['--alg', 'sac', '--env', 'Hopper-v3', '--learn', 'baseline', '--traj', 'medium', '--seed', '3']
episode: 0 training return: tensor(-334.0804, device='cuda:0')
episode: 1 training return: tensor(-247.8421, device='cuda:0')
episode: 2 training return: tensor(-28.4737, device='cuda:0')
episode: 3 training return: tensor(-663.5514, device='cuda:0')
epoch: 1 test_true_pfm: 166.8078403305311 sim_pfm: -906.9921949207783
episode: 4 training return: tensor(-365.4417, device='cuda:0')
episode: 5 training return: tensor(-540.4052, device='cuda:0')
episode: 6 training return: tensor(-290.6320, device='cuda:0')
episode: 7 training return: tensor(-396.9796, device='cuda:0')
epoch: 2 test_true_pfm: 202.4563053751535 sim_pfm: -884.2692107462595
episode: 8 training return: tensor(-255.7629, device='cuda:0')
episode: 9 training return: tensor(-680.8993, device='cuda:0')
episode: 10 training return: tensor(-849.9184, device='cuda:0')
episode: 11 training return: tensor(-884.3284, device='cuda:0')
epoch: 3 test_true_pfm: 228.76505765863496 sim_pfm: -901.5758277471954
episode: 12 training return: tensor(-897.9833, device='cuda:0')
episode: 13 training return: tensor(-891.0165, device='cuda:0')
episode: 14 training return: tensor(-887.5840, device='cuda:0')
episode: 15 training return: tensor(-776.1656, device='cuda:0')
epoch: 4 test_true_pfm: 207.13127470485622 sim_pfm: -840.1981412135938
episode: 16 training return: tensor(-653.4518, device='cuda:0')
episode: 17 training return: tensor(-637.2125, device='cuda:0')
episode: 18 training return: tensor(-575.3032, device='cuda:0')
episode: 19 training return: tensor(-556.3948, device='cuda:0')
epoch: 5 test_true_pfm: 2.4150772964544136 sim_pfm: -242.5642552790426
episode: 20 training return: tensor(-539.0026, device='cuda:0')
episode: 21 training return: tensor(61.6286, device='cuda:0')
episode: 22 training return: tensor(13.6447, device='cuda:0')
episode: 23 training return: tensor(-580.6174, device='cuda:0')
epoch: 6 test_true_pfm: 48.002902531863555 sim_pfm: -446.1597306466817
episode: 24 training return: tensor(-544.0434, device='cuda:0')
episode: 25 training return: tensor(-377.1093, device='cuda:0')
episode: 26 training return: tensor(-353.2344, device='cuda:0')
episode: 27 training return: tensor(-503.0243, device='cuda:0')
epoch: 7 test_true_pfm: -39.90772226203641 sim_pfm: -385.2199547390143
episode: 28 training return: tensor(-429.0264, device='cuda:0')
episode: 29 training return: tensor(-433.2844, device='cuda:0')
episode: 30 training return: tensor(-415.8926, device='cuda:0')
episode: 31 training return: tensor(-569.6797, device='cuda:0')
epoch: 8 test_true_pfm: 204.4299536543324 sim_pfm: -568.5848940660557
episode: 32 training return: tensor(-595.1354, device='cuda:0')
episode: 33 training return: tensor(-591.8693, device='cuda:0')
episode: 34 training return: tensor(-583.7225, device='cuda:0')
episode: 35 training return: tensor(-584.3206, device='cuda:0')
epoch: 9 test_true_pfm: 233.9584464888702 sim_pfm: -562.7349076978862
episode: 36 training return: tensor(-387.7773, device='cuda:0')
episode: 37 training return: tensor(-348.2052, device='cuda:0')
episode: 38 training return: tensor(-81.8962, device='cuda:0')
episode: 39 training return: tensor(-55.8066, device='cuda:0')
epoch: 10 test_true_pfm: 213.95385961205787 sim_pfm: -549.7424104155701
episode: 40 training return: tensor(-553.8011, device='cuda:0')
episode: 41 training return: tensor(-548.7524, device='cuda:0')
episode: 42 training return: tensor(-545.4322, device='cuda:0')
episode: 43 training return: tensor(-534.9355, device='cuda:0')
epoch: 11 test_true_pfm: 195.67107015710985 sim_pfm: -497.2354356307187
episode: 44 training return: tensor(-534.4131, device='cuda:0')
episode: 45 training return: tensor(-546.3817, device='cuda:0')
episode: 46 training return: tensor(-831.1706, device='cuda:0')
episode: 47 training return: tensor(-566.4467, device='cuda:0')
epoch: 12 test_true_pfm: 309.58231245076246 sim_pfm: -499.0279256836511
episode: 48 training return: tensor(-533.1636, device='cuda:0')
episode: 49 training return: tensor(-589.9113, device='cuda:0')
episode: 50 training return: tensor(-555.1681, device='cuda:0')
episode: 51 training return: tensor(-560.1016, device='cuda:0')
epoch: 13 test_true_pfm: 250.44544554791185 sim_pfm: -518.8961794202527
episode: 52 training return: tensor(-548.8016, device='cuda:0')
episode: 53 training return: tensor(-561.2460, device='cuda:0')
episode: 54 training return: tensor(-568.0084, device='cuda:0')
episode: 55 training return: tensor(-553.5720, device='cuda:0')
epoch: 14 test_true_pfm: 183.66850728546407 sim_pfm: -520.5735287256539
episode: 56 training return: tensor(-542.1518, device='cuda:0')
episode: 57 training return: tensor(-551.4521, device='cuda:0')
episode: 58 training return: tensor(-550.1174, device='cuda:0')
episode: 59 training return: tensor(-547.2849, device='cuda:0')
epoch: 15 test_true_pfm: 188.51691838584637 sim_pfm: -501.8407964760748
episode: 60 training return: tensor(-548.4518, device='cuda:0')
episode: 61 training return: tensor(-542.2327, device='cuda:0')
episode: 62 training return: tensor(-551.4438, device='cuda:0')
episode: 63 training return: tensor(-546.2828, device='cuda:0')
epoch: 16 test_true_pfm: 209.4831317395434 sim_pfm: -499.3083842890337
episode: 64 training return: tensor(-554.4426, device='cuda:0')
episode: 65 training return: tensor(-529.6030, device='cuda:0')
episode: 66 training return: tensor(-546.7380, device='cuda:0')
episode: 67 training return: tensor(-523.1707, device='cuda:0')
epoch: 17 test_true_pfm: 223.317440290809 sim_pfm: -491.63286925821257
episode: 68 training return: tensor(-538.6843, device='cuda:0')
episode: 69 training return: tensor(-534.0689, device='cuda:0')
episode: 70 training return: tensor(-537.4738, device='cuda:0')
episode: 71 training return: tensor(-561.1765, device='cuda:0')
epoch: 18 test_true_pfm: 211.9800879604355 sim_pfm: -496.28041265577
episode: 72 training return: tensor(-543.0468, device='cuda:0')
episode: 73 training return: tensor(-554.4885, device='cuda:0')
episode: 74 training return: tensor(-545.6843, device='cuda:0')
episode: 75 training return: tensor(-543.7376, device='cuda:0')
epoch: 19 test_true_pfm: 233.01040918202446 sim_pfm: -476.55453605328995
episode: 76 training return: tensor(-527.9209, device='cuda:0')
episode: 77 training return: tensor(-529.7326, device='cuda:0')
episode: 78 training return: tensor(-538.8879, device='cuda:0')
episode: 79 training return: tensor(-523.6709, device='cuda:0')
epoch: 20 test_true_pfm: 264.9805367072283 sim_pfm: -485.6809150434953
episode: 80 training return: tensor(-547.3231, device='cuda:0')
episode: 81 training return: tensor(-525.8658, device='cuda:0')
episode: 82 training return: tensor(-532.3139, device='cuda:0')
episode: 83 training return: tensor(-531.2250, device='cuda:0')
epoch: 21 test_true_pfm: 228.21710233432486 sim_pfm: -475.4005502151558
episode: 84 training return: tensor(-524.8607, device='cuda:0')
episode: 85 training return: tensor(-527.6594, device='cuda:0')
episode: 86 training return: tensor(-515.4889, device='cuda:0')
episode: 87 training return: tensor(-517.1667, device='cuda:0')
epoch: 22 test_true_pfm: 251.62155630019427 sim_pfm: -472.8798708198592
episode: 88 training return: tensor(-534.8387, device='cuda:0')
episode: 89 training return: tensor(-544.2123, device='cuda:0')
episode: 90 training return: tensor(-514.3975, device='cuda:0')
episode: 91 training return: tensor(-532.2262, device='cuda:0')
epoch: 23 test_true_pfm: 241.41733854769714 sim_pfm: -482.3144539802258
episode: 92 training return: tensor(-521.5393, device='cuda:0')
episode: 93 training return: tensor(-520.3074, device='cuda:0')
episode: 94 training return: tensor(-526.9602, device='cuda:0')
episode: 95 training return: tensor(-524.0656, device='cuda:0')
epoch: 24 test_true_pfm: 255.4163297425724 sim_pfm: -472.54605583668064
episode: 96 training return: tensor(-523.9554, device='cuda:0')
episode: 97 training return: tensor(-520.5085, device='cuda:0')
episode: 98 training return: tensor(-530.7452, device='cuda:0')
episode: 99 training return: tensor(-533.0016, device='cuda:0')
epoch: 25 test_true_pfm: 235.91859411059139 sim_pfm: -482.8937619710341
episode: 100 training return: tensor(-506.8241, device='cuda:0')
episode: 101 training return: tensor(-520.7880, device='cuda:0')
episode: 102 training return: tensor(-524.3137, device='cuda:0')
episode: 103 training return: tensor(-524.2823, device='cuda:0')
epoch: 26 test_true_pfm: 252.66149535997872 sim_pfm: -473.75070902053267
episode: 104 training return: tensor(-530.0461, device='cuda:0')
episode: 105 training return: tensor(-523.3650, device='cuda:0')
episode: 106 training return: tensor(-518.2605, device='cuda:0')
episode: 107 training return: tensor(-523.1436, device='cuda:0')
epoch: 27 test_true_pfm: 259.4623128008911 sim_pfm: -472.7881206565459
episode: 108 training return: tensor(-510.0718, device='cuda:0')
episode: 109 training return: tensor(-538.4969, device='cuda:0')
episode: 110 training return: tensor(-516.0622, device='cuda:0')
episode: 111 training return: tensor(-518.0922, device='cuda:0')
epoch: 28 test_true_pfm: 251.53641026068166 sim_pfm: -473.75464442224865
episode: 112 training return: tensor(-519.2671, device='cuda:0')
episode: 113 training return: tensor(-527.0338, device='cuda:0')
episode: 114 training return: tensor(-521.3082, device='cuda:0')
episode: 115 training return: tensor(-510.7265, device='cuda:0')
epoch: 29 test_true_pfm: 260.79393815829354 sim_pfm: -473.84179601771757
episode: 116 training return: tensor(-515.6824, device='cuda:0')
episode: 117 training return: tensor(-517.6302, device='cuda:0')
episode: 118 training return: tensor(-523.1105, device='cuda:0')
episode: 119 training return: tensor(-522.3497, device='cuda:0')
epoch: 30 test_true_pfm: 265.00618160048435 sim_pfm: -469.8596108068402
episode: 120 training return: tensor(-516.0989, device='cuda:0')
episode: 121 training return: tensor(-513.3358, device='cuda:0')
episode: 122 training return: tensor(-510.0216, device='cuda:0')
episode: 123 training return: tensor(-515.0844, device='cuda:0')
epoch: 31 test_true_pfm: 270.35220292024627 sim_pfm: -468.77973144004744
episode: 124 training return: tensor(-516.9310, device='cuda:0')
episode: 125 training return: tensor(-508.0897, device='cuda:0')
episode: 126 training return: tensor(-529.4684, device='cuda:0')
episode: 127 training return: tensor(-507.9677, device='cuda:0')
epoch: 32 test_true_pfm: 259.58894620347337 sim_pfm: -471.04401245635626
episode: 128 training return: tensor(-520.7495, device='cuda:0')
episode: 129 training return: tensor(-511.8006, device='cuda:0')
episode: 130 training return: tensor(-515.0401, device='cuda:0')
episode: 131 training return: tensor(-514.0509, device='cuda:0')
epoch: 33 test_true_pfm: 255.2531457378835 sim_pfm: -475.67915138974786
episode: 132 training return: tensor(-515.8628, device='cuda:0')
episode: 133 training return: tensor(-512.7553, device='cuda:0')
episode: 134 training return: tensor(-509.9976, device='cuda:0')
episode: 135 training return: tensor(-496.0258, device='cuda:0')
epoch: 34 test_true_pfm: 263.54878578731297 sim_pfm: -470.16813840158284
episode: 136 training return: tensor(-511.8755, device='cuda:0')
episode: 137 training return: tensor(-504.8058, device='cuda:0')
episode: 138 training return: tensor(-503.3870, device='cuda:0')
episode: 139 training return: tensor(-503.0515, device='cuda:0')
epoch: 35 test_true_pfm: 279.6768021906905 sim_pfm: -466.2578288821193
episode: 140 training return: tensor(-514.6364, device='cuda:0')
episode: 141 training return: tensor(-497.6294, device='cuda:0')
episode: 142 training return: tensor(-511.4961, device='cuda:0')
episode: 143 training return: tensor(-508.9185, device='cuda:0')
epoch: 36 test_true_pfm: 256.92803497662095 sim_pfm: -477.1147604038318
episode: 144 training return: tensor(-512.4272, device='cuda:0')
episode: 145 training return: tensor(-519.9238, device='cuda:0')
episode: 146 training return: tensor(-492.7855, device='cuda:0')
episode: 147 training return: tensor(-506.3862, device='cuda:0')
epoch: 37 test_true_pfm: 262.81197280617545 sim_pfm: -468.6170181185007
episode: 148 training return: tensor(-506.9445, device='cuda:0')
episode: 149 training return: tensor(-514.0619, device='cuda:0')
episode: 150 training return: tensor(-505.8105, device='cuda:0')
episode: 151 training return: tensor(-514.2443, device='cuda:0')
epoch: 38 test_true_pfm: 266.5531131545658 sim_pfm: -469.10151791355264
episode: 152 training return: tensor(-504.8136, device='cuda:0')
episode: 153 training return: tensor(-510.0224, device='cuda:0')
episode: 154 training return: tensor(-507.7249, device='cuda:0')
episode: 155 training return: tensor(-525.0992, device='cuda:0')
epoch: 39 test_true_pfm: 269.4115646786367 sim_pfm: -462.8283497934074
episode: 156 training return: tensor(-506.2536, device='cuda:0')
episode: 157 training return: tensor(-505.2867, device='cuda:0')
episode: 158 training return: tensor(-515.7089, device='cuda:0')
episode: 159 training return: tensor(-507.2390, device='cuda:0')
epoch: 40 test_true_pfm: 271.7221392519496 sim_pfm: -469.0927519838636
episode: 160 training return: tensor(-511.9311, device='cuda:0')
episode: 161 training return: tensor(-518.7248, device='cuda:0')
episode: 162 training return: tensor(-510.5118, device='cuda:0')
episode: 163 training return: tensor(-508.9276, device='cuda:0')
epoch: 41 test_true_pfm: 267.66086251181923 sim_pfm: -468.2738666633765
episode: 164 training return: tensor(-514.4144, device='cuda:0')
episode: 165 training return: tensor(-501.1804, device='cuda:0')
episode: 166 training return: tensor(-499.5538, device='cuda:0')
episode: 167 training return: tensor(-514.7428, device='cuda:0')
epoch: 42 test_true_pfm: 274.63480477290875 sim_pfm: -460.4546540961601
episode: 168 training return: tensor(-508.9138, device='cuda:0')
episode: 169 training return: tensor(-494.8554, device='cuda:0')
episode: 170 training return: tensor(-506.5036, device='cuda:0')
episode: 171 training return: tensor(-512.3139, device='cuda:0')
epoch: 43 test_true_pfm: 276.172230607827 sim_pfm: -464.53659964585677
episode: 172 training return: tensor(-522.7233, device='cuda:0')
episode: 173 training return: tensor(-508.7008, device='cuda:0')
episode: 174 training return: tensor(-507.4908, device='cuda:0')
episode: 175 training return: tensor(-515.7405, device='cuda:0')
epoch: 44 test_true_pfm: 261.771731274689 sim_pfm: -470.4055624161265
episode: 176 training return: tensor(-519.3234, device='cuda:0')
episode: 177 training return: tensor(-512.1807, device='cuda:0')
episode: 178 training return: tensor(-523.5218, device='cuda:0')
episode: 179 training return: tensor(-510.0441, device='cuda:0')
epoch: 45 test_true_pfm: 290.6975955447188 sim_pfm: -457.7660401967975
episode: 180 training return: tensor(-500.3285, device='cuda:0')
episode: 181 training return: tensor(-520.0071, device='cuda:0')
episode: 182 training return: tensor(-519.8251, device='cuda:0')
episode: 183 training return: tensor(-513.6416, device='cuda:0')
epoch: 46 test_true_pfm: 262.1321382250676 sim_pfm: -472.59398729889654
episode: 184 training return: tensor(-496.2671, device='cuda:0')
episode: 185 training return: tensor(-515.6755, device='cuda:0')
episode: 186 training return: tensor(-507.3995, device='cuda:0')
episode: 187 training return: tensor(-500.2366, device='cuda:0')
epoch: 47 test_true_pfm: 270.58602044359316 sim_pfm: -465.27459596144035
episode: 188 training return: tensor(-511.1056, device='cuda:0')
episode: 189 training return: tensor(-524.6920, device='cuda:0')
episode: 190 training return: tensor(-508.9546, device='cuda:0')
episode: 191 training return: tensor(-515.7896, device='cuda:0')
epoch: 48 test_true_pfm: 280.9119307309034 sim_pfm: -463.15925556551275
episode: 192 training return: tensor(-513.1104, device='cuda:0')
episode: 193 training return: tensor(-507.6488, device='cuda:0')
episode: 194 training return: tensor(-499.4523, device='cuda:0')
episode: 195 training return: tensor(-503.3289, device='cuda:0')
epoch: 49 test_true_pfm: 264.6836816644571 sim_pfm: -467.64437636562315
episode: 196 training return: tensor(-510.1181, device='cuda:0')
episode: 197 training return: tensor(-500.6293, device='cuda:0')
episode: 198 training return: tensor(-515.6841, device='cuda:0')
episode: 199 training return: tensor(-498.2978, device='cuda:0')
epoch: 50 test_true_pfm: 258.633062202788 sim_pfm: -469.84403447983397
episode: 200 training return: tensor(-528.7078, device='cuda:0')
episode: 201 training return: tensor(-505.0142, device='cuda:0')
episode: 202 training return: tensor(-503.3691, device='cuda:0')
episode: 203 training return: tensor(-512.7419, device='cuda:0')
epoch: 51 test_true_pfm: 276.3798588122749 sim_pfm: -461.71218347596005
episode: 204 training return: tensor(-510.9491, device='cuda:0')
episode: 205 training return: tensor(-517.3995, device='cuda:0')
episode: 206 training return: tensor(-502.2005, device='cuda:0')
episode: 207 training return: tensor(-523.9706, device='cuda:0')
epoch: 52 test_true_pfm: 272.6708546774002 sim_pfm: -467.773992206164
episode: 208 training return: tensor(-498.6260, device='cuda:0')
episode: 209 training return: tensor(-515.9282, device='cuda:0')
episode: 210 training return: tensor(-512.3751, device='cuda:0')
episode: 211 training return: tensor(-498.4106, device='cuda:0')
epoch: 53 test_true_pfm: 275.18489936118124 sim_pfm: -462.9628351616363
episode: 212 training return: tensor(-499.2489, device='cuda:0')
episode: 213 training return: tensor(-514.0308, device='cuda:0')
episode: 214 training return: tensor(-506.0653, device='cuda:0')
episode: 215 training return: tensor(-496.2830, device='cuda:0')
epoch: 54 test_true_pfm: 277.65330637274513 sim_pfm: -464.119332894062
episode: 216 training return: tensor(-508.4817, device='cuda:0')
episode: 217 training return: tensor(-513.7711, device='cuda:0')
episode: 218 training return: tensor(-503.6571, device='cuda:0')
episode: 219 training return: tensor(-505.4898, device='cuda:0')
epoch: 55 test_true_pfm: 261.3702879844007 sim_pfm: -464.5134795065969
episode: 220 training return: tensor(-516.8703, device='cuda:0')
episode: 221 training return: tensor(-506.4314, device='cuda:0')
episode: 222 training return: tensor(-508.5536, device='cuda:0')
episode: 223 training return: tensor(-511.9459, device='cuda:0')
epoch: 56 test_true_pfm: 280.5470540852621 sim_pfm: -462.5151820870815
episode: 224 training return: tensor(-515.3425, device='cuda:0')
episode: 225 training return: tensor(-516.2807, device='cuda:0')
episode: 226 training return: tensor(-505.4578, device='cuda:0')
episode: 227 training return: tensor(-495.3001, device='cuda:0')
epoch: 57 test_true_pfm: 269.8189999006663 sim_pfm: -460.94353101759526
episode: 228 training return: tensor(-492.0930, device='cuda:0')
episode: 229 training return: tensor(-523.5099, device='cuda:0')
episode: 230 training return: tensor(-503.2246, device='cuda:0')
episode: 231 training return: tensor(-506.6935, device='cuda:0')
epoch: 58 test_true_pfm: 281.3304874812591 sim_pfm: -460.87058644307155
episode: 232 training return: tensor(-520.6511, device='cuda:0')
episode: 233 training return: tensor(-509.1153, device='cuda:0')
episode: 234 training return: tensor(-511.3127, device='cuda:0')
episode: 235 training return: tensor(-501.5627, device='cuda:0')
epoch: 59 test_true_pfm: 261.75856187564096 sim_pfm: -469.8530701786901
episode: 236 training return: tensor(-498.8130, device='cuda:0')
episode: 237 training return: tensor(-509.8097, device='cuda:0')
episode: 238 training return: tensor(-504.5858, device='cuda:0')
episode: 239 training return: tensor(-500.0685, device='cuda:0')
epoch: 60 test_true_pfm: 254.85397533986395 sim_pfm: -465.4062898081417
episode: 240 training return: tensor(-514.5687, device='cuda:0')
episode: 241 training return: tensor(-512.1454, device='cuda:0')
episode: 242 training return: tensor(-503.0654, device='cuda:0')
episode: 243 training return: tensor(-504.2020, device='cuda:0')
epoch: 61 test_true_pfm: 276.3403858950717 sim_pfm: -461.33838638445985
episode: 244 training return: tensor(-502.2520, device='cuda:0')
episode: 245 training return: tensor(-502.1694, device='cuda:0')
episode: 246 training return: tensor(-499.9380, device='cuda:0')
episode: 247 training return: tensor(-520.9729, device='cuda:0')
epoch: 62 test_true_pfm: 276.65164518494 sim_pfm: -460.79364736673114
episode: 248 training return: tensor(-506.7347, device='cuda:0')
episode: 249 training return: tensor(-503.8101, device='cuda:0')
episode: 250 training return: tensor(-499.6375, device='cuda:0')
episode: 251 training return: tensor(-501.5506, device='cuda:0')
epoch: 63 test_true_pfm: 288.13427100554617 sim_pfm: -457.6137639526278
episode: 252 training return: tensor(-516.7120, device='cuda:0')
episode: 253 training return: tensor(-499.0352, device='cuda:0')
episode: 254 training return: tensor(-496.1357, device='cuda:0')
episode: 255 training return: tensor(-513.2076, device='cuda:0')
epoch: 64 test_true_pfm: 266.509272375325 sim_pfm: -465.7133717299439
episode: 256 training return: tensor(-513.9184, device='cuda:0')
episode: 257 training return: tensor(-515.5184, device='cuda:0')
episode: 258 training return: tensor(-513.3806, device='cuda:0')
episode: 259 training return: tensor(-505.4057, device='cuda:0')
epoch: 65 test_true_pfm: 296.0522945914301 sim_pfm: -458.46978740017704
episode: 260 training return: tensor(-503.4283, device='cuda:0')
episode: 261 training return: tensor(-511.8216, device='cuda:0')
episode: 262 training return: tensor(-497.3554, device='cuda:0')
episode: 263 training return: tensor(-509.9946, device='cuda:0')
epoch: 66 test_true_pfm: 286.54956999452816 sim_pfm: -460.59452898792614
episode: 264 training return: tensor(-507.8529, device='cuda:0')
episode: 265 training return: tensor(-515.7581, device='cuda:0')
episode: 266 training return: tensor(-514.9924, device='cuda:0')
episode: 267 training return: tensor(-506.3393, device='cuda:0')
epoch: 67 test_true_pfm: 271.24313148297216 sim_pfm: -465.5366454976611
episode: 268 training return: tensor(-522.1630, device='cuda:0')
episode: 269 training return: tensor(-499.0889, device='cuda:0')
episode: 270 training return: tensor(-508.5180, device='cuda:0')
episode: 271 training return: tensor(-509.9656, device='cuda:0')
epoch: 68 test_true_pfm: 279.8091822737918 sim_pfm: -464.2024522551801
episode: 272 training return: tensor(-511.3745, device='cuda:0')
episode: 273 training return: tensor(-506.4969, device='cuda:0')
episode: 274 training return: tensor(-515.0976, device='cuda:0')
episode: 275 training return: tensor(-503.6661, device='cuda:0')
epoch: 69 test_true_pfm: 260.4496277698126 sim_pfm: -465.2100067739278
episode: 276 training return: tensor(-499.7202, device='cuda:0')
episode: 277 training return: tensor(-492.0784, device='cuda:0')
episode: 278 training return: tensor(-503.2096, device='cuda:0')
episode: 279 training return: tensor(-518.4063, device='cuda:0')
epoch: 70 test_true_pfm: 264.7550422846133 sim_pfm: -463.78540711052483
episode: 280 training return: tensor(-497.0370, device='cuda:0')
episode: 281 training return: tensor(-509.3497, device='cuda:0')
episode: 282 training return: tensor(-502.6384, device='cuda:0')
episode: 283 training return: tensor(-503.7492, device='cuda:0')
epoch: 71 test_true_pfm: 282.8598719416527 sim_pfm: -465.4658176874218
episode: 284 training return: tensor(-517.7188, device='cuda:0')
episode: 285 training return: tensor(-501.9835, device='cuda:0')
episode: 286 training return: tensor(-516.4958, device='cuda:0')
episode: 287 training return: tensor(-514.2425, device='cuda:0')
epoch: 72 test_true_pfm: 299.9095646059738 sim_pfm: -456.3671096630084
episode: 288 training return: tensor(-512.5020, device='cuda:0')
episode: 289 training return: tensor(-511.9190, device='cuda:0')
episode: 290 training return: tensor(-514.4507, device='cuda:0')
episode: 291 training return: tensor(-498.5624, device='cuda:0')
epoch: 73 test_true_pfm: 268.9701340764462 sim_pfm: -465.0639005508274
episode: 292 training return: tensor(-508.8076, device='cuda:0')
episode: 293 training return: tensor(-512.9590, device='cuda:0')
episode: 294 training return: tensor(-512.0573, device='cuda:0')
episode: 295 training return: tensor(-507.3691, device='cuda:0')
epoch: 74 test_true_pfm: 295.63292963441535 sim_pfm: -457.1522730626166
episode: 296 training return: tensor(-495.0405, device='cuda:0')
episode: 297 training return: tensor(-512.8959, device='cuda:0')
episode: 298 training return: tensor(-503.2124, device='cuda:0')
episode: 299 training return: tensor(-502.5184, device='cuda:0')
epoch: 75 test_true_pfm: 267.9679274214212 sim_pfm: -463.50056444170576
episode: 300 training return: tensor(-491.5179, device='cuda:0')
episode: 301 training return: tensor(-507.9642, device='cuda:0')
episode: 302 training return: tensor(-506.9051, device='cuda:0')
episode: 303 training return: tensor(-496.5316, device='cuda:0')
epoch: 76 test_true_pfm: 281.86667911123567 sim_pfm: -461.06707192103687
episode: 304 training return: tensor(-519.7479, device='cuda:0')
episode: 305 training return: tensor(-497.9736, device='cuda:0')
episode: 306 training return: tensor(-509.3305, device='cuda:0')
episode: 307 training return: tensor(-495.3788, device='cuda:0')
epoch: 77 test_true_pfm: 287.0692172563227 sim_pfm: -460.22363327490166
episode: 308 training return: tensor(-513.0081, device='cuda:0')
episode: 309 training return: tensor(-510.1770, device='cuda:0')
episode: 310 training return: tensor(-501.1679, device='cuda:0')
episode: 311 training return: tensor(-513.5079, device='cuda:0')
epoch: 78 test_true_pfm: 284.769836228246 sim_pfm: -459.77884782416123
episode: 312 training return: tensor(-515.5795, device='cuda:0')
episode: 313 training return: tensor(-511.9463, device='cuda:0')
episode: 314 training return: tensor(-501.6804, device='cuda:0')
episode: 315 training return: tensor(-505.5328, device='cuda:0')
epoch: 79 test_true_pfm: 281.00487629877347 sim_pfm: -455.6288773852478
episode: 316 training return: tensor(-503.0876, device='cuda:0')
episode: 317 training return: tensor(-513.6363, device='cuda:0')
episode: 318 training return: tensor(-510.0216, device='cuda:0')
episode: 319 training return: tensor(-506.1138, device='cuda:0')
epoch: 80 test_true_pfm: 269.37899323048185 sim_pfm: -472.0396451226746
episode: 320 training return: tensor(-510.9490, device='cuda:0')
episode: 321 training return: tensor(-510.1238, device='cuda:0')
episode: 322 training return: tensor(-496.7944, device='cuda:0')
episode: 323 training return: tensor(-503.5069, device='cuda:0')
epoch: 81 test_true_pfm: 268.80785995246333 sim_pfm: -462.18921219945577
episode: 324 training return: tensor(-505.3512, device='cuda:0')
episode: 325 training return: tensor(-508.9162, device='cuda:0')
episode: 326 training return: tensor(-505.9377, device='cuda:0')
episode: 327 training return: tensor(-510.7058, device='cuda:0')
epoch: 82 test_true_pfm: 274.1446277045905 sim_pfm: -460.1696320249078
episode: 328 training return: tensor(-513.8129, device='cuda:0')
episode: 329 training return: tensor(-508.7128, device='cuda:0')
episode: 330 training return: tensor(-517.3856, device='cuda:0')
episode: 331 training return: tensor(-517.8536, device='cuda:0')
epoch: 83 test_true_pfm: 267.5326299175028 sim_pfm: -470.7264541185771
episode: 332 training return: tensor(-509.1909, device='cuda:0')
episode: 333 training return: tensor(-496.2387, device='cuda:0')
episode: 334 training return: tensor(-505.8185, device='cuda:0')
episode: 335 training return: tensor(-496.3150, device='cuda:0')
epoch: 84 test_true_pfm: 254.22181621135462 sim_pfm: -468.09011929327
episode: 336 training return: tensor(-495.9254, device='cuda:0')
episode: 337 training return: tensor(-506.8358, device='cuda:0')
episode: 338 training return: tensor(-507.5940, device='cuda:0')
episode: 339 training return: tensor(-511.5243, device='cuda:0')
epoch: 85 test_true_pfm: 267.87627840005763 sim_pfm: -465.2584907291457
episode: 340 training return: tensor(-502.5916, device='cuda:0')
episode: 341 training return: tensor(-500.6587, device='cuda:0')
episode: 342 training return: tensor(-503.5023, device='cuda:0')
episode: 343 training return: tensor(-509.9066, device='cuda:0')
epoch: 86 test_true_pfm: 285.4980515376051 sim_pfm: -462.68955920574564
episode: 344 training return: tensor(-500.8169, device='cuda:0')
episode: 345 training return: tensor(-491.6570, device='cuda:0')
episode: 346 training return: tensor(-499.2393, device='cuda:0')
episode: 347 training return: tensor(-493.0216, device='cuda:0')
epoch: 87 test_true_pfm: 289.313628025541 sim_pfm: -458.39731449610554
episode: 348 training return: tensor(-506.9447, device='cuda:0')
episode: 349 training return: tensor(-497.6099, device='cuda:0')
episode: 350 training return: tensor(-502.8690, device='cuda:0')
episode: 351 training return: tensor(-516.3812, device='cuda:0')
epoch: 88 test_true_pfm: 276.3577109285183 sim_pfm: -460.19209375158727
episode: 352 training return: tensor(-506.2590, device='cuda:0')
episode: 353 training return: tensor(-499.2767, device='cuda:0')
episode: 354 training return: tensor(-505.7554, device='cuda:0')
episode: 355 training return: tensor(-518.3631, device='cuda:0')
epoch: 89 test_true_pfm: 279.9883112614346 sim_pfm: -460.11919589564786
episode: 356 training return: tensor(-516.3788, device='cuda:0')
episode: 357 training return: tensor(-513.8898, device='cuda:0')
episode: 358 training return: tensor(-514.5657, device='cuda:0')
episode: 359 training return: tensor(-497.1068, device='cuda:0')
epoch: 90 test_true_pfm: 266.6634051938053 sim_pfm: -464.00346750478883
episode: 360 training return: tensor(-501.9652, device='cuda:0')
episode: 361 training return: tensor(-498.5918, device='cuda:0')
episode: 362 training return: tensor(-498.4737, device='cuda:0')
episode: 363 training return: tensor(-512.5993, device='cuda:0')
epoch: 91 test_true_pfm: 282.35739024418007 sim_pfm: -461.25358833993477
episode: 364 training return: tensor(-499.6539, device='cuda:0')
episode: 365 training return: tensor(-518.3345, device='cuda:0')
episode: 366 training return: tensor(-512.2834, device='cuda:0')
episode: 367 training return: tensor(-506.5662, device='cuda:0')
epoch: 92 test_true_pfm: 285.5867396475471 sim_pfm: -459.9402136763868
episode: 368 training return: tensor(-497.7740, device='cuda:0')
episode: 369 training return: tensor(-501.1527, device='cuda:0')
episode: 370 training return: tensor(-511.8290, device='cuda:0')
episode: 371 training return: tensor(-510.9050, device='cuda:0')
epoch: 93 test_true_pfm: 260.5207503265878 sim_pfm: -470.1480263918638
episode: 372 training return: tensor(-499.9520, device='cuda:0')
episode: 373 training return: tensor(-500.6571, device='cuda:0')
episode: 374 training return: tensor(-504.2696, device='cuda:0')
episode: 375 training return: tensor(-501.7187, device='cuda:0')
epoch: 94 test_true_pfm: 283.9555333924086 sim_pfm: -460.9187385744105
episode: 376 training return: tensor(-504.6942, device='cuda:0')
episode: 377 training return: tensor(-503.4116, device='cuda:0')
episode: 378 training return: tensor(-491.0113, device='cuda:0')
episode: 379 training return: tensor(-508.0520, device='cuda:0')
epoch: 95 test_true_pfm: 288.8999770284342 sim_pfm: -458.4820354381033
episode: 380 training return: tensor(-512.2935, device='cuda:0')
episode: 381 training return: tensor(-493.8052, device='cuda:0')
episode: 382 training return: tensor(-510.4114, device='cuda:0')
episode: 383 training return: tensor(-506.8666, device='cuda:0')
epoch: 96 test_true_pfm: 285.59679873719705 sim_pfm: -456.67070385503274
episode: 384 training return: tensor(-505.5304, device='cuda:0')
episode: 385 training return: tensor(-509.0780, device='cuda:0')
episode: 386 training return: tensor(-510.3073, device='cuda:0')
episode: 387 training return: tensor(-498.0246, device='cuda:0')
epoch: 97 test_true_pfm: 290.5368928347954 sim_pfm: -451.6284661626366
episode: 388 training return: tensor(-504.3973, device='cuda:0')
episode: 389 training return: tensor(-512.3141, device='cuda:0')
episode: 390 training return: tensor(-508.6278, device='cuda:0')
episode: 391 training return: tensor(-505.2461, device='cuda:0')
epoch: 98 test_true_pfm: 280.2044372263284 sim_pfm: -457.64076768496307
episode: 392 training return: tensor(-494.5681, device='cuda:0')
episode: 393 training return: tensor(-500.8288, device='cuda:0')
episode: 394 training return: tensor(-510.9959, device='cuda:0')
episode: 395 training return: tensor(-494.2289, device='cuda:0')
epoch: 99 test_true_pfm: 278.48445466115635 sim_pfm: -458.65736437464756
episode: 396 training return: tensor(-494.8257, device='cuda:0')
episode: 397 training return: tensor(-501.8537, device='cuda:0')
episode: 398 training return: tensor(-502.4133, device='cuda:0')
episode: 399 training return: tensor(-505.6700, device='cuda:0')
epoch: 100 test_true_pfm: 274.15080698549485 sim_pfm: -465.3673036484979
episode: 400 training return: tensor(-523.8806, device='cuda:0')
episode: 401 training return: tensor(-515.3448, device='cuda:0')
episode: 402 training return: tensor(-504.3780, device='cuda:0')
episode: 403 training return: tensor(-495.2271, device='cuda:0')
epoch: 101 test_true_pfm: 281.8226720842035 sim_pfm: -453.6735513236684
episode: 404 training return: tensor(-495.5855, device='cuda:0')
episode: 405 training return: tensor(-502.4166, device='cuda:0')
episode: 406 training return: tensor(-501.2575, device='cuda:0')
episode: 407 training return: tensor(-493.3702, device='cuda:0')
epoch: 102 test_true_pfm: 282.8206510432882 sim_pfm: -462.9499750851343
episode: 408 training return: tensor(-501.1809, device='cuda:0')
episode: 409 training return: tensor(-512.9439, device='cuda:0')
episode: 410 training return: tensor(-504.3126, device='cuda:0')
episode: 411 training return: tensor(-501.7702, device='cuda:0')
epoch: 103 test_true_pfm: 296.18231696847664 sim_pfm: -457.6924328953028
episode: 412 training return: tensor(-508.9670, device='cuda:0')
episode: 413 training return: tensor(-522.8444, device='cuda:0')
episode: 414 training return: tensor(-498.2420, device='cuda:0')
episode: 415 training return: tensor(-505.0586, device='cuda:0')
epoch: 104 test_true_pfm: 273.9302221832066 sim_pfm: -460.2025877023116
episode: 416 training return: tensor(-504.8919, device='cuda:0')
episode: 417 training return: tensor(-512.1434, device='cuda:0')
episode: 418 training return: tensor(-519.2489, device='cuda:0')
episode: 419 training return: tensor(-495.9615, device='cuda:0')
epoch: 105 test_true_pfm: 297.19751439100725 sim_pfm: -451.72312007751316
episode: 420 training return: tensor(-508.7596, device='cuda:0')
episode: 421 training return: tensor(-501.3351, device='cuda:0')
episode: 422 training return: tensor(-495.4384, device='cuda:0')
episode: 423 training return: tensor(-499.8741, device='cuda:0')
epoch: 106 test_true_pfm: 281.9515279888963 sim_pfm: -459.52506104608375
episode: 424 training return: tensor(-493.8823, device='cuda:0')
episode: 425 training return: tensor(-511.2479, device='cuda:0')
episode: 426 training return: tensor(-501.6599, device='cuda:0')
episode: 427 training return: tensor(-505.3346, device='cuda:0')
epoch: 107 test_true_pfm: 286.29827226117897 sim_pfm: -460.99864380744594
episode: 428 training return: tensor(-497.9482, device='cuda:0')
episode: 429 training return: tensor(-507.7785, device='cuda:0')
episode: 430 training return: tensor(-511.4579, device='cuda:0')
episode: 431 training return: tensor(-517.5490, device='cuda:0')
epoch: 108 test_true_pfm: 279.7995669697644 sim_pfm: -461.44939896902844
episode: 432 training return: tensor(-503.1979, device='cuda:0')
episode: 433 training return: tensor(-512.5146, device='cuda:0')
episode: 434 training return: tensor(-509.7287, device='cuda:0')
episode: 435 training return: tensor(-512.4008, device='cuda:0')
epoch: 109 test_true_pfm: 249.37534929014404 sim_pfm: -470.81411172201234
episode: 436 training return: tensor(-501.1956, device='cuda:0')
episode: 437 training return: tensor(-507.7641, device='cuda:0')
episode: 438 training return: tensor(-503.5513, device='cuda:0')
episode: 439 training return: tensor(-503.9781, device='cuda:0')
epoch: 110 test_true_pfm: 283.8446341481151 sim_pfm: -465.25063540584716
episode: 440 training return: tensor(-504.1937, device='cuda:0')
episode: 441 training return: tensor(-513.4492, device='cuda:0')
episode: 442 training return: tensor(-507.2518, device='cuda:0')
episode: 443 training return: tensor(-496.8199, device='cuda:0')
epoch: 111 test_true_pfm: 279.5732477338964 sim_pfm: -466.9320592522466
episode: 444 training return: tensor(-495.5125, device='cuda:0')
episode: 445 training return: tensor(-509.7755, device='cuda:0')
episode: 446 training return: tensor(-501.6911, device='cuda:0')
episode: 447 training return: tensor(-513.6688, device='cuda:0')
epoch: 112 test_true_pfm: 267.31355231046433 sim_pfm: -470.19509517075494
episode: 448 training return: tensor(-493.2732, device='cuda:0')
episode: 449 training return: tensor(-509.3930, device='cuda:0')
episode: 450 training return: tensor(-498.9255, device='cuda:0')
episode: 451 training return: tensor(-498.5495, device='cuda:0')
epoch: 113 test_true_pfm: 278.9866783835741 sim_pfm: -456.98795199021697
episode: 452 training return: tensor(-502.4839, device='cuda:0')
episode: 453 training return: tensor(-515.9023, device='cuda:0')
episode: 454 training return: tensor(-503.3486, device='cuda:0')
episode: 455 training return: tensor(-508.4521, device='cuda:0')
epoch: 114 test_true_pfm: 276.35946432024843 sim_pfm: -461.8027947616453
episode: 456 training return: tensor(-504.1212, device='cuda:0')
episode: 457 training return: tensor(-507.6584, device='cuda:0')
episode: 458 training return: tensor(-501.7290, device='cuda:0')
episode: 459 training return: tensor(-503.8546, device='cuda:0')
epoch: 115 test_true_pfm: 278.66926658458783 sim_pfm: -460.54090853252757
episode: 460 training return: tensor(-507.0190, device='cuda:0')
episode: 461 training return: tensor(-494.9939, device='cuda:0')
episode: 462 training return: tensor(-500.8603, device='cuda:0')
episode: 463 training return: tensor(-511.3637, device='cuda:0')
epoch: 116 test_true_pfm: 266.28123531993657 sim_pfm: -465.81888987496495
episode: 464 training return: tensor(-504.0531, device='cuda:0')
episode: 465 training return: tensor(-509.2595, device='cuda:0')
episode: 466 training return: tensor(-498.6542, device='cuda:0')
episode: 467 training return: tensor(-498.8755, device='cuda:0')
epoch: 117 test_true_pfm: 297.09332792868423 sim_pfm: -452.0611422938916
episode: 468 training return: tensor(-506.0115, device='cuda:0')
episode: 469 training return: tensor(-511.6204, device='cuda:0')
episode: 470 training return: tensor(-499.0519, device='cuda:0')
episode: 471 training return: tensor(-502.8881, device='cuda:0')
epoch: 118 test_true_pfm: 270.93055599766626 sim_pfm: -460.31557410194847
episode: 472 training return: tensor(-501.4674, device='cuda:0')
episode: 473 training return: tensor(-494.5676, device='cuda:0')
episode: 474 training return: tensor(-498.1139, device='cuda:0')
episode: 475 training return: tensor(-503.2028, device='cuda:0')
epoch: 119 test_true_pfm: 274.6900454367532 sim_pfm: -460.07471615619335
episode: 476 training return: tensor(-504.7012, device='cuda:0')
episode: 477 training return: tensor(-504.2437, device='cuda:0')
episode: 478 training return: tensor(-510.6881, device='cuda:0')
episode: 479 training return: tensor(-511.3547, device='cuda:0')
epoch: 120 test_true_pfm: 277.07924105444636 sim_pfm: -461.49159830560285
episode: 480 training return: tensor(-506.3168, device='cuda:0')
episode: 481 training return: tensor(-502.7492, device='cuda:0')
episode: 482 training return: tensor(-510.5114, device='cuda:0')
episode: 483 training return: tensor(-495.0860, device='cuda:0')
epoch: 121 test_true_pfm: 269.69078247541603 sim_pfm: -465.3938003212679
episode: 484 training return: tensor(-503.6260, device='cuda:0')
episode: 485 training return: tensor(-501.4568, device='cuda:0')
episode: 486 training return: tensor(-504.4805, device='cuda:0')
episode: 487 training return: tensor(-507.1164, device='cuda:0')
epoch: 122 test_true_pfm: 276.6311146213061 sim_pfm: -457.94353403523564
episode: 488 training return: tensor(-502.0645, device='cuda:0')
episode: 489 training return: tensor(-503.6625, device='cuda:0')
episode: 490 training return: tensor(-495.1411, device='cuda:0')
episode: 491 training return: tensor(-500.3383, device='cuda:0')
epoch: 123 test_true_pfm: 285.1053309894629 sim_pfm: -459.5943553938996
episode: 492 training return: tensor(-495.3463, device='cuda:0')
episode: 493 training return: tensor(-501.6608, device='cuda:0')
episode: 494 training return: tensor(-506.4992, device='cuda:0')
episode: 495 training return: tensor(-500.2145, device='cuda:0')
epoch: 124 test_true_pfm: 285.51482250841235 sim_pfm: -460.6541597886632
episode: 496 training return: tensor(-512.8541, device='cuda:0')
episode: 497 training return: tensor(-496.3102, device='cuda:0')
episode: 498 training return: tensor(-507.6575, device='cuda:0')
episode: 499 training return: tensor(-501.5986, device='cuda:0')
epoch: 125 test_true_pfm: 282.4700146335859 sim_pfm: -457.4611090486869
episode: 500 training return: tensor(-498.1169, device='cuda:0')
episode: 501 training return: tensor(-512.7043, device='cuda:0')
episode: 502 training return: tensor(-502.2336, device='cuda:0')
episode: 503 training return: tensor(-507.0222, device='cuda:0')
epoch: 126 test_true_pfm: 276.8037999949569 sim_pfm: -468.39522477736074
episode: 504 training return: tensor(-498.7611, device='cuda:0')
episode: 505 training return: tensor(-507.8907, device='cuda:0')
episode: 506 training return: tensor(-498.2530, device='cuda:0')
episode: 507 training return: tensor(-508.3191, device='cuda:0')
epoch: 127 test_true_pfm: 281.90571761177597 sim_pfm: -460.4154328927398
episode: 508 training return: tensor(-503.6668, device='cuda:0')
episode: 509 training return: tensor(-503.5654, device='cuda:0')
episode: 510 training return: tensor(-501.6121, device='cuda:0')
episode: 511 training return: tensor(-510.1436, device='cuda:0')
epoch: 128 test_true_pfm: 282.90649207858894 sim_pfm: -459.95849379136536
episode: 512 training return: tensor(-506.6139, device='cuda:0')
episode: 513 training return: tensor(-505.4432, device='cuda:0')
episode: 514 training return: tensor(-501.4207, device='cuda:0')
episode: 515 training return: tensor(-497.1024, device='cuda:0')
epoch: 129 test_true_pfm: 292.06968720492154 sim_pfm: -457.5369758674254
episode: 516 training return: tensor(-496.7851, device='cuda:0')
episode: 517 training return: tensor(-498.1440, device='cuda:0')
episode: 518 training return: tensor(-504.7741, device='cuda:0')
episode: 519 training return: tensor(-499.6091, device='cuda:0')
epoch: 130 test_true_pfm: 275.6140003424492 sim_pfm: -459.66848815605044
episode: 520 training return: tensor(-500.1058, device='cuda:0')
episode: 521 training return: tensor(-501.2725, device='cuda:0')
episode: 522 training return: tensor(-495.7782, device='cuda:0')
episode: 523 training return: tensor(-492.9608, device='cuda:0')
epoch: 131 test_true_pfm: 285.9580959037762 sim_pfm: -457.5229259369274
episode: 524 training return: tensor(-505.5578, device='cuda:0')
episode: 525 training return: tensor(-502.9843, device='cuda:0')
episode: 526 training return: tensor(-503.1573, device='cuda:0')
episode: 527 training return: tensor(-504.5642, device='cuda:0')
epoch: 132 test_true_pfm: 273.7205532943797 sim_pfm: -463.51331780447316
episode: 528 training return: tensor(-494.9241, device='cuda:0')
episode: 529 training return: tensor(-506.6412, device='cuda:0')
episode: 530 training return: tensor(-510.1939, device='cuda:0')
episode: 531 training return: tensor(-499.1855, device='cuda:0')
epoch: 133 test_true_pfm: 281.9190877586381 sim_pfm: -460.8638045328359
episode: 532 training return: tensor(-496.1864, device='cuda:0')
episode: 533 training return: tensor(-507.4156, device='cuda:0')
episode: 534 training return: tensor(-511.3551, device='cuda:0')
episode: 535 training return: tensor(-513.6157, device='cuda:0')
epoch: 134 test_true_pfm: 282.7602612462838 sim_pfm: -459.18072945748764
episode: 536 training return: tensor(-495.5706, device='cuda:0')
episode: 537 training return: tensor(-504.5665, device='cuda:0')
episode: 538 training return: tensor(-507.1025, device='cuda:0')
episode: 539 training return: tensor(-511.6674, device='cuda:0')
epoch: 135 test_true_pfm: 274.585550038423 sim_pfm: -456.7189721514781
episode: 540 training return: tensor(-500.5404, device='cuda:0')
episode: 541 training return: tensor(-500.1453, device='cuda:0')
episode: 542 training return: tensor(-502.1513, device='cuda:0')
episode: 543 training return: tensor(-499.5068, device='cuda:0')
epoch: 136 test_true_pfm: 283.5102686473552 sim_pfm: -457.79482736593735
episode: 544 training return: tensor(-487.8393, device='cuda:0')
episode: 545 training return: tensor(-501.1364, device='cuda:0')
episode: 546 training return: tensor(-493.8667, device='cuda:0')
episode: 547 training return: tensor(-491.8888, device='cuda:0')
epoch: 137 test_true_pfm: 264.9295102654505 sim_pfm: -464.3801389038563
episode: 548 training return: tensor(-488.2939, device='cuda:0')
episode: 549 training return: tensor(-491.2600, device='cuda:0')
episode: 550 training return: tensor(-506.7975, device='cuda:0')
episode: 551 training return: tensor(-505.3136, device='cuda:0')
epoch: 138 test_true_pfm: 288.5884388664577 sim_pfm: -454.02193789661396
episode: 552 training return: tensor(-499.9909, device='cuda:0')
episode: 553 training return: tensor(-516.7847, device='cuda:0')
episode: 554 training return: tensor(-497.1214, device='cuda:0')
episode: 555 training return: tensor(-499.3354, device='cuda:0')
epoch: 139 test_true_pfm: 302.3563214508504 sim_pfm: -458.41582515261445
episode: 556 training return: tensor(-495.8270, device='cuda:0')
episode: 557 training return: tensor(-501.6864, device='cuda:0')
episode: 558 training return: tensor(-494.1632, device='cuda:0')
episode: 559 training return: tensor(-489.0431, device='cuda:0')
epoch: 140 test_true_pfm: 292.9076141397383 sim_pfm: -452.34428111836314
episode: 560 training return: tensor(-499.0071, device='cuda:0')
episode: 561 training return: tensor(-488.3338, device='cuda:0')
episode: 562 training return: tensor(-494.3871, device='cuda:0')
episode: 563 training return: tensor(-493.4627, device='cuda:0')
epoch: 141 test_true_pfm: 270.0516247307107 sim_pfm: -463.6474665622227
episode: 564 training return: tensor(-490.3911, device='cuda:0')
episode: 565 training return: tensor(-504.0701, device='cuda:0')
episode: 566 training return: tensor(-501.5588, device='cuda:0')
episode: 567 training return: tensor(-496.3181, device='cuda:0')
epoch: 142 test_true_pfm: 292.68683349504335 sim_pfm: -457.2779089709123
episode: 568 training return: tensor(-503.0147, device='cuda:0')
episode: 569 training return: tensor(-495.0768, device='cuda:0')
episode: 570 training return: tensor(-509.6688, device='cuda:0')
episode: 571 training return: tensor(-507.6666, device='cuda:0')
epoch: 143 test_true_pfm: 292.49778058805623 sim_pfm: -451.9183537904173
episode: 572 training return: tensor(-498.3357, device='cuda:0')
episode: 573 training return: tensor(-501.1906, device='cuda:0')
episode: 574 training return: tensor(-498.1659, device='cuda:0')
episode: 575 training return: tensor(-490.3569, device='cuda:0')
epoch: 144 test_true_pfm: 283.760356983247 sim_pfm: -457.5327677267681
episode: 576 training return: tensor(-506.7750, device='cuda:0')
episode: 577 training return: tensor(-498.5273, device='cuda:0')
episode: 578 training return: tensor(-502.8096, device='cuda:0')
episode: 579 training return: tensor(-515.5892, device='cuda:0')
epoch: 145 test_true_pfm: 289.6127192217068 sim_pfm: -451.47948316298425
episode: 580 training return: tensor(-505.1685, device='cuda:0')
episode: 581 training return: tensor(-496.1471, device='cuda:0')
episode: 582 training return: tensor(-507.3454, device='cuda:0')
episode: 583 training return: tensor(-509.2254, device='cuda:0')
epoch: 146 test_true_pfm: 292.2078272569934 sim_pfm: -451.2240224312991
episode: 584 training return: tensor(-491.2354, device='cuda:0')
episode: 585 training return: tensor(-501.7290, device='cuda:0')
episode: 586 training return: tensor(-517.0677, device='cuda:0')
episode: 587 training return: tensor(-495.4511, device='cuda:0')
epoch: 147 test_true_pfm: 277.9590254012422 sim_pfm: -459.2145829061046
episode: 588 training return: tensor(-503.5613, device='cuda:0')
episode: 589 training return: tensor(-505.3095, device='cuda:0')
episode: 590 training return: tensor(-513.4446, device='cuda:0')
episode: 591 training return: tensor(-504.3719, device='cuda:0')
epoch: 148 test_true_pfm: 280.62326912986674 sim_pfm: -458.94842039688956
episode: 592 training return: tensor(-495.0691, device='cuda:0')
episode: 593 training return: tensor(-503.8825, device='cuda:0')
episode: 594 training return: tensor(-490.7593, device='cuda:0')
episode: 595 training return: tensor(-502.6833, device='cuda:0')
epoch: 149 test_true_pfm: 286.4439223754325 sim_pfm: -454.95917816491175
episode: 596 training return: tensor(-503.0007, device='cuda:0')
episode: 597 training return: tensor(-501.2994, device='cuda:0')
episode: 598 training return: tensor(-501.1310, device='cuda:0')
episode: 599 training return: tensor(-514.6525, device='cuda:0')
epoch: 150 test_true_pfm: 285.62835105114283 sim_pfm: -465.5006933904563
