['--alg', 'ddpg', '--env', 'Swimmer-v3', '--learn', 'baseline', '--traj', 'expert', '--seed', '4']
episode: 0 training return: tensor(394.2660, device='cuda:0')
episode: 1 training return: tensor(364.2198, device='cuda:0')
episode: 2 training return: tensor(609.0766, device='cuda:0')
episode: 3 training return: tensor(83.9202, device='cuda:0')
epoch: 1 test_true_pfm: 11.823345977496249 sim_pfm: 571.9377839624882
episode: 4 training return: tensor(412.6209, device='cuda:0')
episode: 5 training return: tensor(298.0723, device='cuda:0')
episode: 6 training return: tensor(491.1685, device='cuda:0')
episode: 7 training return: tensor(299.1216, device='cuda:0')
epoch: 2 test_true_pfm: 14.38932320457597 sim_pfm: 590.1778987407685
episode: 8 training return: tensor(528.9610, device='cuda:0')
episode: 9 training return: tensor(486.1744, device='cuda:0')
episode: 10 training return: tensor(161.1268, device='cuda:0')
episode: 11 training return: tensor(461.3790, device='cuda:0')
epoch: 3 test_true_pfm: -19.36974176206265 sim_pfm: 583.8432809029706
episode: 12 training return: tensor(377.8433, device='cuda:0')
episode: 13 training return: tensor(720.4191, device='cuda:0')
episode: 14 training return: tensor(691.3478, device='cuda:0')
episode: 15 training return: tensor(915.5399, device='cuda:0')
epoch: 4 test_true_pfm: -22.98722759683559 sim_pfm: 769.9072261631488
episode: 16 training return: tensor(959.5286, device='cuda:0')
episode: 17 training return: tensor(984.6884, device='cuda:0')
episode: 18 training return: tensor(984.8990, device='cuda:0')
episode: 19 training return: tensor(981.1674, device='cuda:0')
epoch: 5 test_true_pfm: -20.781932242107427 sim_pfm: 976.9472354009747
episode: 20 training return: tensor(973.2518, device='cuda:0')
episode: 21 training return: tensor(977.0088, device='cuda:0')
episode: 22 training return: tensor(980.4235, device='cuda:0')
episode: 23 training return: tensor(774.0342, device='cuda:0')
epoch: 6 test_true_pfm: -9.106667951841136 sim_pfm: 552.0212217631517
episode: 24 training return: tensor(979.8597, device='cuda:0')
episode: 25 training return: tensor(653.2151, device='cuda:0')
episode: 26 training return: tensor(992.1566, device='cuda:0')
episode: 27 training return: tensor(874.6908, device='cuda:0')
epoch: 7 test_true_pfm: -16.02252288137665 sim_pfm: 988.9380802810192
episode: 28 training return: tensor(830.1143, device='cuda:0')
episode: 29 training return: tensor(993.5344, device='cuda:0')
episode: 30 training return: tensor(994.7260, device='cuda:0')
episode: 31 training return: tensor(994.0271, device='cuda:0')
epoch: 8 test_true_pfm: -21.175660829673877 sim_pfm: 993.6015615791082
episode: 32 training return: tensor(992.0715, device='cuda:0')
episode: 33 training return: tensor(983.0665, device='cuda:0')
episode: 34 training return: tensor(988.3414, device='cuda:0')
episode: 35 training return: tensor(996.6829, device='cuda:0')
epoch: 9 test_true_pfm: -23.24056666653943 sim_pfm: 995.3525589570403
episode: 36 training return: tensor(995.4528, device='cuda:0')
episode: 37 training return: tensor(995.1873, device='cuda:0')
episode: 38 training return: tensor(994.5834, device='cuda:0')
episode: 39 training return: tensor(990.6921, device='cuda:0')
epoch: 10 test_true_pfm: -18.59252166446666 sim_pfm: 992.8278075762094
episode: 40 training return: tensor(993.6421, device='cuda:0')
episode: 41 training return: tensor(993.7623, device='cuda:0')
episode: 42 training return: tensor(995.8730, device='cuda:0')
episode: 43 training return: tensor(997.1509, device='cuda:0')
epoch: 11 test_true_pfm: -11.617729982325987 sim_pfm: 989.0341783896089
episode: 44 training return: tensor(994.0400, device='cuda:0')
episode: 45 training return: tensor(982.1422, device='cuda:0')
episode: 46 training return: tensor(989.4313, device='cuda:0')
episode: 47 training return: tensor(995.6853, device='cuda:0')
epoch: 12 test_true_pfm: -25.180205208682118 sim_pfm: 995.4403950579465
episode: 48 training return: tensor(996.0281, device='cuda:0')
episode: 49 training return: tensor(995.9089, device='cuda:0')
episode: 50 training return: tensor(993.9418, device='cuda:0')
episode: 51 training return: tensor(995.6342, device='cuda:0')
epoch: 13 test_true_pfm: -20.802698391321705 sim_pfm: 995.8009358242155
episode: 52 training return: tensor(995.9695, device='cuda:0')
episode: 53 training return: tensor(994.2380, device='cuda:0')
episode: 54 training return: tensor(990.7427, device='cuda:0')
episode: 55 training return: tensor(993.7825, device='cuda:0')
epoch: 14 test_true_pfm: -19.392895011120622 sim_pfm: 994.7592903614044
episode: 56 training return: tensor(992.3109, device='cuda:0')
episode: 57 training return: tensor(991.3888, device='cuda:0')
episode: 58 training return: tensor(987.8256, device='cuda:0')
episode: 59 training return: tensor(990.3436, device='cuda:0')
epoch: 15 test_true_pfm: -18.784448361920102 sim_pfm: 991.2121702253819
episode: 60 training return: tensor(989.1841, device='cuda:0')
episode: 61 training return: tensor(990.1959, device='cuda:0')
episode: 62 training return: tensor(988.3909, device='cuda:0')
episode: 63 training return: tensor(991.5793, device='cuda:0')
epoch: 16 test_true_pfm: -20.17647111711365 sim_pfm: 992.6906857192516
episode: 64 training return: tensor(993.7333, device='cuda:0')
episode: 65 training return: tensor(993.3436, device='cuda:0')
episode: 66 training return: tensor(994.2983, device='cuda:0')
episode: 67 training return: tensor(993.1483, device='cuda:0')
epoch: 17 test_true_pfm: -20.515515575339396 sim_pfm: 995.149530351162
episode: 68 training return: tensor(993.0610, device='cuda:0')
episode: 69 training return: tensor(992.7930, device='cuda:0')
episode: 70 training return: tensor(994.1563, device='cuda:0')
episode: 71 training return: tensor(995.2163, device='cuda:0')
epoch: 18 test_true_pfm: -21.182761533679304 sim_pfm: 996.7786724537611
episode: 72 training return: tensor(995.0618, device='cuda:0')
episode: 73 training return: tensor(996.3703, device='cuda:0')
episode: 74 training return: tensor(994.3061, device='cuda:0')
episode: 75 training return: tensor(992.1415, device='cuda:0')
epoch: 19 test_true_pfm: -16.23735973224398 sim_pfm: 992.8602020561696
episode: 76 training return: tensor(990.8941, device='cuda:0')
episode: 77 training return: tensor(990.1997, device='cuda:0')
episode: 78 training return: tensor(988.8983, device='cuda:0')
episode: 79 training return: tensor(979.9790, device='cuda:0')
epoch: 20 test_true_pfm: -18.05084936383352 sim_pfm: 987.5305322647094
episode: 80 training return: tensor(981.1990, device='cuda:0')
episode: 81 training return: tensor(984.7316, device='cuda:0')
episode: 82 training return: tensor(985.2796, device='cuda:0')
episode: 83 training return: tensor(992.0190, device='cuda:0')
epoch: 21 test_true_pfm: -17.53731504969821 sim_pfm: 994.8679530143738
episode: 84 training return: tensor(992.7017, device='cuda:0')
episode: 85 training return: tensor(995.9302, device='cuda:0')
episode: 86 training return: tensor(994.4425, device='cuda:0')
episode: 87 training return: tensor(991.8386, device='cuda:0')
epoch: 22 test_true_pfm: -23.27349289884937 sim_pfm: 995.7152807176113
episode: 88 training return: tensor(993.3885, device='cuda:0')
episode: 89 training return: tensor(996.1004, device='cuda:0')
episode: 90 training return: tensor(994.4835, device='cuda:0')
episode: 91 training return: tensor(995.7390, device='cuda:0')
epoch: 23 test_true_pfm: -23.382717983663614 sim_pfm: 996.9714220941066
episode: 92 training return: tensor(995.3817, device='cuda:0')
episode: 93 training return: tensor(995.4186, device='cuda:0')
episode: 94 training return: tensor(996.8488, device='cuda:0')
episode: 95 training return: tensor(996.5959, device='cuda:0')
epoch: 24 test_true_pfm: -15.004931891264837 sim_pfm: 967.9347296148538
episode: 96 training return: tensor(985.4545, device='cuda:0')
episode: 97 training return: tensor(996.3964, device='cuda:0')
episode: 98 training return: tensor(994.5335, device='cuda:0')
episode: 99 training return: tensor(997.1439, device='cuda:0')
epoch: 25 test_true_pfm: -21.88696768741527 sim_pfm: 992.2926486670971
episode: 100 training return: tensor(996.6957, device='cuda:0')
episode: 101 training return: tensor(997.6536, device='cuda:0')
episode: 102 training return: tensor(995.9478, device='cuda:0')
episode: 103 training return: tensor(994.4770, device='cuda:0')
epoch: 26 test_true_pfm: -26.854943399667413 sim_pfm: 993.4407325387001
episode: 104 training return: tensor(995.7341, device='cuda:0')
episode: 105 training return: tensor(996.0819, device='cuda:0')
episode: 106 training return: tensor(997.5104, device='cuda:0')
episode: 107 training return: tensor(996.7494, device='cuda:0')
epoch: 27 test_true_pfm: -25.50584688823802 sim_pfm: 996.9254250735045
episode: 108 training return: tensor(996.9188, device='cuda:0')
episode: 109 training return: tensor(996.0850, device='cuda:0')
episode: 110 training return: tensor(995.7809, device='cuda:0')
episode: 111 training return: tensor(995.7883, device='cuda:0')
epoch: 28 test_true_pfm: -24.61342745972866 sim_pfm: 997.1268635809422
episode: 112 training return: tensor(995.3628, device='cuda:0')
episode: 113 training return: tensor(996.4601, device='cuda:0')
episode: 114 training return: tensor(996.2144, device='cuda:0')
episode: 115 training return: tensor(996.3513, device='cuda:0')
epoch: 29 test_true_pfm: -25.509009581736173 sim_pfm: 995.9872550055385
episode: 116 training return: tensor(996.5986, device='cuda:0')
episode: 117 training return: tensor(995.6743, device='cuda:0')
episode: 118 training return: tensor(997.7952, device='cuda:0')
episode: 119 training return: tensor(996.8107, device='cuda:0')
epoch: 30 test_true_pfm: -26.268082840092667 sim_pfm: 996.80661200881
episode: 120 training return: tensor(997.3029, device='cuda:0')
episode: 121 training return: tensor(996.6373, device='cuda:0')
episode: 122 training return: tensor(995.9749, device='cuda:0')
episode: 123 training return: tensor(994.6141, device='cuda:0')
epoch: 31 test_true_pfm: -26.4946974137112 sim_pfm: 996.1154797554016
episode: 124 training return: tensor(997.2882, device='cuda:0')
episode: 125 training return: tensor(996.3961, device='cuda:0')
episode: 126 training return: tensor(997.2963, device='cuda:0')
episode: 127 training return: tensor(997.3859, device='cuda:0')
epoch: 32 test_true_pfm: -27.42390254853504 sim_pfm: 995.3147022120654
episode: 128 training return: tensor(995.4602, device='cuda:0')
episode: 129 training return: tensor(996.1554, device='cuda:0')
episode: 130 training return: tensor(997.3885, device='cuda:0')
episode: 131 training return: tensor(996.4165, device='cuda:0')
epoch: 33 test_true_pfm: -20.30132370482817 sim_pfm: 996.8574795722961
episode: 132 training return: tensor(995.6157, device='cuda:0')
episode: 133 training return: tensor(995.1815, device='cuda:0')
episode: 134 training return: tensor(997.0983, device='cuda:0')
episode: 135 training return: tensor(994.5905, device='cuda:0')
epoch: 34 test_true_pfm: -26.272904417165865 sim_pfm: 997.2924930214882
episode: 136 training return: tensor(994.7596, device='cuda:0')
episode: 137 training return: tensor(995.3030, device='cuda:0')
episode: 138 training return: tensor(995.8266, device='cuda:0')
episode: 139 training return: tensor(996.7201, device='cuda:0')
epoch: 35 test_true_pfm: -22.928016406558818 sim_pfm: 997.7264746308326
episode: 140 training return: tensor(997.1781, device='cuda:0')
episode: 141 training return: tensor(994.0380, device='cuda:0')
episode: 142 training return: tensor(991.9635, device='cuda:0')
episode: 143 training return: tensor(991.4572, device='cuda:0')
epoch: 36 test_true_pfm: -23.147141127759426 sim_pfm: 995.2030462801456
episode: 144 training return: tensor(990.4753, device='cuda:0')
episode: 145 training return: tensor(988.7720, device='cuda:0')
episode: 146 training return: tensor(988.0214, device='cuda:0')
episode: 147 training return: tensor(990.3557, device='cuda:0')
epoch: 37 test_true_pfm: -16.804298539810183 sim_pfm: 995.0326681017875
episode: 148 training return: tensor(994.3629, device='cuda:0')
episode: 149 training return: tensor(995.0572, device='cuda:0')
episode: 150 training return: tensor(995.6184, device='cuda:0')
episode: 151 training return: tensor(996.7806, device='cuda:0')
epoch: 38 test_true_pfm: -25.144768509066175 sim_pfm: 996.2917448759079
episode: 152 training return: tensor(996.0740, device='cuda:0')
episode: 153 training return: tensor(994.6852, device='cuda:0')
episode: 154 training return: tensor(997.2721, device='cuda:0')
episode: 155 training return: tensor(996.1566, device='cuda:0')
epoch: 39 test_true_pfm: -25.60833299586769 sim_pfm: 997.1984221756459
episode: 156 training return: tensor(997.2597, device='cuda:0')
episode: 157 training return: tensor(997.6887, device='cuda:0')
episode: 158 training return: tensor(997.0337, device='cuda:0')
episode: 159 training return: tensor(997.1154, device='cuda:0')
epoch: 40 test_true_pfm: -24.766145101869704 sim_pfm: 997.0702987968922
episode: 160 training return: tensor(997.7994, device='cuda:0')
episode: 161 training return: tensor(997.1829, device='cuda:0')
episode: 162 training return: tensor(997.8987, device='cuda:0')
episode: 163 training return: tensor(998.1725, device='cuda:0')
epoch: 41 test_true_pfm: -25.377712002297475 sim_pfm: 997.4111035764217
episode: 164 training return: tensor(997.7552, device='cuda:0')
episode: 165 training return: tensor(997.1120, device='cuda:0')
episode: 166 training return: tensor(997.6492, device='cuda:0')
episode: 167 training return: tensor(969.3488, device='cuda:0')
epoch: 42 test_true_pfm: -24.60243813008689 sim_pfm: 996.8148998200893
episode: 168 training return: tensor(995.5954, device='cuda:0')
episode: 169 training return: tensor(996.6713, device='cuda:0')
episode: 170 training return: tensor(997.2834, device='cuda:0')
episode: 171 training return: tensor(997.1112, device='cuda:0')
epoch: 43 test_true_pfm: -22.172908739449312 sim_pfm: 996.3124625146389
episode: 172 training return: tensor(996.4429, device='cuda:0')
episode: 173 training return: tensor(997.5563, device='cuda:0')
episode: 174 training return: tensor(997.6557, device='cuda:0')
episode: 175 training return: tensor(996.8583, device='cuda:0')
epoch: 44 test_true_pfm: -21.76121722357342 sim_pfm: 997.3975379168987
episode: 176 training return: tensor(996.6369, device='cuda:0')
episode: 177 training return: tensor(997.7399, device='cuda:0')
episode: 178 training return: tensor(997.5406, device='cuda:0')
episode: 179 training return: tensor(998.1086, device='cuda:0')
epoch: 45 test_true_pfm: -23.26486965000301 sim_pfm: 997.5445576310158
episode: 180 training return: tensor(996.9209, device='cuda:0')
episode: 181 training return: tensor(995.8475, device='cuda:0')
episode: 182 training return: tensor(997.9100, device='cuda:0')
episode: 183 training return: tensor(996.1899, device='cuda:0')
epoch: 46 test_true_pfm: -22.467447066224462 sim_pfm: 997.0666860580444
episode: 184 training return: tensor(995.6760, device='cuda:0')
episode: 185 training return: tensor(994.9861, device='cuda:0')
episode: 186 training return: tensor(995.2372, device='cuda:0')
episode: 187 training return: tensor(995.7594, device='cuda:0')
epoch: 47 test_true_pfm: -23.762545297616107 sim_pfm: 997.856641280651
episode: 188 training return: tensor(997.2070, device='cuda:0')
episode: 189 training return: tensor(994.3569, device='cuda:0')
episode: 190 training return: tensor(993.9962, device='cuda:0')
episode: 191 training return: tensor(994.6196, device='cuda:0')
epoch: 48 test_true_pfm: -24.37377315832399 sim_pfm: 996.825507503748
episode: 192 training return: tensor(995.9785, device='cuda:0')
episode: 193 training return: tensor(995.0762, device='cuda:0')
episode: 194 training return: tensor(994.6406, device='cuda:0')
episode: 195 training return: tensor(996.3543, device='cuda:0')
epoch: 49 test_true_pfm: -22.523045723098015 sim_pfm: 989.8761377900839
episode: 196 training return: tensor(995.9850, device='cuda:0')
episode: 197 training return: tensor(997.6985, device='cuda:0')
episode: 198 training return: tensor(991.8116, device='cuda:0')
episode: 199 training return: tensor(994.5311, device='cuda:0')
epoch: 50 test_true_pfm: -24.218213436113466 sim_pfm: 995.2767437756062
episode: 200 training return: tensor(991.8481, device='cuda:0')
episode: 201 training return: tensor(989.9390, device='cuda:0')
episode: 202 training return: tensor(990.3481, device='cuda:0')
episode: 203 training return: tensor(994.1271, device='cuda:0')
epoch: 51 test_true_pfm: -14.98210074080833 sim_pfm: 984.1004999637604
episode: 204 training return: tensor(931.6210, device='cuda:0')
episode: 205 training return: tensor(988.1524, device='cuda:0')
episode: 206 training return: tensor(986.3464, device='cuda:0')
episode: 207 training return: tensor(974.0266, device='cuda:0')
epoch: 52 test_true_pfm: -13.333843745373773 sim_pfm: 980.5964384436608
episode: 208 training return: tensor(978.2159, device='cuda:0')
episode: 209 training return: tensor(974.2288, device='cuda:0')
episode: 210 training return: tensor(976.1469, device='cuda:0')
episode: 211 training return: tensor(973.2209, device='cuda:0')
epoch: 53 test_true_pfm: -17.39891287980472 sim_pfm: 980.6130588829517
episode: 212 training return: tensor(975.0557, device='cuda:0')
episode: 213 training return: tensor(996.6789, device='cuda:0')
episode: 214 training return: tensor(996.1771, device='cuda:0')
episode: 215 training return: tensor(996.3834, device='cuda:0')
epoch: 54 test_true_pfm: -27.69395033545233 sim_pfm: 997.0817023336888
episode: 216 training return: tensor(996.7123, device='cuda:0')
episode: 217 training return: tensor(995.7429, device='cuda:0')
episode: 218 training return: tensor(996.5137, device='cuda:0')
episode: 219 training return: tensor(995.7744, device='cuda:0')
epoch: 55 test_true_pfm: -24.481664926171817 sim_pfm: 997.2633485198021
episode: 220 training return: tensor(996.9476, device='cuda:0')
episode: 221 training return: tensor(996.7469, device='cuda:0')
episode: 222 training return: tensor(996.3445, device='cuda:0')
episode: 223 training return: tensor(994.9422, device='cuda:0')
epoch: 56 test_true_pfm: -26.841577084908852 sim_pfm: 997.094723033905
episode: 224 training return: tensor(996.1224, device='cuda:0')
episode: 225 training return: tensor(995.7581, device='cuda:0')
episode: 226 training return: tensor(990.3973, device='cuda:0')
episode: 227 training return: tensor(994.9950, device='cuda:0')
epoch: 57 test_true_pfm: -23.802102897157447 sim_pfm: 996.7075580358505
episode: 228 training return: tensor(985.0964, device='cuda:0')
episode: 229 training return: tensor(987.4792, device='cuda:0')
episode: 230 training return: tensor(988.5722, device='cuda:0')
episode: 231 training return: tensor(989.4362, device='cuda:0')
epoch: 58 test_true_pfm: -19.25803718325 sim_pfm: 992.6782478809357
episode: 232 training return: tensor(990.0476, device='cuda:0')
episode: 233 training return: tensor(992.8138, device='cuda:0')
episode: 234 training return: tensor(953.2241, device='cuda:0')
episode: 235 training return: tensor(994.1564, device='cuda:0')
epoch: 59 test_true_pfm: -21.23340749800197 sim_pfm: 995.5974575400353
episode: 236 training return: tensor(995.7867, device='cuda:0')
episode: 237 training return: tensor(997.2124, device='cuda:0')
episode: 238 training return: tensor(997.2564, device='cuda:0')
episode: 239 training return: tensor(994.9185, device='cuda:0')
epoch: 60 test_true_pfm: -27.290182916538434 sim_pfm: 996.8352890640497
episode: 240 training return: tensor(996.4747, device='cuda:0')
episode: 241 training return: tensor(995.9960, device='cuda:0')
episode: 242 training return: tensor(995.1068, device='cuda:0')
episode: 243 training return: tensor(995.0444, device='cuda:0')
epoch: 61 test_true_pfm: -22.718420021982784 sim_pfm: 996.9282524049282
episode: 244 training return: tensor(995.6750, device='cuda:0')
episode: 245 training return: tensor(997.0896, device='cuda:0')
episode: 246 training return: tensor(997.4211, device='cuda:0')
episode: 247 training return: tensor(992.6361, device='cuda:0')
epoch: 62 test_true_pfm: -22.820927275141425 sim_pfm: 997.4575001001358
episode: 248 training return: tensor(996.6196, device='cuda:0')
episode: 249 training return: tensor(996.6037, device='cuda:0')
episode: 250 training return: tensor(996.5543, device='cuda:0')
episode: 251 training return: tensor(989.3114, device='cuda:0')
epoch: 63 test_true_pfm: -9.961657781042273 sim_pfm: 971.8527968645096
episode: 252 training return: tensor(969.3343, device='cuda:0')
episode: 253 training return: tensor(939.0482, device='cuda:0')
episode: 254 training return: tensor(996.3679, device='cuda:0')
episode: 255 training return: tensor(997.6407, device='cuda:0')
epoch: 64 test_true_pfm: -23.887302308192755 sim_pfm: 997.8910292327404
episode: 256 training return: tensor(997.7374, device='cuda:0')
episode: 257 training return: tensor(998.0620, device='cuda:0')
episode: 258 training return: tensor(997.5281, device='cuda:0')
episode: 259 training return: tensor(997.8491, device='cuda:0')
epoch: 65 test_true_pfm: -23.09480200066802 sim_pfm: 997.0035680890084
episode: 260 training return: tensor(997.1058, device='cuda:0')
episode: 261 training return: tensor(997.3782, device='cuda:0')
episode: 262 training return: tensor(997.5773, device='cuda:0')
episode: 263 training return: tensor(997.9512, device='cuda:0')
epoch: 66 test_true_pfm: -25.39889367028387 sim_pfm: 997.5418497145176
episode: 264 training return: tensor(997.2175, device='cuda:0')
episode: 265 training return: tensor(997.4363, device='cuda:0')
episode: 266 training return: tensor(997.2366, device='cuda:0')
episode: 267 training return: tensor(997.3230, device='cuda:0')
epoch: 67 test_true_pfm: -23.041947792655662 sim_pfm: 997.8906755030155
episode: 268 training return: tensor(997.1101, device='cuda:0')
episode: 269 training return: tensor(996.0436, device='cuda:0')
episode: 270 training return: tensor(997.0028, device='cuda:0')
episode: 271 training return: tensor(997.2917, device='cuda:0')
epoch: 68 test_true_pfm: -21.48084432239105 sim_pfm: 997.4706592381001
episode: 272 training return: tensor(997.6349, device='cuda:0')
episode: 273 training return: tensor(997.1147, device='cuda:0')
episode: 274 training return: tensor(995.8320, device='cuda:0')
episode: 275 training return: tensor(996.8910, device='cuda:0')
epoch: 69 test_true_pfm: -23.966682278742642 sim_pfm: 996.6682501196861
episode: 276 training return: tensor(996.5349, device='cuda:0')
episode: 277 training return: tensor(995.6246, device='cuda:0')
episode: 278 training return: tensor(993.7169, device='cuda:0')
episode: 279 training return: tensor(994.9611, device='cuda:0')
epoch: 70 test_true_pfm: -25.867505465110707 sim_pfm: 996.7976739108562
episode: 280 training return: tensor(995.0197, device='cuda:0')
episode: 281 training return: tensor(996.2266, device='cuda:0')
episode: 282 training return: tensor(995.0972, device='cuda:0')
episode: 283 training return: tensor(995.8875, device='cuda:0')
epoch: 71 test_true_pfm: -25.431874181204407 sim_pfm: 997.7503214538098
episode: 284 training return: tensor(998.0452, device='cuda:0')
episode: 285 training return: tensor(996.3979, device='cuda:0')
episode: 286 training return: tensor(997.2405, device='cuda:0')
episode: 287 training return: tensor(986.1830, device='cuda:0')
epoch: 72 test_true_pfm: -25.53499082853138 sim_pfm: 997.0945771217346
episode: 288 training return: tensor(997.5408, device='cuda:0')
episode: 289 training return: tensor(996.8356, device='cuda:0')
episode: 290 training return: tensor(997.6205, device='cuda:0')
episode: 291 training return: tensor(996.3732, device='cuda:0')
epoch: 73 test_true_pfm: -23.814167222006496 sim_pfm: 997.3190400898457
episode: 292 training return: tensor(993.2207, device='cuda:0')
episode: 293 training return: tensor(997.7889, device='cuda:0')
episode: 294 training return: tensor(997.1675, device='cuda:0')
episode: 295 training return: tensor(996.8121, device='cuda:0')
epoch: 74 test_true_pfm: -23.64109201073328 sim_pfm: 996.793496119976
episode: 296 training return: tensor(995.6805, device='cuda:0')
episode: 297 training return: tensor(991.8813, device='cuda:0')
episode: 298 training return: tensor(995.8099, device='cuda:0')
episode: 299 training return: tensor(996.1724, device='cuda:0')
epoch: 75 test_true_pfm: -27.36341045226568 sim_pfm: 997.1546874582767
episode: 300 training return: tensor(996.5480, device='cuda:0')
episode: 301 training return: tensor(997.3493, device='cuda:0')
episode: 302 training return: tensor(994.8954, device='cuda:0')
episode: 303 training return: tensor(996.9584, device='cuda:0')
epoch: 76 test_true_pfm: -22.98588318883112 sim_pfm: 997.6120823085308
episode: 304 training return: tensor(997.1586, device='cuda:0')
episode: 305 training return: tensor(996.2382, device='cuda:0')
episode: 306 training return: tensor(995.5162, device='cuda:0')
episode: 307 training return: tensor(992.5276, device='cuda:0')
epoch: 77 test_true_pfm: -23.151765654316385 sim_pfm: 996.59820291996
episode: 308 training return: tensor(996.3920, device='cuda:0')
episode: 309 training return: tensor(997.0073, device='cuda:0')
episode: 310 training return: tensor(994.1053, device='cuda:0')
episode: 311 training return: tensor(991.7190, device='cuda:0')
epoch: 78 test_true_pfm: -24.97092325526731 sim_pfm: 993.6354610085488
episode: 312 training return: tensor(994.8796, device='cuda:0')
episode: 313 training return: tensor(996.3076, device='cuda:0')
episode: 314 training return: tensor(996.3461, device='cuda:0')
episode: 315 training return: tensor(995.7939, device='cuda:0')
epoch: 79 test_true_pfm: -22.544503330341904 sim_pfm: 997.4954933583737
episode: 316 training return: tensor(997.4355, device='cuda:0')
episode: 317 training return: tensor(997.2480, device='cuda:0')
episode: 318 training return: tensor(995.9625, device='cuda:0')
episode: 319 training return: tensor(997.5632, device='cuda:0')
epoch: 80 test_true_pfm: -24.91825130452235 sim_pfm: 998.0611401319504
episode: 320 training return: tensor(997.9547, device='cuda:0')
episode: 321 training return: tensor(997.8524, device='cuda:0')
episode: 322 training return: tensor(997.6944, device='cuda:0')
episode: 323 training return: tensor(996.6508, device='cuda:0')
epoch: 81 test_true_pfm: -23.47776183820718 sim_pfm: 996.4750626444817
episode: 324 training return: tensor(996.0530, device='cuda:0')
episode: 325 training return: tensor(991.6395, device='cuda:0')
episode: 326 training return: tensor(995.3630, device='cuda:0')
episode: 327 training return: tensor(967.2238, device='cuda:0')
epoch: 82 test_true_pfm: -19.3903286389387 sim_pfm: 989.0990567028523
episode: 328 training return: tensor(996.8549, device='cuda:0')
episode: 329 training return: tensor(997.3535, device='cuda:0')
episode: 330 training return: tensor(996.4429, device='cuda:0')
episode: 331 training return: tensor(997.5324, device='cuda:0')
epoch: 83 test_true_pfm: -22.197767849878865 sim_pfm: 997.2458333730698
episode: 332 training return: tensor(997.3299, device='cuda:0')
episode: 333 training return: tensor(995.9597, device='cuda:0')
episode: 334 training return: tensor(997.1390, device='cuda:0')
episode: 335 training return: tensor(996.6176, device='cuda:0')
epoch: 84 test_true_pfm: -21.466976640335496 sim_pfm: 996.0643101036549
episode: 336 training return: tensor(996.5095, device='cuda:0')
episode: 337 training return: tensor(994.7974, device='cuda:0')
episode: 338 training return: tensor(992.2678, device='cuda:0')
episode: 339 training return: tensor(995.8791, device='cuda:0')
epoch: 85 test_true_pfm: -20.191898066246797 sim_pfm: 995.9575888931752
episode: 340 training return: tensor(995.7350, device='cuda:0')
episode: 341 training return: tensor(994.2111, device='cuda:0')
episode: 342 training return: tensor(992.6283, device='cuda:0')
episode: 343 training return: tensor(996.3947, device='cuda:0')
epoch: 86 test_true_pfm: -20.554746610815627 sim_pfm: 994.8340908169746
episode: 344 training return: tensor(992.9807, device='cuda:0')
episode: 345 training return: tensor(987.5064, device='cuda:0')
episode: 346 training return: tensor(991.8051, device='cuda:0')
episode: 347 training return: tensor(994.7028, device='cuda:0')
epoch: 87 test_true_pfm: -25.438904710881694 sim_pfm: 996.7814191043377
episode: 348 training return: tensor(987.5700, device='cuda:0')
episode: 349 training return: tensor(985.6352, device='cuda:0')
episode: 350 training return: tensor(996.4665, device='cuda:0')
episode: 351 training return: tensor(995.1717, device='cuda:0')
epoch: 88 test_true_pfm: -24.436189064631336 sim_pfm: 996.6920245170593
episode: 352 training return: tensor(997.5001, device='cuda:0')
episode: 353 training return: tensor(993.7113, device='cuda:0')
episode: 354 training return: tensor(989.6216, device='cuda:0')
episode: 355 training return: tensor(996.5601, device='cuda:0')
epoch: 89 test_true_pfm: -22.069880919509625 sim_pfm: 993.7191432774067
episode: 356 training return: tensor(994.0050, device='cuda:0')
episode: 357 training return: tensor(994.9365, device='cuda:0')
episode: 358 training return: tensor(993.2186, device='cuda:0')
episode: 359 training return: tensor(997.3744, device='cuda:0')
epoch: 90 test_true_pfm: -20.57550380144793 sim_pfm: 996.1876274824142
episode: 360 training return: tensor(994.6550, device='cuda:0')
episode: 361 training return: tensor(989.2289, device='cuda:0')
episode: 362 training return: tensor(997.0995, device='cuda:0')
episode: 363 training return: tensor(996.8725, device='cuda:0')
epoch: 91 test_true_pfm: -21.104551486489118 sim_pfm: 997.4300026953221
episode: 364 training return: tensor(996.8723, device='cuda:0')
episode: 365 training return: tensor(995.0262, device='cuda:0')
episode: 366 training return: tensor(996.8034, device='cuda:0')
episode: 367 training return: tensor(997.4953, device='cuda:0')
epoch: 92 test_true_pfm: -24.965331183443517 sim_pfm: 997.4506527900696
episode: 368 training return: tensor(996.5966, device='cuda:0')
episode: 369 training return: tensor(996.7781, device='cuda:0')
episode: 370 training return: tensor(996.4406, device='cuda:0')
episode: 371 training return: tensor(996.1298, device='cuda:0')
epoch: 93 test_true_pfm: -23.39146566961769 sim_pfm: 995.4743738532067
episode: 372 training return: tensor(995.4492, device='cuda:0')
episode: 373 training return: tensor(993.7529, device='cuda:0')
episode: 374 training return: tensor(996.3396, device='cuda:0')
episode: 375 training return: tensor(997.1082, device='cuda:0')
epoch: 94 test_true_pfm: -24.416987535171195 sim_pfm: 996.7025161743164
episode: 376 training return: tensor(990.5675, device='cuda:0')
episode: 377 training return: tensor(997.9163, device='cuda:0')
episode: 378 training return: tensor(997.3640, device='cuda:0')
episode: 379 training return: tensor(997.9097, device='cuda:0')
epoch: 95 test_true_pfm: -20.34164506795392 sim_pfm: 996.5048104405403
episode: 380 training return: tensor(996.4180, device='cuda:0')
episode: 381 training return: tensor(996.4371, device='cuda:0')
episode: 382 training return: tensor(997.7652, device='cuda:0')
episode: 383 training return: tensor(993.9771, device='cuda:0')
epoch: 96 test_true_pfm: -22.873663884575443 sim_pfm: 997.121478676796
episode: 384 training return: tensor(997.5934, device='cuda:0')
episode: 385 training return: tensor(997.2947, device='cuda:0')
episode: 386 training return: tensor(997.0491, device='cuda:0')
episode: 387 training return: tensor(997.8190, device='cuda:0')
epoch: 97 test_true_pfm: -24.465297098391517 sim_pfm: 997.6249353349209
episode: 388 training return: tensor(997.4022, device='cuda:0')
episode: 389 training return: tensor(996.1878, device='cuda:0')
episode: 390 training return: tensor(997.6057, device='cuda:0')
episode: 391 training return: tensor(992.6283, device='cuda:0')
epoch: 98 test_true_pfm: -16.026175953904268 sim_pfm: 989.9878951489925
episode: 392 training return: tensor(992.3723, device='cuda:0')
episode: 393 training return: tensor(974.2559, device='cuda:0')
episode: 394 training return: tensor(996.9866, device='cuda:0')
episode: 395 training return: tensor(651.3943, device='cuda:0')
epoch: 99 test_true_pfm: -20.427339955718764 sim_pfm: 969.736351197958
episode: 396 training return: tensor(947.3589, device='cuda:0')
episode: 397 training return: tensor(911.9309, device='cuda:0')
episode: 398 training return: tensor(887.9760, device='cuda:0')
episode: 399 training return: tensor(950.4612, device='cuda:0')
epoch: 100 test_true_pfm: -22.545065270197917 sim_pfm: 988.8014503479004
episode: 400 training return: tensor(983.7504, device='cuda:0')
episode: 401 training return: tensor(973.0083, device='cuda:0')
episode: 402 training return: tensor(977.8716, device='cuda:0')
episode: 403 training return: tensor(972.5757, device='cuda:0')
epoch: 101 test_true_pfm: -23.17741184998085 sim_pfm: 976.5575170397758
episode: 404 training return: tensor(964.5836, device='cuda:0')
episode: 405 training return: tensor(971.6221, device='cuda:0')
episode: 406 training return: tensor(973.5200, device='cuda:0')
episode: 407 training return: tensor(973.2252, device='cuda:0')
epoch: 102 test_true_pfm: -21.65612228417427 sim_pfm: 974.8291007578373
episode: 408 training return: tensor(971.0057, device='cuda:0')
episode: 409 training return: tensor(986.0735, device='cuda:0')
episode: 410 training return: tensor(994.8982, device='cuda:0')
episode: 411 training return: tensor(994.8509, device='cuda:0')
epoch: 103 test_true_pfm: -20.185815695197252 sim_pfm: 996.3275260597468
episode: 412 training return: tensor(991.7219, device='cuda:0')
episode: 413 training return: tensor(982.9301, device='cuda:0')
episode: 414 training return: tensor(983.2824, device='cuda:0')
episode: 415 training return: tensor(984.9963, device='cuda:0')
epoch: 104 test_true_pfm: -22.798238943205185 sim_pfm: 989.2230046838522
episode: 416 training return: tensor(983.0121, device='cuda:0')
episode: 417 training return: tensor(981.0820, device='cuda:0')
episode: 418 training return: tensor(979.3060, device='cuda:0')
episode: 419 training return: tensor(980.7510, device='cuda:0')
epoch: 105 test_true_pfm: -23.28746190699574 sim_pfm: 986.5599559307099
episode: 420 training return: tensor(981.5255, device='cuda:0')
episode: 421 training return: tensor(984.6970, device='cuda:0')
episode: 422 training return: tensor(985.4382, device='cuda:0')
episode: 423 training return: tensor(979.8608, device='cuda:0')
epoch: 106 test_true_pfm: -23.26519017968716 sim_pfm: 992.1867251634598
episode: 424 training return: tensor(978.6849, device='cuda:0')
episode: 425 training return: tensor(985.5491, device='cuda:0')
episode: 426 training return: tensor(985.2595, device='cuda:0')
episode: 427 training return: tensor(988.6886, device='cuda:0')
epoch: 107 test_true_pfm: -26.526883302164343 sim_pfm: 991.8510042645037
episode: 428 training return: tensor(967.4368, device='cuda:0')
episode: 429 training return: tensor(993.6612, device='cuda:0')
episode: 430 training return: tensor(911.6657, device='cuda:0')
episode: 431 training return: tensor(995.1636, device='cuda:0')
epoch: 108 test_true_pfm: -21.48531248273097 sim_pfm: 995.962952965498
episode: 432 training return: tensor(937.1931, device='cuda:0')
episode: 433 training return: tensor(989.4689, device='cuda:0')
episode: 434 training return: tensor(985.0026, device='cuda:0')
episode: 435 training return: tensor(986.5503, device='cuda:0')
epoch: 109 test_true_pfm: -24.45215980025761 sim_pfm: 988.1418582081794
episode: 436 training return: tensor(987.8230, device='cuda:0')
episode: 437 training return: tensor(987.8633, device='cuda:0')
episode: 438 training return: tensor(991.5941, device='cuda:0')
episode: 439 training return: tensor(989.3452, device='cuda:0')
epoch: 110 test_true_pfm: -23.890255507597452 sim_pfm: 993.5748360991478
episode: 440 training return: tensor(991.5281, device='cuda:0')
episode: 441 training return: tensor(990.2147, device='cuda:0')
episode: 442 training return: tensor(993.8755, device='cuda:0')
episode: 443 training return: tensor(960.0551, device='cuda:0')
epoch: 111 test_true_pfm: -13.408355243853526 sim_pfm: 960.3338059902192
episode: 444 training return: tensor(938.3277, device='cuda:0')
episode: 445 training return: tensor(983.1694, device='cuda:0')
episode: 446 training return: tensor(996.7245, device='cuda:0')
episode: 447 training return: tensor(997.8144, device='cuda:0')
epoch: 112 test_true_pfm: -21.52001729669957 sim_pfm: 997.6151249408722
episode: 448 training return: tensor(997.2025, device='cuda:0')
episode: 449 training return: tensor(998.0081, device='cuda:0')
episode: 450 training return: tensor(994.7731, device='cuda:0')
episode: 451 training return: tensor(992.3424, device='cuda:0')
epoch: 113 test_true_pfm: -23.99453485916369 sim_pfm: 994.1766222715378
episode: 452 training return: tensor(987.8217, device='cuda:0')
episode: 453 training return: tensor(991.4260, device='cuda:0')
episode: 454 training return: tensor(991.2985, device='cuda:0')
episode: 455 training return: tensor(987.9113, device='cuda:0')
epoch: 114 test_true_pfm: -22.32833926237124 sim_pfm: 994.2776082277298
episode: 456 training return: tensor(985.8149, device='cuda:0')
episode: 457 training return: tensor(993.4332, device='cuda:0')
episode: 458 training return: tensor(989.6744, device='cuda:0')
episode: 459 training return: tensor(971.2124, device='cuda:0')
epoch: 115 test_true_pfm: -22.499397770954243 sim_pfm: 985.4808724820614
episode: 460 training return: tensor(966.3727, device='cuda:0')
episode: 461 training return: tensor(973.9229, device='cuda:0')
episode: 462 training return: tensor(973.8311, device='cuda:0')
episode: 463 training return: tensor(969.6749, device='cuda:0')
epoch: 116 test_true_pfm: -21.895783017646306 sim_pfm: 978.8040126681328
episode: 464 training return: tensor(978.4199, device='cuda:0')
episode: 465 training return: tensor(973.2079, device='cuda:0')
episode: 466 training return: tensor(970.8273, device='cuda:0')
episode: 467 training return: tensor(978.0143, device='cuda:0')
epoch: 117 test_true_pfm: -25.631808477488374 sim_pfm: 980.0933143943548
episode: 468 training return: tensor(984.7528, device='cuda:0')
episode: 469 training return: tensor(980.3454, device='cuda:0')
episode: 470 training return: tensor(980.2525, device='cuda:0')
episode: 471 training return: tensor(980.5599, device='cuda:0')
epoch: 118 test_true_pfm: -25.356513326423734 sim_pfm: 988.08383628726
episode: 472 training return: tensor(984.2015, device='cuda:0')
episode: 473 training return: tensor(981.9965, device='cuda:0')
episode: 474 training return: tensor(984.6880, device='cuda:0')
episode: 475 training return: tensor(984.9220, device='cuda:0')
epoch: 119 test_true_pfm: -23.042016972330355 sim_pfm: 988.6994121588766
episode: 476 training return: tensor(984.7205, device='cuda:0')
episode: 477 training return: tensor(895.7379, device='cuda:0')
episode: 478 training return: tensor(985.4118, device='cuda:0')
episode: 479 training return: tensor(953.9781, device='cuda:0')
epoch: 120 test_true_pfm: -12.276245446664287 sim_pfm: 965.9176438391208
episode: 480 training return: tensor(958.3495, device='cuda:0')
episode: 481 training return: tensor(967.2906, device='cuda:0')
episode: 482 training return: tensor(986.0575, device='cuda:0')
episode: 483 training return: tensor(982.8476, device='cuda:0')
epoch: 121 test_true_pfm: -20.286622574067508 sim_pfm: 986.253474187851
episode: 484 training return: tensor(927.6713, device='cuda:0')
episode: 485 training return: tensor(978.4395, device='cuda:0')
episode: 486 training return: tensor(972.4948, device='cuda:0')
episode: 487 training return: tensor(975.4432, device='cuda:0')
epoch: 122 test_true_pfm: -23.900904748759825 sim_pfm: 981.6703573524952
episode: 488 training return: tensor(991.0869, device='cuda:0')
episode: 489 training return: tensor(993.9599, device='cuda:0')
episode: 490 training return: tensor(991.8101, device='cuda:0')
episode: 491 training return: tensor(995.6844, device='cuda:0')
epoch: 123 test_true_pfm: -13.473429101840717 sim_pfm: 986.6497318714858
episode: 492 training return: tensor(996.6923, device='cuda:0')
episode: 493 training return: tensor(997.2748, device='cuda:0')
episode: 494 training return: tensor(974.4957, device='cuda:0')
episode: 495 training return: tensor(996.6334, device='cuda:0')
epoch: 124 test_true_pfm: -25.157902872184312 sim_pfm: 997.4490320503712
episode: 496 training return: tensor(995.1868, device='cuda:0')
episode: 497 training return: tensor(988.9629, device='cuda:0')
episode: 498 training return: tensor(991.1011, device='cuda:0')
episode: 499 training return: tensor(992.1271, device='cuda:0')
epoch: 125 test_true_pfm: -23.122703681154483 sim_pfm: 994.9930639326573
episode: 500 training return: tensor(995.3259, device='cuda:0')
episode: 501 training return: tensor(992.2621, device='cuda:0')
episode: 502 training return: tensor(991.7697, device='cuda:0')
episode: 503 training return: tensor(989.4216, device='cuda:0')
epoch: 126 test_true_pfm: -23.46341559419355 sim_pfm: 995.6659048557282
episode: 504 training return: tensor(995.0750, device='cuda:0')
episode: 505 training return: tensor(994.9304, device='cuda:0')
episode: 506 training return: tensor(995.5533, device='cuda:0')
episode: 507 training return: tensor(986.2586, device='cuda:0')
epoch: 127 test_true_pfm: -20.238936007802238 sim_pfm: 995.533797544241
episode: 508 training return: tensor(996.4387, device='cuda:0')
episode: 509 training return: tensor(995.3842, device='cuda:0')
episode: 510 training return: tensor(995.2149, device='cuda:0')
episode: 511 training return: tensor(995.4987, device='cuda:0')
epoch: 128 test_true_pfm: -20.914612642591386 sim_pfm: 993.8542922496796
episode: 512 training return: tensor(985.2538, device='cuda:0')
episode: 513 training return: tensor(971.0726, device='cuda:0')
episode: 514 training return: tensor(973.6844, device='cuda:0')
episode: 515 training return: tensor(986.7453, device='cuda:0')
epoch: 129 test_true_pfm: -9.21403668871771 sim_pfm: 565.5516509814013
episode: 516 training return: tensor(509.7350, device='cuda:0')
episode: 517 training return: tensor(859.4863, device='cuda:0')
episode: 518 training return: tensor(973.4297, device='cuda:0')
episode: 519 training return: tensor(984.4333, device='cuda:0')
epoch: 130 test_true_pfm: -25.040058295787535 sim_pfm: 984.9451917529107
episode: 520 training return: tensor(983.3869, device='cuda:0')
episode: 521 training return: tensor(976.4665, device='cuda:0')
episode: 522 training return: tensor(978.5856, device='cuda:0')
episode: 523 training return: tensor(979.7809, device='cuda:0')
epoch: 131 test_true_pfm: -23.022998701576434 sim_pfm: 989.953171363473
episode: 524 training return: tensor(979.7899, device='cuda:0')
episode: 525 training return: tensor(982.4218, device='cuda:0')
episode: 526 training return: tensor(981.1542, device='cuda:0')
episode: 527 training return: tensor(987.8782, device='cuda:0')
epoch: 132 test_true_pfm: -23.779239406701983 sim_pfm: 993.2362234055996
episode: 528 training return: tensor(993.5274, device='cuda:0')
episode: 529 training return: tensor(976.6906, device='cuda:0')
episode: 530 training return: tensor(976.1824, device='cuda:0')
episode: 531 training return: tensor(971.8911, device='cuda:0')
epoch: 133 test_true_pfm: -13.827667802861683 sim_pfm: 983.3440001130105
episode: 532 training return: tensor(980.6235, device='cuda:0')
episode: 533 training return: tensor(982.4933, device='cuda:0')
episode: 534 training return: tensor(996.7601, device='cuda:0')
episode: 535 training return: tensor(995.1431, device='cuda:0')
epoch: 134 test_true_pfm: -11.764538478996698 sim_pfm: 991.3702920794487
episode: 536 training return: tensor(983.8047, device='cuda:0')
episode: 537 training return: tensor(974.7048, device='cuda:0')
episode: 538 training return: tensor(987.8983, device='cuda:0')
episode: 539 training return: tensor(995.8639, device='cuda:0')
epoch: 135 test_true_pfm: -18.439973371317954 sim_pfm: 996.7915362775326
episode: 540 training return: tensor(993.4512, device='cuda:0')
episode: 541 training return: tensor(992.8328, device='cuda:0')
episode: 542 training return: tensor(996.2258, device='cuda:0')
episode: 543 training return: tensor(997.2522, device='cuda:0')
epoch: 136 test_true_pfm: -17.492755363617484 sim_pfm: 995.7430690199137
episode: 544 training return: tensor(991.3572, device='cuda:0')
episode: 545 training return: tensor(990.9208, device='cuda:0')
episode: 546 training return: tensor(996.9282, device='cuda:0')
episode: 547 training return: tensor(996.6888, device='cuda:0')
epoch: 137 test_true_pfm: -17.093451278247496 sim_pfm: 996.6739756703377
episode: 548 training return: tensor(995.8052, device='cuda:0')
episode: 549 training return: tensor(988.8160, device='cuda:0')
episode: 550 training return: tensor(992.1784, device='cuda:0')
episode: 551 training return: tensor(995.5530, device='cuda:0')
epoch: 138 test_true_pfm: -16.70822908913525 sim_pfm: 976.249338978529
episode: 552 training return: tensor(990.9835, device='cuda:0')
episode: 553 training return: tensor(987.7505, device='cuda:0')
episode: 554 training return: tensor(988.5010, device='cuda:0')
episode: 555 training return: tensor(986.4647, device='cuda:0')
epoch: 139 test_true_pfm: -17.029661144678723 sim_pfm: 993.8598716259003
episode: 556 training return: tensor(994.2611, device='cuda:0')
episode: 557 training return: tensor(995.4724, device='cuda:0')
episode: 558 training return: tensor(989.5684, device='cuda:0')
episode: 559 training return: tensor(984.3992, device='cuda:0')
epoch: 140 test_true_pfm: -21.281340176717826 sim_pfm: 982.2011117041111
episode: 560 training return: tensor(990.2982, device='cuda:0')
episode: 561 training return: tensor(984.4344, device='cuda:0')
episode: 562 training return: tensor(989.3383, device='cuda:0')
episode: 563 training return: tensor(985.2758, device='cuda:0')
epoch: 141 test_true_pfm: -21.365787488596222 sim_pfm: 993.1760991215706
episode: 564 training return: tensor(977.2877, device='cuda:0')
episode: 565 training return: tensor(981.3890, device='cuda:0')
episode: 566 training return: tensor(988.3531, device='cuda:0')
episode: 567 training return: tensor(975.8698, device='cuda:0')
epoch: 142 test_true_pfm: -16.646681427007916 sim_pfm: 987.1708113908768
episode: 568 training return: tensor(986.7256, device='cuda:0')
episode: 569 training return: tensor(985.4855, device='cuda:0')
episode: 570 training return: tensor(984.2050, device='cuda:0')
episode: 571 training return: tensor(988.3746, device='cuda:0')
epoch: 143 test_true_pfm: -20.802083212978424 sim_pfm: 993.3365295410156
episode: 572 training return: tensor(988.9070, device='cuda:0')
episode: 573 training return: tensor(990.8599, device='cuda:0')
episode: 574 training return: tensor(994.0477, device='cuda:0')
episode: 575 training return: tensor(989.1378, device='cuda:0')
epoch: 144 test_true_pfm: -11.343519720261536 sim_pfm: 993.0979972600937
episode: 576 training return: tensor(994.2466, device='cuda:0')
episode: 577 training return: tensor(995.1613, device='cuda:0')
episode: 578 training return: tensor(996.6408, device='cuda:0')
episode: 579 training return: tensor(996.1812, device='cuda:0')
epoch: 145 test_true_pfm: -19.436283065761614 sim_pfm: 995.8544811248779
episode: 580 training return: tensor(996.2931, device='cuda:0')
episode: 581 training return: tensor(995.8908, device='cuda:0')
episode: 582 training return: tensor(979.7242, device='cuda:0')
episode: 583 training return: tensor(996.5791, device='cuda:0')
epoch: 146 test_true_pfm: -24.80978206161228 sim_pfm: 997.7308493316174
episode: 584 training return: tensor(996.3156, device='cuda:0')
episode: 585 training return: tensor(997.8439, device='cuda:0')
episode: 586 training return: tensor(996.0894, device='cuda:0')
episode: 587 training return: tensor(997.3523, device='cuda:0')
epoch: 147 test_true_pfm: -16.976265991294593 sim_pfm: 996.8245246469975
episode: 588 training return: tensor(995.2204, device='cuda:0')
episode: 589 training return: tensor(997.2367, device='cuda:0')
episode: 590 training return: tensor(996.9318, device='cuda:0')
episode: 591 training return: tensor(996.1309, device='cuda:0')
epoch: 148 test_true_pfm: -20.129688807818674 sim_pfm: 996.2729974448681
episode: 592 training return: tensor(995.5778, device='cuda:0')
episode: 593 training return: tensor(996.5414, device='cuda:0')
episode: 594 training return: tensor(996.7620, device='cuda:0')
episode: 595 training return: tensor(996.0757, device='cuda:0')
epoch: 149 test_true_pfm: -19.231771127974632 sim_pfm: 997.729497128725
episode: 596 training return: tensor(994.4518, device='cuda:0')
episode: 597 training return: tensor(994.4261, device='cuda:0')
episode: 598 training return: tensor(995.6816, device='cuda:0')
episode: 599 training return: tensor(997.4412, device='cuda:0')
epoch: 150 test_true_pfm: -17.73972748806623 sim_pfm: 996.4103924870491
