['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'behavior', '--traj', 'medium', '--seed', '3', '--data', '100000', '--regu', '0.05']
2702.7487853227667
episode: 0 training return: tensor(-184.7396, device='cuda:0')
episode: 1 training return: tensor(59.4153, device='cuda:0')
episode: 2 training return: tensor(-50.1433, device='cuda:0')
episode: 3 training return: tensor(279.8634, device='cuda:0')
epoch: 1 test_true_pfm: 2859.84640525688 sim_pfm: 192.39145009884183
episode: 4 training return: tensor(-266.3659, device='cuda:0')
episode: 5 training return: tensor(247.7765, device='cuda:0')
episode: 6 training return: tensor(-122.1730, device='cuda:0')
episode: 7 training return: tensor(225.6980, device='cuda:0')
epoch: 2 test_true_pfm: 3162.670343880675 sim_pfm: 262.1485613132633
episode: 8 training return: tensor(247.3205, device='cuda:0')
episode: 9 training return: tensor(60.3517, device='cuda:0')
episode: 10 training return: tensor(33.9586, device='cuda:0')
episode: 11 training return: tensor(-155.3440, device='cuda:0')
epoch: 3 test_true_pfm: 3133.6519400152342 sim_pfm: 282.55020889880444
episode: 12 training return: tensor(61.1369, device='cuda:0')
episode: 13 training return: tensor(255.7912, device='cuda:0')
episode: 14 training return: tensor(268.5565, device='cuda:0')
episode: 15 training return: tensor(202.0721, device='cuda:0')
epoch: 4 test_true_pfm: 2952.561312698914 sim_pfm: -16.885455202825444
episode: 16 training return: tensor(-14.1764, device='cuda:0')
episode: 17 training return: tensor(255.3410, device='cuda:0')
episode: 18 training return: tensor(275.5568, device='cuda:0')
episode: 19 training return: tensor(115.3743, device='cuda:0')
epoch: 5 test_true_pfm: 2260.170247673288 sim_pfm: 46.782092882087454
episode: 20 training return: tensor(-108.3773, device='cuda:0')
episode: 21 training return: tensor(180.5766, device='cuda:0')
episode: 22 training return: tensor(323.0034, device='cuda:0')
episode: 23 training return: tensor(128.7533, device='cuda:0')
epoch: 6 test_true_pfm: 3304.088120185556 sim_pfm: -97.372820445317
episode: 24 training return: tensor(211.8338, device='cuda:0')
episode: 25 training return: tensor(331.4176, device='cuda:0')
episode: 26 training return: tensor(288.7827, device='cuda:0')
episode: 27 training return: tensor(26.7400, device='cuda:0')
epoch: 7 test_true_pfm: 2685.3140617368003 sim_pfm: 201.13904211485837
episode: 28 training return: tensor(205.1858, device='cuda:0')
episode: 29 training return: tensor(-127.0024, device='cuda:0')
episode: 30 training return: tensor(-81.7853, device='cuda:0')
episode: 31 training return: tensor(296.4077, device='cuda:0')
epoch: 8 test_true_pfm: 2520.465917051199 sim_pfm: 165.32501750012548
episode: 32 training return: tensor(122.6204, device='cuda:0')
episode: 33 training return: tensor(301.6518, device='cuda:0')
episode: 34 training return: tensor(161.2283, device='cuda:0')
episode: 35 training return: tensor(260.8292, device='cuda:0')
epoch: 9 test_true_pfm: 3094.090757608957 sim_pfm: -63.9611769762123
episode: 36 training return: tensor(-18.5712, device='cuda:0')
episode: 37 training return: tensor(312.5491, device='cuda:0')
episode: 38 training return: tensor(273.8546, device='cuda:0')
episode: 39 training return: tensor(285.8188, device='cuda:0')
epoch: 10 test_true_pfm: 3324.6273030030934 sim_pfm: 64.2737493229409
episode: 40 training return: tensor(195.7401, device='cuda:0')
episode: 41 training return: tensor(-159.0735, device='cuda:0')
episode: 42 training return: tensor(-183.7726, device='cuda:0')
episode: 43 training return: tensor(-229.2081, device='cuda:0')
epoch: 11 test_true_pfm: 2683.2974642409185 sim_pfm: -32.281913869005315
episode: 44 training return: tensor(247.0490, device='cuda:0')
episode: 45 training return: tensor(10.9148, device='cuda:0')
episode: 46 training return: tensor(184.9861, device='cuda:0')
episode: 47 training return: tensor(219.2035, device='cuda:0')
epoch: 12 test_true_pfm: 2824.1008711400477 sim_pfm: 76.64862518503408
episode: 48 training return: tensor(-219.0598, device='cuda:0')
episode: 49 training return: tensor(-84.3993, device='cuda:0')
episode: 50 training return: tensor(342.9665, device='cuda:0')
episode: 51 training return: tensor(-54.6003, device='cuda:0')
epoch: 13 test_true_pfm: 3315.3696482641676 sim_pfm: 309.52130697106867
episode: 52 training return: tensor(309.9341, device='cuda:0')
episode: 53 training return: tensor(258.8649, device='cuda:0')
episode: 54 training return: tensor(292.9199, device='cuda:0')
episode: 55 training return: tensor(-39.8014, device='cuda:0')
epoch: 14 test_true_pfm: 3194.3560711611613 sim_pfm: 183.15957381612193
episode: 56 training return: tensor(-134.8498, device='cuda:0')
episode: 57 training return: tensor(-212.1700, device='cuda:0')
episode: 58 training return: tensor(248.3042, device='cuda:0')
episode: 59 training return: tensor(266.1197, device='cuda:0')
epoch: 15 test_true_pfm: 3280.5518741073083 sim_pfm: 9.296556197174747
episode: 60 training return: tensor(320.1308, device='cuda:0')
episode: 61 training return: tensor(-207.4451, device='cuda:0')
episode: 62 training return: tensor(202.8911, device='cuda:0')
episode: 63 training return: tensor(264.8247, device='cuda:0')
epoch: 16 test_true_pfm: 3188.6397447297873 sim_pfm: 245.80838818335906
episode: 64 training return: tensor(266.9719, device='cuda:0')
episode: 65 training return: tensor(173.9010, device='cuda:0')
episode: 66 training return: tensor(313.7287, device='cuda:0')
episode: 67 training return: tensor(265.1447, device='cuda:0')
epoch: 17 test_true_pfm: 3295.6979205618445 sim_pfm: 266.9039114403616
episode: 68 training return: tensor(311.6332, device='cuda:0')
episode: 69 training return: tensor(236.2946, device='cuda:0')
episode: 70 training return: tensor(320.2694, device='cuda:0')
episode: 71 training return: tensor(288.9304, device='cuda:0')
epoch: 18 test_true_pfm: 2949.9867171845945 sim_pfm: 84.57758536962017
episode: 72 training return: tensor(-126.6959, device='cuda:0')
episode: 73 training return: tensor(326.5694, device='cuda:0')
episode: 74 training return: tensor(186.5917, device='cuda:0')
episode: 75 training return: tensor(243.6204, device='cuda:0')
epoch: 19 test_true_pfm: 3315.293779574258 sim_pfm: 281.737056935468
episode: 76 training return: tensor(225.6824, device='cuda:0')
episode: 77 training return: tensor(-150.0258, device='cuda:0')
episode: 78 training return: tensor(242.5559, device='cuda:0')
episode: 79 training return: tensor(260.9473, device='cuda:0')
epoch: 20 test_true_pfm: 3341.9326634229474 sim_pfm: 50.41416906842884
episode: 80 training return: tensor(260.9173, device='cuda:0')
episode: 81 training return: tensor(211.8675, device='cuda:0')
episode: 82 training return: tensor(212.5717, device='cuda:0')
episode: 83 training return: tensor(-61.7803, device='cuda:0')
epoch: 21 test_true_pfm: 3275.963236322987 sim_pfm: 264.7201724088518
episode: 84 training return: tensor(165.7251, device='cuda:0')
episode: 85 training return: tensor(-159.2688, device='cuda:0')
episode: 86 training return: tensor(71.1728, device='cuda:0')
episode: 87 training return: tensor(168.0410, device='cuda:0')
epoch: 22 test_true_pfm: 3280.6252607935444 sim_pfm: 244.4265170787306
episode: 88 training return: tensor(-169.9131, device='cuda:0')
episode: 89 training return: tensor(210.9093, device='cuda:0')
episode: 90 training return: tensor(265.4841, device='cuda:0')
episode: 91 training return: tensor(70.4767, device='cuda:0')
epoch: 23 test_true_pfm: 2784.3453667627996 sim_pfm: 287.8936111848452
episode: 92 training return: tensor(299.1606, device='cuda:0')
episode: 93 training return: tensor(204.2327, device='cuda:0')
episode: 94 training return: tensor(70.9361, device='cuda:0')
episode: 95 training return: tensor(331.1394, device='cuda:0')
epoch: 24 test_true_pfm: 2905.5051742902397 sim_pfm: 264.15604416580754
episode: 96 training return: tensor(223.8678, device='cuda:0')
episode: 97 training return: tensor(243.5787, device='cuda:0')
episode: 98 training return: tensor(299.4633, device='cuda:0')
episode: 99 training return: tensor(293.4055, device='cuda:0')
epoch: 25 test_true_pfm: 3333.926746914625 sim_pfm: 246.93579848174704
episode: 100 training return: tensor(-148.7079, device='cuda:0')
episode: 101 training return: tensor(274.9454, device='cuda:0')
episode: 102 training return: tensor(58.8199, device='cuda:0')
episode: 103 training return: tensor(297.9755, device='cuda:0')
epoch: 26 test_true_pfm: 3035.953913159386 sim_pfm: -169.4508341632512
episode: 104 training return: tensor(-129.2196, device='cuda:0')
episode: 105 training return: tensor(351.8194, device='cuda:0')
episode: 106 training return: tensor(319.5886, device='cuda:0')
episode: 107 training return: tensor(323.5672, device='cuda:0')
epoch: 27 test_true_pfm: 3034.4830742466056 sim_pfm: 77.88236643806643
episode: 108 training return: tensor(-180.9947, device='cuda:0')
episode: 109 training return: tensor(-168.8515, device='cuda:0')
episode: 110 training return: tensor(335.7683, device='cuda:0')
episode: 111 training return: tensor(247.9286, device='cuda:0')
epoch: 28 test_true_pfm: 2475.6607124347065 sim_pfm: 312.3688527140378
episode: 112 training return: tensor(237.0948, device='cuda:0')
episode: 113 training return: tensor(-157.3814, device='cuda:0')
episode: 114 training return: tensor(-171.0196, device='cuda:0')
episode: 115 training return: tensor(-217.1336, device='cuda:0')
epoch: 29 test_true_pfm: 3263.1987288399027 sim_pfm: 303.0656302018906
episode: 116 training return: tensor(-165.9275, device='cuda:0')
episode: 117 training return: tensor(117.0826, device='cuda:0')
episode: 118 training return: tensor(308.8109, device='cuda:0')
episode: 119 training return: tensor(-302.9148, device='cuda:0')
epoch: 30 test_true_pfm: 3188.344654996555 sim_pfm: 101.9964390854002
episode: 120 training return: tensor(33.4392, device='cuda:0')
episode: 121 training return: tensor(257.8829, device='cuda:0')
episode: 122 training return: tensor(-290.8284, device='cuda:0')
episode: 123 training return: tensor(-120.6963, device='cuda:0')
epoch: 31 test_true_pfm: 3280.493387017407 sim_pfm: -32.07501611552046
episode: 124 training return: tensor(274.0891, device='cuda:0')
episode: 125 training return: tensor(-22.3279, device='cuda:0')
episode: 126 training return: tensor(206.7788, device='cuda:0')
episode: 127 training return: tensor(351.2718, device='cuda:0')
epoch: 32 test_true_pfm: 3280.8412340980703 sim_pfm: -30.518498540817138
episode: 128 training return: tensor(281.8098, device='cuda:0')
episode: 129 training return: tensor(273.9628, device='cuda:0')
episode: 130 training return: tensor(316.9479, device='cuda:0')
episode: 131 training return: tensor(-78.9178, device='cuda:0')
epoch: 33 test_true_pfm: 2987.1368678668955 sim_pfm: 339.3765683841775
episode: 132 training return: tensor(322.2305, device='cuda:0')
episode: 133 training return: tensor(-257.0834, device='cuda:0')
episode: 134 training return: tensor(-11.8583, device='cuda:0')
episode: 135 training return: tensor(-185.6044, device='cuda:0')
epoch: 34 test_true_pfm: 2438.5495673478827 sim_pfm: 128.4760668669284
episode: 136 training return: tensor(-102.2770, device='cuda:0')
episode: 137 training return: tensor(-173.8914, device='cuda:0')
episode: 138 training return: tensor(293.7745, device='cuda:0')
episode: 139 training return: tensor(341.0184, device='cuda:0')
epoch: 35 test_true_pfm: 3369.168246512752 sim_pfm: 35.02424313832307
episode: 140 training return: tensor(252.7881, device='cuda:0')
episode: 141 training return: tensor(247.7741, device='cuda:0')
episode: 142 training return: tensor(321.7975, device='cuda:0')
episode: 143 training return: tensor(49.2255, device='cuda:0')
epoch: 36 test_true_pfm: 2391.943548694861 sim_pfm: -32.354923363406364
episode: 144 training return: tensor(326.0813, device='cuda:0')
episode: 145 training return: tensor(275.1738, device='cuda:0')
episode: 146 training return: tensor(318.4485, device='cuda:0')
episode: 147 training return: tensor(269.3892, device='cuda:0')
epoch: 37 test_true_pfm: 2773.9152343434575 sim_pfm: 4.626049468449007
episode: 148 training return: tensor(-288.3970, device='cuda:0')
episode: 149 training return: tensor(305.5714, device='cuda:0')
episode: 150 training return: tensor(388.5431, device='cuda:0')
episode: 151 training return: tensor(287.4491, device='cuda:0')
epoch: 38 test_true_pfm: 3131.2751184388762 sim_pfm: 158.9541804989276
episode: 152 training return: tensor(284.3669, device='cuda:0')
episode: 153 training return: tensor(133.9569, device='cuda:0')
episode: 154 training return: tensor(320.8092, device='cuda:0')
episode: 155 training return: tensor(286.9205, device='cuda:0')
epoch: 39 test_true_pfm: 1773.2256749275364 sim_pfm: 318.1816804658641
episode: 156 training return: tensor(348.3316, device='cuda:0')
episode: 157 training return: tensor(315.1042, device='cuda:0')
episode: 158 training return: tensor(40.9961, device='cuda:0')
episode: 159 training return: tensor(354.8069, device='cuda:0')
epoch: 40 test_true_pfm: 3240.2456716845095 sim_pfm: 301.13915949467145
episode: 160 training return: tensor(252.9288, device='cuda:0')
episode: 161 training return: tensor(352.5686, device='cuda:0')
episode: 162 training return: tensor(322.8864, device='cuda:0')
episode: 163 training return: tensor(299.1172, device='cuda:0')
epoch: 41 test_true_pfm: 3222.0541889443243 sim_pfm: 238.2028726564216
episode: 164 training return: tensor(-60.5707, device='cuda:0')
episode: 165 training return: tensor(-95.9902, device='cuda:0')
episode: 166 training return: tensor(279.1221, device='cuda:0')
episode: 167 training return: tensor(385.2614, device='cuda:0')
epoch: 42 test_true_pfm: 2885.8288810152094 sim_pfm: 284.7672243412623
episode: 168 training return: tensor(-259.7415, device='cuda:0')
episode: 169 training return: tensor(295.3873, device='cuda:0')
episode: 170 training return: tensor(234.0779, device='cuda:0')
episode: 171 training return: tensor(345.3398, device='cuda:0')
epoch: 43 test_true_pfm: 3324.2979580942847 sim_pfm: 313.18436821668485
episode: 172 training return: tensor(282.6041, device='cuda:0')
episode: 173 training return: tensor(115.4022, device='cuda:0')
episode: 174 training return: tensor(33.8690, device='cuda:0')
episode: 175 training return: tensor(229.9210, device='cuda:0')
epoch: 44 test_true_pfm: 2893.0591295911363 sim_pfm: 104.11079988188187
episode: 176 training return: tensor(-156.9189, device='cuda:0')
episode: 177 training return: tensor(331.7753, device='cuda:0')
episode: 178 training return: tensor(-251.2329, device='cuda:0')
episode: 179 training return: tensor(332.5598, device='cuda:0')
epoch: 45 test_true_pfm: 3265.629321596085 sim_pfm: 66.15321550304846
episode: 180 training return: tensor(337.1327, device='cuda:0')
episode: 181 training return: tensor(192.3537, device='cuda:0')
episode: 182 training return: tensor(13.1089, device='cuda:0')
episode: 183 training return: tensor(276.9037, device='cuda:0')
epoch: 46 test_true_pfm: 3265.613009621941 sim_pfm: 126.19810494923149
episode: 184 training return: tensor(177.5234, device='cuda:0')
episode: 185 training return: tensor(282.4744, device='cuda:0')
episode: 186 training return: tensor(228.2996, device='cuda:0')
episode: 187 training return: tensor(326.0294, device='cuda:0')
epoch: 47 test_true_pfm: 3305.134624755168 sim_pfm: 295.5329523993035
episode: 188 training return: tensor(289.1226, device='cuda:0')
episode: 189 training return: tensor(320.9811, device='cuda:0')
episode: 190 training return: tensor(302.1820, device='cuda:0')
episode: 191 training return: tensor(318.9782, device='cuda:0')
epoch: 48 test_true_pfm: 3050.4406144697623 sim_pfm: 89.33400299490313
episode: 192 training return: tensor(232.7267, device='cuda:0')
episode: 193 training return: tensor(101.6103, device='cuda:0')
episode: 194 training return: tensor(200.1767, device='cuda:0')
episode: 195 training return: tensor(257.9801, device='cuda:0')
epoch: 49 test_true_pfm: 3257.7885466442913 sim_pfm: -50.04255150957033
episode: 196 training return: tensor(39.6359, device='cuda:0')
episode: 197 training return: tensor(170.4600, device='cuda:0')
episode: 198 training return: tensor(303.1137, device='cuda:0')
episode: 199 training return: tensor(306.5890, device='cuda:0')
epoch: 50 test_true_pfm: 2882.3465831953486 sim_pfm: 168.68110960535705
episode: 200 training return: tensor(302.7365, device='cuda:0')
episode: 201 training return: tensor(280.5924, device='cuda:0')
episode: 202 training return: tensor(-93.0185, device='cuda:0')
episode: 203 training return: tensor(-95.7058, device='cuda:0')
epoch: 51 test_true_pfm: 2218.81740622418 sim_pfm: 311.2549822224537
episode: 204 training return: tensor(271.5037, device='cuda:0')
episode: 205 training return: tensor(256.3909, device='cuda:0')
episode: 206 training return: tensor(215.3680, device='cuda:0')
episode: 207 training return: tensor(272.9662, device='cuda:0')
epoch: 52 test_true_pfm: 2813.2719536762474 sim_pfm: 276.8765111140286
episode: 208 training return: tensor(343.0963, device='cuda:0')
episode: 209 training return: tensor(-189.8380, device='cuda:0')
episode: 210 training return: tensor(292.2351, device='cuda:0')
episode: 211 training return: tensor(252.2796, device='cuda:0')
epoch: 53 test_true_pfm: 3321.8763589821333 sim_pfm: 310.913906265186
episode: 212 training return: tensor(273.5426, device='cuda:0')
episode: 213 training return: tensor(243.8394, device='cuda:0')
episode: 214 training return: tensor(279.5596, device='cuda:0')
episode: 215 training return: tensor(310.8117, device='cuda:0')
epoch: 54 test_true_pfm: 3112.051402972025 sim_pfm: 196.429864263715
episode: 216 training return: tensor(329.3452, device='cuda:0')
episode: 217 training return: tensor(217.5327, device='cuda:0')
episode: 218 training return: tensor(291.2146, device='cuda:0')
episode: 219 training return: tensor(272.3365, device='cuda:0')
epoch: 55 test_true_pfm: 3228.1786459316904 sim_pfm: 313.45812140768976
episode: 220 training return: tensor(245.9966, device='cuda:0')
episode: 221 training return: tensor(-20.3922, device='cuda:0')
episode: 222 training return: tensor(283.1295, device='cuda:0')
episode: 223 training return: tensor(327.7128, device='cuda:0')
epoch: 56 test_true_pfm: 3402.233925861219 sim_pfm: 249.67835650989824
episode: 224 training return: tensor(286.4632, device='cuda:0')
episode: 225 training return: tensor(-144.1897, device='cuda:0')
episode: 226 training return: tensor(277.1880, device='cuda:0')
episode: 227 training return: tensor(-143.5482, device='cuda:0')
epoch: 57 test_true_pfm: 2816.373059790107 sim_pfm: 244.57920436629016
episode: 228 training return: tensor(345.3285, device='cuda:0')
episode: 229 training return: tensor(-122.7486, device='cuda:0')
episode: 230 training return: tensor(-3.1876, device='cuda:0')
episode: 231 training return: tensor(324.4880, device='cuda:0')
epoch: 58 test_true_pfm: 3108.891847112312 sim_pfm: 328.48695386280696
episode: 232 training return: tensor(339.2166, device='cuda:0')
episode: 233 training return: tensor(345.1365, device='cuda:0')
episode: 234 training return: tensor(-119.5788, device='cuda:0')
episode: 235 training return: tensor(-113.3892, device='cuda:0')
epoch: 59 test_true_pfm: 2645.1009284003253 sim_pfm: 194.31811979960185
episode: 236 training return: tensor(232.6070, device='cuda:0')
episode: 237 training return: tensor(375.1339, device='cuda:0')
episode: 238 training return: tensor(322.3860, device='cuda:0')
episode: 239 training return: tensor(256.4460, device='cuda:0')
epoch: 60 test_true_pfm: 2730.1840196346625 sim_pfm: 275.1751483863045
episode: 240 training return: tensor(324.5715, device='cuda:0')
episode: 241 training return: tensor(230.5678, device='cuda:0')
episode: 242 training return: tensor(341.8997, device='cuda:0')
episode: 243 training return: tensor(255.4062, device='cuda:0')
epoch: 61 test_true_pfm: 2800.566900980542 sim_pfm: 179.1970101253537
episode: 244 training return: tensor(255.4947, device='cuda:0')
episode: 245 training return: tensor(287.1819, device='cuda:0')
episode: 246 training return: tensor(-131.8143, device='cuda:0')
episode: 247 training return: tensor(253.2892, device='cuda:0')
epoch: 62 test_true_pfm: 3063.3437380716423 sim_pfm: 333.24356120429
episode: 248 training return: tensor(-156.2200, device='cuda:0')
episode: 249 training return: tensor(305.2913, device='cuda:0')
episode: 250 training return: tensor(214.6304, device='cuda:0')
episode: 251 training return: tensor(193.1999, device='cuda:0')
epoch: 63 test_true_pfm: 2867.897252224239 sim_pfm: 112.86327235990514
episode: 252 training return: tensor(324.3192, device='cuda:0')
episode: 253 training return: tensor(198.5611, device='cuda:0')
episode: 254 training return: tensor(-101.3800, device='cuda:0')
episode: 255 training return: tensor(-126.1050, device='cuda:0')
epoch: 64 test_true_pfm: 3363.4741821508273 sim_pfm: 266.2648809500194
episode: 256 training return: tensor(310.7459, device='cuda:0')
episode: 257 training return: tensor(272.1670, device='cuda:0')
episode: 258 training return: tensor(-232.0555, device='cuda:0')
episode: 259 training return: tensor(325.1008, device='cuda:0')
epoch: 65 test_true_pfm: 3082.6436703497698 sim_pfm: 254.4188599315239
episode: 260 training return: tensor(245.1916, device='cuda:0')
episode: 261 training return: tensor(-210.1903, device='cuda:0')
episode: 262 training return: tensor(-151.8356, device='cuda:0')
episode: 263 training return: tensor(295.7839, device='cuda:0')
epoch: 66 test_true_pfm: 2734.9034483462256 sim_pfm: 260.5584054593055
episode: 264 training return: tensor(290.7054, device='cuda:0')
episode: 265 training return: tensor(260.9668, device='cuda:0')
episode: 266 training return: tensor(-56.8524, device='cuda:0')
episode: 267 training return: tensor(-142.7979, device='cuda:0')
epoch: 67 test_true_pfm: 3354.621544421861 sim_pfm: 315.3814353274647
episode: 268 training return: tensor(278.6702, device='cuda:0')
episode: 269 training return: tensor(228.7695, device='cuda:0')
episode: 270 training return: tensor(273.1443, device='cuda:0')
episode: 271 training return: tensor(301.0449, device='cuda:0')
epoch: 68 test_true_pfm: 3221.9075860020116 sim_pfm: 256.0418354210463
episode: 272 training return: tensor(-161.3298, device='cuda:0')
episode: 273 training return: tensor(-137.2966, device='cuda:0')
episode: 274 training return: tensor(13.9968, device='cuda:0')
episode: 275 training return: tensor(-254.9831, device='cuda:0')
epoch: 69 test_true_pfm: 3028.9873634274295 sim_pfm: 278.73034057189943
episode: 276 training return: tensor(315.7402, device='cuda:0')
episode: 277 training return: tensor(317.6529, device='cuda:0')
episode: 278 training return: tensor(273.7363, device='cuda:0')
episode: 279 training return: tensor(266.3935, device='cuda:0')
epoch: 70 test_true_pfm: 2595.9926627573577 sim_pfm: 321.0301416988077
episode: 280 training return: tensor(315.7003, device='cuda:0')
episode: 281 training return: tensor(43.1988, device='cuda:0')
episode: 282 training return: tensor(185.0175, device='cuda:0')
episode: 283 training return: tensor(-75.6469, device='cuda:0')
epoch: 71 test_true_pfm: 2794.0609736351694 sim_pfm: 204.40247794679212
episode: 284 training return: tensor(266.6975, device='cuda:0')
episode: 285 training return: tensor(309.0893, device='cuda:0')
episode: 286 training return: tensor(97.3526, device='cuda:0')
episode: 287 training return: tensor(298.1250, device='cuda:0')
epoch: 72 test_true_pfm: 2427.2673743493947 sim_pfm: 120.48366008682449
episode: 288 training return: tensor(108.0959, device='cuda:0')
episode: 289 training return: tensor(-102.1025, device='cuda:0')
episode: 290 training return: tensor(282.8177, device='cuda:0')
episode: 291 training return: tensor(303.1773, device='cuda:0')
epoch: 73 test_true_pfm: 3254.9849630863137 sim_pfm: 253.65377490857887
episode: 292 training return: tensor(238.0760, device='cuda:0')
episode: 293 training return: tensor(-122.2337, device='cuda:0')
episode: 294 training return: tensor(359.4938, device='cuda:0')
episode: 295 training return: tensor(294.1061, device='cuda:0')
epoch: 74 test_true_pfm: 3347.8517529622313 sim_pfm: 204.0674407047142
episode: 296 training return: tensor(301.7136, device='cuda:0')
episode: 297 training return: tensor(262.1773, device='cuda:0')
episode: 298 training return: tensor(210.0797, device='cuda:0')
episode: 299 training return: tensor(288.3176, device='cuda:0')
epoch: 75 test_true_pfm: 3302.414572113943 sim_pfm: 230.84101417052443
episode: 300 training return: tensor(-246.7836, device='cuda:0')
episode: 301 training return: tensor(311.6990, device='cuda:0')
episode: 302 training return: tensor(335.2382, device='cuda:0')
episode: 303 training return: tensor(79.5732, device='cuda:0')
epoch: 76 test_true_pfm: 3284.080751419804 sim_pfm: 203.40905058013354
episode: 304 training return: tensor(221.9588, device='cuda:0')
episode: 305 training return: tensor(326.6017, device='cuda:0')
episode: 306 training return: tensor(-76.6943, device='cuda:0')
episode: 307 training return: tensor(302.5191, device='cuda:0')
epoch: 77 test_true_pfm: 3304.3116789255087 sim_pfm: 220.17456485483368
episode: 308 training return: tensor(297.4796, device='cuda:0')
episode: 309 training return: tensor(1.6791, device='cuda:0')
episode: 310 training return: tensor(-57.4182, device='cuda:0')
episode: 311 training return: tensor(267.4478, device='cuda:0')
epoch: 78 test_true_pfm: 3022.557349305018 sim_pfm: 171.80039830697933
episode: 312 training return: tensor(251.1709, device='cuda:0')
episode: 313 training return: tensor(-258.6602, device='cuda:0')
episode: 314 training return: tensor(-236.8497, device='cuda:0')
episode: 315 training return: tensor(257.1994, device='cuda:0')
epoch: 79 test_true_pfm: 3147.3369881097406 sim_pfm: 275.0647368246088
episode: 316 training return: tensor(187.8356, device='cuda:0')
episode: 317 training return: tensor(337.6727, device='cuda:0')
episode: 318 training return: tensor(367.9239, device='cuda:0')
episode: 319 training return: tensor(111.3710, device='cuda:0')
epoch: 80 test_true_pfm: 2315.8393001857385 sim_pfm: 173.9620761370849
episode: 320 training return: tensor(281.5207, device='cuda:0')
episode: 321 training return: tensor(345.3354, device='cuda:0')
episode: 322 training return: tensor(312.1406, device='cuda:0')
episode: 323 training return: tensor(-277.0956, device='cuda:0')
epoch: 81 test_true_pfm: 2549.6505266042273 sim_pfm: 52.860636685140584
episode: 324 training return: tensor(308.5995, device='cuda:0')
episode: 325 training return: tensor(292.9833, device='cuda:0')
episode: 326 training return: tensor(329.1155, device='cuda:0')
episode: 327 training return: tensor(-243.0137, device='cuda:0')
epoch: 82 test_true_pfm: 3334.7559029421463 sim_pfm: 198.48544401161294
episode: 328 training return: tensor(-146.7504, device='cuda:0')
episode: 329 training return: tensor(-140.4627, device='cuda:0')
episode: 330 training return: tensor(283.3071, device='cuda:0')
episode: 331 training return: tensor(235.9302, device='cuda:0')
epoch: 83 test_true_pfm: 3252.1996605339978 sim_pfm: 8.538374899023134
episode: 332 training return: tensor(249.9312, device='cuda:0')
episode: 333 training return: tensor(189.2677, device='cuda:0')
episode: 334 training return: tensor(-221.8649, device='cuda:0')
episode: 335 training return: tensor(255.6288, device='cuda:0')
epoch: 84 test_true_pfm: 3280.7693865166407 sim_pfm: 47.89045597050184
episode: 336 training return: tensor(302.2018, device='cuda:0')
episode: 337 training return: tensor(297.2440, device='cuda:0')
episode: 338 training return: tensor(300.9572, device='cuda:0')
episode: 339 training return: tensor(-16.9117, device='cuda:0')
epoch: 85 test_true_pfm: 3118.0583696842896 sim_pfm: 318.9372108196646
episode: 340 training return: tensor(358.7070, device='cuda:0')
episode: 341 training return: tensor(354.3137, device='cuda:0')
episode: 342 training return: tensor(290.0197, device='cuda:0')
episode: 343 training return: tensor(-238.7175, device='cuda:0')
epoch: 86 test_true_pfm: 3327.0804953229713 sim_pfm: 305.2651560199059
episode: 344 training return: tensor(365.2955, device='cuda:0')
episode: 345 training return: tensor(330.3604, device='cuda:0')
episode: 346 training return: tensor(-213.3496, device='cuda:0')
episode: 347 training return: tensor(309.2480, device='cuda:0')
epoch: 87 test_true_pfm: 3298.326603678379 sim_pfm: 92.97883957196609
episode: 348 training return: tensor(201.5537, device='cuda:0')
episode: 349 training return: tensor(346.7907, device='cuda:0')
episode: 350 training return: tensor(159.2745, device='cuda:0')
episode: 351 training return: tensor(202.1466, device='cuda:0')
epoch: 88 test_true_pfm: 2754.099976292564 sim_pfm: 234.66966740691956
episode: 352 training return: tensor(-71.9023, device='cuda:0')
episode: 353 training return: tensor(-216.8148, device='cuda:0')
episode: 354 training return: tensor(-191.0253, device='cuda:0')
episode: 355 training return: tensor(56.9196, device='cuda:0')
epoch: 89 test_true_pfm: 2459.2820565790685 sim_pfm: 269.9906184792053
episode: 356 training return: tensor(-138.7388, device='cuda:0')
episode: 357 training return: tensor(-55.4432, device='cuda:0')
episode: 358 training return: tensor(216.5176, device='cuda:0')
episode: 359 training return: tensor(248.0946, device='cuda:0')
epoch: 90 test_true_pfm: 2852.102345539493 sim_pfm: 257.7742015755891
episode: 360 training return: tensor(184.6103, device='cuda:0')
episode: 361 training return: tensor(272.0153, device='cuda:0')
episode: 362 training return: tensor(270.0443, device='cuda:0')
episode: 363 training return: tensor(-258.0560, device='cuda:0')
epoch: 91 test_true_pfm: 2884.704221446668 sim_pfm: 335.05362110010657
episode: 364 training return: tensor(309.6934, device='cuda:0')
episode: 365 training return: tensor(257.7722, device='cuda:0')
episode: 366 training return: tensor(-182.4586, device='cuda:0')
episode: 367 training return: tensor(-0.9630, device='cuda:0')
epoch: 92 test_true_pfm: 3331.332661351274 sim_pfm: 307.2812664059068
episode: 368 training return: tensor(299.2348, device='cuda:0')
episode: 369 training return: tensor(351.2646, device='cuda:0')
episode: 370 training return: tensor(351.6126, device='cuda:0')
episode: 371 training return: tensor(167.1999, device='cuda:0')
epoch: 93 test_true_pfm: 3195.5636217237698 sim_pfm: 275.3628696855546
episode: 372 training return: tensor(292.8719, device='cuda:0')
episode: 373 training return: tensor(150.4485, device='cuda:0')
episode: 374 training return: tensor(342.4426, device='cuda:0')
episode: 375 training return: tensor(-223.5144, device='cuda:0')
epoch: 94 test_true_pfm: 3334.206668178477 sim_pfm: 299.0972797999372
episode: 376 training return: tensor(304.6647, device='cuda:0')
episode: 377 training return: tensor(267.8434, device='cuda:0')
episode: 378 training return: tensor(309.8211, device='cuda:0')
episode: 379 training return: tensor(295.6177, device='cuda:0')
epoch: 95 test_true_pfm: 2895.6672153044965 sim_pfm: 178.5268042794778
episode: 380 training return: tensor(305.7721, device='cuda:0')
episode: 381 training return: tensor(264.5065, device='cuda:0')
episode: 382 training return: tensor(141.7144, device='cuda:0')
episode: 383 training return: tensor(245.1674, device='cuda:0')
epoch: 96 test_true_pfm: 3256.521380912309 sim_pfm: 139.88194635519176
episode: 384 training return: tensor(288.8667, device='cuda:0')
episode: 385 training return: tensor(333.8464, device='cuda:0')
episode: 386 training return: tensor(-152.2439, device='cuda:0')
episode: 387 training return: tensor(269.0298, device='cuda:0')
epoch: 97 test_true_pfm: 3308.6704344629266 sim_pfm: 314.83688467543107
episode: 388 training return: tensor(-135.2021, device='cuda:0')
episode: 389 training return: tensor(-199.7587, device='cuda:0')
episode: 390 training return: tensor(308.9415, device='cuda:0')
episode: 391 training return: tensor(311.5714, device='cuda:0')
epoch: 98 test_true_pfm: 2370.163348557671 sim_pfm: 260.31801600783365
episode: 392 training return: tensor(240.9897, device='cuda:0')
episode: 393 training return: tensor(319.6688, device='cuda:0')
episode: 394 training return: tensor(243.2753, device='cuda:0')
episode: 395 training return: tensor(325.6018, device='cuda:0')
epoch: 99 test_true_pfm: 2489.831614593299 sim_pfm: 311.1235435316824
episode: 396 training return: tensor(265.2970, device='cuda:0')
episode: 397 training return: tensor(264.2677, device='cuda:0')
episode: 398 training return: tensor(291.6878, device='cuda:0')
episode: 399 training return: tensor(133.7426, device='cuda:0')
epoch: 100 test_true_pfm: 3337.1284987418258 sim_pfm: 158.2643854226626
episode: 400 training return: tensor(414.6319, device='cuda:0')
episode: 401 training return: tensor(285.5399, device='cuda:0')
episode: 402 training return: tensor(-291.6880, device='cuda:0')
episode: 403 training return: tensor(313.5158, device='cuda:0')
epoch: 101 test_true_pfm: 3092.320084919162 sim_pfm: 193.25203489516085
episode: 404 training return: tensor(111.2350, device='cuda:0')
episode: 405 training return: tensor(291.1638, device='cuda:0')
episode: 406 training return: tensor(257.3471, device='cuda:0')
episode: 407 training return: tensor(-175.3852, device='cuda:0')
epoch: 102 test_true_pfm: 2979.289054740591 sim_pfm: -62.14277110095524
episode: 408 training return: tensor(239.6710, device='cuda:0')
episode: 409 training return: tensor(107.0115, device='cuda:0')
episode: 410 training return: tensor(192.6551, device='cuda:0')
episode: 411 training return: tensor(195.0388, device='cuda:0')
epoch: 103 test_true_pfm: 3317.383106876255 sim_pfm: 298.8266801689945
episode: 412 training return: tensor(303.8106, device='cuda:0')
episode: 413 training return: tensor(242.6811, device='cuda:0')
episode: 414 training return: tensor(285.4045, device='cuda:0')
episode: 415 training return: tensor(300.0120, device='cuda:0')
epoch: 104 test_true_pfm: 3265.2721494985694 sim_pfm: 182.47219070375044
episode: 416 training return: tensor(308.7916, device='cuda:0')
episode: 417 training return: tensor(322.1342, device='cuda:0')
episode: 418 training return: tensor(292.8209, device='cuda:0')
episode: 419 training return: tensor(292.9688, device='cuda:0')
epoch: 105 test_true_pfm: 3323.585330138792 sim_pfm: 266.65423788531916
episode: 420 training return: tensor(-192.0551, device='cuda:0')
episode: 421 training return: tensor(351.2218, device='cuda:0')
episode: 422 training return: tensor(-78.6786, device='cuda:0')
episode: 423 training return: tensor(-173.5947, device='cuda:0')
epoch: 106 test_true_pfm: 3332.8996950010023 sim_pfm: 166.1827664800318
episode: 424 training return: tensor(-151.1902, device='cuda:0')
episode: 425 training return: tensor(334.3739, device='cuda:0')
episode: 426 training return: tensor(193.2417, device='cuda:0')
episode: 427 training return: tensor(332.5844, device='cuda:0')
epoch: 107 test_true_pfm: 3299.193145015955 sim_pfm: 305.9279362442321
episode: 428 training return: tensor(-45.5636, device='cuda:0')
episode: 429 training return: tensor(-64.8901, device='cuda:0')
episode: 430 training return: tensor(365.1700, device='cuda:0')
episode: 431 training return: tensor(-148.8005, device='cuda:0')
epoch: 108 test_true_pfm: 3381.0276556839067 sim_pfm: 195.44025928368015
episode: 432 training return: tensor(-154.4178, device='cuda:0')
episode: 433 training return: tensor(165.9310, device='cuda:0')
episode: 434 training return: tensor(323.5133, device='cuda:0')
episode: 435 training return: tensor(238.0764, device='cuda:0')
epoch: 109 test_true_pfm: 3329.4318135903172 sim_pfm: 312.4999562953114
episode: 436 training return: tensor(293.3617, device='cuda:0')
episode: 437 training return: tensor(-10.0554, device='cuda:0')
episode: 438 training return: tensor(354.2845, device='cuda:0')
episode: 439 training return: tensor(-262.3908, device='cuda:0')
epoch: 110 test_true_pfm: 3195.3000548678106 sim_pfm: 312.3542861569052
episode: 440 training return: tensor(269.9510, device='cuda:0')
episode: 441 training return: tensor(327.8185, device='cuda:0')
episode: 442 training return: tensor(246.0576, device='cuda:0')
episode: 443 training return: tensor(354.4641, device='cuda:0')
epoch: 111 test_true_pfm: 2598.7073244540984 sim_pfm: 0.944099807064049
episode: 444 training return: tensor(281.2340, device='cuda:0')
episode: 445 training return: tensor(-282.9793, device='cuda:0')
episode: 446 training return: tensor(37.0429, device='cuda:0')
episode: 447 training return: tensor(313.6517, device='cuda:0')
epoch: 112 test_true_pfm: 2992.898123495652 sim_pfm: 146.10704055432385
episode: 448 training return: tensor(199.2147, device='cuda:0')
episode: 449 training return: tensor(256.2086, device='cuda:0')
episode: 450 training return: tensor(297.0767, device='cuda:0')
episode: 451 training return: tensor(312.0693, device='cuda:0')
epoch: 113 test_true_pfm: 2711.5071385092183 sim_pfm: 205.01750672920994
episode: 452 training return: tensor(16.6341, device='cuda:0')
episode: 453 training return: tensor(-25.2771, device='cuda:0')
episode: 454 training return: tensor(-129.1221, device='cuda:0')
episode: 455 training return: tensor(248.6875, device='cuda:0')
epoch: 114 test_true_pfm: 3283.9188198921124 sim_pfm: 273.4013778240672
episode: 456 training return: tensor(277.1117, device='cuda:0')
episode: 457 training return: tensor(238.5951, device='cuda:0')
episode: 458 training return: tensor(120.3952, device='cuda:0')
episode: 459 training return: tensor(-208.0406, device='cuda:0')
epoch: 115 test_true_pfm: 3270.3443732830833 sim_pfm: 295.355492946653
episode: 460 training return: tensor(321.2731, device='cuda:0')
episode: 461 training return: tensor(217.1798, device='cuda:0')
episode: 462 training return: tensor(263.5178, device='cuda:0')
episode: 463 training return: tensor(314.7808, device='cuda:0')
epoch: 116 test_true_pfm: 2673.816408068429 sim_pfm: -40.74541262178294
episode: 464 training return: tensor(-338.1452, device='cuda:0')
episode: 465 training return: tensor(354.3024, device='cuda:0')
episode: 466 training return: tensor(331.5879, device='cuda:0')
episode: 467 training return: tensor(170.4474, device='cuda:0')
epoch: 117 test_true_pfm: 1917.7665673423608 sim_pfm: 254.04014879827932
episode: 468 training return: tensor(283.6468, device='cuda:0')
episode: 469 training return: tensor(-204.5126, device='cuda:0')
episode: 470 training return: tensor(304.2118, device='cuda:0')
episode: 471 training return: tensor(257.7219, device='cuda:0')
epoch: 118 test_true_pfm: 3282.842805668355 sim_pfm: 311.55903508589836
episode: 472 training return: tensor(-123.3522, device='cuda:0')
episode: 473 training return: tensor(333.0567, device='cuda:0')
episode: 474 training return: tensor(310.0789, device='cuda:0')
episode: 475 training return: tensor(-161.2313, device='cuda:0')
epoch: 119 test_true_pfm: 3249.3684785129026 sim_pfm: -87.84673114705947
episode: 476 training return: tensor(270.7014, device='cuda:0')
episode: 477 training return: tensor(-17.8725, device='cuda:0')
episode: 478 training return: tensor(294.3075, device='cuda:0')
episode: 479 training return: tensor(-327.0757, device='cuda:0')
epoch: 120 test_true_pfm: 3328.000012480541 sim_pfm: 281.7226445464864
episode: 480 training return: tensor(339.1020, device='cuda:0')
episode: 481 training return: tensor(-273.5800, device='cuda:0')
episode: 482 training return: tensor(347.2388, device='cuda:0')
episode: 483 training return: tensor(286.6637, device='cuda:0')
epoch: 121 test_true_pfm: 3165.247574582047 sim_pfm: 232.78896385685462
episode: 484 training return: tensor(391.3679, device='cuda:0')
episode: 485 training return: tensor(-290.0537, device='cuda:0')
episode: 486 training return: tensor(-169.1326, device='cuda:0')
episode: 487 training return: tensor(266.5826, device='cuda:0')
epoch: 122 test_true_pfm: 3334.089257798514 sim_pfm: 311.4206954764086
episode: 488 training return: tensor(293.2836, device='cuda:0')
episode: 489 training return: tensor(268.5820, device='cuda:0')
episode: 490 training return: tensor(310.2607, device='cuda:0')
episode: 491 training return: tensor(278.6810, device='cuda:0')
epoch: 123 test_true_pfm: 3036.075989532608 sim_pfm: 165.78324205602016
episode: 492 training return: tensor(240.7847, device='cuda:0')
episode: 493 training return: tensor(257.1429, device='cuda:0')
episode: 494 training return: tensor(291.2236, device='cuda:0')
episode: 495 training return: tensor(305.0653, device='cuda:0')
epoch: 124 test_true_pfm: 2887.7794053193434 sim_pfm: 304.1887815610583
episode: 496 training return: tensor(312.3074, device='cuda:0')
episode: 497 training return: tensor(-256.2034, device='cuda:0')
episode: 498 training return: tensor(226.1019, device='cuda:0')
episode: 499 training return: tensor(304.8002, device='cuda:0')
epoch: 125 test_true_pfm: 3365.291571019723 sim_pfm: 294.3840573720324
episode: 500 training return: tensor(291.5270, device='cuda:0')
episode: 501 training return: tensor(-161.0742, device='cuda:0')
episode: 502 training return: tensor(265.0169, device='cuda:0')
episode: 503 training return: tensor(231.6052, device='cuda:0')
epoch: 126 test_true_pfm: 2906.1236280751605 sim_pfm: 296.60523257625755
episode: 504 training return: tensor(317.2427, device='cuda:0')
episode: 505 training return: tensor(268.2605, device='cuda:0')
episode: 506 training return: tensor(278.5011, device='cuda:0')
episode: 507 training return: tensor(320.5547, device='cuda:0')
epoch: 127 test_true_pfm: 3382.807501756857 sim_pfm: 287.00260795630555
episode: 508 training return: tensor(-220.4544, device='cuda:0')
episode: 509 training return: tensor(289.4686, device='cuda:0')
episode: 510 training return: tensor(369.6102, device='cuda:0')
episode: 511 training return: tensor(249.8611, device='cuda:0')
epoch: 128 test_true_pfm: 3320.1793799971397 sim_pfm: 209.39475741043375
episode: 512 training return: tensor(-112.2148, device='cuda:0')
episode: 513 training return: tensor(278.8042, device='cuda:0')
episode: 514 training return: tensor(292.9195, device='cuda:0')
episode: 515 training return: tensor(337.5174, device='cuda:0')
epoch: 129 test_true_pfm: 2864.141978912001 sim_pfm: 198.5773710378853
episode: 516 training return: tensor(312.4254, device='cuda:0')
episode: 517 training return: tensor(252.9671, device='cuda:0')
episode: 518 training return: tensor(-174.5451, device='cuda:0')
episode: 519 training return: tensor(-40.2659, device='cuda:0')
epoch: 130 test_true_pfm: 3343.4298804335194 sim_pfm: 246.80295220787715
episode: 520 training return: tensor(277.1339, device='cuda:0')
episode: 521 training return: tensor(323.7693, device='cuda:0')
episode: 522 training return: tensor(289.3398, device='cuda:0')
episode: 523 training return: tensor(187.8566, device='cuda:0')
epoch: 131 test_true_pfm: 3080.267074726502 sim_pfm: 269.9582614193884
episode: 524 training return: tensor(309.5349, device='cuda:0')
episode: 525 training return: tensor(6.2048, device='cuda:0')
episode: 526 training return: tensor(283.8879, device='cuda:0')
episode: 527 training return: tensor(302.3478, device='cuda:0')
epoch: 132 test_true_pfm: 3377.2321798463067 sim_pfm: -9.47107241032063
episode: 528 training return: tensor(301.6149, device='cuda:0')
episode: 529 training return: tensor(260.3695, device='cuda:0')
episode: 530 training return: tensor(309.9995, device='cuda:0')
episode: 531 training return: tensor(308.4317, device='cuda:0')
epoch: 133 test_true_pfm: 3398.773544090395 sim_pfm: -34.222184162121266
episode: 532 training return: tensor(-266.7610, device='cuda:0')
episode: 533 training return: tensor(343.1672, device='cuda:0')
episode: 534 training return: tensor(234.0625, device='cuda:0')
episode: 535 training return: tensor(210.0006, device='cuda:0')
epoch: 134 test_true_pfm: 3448.186036798059 sim_pfm: 83.40132506064644
episode: 536 training return: tensor(305.0145, device='cuda:0')
episode: 537 training return: tensor(106.5555, device='cuda:0')
episode: 538 training return: tensor(-58.4240, device='cuda:0')
episode: 539 training return: tensor(281.3220, device='cuda:0')
epoch: 135 test_true_pfm: 2893.9557927298033 sim_pfm: 312.7514369901328
episode: 540 training return: tensor(-39.9343, device='cuda:0')
episode: 541 training return: tensor(279.1899, device='cuda:0')
episode: 542 training return: tensor(51.7375, device='cuda:0')
episode: 543 training return: tensor(127.1783, device='cuda:0')
epoch: 136 test_true_pfm: 2800.420180744697 sim_pfm: 292.67847076429945
episode: 544 training return: tensor(322.2664, device='cuda:0')
episode: 545 training return: tensor(-9.7036, device='cuda:0')
episode: 546 training return: tensor(307.4828, device='cuda:0')
episode: 547 training return: tensor(239.5150, device='cuda:0')
epoch: 137 test_true_pfm: 2842.8265425225104 sim_pfm: 220.55806243239203
episode: 548 training return: tensor(63.0497, device='cuda:0')
episode: 549 training return: tensor(247.1076, device='cuda:0')
episode: 550 training return: tensor(317.9096, device='cuda:0')
episode: 551 training return: tensor(296.9157, device='cuda:0')
epoch: 138 test_true_pfm: 3204.2713510303897 sim_pfm: 277.4190484091329
episode: 552 training return: tensor(328.5457, device='cuda:0')
episode: 553 training return: tensor(-312.4898, device='cuda:0')
episode: 554 training return: tensor(271.3348, device='cuda:0')
episode: 555 training return: tensor(310.5816, device='cuda:0')
epoch: 139 test_true_pfm: 3369.5233722968733 sim_pfm: 350.1355054198745
episode: 556 training return: tensor(272.0718, device='cuda:0')
episode: 557 training return: tensor(279.0601, device='cuda:0')
episode: 558 training return: tensor(256.0043, device='cuda:0')
episode: 559 training return: tensor(-211.4586, device='cuda:0')
epoch: 140 test_true_pfm: 3381.5278477136358 sim_pfm: 237.75908725854242
episode: 560 training return: tensor(295.0490, device='cuda:0')
episode: 561 training return: tensor(313.0234, device='cuda:0')
episode: 562 training return: tensor(272.7083, device='cuda:0')
episode: 563 training return: tensor(134.8567, device='cuda:0')
epoch: 141 test_true_pfm: 3101.3849762928544 sim_pfm: 308.35479660871596
episode: 564 training return: tensor(117.4314, device='cuda:0')
episode: 565 training return: tensor(328.8122, device='cuda:0')
episode: 566 training return: tensor(314.8292, device='cuda:0')
episode: 567 training return: tensor(-333.0656, device='cuda:0')
epoch: 142 test_true_pfm: 3222.7883987398013 sim_pfm: 161.4300950281419
episode: 568 training return: tensor(326.7630, device='cuda:0')
episode: 569 training return: tensor(-185.4273, device='cuda:0')
episode: 570 training return: tensor(353.7259, device='cuda:0')
episode: 571 training return: tensor(229.6265, device='cuda:0')
epoch: 143 test_true_pfm: 3322.717209101693 sim_pfm: 262.302936138527
episode: 572 training return: tensor(137.3738, device='cuda:0')
episode: 573 training return: tensor(277.0125, device='cuda:0')
episode: 574 training return: tensor(315.4915, device='cuda:0')
episode: 575 training return: tensor(33.4863, device='cuda:0')
epoch: 144 test_true_pfm: 2945.7920634743346 sim_pfm: 290.95079668607406
episode: 576 training return: tensor(-249.3275, device='cuda:0')
episode: 577 training return: tensor(280.9473, device='cuda:0')
episode: 578 training return: tensor(-93.8401, device='cuda:0')
episode: 579 training return: tensor(-200.4428, device='cuda:0')
epoch: 145 test_true_pfm: 3306.1573027096533 sim_pfm: 51.66049683536403
episode: 580 training return: tensor(232.3917, device='cuda:0')
episode: 581 training return: tensor(313.3966, device='cuda:0')
episode: 582 training return: tensor(256.7477, device='cuda:0')
episode: 583 training return: tensor(243.2215, device='cuda:0')
epoch: 146 test_true_pfm: 3256.8407975141877 sim_pfm: 236.5725484736419
episode: 584 training return: tensor(265.0366, device='cuda:0')
episode: 585 training return: tensor(-51.1349, device='cuda:0')
episode: 586 training return: tensor(305.9242, device='cuda:0')
episode: 587 training return: tensor(-87.6627, device='cuda:0')
epoch: 147 test_true_pfm: 3193.662466508442 sim_pfm: 226.11689051033076
episode: 588 training return: tensor(352.1187, device='cuda:0')
episode: 589 training return: tensor(-265.4522, device='cuda:0')
episode: 590 training return: tensor(-150.1471, device='cuda:0')
episode: 591 training return: tensor(145.9713, device='cuda:0')
epoch: 148 test_true_pfm: 2885.638255637566 sim_pfm: 316.88394249539124
episode: 592 training return: tensor(263.5349, device='cuda:0')
episode: 593 training return: tensor(315.1583, device='cuda:0')
episode: 594 training return: tensor(294.0488, device='cuda:0')
episode: 595 training return: tensor(329.3989, device='cuda:0')
epoch: 149 test_true_pfm: 3086.0783100885506 sim_pfm: 284.30778676519793
episode: 596 training return: tensor(210.1052, device='cuda:0')
episode: 597 training return: tensor(330.4546, device='cuda:0')
episode: 598 training return: tensor(249.8050, device='cuda:0')
episode: 599 training return: tensor(393.5419, device='cuda:0')
epoch: 150 test_true_pfm: 2886.682149425009 sim_pfm: -25.165894886905637
