: 1 test_true_pfm: 4803.678113993385 sim_pfm: -668.1049795379319
episode: 4 training return: tensor(-652.4792, device='cuda:0')
episode: 5 training return: tensor(-876.8174, device='cuda:0')
episode: 6 training return: tensor(-740.4968, device='cuda:0')
episode: 7 training return: tensor(-999.9943, device='cuda:0')
epoch: 2 test_true_pfm: 7615.295702348964 sim_pfm: -689.2880772454664
episode: 8 training return: tensor(-504.6761, device='cuda:0')
episode: 9 training return: tensor(-821.9376, device='cuda:0')
episode: 10 training return: tensor(-870.2369, device='cuda:0')
episode: 11 training return: tensor(-803.8705, device='cuda:0')
epoch: 3 test_true_pfm: 2971.6133218345053 sim_pfm: -685.3277164896717
episode: 12 training return: tensor(-801.8241, device='cuda:0')
episode: 13 training return: tensor(-736.8196, device='cuda:0')
episode: 14 training return: tensor(-992.7663, device='cuda:0')
episode: 15 training return: tensor(-688.9459, device='cuda:0')
epoch: 4 test_true_pfm: 7724.504382597665 sim_pfm: -470.5802593578701
episode: 16 training return: tensor(-418.0968, device='cuda:0')
episode: 17 training return: tensor(-999.9437, device='cuda:0')
episode: 18 training return: tensor(-800.7186, device='cuda:0')
episode: 19 training return: tensor(-700.9528, device='cuda:0')
epoch: 5 test_true_pfm: 2162.4057914548353 sim_pfm: -804.9046131623812
episode: 20 training return: tensor(-832.3815, device='cuda:0')
episode: 21 training return: tensor(-999.6892, device='cuda:0')
episode: 22 training return: tensor(-581.9560, device='cuda:0')
episode: 23 training return: tensor(-977.2993, device='cuda:0')
epoch: 6 test_true_pfm: 6953.394960810787 sim_pfm: -660.3263169118824
episode: 24 training return: tensor(-999.9989, device='cuda:0')
episode: 25 training return: tensor(-548.1418, device='cuda:0')
episode: 26 training return: tensor(-722.2827, device='cuda:0')
episode: 27 training return: tensor(-803.1550, device='cuda:0')
epoch: 7 test_true_pfm: 7494.7642531044185 sim_pfm: -472.88742738275323
episode: 28 training return: tensor(-999.9286, device='cuda:0')
episode: 29 training return: tensor(-860.3647, device='cuda:0')
episode: 30 training return: tensor(-785.6354, device='cuda:0')
episode: 31 training return: tensor(-965.6281, device='cuda:0')
epoch: 8 test_true_pfm: 5552.386252417214 sim_pfm: -649.7504242016003
episode: 32 training return: tensor(-583.5963, device='cuda:0')
episode: 33 training return: tensor(-651.5608, device='cuda:0')
episode: 34 training return: tensor(-780.7858, device='cuda:0')
episode: 35 training return: tensor(-905.1533, device='cuda:0')
epoch: 9 test_true_pfm: 6373.232885967939 sim_pfm: -458.0499685382626
episode: 36 training return: tensor(-834.5984, device='cuda:0')
episode: 37 training return: tensor(-999.8220, device='cuda:0')
episode: 38 training return: tensor(-888.0632, device='cuda:0')
episode: 39 training return: tensor(-485.0609, device='cuda:0')
epoch: 10 test_true_pfm: 4719.032536088339 sim_pfm: -809.3212279748792
episode: 40 training return: tensor(-556.2631, device='cuda:0')
episode: 41 training return: tensor(-919.7791, device='cuda:0')
episode: 42 training return: tensor(-633.8900, device='cuda:0')
episode: 43 training return: tensor(-999.0449, device='cuda:0')
epoch: 11 test_true_pfm: 4465.404440070958 sim_pfm: -357.347936826176
episode: 44 training return: tensor(-463.9489, device='cuda:0')
episode: 45 training return: tensor(-555.9829, device='cuda:0')
episode: 46 training return: tensor(-736.3445, device='cuda:0')
episode: 47 training return: tensor(-745.1355, device='cuda:0')
epoch: 12 test_true_pfm: 1895.5090026902424 sim_pfm: -709.712859442574
episode: 48 training return: tensor(-635.2014, device='cuda:0')
episode: 49 training return: tensor(-282.4449, device='cuda:0')
episode: 50 training return: tensor(-999.8315, device='cuda:0')
episode: 51 training return: tensor(-922.0377, device='cuda:0')
epoch: 13 test_true_pfm: 5014.302884378848 sim_pfm: -692.6505344626299
episode: 52 training return: tensor(-429.3650, device='cuda:0')
episode: 53 training return: tensor(-934.9336, device='cuda:0')
episode: 54 training return: tensor(-725.9334, device='cuda:0')
episode: 55 training return: tensor(-175.3124, device='cuda:0')
epoch: 14 test_true_pfm: 3531.1463633876697 sim_pfm: -451.97117220794706
episode: 56 training return: tensor(-374.8188, device='cuda:0')
episode: 57 training return: tensor(-254.3475, device='cuda:0')
episode: 58 training return: tensor(-712.0541, device='cuda:0')
episode: 59 training return: tensor(-983.8195, device='cuda:0')
epoch: 15 test_true_pfm: 3608.4576404539184 sim_pfm: -615.6272138343969
episode: 60 training return: tensor(-737.9828, device='cuda:0')
episode: 61 training return: tensor(-685.0336, device='cuda:0')
episode: 62 training return: tensor(-690.9045, device='cuda:0')
episode: 63 training return: tensor(-589.4522, device='cuda:0')
epoch: 16 test_true_pfm: 9412.930502987607 sim_pfm: -395.05386358635343
episode: 64 training return: tensor(-854.6514, device='cuda:0')
episode: 65 training return: tensor(-585.5081, device='cuda:0')
episode: 66 training return: tensor(-484.7663, device='cuda:0')
episode: 67 training return: tensor(-478.8268, device='cuda:0')
epoch: 17 test_true_pfm: 4370.607260641712 sim_pfm: -227.03011919373725
episode: 68 training return: tensor(-999.8928, device='cuda:0')
episode: 69 training return: tensor(-654.4266, device='cuda:0')
episode: 70 training return: tensor(-414.6692, device='cuda:0')
episode: 71 training return: tensor(-563.4515, device='cuda:0')
epoch: 18 test_true_pfm: 4780.709887667501 sim_pfm: -699.3593679645564
episode: 72 training return: tensor(-670.1274, device='cuda:0')
episode: 73 training return: tensor(-999.9904, device='cuda:0')
episode: 74 training return: tensor(-999.8793, device='cuda:0')
episode: 75 training return: tensor(-867.4227, device='cuda:0')
epoch: 19 test_true_pfm: 7750.425878491359 sim_pfm: -507.677927737978
episode: 76 training return: tensor(-999.9548, device='cuda:0')
episode: 77 training return: tensor(-964.0822, device='cuda:0')
episode: 78 training return: tensor(-417.1724, device='cuda:0')
episode: 79 training return: tensor(-999.6004, device='cuda:0')
epoch: 20 test_true_pfm: 2330.2312651023058 sim_pfm: -342.7231453770655
episode: 80 training return: tensor(-609.0087, device='cuda:0')
episode: 81 training return: tensor(-480.2886, device='cuda:0')
episode: 82 training return: tensor(-382.4585, device='cuda:0')
episode: 83 training return: tensor(-993.5684, device='cuda:0')
epoch: 21 test_true_pfm: 7070.912931605326 sim_pfm: -450.69458741388127
episode: 84 training return: tensor(-868.2341, device='cuda:0')
episode: 85 training return: tensor(-998.7452, device='cuda:0')
episode: 86 training return: tensor(-630.8902, device='cuda:0')
episode: 87 training return: tensor(-583.8500, device='cuda:0')
epoch: 22 test_true_pfm: 3867.8612741493685 sim_pfm: -629.481731758453
episode: 88 training return: tensor(-440.4586, device='cuda:0')
episode: 89 training return: tensor(-303.9723, device='cuda:0')
episode: 90 training return: tensor(-918.3083, device='cuda:0')
episode: 91 training return: tensor(-949.7777, device='cuda:0')
epoch: 23 test_true_pfm: 8477.410072659679 sim_pfm: -470.58286705533584
episode: 92 training return: tensor(-381.4611, device='cuda:0')
episode: 93 training return: tensor(-660.7246, device='cuda:0')
episode: 94 training return: tensor(-981.8087, device='cuda:0')
episode: 95 training return: tensor(-520.7233, device='cuda:0')
epoch: 24 test_true_pfm: 5059.203356131514 sim_pfm: -630.6304131419553
episode: 96 training return: tensor(-601.0341, device='cuda:0')
episode: 97 training return: tensor(-703.5117, device='cuda:0')
episode: 98 training return: tensor(-525.2037, device='cuda:0')
episode: 99 training return: tensor(-915.3959, device='cuda:0')
epoch: 25 test_true_pfm: 7569.65575837935 sim_pfm: -188.48622644558782
episode: 100 training return: tensor(-999.9105, device='cuda:0')
episode: 101 training return: tensor(-559.7304, device='cuda:0')
episode: 102 training return: tensor(-321.1419, device='cuda:0')
episode: 103 training return: tensor(-649.2010, device='cuda:0')
epoch: 26 test_true_pfm: 6265.1544097316755 sim_pfm: -439.434971112496
episode: 104 training return: tensor(-907.6101, device='cuda:0')
episode: 105 training return: tensor(-932.8620, device='cuda:0')
episode: 106 training return: tensor(-946.8263, device='cuda:0')
episode: 107 training return: tensor(-168.1156, device='cuda:0')
epoch: 27 test_true_pfm: 5018.305631605962 sim_pfm: -473.8417767378269
episode: 108 training return: tensor(-999.9984, device='cuda:0')
episode: 109 training return: tensor(-949.8685, device='cuda:0')
episode: 110 training return: tensor(-707.4885, device='cuda:0')
episode: 111 training return: tensor(-980.6526, device='cuda:0')
epoch: 28 test_true_pfm: 2887.1250898376074 sim_pfm: -466.8655653526851
episode: 112 training return: tensor(-535.6531, device='cuda:0')
episode: 113 training return: tensor(-734.6685, device='cuda:0')
episode: 114 training return: tensor(-999.8813, device='cuda:0')
episode: 115 training return: tensor(-733.5005, device='cuda:0')
epoch: 29 test_true_pfm: 2942.266710958523 sim_pfm: -724.3541123489462
episode: 116 training return: tensor(-969.0417, device='cuda:0')
episode: 117 training return: tensor(-685.9519, device='cuda:0')
episode: 118 training return: tensor(-440.0479, device='cuda:0')
episode: 119 training return: tensor(-981.4125, device='cuda:0')
epoch: 30 test_true_pfm: 8644.13812174259 sim_pfm: -515.8280519282949
episode: 120 training return: tensor(-224.5068, device='cuda:0')
episode: 121 training return: tensor(-463.2376, device='cuda:0')
episode: 122 training return: tensor(-485.6052, device='cuda:0')
episode: 123 training return: tensor(-341.2485, device='cuda:0')
epoch: 31 test_true_pfm: 5498.713657652249 sim_pfm: -501.5313908997826
episode: 124 training return: tensor(-444.3448, device='cuda:0')
episode: 125 training return: tensor(-742.4875, device='cuda:0')
episode: 126 training return: tensor(-971.6081, device='cuda:0')
episode: 127 training return: tensor(-770.5216, device='cuda:0')
epoch: 32 test_true_pfm: 9177.832380210042 sim_pfm: -464.1746062634823
episode: 128 training return: tensor(-514.5058, device='cuda:0')
episode: 129 training return: tensor(-948.8298, device='cuda:0')
episode: 130 training return: tensor(-297.4663, device='cuda:0')
episode: 131 training return: tensor(-610.7880, device='cuda:0')
epoch: 33 test_true_pfm: 6552.987720138503 sim_pfm: -772.6059906929731
episode: 132 training return: tensor(-696.3412, device='cuda:0')
episode: 133 training return: tensor(-855.3544, device='cuda:0')
episode: 134 training return: tensor(-848.0609, device='cuda:0')
episode: 135 training return: tensor(-644.9120, device='cuda:0')
epoch: 34 test_true_pfm: 3484.215655687856 sim_pfm: -878.4129198341785
episode: 136 training return: tensor(-479.7962, device='cuda:0')
episode: 137 training return: tensor(-537.8166, device='cuda:0')
episode: 138 training return: tensor(-136.2108, device='cuda:0')
episode: 139 training return: tensor(-374.7742, device='cuda:0')
epoch: 35 test_true_pfm: 5060.222999786312 sim_pfm: -930.1103508522114
episode: 140 training return: tensor(-434.4207, device='cuda:0')
episode: 141 training return: tensor(-372.6460, device='cuda:0')
episode: 142 training return: tensor(-503.4251, device='cuda:0')
episode: 143 training return: tensor(-900.1990, device='cuda:0')
epoch: 36 test_true_pfm: 4329.23064893686 sim_pfm: -545.2948320950964
episode: 144 training return: tensor(-736.1442, device='cuda:0')
episode: 145 training return: tensor(-406.6238, device='cuda:0')
episode: 146 training return: tensor(-786.6299, device='cuda:0')
episode: 147 training return: tensor(-427.9765, device='cuda:0')
epoch: 37 test_true_pfm: 7190.448982164055 sim_pfm: -657.2144951988981
episode: 148 training return: tensor(-997.6274, device='cuda:0')
episode: 149 training return: tensor(-705.8668, device='cuda:0')
episode: 150 training return: tensor(-594.1063, device='cuda:0')
episode: 151 training return: tensor(-751.6524, device='cuda:0')
epoch: 38 test_true_pfm: 8540.355150044035 sim_pfm: -355.1535021211894
episode: 152 training return: tensor(-730.1801, device='cuda:0')
episode: 153 training return: tensor(-522.7729, device='cuda:0')
episode: 154 training return: tensor(-336.6829, device='cuda:0')
episode: 155 training return: tensor(-739.1895, device='cuda:0')
epoch: 39 test_true_pfm: 6194.576492175914 sim_pfm: -543.8551759369244
episode: 156 training return: tensor(-752.2123, device='cuda:0')
episode: 157 training return: tensor(-999.9123, device='cuda:0')
episode: 158 training return: tensor(-377.6203, device='cuda:0')
episode: 159 training return: tensor(-574.0921, device='cuda:0')
epoch: 40 test_true_pfm: 2291.116886415901 sim_pfm: -704.8751788312996
episode: 160 training return: tensor(-722.7463, device='cuda:0')
episode: 161 training return: tensor(-714.2052, device='cuda:0')
episode: 162 training return: tensor(-242.2695, device='cuda:0')
episode: 163 training return: tensor(-999.7252, device='cuda:0')
epoch: 41 test_true_pfm: 4073.166104950016 sim_pfm: -179.14837626587055
episode: 164 training return: tensor(-997.2395, device='cuda:0')
episode: 165 training return: tensor(-974.9452, device='cuda:0')
episode: 166 training return: tensor(-951.9770, device='cuda:0')
episode: 167 training return: tensor(-955.1100, device='cuda:0')
epoch: 42 test_true_pfm: 8147.491798221937 sim_pfm: -790.2929641355295
episode: 168 training return: tensor(-638.2091, device='cuda:0')
episode: 169 training return: tensor(-577.0557, device='cuda:0')
episode: 170 training return: tensor(-763.7003, device='cuda:0')
episode: 171 training return: tensor(-647.5155, device='cuda:0')
epoch: 43 test_true_pfm: 5081.675685629463 sim_pfm: -445.8888460722713
episode: 172 training return: tensor(-999.9805, device='cuda:0')
episode: 173 training return: tensor(-954.3965, device='cuda:0')
episode: 174 training return: tensor(-478.8921, device='cuda:0')
episode: 175 training return: tensor(-507.5358, device='cuda:0')
epoch: 44 test_true_pfm: 3128.218201103157 sim_pfm: -404.3044721437618
episode: 176 training return: tensor(-368.0079, device='cuda:0')
episode: 177 training return: tensor(-362.4501, device='cuda:0')
episode: 178 training return: tensor(-999.7689, device='cuda:0')
episode: 179 training return: tensor(-539.8662, device='cuda:0')
epoch: 45 test_true_pfm: 5180.68720012578 sim_pfm: -79.6314254742271
episode: 180 training return: tensor(-248.2948, device='cuda:0')
episode: 181 training return: tensor(-744.5253, device='cuda:0')
episode: 182 training return: tensor(-577.0990, device='cuda:0')
episode: 183 training return: tensor(-957.5601, device='cuda:0')
epoch: 46 test_true_pfm: 5795.358395081302 sim_pfm: -228.65922768848637
episode: 184 training return: tensor(-999.9788, device='cuda:0')
episode: 185 training return: tensor(-901.4073, device='cuda:0')
episode: 186 training return: tensor(-998.9097, device='cuda:0')
episode: 187 training return: tensor(-487.7355, device='cuda:0')
epoch: 47 test_true_pfm: 7345.4695282499115 sim_pfm: -405.14962151369156
episode: 188 training return: tensor(-996.4236, device='cuda:0')
episode: 189 training return: tensor(-736.2485, device='cuda:0')
episode: 190 training return: tensor(-427.3311, device='cuda:0')
episode: 191 training return: tensor(-798.0365, device='cuda:0')
epoch: 48 test_true_pfm: 6568.475328347898 sim_pfm: -312.953053203586
episode: 192 training return: tensor(-562.3602, device='cuda:0')
episode: 193 training return: tensor(-839.6476, device='cuda:0')
episode: 194 training return: tensor(-791.2811, device='cuda:0')
episode: 195 training return: tensor(-854.6765, device='cuda:0')
epoch: 49 test_true_pfm: 7574.4689195326 sim_pfm: -699.3473170418487
episode: 196 training return: tensor(-581.1876, device='cuda:0')
episode: 197 training return: tensor(-685.2148, device='cuda:0')
episode: 198 training return: tensor(-419.3012, device='cuda:0')
episode: 199 training return: tensor(-556.9712, device='cuda:0')
epoch: 50 test_true_pfm: 3567.663849743842 sim_pfm: -585.3155322571596
episode: 200 training return: tensor(-443.1163, device='cuda:0')
episode: 201 training return: tensor(-724.3806, device='cuda:0')
episode: 202 training return: tensor(-831.6586, device='cuda:0')
episode: 203 training return: tensor(-911.8221, device='cuda:0')
epoch: 51 test_true_pfm: 8851.631495387583 sim_pfm: -324.5440117586016
episode: 204 training return: tensor(-996.2126, device='cuda:0')
episode: 205 training return: tensor(-888.1614, device='cuda:0')
episode: 206 training return: tensor(-788.8204, device='cuda:0')
episode: 207 training return: tensor(-848.8083, device='cuda:0')
epoch: 52 test_true_pfm: 6578.924758963861 sim_pfm: -739.8004490156503
episode: 208 training return: tensor(-542.9468, device='cuda:0')
episode: 209 training return: tensor(-746.7964, device='cuda:0')
episode: 210 training return: tensor(-835.0522, device='cuda:0')
episode: 211 training return: tensor(-526.4648, device='cuda:0')
epoch: 53 test_true_pfm: 4539.689879499427 sim_pfm: -552.5086094139066
episode: 212 training return: tensor(-881.4470, device='cuda:0')
episode: 213 training return: tensor(-934.4464, device='cuda:0')
episode: 214 training return: tensor(-999.3716, device='cuda:0')
episode: 215 training return: tensor(-492.2624, device='cuda:0')
epoch: 54 test_true_pfm: 9428.409712738425 sim_pfm: -333.8101043695933
episode: 216 training return: tensor(-524.2543, device='cuda:0')
episode: 217 training return: tensor(-676.4506, device='cuda:0')
