['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'baseline', '--traj', 'expert', '--seed', '2']
episode: 0 training return: tensor(-18.2300, device='cuda:0')
episode: 1 training return: tensor(96.7260, device='cuda:0')
episode: 2 training return: tensor(176.8568, device='cuda:0')
episode: 3 training return: tensor(-36.8433, device='cuda:0')
epoch: 1 test_true_pfm: 8.113125725379552 sim_pfm: 87.64183129140875
episode: 4 training return: tensor(134.0364, device='cuda:0')
episode: 5 training return: tensor(169.0556, device='cuda:0')
episode: 6 training return: tensor(68.3229, device='cuda:0')
episode: 7 training return: tensor(-96.6358, device='cuda:0')
epoch: 2 test_true_pfm: 22.61143942500305 sim_pfm: -718.876486299769
episode: 8 training return: tensor(115.1862, device='cuda:0')
episode: 9 training return: tensor(212.5543, device='cuda:0')
episode: 10 training return: tensor(-409.3650, device='cuda:0')
episode: 11 training return: tensor(-35.6200, device='cuda:0')
epoch: 3 test_true_pfm: 14.174255822002502 sim_pfm: 194.57374767176807
episode: 12 training return: tensor(193.1770, device='cuda:0')
episode: 13 training return: tensor(100.1254, device='cuda:0')
episode: 14 training return: tensor(891.5880, device='cuda:0')
episode: 15 training return: tensor(889.1831, device='cuda:0')
epoch: 4 test_true_pfm: -6.03645266765846 sim_pfm: 767.58570304811
episode: 16 training return: tensor(660.5422, device='cuda:0')
episode: 17 training return: tensor(596.1252, device='cuda:0')
episode: 18 training return: tensor(721.3592, device='cuda:0')
episode: 19 training return: tensor(95.3600, device='cuda:0')
epoch: 5 test_true_pfm: 29.031410581076756 sim_pfm: -386.35288717848016
episode: 20 training return: tensor(-183.8881, device='cuda:0')
episode: 21 training return: tensor(4.1258, device='cuda:0')
episode: 22 training return: tensor(436.7295, device='cuda:0')
episode: 23 training return: tensor(647.2111, device='cuda:0')
epoch: 6 test_true_pfm: 5.973139754270199 sim_pfm: 833.6511071518064
episode: 24 training return: tensor(844.0580, device='cuda:0')
episode: 25 training return: tensor(130.2554, device='cuda:0')
episode: 26 training return: tensor(763.7688, device='cuda:0')
episode: 27 training return: tensor(780.4519, device='cuda:0')
epoch: 7 test_true_pfm: 1.272593569781185 sim_pfm: 962.2245299950242
episode: 28 training return: tensor(882.6254, device='cuda:0')
episode: 29 training return: tensor(961.2798, device='cuda:0')
episode: 30 training return: tensor(967.0677, device='cuda:0')
episode: 31 training return: tensor(967.8499, device='cuda:0')
epoch: 8 test_true_pfm: -11.719512891089156 sim_pfm: 963.2751031316817
episode: 32 training return: tensor(970.5549, device='cuda:0')
episode: 33 training return: tensor(961.1533, device='cuda:0')
episode: 34 training return: tensor(963.6066, device='cuda:0')
episode: 35 training return: tensor(953.0806, device='cuda:0')
epoch: 9 test_true_pfm: -19.57013478332423 sim_pfm: 933.5903310470283
episode: 36 training return: tensor(945.1809, device='cuda:0')
episode: 37 training return: tensor(983.9083, device='cuda:0')
episode: 38 training return: tensor(982.2062, device='cuda:0')
episode: 39 training return: tensor(968.4179, device='cuda:0')
epoch: 10 test_true_pfm: -15.69883602910345 sim_pfm: 973.8754245575517
episode: 40 training return: tensor(986.2997, device='cuda:0')
episode: 41 training return: tensor(956.6338, device='cuda:0')
episode: 42 training return: tensor(988.6085, device='cuda:0')
episode: 43 training return: tensor(963.9265, device='cuda:0')
epoch: 11 test_true_pfm: -9.461169172873936 sim_pfm: 986.4089030206203
episode: 44 training return: tensor(981.9602, device='cuda:0')
episode: 45 training return: tensor(978.7287, device='cuda:0')
episode: 46 training return: tensor(981.5684, device='cuda:0')
episode: 47 training return: tensor(975.5713, device='cuda:0')
epoch: 12 test_true_pfm: -18.100293538627785 sim_pfm: 978.914942239225
episode: 48 training return: tensor(976.6946, device='cuda:0')
episode: 49 training return: tensor(979.1497, device='cuda:0')
episode: 50 training return: tensor(973.9919, device='cuda:0')
episode: 51 training return: tensor(945.2192, device='cuda:0')
epoch: 13 test_true_pfm: -6.489073800701209 sim_pfm: 959.9465201281128
episode: 52 training return: tensor(976.6964, device='cuda:0')
episode: 53 training return: tensor(974.2194, device='cuda:0')
episode: 54 training return: tensor(976.0609, device='cuda:0')
episode: 55 training return: tensor(974.9199, device='cuda:0')
epoch: 14 test_true_pfm: -14.215428324323375 sim_pfm: 972.0599052846432
episode: 56 training return: tensor(964.0070, device='cuda:0')
episode: 57 training return: tensor(982.3306, device='cuda:0')
episode: 58 training return: tensor(987.7344, device='cuda:0')
episode: 59 training return: tensor(985.6889, device='cuda:0')
epoch: 15 test_true_pfm: -18.5106752527796 sim_pfm: 984.136795425415
episode: 60 training return: tensor(983.4488, device='cuda:0')
episode: 61 training return: tensor(983.0253, device='cuda:0')
episode: 62 training return: tensor(980.4041, device='cuda:0')
episode: 63 training return: tensor(979.7883, device='cuda:0')
epoch: 16 test_true_pfm: -6.718948405386572 sim_pfm: 985.1796735584736
episode: 64 training return: tensor(971.5099, device='cuda:0')
episode: 65 training return: tensor(976.2410, device='cuda:0')
episode: 66 training return: tensor(972.1725, device='cuda:0')
episode: 67 training return: tensor(974.5325, device='cuda:0')
epoch: 17 test_true_pfm: -10.37971682833109 sim_pfm: 985.1134196193423
episode: 68 training return: tensor(979.5784, device='cuda:0')
episode: 69 training return: tensor(974.4368, device='cuda:0')
episode: 70 training return: tensor(962.3318, device='cuda:0')
episode: 71 training return: tensor(969.5734, device='cuda:0')
epoch: 18 test_true_pfm: -13.807481037344285 sim_pfm: 982.1136196985841
episode: 72 training return: tensor(962.5670, device='cuda:0')
episode: 73 training return: tensor(979.2617, device='cuda:0')
episode: 74 training return: tensor(987.5888, device='cuda:0')
episode: 75 training return: tensor(978.6313, device='cuda:0')
epoch: 19 test_true_pfm: -7.260710777437495 sim_pfm: 987.8311623603106
episode: 76 training return: tensor(986.9292, device='cuda:0')
episode: 77 training return: tensor(992.9076, device='cuda:0')
episode: 78 training return: tensor(991.6357, device='cuda:0')
episode: 79 training return: tensor(982.1283, device='cuda:0')
epoch: 20 test_true_pfm: -9.469501846343555 sim_pfm: 987.7029421538115
episode: 80 training return: tensor(989.5718, device='cuda:0')
episode: 81 training return: tensor(984.9957, device='cuda:0')
episode: 82 training return: tensor(988.0062, device='cuda:0')
episode: 83 training return: tensor(993.0505, device='cuda:0')
epoch: 21 test_true_pfm: -7.134075287057601 sim_pfm: 983.6440321689472
episode: 84 training return: tensor(985.3575, device='cuda:0')
episode: 85 training return: tensor(989.6726, device='cuda:0')
episode: 86 training return: tensor(991.8727, device='cuda:0')
episode: 87 training return: tensor(992.7380, device='cuda:0')
epoch: 22 test_true_pfm: -10.732960970149284 sim_pfm: 993.3953397065401
episode: 88 training return: tensor(993.0567, device='cuda:0')
episode: 89 training return: tensor(988.6616, device='cuda:0')
episode: 90 training return: tensor(990.2182, device='cuda:0')
episode: 91 training return: tensor(992.6573, device='cuda:0')
epoch: 23 test_true_pfm: -8.420316188648613 sim_pfm: 991.8197178870439
episode: 92 training return: tensor(990.3083, device='cuda:0')
episode: 93 training return: tensor(969.0088, device='cuda:0')
episode: 94 training return: tensor(953.7234, device='cuda:0')
episode: 95 training return: tensor(966.4678, device='cuda:0')
epoch: 24 test_true_pfm: -0.04554933539697022 sim_pfm: 981.4579842016101
episode: 96 training return: tensor(977.9035, device='cuda:0')
episode: 97 training return: tensor(954.5207, device='cuda:0')
episode: 98 training return: tensor(986.1622, device='cuda:0')
episode: 99 training return: tensor(983.8148, device='cuda:0')
epoch: 25 test_true_pfm: -2.7511665398821705 sim_pfm: 984.8659632444381
episode: 100 training return: tensor(977.2333, device='cuda:0')
episode: 101 training return: tensor(986.2820, device='cuda:0')
episode: 102 training return: tensor(988.5602, device='cuda:0')
episode: 103 training return: tensor(982.6008, device='cuda:0')
epoch: 26 test_true_pfm: -14.378317657635495 sim_pfm: 992.6258411735296
episode: 104 training return: tensor(989.3397, device='cuda:0')
episode: 105 training return: tensor(989.3360, device='cuda:0')
episode: 106 training return: tensor(979.0895, device='cuda:0')
episode: 107 training return: tensor(987.1342, device='cuda:0')
epoch: 27 test_true_pfm: -11.737335284899428 sim_pfm: 989.0176052063704
episode: 108 training return: tensor(988.7435, device='cuda:0')
episode: 109 training return: tensor(978.2910, device='cuda:0')
episode: 110 training return: tensor(976.1230, device='cuda:0')
episode: 111 training return: tensor(967.6818, device='cuda:0')
epoch: 28 test_true_pfm: -9.355569728601637 sim_pfm: 980.3942067623138
episode: 112 training return: tensor(979.5252, device='cuda:0')
episode: 113 training return: tensor(980.6649, device='cuda:0')
episode: 114 training return: tensor(979.9349, device='cuda:0')
episode: 115 training return: tensor(968.7984, device='cuda:0')
epoch: 29 test_true_pfm: -1.5077586061837662 sim_pfm: 977.1607425287366
episode: 116 training return: tensor(969.4660, device='cuda:0')
episode: 117 training return: tensor(973.3807, device='cuda:0')
episode: 118 training return: tensor(967.2665, device='cuda:0')
episode: 119 training return: tensor(966.1456, device='cuda:0')
epoch: 30 test_true_pfm: -5.592942946002687 sim_pfm: 969.552213037014
episode: 120 training return: tensor(965.0577, device='cuda:0')
episode: 121 training return: tensor(961.4547, device='cuda:0')
episode: 122 training return: tensor(955.8720, device='cuda:0')
episode: 123 training return: tensor(962.2679, device='cuda:0')
epoch: 31 test_true_pfm: 1.7357687901699126 sim_pfm: 980.5751733854413
episode: 124 training return: tensor(973.3759, device='cuda:0')
episode: 125 training return: tensor(971.3831, device='cuda:0')
episode: 126 training return: tensor(967.1334, device='cuda:0')
episode: 127 training return: tensor(965.7222, device='cuda:0')
epoch: 32 test_true_pfm: -13.32370625104787 sim_pfm: 977.5843302967027
episode: 128 training return: tensor(989.5215, device='cuda:0')
episode: 129 training return: tensor(983.2022, device='cuda:0')
episode: 130 training return: tensor(961.3345, device='cuda:0')
episode: 131 training return: tensor(981.2802, device='cuda:0')
epoch: 33 test_true_pfm: -5.2046795580853455 sim_pfm: 972.7662535876036
episode: 132 training return: tensor(964.0008, device='cuda:0')
episode: 133 training return: tensor(976.9393, device='cuda:0')
episode: 134 training return: tensor(989.4066, device='cuda:0')
episode: 135 training return: tensor(985.4349, device='cuda:0')
epoch: 34 test_true_pfm: -11.977015404606416 sim_pfm: 987.3782123178244
episode: 136 training return: tensor(988.0245, device='cuda:0')
episode: 137 training return: tensor(990.9943, device='cuda:0')
episode: 138 training return: tensor(987.2151, device='cuda:0')
episode: 139 training return: tensor(984.1100, device='cuda:0')
epoch: 35 test_true_pfm: -15.77770493929861 sim_pfm: 988.1192261308431
episode: 140 training return: tensor(988.9132, device='cuda:0')
episode: 141 training return: tensor(984.2505, device='cuda:0')
episode: 142 training return: tensor(982.7824, device='cuda:0')
episode: 143 training return: tensor(989.9926, device='cuda:0')
epoch: 36 test_true_pfm: -17.193857519209224 sim_pfm: 976.2835036549717
episode: 144 training return: tensor(973.5459, device='cuda:0')
episode: 145 training return: tensor(989.6246, device='cuda:0')
episode: 146 training return: tensor(992.3161, device='cuda:0')
episode: 147 training return: tensor(990.9055, device='cuda:0')
epoch: 37 test_true_pfm: -10.2370663143932 sim_pfm: 987.7360490456224
episode: 148 training return: tensor(990.4648, device='cuda:0')
episode: 149 training return: tensor(981.4070, device='cuda:0')
episode: 150 training return: tensor(989.6711, device='cuda:0')
episode: 151 training return: tensor(985.9966, device='cuda:0')
epoch: 38 test_true_pfm: -11.832955274574608 sim_pfm: 986.8460054725408
episode: 152 training return: tensor(989.3219, device='cuda:0')
episode: 153 training return: tensor(987.8722, device='cuda:0')
episode: 154 training return: tensor(990.8698, device='cuda:0')
episode: 155 training return: tensor(986.7972, device='cuda:0')
epoch: 39 test_true_pfm: -12.107947863562837 sim_pfm: 983.480883602798
episode: 156 training return: tensor(989.6750, device='cuda:0')
episode: 157 training return: tensor(988.9730, device='cuda:0')
episode: 158 training return: tensor(991.0700, device='cuda:0')
episode: 159 training return: tensor(989.9832, device='cuda:0')
epoch: 40 test_true_pfm: -15.708970428219317 sim_pfm: 987.0781876400113
episode: 160 training return: tensor(981.2090, device='cuda:0')
episode: 161 training return: tensor(981.9998, device='cuda:0')
episode: 162 training return: tensor(981.2665, device='cuda:0')
episode: 163 training return: tensor(992.6490, device='cuda:0')
epoch: 41 test_true_pfm: -12.38890423326743 sim_pfm: 986.531115758419
episode: 164 training return: tensor(988.8115, device='cuda:0')
episode: 165 training return: tensor(993.7037, device='cuda:0')
episode: 166 training return: tensor(992.0804, device='cuda:0')
episode: 167 training return: tensor(973.8002, device='cuda:0')
epoch: 42 test_true_pfm: -9.440035412394474 sim_pfm: 981.0490706175566
episode: 168 training return: tensor(989.2003, device='cuda:0')
episode: 169 training return: tensor(990.3483, device='cuda:0')
episode: 170 training return: tensor(992.0925, device='cuda:0')
episode: 171 training return: tensor(992.0290, device='cuda:0')
epoch: 43 test_true_pfm: -13.70717502487222 sim_pfm: 990.1512754261494
episode: 172 training return: tensor(991.5178, device='cuda:0')
episode: 173 training return: tensor(990.4680, device='cuda:0')
episode: 174 training return: tensor(990.6002, device='cuda:0')
episode: 175 training return: tensor(990.1548, device='cuda:0')
epoch: 44 test_true_pfm: -10.824739532023123 sim_pfm: 990.9993624128401
episode: 176 training return: tensor(990.0914, device='cuda:0')
episode: 177 training return: tensor(993.4126, device='cuda:0')
episode: 178 training return: tensor(991.0324, device='cuda:0')
episode: 179 training return: tensor(992.8952, device='cuda:0')
epoch: 45 test_true_pfm: -7.281624620157515 sim_pfm: 993.367086276412
episode: 180 training return: tensor(991.9256, device='cuda:0')
episode: 181 training return: tensor(991.3488, device='cuda:0')
episode: 182 training return: tensor(978.5841, device='cuda:0')
episode: 183 training return: tensor(980.9370, device='cuda:0')
epoch: 46 test_true_pfm: -7.476404414343475 sim_pfm: 993.0048760473728
episode: 184 training return: tensor(989.2988, device='cuda:0')
episode: 185 training return: tensor(990.6549, device='cuda:0')
episode: 186 training return: tensor(973.4496, device='cuda:0')
episode: 187 training return: tensor(956.7764, device='cuda:0')
epoch: 47 test_true_pfm: -6.559005345837645 sim_pfm: 978.8505331616849
episode: 188 training return: tensor(973.2608, device='cuda:0')
episode: 189 training return: tensor(988.1843, device='cuda:0')
episode: 190 training return: tensor(980.0961, device='cuda:0')
episode: 191 training return: tensor(976.5759, device='cuda:0')
epoch: 48 test_true_pfm: -10.189940351118574 sim_pfm: 990.586472183466
episode: 192 training return: tensor(948.2518, device='cuda:0')
episode: 193 training return: tensor(983.8013, device='cuda:0')
episode: 194 training return: tensor(989.9247, device='cuda:0')
episode: 195 training return: tensor(989.8584, device='cuda:0')
epoch: 49 test_true_pfm: -6.821644322312949 sim_pfm: 989.7336123257876
episode: 196 training return: tensor(985.3597, device='cuda:0')
episode: 197 training return: tensor(987.4704, device='cuda:0')
episode: 198 training return: tensor(981.9196, device='cuda:0')
episode: 199 training return: tensor(983.3537, device='cuda:0')
epoch: 50 test_true_pfm: -7.832873105051107 sim_pfm: 987.0863150119782
episode: 200 training return: tensor(986.8307, device='cuda:0')
episode: 201 training return: tensor(986.6049, device='cuda:0')
episode: 202 training return: tensor(981.1600, device='cuda:0')
episode: 203 training return: tensor(981.6846, device='cuda:0')
epoch: 51 test_true_pfm: -5.493115391155444 sim_pfm: 979.9945756852627
episode: 204 training return: tensor(980.5059, device='cuda:0')
episode: 205 training return: tensor(984.3657, device='cuda:0')
episode: 206 training return: tensor(966.8516, device='cuda:0')
episode: 207 training return: tensor(988.3643, device='cuda:0')
epoch: 52 test_true_pfm: -10.00803645721502 sim_pfm: 974.3035808570683
episode: 208 training return: tensor(984.0543, device='cuda:0')
episode: 209 training return: tensor(979.1083, device='cuda:0')
episode: 210 training return: tensor(983.0266, device='cuda:0')
episode: 211 training return: tensor(982.0405, device='cuda:0')
epoch: 53 test_true_pfm: -10.337274355520254 sim_pfm: 981.7867937259376
episode: 212 training return: tensor(982.5247, device='cuda:0')
episode: 213 training return: tensor(982.1785, device='cuda:0')
episode: 214 training return: tensor(917.7928, device='cuda:0')
episode: 215 training return: tensor(982.0662, device='cuda:0')
epoch: 54 test_true_pfm: 7.250246420515483 sim_pfm: 933.5198528669774
episode: 216 training return: tensor(984.6150, device='cuda:0')
episode: 217 training return: tensor(986.7125, device='cuda:0')
episode: 218 training return: tensor(987.5132, device='cuda:0')
episode: 219 training return: tensor(984.5991, device='cuda:0')
epoch: 55 test_true_pfm: -8.552371443468713 sim_pfm: 985.8117741160095
episode: 220 training return: tensor(984.6238, device='cuda:0')
episode: 221 training return: tensor(986.7278, device='cuda:0')
episode: 222 training return: tensor(987.3373, device='cuda:0')
episode: 223 training return: tensor(989.0183, device='cuda:0')
epoch: 56 test_true_pfm: -14.356778630261752 sim_pfm: 982.9522331148386
episode: 224 training return: tensor(987.4930, device='cuda:0')
episode: 225 training return: tensor(981.9404, device='cuda:0')
episode: 226 training return: tensor(983.8362, device='cuda:0')
episode: 227 training return: tensor(976.8250, device='cuda:0')
epoch: 57 test_true_pfm: -13.113150547290171 sim_pfm: 989.3575837746263
episode: 228 training return: tensor(979.2582, device='cuda:0')
episode: 229 training return: tensor(978.6957, device='cuda:0')
episode: 230 training return: tensor(987.4414, device='cuda:0')
episode: 231 training return: tensor(986.9875, device='cuda:0')
epoch: 58 test_true_pfm: -9.575806452860206 sim_pfm: 987.9324168115854
episode: 232 training return: tensor(983.6288, device='cuda:0')
episode: 233 training return: tensor(986.7285, device='cuda:0')
episode: 234 training return: tensor(983.7031, device='cuda:0')
episode: 235 training return: tensor(978.5007, device='cuda:0')
epoch: 59 test_true_pfm: -1.0073573435406435 sim_pfm: 985.9300283372402
episode: 236 training return: tensor(980.6143, device='cuda:0')
episode: 237 training return: tensor(984.7675, device='cuda:0')
episode: 238 training return: tensor(981.8144, device='cuda:0')
episode: 239 training return: tensor(986.1232, device='cuda:0')
epoch: 60 test_true_pfm: -7.544260012010783 sim_pfm: 991.1625350490212
episode: 240 training return: tensor(987.7258, device='cuda:0')
episode: 241 training return: tensor(985.5020, device='cuda:0')
episode: 242 training return: tensor(990.0300, device='cuda:0')
episode: 243 training return: tensor(986.8484, device='cuda:0')
epoch: 61 test_true_pfm: -11.265175495911448 sim_pfm: 988.1924774587154
episode: 244 training return: tensor(984.1464, device='cuda:0')
episode: 245 training return: tensor(989.0415, device='cuda:0')
episode: 246 training return: tensor(984.9335, device='cuda:0')
episode: 247 training return: tensor(988.9720, device='cuda:0')
epoch: 62 test_true_pfm: -10.710938130082333 sim_pfm: 991.5776604890823
episode: 248 training return: tensor(987.1206, device='cuda:0')
episode: 249 training return: tensor(973.0869, device='cuda:0')
episode: 250 training return: tensor(987.1518, device='cuda:0')
episode: 251 training return: tensor(932.1287, device='cuda:0')
epoch: 63 test_true_pfm: -6.986794674791746 sim_pfm: 984.7944250941276
episode: 252 training return: tensor(958.0645, device='cuda:0')
episode: 253 training return: tensor(980.3963, device='cuda:0')
episode: 254 training return: tensor(984.4780, device='cuda:0')
episode: 255 training return: tensor(980.7630, device='cuda:0')
epoch: 64 test_true_pfm: -11.440613178453152 sim_pfm: 983.7591695576906
episode: 256 training return: tensor(981.4016, device='cuda:0')
episode: 257 training return: tensor(985.2520, device='cuda:0')
episode: 258 training return: tensor(983.7507, device='cuda:0')
episode: 259 training return: tensor(977.9291, device='cuda:0')
epoch: 65 test_true_pfm: -4.20216057355494 sim_pfm: 988.7327071815729
episode: 260 training return: tensor(988.7358, device='cuda:0')
episode: 261 training return: tensor(984.3610, device='cuda:0')
episode: 262 training return: tensor(988.1066, device='cuda:0')
episode: 263 training return: tensor(988.9818, device='cuda:0')
epoch: 66 test_true_pfm: -14.242369168279035 sim_pfm: 976.7630368024111
episode: 264 training return: tensor(977.4326, device='cuda:0')
episode: 265 training return: tensor(987.5119, device='cuda:0')
episode: 266 training return: tensor(984.9567, device='cuda:0')
episode: 267 training return: tensor(988.0730, device='cuda:0')
epoch: 67 test_true_pfm: -2.0921197339037834 sim_pfm: 969.8697638958693
episode: 268 training return: tensor(967.5131, device='cuda:0')
episode: 269 training return: tensor(945.2443, device='cuda:0')
episode: 270 training return: tensor(986.4235, device='cuda:0')
episode: 271 training return: tensor(977.9210, device='cuda:0')
epoch: 68 test_true_pfm: -6.921536261342031 sim_pfm: 988.2543261408806
episode: 272 training return: tensor(975.8836, device='cuda:0')
episode: 273 training return: tensor(976.0305, device='cuda:0')
episode: 274 training return: tensor(983.8062, device='cuda:0')
episode: 275 training return: tensor(896.5724, device='cuda:0')
epoch: 69 test_true_pfm: -0.029601425222440268 sim_pfm: 875.5965582191013
episode: 276 training return: tensor(979.8705, device='cuda:0')
episode: 277 training return: tensor(983.0577, device='cuda:0')
episode: 278 training return: tensor(979.3693, device='cuda:0')
episode: 279 training return: tensor(976.6148, device='cuda:0')
epoch: 70 test_true_pfm: -10.32921993343849 sim_pfm: 986.4819630205632
episode: 280 training return: tensor(974.2865, device='cuda:0')
episode: 281 training return: tensor(970.1656, device='cuda:0')
episode: 282 training return: tensor(972.8797, device='cuda:0')
episode: 283 training return: tensor(972.5161, device='cuda:0')
epoch: 71 test_true_pfm: -5.881878258292025 sim_pfm: 982.5513038288802
episode: 284 training return: tensor(977.9185, device='cuda:0')
episode: 285 training return: tensor(972.0002, device='cuda:0')
episode: 286 training return: tensor(975.6332, device='cuda:0')
episode: 287 training return: tensor(973.6624, device='cuda:0')
epoch: 72 test_true_pfm: -13.13209913046748 sim_pfm: 986.8241830646991
episode: 288 training return: tensor(985.5298, device='cuda:0')
episode: 289 training return: tensor(981.0228, device='cuda:0')
episode: 290 training return: tensor(970.8016, device='cuda:0')
episode: 291 training return: tensor(984.2173, device='cuda:0')
epoch: 73 test_true_pfm: -12.48884371944954 sim_pfm: 977.028793695569
episode: 292 training return: tensor(986.2354, device='cuda:0')
episode: 293 training return: tensor(970.9507, device='cuda:0')
episode: 294 training return: tensor(975.0037, device='cuda:0')
episode: 295 training return: tensor(987.5043, device='cuda:0')
epoch: 74 test_true_pfm: -14.839345652413687 sim_pfm: 986.5489099115133
episode: 296 training return: tensor(983.9060, device='cuda:0')
episode: 297 training return: tensor(973.1653, device='cuda:0')
episode: 298 training return: tensor(972.7026, device='cuda:0')
episode: 299 training return: tensor(976.4318, device='cuda:0')
epoch: 75 test_true_pfm: -12.329760245906154 sim_pfm: 987.9701860681176
episode: 300 training return: tensor(983.6401, device='cuda:0')
episode: 301 training return: tensor(986.6338, device='cuda:0')
episode: 302 training return: tensor(973.7586, device='cuda:0')
episode: 303 training return: tensor(987.2733, device='cuda:0')
epoch: 76 test_true_pfm: -19.976157207888935 sim_pfm: 986.699039515853
episode: 304 training return: tensor(988.2048, device='cuda:0')
episode: 305 training return: tensor(990.3510, device='cuda:0')
episode: 306 training return: tensor(992.1095, device='cuda:0')
episode: 307 training return: tensor(989.6749, device='cuda:0')
epoch: 77 test_true_pfm: -17.2280326701307 sim_pfm: 978.2642759427429
episode: 308 training return: tensor(989.5444, device='cuda:0')
episode: 309 training return: tensor(990.1829, device='cuda:0')
episode: 310 training return: tensor(991.6702, device='cuda:0')
episode: 311 training return: tensor(990.9279, device='cuda:0')
epoch: 78 test_true_pfm: -10.566305948324105 sim_pfm: 992.4688954129815
episode: 312 training return: tensor(987.3715, device='cuda:0')
episode: 313 training return: tensor(982.0955, device='cuda:0')
episode: 314 training return: tensor(987.9047, device='cuda:0')
episode: 315 training return: tensor(985.2646, device='cuda:0')
epoch: 79 test_true_pfm: -10.255967874646931 sim_pfm: 986.8777693152427
episode: 316 training return: tensor(983.3580, device='cuda:0')
episode: 317 training return: tensor(982.4689, device='cuda:0')
episode: 318 training return: tensor(978.3025, device='cuda:0')
episode: 319 training return: tensor(988.5344, device='cuda:0')
epoch: 80 test_true_pfm: -14.684856773301727 sim_pfm: 989.2788768291473
episode: 320 training return: tensor(987.4773, device='cuda:0')
episode: 321 training return: tensor(989.3804, device='cuda:0')
episode: 322 training return: tensor(977.3201, device='cuda:0')
episode: 323 training return: tensor(990.3967, device='cuda:0')
epoch: 81 test_true_pfm: -12.823958765221954 sim_pfm: 985.1785632491112
episode: 324 training return: tensor(992.1740, device='cuda:0')
episode: 325 training return: tensor(990.8026, device='cuda:0')
episode: 326 training return: tensor(990.1550, device='cuda:0')
episode: 327 training return: tensor(985.4385, device='cuda:0')
epoch: 82 test_true_pfm: -9.906507179669134 sim_pfm: 986.8163161635399
episode: 328 training return: tensor(989.5041, device='cuda:0')
episode: 329 training return: tensor(982.3029, device='cuda:0')
episode: 330 training return: tensor(988.7297, device='cuda:0')
episode: 331 training return: tensor(986.7635, device='cuda:0')
epoch: 83 test_true_pfm: -12.201016739087999 sim_pfm: 987.2398326605559
episode: 332 training return: tensor(986.0696, device='cuda:0')
episode: 333 training return: tensor(987.9453, device='cuda:0')
episode: 334 training return: tensor(989.6006, device='cuda:0')
episode: 335 training return: tensor(987.8504, device='cuda:0')
epoch: 84 test_true_pfm: -9.838551055326453 sim_pfm: 990.0918523877859
episode: 336 training return: tensor(989.4000, device='cuda:0')
episode: 337 training return: tensor(987.5692, device='cuda:0')
episode: 338 training return: tensor(988.8055, device='cuda:0')
episode: 339 training return: tensor(988.5288, device='cuda:0')
epoch: 85 test_true_pfm: -7.226977677605676 sim_pfm: 991.1220756575465
episode: 340 training return: tensor(989.4586, device='cuda:0')
episode: 341 training return: tensor(987.7123, device='cuda:0')
episode: 342 training return: tensor(991.8268, device='cuda:0')
episode: 343 training return: tensor(986.0862, device='cuda:0')
epoch: 86 test_true_pfm: -8.503477112937226 sim_pfm: 989.7702822461724
episode: 344 training return: tensor(984.1240, device='cuda:0')
episode: 345 training return: tensor(988.2009, device='cuda:0')
episode: 346 training return: tensor(990.5373, device='cuda:0')
episode: 347 training return: tensor(988.0926, device='cuda:0')
epoch: 87 test_true_pfm: -15.304696234798575 sim_pfm: 992.6868413180113
episode: 348 training return: tensor(992.4385, device='cuda:0')
episode: 349 training return: tensor(990.9566, device='cuda:0')
episode: 350 training return: tensor(974.8994, device='cuda:0')
episode: 351 training return: tensor(988.3163, device='cuda:0')
epoch: 88 test_true_pfm: -11.089831336467737 sim_pfm: 985.0625846462324
episode: 352 training return: tensor(988.6505, device='cuda:0')
episode: 353 training return: tensor(988.2483, device='cuda:0')
episode: 354 training return: tensor(964.6054, device='cuda:0')
episode: 355 training return: tensor(990.8351, device='cuda:0')
epoch: 89 test_true_pfm: -2.5141530513862707 sim_pfm: 972.7571137517691
episode: 356 training return: tensor(966.7249, device='cuda:0')
episode: 357 training return: tensor(960.1948, device='cuda:0')
episode: 358 training return: tensor(939.1583, device='cuda:0')
episode: 359 training return: tensor(872.6701, device='cuda:0')
epoch: 90 test_true_pfm: -4.180641163348488 sim_pfm: 905.5335580591112
episode: 360 training return: tensor(875.1703, device='cuda:0')
episode: 361 training return: tensor(987.0540, device='cuda:0')
episode: 362 training return: tensor(979.1949, device='cuda:0')
episode: 363 training return: tensor(989.9290, device='cuda:0')
epoch: 91 test_true_pfm: -11.685964590882662 sim_pfm: 985.4244104102254
episode: 364 training return: tensor(960.3699, device='cuda:0')
episode: 365 training return: tensor(980.1456, device='cuda:0')
episode: 366 training return: tensor(984.8880, device='cuda:0')
episode: 367 training return: tensor(970.2906, device='cuda:0')
epoch: 92 test_true_pfm: -8.863214370676639 sim_pfm: 982.0098030567169
episode: 368 training return: tensor(974.2280, device='cuda:0')
episode: 369 training return: tensor(979.1464, device='cuda:0')
episode: 370 training return: tensor(979.2595, device='cuda:0')
episode: 371 training return: tensor(981.5175, device='cuda:0')
epoch: 93 test_true_pfm: -3.7323503013895647 sim_pfm: 983.6670203149318
episode: 372 training return: tensor(983.7239, device='cuda:0')
episode: 373 training return: tensor(985.9947, device='cuda:0')
episode: 374 training return: tensor(983.5082, device='cuda:0')
episode: 375 training return: tensor(982.6289, device='cuda:0')
epoch: 94 test_true_pfm: -7.37950314265772 sim_pfm: 987.2820480883122
episode: 376 training return: tensor(981.5760, device='cuda:0')
episode: 377 training return: tensor(977.8713, device='cuda:0')
episode: 378 training return: tensor(982.9288, device='cuda:0')
episode: 379 training return: tensor(980.5328, device='cuda:0')
epoch: 95 test_true_pfm: -4.701756480399627 sim_pfm: 984.844874459505
episode: 380 training return: tensor(983.7883, device='cuda:0')
episode: 381 training return: tensor(978.1585, device='cuda:0')
episode: 382 training return: tensor(978.9072, device='cuda:0')
episode: 383 training return: tensor(974.5404, device='cuda:0')
epoch: 96 test_true_pfm: -4.858033391255233 sim_pfm: 982.9208421707153
episode: 384 training return: tensor(979.6972, device='cuda:0')
episode: 385 training return: tensor(978.7693, device='cuda:0')
episode: 386 training return: tensor(981.5023, device='cuda:0')
episode: 387 training return: tensor(985.1436, device='cuda:0')
epoch: 97 test_true_pfm: -2.719677668333831 sim_pfm: 974.2406042600051
episode: 388 training return: tensor(984.2260, device='cuda:0')
episode: 389 training return: tensor(977.7966, device='cuda:0')
episode: 390 training return: tensor(977.6078, device='cuda:0')
episode: 391 training return: tensor(964.2972, device='cuda:0')
epoch: 98 test_true_pfm: -2.1444517073005134 sim_pfm: 979.4941841244697
episode: 392 training return: tensor(967.6764, device='cuda:0')
episode: 393 training return: tensor(975.9706, device='cuda:0')
episode: 394 training return: tensor(985.1292, device='cuda:0')
episode: 395 training return: tensor(990.6235, device='cuda:0')
epoch: 99 test_true_pfm: -4.72992225192089 sim_pfm: 993.4556000925601
episode: 396 training return: tensor(988.7787, device='cuda:0')
episode: 397 training return: tensor(991.0587, device='cuda:0')
episode: 398 training return: tensor(982.6118, device='cuda:0')
episode: 399 training return: tensor(967.9657, device='cuda:0')
epoch: 100 test_true_pfm: -2.417627170685987 sim_pfm: 976.9278551220893
episode: 400 training return: tensor(960.4596, device='cuda:0')
episode: 401 training return: tensor(975.7798, device='cuda:0')
episode: 402 training return: tensor(975.0404, device='cuda:0')
episode: 403 training return: tensor(971.7922, device='cuda:0')
epoch: 101 test_true_pfm: -4.294384034128101 sim_pfm: 987.3864185728132
episode: 404 training return: tensor(980.5839, device='cuda:0')
episode: 405 training return: tensor(982.6307, device='cuda:0')
episode: 406 training return: tensor(981.1149, device='cuda:0')
episode: 407 training return: tensor(990.4353, device='cuda:0')
epoch: 102 test_true_pfm: -12.342973937479455 sim_pfm: 992.1919704407453
episode: 408 training return: tensor(986.6203, device='cuda:0')
episode: 409 training return: tensor(990.9332, device='cuda:0')
episode: 410 training return: tensor(991.0651, device='cuda:0')
episode: 411 training return: tensor(970.3588, device='cuda:0')
epoch: 103 test_true_pfm: 2.295115218182311 sim_pfm: 955.3755999520421
episode: 412 training return: tensor(962.8795, device='cuda:0')
episode: 413 training return: tensor(991.5327, device='cuda:0')
episode: 414 training return: tensor(978.4022, device='cuda:0')
episode: 415 training return: tensor(983.8336, device='cuda:0')
epoch: 104 test_true_pfm: -13.630344509830318 sim_pfm: 986.5091387912631
episode: 416 training return: tensor(976.8685, device='cuda:0')
episode: 417 training return: tensor(977.3197, device='cuda:0')
episode: 418 training return: tensor(982.3074, device='cuda:0')
episode: 419 training return: tensor(974.8273, device='cuda:0')
epoch: 105 test_true_pfm: -19.336107897029546 sim_pfm: 987.6409592561424
episode: 420 training return: tensor(989.5690, device='cuda:0')
episode: 421 training return: tensor(935.8872, device='cuda:0')
episode: 422 training return: tensor(987.5632, device='cuda:0')
episode: 423 training return: tensor(982.0587, device='cuda:0')
epoch: 106 test_true_pfm: -10.618855907066102 sim_pfm: 990.3376926317811
episode: 424 training return: tensor(987.7339, device='cuda:0')
episode: 425 training return: tensor(990.3521, device='cuda:0')
episode: 426 training return: tensor(990.7375, device='cuda:0')
episode: 427 training return: tensor(987.2009, device='cuda:0')
epoch: 107 test_true_pfm: -11.459860037674549 sim_pfm: 990.2299649730325
episode: 428 training return: tensor(988.5357, device='cuda:0')
episode: 429 training return: tensor(987.0867, device='cuda:0')
episode: 430 training return: tensor(990.3415, device='cuda:0')
episode: 431 training return: tensor(992.4650, device='cuda:0')
epoch: 108 test_true_pfm: -11.702254214840398 sim_pfm: 993.6841719537973
episode: 432 training return: tensor(993.6505, device='cuda:0')
episode: 433 training return: tensor(992.7480, device='cuda:0')
episode: 434 training return: tensor(988.4722, device='cuda:0')
episode: 435 training return: tensor(990.1313, device='cuda:0')
epoch: 109 test_true_pfm: -11.751271681959462 sim_pfm: 994.8256440222264
episode: 436 training return: tensor(988.2925, device='cuda:0')
episode: 437 training return: tensor(987.3053, device='cuda:0')
episode: 438 training return: tensor(990.1376, device='cuda:0')
episode: 439 training return: tensor(952.0558, device='cuda:0')
epoch: 110 test_true_pfm: -8.661283218653569 sim_pfm: 962.4652224928141
episode: 440 training return: tensor(972.3218, device='cuda:0')
episode: 441 training return: tensor(965.1184, device='cuda:0')
episode: 442 training return: tensor(964.5244, device='cuda:0')
episode: 443 training return: tensor(992.8679, device='cuda:0')
epoch: 111 test_true_pfm: -5.737945988548722 sim_pfm: 994.2646283626557
episode: 444 training return: tensor(993.7240, device='cuda:0')
episode: 445 training return: tensor(989.4695, device='cuda:0')
episode: 446 training return: tensor(967.3060, device='cuda:0')
episode: 447 training return: tensor(960.6436, device='cuda:0')
epoch: 112 test_true_pfm: 0.5225821165981904 sim_pfm: 974.3280360251665
episode: 448 training return: tensor(970.6340, device='cuda:0')
episode: 449 training return: tensor(986.8790, device='cuda:0')
episode: 450 training return: tensor(985.8577, device='cuda:0')
episode: 451 training return: tensor(964.3963, device='cuda:0')
epoch: 113 test_true_pfm: -8.621808345828715 sim_pfm: 976.7004650503397
episode: 452 training return: tensor(970.9578, device='cuda:0')
episode: 453 training return: tensor(982.7034, device='cuda:0')
episode: 454 training return: tensor(983.2537, device='cuda:0')
episode: 455 training return: tensor(941.3327, device='cuda:0')
epoch: 114 test_true_pfm: -7.221538790500722 sim_pfm: 985.465437400341
episode: 456 training return: tensor(972.1824, device='cuda:0')
episode: 457 training return: tensor(987.6766, device='cuda:0')
episode: 458 training return: tensor(989.1942, device='cuda:0')
episode: 459 training return: tensor(985.7877, device='cuda:0')
epoch: 115 test_true_pfm: -8.682056810983806 sim_pfm: 990.7012978091836
episode: 460 training return: tensor(986.9903, device='cuda:0')
episode: 461 training return: tensor(963.5884, device='cuda:0')
episode: 462 training return: tensor(982.0966, device='cuda:0')
episode: 463 training return: tensor(985.7310, device='cuda:0')
epoch: 116 test_true_pfm: -6.289580671436562 sim_pfm: 990.8467024132609
episode: 464 training return: tensor(978.3779, device='cuda:0')
episode: 465 training return: tensor(979.8889, device='cuda:0')
episode: 466 training return: tensor(976.4402, device='cuda:0')
episode: 467 training return: tensor(983.2706, device='cuda:0')
epoch: 117 test_true_pfm: -7.4494822386396224 sim_pfm: 981.8052465934306
episode: 468 training return: tensor(971.0817, device='cuda:0')
episode: 469 training return: tensor(985.2775, device='cuda:0')
episode: 470 training return: tensor(983.8979, device='cuda:0')
episode: 471 training return: tensor(988.7162, device='cuda:0')
epoch: 118 test_true_pfm: -4.368654405642968 sim_pfm: 978.1946556165815
episode: 472 training return: tensor(986.3581, device='cuda:0')
episode: 473 training return: tensor(987.6413, device='cuda:0')
episode: 474 training return: tensor(985.9650, device='cuda:0')
episode: 475 training return: tensor(985.2244, device='cuda:0')
epoch: 119 test_true_pfm: -5.3225715508858 sim_pfm: 979.8480474874377
episode: 476 training return: tensor(984.3287, device='cuda:0')
episode: 477 training return: tensor(984.1099, device='cuda:0')
episode: 478 training return: tensor(985.2606, device='cuda:0')
episode: 479 training return: tensor(983.1041, device='cuda:0')
epoch: 120 test_true_pfm: -6.862391467936772 sim_pfm: 987.1148676127195
episode: 480 training return: tensor(980.6401, device='cuda:0')
episode: 481 training return: tensor(983.1339, device='cuda:0')
episode: 482 training return: tensor(981.0598, device='cuda:0')
episode: 483 training return: tensor(979.6310, device='cuda:0')
epoch: 121 test_true_pfm: -1.6788058536728598 sim_pfm: 982.3437700554729
episode: 484 training return: tensor(982.6702, device='cuda:0')
episode: 485 training return: tensor(977.9819, device='cuda:0')
episode: 486 training return: tensor(980.6441, device='cuda:0')
episode: 487 training return: tensor(989.7784, device='cuda:0')
epoch: 122 test_true_pfm: -11.926287088570135 sim_pfm: 985.5907791882753
episode: 488 training return: tensor(983.5943, device='cuda:0')
episode: 489 training return: tensor(986.8419, device='cuda:0')
episode: 490 training return: tensor(985.2982, device='cuda:0')
episode: 491 training return: tensor(981.2682, device='cuda:0')
epoch: 123 test_true_pfm: -17.080398190193637 sim_pfm: 984.539753331989
episode: 492 training return: tensor(979.4706, device='cuda:0')
episode: 493 training return: tensor(980.4819, device='cuda:0')
episode: 494 training return: tensor(984.9221, device='cuda:0')
episode: 495 training return: tensor(984.3049, device='cuda:0')
epoch: 124 test_true_pfm: -15.074276600934207 sim_pfm: 977.090777772665
episode: 496 training return: tensor(976.8370, device='cuda:0')
episode: 497 training return: tensor(974.4509, device='cuda:0')
episode: 498 training return: tensor(971.4850, device='cuda:0')
episode: 499 training return: tensor(956.9241, device='cuda:0')
epoch: 125 test_true_pfm: -10.79250520752851 sim_pfm: 971.0416664153338
episode: 500 training return: tensor(977.7650, device='cuda:0')
episode: 501 training return: tensor(986.1918, device='cuda:0')
episode: 502 training return: tensor(986.1100, device='cuda:0')
episode: 503 training return: tensor(980.3005, device='cuda:0')
epoch: 126 test_true_pfm: -3.715974098184551 sim_pfm: 989.8328390210867
episode: 504 training return: tensor(981.0748, device='cuda:0')
episode: 505 training return: tensor(962.1805, device='cuda:0')
episode: 506 training return: tensor(989.9913, device='cuda:0')
episode: 507 training return: tensor(979.6053, device='cuda:0')
epoch: 127 test_true_pfm: -7.85743506574393 sim_pfm: 994.0021579381079
episode: 508 training return: tensor(986.2225, device='cuda:0')
episode: 509 training return: tensor(988.4022, device='cuda:0')
episode: 510 training return: tensor(988.3961, device='cuda:0')
episode: 511 training return: tensor(988.2691, device='cuda:0')
epoch: 128 test_true_pfm: -2.319305976181894 sim_pfm: 991.5075390815734
episode: 512 training return: tensor(987.2257, device='cuda:0')
episode: 513 training return: tensor(982.5052, device='cuda:0')
episode: 514 training return: tensor(832.1793, device='cuda:0')
episode: 515 training return: tensor(976.7110, device='cuda:0')
epoch: 129 test_true_pfm: -3.219083101448111 sim_pfm: 963.7086543917655
episode: 516 training return: tensor(978.2975, device='cuda:0')
episode: 517 training return: tensor(980.3483, device='cuda:0')
episode: 518 training return: tensor(976.9647, device='cuda:0')
episode: 519 training return: tensor(977.4099, device='cuda:0')
epoch: 130 test_true_pfm: -7.167728166344176 sim_pfm: 975.0785958319902
episode: 520 training return: tensor(969.4280, device='cuda:0')
episode: 521 training return: tensor(969.3299, device='cuda:0')
episode: 522 training return: tensor(956.1859, device='cuda:0')
episode: 523 training return: tensor(959.8271, device='cuda:0')
epoch: 131 test_true_pfm: 2.757193504472574 sim_pfm: 966.0084503471851
episode: 524 training return: tensor(955.1757, device='cuda:0')
episode: 525 training return: tensor(953.4774, device='cuda:0')
episode: 526 training return: tensor(946.9852, device='cuda:0')
episode: 527 training return: tensor(955.8985, device='cuda:0')
epoch: 132 test_true_pfm: 8.462830237414474 sim_pfm: 961.0480290306732
episode: 528 training return: tensor(960.2508, device='cuda:0')
episode: 529 training return: tensor(957.4291, device='cuda:0')
episode: 530 training return: tensor(958.2467, device='cuda:0')
episode: 531 training return: tensor(958.0854, device='cuda:0')
epoch: 133 test_true_pfm: 4.125832768748124 sim_pfm: 963.7402558434754
episode: 532 training return: tensor(946.7236, device='cuda:0')
episode: 533 training return: tensor(964.6332, device='cuda:0')
episode: 534 training return: tensor(965.1543, device='cuda:0')
episode: 535 training return: tensor(957.4208, device='cuda:0')
epoch: 134 test_true_pfm: 2.4853534777190314 sim_pfm: 979.9861298892647
episode: 536 training return: tensor(956.9582, device='cuda:0')
episode: 537 training return: tensor(961.8795, device='cuda:0')
episode: 538 training return: tensor(958.5349, device='cuda:0')
episode: 539 training return: tensor(960.4609, device='cuda:0')
epoch: 135 test_true_pfm: 4.567336028086558 sim_pfm: 967.3119114423171
episode: 540 training return: tensor(961.1492, device='cuda:0')
episode: 541 training return: tensor(961.1293, device='cuda:0')
episode: 542 training return: tensor(957.7199, device='cuda:0')
episode: 543 training return: tensor(958.0968, device='cuda:0')
epoch: 136 test_true_pfm: 4.699863753349292 sim_pfm: 974.8734457105398
episode: 544 training return: tensor(955.0122, device='cuda:0')
episode: 545 training return: tensor(950.6154, device='cuda:0')
episode: 546 training return: tensor(956.1814, device='cuda:0')
episode: 547 training return: tensor(971.8071, device='cuda:0')
epoch: 137 test_true_pfm: -7.043330677909614 sim_pfm: 983.4402435339987
episode: 548 training return: tensor(977.6226, device='cuda:0')
episode: 549 training return: tensor(978.4943, device='cuda:0')
episode: 550 training return: tensor(979.2991, device='cuda:0')
episode: 551 training return: tensor(976.8691, device='cuda:0')
epoch: 138 test_true_pfm: -2.031258985025445 sim_pfm: 983.0819161817432
episode: 552 training return: tensor(973.1939, device='cuda:0')
episode: 553 training return: tensor(968.3615, device='cuda:0')
episode: 554 training return: tensor(970.4875, device='cuda:0')
episode: 555 training return: tensor(972.3682, device='cuda:0')
epoch: 139 test_true_pfm: 3.380595210901615 sim_pfm: 981.1101319596171
episode: 556 training return: tensor(974.7550, device='cuda:0')
episode: 557 training return: tensor(970.5798, device='cuda:0')
episode: 558 training return: tensor(961.0813, device='cuda:0')
episode: 559 training return: tensor(971.0623, device='cuda:0')
epoch: 140 test_true_pfm: -7.6542999659229265 sim_pfm: 977.5768956363202
episode: 560 training return: tensor(974.3537, device='cuda:0')
episode: 561 training return: tensor(969.7559, device='cuda:0')
episode: 562 training return: tensor(981.3281, device='cuda:0')
episode: 563 training return: tensor(975.0479, device='cuda:0')
epoch: 141 test_true_pfm: -5.988871469572462 sim_pfm: 983.3149203575216
episode: 564 training return: tensor(983.8914, device='cuda:0')
episode: 565 training return: tensor(979.3100, device='cuda:0')
episode: 566 training return: tensor(978.5854, device='cuda:0')
episode: 567 training return: tensor(973.5403, device='cuda:0')
epoch: 142 test_true_pfm: -4.903595601423423 sim_pfm: 975.68248034399
episode: 568 training return: tensor(975.2926, device='cuda:0')
episode: 569 training return: tensor(974.9149, device='cuda:0')
episode: 570 training return: tensor(976.1591, device='cuda:0')
episode: 571 training return: tensor(971.4005, device='cuda:0')
epoch: 143 test_true_pfm: -8.269767784672345 sim_pfm: 970.3867614477873
episode: 572 training return: tensor(974.4297, device='cuda:0')
episode: 573 training return: tensor(964.7416, device='cuda:0')
episode: 574 training return: tensor(968.9411, device='cuda:0')
episode: 575 training return: tensor(967.4218, device='cuda:0')
epoch: 144 test_true_pfm: -2.5227587193337997 sim_pfm: 971.7732032179832
episode: 576 training return: tensor(968.1159, device='cuda:0')
episode: 577 training return: tensor(961.1004, device='cuda:0')
episode: 578 training return: tensor(952.4610, device='cuda:0')
episode: 579 training return: tensor(963.6492, device='cuda:0')
epoch: 145 test_true_pfm: 7.190056684989824 sim_pfm: 959.395889404416
episode: 580 training return: tensor(962.3150, device='cuda:0')
episode: 581 training return: tensor(971.6463, device='cuda:0')
episode: 582 training return: tensor(973.8128, device='cuda:0')
episode: 583 training return: tensor(969.2913, device='cuda:0')
epoch: 146 test_true_pfm: -9.494533805716642 sim_pfm: 986.3474981486797
episode: 584 training return: tensor(967.9683, device='cuda:0')
episode: 585 training return: tensor(979.8704, device='cuda:0')
episode: 586 training return: tensor(910.6723, device='cuda:0')
episode: 587 training return: tensor(975.9077, device='cuda:0')
epoch: 147 test_true_pfm: -9.216551545308267 sim_pfm: 956.9224693529308
episode: 588 training return: tensor(972.2534, device='cuda:0')
episode: 589 training return: tensor(965.4573, device='cuda:0')
episode: 590 training return: tensor(975.6077, device='cuda:0')
episode: 591 training return: tensor(981.5811, device='cuda:0')
epoch: 148 test_true_pfm: -8.133323556500097 sim_pfm: 990.2213865101337
episode: 592 training return: tensor(983.4231, device='cuda:0')
episode: 593 training return: tensor(971.0503, device='cuda:0')
episode: 594 training return: tensor(977.1071, device='cuda:0')
episode: 595 training return: tensor(953.8361, device='cuda:0')
epoch: 149 test_true_pfm: -5.689185488601618 sim_pfm: 979.3047441750765
episode: 596 training return: tensor(960.8879, device='cuda:0')
episode: 597 training return: tensor(896.4635, device='cuda:0')
episode: 598 training return: tensor(959.4029, device='cuda:0')
episode: 599 training return: tensor(948.4610, device='cuda:0')
epoch: 150 test_true_pfm: -6.290453659435313 sim_pfm: 958.6627822600306
