['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'baseline', '--traj', 'expert', '--seed', '3']
episode: 0 training return: tensor(-829.2538, device='cuda:0')
episode: 1 training return: tensor(-897.6293, device='cuda:0')
episode: 2 training return: tensor(-886.6139, device='cuda:0')
episode: 3 training return: tensor(-972.0399, device='cuda:0')
epoch: 1 test_true_pfm: 584.2591796542083 sim_pfm: -873.1158925437679
episode: 4 training return: tensor(-924.8726, device='cuda:0')
episode: 5 training return: tensor(-889.6354, device='cuda:0')
episode: 6 training return: tensor(-941.7579, device='cuda:0')
episode: 7 training return: tensor(-875.7053, device='cuda:0')
epoch: 2 test_true_pfm: 278.1021290690384 sim_pfm: -898.7040855508918
episode: 8 training return: tensor(-919.7955, device='cuda:0')
episode: 9 training return: tensor(-935.7599, device='cuda:0')
episode: 10 training return: tensor(-838.7579, device='cuda:0')
episode: 11 training return: tensor(-889.9766, device='cuda:0')
epoch: 3 test_true_pfm: 0.2005723096757954 sim_pfm: -993.5131078710159
episode: 12 training return: tensor(-993.9399, device='cuda:0')
episode: 13 training return: tensor(-979.3210, device='cuda:0')
episode: 14 training return: tensor(-991.2104, device='cuda:0')
episode: 15 training return: tensor(-934.0589, device='cuda:0')
epoch: 4 test_true_pfm: -793.1263928917546 sim_pfm: -939.0730006598557
episode: 16 training return: tensor(-666.9919, device='cuda:0')
episode: 17 training return: tensor(-903.1047, device='cuda:0')
episode: 18 training return: tensor(-918.5599, device='cuda:0')
episode: 19 training return: tensor(-933.5115, device='cuda:0')
epoch: 5 test_true_pfm: 28.61422322311066 sim_pfm: -905.1587254802386
episode: 20 training return: tensor(-915.3909, device='cuda:0')
episode: 21 training return: tensor(-947.1058, device='cuda:0')
episode: 22 training return: tensor(-950.1206, device='cuda:0')
episode: 23 training return: tensor(-909.4282, device='cuda:0')
epoch: 6 test_true_pfm: -85.93020010468315 sim_pfm: -994.9544533689817
episode: 24 training return: tensor(-864.9172, device='cuda:0')
episode: 25 training return: tensor(-886.7879, device='cuda:0')
episode: 26 training return: tensor(-982.1186, device='cuda:0')
episode: 27 training return: tensor(-987.5081, device='cuda:0')
epoch: 7 test_true_pfm: -3.746954517504184 sim_pfm: -999.8350023428599
episode: 28 training return: tensor(-988.1298, device='cuda:0')
episode: 29 training return: tensor(-977.2052, device='cuda:0')
episode: 30 training return: tensor(-970.5221, device='cuda:0')
episode: 31 training return: tensor(-975.4632, device='cuda:0')
epoch: 8 test_true_pfm: 74.34942646600597 sim_pfm: -920.0632969084351
episode: 32 training return: tensor(-952.8945, device='cuda:0')
episode: 33 training return: tensor(-895.5653, device='cuda:0')
episode: 34 training return: tensor(-947.1326, device='cuda:0')
episode: 35 training return: tensor(-933.8321, device='cuda:0')
epoch: 9 test_true_pfm: 4.291156193114991 sim_pfm: -965.9445803898076
episode: 36 training return: tensor(-944.6777, device='cuda:0')
episode: 37 training return: tensor(-897.7310, device='cuda:0')
episode: 38 training return: tensor(-950.9380, device='cuda:0')
episode: 39 training return: tensor(-817.2522, device='cuda:0')
epoch: 10 test_true_pfm: 179.55109708665577 sim_pfm: -945.6674049023617
episode: 40 training return: tensor(-962.2936, device='cuda:0')
episode: 41 training return: tensor(-937.4997, device='cuda:0')
episode: 42 training return: tensor(-965.1985, device='cuda:0')
episode: 43 training return: tensor(-963.1705, device='cuda:0')
epoch: 11 test_true_pfm: 91.73695670595366 sim_pfm: -934.6272638435476
episode: 44 training return: tensor(-931.8508, device='cuda:0')
episode: 45 training return: tensor(-947.1331, device='cuda:0')
episode: 46 training return: tensor(-945.1166, device='cuda:0')
episode: 47 training return: tensor(-944.0239, device='cuda:0')
epoch: 12 test_true_pfm: 60.50891933765598 sim_pfm: -945.2075962542245
episode: 48 training return: tensor(-955.9067, device='cuda:0')
episode: 49 training return: tensor(-936.2822, device='cuda:0')
episode: 50 training return: tensor(-931.3408, device='cuda:0')
episode: 51 training return: tensor(-958.4623, device='cuda:0')
epoch: 13 test_true_pfm: 107.21646194813952 sim_pfm: -886.231840411822
episode: 52 training return: tensor(-945.8421, device='cuda:0')
episode: 53 training return: tensor(-955.0405, device='cuda:0')
episode: 54 training return: tensor(-943.0316, device='cuda:0')
episode: 55 training return: tensor(-896.3098, device='cuda:0')
epoch: 14 test_true_pfm: 154.82142325214784 sim_pfm: -835.2773894246202
episode: 56 training return: tensor(-941.2450, device='cuda:0')
episode: 57 training return: tensor(-919.4092, device='cuda:0')
episode: 58 training return: tensor(-925.2272, device='cuda:0')
episode: 59 training return: tensor(-918.5528, device='cuda:0')
epoch: 15 test_true_pfm: 133.30716074010596 sim_pfm: -913.5248613557391
episode: 60 training return: tensor(-899.1232, device='cuda:0')
episode: 61 training return: tensor(-939.4064, device='cuda:0')
episode: 62 training return: tensor(-935.8785, device='cuda:0')
episode: 63 training return: tensor(-907.1456, device='cuda:0')
epoch: 16 test_true_pfm: 114.67426434156387 sim_pfm: -949.5627313291965
episode: 64 training return: tensor(-918.1496, device='cuda:0')
episode: 65 training return: tensor(-902.9739, device='cuda:0')
episode: 66 training return: tensor(-900.4937, device='cuda:0')
episode: 67 training return: tensor(-905.9731, device='cuda:0')
epoch: 17 test_true_pfm: 78.5568171686629 sim_pfm: -961.0482303102812
episode: 68 training return: tensor(-862.7924, device='cuda:0')
episode: 69 training return: tensor(-561.0652, device='cuda:0')
episode: 70 training return: tensor(-889.3984, device='cuda:0')
episode: 71 training return: tensor(-840.1181, device='cuda:0')
epoch: 18 test_true_pfm: 125.91502711518696 sim_pfm: -854.7264844129483
episode: 72 training return: tensor(-904.7912, device='cuda:0')
episode: 73 training return: tensor(-906.7780, device='cuda:0')
episode: 74 training return: tensor(-919.0262, device='cuda:0')
episode: 75 training return: tensor(-876.9813, device='cuda:0')
epoch: 19 test_true_pfm: 101.02844440401135 sim_pfm: -857.7043911044797
episode: 76 training return: tensor(-881.4530, device='cuda:0')
episode: 77 training return: tensor(-929.5331, device='cuda:0')
episode: 78 training return: tensor(-902.7021, device='cuda:0')
episode: 79 training return: tensor(-893.2761, device='cuda:0')
epoch: 20 test_true_pfm: 117.78959520809447 sim_pfm: -861.2042076485232
episode: 80 training return: tensor(-859.2609, device='cuda:0')
episode: 81 training return: tensor(-869.0242, device='cuda:0')
episode: 82 training return: tensor(-908.5404, device='cuda:0')
episode: 83 training return: tensor(-781.8433, device='cuda:0')
epoch: 21 test_true_pfm: 145.28634135193758 sim_pfm: -851.6537467141947
episode: 84 training return: tensor(-880.9809, device='cuda:0')
episode: 85 training return: tensor(-896.4519, device='cuda:0')
episode: 86 training return: tensor(-810.8536, device='cuda:0')
episode: 87 training return: tensor(-811.0569, device='cuda:0')
epoch: 22 test_true_pfm: 107.59391435926176 sim_pfm: -835.7953136349097
episode: 88 training return: tensor(-767.3289, device='cuda:0')
episode: 89 training return: tensor(-891.6746, device='cuda:0')
episode: 90 training return: tensor(-794.6514, device='cuda:0')
episode: 91 training return: tensor(-810.1349, device='cuda:0')
epoch: 23 test_true_pfm: 103.40127042997786 sim_pfm: -851.3925302865294
episode: 92 training return: tensor(-808.3856, device='cuda:0')
episode: 93 training return: tensor(-795.5143, device='cuda:0')
episode: 94 training return: tensor(-830.1876, device='cuda:0')
episode: 95 training return: tensor(-848.8997, device='cuda:0')
epoch: 24 test_true_pfm: 125.57887732108618 sim_pfm: -860.8786503076553
episode: 96 training return: tensor(-768.5701, device='cuda:0')
episode: 97 training return: tensor(-757.2390, device='cuda:0')
episode: 98 training return: tensor(-693.9834, device='cuda:0')
episode: 99 training return: tensor(-783.2280, device='cuda:0')
epoch: 25 test_true_pfm: 118.0174916126298 sim_pfm: -823.001909510543
episode: 100 training return: tensor(-812.4534, device='cuda:0')
episode: 101 training return: tensor(-857.1481, device='cuda:0')
episode: 102 training return: tensor(-743.1638, device='cuda:0')
episode: 103 training return: tensor(-768.9451, device='cuda:0')
epoch: 26 test_true_pfm: 71.38301678511057 sim_pfm: -804.54683545356
episode: 104 training return: tensor(-756.1257, device='cuda:0')
episode: 105 training return: tensor(-745.1097, device='cuda:0')
episode: 106 training return: tensor(-709.4482, device='cuda:0')
episode: 107 training return: tensor(-551.1725, device='cuda:0')
epoch: 27 test_true_pfm: 57.44666246034189 sim_pfm: -785.3025150455845
episode: 108 training return: tensor(-764.9427, device='cuda:0')
episode: 109 training return: tensor(-829.1998, device='cuda:0')
episode: 110 training return: tensor(-727.6779, device='cuda:0')
episode: 111 training return: tensor(-731.0871, device='cuda:0')
epoch: 28 test_true_pfm: -205.73327784331636 sim_pfm: -737.4169507720508
episode: 112 training return: tensor(-816.0729, device='cuda:0')
episode: 113 training return: tensor(-775.2694, device='cuda:0')
episode: 114 training return: tensor(-733.4835, device='cuda:0')
episode: 115 training return: tensor(-800.1951, device='cuda:0')
epoch: 29 test_true_pfm: 50.26511733084366 sim_pfm: -789.7459652075389
episode: 116 training return: tensor(-710.2748, device='cuda:0')
episode: 117 training return: tensor(-821.6011, device='cuda:0')
episode: 118 training return: tensor(-712.9850, device='cuda:0')
episode: 119 training return: tensor(-765.6059, device='cuda:0')
epoch: 30 test_true_pfm: 103.00703932913524 sim_pfm: -689.4263971820861
episode: 120 training return: tensor(-740.8278, device='cuda:0')
episode: 121 training return: tensor(-733.0327, device='cuda:0')
episode: 122 training return: tensor(-723.5954, device='cuda:0')
episode: 123 training return: tensor(-757.4020, device='cuda:0')
epoch: 31 test_true_pfm: -26.964815908809836 sim_pfm: -713.9070990906717
episode: 124 training return: tensor(-717.9338, device='cuda:0')
episode: 125 training return: tensor(-745.3968, device='cuda:0')
episode: 126 training return: tensor(-764.5773, device='cuda:0')
episode: 127 training return: tensor(-620.9374, device='cuda:0')
epoch: 32 test_true_pfm: 86.92285107764968 sim_pfm: -773.5799061600119
episode: 128 training return: tensor(-731.2180, device='cuda:0')
episode: 129 training return: tensor(-657.1864, device='cuda:0')
episode: 130 training return: tensor(-684.2585, device='cuda:0')
episode: 131 training return: tensor(-908.1702, device='cuda:0')
epoch: 33 test_true_pfm: 47.88580036434371 sim_pfm: -783.7509943866947
episode: 132 training return: tensor(-746.3729, device='cuda:0')
episode: 133 training return: tensor(-664.3513, device='cuda:0')
episode: 134 training return: tensor(-768.0226, device='cuda:0')
episode: 135 training return: tensor(-690.3210, device='cuda:0')
epoch: 34 test_true_pfm: 90.45106638299534 sim_pfm: -703.6859678986172
episode: 136 training return: tensor(-732.5455, device='cuda:0')
episode: 137 training return: tensor(-695.5597, device='cuda:0')
episode: 138 training return: tensor(-694.5228, device='cuda:0')
episode: 139 training return: tensor(-642.3991, device='cuda:0')
epoch: 35 test_true_pfm: 68.21629035142074 sim_pfm: -680.7754474232594
episode: 140 training return: tensor(-671.7019, device='cuda:0')
episode: 141 training return: tensor(-668.6730, device='cuda:0')
episode: 142 training return: tensor(-737.4281, device='cuda:0')
episode: 143 training return: tensor(-716.7482, device='cuda:0')
epoch: 36 test_true_pfm: 70.76313915641526 sim_pfm: -722.0993037450438
episode: 144 training return: tensor(-710.5690, device='cuda:0')
episode: 145 training return: tensor(-706.3217, device='cuda:0')
episode: 146 training return: tensor(-791.2178, device='cuda:0')
episode: 147 training return: tensor(-721.6647, device='cuda:0')
epoch: 37 test_true_pfm: -82.25623189201586 sim_pfm: -664.8733641180443
episode: 148 training return: tensor(-689.5423, device='cuda:0')
episode: 149 training return: tensor(-698.1752, device='cuda:0')
episode: 150 training return: tensor(-698.3589, device='cuda:0')
episode: 151 training return: tensor(-673.4696, device='cuda:0')
epoch: 38 test_true_pfm: 5.056705876289624 sim_pfm: -661.8173707043752
episode: 152 training return: tensor(-710.7654, device='cuda:0')
episode: 153 training return: tensor(-699.2944, device='cuda:0')
episode: 154 training return: tensor(-693.3869, device='cuda:0')
episode: 155 training return: tensor(-898.4040, device='cuda:0')
epoch: 39 test_true_pfm: 87.09838628586586 sim_pfm: -635.5723912036046
episode: 156 training return: tensor(-651.8159, device='cuda:0')
episode: 157 training return: tensor(-738.1312, device='cuda:0')
episode: 158 training return: tensor(-741.5807, device='cuda:0')
episode: 159 training return: tensor(-704.6817, device='cuda:0')
epoch: 40 test_true_pfm: -81.1665788296323 sim_pfm: -674.5669874291247
episode: 160 training return: tensor(-647.0482, device='cuda:0')
episode: 161 training return: tensor(-753.5869, device='cuda:0')
episode: 162 training return: tensor(-812.8696, device='cuda:0')
episode: 163 training return: tensor(-667.7063, device='cuda:0')
epoch: 41 test_true_pfm: -130.5430650356135 sim_pfm: -679.9393701494361
episode: 164 training return: tensor(-676.8047, device='cuda:0')
episode: 165 training return: tensor(-780.9748, device='cuda:0')
episode: 166 training return: tensor(-673.8072, device='cuda:0')
episode: 167 training return: tensor(-700.8132, device='cuda:0')
epoch: 42 test_true_pfm: -132.12039144425933 sim_pfm: -673.1109602781944
episode: 168 training return: tensor(-708.0251, device='cuda:0')
episode: 169 training return: tensor(-717.4235, device='cuda:0')
episode: 170 training return: tensor(-728.3460, device='cuda:0')
episode: 171 training return: tensor(-712.0931, device='cuda:0')
epoch: 43 test_true_pfm: -269.03025195849614 sim_pfm: -697.5344725850349
episode: 172 training return: tensor(-714.4692, device='cuda:0')
episode: 173 training return: tensor(-779.3471, device='cuda:0')
episode: 174 training return: tensor(-781.4905, device='cuda:0')
episode: 175 training return: tensor(-806.7678, device='cuda:0')
epoch: 44 test_true_pfm: -232.49986210950786 sim_pfm: -679.7997046158416
episode: 176 training return: tensor(-760.7295, device='cuda:0')
episode: 177 training return: tensor(-714.1166, device='cuda:0')
episode: 178 training return: tensor(-662.3301, device='cuda:0')
episode: 179 training return: tensor(-710.0812, device='cuda:0')
epoch: 45 test_true_pfm: -189.2198642785129 sim_pfm: -686.6818016791561
episode: 180 training return: tensor(-769.5323, device='cuda:0')
episode: 181 training return: tensor(-727.2854, device='cuda:0')
episode: 182 training return: tensor(-719.8316, device='cuda:0')
episode: 183 training return: tensor(-689.0697, device='cuda:0')
epoch: 46 test_true_pfm: -167.4083868469024 sim_pfm: -686.7436746150876
episode: 184 training return: tensor(-771.3786, device='cuda:0')
episode: 185 training return: tensor(-710.8237, device='cuda:0')
episode: 186 training return: tensor(-746.8348, device='cuda:0')
episode: 187 training return: tensor(-676.6801, device='cuda:0')
epoch: 47 test_true_pfm: -56.9417129237624 sim_pfm: -692.6809932809944
episode: 188 training return: tensor(-724.5549, device='cuda:0')
episode: 189 training return: tensor(-693.3395, device='cuda:0')
episode: 190 training return: tensor(-698.6488, device='cuda:0')
episode: 191 training return: tensor(-865.8222, device='cuda:0')
epoch: 48 test_true_pfm: -347.03835407337095 sim_pfm: -684.6396042609898
episode: 192 training return: tensor(-715.9530, device='cuda:0')
episode: 193 training return: tensor(-652.3563, device='cuda:0')
episode: 194 training return: tensor(-683.7471, device='cuda:0')
episode: 195 training return: tensor(-676.8756, device='cuda:0')
epoch: 49 test_true_pfm: -266.3882399577622 sim_pfm: -695.9424132066779
episode: 196 training return: tensor(-712.2032, device='cuda:0')
episode: 197 training return: tensor(-761.6613, device='cuda:0')
episode: 198 training return: tensor(-720.0771, device='cuda:0')
episode: 199 training return: tensor(-668.8633, device='cuda:0')
epoch: 50 test_true_pfm: -276.3867754770763 sim_pfm: -691.2439250670528
episode: 200 training return: tensor(-632.8694, device='cuda:0')
episode: 201 training return: tensor(-665.0102, device='cuda:0')
episode: 202 training return: tensor(-648.1749, device='cuda:0')
episode: 203 training return: tensor(-723.8979, device='cuda:0')
epoch: 51 test_true_pfm: -4.988388295570384 sim_pfm: -639.1986585166693
episode: 204 training return: tensor(-642.9986, device='cuda:0')
episode: 205 training return: tensor(-686.1068, device='cuda:0')
episode: 206 training return: tensor(-674.4841, device='cuda:0')
episode: 207 training return: tensor(-734.3204, device='cuda:0')
epoch: 52 test_true_pfm: -90.37258823850256 sim_pfm: -651.1046751487689
episode: 208 training return: tensor(-669.2328, device='cuda:0')
episode: 209 training return: tensor(-688.8679, device='cuda:0')
episode: 210 training return: tensor(-716.8290, device='cuda:0')
episode: 211 training return: tensor(-756.6444, device='cuda:0')
epoch: 53 test_true_pfm: -342.20785545584494 sim_pfm: -679.8396202297881
episode: 212 training return: tensor(-644.1410, device='cuda:0')
episode: 213 training return: tensor(-755.5212, device='cuda:0')
episode: 214 training return: tensor(-720.6340, device='cuda:0')
episode: 215 training return: tensor(-708.4643, device='cuda:0')
epoch: 54 test_true_pfm: -156.71226056378396 sim_pfm: -663.8238926571794
episode: 216 training return: tensor(-672.9100, device='cuda:0')
episode: 217 training return: tensor(-651.0919, device='cuda:0')
episode: 218 training return: tensor(-634.8788, device='cuda:0')
episode: 219 training return: tensor(-698.0628, device='cuda:0')
epoch: 55 test_true_pfm: -163.7471519006773 sim_pfm: -630.0152067693028
episode: 220 training return: tensor(-687.4484, device='cuda:0')
episode: 221 training return: tensor(-633.2708, device='cuda:0')
episode: 222 training return: tensor(-736.6036, device='cuda:0')
episode: 223 training return: tensor(-651.6618, device='cuda:0')
epoch: 56 test_true_pfm: -173.38075804651012 sim_pfm: -669.6690217768773
episode: 224 training return: tensor(-695.2081, device='cuda:0')
episode: 225 training return: tensor(-726.3184, device='cuda:0')
episode: 226 training return: tensor(-756.2558, device='cuda:0')
episode: 227 training return: tensor(-688.7786, device='cuda:0')
epoch: 57 test_true_pfm: -164.98072421061508 sim_pfm: -724.9298660273975
episode: 228 training return: tensor(-653.2910, device='cuda:0')
episode: 229 training return: tensor(-627.2792, device='cuda:0')
episode: 230 training return: tensor(-688.2900, device='cuda:0')
episode: 231 training return: tensor(-906.7671, device='cuda:0')
epoch: 58 test_true_pfm: -130.3351446000902 sim_pfm: -659.4013404163221
episode: 232 training return: tensor(-731.9044, device='cuda:0')
episode: 233 training return: tensor(-761.1078, device='cuda:0')
episode: 234 training return: tensor(-713.5986, device='cuda:0')
episode: 235 training return: tensor(-733.8842, device='cuda:0')
epoch: 59 test_true_pfm: -133.3287654844616 sim_pfm: -628.3955580577409
episode: 236 training return: tensor(-624.3656, device='cuda:0')
episode: 237 training return: tensor(-711.1283, device='cuda:0')
episode: 238 training return: tensor(-666.6100, device='cuda:0')
episode: 239 training return: tensor(-715.2109, device='cuda:0')
epoch: 60 test_true_pfm: -82.42501257437804 sim_pfm: -667.5981238471965
episode: 240 training return: tensor(-754.7874, device='cuda:0')
episode: 241 training return: tensor(-651.1631, device='cuda:0')
episode: 242 training return: tensor(-583.2990, device='cuda:0')
episode: 243 training return: tensor(-667.0206, device='cuda:0')
epoch: 61 test_true_pfm: 18.655313193505048 sim_pfm: -613.5885732116488
episode: 244 training return: tensor(-613.5854, device='cuda:0')
episode: 245 training return: tensor(-695.7363, device='cuda:0')
episode: 246 training return: tensor(-695.6382, device='cuda:0')
episode: 247 training return: tensor(-640.5206, device='cuda:0')
epoch: 62 test_true_pfm: -94.108355520913 sim_pfm: -596.2071842519412
episode: 248 training return: tensor(-602.2148, device='cuda:0')
episode: 249 training return: tensor(-694.5467, device='cuda:0')
episode: 250 training return: tensor(-661.3917, device='cuda:0')
episode: 251 training return: tensor(-680.7975, device='cuda:0')
epoch: 63 test_true_pfm: -74.64451669765026 sim_pfm: -604.3018379076384
episode: 252 training return: tensor(-685.3850, device='cuda:0')
episode: 253 training return: tensor(-667.6351, device='cuda:0')
episode: 254 training return: tensor(-799.2017, device='cuda:0')
episode: 255 training return: tensor(-649.8476, device='cuda:0')
epoch: 64 test_true_pfm: -234.65946731972713 sim_pfm: -570.474489716813
episode: 256 training return: tensor(-702.1308, device='cuda:0')
episode: 257 training return: tensor(-665.7613, device='cuda:0')
episode: 258 training return: tensor(-674.6406, device='cuda:0')
episode: 259 training return: tensor(-665.9955, device='cuda:0')
epoch: 65 test_true_pfm: -4.71452386410787 sim_pfm: -597.8536170745889
episode: 260 training return: tensor(-657.7183, device='cuda:0')
episode: 261 training return: tensor(-665.7296, device='cuda:0')
episode: 262 training return: tensor(-658.1329, device='cuda:0')
episode: 263 training return: tensor(-678.3799, device='cuda:0')
epoch: 66 test_true_pfm: -138.12951455389376 sim_pfm: -685.0733113596992
episode: 264 training return: tensor(-672.5774, device='cuda:0')
episode: 265 training return: tensor(-687.4069, device='cuda:0')
episode: 266 training return: tensor(-596.7872, device='cuda:0')
episode: 267 training return: tensor(-636.9133, device='cuda:0')
epoch: 67 test_true_pfm: -87.54985454643429 sim_pfm: -637.6882715525184
episode: 268 training return: tensor(-620.8487, device='cuda:0')
episode: 269 training return: tensor(-711.5486, device='cuda:0')
episode: 270 training return: tensor(-619.2927, device='cuda:0')
episode: 271 training return: tensor(-634.6720, device='cuda:0')
epoch: 68 test_true_pfm: 26.644139486102265 sim_pfm: -711.198273109893
episode: 272 training return: tensor(-649.7163, device='cuda:0')
episode: 273 training return: tensor(-776.2827, device='cuda:0')
episode: 274 training return: tensor(-669.2784, device='cuda:0')
episode: 275 training return: tensor(-652.1648, device='cuda:0')
epoch: 69 test_true_pfm: 83.63504912243137 sim_pfm: -646.1224055578932
episode: 276 training return: tensor(-713.9937, device='cuda:0')
episode: 277 training return: tensor(-629.2194, device='cuda:0')
episode: 278 training return: tensor(-657.9399, device='cuda:0')
episode: 279 training return: tensor(-843.3807, device='cuda:0')
epoch: 70 test_true_pfm: -281.65993680201103 sim_pfm: -629.5112451758856
episode: 280 training return: tensor(-819.4905, device='cuda:0')
episode: 281 training return: tensor(-674.6004, device='cuda:0')
episode: 282 training return: tensor(-745.4174, device='cuda:0')
episode: 283 training return: tensor(-656.4366, device='cuda:0')
epoch: 71 test_true_pfm: 16.069030749653603 sim_pfm: -575.4590933672929
episode: 284 training return: tensor(-723.2347, device='cuda:0')
episode: 285 training return: tensor(-704.4946, device='cuda:0')
episode: 286 training return: tensor(-793.4863, device='cuda:0')
episode: 287 training return: tensor(-631.6682, device='cuda:0')
epoch: 72 test_true_pfm: 24.804060197538416 sim_pfm: -619.4995411353497
episode: 288 training return: tensor(-685.1639, device='cuda:0')
episode: 289 training return: tensor(-687.4848, device='cuda:0')
episode: 290 training return: tensor(-599.4274, device='cuda:0')
episode: 291 training return: tensor(-651.8347, device='cuda:0')
epoch: 73 test_true_pfm: 46.629228378820365 sim_pfm: -601.1118122574408
episode: 292 training return: tensor(-666.6470, device='cuda:0')
episode: 293 training return: tensor(-798.7753, device='cuda:0')
episode: 294 training return: tensor(-647.6578, device='cuda:0')
episode: 295 training return: tensor(-761.5892, device='cuda:0')
epoch: 74 test_true_pfm: -15.450944948358787 sim_pfm: -607.0654490755405
episode: 296 training return: tensor(-634.4332, device='cuda:0')
episode: 297 training return: tensor(-623.9119, device='cuda:0')
episode: 298 training return: tensor(-675.9960, device='cuda:0')
episode: 299 training return: tensor(-651.4957, device='cuda:0')
epoch: 75 test_true_pfm: -89.88341196982537 sim_pfm: -573.1106029271226
episode: 300 training return: tensor(-650.4299, device='cuda:0')
episode: 301 training return: tensor(-644.0717, device='cuda:0')
episode: 302 training return: tensor(-629.8904, device='cuda:0')
episode: 303 training return: tensor(-655.0906, device='cuda:0')
epoch: 76 test_true_pfm: -46.22031732094457 sim_pfm: -673.745409289375
episode: 304 training return: tensor(-592.7953, device='cuda:0')
episode: 305 training return: tensor(-639.4586, device='cuda:0')
episode: 306 training return: tensor(-712.7075, device='cuda:0')
episode: 307 training return: tensor(-657.4860, device='cuda:0')
epoch: 77 test_true_pfm: -26.71664305136059 sim_pfm: -641.2141942883221
episode: 308 training return: tensor(-669.4927, device='cuda:0')
episode: 309 training return: tensor(-655.6031, device='cuda:0')
episode: 310 training return: tensor(-656.0503, device='cuda:0')
episode: 311 training return: tensor(-701.1309, device='cuda:0')
epoch: 78 test_true_pfm: 45.92359258386178 sim_pfm: -572.2376988329148
episode: 312 training return: tensor(-911.9642, device='cuda:0')
episode: 313 training return: tensor(-712.0366, device='cuda:0')
episode: 314 training return: tensor(-632.5764, device='cuda:0')
episode: 315 training return: tensor(-657.2247, device='cuda:0')
epoch: 79 test_true_pfm: 93.56439287992276 sim_pfm: -650.8464756878869
episode: 316 training return: tensor(-687.5386, device='cuda:0')
episode: 317 training return: tensor(-809.8708, device='cuda:0')
episode: 318 training return: tensor(-720.8525, device='cuda:0')
episode: 319 training return: tensor(-744.5061, device='cuda:0')
epoch: 80 test_true_pfm: 164.64913889827753 sim_pfm: -605.3438657543933
episode: 320 training return: tensor(-535.6569, device='cuda:0')
episode: 321 training return: tensor(-674.2288, device='cuda:0')
episode: 322 training return: tensor(-729.1085, device='cuda:0')
episode: 323 training return: tensor(-736.1417, device='cuda:0')
epoch: 81 test_true_pfm: -146.87067493187854 sim_pfm: -540.5055043205211
episode: 324 training return: tensor(-695.3021, device='cuda:0')
episode: 325 training return: tensor(-662.8987, device='cuda:0')
episode: 326 training return: tensor(-615.1519, device='cuda:0')
episode: 327 training return: tensor(-625.7329, device='cuda:0')
epoch: 82 test_true_pfm: 57.70101849802796 sim_pfm: -589.725883041819
episode: 328 training return: tensor(-669.0329, device='cuda:0')
episode: 329 training return: tensor(-698.8193, device='cuda:0')
episode: 330 training return: tensor(-608.2403, device='cuda:0')
episode: 331 training return: tensor(-671.6548, device='cuda:0')
epoch: 83 test_true_pfm: -28.783129862592535 sim_pfm: -542.9076865296034
episode: 332 training return: tensor(-743.1082, device='cuda:0')
episode: 333 training return: tensor(-679.2148, device='cuda:0')
episode: 334 training return: tensor(-681.4671, device='cuda:0')
episode: 335 training return: tensor(-633.2935, device='cuda:0')
epoch: 84 test_true_pfm: -22.676778532034106 sim_pfm: -585.9370530145243
episode: 336 training return: tensor(-718.2077, device='cuda:0')
episode: 337 training return: tensor(-624.6713, device='cuda:0')
episode: 338 training return: tensor(-632.6277, device='cuda:0')
episode: 339 training return: tensor(-819.0620, device='cuda:0')
epoch: 85 test_true_pfm: 42.56165984827977 sim_pfm: -558.7067061935862
episode: 340 training return: tensor(-715.5732, device='cuda:0')
episode: 341 training return: tensor(-621.2272, device='cuda:0')
episode: 342 training return: tensor(-644.0735, device='cuda:0')
episode: 343 training return: tensor(-664.8618, device='cuda:0')
epoch: 86 test_true_pfm: -89.88409433135872 sim_pfm: -640.8993151662871
episode: 344 training return: tensor(-659.0665, device='cuda:0')
episode: 345 training return: tensor(-721.8975, device='cuda:0')
episode: 346 training return: tensor(-577.5733, device='cuda:0')
episode: 347 training return: tensor(-806.3663, device='cuda:0')
epoch: 87 test_true_pfm: -18.067428462930792 sim_pfm: -553.6591192645332
episode: 348 training return: tensor(-679.9760, device='cuda:0')
episode: 349 training return: tensor(-698.8826, device='cuda:0')
episode: 350 training return: tensor(-626.1481, device='cuda:0')
episode: 351 training return: tensor(-729.0353, device='cuda:0')
epoch: 88 test_true_pfm: 49.37773682256372 sim_pfm: -575.2030204205463
episode: 352 training return: tensor(-661.1445, device='cuda:0')
episode: 353 training return: tensor(-760.1842, device='cuda:0')
episode: 354 training return: tensor(-726.6901, device='cuda:0')
episode: 355 training return: tensor(-661.2306, device='cuda:0')
epoch: 89 test_true_pfm: 102.23207976622466 sim_pfm: -592.7279019424071
episode: 356 training return: tensor(-598.7739, device='cuda:0')
episode: 357 training return: tensor(-738.3967, device='cuda:0')
episode: 358 training return: tensor(-655.9345, device='cuda:0')
episode: 359 training return: tensor(-676.4262, device='cuda:0')
epoch: 90 test_true_pfm: 98.63524435829471 sim_pfm: -550.174018612442
episode: 360 training return: tensor(-585.2358, device='cuda:0')
episode: 361 training return: tensor(-697.2970, device='cuda:0')
episode: 362 training return: tensor(-709.6660, device='cuda:0')
episode: 363 training return: tensor(-787.0323, device='cuda:0')
epoch: 91 test_true_pfm: -62.73822942944477 sim_pfm: -580.0292010901807
episode: 364 training return: tensor(-703.5726, device='cuda:0')
episode: 365 training return: tensor(-618.3680, device='cuda:0')
episode: 366 training return: tensor(-648.5607, device='cuda:0')
episode: 367 training return: tensor(-649.0806, device='cuda:0')
epoch: 92 test_true_pfm: 27.60370749719569 sim_pfm: -720.6032213683551
episode: 368 training return: tensor(-683.7978, device='cuda:0')
episode: 369 training return: tensor(-640.6095, device='cuda:0')
episode: 370 training return: tensor(-795.2525, device='cuda:0')
episode: 371 training return: tensor(-660.0534, device='cuda:0')
epoch: 93 test_true_pfm: 25.76415373264672 sim_pfm: -616.6367857589697
episode: 372 training return: tensor(-678.9331, device='cuda:0')
episode: 373 training return: tensor(-690.0107, device='cuda:0')
episode: 374 training return: tensor(-646.5536, device='cuda:0')
episode: 375 training return: tensor(-663.2877, device='cuda:0')
epoch: 94 test_true_pfm: 51.78190286752244 sim_pfm: -595.4426077837124
episode: 376 training return: tensor(-687.9380, device='cuda:0')
episode: 377 training return: tensor(-690.1725, device='cuda:0')
episode: 378 training return: tensor(-585.7357, device='cuda:0')
episode: 379 training return: tensor(-677.7289, device='cuda:0')
epoch: 95 test_true_pfm: -2.373520936745114 sim_pfm: -616.5742150990603
episode: 380 training return: tensor(-587.5099, device='cuda:0')
episode: 381 training return: tensor(-629.4650, device='cuda:0')
episode: 382 training return: tensor(-626.9336, device='cuda:0')
episode: 383 training return: tensor(-564.6671, device='cuda:0')
epoch: 96 test_true_pfm: 41.47042108355033 sim_pfm: -575.2050043174144
episode: 384 training return: tensor(-693.2253, device='cuda:0')
episode: 385 training return: tensor(-626.7208, device='cuda:0')
episode: 386 training return: tensor(-642.9067, device='cuda:0')
episode: 387 training return: tensor(-575.0306, device='cuda:0')
epoch: 97 test_true_pfm: -160.8672037871437 sim_pfm: -554.1993631531271
episode: 388 training return: tensor(-612.7357, device='cuda:0')
episode: 389 training return: tensor(-659.7303, device='cuda:0')
episode: 390 training return: tensor(-706.6091, device='cuda:0')
episode: 391 training return: tensor(-779.6270, device='cuda:0')
epoch: 98 test_true_pfm: -67.86366936535485 sim_pfm: -532.3436219671858
episode: 392 training return: tensor(-692.8376, device='cuda:0')
episode: 393 training return: tensor(-646.2327, device='cuda:0')
episode: 394 training return: tensor(-630.8657, device='cuda:0')
episode: 395 training return: tensor(-711.1394, device='cuda:0')
epoch: 99 test_true_pfm: 10.722464606919145 sim_pfm: -562.5662314766669
episode: 396 training return: tensor(-592.6651, device='cuda:0')
episode: 397 training return: tensor(-610.3083, device='cuda:0')
episode: 398 training return: tensor(-670.3492, device='cuda:0')
episode: 399 training return: tensor(-692.7099, device='cuda:0')
epoch: 100 test_true_pfm: 14.870392266146562 sim_pfm: -535.797640175481
episode: 400 training return: tensor(-635.9488, device='cuda:0')
episode: 401 training return: tensor(-659.6154, device='cuda:0')
episode: 402 training return: tensor(-632.5414, device='cuda:0')
episode: 403 training return: tensor(-700.0925, device='cuda:0')
epoch: 101 test_true_pfm: -23.403019727059146 sim_pfm: -643.2472544902024
episode: 404 training return: tensor(-672.6253, device='cuda:0')
episode: 405 training return: tensor(-559.0899, device='cuda:0')
episode: 406 training return: tensor(-631.9094, device='cuda:0')
episode: 407 training return: tensor(-648.9056, device='cuda:0')
epoch: 102 test_true_pfm: 51.37544356013271 sim_pfm: -542.0008764421412
episode: 408 training return: tensor(-607.9941, device='cuda:0')
episode: 409 training return: tensor(-743.2336, device='cuda:0')
episode: 410 training return: tensor(-678.8571, device='cuda:0')
episode: 411 training return: tensor(-758.3693, device='cuda:0')
epoch: 103 test_true_pfm: 80.98362106230313 sim_pfm: -544.5684084615204
episode: 412 training return: tensor(-673.1431, device='cuda:0')
episode: 413 training return: tensor(-635.9788, device='cuda:0')
episode: 414 training return: tensor(-621.4708, device='cuda:0')
episode: 415 training return: tensor(-702.1113, device='cuda:0')
epoch: 104 test_true_pfm: -75.39455565076209 sim_pfm: -819.6897359915698
episode: 416 training return: tensor(-609.8016, device='cuda:0')
episode: 417 training return: tensor(-634.2394, device='cuda:0')
episode: 418 training return: tensor(-589.9278, device='cuda:0')
episode: 419 training return: tensor(-592.1101, device='cuda:0')
epoch: 105 test_true_pfm: 61.17029416353722 sim_pfm: -882.6267739335696
episode: 420 training return: tensor(-621.7160, device='cuda:0')
episode: 421 training return: tensor(-610.0728, device='cuda:0')
episode: 422 training return: tensor(-706.3292, device='cuda:0')
episode: 423 training return: tensor(-608.2355, device='cuda:0')
epoch: 106 test_true_pfm: 57.397819293375335 sim_pfm: -635.7765131791433
episode: 424 training return: tensor(-703.4856, device='cuda:0')
episode: 425 training return: tensor(-681.4661, device='cuda:0')
episode: 426 training return: tensor(-617.7469, device='cuda:0')
episode: 427 training return: tensor(-628.8171, device='cuda:0')
epoch: 107 test_true_pfm: -2.495908323195541 sim_pfm: -649.1073226295412
episode: 428 training return: tensor(-638.5150, device='cuda:0')
episode: 429 training return: tensor(-687.2190, device='cuda:0')
episode: 430 training return: tensor(-731.0521, device='cuda:0')
episode: 431 training return: tensor(-684.0062, device='cuda:0')
epoch: 108 test_true_pfm: -122.50343045017473 sim_pfm: -621.5573675535464
episode: 432 training return: tensor(-635.6788, device='cuda:0')
episode: 433 training return: tensor(-620.6212, device='cuda:0')
episode: 434 training return: tensor(-609.1997, device='cuda:0')
episode: 435 training return: tensor(-679.8959, device='cuda:0')
epoch: 109 test_true_pfm: 63.59782070167477 sim_pfm: -633.4549369678522
episode: 436 training return: tensor(-651.0583, device='cuda:0')
episode: 437 training return: tensor(-729.4420, device='cuda:0')
episode: 438 training return: tensor(-639.4254, device='cuda:0')
episode: 439 training return: tensor(-697.2327, device='cuda:0')
epoch: 110 test_true_pfm: -89.60729525446156 sim_pfm: -591.0836393858772
episode: 440 training return: tensor(-666.8676, device='cuda:0')
episode: 441 training return: tensor(-631.5307, device='cuda:0')
episode: 442 training return: tensor(-636.7151, device='cuda:0')
episode: 443 training return: tensor(-712.5403, device='cuda:0')
epoch: 111 test_true_pfm: -92.131727497939 sim_pfm: -569.1001151051605
episode: 444 training return: tensor(-629.0850, device='cuda:0')
episode: 445 training return: tensor(-628.6897, device='cuda:0')
episode: 446 training return: tensor(-688.1973, device='cuda:0')
episode: 447 training return: tensor(-614.8765, device='cuda:0')
epoch: 112 test_true_pfm: -19.59193120565735 sim_pfm: -674.8611083167294
episode: 448 training return: tensor(-595.7001, device='cuda:0')
episode: 449 training return: tensor(-771.8879, device='cuda:0')
episode: 450 training return: tensor(-750.7159, device='cuda:0')
episode: 451 training return: tensor(-620.1648, device='cuda:0')
epoch: 113 test_true_pfm: -204.4506032164717 sim_pfm: -599.6172900817668
episode: 452 training return: tensor(-846.3008, device='cuda:0')
episode: 453 training return: tensor(-587.5119, device='cuda:0')
episode: 454 training return: tensor(-674.4034, device='cuda:0')
episode: 455 training return: tensor(-643.0544, device='cuda:0')
epoch: 114 test_true_pfm: 170.42458396490636 sim_pfm: -648.0449958433164
episode: 456 training return: tensor(-704.0162, device='cuda:0')
episode: 457 training return: tensor(-600.9984, device='cuda:0')
episode: 458 training return: tensor(-663.0738, device='cuda:0')
episode: 459 training return: tensor(-821.9534, device='cuda:0')
epoch: 115 test_true_pfm: -111.05494047736322 sim_pfm: -569.6384946713903
episode: 460 training return: tensor(-547.8754, device='cuda:0')
episode: 461 training return: tensor(-736.5101, device='cuda:0')
episode: 462 training return: tensor(-588.0872, device='cuda:0')
episode: 463 training return: tensor(-624.9426, device='cuda:0')
epoch: 116 test_true_pfm: -141.7683092727792 sim_pfm: -649.525324624643
episode: 464 training return: tensor(-791.1761, device='cuda:0')
episode: 465 training return: tensor(-717.0341, device='cuda:0')
episode: 466 training return: tensor(-579.9653, device='cuda:0')
episode: 467 training return: tensor(-624.0963, device='cuda:0')
epoch: 117 test_true_pfm: -9.59227710894217 sim_pfm: -604.6306901242351
episode: 468 training return: tensor(-744.4214, device='cuda:0')
episode: 469 training return: tensor(-750.1976, device='cuda:0')
episode: 470 training return: tensor(-674.7113, device='cuda:0')
episode: 471 training return: tensor(-617.1888, device='cuda:0')
epoch: 118 test_true_pfm: 42.12175415787018 sim_pfm: -525.1353848110108
episode: 472 training return: tensor(-627.0107, device='cuda:0')
episode: 473 training return: tensor(-629.2640, device='cuda:0')
episode: 474 training return: tensor(-671.3159, device='cuda:0')
episode: 475 training return: tensor(-615.7670, device='cuda:0')
epoch: 119 test_true_pfm: 37.13283715442032 sim_pfm: -722.185504252091
episode: 476 training return: tensor(-712.4008, device='cuda:0')
episode: 477 training return: tensor(-654.7136, device='cuda:0')
episode: 478 training return: tensor(-644.9213, device='cuda:0')
episode: 479 training return: tensor(-768.8287, device='cuda:0')
epoch: 120 test_true_pfm: -174.70706907457907 sim_pfm: -541.2817740136137
episode: 480 training return: tensor(-724.7152, device='cuda:0')
episode: 481 training return: tensor(-769.8073, device='cuda:0')
episode: 482 training return: tensor(-777.5620, device='cuda:0')
episode: 483 training return: tensor(-674.8983, device='cuda:0')
epoch: 121 test_true_pfm: 37.239173413658584 sim_pfm: -584.3745149866057
episode: 484 training return: tensor(-680.1851, device='cuda:0')
episode: 485 training return: tensor(-689.2432, device='cuda:0')
episode: 486 training return: tensor(-649.2056, device='cuda:0')
episode: 487 training return: tensor(-680.6789, device='cuda:0')
epoch: 122 test_true_pfm: 78.37285890587712 sim_pfm: -549.8834841729453
episode: 488 training return: tensor(-655.0882, device='cuda:0')
episode: 489 training return: tensor(-897.1907, device='cuda:0')
episode: 490 training return: tensor(-619.5350, device='cuda:0')
episode: 491 training return: tensor(-685.0292, device='cuda:0')
epoch: 123 test_true_pfm: -3.7225174955007723 sim_pfm: -606.1548406152675
episode: 492 training return: tensor(-832.2676, device='cuda:0')
episode: 493 training return: tensor(-658.8033, device='cuda:0')
episode: 494 training return: tensor(-721.7724, device='cuda:0')
episode: 495 training return: tensor(-552.0784, device='cuda:0')
epoch: 124 test_true_pfm: -13.48406786164343 sim_pfm: -582.9074932155587
episode: 496 training return: tensor(-727.5775, device='cuda:0')
episode: 497 training return: tensor(-639.0178, device='cuda:0')
episode: 498 training return: tensor(-718.4965, device='cuda:0')
episode: 499 training return: tensor(-800.0519, device='cuda:0')
epoch: 125 test_true_pfm: -28.083547366484364 sim_pfm: -640.0487457552614
episode: 500 training return: tensor(-627.9160, device='cuda:0')
episode: 501 training return: tensor(-614.6726, device='cuda:0')
episode: 502 training return: tensor(-733.0251, device='cuda:0')
episode: 503 training return: tensor(-610.6316, device='cuda:0')
epoch: 126 test_true_pfm: -107.9480414326945 sim_pfm: -613.7705919983564
episode: 504 training return: tensor(-633.7101, device='cuda:0')
episode: 505 training return: tensor(-726.9316, device='cuda:0')
episode: 506 training return: tensor(-734.7528, device='cuda:0')
episode: 507 training return: tensor(-703.2913, device='cuda:0')
epoch: 127 test_true_pfm: -173.2880721015969 sim_pfm: -595.8744294266216
episode: 508 training return: tensor(-688.5037, device='cuda:0')
episode: 509 training return: tensor(-654.0186, device='cuda:0')
episode: 510 training return: tensor(-621.4799, device='cuda:0')
episode: 511 training return: tensor(-673.7819, device='cuda:0')
epoch: 128 test_true_pfm: 68.96681228056413 sim_pfm: -588.7709784325174
episode: 512 training return: tensor(-770.6490, device='cuda:0')
episode: 513 training return: tensor(-615.4029, device='cuda:0')
episode: 514 training return: tensor(-653.9418, device='cuda:0')
episode: 515 training return: tensor(-708.5140, device='cuda:0')
epoch: 129 test_true_pfm: -140.2465367297277 sim_pfm: -573.6062652401937
episode: 516 training return: tensor(-591.9440, device='cuda:0')
episode: 517 training return: tensor(-664.8843, device='cuda:0')
episode: 518 training return: tensor(-631.2779, device='cuda:0')
episode: 519 training return: tensor(-683.5997, device='cuda:0')
epoch: 130 test_true_pfm: 31.5564667031977 sim_pfm: -557.7596675975559
episode: 520 training return: tensor(-575.2267, device='cuda:0')
episode: 521 training return: tensor(-630.9826, device='cuda:0')
episode: 522 training return: tensor(-693.7925, device='cuda:0')
episode: 523 training return: tensor(-633.3539, device='cuda:0')
epoch: 131 test_true_pfm: 35.121774754480654 sim_pfm: -628.3470967896865
episode: 524 training return: tensor(-690.8802, device='cuda:0')
episode: 525 training return: tensor(-750.9588, device='cuda:0')
episode: 526 training return: tensor(-580.6447, device='cuda:0')
episode: 527 training return: tensor(-731.8695, device='cuda:0')
epoch: 132 test_true_pfm: -160.1358083605513 sim_pfm: -581.6400972945461
episode: 528 training return: tensor(-622.1628, device='cuda:0')
episode: 529 training return: tensor(-794.7339, device='cuda:0')
episode: 530 training return: tensor(-693.6520, device='cuda:0')
episode: 531 training return: tensor(-622.2356, device='cuda:0')
epoch: 133 test_true_pfm: 145.15451106516687 sim_pfm: -575.2805880052038
episode: 532 training return: tensor(-633.2086, device='cuda:0')
episode: 533 training return: tensor(-542.8956, device='cuda:0')
episode: 534 training return: tensor(-658.9123, device='cuda:0')
episode: 535 training return: tensor(-639.2767, device='cuda:0')
epoch: 134 test_true_pfm: 4.404126561491732 sim_pfm: -591.57014188834
episode: 536 training return: tensor(-729.0519, device='cuda:0')
episode: 537 training return: tensor(-703.6934, device='cuda:0')
episode: 538 training return: tensor(-667.8632, device='cuda:0')
episode: 539 training return: tensor(-710.9565, device='cuda:0')
epoch: 135 test_true_pfm: -96.46708733203462 sim_pfm: -595.3168844940761
episode: 540 training return: tensor(-654.4182, device='cuda:0')
episode: 541 training return: tensor(-643.9660, device='cuda:0')
episode: 542 training return: tensor(-746.1229, device='cuda:0')
episode: 543 training return: tensor(-751.1048, device='cuda:0')
epoch: 136 test_true_pfm: 6.75926446558952 sim_pfm: -538.9746712837756
episode: 544 training return: tensor(-806.1965, device='cuda:0')
episode: 545 training return: tensor(-807.0081, device='cuda:0')
episode: 546 training return: tensor(-604.4715, device='cuda:0')
episode: 547 training return: tensor(-632.6648, device='cuda:0')
epoch: 137 test_true_pfm: 23.164828535800428 sim_pfm: -512.8596395300701
episode: 548 training return: tensor(-887.0452, device='cuda:0')
episode: 549 training return: tensor(-639.3937, device='cuda:0')
episode: 550 training return: tensor(-785.9011, device='cuda:0')
episode: 551 training return: tensor(-682.2802, device='cuda:0')
epoch: 138 test_true_pfm: -32.96835167748187 sim_pfm: -666.0956360379545
episode: 552 training return: tensor(-587.0093, device='cuda:0')
episode: 553 training return: tensor(-684.2988, device='cuda:0')
episode: 554 training return: tensor(-692.5220, device='cuda:0')
episode: 555 training return: tensor(-616.6776, device='cuda:0')
epoch: 139 test_true_pfm: -229.99740481535582 sim_pfm: -633.1045691532394
episode: 556 training return: tensor(-624.4338, device='cuda:0')
episode: 557 training return: tensor(-686.4428, device='cuda:0')
episode: 558 training return: tensor(-719.7794, device='cuda:0')
episode: 559 training return: tensor(-806.4070, device='cuda:0')
epoch: 140 test_true_pfm: -100.01477634805582 sim_pfm: -581.6234747705361
episode: 560 training return: tensor(-708.5669, device='cuda:0')
episode: 561 training return: tensor(-657.7378, device='cuda:0')
episode: 562 training return: tensor(-667.0643, device='cuda:0')
episode: 563 training return: tensor(-676.1801, device='cuda:0')
epoch: 141 test_true_pfm: -91.12183538472675 sim_pfm: -619.5757441272339
episode: 564 training return: tensor(-712.7272, device='cuda:0')
episode: 565 training return: tensor(-615.1423, device='cuda:0')
episode: 566 training return: tensor(-695.1855, device='cuda:0')
episode: 567 training return: tensor(-590.8356, device='cuda:0')
epoch: 142 test_true_pfm: 3.976406370692731 sim_pfm: -526.4817523956299
episode: 568 training return: tensor(-689.2837, device='cuda:0')
episode: 569 training return: tensor(-549.7614, device='cuda:0')
episode: 570 training return: tensor(-590.1754, device='cuda:0')
episode: 571 training return: tensor(-644.2553, device='cuda:0')
epoch: 143 test_true_pfm: -146.3641756053415 sim_pfm: -654.1378018861482
episode: 572 training return: tensor(-723.5099, device='cuda:0')
episode: 573 training return: tensor(-856.0209, device='cuda:0')
episode: 574 training return: tensor(-743.4179, device='cuda:0')
episode: 575 training return: tensor(-634.7519, device='cuda:0')
epoch: 144 test_true_pfm: -9.826563250811583 sim_pfm: -759.5435845536025
episode: 576 training return: tensor(-736.9642, device='cuda:0')
episode: 577 training return: tensor(-833.4263, device='cuda:0')
episode: 578 training return: tensor(-588.7791, device='cuda:0')
episode: 579 training return: tensor(-675.5553, device='cuda:0')
epoch: 145 test_true_pfm: -191.633660002326 sim_pfm: -679.5844967950446
episode: 580 training return: tensor(-819.1821, device='cuda:0')
episode: 581 training return: tensor(-680.0384, device='cuda:0')
episode: 582 training return: tensor(-616.4744, device='cuda:0')
episode: 583 training return: tensor(-822.8769, device='cuda:0')
epoch: 146 test_true_pfm: 75.90113705487813 sim_pfm: -627.1865138982733
episode: 584 training return: tensor(-752.7796, device='cuda:0')
episode: 585 training return: tensor(-600.0409, device='cuda:0')
episode: 586 training return: tensor(-712.9693, device='cuda:0')
episode: 587 training return: tensor(-721.0945, device='cuda:0')
epoch: 147 test_true_pfm: -68.53678953834745 sim_pfm: -639.7548648663796
episode: 588 training return: tensor(-775.2140, device='cuda:0')
episode: 589 training return: tensor(-761.2117, device='cuda:0')
episode: 590 training return: tensor(-652.3810, device='cuda:0')
episode: 591 training return: tensor(-822.3754, device='cuda:0')
epoch: 148 test_true_pfm: -135.2104805202592 sim_pfm: -562.7890476423005
episode: 592 training return: tensor(-711.3879, device='cuda:0')
episode: 593 training return: tensor(-721.9951, device='cuda:0')
episode: 594 training return: tensor(-666.6991, device='cuda:0')
episode: 595 training return: tensor(-591.7668, device='cuda:0')
epoch: 149 test_true_pfm: 1.7036215454801849 sim_pfm: -658.8293584978674
episode: 596 training return: tensor(-783.9228, device='cuda:0')
episode: 597 training return: tensor(-612.3857, device='cuda:0')
episode: 598 training return: tensor(-646.2439, device='cuda:0')
episode: 599 training return: tensor(-765.5585, device='cuda:0')
epoch: 150 test_true_pfm: 20.88109495605146 sim_pfm: -577.6692419009827
