['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'brac', '--traj', 'medium', '--seed', '3', '--data', '100000']
2568.067441572758
episode: 0 training return: tensor(-3956379., device='cuda:0')
episode: 1 training return: tensor(-5829.5298, device='cuda:0')
episode: 2 training return: tensor(-13490.7129, device='cuda:0')
episode: 3 training return: tensor(-52572124., device='cuda:0')
epoch: 1 test_true_pfm: -181.6253980340191
episode: 4 training return: tensor(-14896.6123, device='cuda:0')
episode: 5 training return: tensor(-2.1155e+08, device='cuda:0')
episode: 6 training return: tensor(-17325.6172, device='cuda:0')
episode: 7 training return: tensor(-2879578.5000, device='cuda:0')
epoch: 2 test_true_pfm: -81.61612055711701
episode: 8 training return: tensor(-14966.7686, device='cuda:0')
episode: 9 training return: tensor(-65942796., device='cuda:0')
episode: 10 training return: tensor(-5369.4546, device='cuda:0')
episode: 11 training return: tensor(-3642.1462, device='cuda:0')
epoch: 3 test_true_pfm: -38.23573388926648
episode: 12 training return: tensor(-27318.9590, device='cuda:0')
episode: 13 training return: tensor(-28820.7969, device='cuda:0')
episode: 14 training return: tensor(-3435.2192, device='cuda:0')
episode: 15 training return: tensor(-694532.2500, device='cuda:0')
epoch: 4 test_true_pfm: -94.31216429620537
episode: 16 training return: tensor(-20120.0547, device='cuda:0')
episode: 17 training return: tensor(-30372.7754, device='cuda:0')
episode: 18 training return: tensor(-20772.1152, device='cuda:0')
episode: 19 training return: tensor(-18951.8125, device='cuda:0')
epoch: 5 test_true_pfm: -98.07345380015414
episode: 20 training return: tensor(-18465.0820, device='cuda:0')
episode: 21 training return: tensor(-3991.2119, device='cuda:0')
episode: 22 training return: tensor(-23915.2852, device='cuda:0')
episode: 23 training return: tensor(-1728454.7500, device='cuda:0')
epoch: 6 test_true_pfm: -55.669269379826005
episode: 24 training return: tensor(-17924.5762, device='cuda:0')
episode: 25 training return: tensor(-17082.6387, device='cuda:0')
episode: 26 training return: tensor(-23475.2832, device='cuda:0')
episode: 27 training return: tensor(-19958.9688, device='cuda:0')
epoch: 7 test_true_pfm: -106.31994831577872
episode: 28 training return: tensor(-19586.7266, device='cuda:0')
episode: 29 training return: tensor(-22100.5566, device='cuda:0')
episode: 30 training return: tensor(-22709.1816, device='cuda:0')
episode: 31 training return: tensor(-2991.2217, device='cuda:0')
epoch: 8 test_true_pfm: -41.52306315859347
episode: 32 training return: tensor(-18883.8320, device='cuda:0')
episode: 33 training return: tensor(-18761.0332, device='cuda:0')
episode: 34 training return: tensor(-19859.7812, device='cuda:0')
episode: 35 training return: tensor(-1309238.3750, device='cuda:0')
epoch: 9 test_true_pfm: -101.93083371343134
episode: 36 training return: tensor(-17819.9199, device='cuda:0')
episode: 37 training return: tensor(-18585.2207, device='cuda:0')
episode: 38 training return: tensor(-21278.4121, device='cuda:0')
episode: 39 training return: tensor(-17371.7227, device='cuda:0')
epoch: 10 test_true_pfm: -60.35503605667572
episode: 40 training return: tensor(-18207.8184, device='cuda:0')
episode: 41 training return: tensor(-18005.7676, device='cuda:0')
episode: 42 training return: tensor(-17859.6582, device='cuda:0')
episode: 43 training return: tensor(-19278.2402, device='cuda:0')
epoch: 11 test_true_pfm: -147.2828291789763
episode: 44 training return: tensor(-17071.0918, device='cuda:0')
episode: 45 training return: tensor(-20738.6992, device='cuda:0')
episode: 46 training return: tensor(-18860.1152, device='cuda:0')
episode: 47 training return: tensor(-18175.3555, device='cuda:0')
epoch: 12 test_true_pfm: -99.81510093873614
episode: 48 training return: tensor(-18938.4629, device='cuda:0')
episode: 49 training return: tensor(-18101.8477, device='cuda:0')
episode: 50 training return: tensor(-18769.3379, device='cuda:0')
episode: 51 training return: tensor(-19949.8613, device='cuda:0')
epoch: 13 test_true_pfm: -59.917841292851485
episode: 52 training return: tensor(-17943.4121, device='cuda:0')
episode: 53 training return: tensor(-22571.4414, device='cuda:0')
episode: 54 training return: tensor(-19492.0996, device='cuda:0')
episode: 55 training return: tensor(-19942.2637, device='cuda:0')
epoch: 14 test_true_pfm: 55.47946678530906
episode: 56 training return: tensor(-21503.7637, device='cuda:0')
episode: 57 training return: tensor(-16942.3457, device='cuda:0')
episode: 58 training return: tensor(-23786.1699, device='cuda:0')
episode: 59 training return: tensor(-15771.9463, device='cuda:0')
epoch: 15 test_true_pfm: -138.79063569798222
episode: 60 training return: tensor(-19370.0977, device='cuda:0')
episode: 61 training return: tensor(-18333.9473, device='cuda:0')
episode: 62 training return: tensor(-17598.7969, device='cuda:0')
episode: 63 training return: tensor(-16250.7227, device='cuda:0')
epoch: 16 test_true_pfm: -104.70123916029037
episode: 64 training return: tensor(-17448.2188, device='cuda:0')
episode: 65 training return: tensor(-17977.3906, device='cuda:0')
episode: 66 training return: tensor(-15242.2920, device='cuda:0')
episode: 67 training return: tensor(-18585.5938, device='cuda:0')
epoch: 17 test_true_pfm: -158.71898220332994
episode: 68 training return: tensor(-17628.3926, device='cuda:0')
episode: 69 training return: tensor(-17620.4453, device='cuda:0')
episode: 70 training return: tensor(-15611.3096, device='cuda:0')
episode: 71 training return: tensor(-16976.6836, device='cuda:0')
epoch: 18 test_true_pfm: -133.05085033684006
episode: 72 training return: tensor(-15261.6299, device='cuda:0')
episode: 73 training return: tensor(-18041.2559, device='cuda:0')
episode: 74 training return: tensor(-62997684., device='cuda:0')
episode: 75 training return: tensor(-22377.9512, device='cuda:0')
epoch: 19 test_true_pfm: 62.383622951881875
episode: 76 training return: tensor(-5.7539e+09, device='cuda:0')
episode: 77 training return: tensor(-23838.5566, device='cuda:0')
episode: 78 training return: tensor(-26878.0840, device='cuda:0')
episode: 79 training return: tensor(-4198.0562, device='cuda:0')
epoch: 20 test_true_pfm: 79.34678519896546
episode: 80 training return: tensor(-3395.4038, device='cuda:0')
episode: 81 training return: tensor(-38794.9258, device='cuda:0')
episode: 82 training return: tensor(-3861.3311, device='cuda:0')
episode: 83 training return: tensor(-4421.7368, device='cuda:0')
epoch: 21 test_true_pfm: 2.1202049595951777
episode: 84 training return: tensor(-61056.9531, device='cuda:0')
episode: 85 training return: tensor(-9921.9141, device='cuda:0')
episode: 86 training return: tensor(-47164.1523, device='cuda:0')
episode: 87 training return: tensor(-8333.7129, device='cuda:0')
epoch: 22 test_true_pfm: -36.36592406113738
episode: 88 training return: tensor(-53043.9961, device='cuda:0')
episode: 89 training return: tensor(-53530.8906, device='cuda:0')
episode: 90 training return: tensor(-57412.5859, device='cuda:0')
episode: 91 training return: tensor(-52482.3906, device='cuda:0')
epoch: 23 test_true_pfm: -38.29804414968265
episode: 92 training return: tensor(-53761.0039, device='cuda:0')
episode: 93 training return: tensor(-54393.1289, device='cuda:0')
episode: 94 training return: tensor(-3717.9417, device='cuda:0')
episode: 95 training return: tensor(-3687.1367, device='cuda:0')
epoch: 24 test_true_pfm: 91.19448098564057
episode: 96 training return: tensor(-3752.3813, device='cuda:0')
episode: 97 training return: tensor(-3706.1550, device='cuda:0')
episode: 98 training return: tensor(-3695.8293, device='cuda:0')
episode: 99 training return: tensor(-3705.7156, device='cuda:0')
epoch: 25 test_true_pfm: 117.40843166386833
episode: 100 training return: tensor(-3734.9199, device='cuda:0')
episode: 101 training return: tensor(-3903.7615, device='cuda:0')
episode: 102 training return: tensor(-53494.9219, device='cuda:0')
episode: 103 training return: tensor(-3728.7297, device='cuda:0')
epoch: 26 test_true_pfm: 163.6870466483677
episode: 104 training return: tensor(-3872.3281, device='cuda:0')
episode: 105 training return: tensor(-3731.5713, device='cuda:0')
episode: 106 training return: tensor(-60275.6992, device='cuda:0')
episode: 107 training return: tensor(-52492.5156, device='cuda:0')
epoch: 27 test_true_pfm: -68.08582786487874
episode: 108 training return: tensor(-52857.4531, device='cuda:0')
episode: 109 training return: tensor(-3851.7798, device='cuda:0')
episode: 110 training return: tensor(-3903.4526, device='cuda:0')
episode: 111 training return: tensor(-3847.4285, device='cuda:0')
epoch: 28 test_true_pfm: 178.17866981036627
episode: 112 training return: tensor(-4030.3721, device='cuda:0')
episode: 113 training return: tensor(-5095.4004, device='cuda:0')
episode: 114 training return: tensor(-4304.5928, device='cuda:0')
episode: 115 training return: tensor(-4267.8774, device='cuda:0')
epoch: 29 test_true_pfm: 159.30247649261517
episode: 116 training return: tensor(-4069.2979, device='cuda:0')
episode: 117 training return: tensor(-3771.3337, device='cuda:0')
episode: 118 training return: tensor(-3375.8806, device='cuda:0')
episode: 119 training return: tensor(-3412.4995, device='cuda:0')
epoch: 30 test_true_pfm: 88.37840351597528
episode: 120 training return: tensor(-3668.7227, device='cuda:0')
episode: 121 training return: tensor(-3714.9358, device='cuda:0')
episode: 122 training return: tensor(-3733.9343, device='cuda:0')
episode: 123 training return: tensor(-3299.7029, device='cuda:0')
epoch: 31 test_true_pfm: 101.11889898478437
episode: 124 training return: tensor(-4318.3066, device='cuda:0')
episode: 125 training return: tensor(-3430.9453, device='cuda:0')
episode: 126 training return: tensor(-4575.3413, device='cuda:0')
episode: 127 training return: tensor(-4403.0605, device='cuda:0')
epoch: 32 test_true_pfm: 149.62327867093146
episode: 128 training return: tensor(-3316.4517, device='cuda:0')
episode: 129 training return: tensor(-52902.1016, device='cuda:0')
episode: 130 training return: tensor(-3399.1814, device='cuda:0')
episode: 131 training return: tensor(-51400.0391, device='cuda:0')
epoch: 33 test_true_pfm: -30.187198643870403
episode: 132 training return: tensor(-50808.4414, device='cuda:0')
episode: 133 training return: tensor(-48220.4648, device='cuda:0')
episode: 134 training return: tensor(-57713.6094, device='cuda:0')
episode: 135 training return: tensor(-3807.7356, device='cuda:0')
epoch: 34 test_true_pfm: -77.48239816823276
episode: 136 training return: tensor(-50491.3438, device='cuda:0')
episode: 137 training return: tensor(-51644.9805, device='cuda:0')
episode: 138 training return: tensor(-49786.6406, device='cuda:0')
episode: 139 training return: tensor(-49249.6094, device='cuda:0')
epoch: 35 test_true_pfm: -76.54166092789156
episode: 140 training return: tensor(-52127.6953, device='cuda:0')
episode: 141 training return: tensor(-46970.5391, device='cuda:0')
episode: 142 training return: tensor(-3385.2664, device='cuda:0')
episode: 143 training return: tensor(-3343.1941, device='cuda:0')
epoch: 36 test_true_pfm: 73.39855888128072
episode: 144 training return: tensor(-3976.9226, device='cuda:0')
episode: 145 training return: tensor(-3627.1921, device='cuda:0')
episode: 146 training return: tensor(-3454.7297, device='cuda:0')
episode: 147 training return: tensor(-48971.9844, device='cuda:0')
epoch: 37 test_true_pfm: 172.12808230283179
episode: 148 training return: tensor(-3475.7805, device='cuda:0')
episode: 149 training return: tensor(-51271.1523, device='cuda:0')
episode: 150 training return: tensor(-4048.4653, device='cuda:0')
episode: 151 training return: tensor(-4731.6406, device='cuda:0')
epoch: 38 test_true_pfm: 241.2477913268017
episode: 152 training return: tensor(-3417.5386, device='cuda:0')
episode: 153 training return: tensor(-3866.0691, device='cuda:0')
episode: 154 training return: tensor(-49146.8125, device='cuda:0')
episode: 155 training return: tensor(-3994.4492, device='cuda:0')
epoch: 39 test_true_pfm: 265.2240607387882
episode: 156 training return: tensor(-3404.9553, device='cuda:0')
episode: 157 training return: tensor(-51815.8438, device='cuda:0')
episode: 158 training return: tensor(-51105.0742, device='cuda:0')
episode: 159 training return: tensor(-50533.2930, device='cuda:0')
epoch: 40 test_true_pfm: 4.565126986435653
episode: 160 training return: tensor(-54002.9766, device='cuda:0')
episode: 161 training return: tensor(-52395.3164, device='cuda:0')
episode: 162 training return: tensor(-4185.3418, device='cuda:0')
episode: 163 training return: tensor(-50811.7812, device='cuda:0')
epoch: 41 test_true_pfm: 34.335473401048034
episode: 164 training return: tensor(-54968.8828, device='cuda:0')
episode: 165 training return: tensor(-6005.2505, device='cuda:0')
episode: 166 training return: tensor(-55419.1953, device='cuda:0')
episode: 167 training return: tensor(-52497.0391, device='cuda:0')
epoch: 42 test_true_pfm: 24.019976434651635
episode: 168 training return: tensor(-52936.4258, device='cuda:0')
episode: 169 training return: tensor(-4544.8862, device='cuda:0')
episode: 170 training return: tensor(-5925.4238, device='cuda:0')
episode: 171 training return: tensor(-56692.7383, device='cuda:0')
epoch: 43 test_true_pfm: 81.36333699530317
episode: 172 training return: tensor(-54940.8906, device='cuda:0')
episode: 173 training return: tensor(-52591.2812, device='cuda:0')
episode: 174 training return: tensor(-48597.8047, device='cuda:0')
episode: 175 training return: tensor(-3471.9614, device='cuda:0')
epoch: 44 test_true_pfm: 234.6047558806653
episode: 176 training return: tensor(-3375.6704, device='cuda:0')
episode: 177 training return: tensor(-49200.1484, device='cuda:0')
episode: 178 training return: tensor(-3385.8323, device='cuda:0')
episode: 179 training return: tensor(-51272.5820, device='cuda:0')
epoch: 45 test_true_pfm: 67.221369934215
episode: 180 training return: tensor(-3561.3723, device='cuda:0')
episode: 181 training return: tensor(-51489.1602, device='cuda:0')
episode: 182 training return: tensor(-52460.3672, device='cuda:0')
episode: 183 training return: tensor(-51400.6641, device='cuda:0')
epoch: 46 test_true_pfm: -23.5744098368594
episode: 184 training return: tensor(-54602.9336, device='cuda:0')
episode: 185 training return: tensor(-51233.3984, device='cuda:0')
episode: 186 training return: tensor(-57309.8516, device='cuda:0')
episode: 187 training return: tensor(-4515.0264, device='cuda:0')
epoch: 47 test_true_pfm: -28.958211508665784
episode: 188 training return: tensor(-53800.3477, device='cuda:0')
episode: 189 training return: tensor(-54263.3867, device='cuda:0')
episode: 190 training return: tensor(-53826.2656, device='cuda:0')
episode: 191 training return: tensor(-53747.5000, device='cuda:0')
epoch: 48 test_true_pfm: -5.418466362438899
episode: 192 training return: tensor(-52812.8242, device='cuda:0')
episode: 193 training return: tensor(-52565.1133, device='cuda:0')
episode: 194 training return: tensor(-56021.0469, device='cuda:0')
episode: 195 training return: tensor(-57742.7109, device='cuda:0')
epoch: 49 test_true_pfm: -11.869797660810676
episode: 196 training return: tensor(-49729.1367, device='cuda:0')
episode: 197 training return: tensor(-53616.6758, device='cuda:0')
episode: 198 training return: tensor(-10695.8301, device='cuda:0')
episode: 199 training return: tensor(-50268.9844, device='cuda:0')
epoch: 50 test_true_pfm: -56.33626157021945
episode: 200 training return: tensor(-51730.1211, device='cuda:0')
episode: 201 training return: tensor(-51087.9414, device='cuda:0')
episode: 202 training return: tensor(-57248.8789, device='cuda:0')
episode: 203 training return: tensor(-53496.4805, device='cuda:0')
epoch: 51 test_true_pfm: -35.90881280299202
episode: 204 training return: tensor(-6985.0386, device='cuda:0')
episode: 205 training return: tensor(-49939.5234, device='cuda:0')
episode: 206 training return: tensor(-61031.5156, device='cuda:0')
episode: 207 training return: tensor(-4619.5063, device='cuda:0')
epoch: 52 test_true_pfm: -29.731403357451995
episode: 208 training return: tensor(-57110.4062, device='cuda:0')
episode: 209 training return: tensor(-5468.1079, device='cuda:0')
episode: 210 training return: tensor(-60003.1914, device='cuda:0')
episode: 211 training return: tensor(-52701.0547, device='cuda:0')
epoch: 53 test_true_pfm: -62.0856718961085
episode: 212 training return: tensor(-52973.5312, device='cuda:0')
episode: 213 training return: tensor(-52465.9727, device='cuda:0')
episode: 214 training return: tensor(-52773.2266, device='cuda:0')
episode: 215 training return: tensor(-53223.1055, device='cuda:0')
epoch: 54 test_true_pfm: -68.64306107969635
episode: 216 training return: tensor(-51994.2617, device='cuda:0')
episode: 217 training return: tensor(-52103.4297, device='cuda:0')
episode: 218 training return: tensor(-56041.2266, device='cuda:0')
episode: 219 training return: tensor(-52560.2969, device='cuda:0')
epoch: 55 test_true_pfm: -127.11263872689223
episode: 220 training return: tensor(-55193.4023, device='cuda:0')
episode: 221 training return: tensor(-53824.4297, device='cuda:0')
episode: 222 training return: tensor(-53021.1602, device='cuda:0')
episode: 223 training return: tensor(-55164.0352, device='cuda:0')
epoch: 56 test_true_pfm: 140.3114503002063
episode: 224 training return: tensor(-52777.1719, device='cuda:0')
episode: 225 training return: tensor(-51740.9102, device='cuda:0')
episode: 226 training return: tensor(-48473.2812, device='cuda:0')
episode: 227 training return: tensor(-7518.9341, device='cuda:0')
epoch: 57 test_true_pfm: -57.41743539395676
episode: 228 training return: tensor(-51629.3516, device='cuda:0')
episode: 229 training return: tensor(-49591.0703, device='cuda:0')
episode: 230 training return: tensor(-50863.4531, device='cuda:0')
episode: 231 training return: tensor(-51396.9102, device='cuda:0')
epoch: 58 test_true_pfm: 95.01482486234528
episode: 232 training return: tensor(-59252.2969, device='cuda:0')
episode: 233 training return: tensor(-50748.0117, device='cuda:0')
episode: 234 training return: tensor(-52368.4219, device='cuda:0')
episode: 235 training return: tensor(-56951.0234, device='cuda:0')
epoch: 59 test_true_pfm: -108.79896235405124
episode: 236 training return: tensor(-49978., device='cuda:0')
episode: 237 training return: tensor(-54486.9375, device='cuda:0')
episode: 238 training return: tensor(-51472.8906, device='cuda:0')
episode: 239 training return: tensor(-53176.5547, device='cuda:0')
epoch: 60 test_true_pfm: -45.01966672743749
episode: 240 training return: tensor(-51282.0391, device='cuda:0')
episode: 241 training return: tensor(-58242.4531, device='cuda:0')
episode: 242 training return: tensor(-70643.6250, device='cuda:0')
episode: 243 training return: tensor(-19097.0879, device='cuda:0')
epoch: 61 test_true_pfm: 146.11861548003196
episode: 244 training return: tensor(-10657.8311, device='cuda:0')
episode: 245 training return: tensor(-9044.8555, device='cuda:0')
episode: 246 training return: tensor(-52083.9727, device='cuda:0')
episode: 247 training return: tensor(-49145.8164, device='cuda:0')
epoch: 62 test_true_pfm: 49.83622731709344
episode: 248 training return: tensor(-53204.0078, device='cuda:0')
episode: 249 training return: tensor(-51027.2812, device='cuda:0')
episode: 250 training return: tensor(-54978.6875, device='cuda:0')
episode: 251 training return: tensor(-53198.4023, device='cuda:0')
epoch: 63 test_true_pfm: 7.5641161420103264
episode: 252 training return: tensor(-51363.2500, device='cuda:0')
episode: 253 training return: tensor(-28319.1621, device='cuda:0')
episode: 254 training return: tensor(-11839.8262, device='cuda:0')
episode: 255 training return: tensor(-57527.1016, device='cuda:0')
epoch: 64 test_true_pfm: 90.06544545863854
episode: 256 training return: tensor(-60492.4141, device='cuda:0')
episode: 257 training return: tensor(-10656.3613, device='cuda:0')
episode: 258 training return: tensor(-8126.8032, device='cuda:0')
episode: 259 training return: tensor(-13837.6162, device='cuda:0')
epoch: 65 test_true_pfm: -133.2502848187922
episode: 260 training return: tensor(-57913.2500, device='cuda:0')
episode: 261 training return: tensor(-12553.6387, device='cuda:0')
episode: 262 training return: tensor(-37117.5391, device='cuda:0')
episode: 263 training return: tensor(-17692.7285, device='cuda:0')
epoch: 66 test_true_pfm: -51.85593990220474
episode: 264 training return: tensor(-2775587.7500, device='cuda:0')
episode: 265 training return: tensor(-9648.4482, device='cuda:0')
episode: 266 training return: tensor(-58493., device='cuda:0')
episode: 267 training return: tensor(-10766.6631, device='cuda:0')
epoch: 67 test_true_pfm: 72.28315229165193
episode: 268 training return: tensor(-6316.7334, device='cuda:0')
episode: 269 training return: tensor(-7064.4741, device='cuda:0')
episode: 270 training return: tensor(-52905.1719, device='cuda:0')
episode: 271 training return: tensor(-50556.8906, device='cuda:0')
epoch: 68 test_true_pfm: -6.338117675061697
episode: 272 training return: tensor(-50061.3594, device='cuda:0')
episode: 273 training return: tensor(-8722.8506, device='cuda:0')
episode: 274 training return: tensor(-61939.5898, device='cuda:0')
episode: 275 training return: tensor(-8685.9502, device='cuda:0')
epoch: 69 test_true_pfm: 118.04025553154732
episode: 276 training return: tensor(-57227.7969, device='cuda:0')
episode: 277 training return: tensor(-6903.0415, device='cuda:0')
episode: 278 training return: tensor(-53951.8594, device='cuda:0')
episode: 279 training return: tensor(-55586.3633, device='cuda:0')
epoch: 70 test_true_pfm: 53.23366732984633
episode: 280 training return: tensor(-7176.6499, device='cuda:0')
episode: 281 training return: tensor(-65132.2344, device='cuda:0')
episode: 282 training return: tensor(-86500.3516, device='cuda:0')
episode: 283 training return: tensor(-13988.3076, device='cuda:0')
epoch: 71 test_true_pfm: -156.31720636888687
episode: 284 training return: tensor(-48966.0469, device='cuda:0')
episode: 285 training return: tensor(-17563.7129, device='cuda:0')
episode: 286 training return: tensor(-9850.8389, device='cuda:0')
episode: 287 training return: tensor(-12008.8779, device='cuda:0')
epoch: 72 test_true_pfm: 111.20927015828312
episode: 288 training return: tensor(-97895.8594, device='cuda:0')
episode: 289 training return: tensor(-5306.1855, device='cuda:0')
episode: 290 training return: tensor(-35916.2930, device='cuda:0')
episode: 291 training return: tensor(-54732.8242, device='cuda:0')
epoch: 73 test_true_pfm: 13.850852401083822
episode: 292 training return: tensor(-55742.0391, device='cuda:0')
episode: 293 training return: tensor(-52852.2930, device='cuda:0')
episode: 294 training return: tensor(-62492.3086, device='cuda:0')
episode: 295 training return: tensor(-60019.9688, device='cuda:0')
epoch: 74 test_true_pfm: 208.4335529356184
episode: 296 training return: tensor(-13742.2559, device='cuda:0')
episode: 297 training return: tensor(-3033017., device='cuda:0')
episode: 298 training return: tensor(-5666.1162, device='cuda:0')
episode: 299 training return: tensor(-9250.5967, device='cuda:0')
epoch: 75 test_true_pfm: 79.14899906311861
episode: 300 training return: tensor(-57661.8984, device='cuda:0')
episode: 301 training return: tensor(-7885.6294, device='cuda:0')
episode: 302 training return: tensor(-56932.7578, device='cuda:0')
episode: 303 training return: tensor(-55080.5234, device='cuda:0')
epoch: 76 test_true_pfm: -114.07477081225885
episode: 304 training return: tensor(-58757.6172, device='cuda:0')
episode: 305 training return: tensor(-5553.5732, device='cuda:0')
episode: 306 training return: tensor(-63952.3789, device='cuda:0')
episode: 307 training return: tensor(-976533.5000, device='cuda:0')
epoch: 77 test_true_pfm: 54.390464992793234
episode: 308 training return: tensor(-23387.9375, device='cuda:0')
episode: 309 training return: tensor(-8296.7676, device='cuda:0')
episode: 310 training return: tensor(-51578.3242, device='cuda:0')
episode: 311 training return: tensor(-6339.2295, device='cuda:0')
epoch: 78 test_true_pfm: 146.43485380528372
episode: 312 training return: tensor(-60792.7656, device='cuda:0')
episode: 313 training return: tensor(-71011.5859, device='cuda:0')
episode: 314 training return: tensor(-12451.3564, device='cuda:0')
episode: 315 training return: tensor(-7813.5571, device='cuda:0')
epoch: 79 test_true_pfm: 59.79491113527616
episode: 316 training return: tensor(-10094.3154, device='cuda:0')
episode: 317 training return: tensor(-16915.7871, device='cuda:0')
episode: 318 training return: tensor(-7426.8262, device='cuda:0')
episode: 319 training return: tensor(-66788.5859, device='cuda:0')
epoch: 80 test_true_pfm: -125.14119769879544
episode: 320 training return: tensor(-10922.2891, device='cuda:0')
episode: 321 training return: tensor(-76277.7344, device='cuda:0')
episode: 322 training return: tensor(-62443.5859, device='cuda:0')
episode: 323 training return: tensor(-57240.1875, device='cuda:0')
epoch: 81 test_true_pfm: -82.51042902520767
episode: 324 training return: tensor(-13055.0137, device='cuda:0')
episode: 325 training return: tensor(-60471.5820, device='cuda:0')
episode: 326 training return: tensor(-56806.3750, device='cuda:0')
episode: 327 training return: tensor(-61445.0625, device='cuda:0')
epoch: 82 test_true_pfm: -35.299464762124344
episode: 328 training return: tensor(-53934.7031, device='cuda:0')
episode: 329 training return: tensor(-56023.5195, device='cuda:0')
episode: 330 training return: tensor(-49479.1953, device='cuda:0')
episode: 331 training return: tensor(-50490.9258, device='cuda:0')
epoch: 83 test_true_pfm: -5.876002335989372
episode: 332 training return: tensor(-12409.4453, device='cuda:0')
episode: 333 training return: tensor(-10022.9912, device='cuda:0')
episode: 334 training return: tensor(-2372434., device='cuda:0')
episode: 335 training return: tensor(-4509.4067, device='cuda:0')
epoch: 84 test_true_pfm: 22.85124750490853
episode: 336 training return: tensor(-57005.4336, device='cuda:0')
episode: 337 training return: tensor(-79010.4688, device='cuda:0')
episode: 338 training return: tensor(-49055.9648, device='cuda:0')
episode: 339 training return: tensor(-7448.0615, device='cuda:0')
epoch: 85 test_true_pfm: 46.52532535939914
episode: 340 training return: tensor(-12099.0020, device='cuda:0')
episode: 341 training return: tensor(-53423.0273, device='cuda:0')
episode: 342 training return: tensor(-49519.4922, device='cuda:0')
episode: 343 training return: tensor(-52532.3867, device='cuda:0')
epoch: 86 test_true_pfm: 88.13519014935495
episode: 344 training return: tensor(-62231.5234, device='cuda:0')
episode: 345 training return: tensor(-69199.0938, device='cuda:0')
episode: 346 training return: tensor(-74469.3203, device='cuda:0')
episode: 347 training return: tensor(-51588.9805, device='cuda:0')
epoch: 87 test_true_pfm: -9.66971424249323
episode: 348 training return: tensor(-1693646.6250, device='cuda:0')
episode: 349 training return: tensor(-5831.2637, device='cuda:0')
episode: 350 training return: tensor(-1811880.2500, device='cuda:0')
episode: 351 training return: tensor(-33666.3906, device='cuda:0')
epoch: 88 test_true_pfm: 96.25457071109197
episode: 352 training return: tensor(-10407.2529, device='cuda:0')
episode: 353 training return: tensor(-705600.3750, device='cuda:0')
episode: 354 training return: tensor(-46867148., device='cuda:0')
episode: 355 training return: tensor(-552770.2500, device='cuda:0')
epoch: 89 test_true_pfm: 4.124336405991595
episode: 356 training return: tensor(-8475.4785, device='cuda:0')
episode: 357 training return: tensor(-5138622.5000, device='cuda:0')
episode: 358 training return: tensor(-10941.5645, device='cuda:0')
episode: 359 training return: tensor(-11359.7334, device='cuda:0')
epoch: 90 test_true_pfm: -20.038731548004474
episode: 360 training return: tensor(-24722.6719, device='cuda:0')
episode: 361 training return: tensor(-51394.8594, device='cuda:0')
episode: 362 training return: tensor(-8283.9609, device='cuda:0')
episode: 363 training return: tensor(-9301.2109, device='cuda:0')
epoch: 91 test_true_pfm: -344.20266662380965
episode: 364 training return: tensor(-111165.5781, device='cuda:0')
episode: 365 training return: tensor(-10498.3516, device='cuda:0')
episode: 366 training return: tensor(-103504.3047, device='cuda:0')
episode: 367 training return: tensor(-4460840.5000, device='cuda:0')
epoch: 92 test_true_pfm: -91.6358812021935
episode: 368 training return: tensor(-1335303.1250, device='cuda:0')
episode: 369 training return: tensor(-16075.8096, device='cuda:0')
episode: 370 training return: tensor(-9362.8984, device='cuda:0')
episode: 371 training return: tensor(-12047.6445, device='cuda:0')
epoch: 93 test_true_pfm: -0.9658165510604301
episode: 372 training return: tensor(-89459.8359, device='cuda:0')
episode: 373 training return: tensor(-10290.9277, device='cuda:0')
episode: 374 training return: tensor(-12971329., device='cuda:0')
episode: 375 training return: tensor(-117959.0859, device='cuda:0')
epoch: 94 test_true_pfm: 7.422198866946329
episode: 376 training return: tensor(-154389.9375, device='cuda:0')
episode: 377 training return: tensor(-120009.6953, device='cuda:0')
episode: 378 training return: tensor(-115149.4609, device='cuda:0')
episode: 379 training return: tensor(-8284.4902, device='cuda:0')
epoch: 95 test_true_pfm: 71.08303042478069
episode: 380 training return: tensor(-81954.0391, device='cuda:0')
episode: 381 training return: tensor(-1211434.7500, device='cuda:0')
episode: 382 training return: tensor(-731535.8125, device='cuda:0')
episode: 383 training return: tensor(-11458.8086, device='cuda:0')
epoch: 96 test_true_pfm: -18.735399227947127
episode: 384 training return: tensor(-860440.1875, device='cuda:0')
episode: 385 training return: tensor(-1106497.8750, device='cuda:0')
episode: 386 training return: tensor(-117753.7891, device='cuda:0')
episode: 387 training return: tensor(-789914.5000, device='cuda:0')
epoch: 97 test_true_pfm: -62.59141538522863
episode: 388 training return: tensor(-826114.2500, device='cuda:0')
episode: 389 training return: tensor(-17693.7344, device='cuda:0')
episode: 390 training return: tensor(-946087.5625, device='cuda:0')
episode: 391 training return: tensor(-14631.4170, device='cuda:0')
epoch: 98 test_true_pfm: -17.832186403099314
episode: 392 training return: tensor(-107499.1641, device='cuda:0')
episode: 393 training return: tensor(-2534096.7500, device='cuda:0')
episode: 394 training return: tensor(-115446.2812, device='cuda:0')
episode: 395 training return: tensor(-1420150.1250, device='cuda:0')
epoch: 99 test_true_pfm: 97.36083402858283
episode: 396 training return: tensor(-76441.0469, device='cuda:0')
episode: 397 training return: tensor(-1569910.3750, device='cuda:0')
episode: 398 training return: tensor(-2.6534e+08, device='cuda:0')
episode: 399 training return: tensor(-163970.6719, device='cuda:0')
epoch: 100 test_true_pfm: -58.941653509121515
episode: 400 training return: tensor(-9539.0713, device='cuda:0')
episode: 401 training return: tensor(-10782.9453, device='cuda:0')
episode: 402 training return: tensor(-721371.6875, device='cuda:0')
episode: 403 training return: tensor(-7880293.5000, device='cuda:0')
epoch: 101 test_true_pfm: -259.4940389689467
episode: 404 training return: tensor(-14418309., device='cuda:0')
episode: 405 training return: tensor(-12264.6113, device='cuda:0')
episode: 406 training return: tensor(-22380.6406, device='cuda:0')
episode: 407 training return: tensor(-3466312.5000, device='cuda:0')
epoch: 102 test_true_pfm: -9.252499537252316
episode: 408 training return: tensor(-8380.1104, device='cuda:0')
episode: 409 training return: tensor(-5145705., device='cuda:0')
episode: 410 training return: tensor(-80407.1953, device='cuda:0')
episode: 411 training return: tensor(-4.3002e+08, device='cuda:0')
epoch: 103 test_true_pfm: -9.449888489860044
episode: 412 training return: tensor(-10385.7822, device='cuda:0')
episode: 413 training return: tensor(-78925.8750, device='cuda:0')
episode: 414 training return: tensor(-28842.3613, device='cuda:0')
episode: 415 training return: tensor(-56405.7539, device='cuda:0')
epoch: 104 test_true_pfm: -156.9915671178584
episode: 416 training return: tensor(-4793390., device='cuda:0')
episode: 417 training return: tensor(-6021457.5000, device='cuda:0')
episode: 418 training return: tensor(-906813.5000, device='cuda:0')
episode: 419 training return: tensor(-118544.2656, device='cuda:0')
epoch: 105 test_true_pfm: 7.8842284547466095
episode: 420 training return: tensor(-10374.8135, device='cuda:0')
episode: 421 training return: tensor(-1676247.2500, device='cuda:0')
episode: 422 training return: tensor(-1110364.2500, device='cuda:0')
episode: 423 training return: tensor(-9003329., device='cuda:0')
epoch: 106 test_true_pfm: 9.853110994496545
episode: 424 training return: tensor(-3473095.7500, device='cuda:0')
episode: 425 training return: tensor(-1070466.2500, device='cuda:0')
episode: 426 training return: tensor(-111748.6797, device='cuda:0')
episode: 427 training return: tensor(-6.4053e+08, device='cuda:0')
epoch: 107 test_true_pfm: -178.15298270761343
episode: 428 training return: tensor(-5.8341e+08, device='cuda:0')
episode: 429 training return: tensor(-14086.2363, device='cuda:0')
episode: 430 training return: tensor(-102905.6094, device='cuda:0')
episode: 431 training return: tensor(-988502.8750, device='cuda:0')
epoch: 108 test_true_pfm: -42.20279426635552
episode: 432 training return: tensor(-126576.0312, device='cuda:0')
episode: 433 training return: tensor(-123703.5000, device='cuda:0')
episode: 434 training return: tensor(-1046947.2500, device='cuda:0')
episode: 435 training return: tensor(-124903.1016, device='cuda:0')
epoch: 109 test_true_pfm: -112.20317853103715
episode: 436 training return: tensor(-1437568., device='cuda:0')
episode: 437 training return: tensor(-2183052.7500, device='cuda:0')
episode: 438 training return: tensor(-122924.6797, device='cuda:0')
episode: 439 training return: tensor(-105744.7656, device='cuda:0')
epoch: 110 test_true_pfm: -99.06136666091517
episode: 440 training return: tensor(-125710.4141, device='cuda:0')
episode: 441 training return: tensor(-10697.6797, device='cuda:0')
episode: 442 training return: tensor(-13981.8975, device='cuda:0')
episode: 443 training return: tensor(-9702539., device='cuda:0')
epoch: 111 test_true_pfm: -47.0444682245818
episode: 444 training return: tensor(-1295188.3750, device='cuda:0')
episode: 445 training return: tensor(-120856.5000, device='cuda:0')
episode: 446 training return: tensor(-2.6689e+08, device='cuda:0')
episode: 447 training return: tensor(-123624.3750, device='cuda:0')
epoch: 112 test_true_pfm: 4.770991564452017
episode: 448 training return: tensor(-2.2784e+08, device='cuda:0')
episode: 449 training return: tensor(-116614.6719, device='cuda:0')
episode: 450 training return: tensor(-21689.5312, device='cuda:0')
episode: 451 training return: tensor(-120440.1250, device='cuda:0')
epoch: 113 test_true_pfm: -82.67132249070768
episode: 452 training return: tensor(-2684271.7500, device='cuda:0')
episode: 453 training return: tensor(-1445048.8750, device='cuda:0')
episode: 454 training return: tensor(-1279049.2500, device='cuda:0')
episode: 455 training return: tensor(-1378159.8750, device='cuda:0')
epoch: 114 test_true_pfm: -80.02985587733308
episode: 456 training return: tensor(-1250515.3750, device='cuda:0')
episode: 457 training return: tensor(-2438790., device='cuda:0')
episode: 458 training return: tensor(-880010.4375, device='cuda:0')
episode: 459 training return: tensor(-1634052.8750, device='cuda:0')
epoch: 115 test_true_pfm: -88.99049476697907
episode: 460 training return: tensor(-1225004., device='cuda:0')
episode: 461 training return: tensor(-1.5676e+08, device='cuda:0')
episode: 462 training return: tensor(-4.0163e+08, device='cuda:0')
episode: 463 training return: tensor(-117438.5234, device='cuda:0')
epoch: 116 test_true_pfm: 50.382436047431064
episode: 464 training return: tensor(-1148928.7500, device='cuda:0')
episode: 465 training return: tensor(-7885217., device='cuda:0')
episode: 466 training return: tensor(-129348.3828, device='cuda:0')
episode: 467 training return: tensor(-125298.5781, device='cuda:0')
epoch: 117 test_true_pfm: -4.760833598638996
episode: 468 training return: tensor(-89996824., device='cuda:0')
episode: 469 training return: tensor(-1520887.8750, device='cuda:0')
episode: 470 training return: tensor(-1328902.5000, device='cuda:0')
episode: 471 training return: tensor(-1270811.7500, device='cuda:0')
epoch: 118 test_true_pfm: -125.17679540661568
episode: 472 training return: tensor(-124874.6562, device='cuda:0')
episode: 473 training return: tensor(-1108835.6250, device='cuda:0')
episode: 474 training return: tensor(-1495500.2500, device='cuda:0')
episode: 475 training return: tensor(-1244598.1250, device='cuda:0')
epoch: 119 test_true_pfm: 41.21146016986387
episode: 476 training return: tensor(-119963.2188, device='cuda:0')
episode: 477 training return: tensor(-1013113.2500, device='cuda:0')
episode: 478 training return: tensor(-1688111.7500, device='cuda:0')
episode: 479 training return: tensor(-1275796.3750, device='cuda:0')
epoch: 120 test_true_pfm: -60.16271609659256
episode: 480 training return: tensor(-6310923.5000, device='cuda:0')
episode: 481 training return: tensor(-106804.0078, device='cuda:0')
episode: 482 training return: tensor(-122363.3750, device='cuda:0')
episode: 483 training return: tensor(-4.0781e+08, device='cuda:0')
epoch: 121 test_true_pfm: 15.783538866673121
episode: 484 training return: tensor(-1238729.1250, device='cuda:0')
episode: 485 training return: tensor(-10556.8916, device='cuda:0')
episode: 486 training return: tensor(-17128.5645, device='cuda:0')
episode: 487 training return: tensor(-114978.9844, device='cuda:0')
epoch: 122 test_true_pfm: 22.743576177818415
episode: 488 training return: tensor(-7085113., device='cuda:0')
episode: 489 training return: tensor(-858421.6875, device='cuda:0')
episode: 490 training return: tensor(-115354.9219, device='cuda:0')
episode: 491 training return: tensor(-1327471., device='cuda:0')
epoch: 123 test_true_pfm: -55.24077832279318
episode: 492 training return: tensor(-1137248.2500, device='cuda:0')
episode: 493 training return: tensor(-905524.2500, device='cuda:0')
episode: 494 training return: tensor(-1.5601e+08, device='cuda:0')
episode: 495 training return: tensor(-1335672.1250, device='cuda:0')
epoch: 124 test_true_pfm: 32.503662437841705
episode: 496 training return: tensor(-1003251.4375, device='cuda:0')
episode: 497 training return: tensor(-16277.1816, device='cuda:0')
episode: 498 training return: tensor(-1354672.5000, device='cuda:0')
episode: 499 training return: tensor(-857612.1250, device='cuda:0')
epoch: 125 test_true_pfm: -23.276752548168712
episode: 500 training return: tensor(-12471.3291, device='cuda:0')
episode: 501 training return: tensor(-727091.9375, device='cuda:0')
episode: 502 training return: tensor(-953824., device='cuda:0')
episode: 503 training return: tensor(-2601330.2500, device='cuda:0')
epoch: 126 test_true_pfm: -49.6613715600519
episode: 504 training return: tensor(-1119920., device='cuda:0')
episode: 505 training return: tensor(-1076452.6250, device='cuda:0')
episode: 506 training return: tensor(-1208007.3750, device='cuda:0')
episode: 507 training return: tensor(-1219277., device='cuda:0')
epoch: 127 test_true_pfm: -63.71992338328113
episode: 508 training return: tensor(-1664108., device='cuda:0')
episode: 509 training return: tensor(-1461153.8750, device='cuda:0')
episode: 510 training return: tensor(-1137744.2500, device='cuda:0')
episode: 511 training return: tensor(-1075839.5000, device='cuda:0')
epoch: 128 test_true_pfm: 9.461219534618023
episode: 512 training return: tensor(-9507116., device='cuda:0')
episode: 513 training return: tensor(-1171515.2500, device='cuda:0')
episode: 514 training return: tensor(-1451364.8750, device='cuda:0')
episode: 515 training return: tensor(-1323168.8750, device='cuda:0')
epoch: 129 test_true_pfm: -127.08165845106964
episode: 516 training return: tensor(-1084205.6250, device='cuda:0')
episode: 517 training return: tensor(-1431000., device='cuda:0')
episode: 518 training return: tensor(-1071039.8750, device='cuda:0')
episode: 519 training return: tensor(-3203184.5000, device='cuda:0')
epoch: 130 test_true_pfm: -49.90054940660871
episode: 520 training return: tensor(-125415.3672, device='cuda:0')
episode: 521 training return: tensor(-1171531.7500, device='cuda:0')
episode: 522 training return: tensor(-1120121.2500, device='cuda:0')
episode: 523 training return: tensor(-9647291., device='cuda:0')
epoch: 131 test_true_pfm: -191.28774042967078
episode: 524 training return: tensor(-1129652., device='cuda:0')
episode: 525 training return: tensor(-826148.6250, device='cuda:0')
episode: 526 training return: tensor(-1056379.1250, device='cuda:0')
episode: 527 training return: tensor(-609483.1875, device='cuda:0')
epoch: 132 test_true_pfm: -28.756538970967814
episode: 528 training return: tensor(-1080473., device='cuda:0')
episode: 529 training return: tensor(-1057730.2500, device='cuda:0')
episode: 530 training return: tensor(-1.7577e+08, device='cuda:0')
episode: 531 training return: tensor(-2070764.1250, device='cuda:0')
epoch: 133 test_true_pfm: 14.045066313672587
episode: 532 training return: tensor(-1246189.2500, device='cuda:0')
episode: 533 training return: tensor(-1153982.3750, device='cuda:0')
episode: 534 training return: tensor(-110218.1250, device='cuda:0')
episode: 535 training return: tensor(-107116.9844, device='cuda:0')
epoch: 134 test_true_pfm: -21.338849879120982
episode: 536 training return: tensor(-103456.8125, device='cuda:0')
episode: 537 training return: tensor(-109804.8984, device='cuda:0')
episode: 538 training return: tensor(-9.4774e+08, device='cuda:0')
episode: 539 training return: tensor(-1297498., device='cuda:0')
epoch: 135 test_true_pfm: 72.5890269948328
episode: 540 training return: tensor(-1382520.8750, device='cuda:0')
episode: 541 training return: tensor(-3666597.5000, device='cuda:0')
episode: 542 training return: tensor(-719441.5625, device='cuda:0')
episode: 543 training return: tensor(-1526519.7500, device='cuda:0')
epoch: 136 test_true_pfm: 20.400140286841523
episode: 544 training return: tensor(-112529.6875, device='cuda:0')
episode: 545 training return: tensor(-28009.8691, device='cuda:0')
episode: 546 training return: tensor(-1532150.8750, device='cuda:0')
episode: 547 training return: tensor(-15717.2764, device='cuda:0')
epoch: 137 test_true_pfm: -103.87315327373379
episode: 548 training return: tensor(-1738882.6250, device='cuda:0')
episode: 549 training return: tensor(-64972.5273, device='cuda:0')
episode: 550 training return: tensor(-5843847.5000, device='cuda:0')
episode: 551 training return: tensor(-121528.5938, device='cuda:0')
epoch: 138 test_true_pfm: -57.02228127700462
episode: 552 training return: tensor(-102421.8438, device='cuda:0')
episode: 553 training return: tensor(-96994.7422, device='cuda:0')
episode: 554 training return: tensor(-108970.2891, device='cuda:0')
episode: 555 training return: tensor(-112117.2656, device='cuda:0')
epoch: 139 test_true_pfm: -79.90713373233939
episode: 556 training return: tensor(-991364.1250, device='cuda:0')
episode: 557 training return: tensor(-873986.5000, device='cuda:0')
episode: 558 training return: tensor(-1072855.1250, device='cuda:0')
episode: 559 training return: tensor(-108607.8594, device='cuda:0')
epoch: 140 test_true_pfm: -165.89965244140697
episode: 560 training return: tensor(-1465590.8750, device='cuda:0')
episode: 561 training return: tensor(-1267880.1250, device='cuda:0')
episode: 562 training return: tensor(-8699268., device='cuda:0')
episode: 563 training return: tensor(-1392692.7500, device='cuda:0')
epoch: 141 test_true_pfm: -85.54224183885157
episode: 564 training return: tensor(-1186626.3750, device='cuda:0')
episode: 565 training return: tensor(-997544.3750, device='cuda:0')
episode: 566 training return: tensor(-1428073.6250, device='cuda:0')
episode: 567 training return: tensor(-1061719.3750, device='cuda:0')
epoch: 142 test_true_pfm: 13.157551805266221
episode: 568 training return: tensor(-972954.2500, device='cuda:0')
episode: 569 training return: tensor(-119751.4531, device='cuda:0')
episode: 570 training return: tensor(-970276.1875, device='cuda:0')
episode: 571 training return: tensor(-1043542.9375, device='cuda:0')
epoch: 143 test_true_pfm: -0.0207884185643555
episode: 572 training return: tensor(-1267237.7500, device='cuda:0')
episode: 573 training return: tensor(-116912.8984, device='cuda:0')
episode: 574 training return: tensor(-26618506., device='cuda:0')
episode: 575 training return: tensor(-983012.8750, device='cuda:0')
epoch: 144 test_true_pfm: -48.92969640079402
episode: 576 training return: tensor(-103243.2344, device='cuda:0')
episode: 577 training return: tensor(-97820.6562, device='cuda:0')
episode: 578 training return: tensor(-28498268., device='cuda:0')
episode: 579 training return: tensor(-111323.0234, device='cuda:0')
epoch: 145 test_true_pfm: -23.911112937653968
episode: 580 training return: tensor(-11460.9902, device='cuda:0')
episode: 581 training return: tensor(-15203.8691, device='cuda:0')
episode: 582 training return: tensor(-10818.2891, device='cuda:0')
episode: 583 training return: tensor(-14415.4033, device='cuda:0')
epoch: 146 test_true_pfm: -25.562259041363802
episode: 584 training return: tensor(-2599040., device='cuda:0')
episode: 585 training return: tensor(-96945.0703, device='cuda:0')
episode: 586 training return: tensor(-14994.4141, device='cuda:0')
episode: 587 training return: tensor(-23651872., device='cuda:0')
epoch: 147 test_true_pfm: -52.27561813638115
episode: 588 training return: tensor(-13336.0566, device='cuda:0')
episode: 589 training return: tensor(-1305386.3750, device='cuda:0')
episode: 590 training return: tensor(-12288.4883, device='cuda:0')
episode: 591 training return: tensor(-119993.6172, device='cuda:0')
epoch: 148 test_true_pfm: -38.55540601029478
episode: 592 training return: tensor(-2022111.3750, device='cuda:0')
episode: 593 training return: tensor(-1506959.8750, device='cuda:0')
episode: 594 training return: tensor(-99009.0938, device='cuda:0')
episode: 595 training return: tensor(-986750.8750, device='cuda:0')
epoch: 149 test_true_pfm: 10.30891449078724
episode: 596 training return: tensor(-1047658.8125, device='cuda:0')
episode: 597 training return: tensor(-13296.3555, device='cuda:0')
episode: 598 training return: tensor(-56962.0547, device='cuda:0')
episode: 599 training return: tensor(-2752503., device='cuda:0')
epoch: 150 test_true_pfm: 235.28720060717492
