['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '2']
episode: 0 training return: tensor(-444.1550, device='cuda:0')
episode: 1 training return: tensor(-675.7776, device='cuda:0')
episode: 2 training return: tensor(-605.5047, device='cuda:0')
episode: 3 training return: tensor(-472.7062, device='cuda:0')
epoch: 1 test_true_pfm: -28.703081100233902 sim_pfm: -599.9396955569586
episode: 4 training return: tensor(-452.3517, device='cuda:0')
episode: 5 training return: tensor(-548.7845, device='cuda:0')
episode: 6 training return: tensor(-408.3316, device='cuda:0')
episode: 7 training return: tensor(-606.2164, device='cuda:0')
epoch: 2 test_true_pfm: -199.8556186085135 sim_pfm: -567.334693726773
episode: 8 training return: tensor(-599.5395, device='cuda:0')
episode: 9 training return: tensor(-649.0974, device='cuda:0')
episode: 10 training return: tensor(-600.6138, device='cuda:0')
episode: 11 training return: tensor(-633.8049, device='cuda:0')
epoch: 3 test_true_pfm: -830.3519212272754 sim_pfm: -577.7019888815315
episode: 12 training return: tensor(-512.1902, device='cuda:0')
episode: 13 training return: tensor(-596.5879, device='cuda:0')
episode: 14 training return: tensor(-423.9300, device='cuda:0')
episode: 15 training return: tensor(-346.2649, device='cuda:0')
epoch: 4 test_true_pfm: 0.1307825750417185 sim_pfm: -561.6284306771122
episode: 16 training return: tensor(-676.1784, device='cuda:0')
episode: 17 training return: tensor(-457.2610, device='cuda:0')
episode: 18 training return: tensor(-531.2570, device='cuda:0')
episode: 19 training return: tensor(-690.9944, device='cuda:0')
epoch: 5 test_true_pfm: -3.5801582663659226 sim_pfm: -509.67665783921257
episode: 20 training return: tensor(-173.2990, device='cuda:0')
episode: 21 training return: tensor(-693.8802, device='cuda:0')
episode: 22 training return: tensor(-606.2849, device='cuda:0')
episode: 23 training return: tensor(-619.5943, device='cuda:0')
epoch: 6 test_true_pfm: 147.59411896446485 sim_pfm: -628.6982931994717
episode: 24 training return: tensor(-696.1445, device='cuda:0')
episode: 25 training return: tensor(-714.1406, device='cuda:0')
episode: 26 training return: tensor(-434.5521, device='cuda:0')
episode: 27 training return: tensor(-734.5724, device='cuda:0')
epoch: 7 test_true_pfm: -71.22819496110397 sim_pfm: -503.5690665862833
episode: 28 training return: tensor(-762.5873, device='cuda:0')
episode: 29 training return: tensor(-743.0989, device='cuda:0')
episode: 30 training return: tensor(-751.3227, device='cuda:0')
episode: 31 training return: tensor(-535.5784, device='cuda:0')
epoch: 8 test_true_pfm: -40.449630817277345 sim_pfm: -399.60054456675425
episode: 32 training return: tensor(-608.4599, device='cuda:0')
episode: 33 training return: tensor(-407.3680, device='cuda:0')
episode: 34 training return: tensor(-392.1708, device='cuda:0')
episode: 35 training return: tensor(-458.7422, device='cuda:0')
epoch: 9 test_true_pfm: 141.32526215559443 sim_pfm: -765.8027326681962
episode: 36 training return: tensor(-738.2847, device='cuda:0')
episode: 37 training return: tensor(-724.1935, device='cuda:0')
episode: 38 training return: tensor(-710.2369, device='cuda:0')
episode: 39 training return: tensor(-715.9363, device='cuda:0')
epoch: 10 test_true_pfm: 132.76501978110062 sim_pfm: -663.8689783351341
episode: 40 training return: tensor(-670.0121, device='cuda:0')
episode: 41 training return: tensor(-678.8232, device='cuda:0')
episode: 42 training return: tensor(-686.1656, device='cuda:0')
episode: 43 training return: tensor(-692.0430, device='cuda:0')
epoch: 11 test_true_pfm: 203.84282641106157 sim_pfm: -736.2041187050442
episode: 44 training return: tensor(-674.1948, device='cuda:0')
episode: 45 training return: tensor(-680.3430, device='cuda:0')
episode: 46 training return: tensor(-684.8508, device='cuda:0')
episode: 47 training return: tensor(-663.5117, device='cuda:0')
epoch: 12 test_true_pfm: 185.90996109996385 sim_pfm: -642.2957786996849
episode: 48 training return: tensor(-660.9572, device='cuda:0')
episode: 49 training return: tensor(-695.4775, device='cuda:0')
episode: 50 training return: tensor(-695.2040, device='cuda:0')
episode: 51 training return: tensor(-669.7128, device='cuda:0')
epoch: 13 test_true_pfm: 171.76235382613686 sim_pfm: -653.3565046029786
episode: 52 training return: tensor(-684.8820, device='cuda:0')
episode: 53 training return: tensor(-649.5150, device='cuda:0')
episode: 54 training return: tensor(-677.3652, device='cuda:0')
episode: 55 training return: tensor(-674.3003, device='cuda:0')
epoch: 14 test_true_pfm: 144.12799440951312 sim_pfm: -672.3271553255618
episode: 56 training return: tensor(-685.4462, device='cuda:0')
episode: 57 training return: tensor(-698.5073, device='cuda:0')
episode: 58 training return: tensor(-674.8906, device='cuda:0')
episode: 59 training return: tensor(-675.4396, device='cuda:0')
epoch: 15 test_true_pfm: 166.4721445813026 sim_pfm: -634.031362500973
episode: 60 training return: tensor(-669.5646, device='cuda:0')
episode: 61 training return: tensor(-705.0634, device='cuda:0')
episode: 62 training return: tensor(-673.9498, device='cuda:0')
episode: 63 training return: tensor(-676.9594, device='cuda:0')
epoch: 16 test_true_pfm: 131.48605039655263 sim_pfm: -649.3979403659081
episode: 64 training return: tensor(-680.7759, device='cuda:0')
episode: 65 training return: tensor(-661.8896, device='cuda:0')
episode: 66 training return: tensor(-659.3714, device='cuda:0')
episode: 67 training return: tensor(-685.9948, device='cuda:0')
epoch: 17 test_true_pfm: 144.8434502167136 sim_pfm: -648.6709667906786
episode: 68 training return: tensor(-667.4786, device='cuda:0')
episode: 69 training return: tensor(-629.9869, device='cuda:0')
episode: 70 training return: tensor(-669.6968, device='cuda:0')
episode: 71 training return: tensor(-655.8120, device='cuda:0')
epoch: 18 test_true_pfm: 130.58502794949945 sim_pfm: -652.0720365295807
episode: 72 training return: tensor(-658.4627, device='cuda:0')
episode: 73 training return: tensor(-576.5879, device='cuda:0')
episode: 74 training return: tensor(-623.5833, device='cuda:0')
episode: 75 training return: tensor(-590.9442, device='cuda:0')
epoch: 19 test_true_pfm: 149.10786415008556 sim_pfm: -648.2980136672655
episode: 76 training return: tensor(-546.3948, device='cuda:0')
episode: 77 training return: tensor(-578.3204, device='cuda:0')
episode: 78 training return: tensor(-560.6743, device='cuda:0')
episode: 79 training return: tensor(-567.1068, device='cuda:0')
epoch: 20 test_true_pfm: 129.9195325620781 sim_pfm: -646.8262710236013
episode: 80 training return: tensor(-568.0793, device='cuda:0')
episode: 81 training return: tensor(-533.5703, device='cuda:0')
episode: 82 training return: tensor(-543.5251, device='cuda:0')
episode: 83 training return: tensor(-547.2001, device='cuda:0')
epoch: 21 test_true_pfm: 144.30866623239348 sim_pfm: -563.8411725196056
episode: 84 training return: tensor(-526.9738, device='cuda:0')
episode: 85 training return: tensor(-544.9362, device='cuda:0')
episode: 86 training return: tensor(-511.8454, device='cuda:0')
episode: 87 training return: tensor(-523.5802, device='cuda:0')
epoch: 22 test_true_pfm: 103.18014507918487 sim_pfm: -489.0450155187088
episode: 88 training return: tensor(-485.7424, device='cuda:0')
episode: 89 training return: tensor(-551.7690, device='cuda:0')
episode: 90 training return: tensor(-484.1526, device='cuda:0')
episode: 91 training return: tensor(-387.8471, device='cuda:0')
epoch: 23 test_true_pfm: 221.70650138371136 sim_pfm: -438.80232683441136
episode: 92 training return: tensor(-481.7120, device='cuda:0')
episode: 93 training return: tensor(-539.8033, device='cuda:0')
episode: 94 training return: tensor(-468.6085, device='cuda:0')
episode: 95 training return: tensor(-471.4688, device='cuda:0')
epoch: 24 test_true_pfm: 175.05831381532298 sim_pfm: -447.27807878276025
episode: 96 training return: tensor(-512.8411, device='cuda:0')
episode: 97 training return: tensor(-275.4843, device='cuda:0')
episode: 98 training return: tensor(-512.0363, device='cuda:0')
episode: 99 training return: tensor(-484.4015, device='cuda:0')
epoch: 25 test_true_pfm: 181.18328284421702 sim_pfm: -537.731608018706
episode: 100 training return: tensor(-469.1040, device='cuda:0')
episode: 101 training return: tensor(-525.9954, device='cuda:0')
episode: 102 training return: tensor(-489.0835, device='cuda:0')
episode: 103 training return: tensor(-445.2352, device='cuda:0')
epoch: 26 test_true_pfm: 153.52203339394916 sim_pfm: -439.6949532384363
episode: 104 training return: tensor(-510.5703, device='cuda:0')
episode: 105 training return: tensor(-488.3402, device='cuda:0')
episode: 106 training return: tensor(-578.7408, device='cuda:0')
episode: 107 training return: tensor(-452.7772, device='cuda:0')
epoch: 27 test_true_pfm: 249.97082391614785 sim_pfm: -425.51764297198196
episode: 108 training return: tensor(-474.1059, device='cuda:0')
episode: 109 training return: tensor(-454.8081, device='cuda:0')
episode: 110 training return: tensor(-505.6521, device='cuda:0')
episode: 111 training return: tensor(-471.8634, device='cuda:0')
epoch: 28 test_true_pfm: 386.8601329925603 sim_pfm: -403.43584574836615
episode: 112 training return: tensor(-457.7702, device='cuda:0')
episode: 113 training return: tensor(-467.6503, device='cuda:0')
episode: 114 training return: tensor(-488.5321, device='cuda:0')
episode: 115 training return: tensor(-456.3888, device='cuda:0')
epoch: 29 test_true_pfm: 205.74933938910968 sim_pfm: -439.4390575035165
episode: 116 training return: tensor(-483.2333, device='cuda:0')
episode: 117 training return: tensor(-481.0007, device='cuda:0')
episode: 118 training return: tensor(-445.4898, device='cuda:0')
episode: 119 training return: tensor(-448.6012, device='cuda:0')
epoch: 30 test_true_pfm: 204.448754144134 sim_pfm: -414.5366041579594
episode: 120 training return: tensor(-573.4226, device='cuda:0')
episode: 121 training return: tensor(-478.6785, device='cuda:0')
episode: 122 training return: tensor(-451.7715, device='cuda:0')
episode: 123 training return: tensor(-456.2888, device='cuda:0')
epoch: 31 test_true_pfm: 852.7424637247901 sim_pfm: -357.5948816361585
episode: 124 training return: tensor(-433.6614, device='cuda:0')
episode: 125 training return: tensor(-418.2520, device='cuda:0')
episode: 126 training return: tensor(-501.9408, device='cuda:0')
episode: 127 training return: tensor(-464.1827, device='cuda:0')
epoch: 32 test_true_pfm: 296.50973076412896 sim_pfm: -395.1258786813317
episode: 128 training return: tensor(-500.6642, device='cuda:0')
episode: 129 training return: tensor(-466.1777, device='cuda:0')
episode: 130 training return: tensor(-477.5622, device='cuda:0')
episode: 131 training return: tensor(-452.7197, device='cuda:0')
epoch: 33 test_true_pfm: 177.4989993994989 sim_pfm: -435.11510350353393
episode: 132 training return: tensor(-430.8890, device='cuda:0')
episode: 133 training return: tensor(-480.4554, device='cuda:0')
episode: 134 training return: tensor(-432.4217, device='cuda:0')
episode: 135 training return: tensor(-385.8612, device='cuda:0')
epoch: 34 test_true_pfm: 540.8862856404211 sim_pfm: -402.4551689279421
episode: 136 training return: tensor(-469.2836, device='cuda:0')
episode: 137 training return: tensor(-487.1868, device='cuda:0')
episode: 138 training return: tensor(-438.7556, device='cuda:0')
episode: 139 training return: tensor(-498.9708, device='cuda:0')
epoch: 35 test_true_pfm: 324.27810395963616 sim_pfm: -405.18336672894657
episode: 140 training return: tensor(-538.4792, device='cuda:0')
episode: 141 training return: tensor(-484.8705, device='cuda:0')
episode: 142 training return: tensor(-440.7123, device='cuda:0')
episode: 143 training return: tensor(-462.4416, device='cuda:0')
epoch: 36 test_true_pfm: 384.35011286963027 sim_pfm: -376.185052276589
episode: 144 training return: tensor(-496.4563, device='cuda:0')
episode: 145 training return: tensor(-502.7659, device='cuda:0')
episode: 146 training return: tensor(-535.9120, device='cuda:0')
episode: 147 training return: tensor(-437.5344, device='cuda:0')
epoch: 37 test_true_pfm: 531.9837646678693 sim_pfm: -386.10722261772025
episode: 148 training return: tensor(-473.9602, device='cuda:0')
episode: 149 training return: tensor(-442.3626, device='cuda:0')
episode: 150 training return: tensor(-480.6342, device='cuda:0')
episode: 151 training return: tensor(-404.7834, device='cuda:0')
epoch: 38 test_true_pfm: 644.5034369542855 sim_pfm: -383.42284807915956
episode: 152 training return: tensor(-430.1485, device='cuda:0')
episode: 153 training return: tensor(-456.1775, device='cuda:0')
episode: 154 training return: tensor(-450.1116, device='cuda:0')
episode: 155 training return: tensor(-424.1070, device='cuda:0')
epoch: 39 test_true_pfm: 612.1469045033368 sim_pfm: -344.15597570920363
episode: 156 training return: tensor(-445.5275, device='cuda:0')
episode: 157 training return: tensor(-478.0126, device='cuda:0')
episode: 158 training return: tensor(-428.9001, device='cuda:0')
episode: 159 training return: tensor(-443.1327, device='cuda:0')
epoch: 40 test_true_pfm: 668.546920934906 sim_pfm: -343.6631563268602
episode: 160 training return: tensor(-406.9744, device='cuda:0')
episode: 161 training return: tensor(-433.9003, device='cuda:0')
episode: 162 training return: tensor(-450.9113, device='cuda:0')
episode: 163 training return: tensor(-459.1607, device='cuda:0')
epoch: 41 test_true_pfm: 582.0274839861614 sim_pfm: -341.07131490992225
episode: 164 training return: tensor(-440.2034, device='cuda:0')
episode: 165 training return: tensor(-479.6873, device='cuda:0')
episode: 166 training return: tensor(-459.7052, device='cuda:0')
episode: 167 training return: tensor(-406.9291, device='cuda:0')
epoch: 42 test_true_pfm: 548.2721263161512 sim_pfm: -360.95657566918334
episode: 168 training return: tensor(-409.2250, device='cuda:0')
episode: 169 training return: tensor(-431.1732, device='cuda:0')
episode: 170 training return: tensor(-425.4473, device='cuda:0')
episode: 171 training return: tensor(-433.5928, device='cuda:0')
epoch: 43 test_true_pfm: 519.6850523617636 sim_pfm: -389.7823557095544
episode: 172 training return: tensor(-408.4210, device='cuda:0')
episode: 173 training return: tensor(-471.7292, device='cuda:0')
episode: 174 training return: tensor(-461.0017, device='cuda:0')
episode: 175 training return: tensor(-434.3992, device='cuda:0')
epoch: 44 test_true_pfm: 507.41196460745914 sim_pfm: -339.2597103427591
episode: 176 training return: tensor(-435.5582, device='cuda:0')
episode: 177 training return: tensor(-491.6274, device='cuda:0')
episode: 178 training return: tensor(-459.8461, device='cuda:0')
episode: 179 training return: tensor(-450.5942, device='cuda:0')
epoch: 45 test_true_pfm: 621.9496228583068 sim_pfm: -375.34460659961525
episode: 180 training return: tensor(-445.2313, device='cuda:0')
episode: 181 training return: tensor(-442.9035, device='cuda:0')
episode: 182 training return: tensor(-434.8117, device='cuda:0')
episode: 183 training return: tensor(-431.4460, device='cuda:0')
epoch: 46 test_true_pfm: 559.83998177782 sim_pfm: -363.6199023592053
episode: 184 training return: tensor(-408.0079, device='cuda:0')
episode: 185 training return: tensor(-475.9826, device='cuda:0')
episode: 186 training return: tensor(-439.4696, device='cuda:0')
episode: 187 training return: tensor(-436.5738, device='cuda:0')
epoch: 47 test_true_pfm: 604.1764341431714 sim_pfm: -326.7556572031851
episode: 188 training return: tensor(-403.1544, device='cuda:0')
episode: 189 training return: tensor(-438.4030, device='cuda:0')
episode: 190 training return: tensor(-416.2555, device='cuda:0')
episode: 191 training return: tensor(-429.3781, device='cuda:0')
epoch: 48 test_true_pfm: 742.274018070742 sim_pfm: -310.894309601048
episode: 192 training return: tensor(-525.1295, device='cuda:0')
episode: 193 training return: tensor(-463.5071, device='cuda:0')
episode: 194 training return: tensor(-451.8069, device='cuda:0')
episode: 195 training return: tensor(-395.0599, device='cuda:0')
epoch: 49 test_true_pfm: 718.5827447373637 sim_pfm: -311.9698809213781
episode: 196 training return: tensor(-478.6025, device='cuda:0')
episode: 197 training return: tensor(-391.2262, device='cuda:0')
episode: 198 training return: tensor(-406.3117, device='cuda:0')
episode: 199 training return: tensor(-424.4445, device='cuda:0')
epoch: 50 test_true_pfm: 349.8611264434112 sim_pfm: -344.4571598415884
episode: 200 training return: tensor(-445.2674, device='cuda:0')
episode: 201 training return: tensor(-392.7591, device='cuda:0')
episode: 202 training return: tensor(-420.0333, device='cuda:0')
episode: 203 training return: tensor(-414.5336, device='cuda:0')
epoch: 51 test_true_pfm: 680.0616638267015 sim_pfm: -355.4453976932952
episode: 204 training return: tensor(-396.0277, device='cuda:0')
episode: 205 training return: tensor(-448.6593, device='cuda:0')
episode: 206 training return: tensor(-448.2800, device='cuda:0')
episode: 207 training return: tensor(-437.6244, device='cuda:0')
epoch: 52 test_true_pfm: 675.5470263890662 sim_pfm: -357.0789716946213
episode: 208 training return: tensor(-424.0038, device='cuda:0')
episode: 209 training return: tensor(-461.4388, device='cuda:0')
episode: 210 training return: tensor(-444.1379, device='cuda:0')
episode: 211 training return: tensor(-408.0044, device='cuda:0')
epoch: 53 test_true_pfm: 605.9797166546116 sim_pfm: -350.98109779988107
episode: 212 training return: tensor(-403.8412, device='cuda:0')
episode: 213 training return: tensor(-412.5616, device='cuda:0')
episode: 214 training return: tensor(-427.0450, device='cuda:0')
episode: 215 training return: tensor(-422.7022, device='cuda:0')
epoch: 54 test_true_pfm: 588.2930843078669 sim_pfm: -383.0102984595578
episode: 216 training return: tensor(-438.0772, device='cuda:0')
episode: 217 training return: tensor(-482.9762, device='cuda:0')
episode: 218 training return: tensor(-456.0106, device='cuda:0')
episode: 219 training return: tensor(-430.6523, device='cuda:0')
epoch: 55 test_true_pfm: 514.817361976295 sim_pfm: -372.5503511331044
episode: 220 training return: tensor(-423.8058, device='cuda:0')
episode: 221 training return: tensor(-477.1291, device='cuda:0')
episode: 222 training return: tensor(-387.9078, device='cuda:0')
episode: 223 training return: tensor(-416.8725, device='cuda:0')
epoch: 56 test_true_pfm: 678.8574498881189 sim_pfm: -335.13033281251165
episode: 224 training return: tensor(-464.6541, device='cuda:0')
episode: 225 training return: tensor(-444.3241, device='cuda:0')
episode: 226 training return: tensor(-422.6725, device='cuda:0')
episode: 227 training return: tensor(-446.4077, device='cuda:0')
epoch: 57 test_true_pfm: 586.3227536343619 sim_pfm: -345.3042623841514
episode: 228 training return: tensor(-447.5727, device='cuda:0')
episode: 229 training return: tensor(-445.8505, device='cuda:0')
episode: 230 training return: tensor(-391.5470, device='cuda:0')
episode: 231 training return: tensor(-441.6775, device='cuda:0')
epoch: 58 test_true_pfm: 603.0000868418756 sim_pfm: -347.75511374006356
episode: 232 training return: tensor(-412.0159, device='cuda:0')
episode: 233 training return: tensor(-393.1020, device='cuda:0')
episode: 234 training return: tensor(-410.5206, device='cuda:0')
episode: 235 training return: tensor(-434.7017, device='cuda:0')
epoch: 59 test_true_pfm: 477.12898732852835 sim_pfm: -349.63496912870323
episode: 236 training return: tensor(-411.2600, device='cuda:0')
episode: 237 training return: tensor(-430.8342, device='cuda:0')
episode: 238 training return: tensor(-407.9907, device='cuda:0')
episode: 239 training return: tensor(-452.6021, device='cuda:0')
epoch: 60 test_true_pfm: 581.3257806964011 sim_pfm: -330.28992651670706
episode: 240 training return: tensor(-429.7042, device='cuda:0')
episode: 241 training return: tensor(-420.9976, device='cuda:0')
episode: 242 training return: tensor(-461.2466, device='cuda:0')
episode: 243 training return: tensor(-370.3824, device='cuda:0')
epoch: 61 test_true_pfm: 639.0386493043629 sim_pfm: -321.0146355848604
episode: 244 training return: tensor(-411.1371, device='cuda:0')
episode: 245 training return: tensor(-454.0259, device='cuda:0')
episode: 246 training return: tensor(-426.4661, device='cuda:0')
episode: 247 training return: tensor(-415.0555, device='cuda:0')
epoch: 62 test_true_pfm: 600.304275142607 sim_pfm: -375.9416595394141
episode: 248 training return: tensor(-416.8130, device='cuda:0')
episode: 249 training return: tensor(-438.4341, device='cuda:0')
episode: 250 training return: tensor(-420.6205, device='cuda:0')
episode: 251 training return: tensor(-410.2622, device='cuda:0')
epoch: 63 test_true_pfm: 591.7723518563872 sim_pfm: -361.24797847360605
episode: 252 training return: tensor(-375.1618, device='cuda:0')
episode: 253 training return: tensor(-444.7171, device='cuda:0')
episode: 254 training return: tensor(-480.5038, device='cuda:0')
episode: 255 training return: tensor(-357.7515, device='cuda:0')
epoch: 64 test_true_pfm: 688.5834003640103 sim_pfm: -306.7114069043503
episode: 256 training return: tensor(-418.6407, device='cuda:0')
episode: 257 training return: tensor(-455.9633, device='cuda:0')
episode: 258 training return: tensor(-409.3228, device='cuda:0')
episode: 259 training return: tensor(-403.2336, device='cuda:0')
epoch: 65 test_true_pfm: 755.586969865858 sim_pfm: -322.05013601700193
episode: 260 training return: tensor(-413.1670, device='cuda:0')
episode: 261 training return: tensor(-410.6545, device='cuda:0')
episode: 262 training return: tensor(-413.9062, device='cuda:0')
episode: 263 training return: tensor(-474.2283, device='cuda:0')
epoch: 66 test_true_pfm: 692.8381910239677 sim_pfm: -345.0699690148467
episode: 264 training return: tensor(-469.6343, device='cuda:0')
episode: 265 training return: tensor(-434.1465, device='cuda:0')
episode: 266 training return: tensor(-449.7046, device='cuda:0')
episode: 267 training return: tensor(-490.6063, device='cuda:0')
epoch: 67 test_true_pfm: 690.1315775915473 sim_pfm: -340.80264305253513
episode: 268 training return: tensor(-447.9124, device='cuda:0')
episode: 269 training return: tensor(-483.7917, device='cuda:0')
episode: 270 training return: tensor(-432.1828, device='cuda:0')
episode: 271 training return: tensor(-434.3997, device='cuda:0')
epoch: 68 test_true_pfm: 634.0329660210278 sim_pfm: -335.19299186145264
episode: 272 training return: tensor(-413.1813, device='cuda:0')
episode: 273 training return: tensor(-412.4025, device='cuda:0')
episode: 274 training return: tensor(-412.2703, device='cuda:0')
episode: 275 training return: tensor(-379.8933, device='cuda:0')
epoch: 69 test_true_pfm: 546.2947613693559 sim_pfm: -367.3914855635182
episode: 276 training return: tensor(-413.6870, device='cuda:0')
episode: 277 training return: tensor(-417.1326, device='cuda:0')
episode: 278 training return: tensor(-403.7109, device='cuda:0')
episode: 279 training return: tensor(-476.2097, device='cuda:0')
epoch: 70 test_true_pfm: 751.4706030841154 sim_pfm: -346.18912147959537
episode: 280 training return: tensor(-412.4892, device='cuda:0')
episode: 281 training return: tensor(-401.3392, device='cuda:0')
episode: 282 training return: tensor(-409.1127, device='cuda:0')
episode: 283 training return: tensor(-410.8948, device='cuda:0')
epoch: 71 test_true_pfm: 485.26513746548517 sim_pfm: -332.35622104175854
episode: 284 training return: tensor(-411.9429, device='cuda:0')
episode: 285 training return: tensor(-413.4975, device='cuda:0')
episode: 286 training return: tensor(-416.0788, device='cuda:0')
episode: 287 training return: tensor(-398.4096, device='cuda:0')
epoch: 72 test_true_pfm: 649.9017609986662 sim_pfm: -339.38741708764184
episode: 288 training return: tensor(-396.9716, device='cuda:0')
episode: 289 training return: tensor(-410.9833, device='cuda:0')
episode: 290 training return: tensor(-483.2476, device='cuda:0')
episode: 291 training return: tensor(-436.1964, device='cuda:0')
epoch: 73 test_true_pfm: 776.0879526128386 sim_pfm: -312.6679009529956
episode: 292 training return: tensor(-493.0855, device='cuda:0')
episode: 293 training return: tensor(-438.8357, device='cuda:0')
episode: 294 training return: tensor(-393.3177, device='cuda:0')
episode: 295 training return: tensor(-422.6144, device='cuda:0')
epoch: 74 test_true_pfm: 440.92798373804817 sim_pfm: -330.6201590083753
episode: 296 training return: tensor(-391.7797, device='cuda:0')
episode: 297 training return: tensor(-443.9073, device='cuda:0')
episode: 298 training return: tensor(-402.7568, device='cuda:0')
episode: 299 training return: tensor(-414.8756, device='cuda:0')
epoch: 75 test_true_pfm: 737.4918348161876 sim_pfm: -329.6086967356193
episode: 300 training return: tensor(-393.0068, device='cuda:0')
episode: 301 training return: tensor(-427.1302, device='cuda:0')
episode: 302 training return: tensor(-435.6066, device='cuda:0')
episode: 303 training return: tensor(-399.2577, device='cuda:0')
epoch: 76 test_true_pfm: 588.5757765290246 sim_pfm: -336.4715345640822
episode: 304 training return: tensor(-398.4669, device='cuda:0')
episode: 305 training return: tensor(-431.5669, device='cuda:0')
episode: 306 training return: tensor(-429.1168, device='cuda:0')
episode: 307 training return: tensor(-453.3952, device='cuda:0')
epoch: 77 test_true_pfm: 616.4711436338062 sim_pfm: -355.4186070759897
episode: 308 training return: tensor(-447.3072, device='cuda:0')
episode: 309 training return: tensor(-457.3266, device='cuda:0')
episode: 310 training return: tensor(-404.9493, device='cuda:0')
episode: 311 training return: tensor(-373.6641, device='cuda:0')
epoch: 78 test_true_pfm: 587.0717481971272 sim_pfm: -351.99331417586654
episode: 312 training return: tensor(-430.5927, device='cuda:0')
episode: 313 training return: tensor(-399.8312, device='cuda:0')
episode: 314 training return: tensor(-414.1604, device='cuda:0')
episode: 315 training return: tensor(-394.9977, device='cuda:0')
epoch: 79 test_true_pfm: 649.9015886235275 sim_pfm: -346.84670082248823
episode: 316 training return: tensor(-399.4319, device='cuda:0')
episode: 317 training return: tensor(-406.9089, device='cuda:0')
episode: 318 training return: tensor(-420.3340, device='cuda:0')
episode: 319 training return: tensor(-423.3894, device='cuda:0')
epoch: 80 test_true_pfm: 637.2242723713495 sim_pfm: -357.15184863571386
episode: 320 training return: tensor(-438.3322, device='cuda:0')
episode: 321 training return: tensor(-328.1591, device='cuda:0')
episode: 322 training return: tensor(-419.7928, device='cuda:0')
episode: 323 training return: tensor(-421.7420, device='cuda:0')
epoch: 81 test_true_pfm: 596.9096115344047 sim_pfm: -318.4268350068014
episode: 324 training return: tensor(-388.3433, device='cuda:0')
episode: 325 training return: tensor(-422.7784, device='cuda:0')
episode: 326 training return: tensor(-395.5925, device='cuda:0')
episode: 327 training return: tensor(-378.9334, device='cuda:0')
epoch: 82 test_true_pfm: 685.3643620914559 sim_pfm: -314.90103323874064
episode: 328 training return: tensor(-471.5815, device='cuda:0')
episode: 329 training return: tensor(-404.7100, device='cuda:0')
episode: 330 training return: tensor(-467.1817, device='cuda:0')
episode: 331 training return: tensor(-399.0909, device='cuda:0')
epoch: 83 test_true_pfm: 608.7476706719948 sim_pfm: -337.3676467308542
episode: 332 training return: tensor(-406.9588, device='cuda:0')
episode: 333 training return: tensor(-384.2757, device='cuda:0')
episode: 334 training return: tensor(-448.1263, device='cuda:0')
episode: 335 training return: tensor(-388.6030, device='cuda:0')
epoch: 84 test_true_pfm: 632.8749900670447 sim_pfm: -350.0243886552441
episode: 336 training return: tensor(-404.4466, device='cuda:0')
episode: 337 training return: tensor(-448.0059, device='cuda:0')
episode: 338 training return: tensor(-380.5772, device='cuda:0')
episode: 339 training return: tensor(-410.0851, device='cuda:0')
epoch: 85 test_true_pfm: 570.1981072129049 sim_pfm: -339.94753912758705
episode: 340 training return: tensor(-402.8189, device='cuda:0')
episode: 341 training return: tensor(-374.2983, device='cuda:0')
episode: 342 training return: tensor(-417.9557, device='cuda:0')
episode: 343 training return: tensor(-414.8744, device='cuda:0')
epoch: 86 test_true_pfm: 549.8420196629805 sim_pfm: -337.5944047142111
episode: 344 training return: tensor(-412.4573, device='cuda:0')
episode: 345 training return: tensor(-434.9032, device='cuda:0')
episode: 346 training return: tensor(-450.1084, device='cuda:0')
episode: 347 training return: tensor(-435.8094, device='cuda:0')
epoch: 87 test_true_pfm: 676.1393835578815 sim_pfm: -350.53886220095836
episode: 348 training return: tensor(-394.6613, device='cuda:0')
episode: 349 training return: tensor(-418.4156, device='cuda:0')
episode: 350 training return: tensor(-389.7690, device='cuda:0')
episode: 351 training return: tensor(-411.6951, device='cuda:0')
epoch: 88 test_true_pfm: 633.6180819742441 sim_pfm: -321.7715513660417
episode: 352 training return: tensor(-404.9864, device='cuda:0')
episode: 353 training return: tensor(-391.2202, device='cuda:0')
episode: 354 training return: tensor(-381.6674, device='cuda:0')
episode: 355 training return: tensor(-427.8897, device='cuda:0')
epoch: 89 test_true_pfm: 828.9972731713584 sim_pfm: -338.82646760476445
episode: 356 training return: tensor(-412.0335, device='cuda:0')
episode: 357 training return: tensor(-421.7402, device='cuda:0')
episode: 358 training return: tensor(-401.1660, device='cuda:0')
episode: 359 training return: tensor(-390.4086, device='cuda:0')
epoch: 90 test_true_pfm: 786.41467451812 sim_pfm: -317.5778985089855
episode: 360 training return: tensor(-424.2639, device='cuda:0')
episode: 361 training return: tensor(-415.7137, device='cuda:0')
episode: 362 training return: tensor(-336.6269, device='cuda:0')
episode: 363 training return: tensor(-346.7979, device='cuda:0')
epoch: 91 test_true_pfm: 715.1106630010362 sim_pfm: -301.8715854322363
episode: 364 training return: tensor(-375.9297, device='cuda:0')
episode: 365 training return: tensor(-407.2562, device='cuda:0')
episode: 366 training return: tensor(-396.6504, device='cuda:0')
episode: 367 training return: tensor(-513.8966, device='cuda:0')
epoch: 92 test_true_pfm: 597.9244034398213 sim_pfm: -339.99841359009343
episode: 368 training return: tensor(-444.2665, device='cuda:0')
episode: 369 training return: tensor(-395.9204, device='cuda:0')
episode: 370 training return: tensor(-393.6208, device='cuda:0')
episode: 371 training return: tensor(-393.2517, device='cuda:0')
epoch: 93 test_true_pfm: 649.6998535700404 sim_pfm: -327.79094442824135
episode: 372 training return: tensor(-440.1655, device='cuda:0')
episode: 373 training return: tensor(-413.2000, device='cuda:0')
episode: 374 training return: tensor(-377.2908, device='cuda:0')
episode: 375 training return: tensor(-407.7443, device='cuda:0')
epoch: 94 test_true_pfm: 548.5534716791614 sim_pfm: -359.8606118662283
episode: 376 training return: tensor(-379.0712, device='cuda:0')
episode: 377 training return: tensor(-446.9496, device='cuda:0')
episode: 378 training return: tensor(-419.6449, device='cuda:0')
episode: 379 training return: tensor(-424.5542, device='cuda:0')
epoch: 95 test_true_pfm: 588.7582606097448 sim_pfm: -323.9234872484424
episode: 380 training return: tensor(-376.4403, device='cuda:0')
episode: 381 training return: tensor(-431.5529, device='cuda:0')
episode: 382 training return: tensor(-398.7960, device='cuda:0')
episode: 383 training return: tensor(-407.9349, device='cuda:0')
epoch: 96 test_true_pfm: 664.7190397342874 sim_pfm: -328.02917560686666
episode: 384 training return: tensor(-423.2619, device='cuda:0')
episode: 385 training return: tensor(-416.3009, device='cuda:0')
episode: 386 training return: tensor(-389.5157, device='cuda:0')
episode: 387 training return: tensor(-416.6874, device='cuda:0')
epoch: 97 test_true_pfm: 653.7982578222956 sim_pfm: -329.2953952216388
episode: 388 training return: tensor(-402.8799, device='cuda:0')
episode: 389 training return: tensor(-391.8295, device='cuda:0')
episode: 390 training return: tensor(-407.9213, device='cuda:0')
episode: 391 training return: tensor(-420.0728, device='cuda:0')
epoch: 98 test_true_pfm: 666.3661239962175 sim_pfm: -313.8760868429672
episode: 392 training return: tensor(-423.1615, device='cuda:0')
episode: 393 training return: tensor(-366.2183, device='cuda:0')
episode: 394 training return: tensor(-445.8848, device='cuda:0')
episode: 395 training return: tensor(-379.5772, device='cuda:0')
epoch: 99 test_true_pfm: 660.574022572927 sim_pfm: -328.82303125889547
episode: 396 training return: tensor(-364.1562, device='cuda:0')
episode: 397 training return: tensor(-394.2308, device='cuda:0')
episode: 398 training return: tensor(-399.0416, device='cuda:0')
episode: 399 training return: tensor(-418.3788, device='cuda:0')
epoch: 100 test_true_pfm: 652.8076969875949 sim_pfm: -329.7328261484702
episode: 400 training return: tensor(-420.8341, device='cuda:0')
episode: 401 training return: tensor(-391.7487, device='cuda:0')
episode: 402 training return: tensor(-417.9530, device='cuda:0')
episode: 403 training return: tensor(-455.3322, device='cuda:0')
epoch: 101 test_true_pfm: 700.7873858174338 sim_pfm: -337.87470216024667
episode: 404 training return: tensor(-407.9437, device='cuda:0')
episode: 405 training return: tensor(-403.0192, device='cuda:0')
episode: 406 training return: tensor(-423.0104, device='cuda:0')
episode: 407 training return: tensor(-400.2708, device='cuda:0')
epoch: 102 test_true_pfm: 762.6854837725518 sim_pfm: -326.32902075652964
episode: 408 training return: tensor(-397.2264, device='cuda:0')
episode: 409 training return: tensor(-392.4979, device='cuda:0')
episode: 410 training return: tensor(-406.8178, device='cuda:0')
episode: 411 training return: tensor(-384.9483, device='cuda:0')
epoch: 103 test_true_pfm: 527.3071996257671 sim_pfm: -332.3925506422917
episode: 412 training return: tensor(-403.4201, device='cuda:0')
episode: 413 training return: tensor(-421.1469, device='cuda:0')
episode: 414 training return: tensor(-377.8509, device='cuda:0')
episode: 415 training return: tensor(-395.9662, device='cuda:0')
epoch: 104 test_true_pfm: 655.2898862037742 sim_pfm: -322.8746922153902
episode: 416 training return: tensor(-380.1737, device='cuda:0')
episode: 417 training return: tensor(-404.9130, device='cuda:0')
episode: 418 training return: tensor(-400.2321, device='cuda:0')
episode: 419 training return: tensor(-423.0699, device='cuda:0')
epoch: 105 test_true_pfm: 557.5531632661839 sim_pfm: -354.95644014670205
episode: 420 training return: tensor(-392.4438, device='cuda:0')
episode: 421 training return: tensor(-416.4668, device='cuda:0')
episode: 422 training return: tensor(-394.3300, device='cuda:0')
episode: 423 training return: tensor(-404.2481, device='cuda:0')
epoch: 106 test_true_pfm: 666.6452919595812 sim_pfm: -330.4027630317335
episode: 424 training return: tensor(-387.8477, device='cuda:0')
episode: 425 training return: tensor(-362.3457, device='cuda:0')
episode: 426 training return: tensor(-400.4283, device='cuda:0')
episode: 427 training return: tensor(-431.4417, device='cuda:0')
epoch: 107 test_true_pfm: 556.4338893513633 sim_pfm: -318.12497771007475
episode: 428 training return: tensor(-430.4830, device='cuda:0')
episode: 429 training return: tensor(-402.5225, device='cuda:0')
episode: 430 training return: tensor(-412.5821, device='cuda:0')
episode: 431 training return: tensor(-410.4548, device='cuda:0')
epoch: 108 test_true_pfm: 662.1766741415886 sim_pfm: -331.48099817558733
episode: 432 training return: tensor(-378.1244, device='cuda:0')
episode: 433 training return: tensor(-403.9480, device='cuda:0')
episode: 434 training return: tensor(-430.5432, device='cuda:0')
episode: 435 training return: tensor(-396.0168, device='cuda:0')
epoch: 109 test_true_pfm: 598.8953977617044 sim_pfm: -326.99795436573913
episode: 436 training return: tensor(-368.6645, device='cuda:0')
episode: 437 training return: tensor(-406.1886, device='cuda:0')
episode: 438 training return: tensor(-440.3627, device='cuda:0')
episode: 439 training return: tensor(-414.9930, device='cuda:0')
epoch: 110 test_true_pfm: 730.4538789194426 sim_pfm: -324.09113952773623
episode: 440 training return: tensor(-414.1055, device='cuda:0')
episode: 441 training return: tensor(-364.2574, device='cuda:0')
episode: 442 training return: tensor(-414.6963, device='cuda:0')
episode: 443 training return: tensor(-457.3892, device='cuda:0')
epoch: 111 test_true_pfm: 652.0175110120784 sim_pfm: -316.1517995952163
episode: 444 training return: tensor(-403.8355, device='cuda:0')
episode: 445 training return: tensor(-387.4424, device='cuda:0')
episode: 446 training return: tensor(-361.2057, device='cuda:0')
episode: 447 training return: tensor(-437.8280, device='cuda:0')
epoch: 112 test_true_pfm: 561.1834981950224 sim_pfm: -329.15608786562615
episode: 448 training return: tensor(-422.4797, device='cuda:0')
episode: 449 training return: tensor(-401.0741, device='cuda:0')
episode: 450 training return: tensor(-461.9254, device='cuda:0')
episode: 451 training return: tensor(-444.6011, device='cuda:0')
epoch: 113 test_true_pfm: 705.5533017717709 sim_pfm: -296.76994229247794
episode: 452 training return: tensor(-412.9790, device='cuda:0')
episode: 453 training return: tensor(-410.8443, device='cuda:0')
episode: 454 training return: tensor(-401.9526, device='cuda:0')
episode: 455 training return: tensor(-362.3743, device='cuda:0')
epoch: 114 test_true_pfm: 641.8998191357138 sim_pfm: -321.12196385115385
episode: 456 training return: tensor(-424.6016, device='cuda:0')
episode: 457 training return: tensor(-394.0423, device='cuda:0')
episode: 458 training return: tensor(-409.1437, device='cuda:0')
episode: 459 training return: tensor(-390.5499, device='cuda:0')
epoch: 115 test_true_pfm: 633.2230621261093 sim_pfm: -317.87133995299035
episode: 460 training return: tensor(-359.3299, device='cuda:0')
episode: 461 training return: tensor(-413.7493, device='cuda:0')
episode: 462 training return: tensor(-385.4670, device='cuda:0')
episode: 463 training return: tensor(-370.9718, device='cuda:0')
epoch: 116 test_true_pfm: 725.5636241738617 sim_pfm: -304.5051117273203
episode: 464 training return: tensor(-406.0988, device='cuda:0')
episode: 465 training return: tensor(-419.5457, device='cuda:0')
episode: 466 training return: tensor(-373.3030, device='cuda:0')
episode: 467 training return: tensor(-373.7136, device='cuda:0')
epoch: 117 test_true_pfm: 622.3474850339268 sim_pfm: -334.81939173377276
episode: 468 training return: tensor(-377.4466, device='cuda:0')
episode: 469 training return: tensor(-412.0545, device='cuda:0')
episode: 470 training return: tensor(-368.2864, device='cuda:0')
episode: 471 training return: tensor(-403.4089, device='cuda:0')
epoch: 118 test_true_pfm: 726.7096284469368 sim_pfm: -296.23716745257843
episode: 472 training return: tensor(-374.8826, device='cuda:0')
episode: 473 training return: tensor(-401.7781, device='cuda:0')
episode: 474 training return: tensor(-424.4626, device='cuda:0')
episode: 475 training return: tensor(-438.3925, device='cuda:0')
epoch: 119 test_true_pfm: 720.6282371762524 sim_pfm: -321.9770282274112
episode: 476 training return: tensor(-422.5451, device='cuda:0')
episode: 477 training return: tensor(-394.6232, device='cuda:0')
episode: 478 training return: tensor(-422.3956, device='cuda:0')
episode: 479 training return: tensor(-406.5200, device='cuda:0')
epoch: 120 test_true_pfm: 703.3282224013143 sim_pfm: -322.6001656348041
episode: 480 training return: tensor(-413.9803, device='cuda:0')
episode: 481 training return: tensor(-391.5734, device='cuda:0')
episode: 482 training return: tensor(-435.5885, device='cuda:0')
episode: 483 training return: tensor(-399.2179, device='cuda:0')
epoch: 121 test_true_pfm: 618.8759547720903 sim_pfm: -306.6576870511829
episode: 484 training return: tensor(-418.5328, device='cuda:0')
episode: 485 training return: tensor(-418.5679, device='cuda:0')
episode: 486 training return: tensor(-399.7823, device='cuda:0')
episode: 487 training return: tensor(-408.5002, device='cuda:0')
epoch: 122 test_true_pfm: 709.1097362058567 sim_pfm: -325.36273284908384
episode: 488 training return: tensor(-417.9395, device='cuda:0')
episode: 489 training return: tensor(-409.9207, device='cuda:0')
episode: 490 training return: tensor(-400.4236, device='cuda:0')
episode: 491 training return: tensor(-381.0575, device='cuda:0')
epoch: 123 test_true_pfm: 732.0895609453279 sim_pfm: -319.0149205196455
episode: 492 training return: tensor(-389.6330, device='cuda:0')
episode: 493 training return: tensor(-395.2794, device='cuda:0')
episode: 494 training return: tensor(-392.5876, device='cuda:0')
episode: 495 training return: tensor(-363.9860, device='cuda:0')
epoch: 124 test_true_pfm: 664.2904112355628 sim_pfm: -311.2526165735132
episode: 496 training return: tensor(-401.9113, device='cuda:0')
episode: 497 training return: tensor(-421.6121, device='cuda:0')
episode: 498 training return: tensor(-418.6576, device='cuda:0')
episode: 499 training return: tensor(-381.4093, device='cuda:0')
epoch: 125 test_true_pfm: 608.0414721052697 sim_pfm: -318.31740520498715
episode: 500 training return: tensor(-406.9387, device='cuda:0')
episode: 501 training return: tensor(-400.3298, device='cuda:0')
episode: 502 training return: tensor(-390.0111, device='cuda:0')
episode: 503 training return: tensor(-353.5511, device='cuda:0')
epoch: 126 test_true_pfm: 607.8957765559668 sim_pfm: -333.36811329153716
episode: 504 training return: tensor(-394.6255, device='cuda:0')
episode: 505 training return: tensor(-398.3075, device='cuda:0')
episode: 506 training return: tensor(-402.9666, device='cuda:0')
episode: 507 training return: tensor(-378.4956, device='cuda:0')
epoch: 127 test_true_pfm: 680.1254257196475 sim_pfm: -324.4987250479171
episode: 508 training return: tensor(-399.6348, device='cuda:0')
episode: 509 training return: tensor(-382.6239, device='cuda:0')
episode: 510 training return: tensor(-376.9798, device='cuda:0')
episode: 511 training return: tensor(-383.1837, device='cuda:0')
epoch: 128 test_true_pfm: 626.7280178075745 sim_pfm: -282.8242857469789
episode: 512 training return: tensor(-382.1696, device='cuda:0')
episode: 513 training return: tensor(-389.5300, device='cuda:0')
episode: 514 training return: tensor(-403.8794, device='cuda:0')
episode: 515 training return: tensor(-371.7587, device='cuda:0')
epoch: 129 test_true_pfm: 702.996100762713 sim_pfm: -312.23345495795365
episode: 516 training return: tensor(-356.6259, device='cuda:0')
episode: 517 training return: tensor(-415.3411, device='cuda:0')
episode: 518 training return: tensor(-351.4745, device='cuda:0')
episode: 519 training return: tensor(-388.4357, device='cuda:0')
epoch: 130 test_true_pfm: 750.9188470237992 sim_pfm: -295.92723123310134
episode: 520 training return: tensor(-351.2476, device='cuda:0')
episode: 521 training return: tensor(-403.6362, device='cuda:0')
episode: 522 training return: tensor(-391.8117, device='cuda:0')
episode: 523 training return: tensor(-400.5525, device='cuda:0')
epoch: 131 test_true_pfm: 718.5027977843524 sim_pfm: -301.3190265849116
episode: 524 training return: tensor(-427.5422, device='cuda:0')
episode: 525 training return: tensor(-408.2973, device='cuda:0')
episode: 526 training return: tensor(-369.3372, device='cuda:0')
episode: 527 training return: tensor(-447.4654, device='cuda:0')
epoch: 132 test_true_pfm: 718.6472414539558 sim_pfm: -298.6487187492894
episode: 528 training return: tensor(-395.9759, device='cuda:0')
episode: 529 training return: tensor(-434.9622, device='cuda:0')
episode: 530 training return: tensor(-384.8329, device='cuda:0')
episode: 531 training return: tensor(-404.9237, device='cuda:0')
epoch: 133 test_true_pfm: 690.1127445594199 sim_pfm: -315.89528782774386
episode: 532 training return: tensor(-447.0111, device='cuda:0')
episode: 533 training return: tensor(-404.3601, device='cuda:0')
episode: 534 training return: tensor(-402.8773, device='cuda:0')
episode: 535 training return: tensor(-373.5750, device='cuda:0')
epoch: 134 test_true_pfm: 710.732504962309 sim_pfm: -316.10239219650003
episode: 536 training return: tensor(-359.1037, device='cuda:0')
episode: 537 training return: tensor(-400.1379, device='cuda:0')
episode: 538 training return: tensor(-377.0306, device='cuda:0')
episode: 539 training return: tensor(-387.8802, device='cuda:0')
epoch: 135 test_true_pfm: 651.4118735022154 sim_pfm: -307.9782111130965
episode: 540 training return: tensor(-374.2423, device='cuda:0')
episode: 541 training return: tensor(-378.0623, device='cuda:0')
episode: 542 training return: tensor(-373.3924, device='cuda:0')
episode: 543 training return: tensor(-405.1563, device='cuda:0')
epoch: 136 test_true_pfm: 734.1908205708991 sim_pfm: -328.16143378832686
episode: 544 training return: tensor(-366.4392, device='cuda:0')
episode: 545 training return: tensor(-387.6896, device='cuda:0')
episode: 546 training return: tensor(-414.4657, device='cuda:0')
episode: 547 training return: tensor(-442.1530, device='cuda:0')
epoch: 137 test_true_pfm: 705.0391619968756 sim_pfm: -283.81147938990034
episode: 548 training return: tensor(-436.0357, device='cuda:0')
episode: 549 training return: tensor(-375.7523, device='cuda:0')
episode: 550 training return: tensor(-402.4291, device='cuda:0')
episode: 551 training return: tensor(-422.4718, device='cuda:0')
epoch: 138 test_true_pfm: 805.3759379416041 sim_pfm: -310.1390808766203
episode: 552 training return: tensor(-422.6009, device='cuda:0')
episode: 553 training return: tensor(-374.9799, device='cuda:0')
episode: 554 training return: tensor(-373.0501, device='cuda:0')
episode: 555 training return: tensor(-349.0163, device='cuda:0')
epoch: 139 test_true_pfm: 688.9254869608973 sim_pfm: -343.0761104143069
episode: 556 training return: tensor(-407.1831, device='cuda:0')
episode: 557 training return: tensor(-343.9788, device='cuda:0')
episode: 558 training return: tensor(-423.9373, device='cuda:0')
episode: 559 training return: tensor(-406.1151, device='cuda:0')
epoch: 140 test_true_pfm: 680.6843646096398 sim_pfm: -306.9012903289792
episode: 560 training return: tensor(-383.2230, device='cuda:0')
episode: 561 training return: tensor(-394.1771, device='cuda:0')
episode: 562 training return: tensor(-401.4598, device='cuda:0')
episode: 563 training return: tensor(-357.1419, device='cuda:0')
epoch: 141 test_true_pfm: 686.8368062390308 sim_pfm: -333.27521960037603
episode: 564 training return: tensor(-391.4665, device='cuda:0')
episode: 565 training return: tensor(-373.9110, device='cuda:0')
episode: 566 training return: tensor(-399.5072, device='cuda:0')
episode: 567 training return: tensor(-382.5125, device='cuda:0')
epoch: 142 test_true_pfm: 715.7035169994488 sim_pfm: -310.6532174056629
episode: 568 training return: tensor(-337.6355, device='cuda:0')
episode: 569 training return: tensor(-393.4184, device='cuda:0')
episode: 570 training return: tensor(-462.0819, device='cuda:0')
episode: 571 training return: tensor(-391.8636, device='cuda:0')
epoch: 143 test_true_pfm: 741.6879654108835 sim_pfm: -314.12317389502033
episode: 572 training return: tensor(-363.7020, device='cuda:0')
episode: 573 training return: tensor(-422.2531, device='cuda:0')
episode: 574 training return: tensor(-336.3459, device='cuda:0')
episode: 575 training return: tensor(-343.7302, device='cuda:0')
epoch: 144 test_true_pfm: 738.7580242526523 sim_pfm: -294.85747555946
episode: 576 training return: tensor(-435.1893, device='cuda:0')
episode: 577 training return: tensor(-382.9647, device='cuda:0')
episode: 578 training return: tensor(-386.3724, device='cuda:0')
episode: 579 training return: tensor(-392.2663, device='cuda:0')
epoch: 145 test_true_pfm: 756.9507033098816 sim_pfm: -304.2845634911985
episode: 580 training return: tensor(-385.6415, device='cuda:0')
episode: 581 training return: tensor(-388.4368, device='cuda:0')
episode: 582 training return: tensor(-424.4152, device='cuda:0')
episode: 583 training return: tensor(-407.7495, device='cuda:0')
epoch: 146 test_true_pfm: 675.2890475245315 sim_pfm: -316.2592565009836
episode: 584 training return: tensor(-350.3011, device='cuda:0')
episode: 585 training return: tensor(-413.1899, device='cuda:0')
episode: 586 training return: tensor(-386.4882, device='cuda:0')
episode: 587 training return: tensor(-387.3879, device='cuda:0')
epoch: 147 test_true_pfm: 822.6044066599306 sim_pfm: -297.58536989746307
episode: 588 training return: tensor(-401.1592, device='cuda:0')
episode: 589 training return: tensor(-404.8787, device='cuda:0')
episode: 590 training return: tensor(-396.6391, device='cuda:0')
episode: 591 training return: tensor(-414.6268, device='cuda:0')
epoch: 148 test_true_pfm: 714.9352317084939 sim_pfm: -324.1940549976037
episode: 592 training return: tensor(-392.7144, device='cuda:0')
episode: 593 training return: tensor(-380.0296, device='cuda:0')
episode: 594 training return: tensor(-431.5664, device='cuda:0')
episode: 595 training return: tensor(-365.8321, device='cuda:0')
epoch: 149 test_true_pfm: 903.4816387399869 sim_pfm: -277.134173750014
episode: 596 training return: tensor(-389.6665, device='cuda:0')
episode: 597 training return: tensor(-403.0645, device='cuda:0')
episode: 598 training return: tensor(-387.4106, device='cuda:0')
episode: 599 training return: tensor(-373.5640, device='cuda:0')
epoch: 150 test_true_pfm: 847.5408837989665 sim_pfm: -303.6214259537519
