['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'baseline', '--traj', 'expert', '--seed', '2']
episode: 0 training return: tensor(-930.0156, device='cuda:0')
episode: 1 training return: tensor(-872.7469, device='cuda:0')
episode: 2 training return: tensor(-957.6701, device='cuda:0')
episode: 3 training return: tensor(-939.4556, device='cuda:0')
epoch: 1 test_true_pfm: -81.7805924189223 sim_pfm: -886.1693956851959
episode: 4 training return: tensor(-909.1331, device='cuda:0')
episode: 5 training return: tensor(-838.2697, device='cuda:0')
episode: 6 training return: tensor(-924.0759, device='cuda:0')
episode: 7 training return: tensor(-911.8900, device='cuda:0')
epoch: 2 test_true_pfm: -98.68358911601912 sim_pfm: -958.2932872672876
episode: 8 training return: tensor(-883.5121, device='cuda:0')
episode: 9 training return: tensor(-952.6949, device='cuda:0')
episode: 10 training return: tensor(-910.6456, device='cuda:0')
episode: 11 training return: tensor(-921.9540, device='cuda:0')
epoch: 3 test_true_pfm: 95.64221450668613 sim_pfm: -884.5408535078168
episode: 12 training return: tensor(-922.8370, device='cuda:0')
episode: 13 training return: tensor(-904.9944, device='cuda:0')
episode: 14 training return: tensor(-805.1147, device='cuda:0')
episode: 15 training return: tensor(-900.9797, device='cuda:0')
epoch: 4 test_true_pfm: 35.294933235058465 sim_pfm: -902.141132692496
episode: 16 training return: tensor(-922.5408, device='cuda:0')
episode: 17 training return: tensor(-927.1050, device='cuda:0')
episode: 18 training return: tensor(-917.1853, device='cuda:0')
episode: 19 training return: tensor(-924.7993, device='cuda:0')
epoch: 5 test_true_pfm: -23.945826033272454 sim_pfm: -921.6163539389769
episode: 20 training return: tensor(-921.0706, device='cuda:0')
episode: 21 training return: tensor(-919.9424, device='cuda:0')
episode: 22 training return: tensor(-911.6377, device='cuda:0')
episode: 23 training return: tensor(-838.6949, device='cuda:0')
epoch: 6 test_true_pfm: 460.30780251586884 sim_pfm: -744.1487949224926
episode: 24 training return: tensor(-898.8574, device='cuda:0')
episode: 25 training return: tensor(-955.4065, device='cuda:0')
episode: 26 training return: tensor(-957.3410, device='cuda:0')
episode: 27 training return: tensor(-916.4772, device='cuda:0')
epoch: 7 test_true_pfm: 66.73152702597118 sim_pfm: -921.3101331057647
episode: 28 training return: tensor(-944.3813, device='cuda:0')
episode: 29 training return: tensor(-891.2230, device='cuda:0')
episode: 30 training return: tensor(-900.1090, device='cuda:0')
episode: 31 training return: tensor(-776.7767, device='cuda:0')
epoch: 8 test_true_pfm: 49.063054011684784 sim_pfm: -706.7503225154554
episode: 32 training return: tensor(-905.8876, device='cuda:0')
episode: 33 training return: tensor(-803.9138, device='cuda:0')
episode: 34 training return: tensor(-852.4001, device='cuda:0')
episode: 35 training return: tensor(-875.5661, device='cuda:0')
epoch: 9 test_true_pfm: 233.21992539207815 sim_pfm: -869.8674321734192
episode: 36 training return: tensor(-685.2819, device='cuda:0')
episode: 37 training return: tensor(-861.5454, device='cuda:0')
episode: 38 training return: tensor(-765.9432, device='cuda:0')
episode: 39 training return: tensor(-710.6102, device='cuda:0')
epoch: 10 test_true_pfm: 111.59068236867627 sim_pfm: -813.8968508642478
episode: 40 training return: tensor(-832.1602, device='cuda:0')
episode: 41 training return: tensor(-807.9579, device='cuda:0')
episode: 42 training return: tensor(-787.9343, device='cuda:0')
episode: 43 training return: tensor(-889.3013, device='cuda:0')
epoch: 11 test_true_pfm: -7.615833380911165 sim_pfm: -779.464507249184
episode: 44 training return: tensor(-842.6496, device='cuda:0')
episode: 45 training return: tensor(-771.1716, device='cuda:0')
episode: 46 training return: tensor(-831.9591, device='cuda:0')
episode: 47 training return: tensor(-687.2615, device='cuda:0')
epoch: 12 test_true_pfm: 143.7234493469959 sim_pfm: -767.5304054300456
episode: 48 training return: tensor(-751.6583, device='cuda:0')
episode: 49 training return: tensor(-885.4480, device='cuda:0')
episode: 50 training return: tensor(-688.8134, device='cuda:0')
episode: 51 training return: tensor(-838.5344, device='cuda:0')
epoch: 13 test_true_pfm: 76.60409945623391 sim_pfm: -698.0465586745801
episode: 52 training return: tensor(-695.6825, device='cuda:0')
episode: 53 training return: tensor(-769.8845, device='cuda:0')
episode: 54 training return: tensor(-782.4432, device='cuda:0')
episode: 55 training return: tensor(-737.7386, device='cuda:0')
epoch: 14 test_true_pfm: 22.83021996817676 sim_pfm: -663.9730705223046
episode: 56 training return: tensor(-724.9024, device='cuda:0')
episode: 57 training return: tensor(-837.3559, device='cuda:0')
episode: 58 training return: tensor(-726.3050, device='cuda:0')
episode: 59 training return: tensor(-683.9677, device='cuda:0')
epoch: 15 test_true_pfm: 18.415092785631515 sim_pfm: -678.1140993731096
episode: 60 training return: tensor(-711.3311, device='cuda:0')
episode: 61 training return: tensor(-710.0272, device='cuda:0')
episode: 62 training return: tensor(-716.1435, device='cuda:0')
episode: 63 training return: tensor(-727.3019, device='cuda:0')
epoch: 16 test_true_pfm: -117.39360520426273 sim_pfm: -640.8821227100367
episode: 64 training return: tensor(-756.4731, device='cuda:0')
episode: 65 training return: tensor(-677.9763, device='cuda:0')
episode: 66 training return: tensor(-702.7754, device='cuda:0')
episode: 67 training return: tensor(-799.8695, device='cuda:0')
epoch: 17 test_true_pfm: -229.1692316993069 sim_pfm: -678.9753906819291
episode: 68 training return: tensor(-656.4851, device='cuda:0')
episode: 69 training return: tensor(-823.2654, device='cuda:0')
episode: 70 training return: tensor(-674.8511, device='cuda:0')
episode: 71 training return: tensor(-697.1755, device='cuda:0')
epoch: 18 test_true_pfm: -176.058640383217 sim_pfm: -734.3690880481154
episode: 72 training return: tensor(-791.3848, device='cuda:0')
episode: 73 training return: tensor(-710.9069, device='cuda:0')
episode: 74 training return: tensor(-744.8738, device='cuda:0')
episode: 75 training return: tensor(-790.8744, device='cuda:0')
epoch: 19 test_true_pfm: -166.50602499274183 sim_pfm: -799.5670908534279
episode: 76 training return: tensor(-589.8667, device='cuda:0')
episode: 77 training return: tensor(-919.7390, device='cuda:0')
episode: 78 training return: tensor(-672.4391, device='cuda:0')
episode: 79 training return: tensor(-885.3908, device='cuda:0')
epoch: 20 test_true_pfm: -113.72679281946864 sim_pfm: -699.7849145919705
episode: 80 training return: tensor(-708.3885, device='cuda:0')
episode: 81 training return: tensor(-797.9699, device='cuda:0')
episode: 82 training return: tensor(-787.8674, device='cuda:0')
episode: 83 training return: tensor(-736.9894, device='cuda:0')
epoch: 21 test_true_pfm: -231.91816598246882 sim_pfm: -664.6601978753073
episode: 84 training return: tensor(-637.8129, device='cuda:0')
episode: 85 training return: tensor(-711.6637, device='cuda:0')
episode: 86 training return: tensor(-704.7800, device='cuda:0')
episode: 87 training return: tensor(-705.8879, device='cuda:0')
epoch: 22 test_true_pfm: -81.05095286182046 sim_pfm: -655.7293411096713
episode: 88 training return: tensor(-740.3085, device='cuda:0')
episode: 89 training return: tensor(-666.3115, device='cuda:0')
episode: 90 training return: tensor(-762.9917, device='cuda:0')
episode: 91 training return: tensor(-750.1968, device='cuda:0')
epoch: 23 test_true_pfm: 44.823978089915634 sim_pfm: -656.2259920584038
episode: 92 training return: tensor(-691.2010, device='cuda:0')
episode: 93 training return: tensor(-744.5027, device='cuda:0')
episode: 94 training return: tensor(-758.5107, device='cuda:0')
episode: 95 training return: tensor(-698.9609, device='cuda:0')
epoch: 24 test_true_pfm: -175.2745731060918 sim_pfm: -676.8901649663845
episode: 96 training return: tensor(-666.0729, device='cuda:0')
episode: 97 training return: tensor(-661.2192, device='cuda:0')
episode: 98 training return: tensor(-715.1526, device='cuda:0')
episode: 99 training return: tensor(-713.5089, device='cuda:0')
epoch: 25 test_true_pfm: -41.67576601107643 sim_pfm: -684.5773357360935
episode: 100 training return: tensor(-768.3655, device='cuda:0')
episode: 101 training return: tensor(-722.4070, device='cuda:0')
episode: 102 training return: tensor(-676.1517, device='cuda:0')
episode: 103 training return: tensor(-674.9176, device='cuda:0')
epoch: 26 test_true_pfm: -178.4754388094806 sim_pfm: -664.2859684365491
episode: 104 training return: tensor(-675.0168, device='cuda:0')
episode: 105 training return: tensor(-760.2062, device='cuda:0')
episode: 106 training return: tensor(-732.9739, device='cuda:0')
episode: 107 training return: tensor(-664.3301, device='cuda:0')
epoch: 27 test_true_pfm: -98.7142467762476 sim_pfm: -649.235819700174
episode: 108 training return: tensor(-671.7903, device='cuda:0')
episode: 109 training return: tensor(-759.2766, device='cuda:0')
episode: 110 training return: tensor(-744.1190, device='cuda:0')
episode: 111 training return: tensor(-838.3950, device='cuda:0')
epoch: 28 test_true_pfm: -62.797677929699915 sim_pfm: -660.8741748838996
episode: 112 training return: tensor(-683.8445, device='cuda:0')
episode: 113 training return: tensor(-689.3621, device='cuda:0')
episode: 114 training return: tensor(-851.4413, device='cuda:0')
episode: 115 training return: tensor(-614.0026, device='cuda:0')
epoch: 29 test_true_pfm: -75.88927691742322 sim_pfm: -640.1100366779914
episode: 116 training return: tensor(-722.4536, device='cuda:0')
episode: 117 training return: tensor(-716.4874, device='cuda:0')
episode: 118 training return: tensor(-749.7050, device='cuda:0')
episode: 119 training return: tensor(-780.1412, device='cuda:0')
epoch: 30 test_true_pfm: 77.97888243017023 sim_pfm: -628.1353734786002
episode: 120 training return: tensor(-670.6993, device='cuda:0')
episode: 121 training return: tensor(-705.2352, device='cuda:0')
episode: 122 training return: tensor(-642.9869, device='cuda:0')
episode: 123 training return: tensor(-740.3622, device='cuda:0')
epoch: 31 test_true_pfm: -204.62933854373753 sim_pfm: -781.9789193582255
episode: 124 training return: tensor(-667.3378, device='cuda:0')
episode: 125 training return: tensor(-667.0195, device='cuda:0')
episode: 126 training return: tensor(-826.4732, device='cuda:0')
episode: 127 training return: tensor(-753.4641, device='cuda:0')
epoch: 32 test_true_pfm: -44.51811072821945 sim_pfm: -653.5356527626476
episode: 128 training return: tensor(-679.4174, device='cuda:0')
episode: 129 training return: tensor(-700.5920, device='cuda:0')
episode: 130 training return: tensor(-715.4050, device='cuda:0')
episode: 131 training return: tensor(-680.3922, device='cuda:0')
epoch: 33 test_true_pfm: -170.69428179766814 sim_pfm: -705.2028654011859
episode: 132 training return: tensor(-684.4482, device='cuda:0')
episode: 133 training return: tensor(-678.7877, device='cuda:0')
episode: 134 training return: tensor(-747.0364, device='cuda:0')
episode: 135 training return: tensor(-702.7562, device='cuda:0')
epoch: 34 test_true_pfm: -84.63510833433033 sim_pfm: -661.6411945737976
episode: 136 training return: tensor(-876.7046, device='cuda:0')
episode: 137 training return: tensor(-658.6545, device='cuda:0')
episode: 138 training return: tensor(-670.9090, device='cuda:0')
episode: 139 training return: tensor(-709.2903, device='cuda:0')
epoch: 35 test_true_pfm: -71.02974511861319 sim_pfm: -656.7842453553652
episode: 140 training return: tensor(-694.5520, device='cuda:0')
episode: 141 training return: tensor(-788.7684, device='cuda:0')
episode: 142 training return: tensor(-679.0477, device='cuda:0')
episode: 143 training return: tensor(-776.5974, device='cuda:0')
epoch: 36 test_true_pfm: -153.0793324206351 sim_pfm: -640.9435589294104
episode: 144 training return: tensor(-666.2548, device='cuda:0')
episode: 145 training return: tensor(-661.7321, device='cuda:0')
episode: 146 training return: tensor(-700.4722, device='cuda:0')
episode: 147 training return: tensor(-667.1990, device='cuda:0')
epoch: 37 test_true_pfm: -54.78835527034101 sim_pfm: -650.0842245851333
episode: 148 training return: tensor(-705.1729, device='cuda:0')
episode: 149 training return: tensor(-755.3404, device='cuda:0')
episode: 150 training return: tensor(-726.1571, device='cuda:0')
episode: 151 training return: tensor(-678.0937, device='cuda:0')
epoch: 38 test_true_pfm: -80.68108020438325 sim_pfm: -617.3202441342097
episode: 152 training return: tensor(-669.7424, device='cuda:0')
episode: 153 training return: tensor(-669.9713, device='cuda:0')
episode: 154 training return: tensor(-668.5862, device='cuda:0')
episode: 155 training return: tensor(-688.6953, device='cuda:0')
epoch: 39 test_true_pfm: -24.195087378769582 sim_pfm: -711.165063518701
episode: 156 training return: tensor(-685.9342, device='cuda:0')
episode: 157 training return: tensor(-643.4278, device='cuda:0')
episode: 158 training return: tensor(-683.7660, device='cuda:0')
episode: 159 training return: tensor(-707.0491, device='cuda:0')
epoch: 40 test_true_pfm: -144.79787792655495 sim_pfm: -654.1846369054789
episode: 160 training return: tensor(-661.3120, device='cuda:0')
episode: 161 training return: tensor(-755.3180, device='cuda:0')
episode: 162 training return: tensor(-644.1914, device='cuda:0')
episode: 163 training return: tensor(-727.7881, device='cuda:0')
epoch: 41 test_true_pfm: 11.577051468991522 sim_pfm: -634.4992218686966
episode: 164 training return: tensor(-755.6310, device='cuda:0')
episode: 165 training return: tensor(-714.5685, device='cuda:0')
episode: 166 training return: tensor(-680.6158, device='cuda:0')
episode: 167 training return: tensor(-636.5540, device='cuda:0')
epoch: 42 test_true_pfm: 7.99742603359008 sim_pfm: -662.8593331267281
episode: 168 training return: tensor(-799.4858, device='cuda:0')
episode: 169 training return: tensor(-717.7881, device='cuda:0')
episode: 170 training return: tensor(-679.2792, device='cuda:0')
episode: 171 training return: tensor(-665.1270, device='cuda:0')
epoch: 43 test_true_pfm: -37.56161997024939 sim_pfm: -642.6063508541944
episode: 172 training return: tensor(-687.5734, device='cuda:0')
episode: 173 training return: tensor(-722.7234, device='cuda:0')
episode: 174 training return: tensor(-677.9342, device='cuda:0')
episode: 175 training return: tensor(-686.6720, device='cuda:0')
epoch: 44 test_true_pfm: 77.19345623626742 sim_pfm: -600.0658317285512
episode: 176 training return: tensor(-683.9415, device='cuda:0')
episode: 177 training return: tensor(-737.1770, device='cuda:0')
episode: 178 training return: tensor(-696.6675, device='cuda:0')
episode: 179 training return: tensor(-682.4420, device='cuda:0')
epoch: 45 test_true_pfm: 60.08412350828695 sim_pfm: -720.6420837189071
episode: 180 training return: tensor(-766.6836, device='cuda:0')
episode: 181 training return: tensor(-690.8875, device='cuda:0')
episode: 182 training return: tensor(-712.9274, device='cuda:0')
episode: 183 training return: tensor(-755.5720, device='cuda:0')
epoch: 46 test_true_pfm: 43.74196610425821 sim_pfm: -704.2655809456483
episode: 184 training return: tensor(-705.4048, device='cuda:0')
episode: 185 training return: tensor(-716.6733, device='cuda:0')
episode: 186 training return: tensor(-648.2065, device='cuda:0')
episode: 187 training return: tensor(-696.4110, device='cuda:0')
epoch: 47 test_true_pfm: -15.330362298425811 sim_pfm: -637.5885408717053
episode: 188 training return: tensor(-674.0682, device='cuda:0')
episode: 189 training return: tensor(-670.9860, device='cuda:0')
episode: 190 training return: tensor(-670.5070, device='cuda:0')
episode: 191 training return: tensor(-663.0351, device='cuda:0')
epoch: 48 test_true_pfm: 92.93355872483544 sim_pfm: -633.735368745091
episode: 192 training return: tensor(-740.9384, device='cuda:0')
episode: 193 training return: tensor(-697.9614, device='cuda:0')
episode: 194 training return: tensor(-659.0507, device='cuda:0')
episode: 195 training return: tensor(-670.2922, device='cuda:0')
epoch: 49 test_true_pfm: -112.2115633879783 sim_pfm: -646.3951914217323
episode: 196 training return: tensor(-681.3027, device='cuda:0')
episode: 197 training return: tensor(-635.9672, device='cuda:0')
episode: 198 training return: tensor(-785.9839, device='cuda:0')
episode: 199 training return: tensor(-660.5627, device='cuda:0')
epoch: 50 test_true_pfm: -34.55564883064201 sim_pfm: -711.4110619768035
episode: 200 training return: tensor(-676.8628, device='cuda:0')
episode: 201 training return: tensor(-765.6211, device='cuda:0')
episode: 202 training return: tensor(-742.8285, device='cuda:0')
episode: 203 training return: tensor(-675.3947, device='cuda:0')
epoch: 51 test_true_pfm: -92.74776575234553 sim_pfm: -647.3919856538996
episode: 204 training return: tensor(-849.7347, device='cuda:0')
episode: 205 training return: tensor(-797.5544, device='cuda:0')
episode: 206 training return: tensor(-655.6211, device='cuda:0')
episode: 207 training return: tensor(-664.6326, device='cuda:0')
epoch: 52 test_true_pfm: -32.671430629619024 sim_pfm: -634.2103880552264
episode: 208 training return: tensor(-662.0241, device='cuda:0')
episode: 209 training return: tensor(-632.9529, device='cuda:0')
episode: 210 training return: tensor(-638.0414, device='cuda:0')
episode: 211 training return: tensor(-670.8907, device='cuda:0')
epoch: 53 test_true_pfm: 18.81875100183213 sim_pfm: -655.5326558630913
episode: 212 training return: tensor(-653.0038, device='cuda:0')
episode: 213 training return: tensor(-644.0938, device='cuda:0')
episode: 214 training return: tensor(-867.8594, device='cuda:0')
episode: 215 training return: tensor(-722.1540, device='cuda:0')
epoch: 54 test_true_pfm: 23.18946126363787 sim_pfm: -622.650582145589
episode: 216 training return: tensor(-657.9509, device='cuda:0')
episode: 217 training return: tensor(-617.9850, device='cuda:0')
episode: 218 training return: tensor(-654.4378, device='cuda:0')
episode: 219 training return: tensor(-735.1597, device='cuda:0')
epoch: 55 test_true_pfm: -189.1003178468941 sim_pfm: -628.1231812660893
episode: 220 training return: tensor(-676.3851, device='cuda:0')
episode: 221 training return: tensor(-637.0553, device='cuda:0')
episode: 222 training return: tensor(-670.4327, device='cuda:0')
episode: 223 training return: tensor(-661.3615, device='cuda:0')
epoch: 56 test_true_pfm: 39.81637542989811 sim_pfm: -634.646536627862
episode: 224 training return: tensor(-663.2457, device='cuda:0')
episode: 225 training return: tensor(-724.5600, device='cuda:0')
episode: 226 training return: tensor(-643.9697, device='cuda:0')
episode: 227 training return: tensor(-670.4597, device='cuda:0')
epoch: 57 test_true_pfm: -168.29682775342133 sim_pfm: -616.2723608923455
episode: 228 training return: tensor(-664.1185, device='cuda:0')
episode: 229 training return: tensor(-748.8546, device='cuda:0')
episode: 230 training return: tensor(-688.4000, device='cuda:0')
episode: 231 training return: tensor(-755.5536, device='cuda:0')
epoch: 58 test_true_pfm: 56.07422497756854 sim_pfm: -655.8592427959666
episode: 232 training return: tensor(-755.2587, device='cuda:0')
episode: 233 training return: tensor(-672.2193, device='cuda:0')
episode: 234 training return: tensor(-662.0154, device='cuda:0')
episode: 235 training return: tensor(-699.9260, device='cuda:0')
epoch: 59 test_true_pfm: 58.15253971884843 sim_pfm: -593.3024961343812
episode: 236 training return: tensor(-738.0827, device='cuda:0')
episode: 237 training return: tensor(-643.1677, device='cuda:0')
episode: 238 training return: tensor(-693.0383, device='cuda:0')
episode: 239 training return: tensor(-737.9708, device='cuda:0')
epoch: 60 test_true_pfm: 68.44379936628049 sim_pfm: -625.7347287106483
episode: 240 training return: tensor(-669.6217, device='cuda:0')
episode: 241 training return: tensor(-662.1788, device='cuda:0')
episode: 242 training return: tensor(-692.5981, device='cuda:0')
episode: 243 training return: tensor(-682.7045, device='cuda:0')
epoch: 61 test_true_pfm: 200.81309961799457 sim_pfm: -619.8927992687871
episode: 244 training return: tensor(-721.8735, device='cuda:0')
episode: 245 training return: tensor(-796.3109, device='cuda:0')
episode: 246 training return: tensor(-669.8862, device='cuda:0')
episode: 247 training return: tensor(-655.7518, device='cuda:0')
epoch: 62 test_true_pfm: 152.08715901275477 sim_pfm: -640.0639527271657
episode: 248 training return: tensor(-670.2779, device='cuda:0')
episode: 249 training return: tensor(-697.0536, device='cuda:0')
episode: 250 training return: tensor(-654.3683, device='cuda:0')
episode: 251 training return: tensor(-625.3282, device='cuda:0')
epoch: 63 test_true_pfm: 121.50194250242485 sim_pfm: -620.8252037068984
episode: 252 training return: tensor(-662.6802, device='cuda:0')
episode: 253 training return: tensor(-661.2443, device='cuda:0')
episode: 254 training return: tensor(-647.1738, device='cuda:0')
episode: 255 training return: tensor(-707.2457, device='cuda:0')
epoch: 64 test_true_pfm: -0.5597864799210299 sim_pfm: -640.5316307294028
episode: 256 training return: tensor(-652.2166, device='cuda:0')
episode: 257 training return: tensor(-677.9721, device='cuda:0')
episode: 258 training return: tensor(-627.9277, device='cuda:0')
episode: 259 training return: tensor(-660.3834, device='cuda:0')
epoch: 65 test_true_pfm: -8.585094452622064 sim_pfm: -690.5609003699307
episode: 260 training return: tensor(-682.9462, device='cuda:0')
episode: 261 training return: tensor(-633.1385, device='cuda:0')
episode: 262 training return: tensor(-673.7536, device='cuda:0')
episode: 263 training return: tensor(-669.1638, device='cuda:0')
epoch: 66 test_true_pfm: -111.98975455993669 sim_pfm: -632.1108674504794
episode: 264 training return: tensor(-713.1490, device='cuda:0')
episode: 265 training return: tensor(-697.6006, device='cuda:0')
episode: 266 training return: tensor(-681.7869, device='cuda:0')
episode: 267 training return: tensor(-653.8926, device='cuda:0')
epoch: 67 test_true_pfm: 60.463601524547464 sim_pfm: -707.2130330167711
episode: 268 training return: tensor(-688.0433, device='cuda:0')
episode: 269 training return: tensor(-659.8080, device='cuda:0')
episode: 270 training return: tensor(-740.8146, device='cuda:0')
episode: 271 training return: tensor(-661.2655, device='cuda:0')
epoch: 68 test_true_pfm: 67.5406175439305 sim_pfm: -652.2852762987217
episode: 272 training return: tensor(-683.2634, device='cuda:0')
episode: 273 training return: tensor(-678.4517, device='cuda:0')
episode: 274 training return: tensor(-654.0482, device='cuda:0')
episode: 275 training return: tensor(-677.6266, device='cuda:0')
epoch: 69 test_true_pfm: -68.71893264348704 sim_pfm: -647.4044973274382
episode: 276 training return: tensor(-677.1903, device='cuda:0')
episode: 277 training return: tensor(-753.5712, device='cuda:0')
episode: 278 training return: tensor(-691.7117, device='cuda:0')
episode: 279 training return: tensor(-641.8774, device='cuda:0')
epoch: 70 test_true_pfm: 17.19815073342721 sim_pfm: -726.8522585045235
episode: 280 training return: tensor(-835.0396, device='cuda:0')
episode: 281 training return: tensor(-837.4296, device='cuda:0')
episode: 282 training return: tensor(-711.1979, device='cuda:0')
episode: 283 training return: tensor(-683.9931, device='cuda:0')
epoch: 71 test_true_pfm: -52.384819841239356 sim_pfm: -647.3863146995815
episode: 284 training return: tensor(-834.5227, device='cuda:0')
episode: 285 training return: tensor(-705.7612, device='cuda:0')
episode: 286 training return: tensor(-636.4001, device='cuda:0')
episode: 287 training return: tensor(-637.8840, device='cuda:0')
epoch: 72 test_true_pfm: 85.85053678191916 sim_pfm: -740.1735921913447
episode: 288 training return: tensor(-692.0207, device='cuda:0')
episode: 289 training return: tensor(-667.8952, device='cuda:0')
episode: 290 training return: tensor(-636.9261, device='cuda:0')
episode: 291 training return: tensor(-720.1545, device='cuda:0')
epoch: 73 test_true_pfm: 5.513054793267451 sim_pfm: -669.42602432818
episode: 292 training return: tensor(-652.1335, device='cuda:0')
episode: 293 training return: tensor(-663.0923, device='cuda:0')
episode: 294 training return: tensor(-670.3812, device='cuda:0')
episode: 295 training return: tensor(-673.7074, device='cuda:0')
epoch: 74 test_true_pfm: 110.64865395291788 sim_pfm: -613.633271236904
episode: 296 training return: tensor(-634.4271, device='cuda:0')
episode: 297 training return: tensor(-737.4031, device='cuda:0')
episode: 298 training return: tensor(-645.5225, device='cuda:0')
episode: 299 training return: tensor(-646.9153, device='cuda:0')
epoch: 75 test_true_pfm: 50.542010939836736 sim_pfm: -630.7877438276386
episode: 300 training return: tensor(-683.2385, device='cuda:0')
episode: 301 training return: tensor(-723.0310, device='cuda:0')
episode: 302 training return: tensor(-661.2196, device='cuda:0')
episode: 303 training return: tensor(-729.5671, device='cuda:0')
epoch: 76 test_true_pfm: -47.47472368297295 sim_pfm: -703.7563580386341
episode: 304 training return: tensor(-670.1252, device='cuda:0')
episode: 305 training return: tensor(-661.2516, device='cuda:0')
episode: 306 training return: tensor(-668.0378, device='cuda:0')
episode: 307 training return: tensor(-657.8486, device='cuda:0')
epoch: 77 test_true_pfm: 56.5157267971336 sim_pfm: -667.7612917351847
episode: 308 training return: tensor(-717.1883, device='cuda:0')
episode: 309 training return: tensor(-729.2470, device='cuda:0')
episode: 310 training return: tensor(-671.0570, device='cuda:0')
episode: 311 training return: tensor(-676.6531, device='cuda:0')
epoch: 78 test_true_pfm: 43.59291805114086 sim_pfm: -652.3900524906348
episode: 312 training return: tensor(-657.3008, device='cuda:0')
episode: 313 training return: tensor(-716.6648, device='cuda:0')
episode: 314 training return: tensor(-637.3630, device='cuda:0')
episode: 315 training return: tensor(-617.7107, device='cuda:0')
epoch: 79 test_true_pfm: -31.11759992971386 sim_pfm: -756.731918700505
episode: 316 training return: tensor(-653.0432, device='cuda:0')
episode: 317 training return: tensor(-737.2670, device='cuda:0')
episode: 318 training return: tensor(-726.1746, device='cuda:0')
episode: 319 training return: tensor(-637.8763, device='cuda:0')
epoch: 80 test_true_pfm: 74.58571328882914 sim_pfm: -690.2154538438384
episode: 320 training return: tensor(-658.9254, device='cuda:0')
episode: 321 training return: tensor(-659.9884, device='cuda:0')
episode: 322 training return: tensor(-680.5164, device='cuda:0')
episode: 323 training return: tensor(-669.6259, device='cuda:0')
epoch: 81 test_true_pfm: -15.29188524449759 sim_pfm: -659.4208629188748
episode: 324 training return: tensor(-663.8680, device='cuda:0')
episode: 325 training return: tensor(-777.6164, device='cuda:0')
episode: 326 training return: tensor(-703.3622, device='cuda:0')
episode: 327 training return: tensor(-686.4890, device='cuda:0')
epoch: 82 test_true_pfm: -26.552746368732098 sim_pfm: -610.5021035990212
episode: 328 training return: tensor(-672.2673, device='cuda:0')
episode: 329 training return: tensor(-663.9330, device='cuda:0')
episode: 330 training return: tensor(-705.2498, device='cuda:0')
episode: 331 training return: tensor(-681.4764, device='cuda:0')
epoch: 83 test_true_pfm: 44.3311925132812 sim_pfm: -605.7215804282265
episode: 332 training return: tensor(-640.8381, device='cuda:0')
episode: 333 training return: tensor(-672.2383, device='cuda:0')
episode: 334 training return: tensor(-728.7870, device='cuda:0')
episode: 335 training return: tensor(-637.1288, device='cuda:0')
epoch: 84 test_true_pfm: 91.33620578792689 sim_pfm: -608.9929301753291
episode: 336 training return: tensor(-655.8419, device='cuda:0')
episode: 337 training return: tensor(-646.0101, device='cuda:0')
episode: 338 training return: tensor(-699.3542, device='cuda:0')
episode: 339 training return: tensor(-703.9534, device='cuda:0')
epoch: 85 test_true_pfm: -84.65474659961883 sim_pfm: -612.1630511811624
episode: 340 training return: tensor(-663.0745, device='cuda:0')
episode: 341 training return: tensor(-651.0453, device='cuda:0')
episode: 342 training return: tensor(-666.2812, device='cuda:0')
episode: 343 training return: tensor(-711.7688, device='cuda:0')
epoch: 86 test_true_pfm: 122.7006146626736 sim_pfm: -606.2714153238727
episode: 344 training return: tensor(-699.2726, device='cuda:0')
episode: 345 training return: tensor(-669.0061, device='cuda:0')
episode: 346 training return: tensor(-670.4791, device='cuda:0')
episode: 347 training return: tensor(-685.6111, device='cuda:0')
epoch: 87 test_true_pfm: 115.44247758457936 sim_pfm: -592.9715861068107
episode: 348 training return: tensor(-669.2437, device='cuda:0')
episode: 349 training return: tensor(-687.4318, device='cuda:0')
episode: 350 training return: tensor(-711.2131, device='cuda:0')
episode: 351 training return: tensor(-669.3724, device='cuda:0')
epoch: 88 test_true_pfm: -46.79858888428377 sim_pfm: -699.334804989087
episode: 352 training return: tensor(-666.8206, device='cuda:0')
episode: 353 training return: tensor(-649.5515, device='cuda:0')
episode: 354 training return: tensor(-684.3893, device='cuda:0')
episode: 355 training return: tensor(-659.4675, device='cuda:0')
epoch: 89 test_true_pfm: 80.81942911183906 sim_pfm: -645.6062341453508
episode: 356 training return: tensor(-699.1705, device='cuda:0')
episode: 357 training return: tensor(-674.4545, device='cuda:0')
episode: 358 training return: tensor(-646.7123, device='cuda:0')
episode: 359 training return: tensor(-686.5170, device='cuda:0')
epoch: 90 test_true_pfm: 57.97528554989005 sim_pfm: -663.6713136921171
episode: 360 training return: tensor(-628.5518, device='cuda:0')
episode: 361 training return: tensor(-714.6074, device='cuda:0')
episode: 362 training return: tensor(-646.3286, device='cuda:0')
episode: 363 training return: tensor(-717.5465, device='cuda:0')
epoch: 91 test_true_pfm: 111.57786974198433 sim_pfm: -653.8992273034528
episode: 364 training return: tensor(-714.1808, device='cuda:0')
episode: 365 training return: tensor(-672.6768, device='cuda:0')
episode: 366 training return: tensor(-696.7181, device='cuda:0')
episode: 367 training return: tensor(-733.9885, device='cuda:0')
epoch: 92 test_true_pfm: 120.27322655460397 sim_pfm: -595.72053953136
episode: 368 training return: tensor(-650.6367, device='cuda:0')
episode: 369 training return: tensor(-721.2360, device='cuda:0')
episode: 370 training return: tensor(-688.8784, device='cuda:0')
episode: 371 training return: tensor(-638.7796, device='cuda:0')
epoch: 93 test_true_pfm: 43.41585553009779 sim_pfm: -604.6686368688728
episode: 372 training return: tensor(-646.3359, device='cuda:0')
episode: 373 training return: tensor(-647.5594, device='cuda:0')
episode: 374 training return: tensor(-739.1310, device='cuda:0')
episode: 375 training return: tensor(-670.2203, device='cuda:0')
epoch: 94 test_true_pfm: 107.30903374846734 sim_pfm: -668.885389408019
episode: 376 training return: tensor(-657.5909, device='cuda:0')
episode: 377 training return: tensor(-640.0970, device='cuda:0')
episode: 378 training return: tensor(-658.0829, device='cuda:0')
episode: 379 training return: tensor(-659.7451, device='cuda:0')
epoch: 95 test_true_pfm: 184.61697311977593 sim_pfm: -607.6163392223729
episode: 380 training return: tensor(-636.6162, device='cuda:0')
episode: 381 training return: tensor(-673.1829, device='cuda:0')
episode: 382 training return: tensor(-654.2303, device='cuda:0')
episode: 383 training return: tensor(-672.7585, device='cuda:0')
epoch: 96 test_true_pfm: -53.48531791507832 sim_pfm: -741.5627474374293
episode: 384 training return: tensor(-669.8329, device='cuda:0')
episode: 385 training return: tensor(-834.4844, device='cuda:0')
episode: 386 training return: tensor(-643.1821, device='cuda:0')
episode: 387 training return: tensor(-624.3002, device='cuda:0')
epoch: 97 test_true_pfm: 62.72734239449701 sim_pfm: -579.2890629020209
episode: 388 training return: tensor(-652.4578, device='cuda:0')
episode: 389 training return: tensor(-715.4178, device='cuda:0')
episode: 390 training return: tensor(-613.4886, device='cuda:0')
episode: 391 training return: tensor(-625.1899, device='cuda:0')
epoch: 98 test_true_pfm: 86.26731803615273 sim_pfm: -661.0864744489081
episode: 392 training return: tensor(-709.6985, device='cuda:0')
episode: 393 training return: tensor(-660.7652, device='cuda:0')
episode: 394 training return: tensor(-705.9971, device='cuda:0')
episode: 395 training return: tensor(-665.2916, device='cuda:0')
epoch: 99 test_true_pfm: 88.73367513795426 sim_pfm: -707.1630081095112
episode: 396 training return: tensor(-640.1358, device='cuda:0')
episode: 397 training return: tensor(-673.4924, device='cuda:0')
episode: 398 training return: tensor(-804.0634, device='cuda:0')
episode: 399 training return: tensor(-766.7780, device='cuda:0')
epoch: 100 test_true_pfm: 165.11132426823812 sim_pfm: -590.2680985346475
episode: 400 training return: tensor(-748.4238, device='cuda:0')
episode: 401 training return: tensor(-673.8970, device='cuda:0')
episode: 402 training return: tensor(-642.0591, device='cuda:0')
episode: 403 training return: tensor(-750.6622, device='cuda:0')
epoch: 101 test_true_pfm: 86.43730917864012 sim_pfm: -704.0556063963255
episode: 404 training return: tensor(-628.6210, device='cuda:0')
episode: 405 training return: tensor(-637.2753, device='cuda:0')
episode: 406 training return: tensor(-829.0503, device='cuda:0')
episode: 407 training return: tensor(-741.1683, device='cuda:0')
epoch: 102 test_true_pfm: 83.17352638693212 sim_pfm: -668.7654011917766
episode: 408 training return: tensor(-638.8444, device='cuda:0')
episode: 409 training return: tensor(-665.4556, device='cuda:0')
episode: 410 training return: tensor(-642.7836, device='cuda:0')
episode: 411 training return: tensor(-652.4909, device='cuda:0')
epoch: 103 test_true_pfm: 101.286505365769 sim_pfm: -744.5753240184955
episode: 412 training return: tensor(-808.5015, device='cuda:0')
episode: 413 training return: tensor(-625.2415, device='cuda:0')
episode: 414 training return: tensor(-649.3282, device='cuda:0')
episode: 415 training return: tensor(-722.0133, device='cuda:0')
epoch: 104 test_true_pfm: 49.19745195044069 sim_pfm: -607.2084401392882
episode: 416 training return: tensor(-578.5738, device='cuda:0')
episode: 417 training return: tensor(-681.7362, device='cuda:0')
episode: 418 training return: tensor(-638.2538, device='cuda:0')
episode: 419 training return: tensor(-739.9272, device='cuda:0')
epoch: 105 test_true_pfm: -52.08985702181553 sim_pfm: -588.3222648209581
episode: 420 training return: tensor(-756.7470, device='cuda:0')
episode: 421 training return: tensor(-663.3010, device='cuda:0')
episode: 422 training return: tensor(-706.3213, device='cuda:0')
episode: 423 training return: tensor(-686.4929, device='cuda:0')
epoch: 106 test_true_pfm: 21.669202999085524 sim_pfm: -718.3291435576199
episode: 424 training return: tensor(-700.9698, device='cuda:0')
episode: 425 training return: tensor(-660.4734, device='cuda:0')
episode: 426 training return: tensor(-606.6495, device='cuda:0')
episode: 427 training return: tensor(-621.4980, device='cuda:0')
epoch: 107 test_true_pfm: 105.06184557259151 sim_pfm: -730.8494843494846
episode: 428 training return: tensor(-715.0854, device='cuda:0')
episode: 429 training return: tensor(-669.8492, device='cuda:0')
episode: 430 training return: tensor(-856.0411, device='cuda:0')
episode: 431 training return: tensor(-648.5588, device='cuda:0')
epoch: 108 test_true_pfm: 208.61750399876658 sim_pfm: -597.6609722615685
episode: 432 training return: tensor(-682.6600, device='cuda:0')
episode: 433 training return: tensor(-705.5993, device='cuda:0')
episode: 434 training return: tensor(-830.1403, device='cuda:0')
episode: 435 training return: tensor(-643.2879, device='cuda:0')
epoch: 109 test_true_pfm: 112.73295639293588 sim_pfm: -601.7751883134091
episode: 436 training return: tensor(-733.5624, device='cuda:0')
episode: 437 training return: tensor(-651.6993, device='cuda:0')
episode: 438 training return: tensor(-653.2043, device='cuda:0')
episode: 439 training return: tensor(-723.2699, device='cuda:0')
epoch: 110 test_true_pfm: -16.685953948394843 sim_pfm: -585.5211512584938
episode: 440 training return: tensor(-662.1176, device='cuda:0')
episode: 441 training return: tensor(-644.8133, device='cuda:0')
episode: 442 training return: tensor(-637.8769, device='cuda:0')
episode: 443 training return: tensor(-651.1688, device='cuda:0')
epoch: 111 test_true_pfm: 124.5987874302091 sim_pfm: -595.9524744000324
episode: 444 training return: tensor(-859.5392, device='cuda:0')
episode: 445 training return: tensor(-641.5590, device='cuda:0')
episode: 446 training return: tensor(-663.0684, device='cuda:0')
episode: 447 training return: tensor(-646.4603, device='cuda:0')
epoch: 112 test_true_pfm: 68.75699779489894 sim_pfm: -594.7810271124666
episode: 448 training return: tensor(-612.2858, device='cuda:0')
episode: 449 training return: tensor(-727.5825, device='cuda:0')
episode: 450 training return: tensor(-668.5161, device='cuda:0')
episode: 451 training return: tensor(-638.7222, device='cuda:0')
epoch: 113 test_true_pfm: 163.08424576140138 sim_pfm: -589.6358489269429
episode: 452 training return: tensor(-721.3168, device='cuda:0')
episode: 453 training return: tensor(-661.6633, device='cuda:0')
episode: 454 training return: tensor(-659.3364, device='cuda:0')
episode: 455 training return: tensor(-640.0667, device='cuda:0')
epoch: 114 test_true_pfm: 14.638964249416688 sim_pfm: -584.9762131889971
episode: 456 training return: tensor(-644.6260, device='cuda:0')
episode: 457 training return: tensor(-642.9022, device='cuda:0')
episode: 458 training return: tensor(-657.8434, device='cuda:0')
episode: 459 training return: tensor(-757.9557, device='cuda:0')
epoch: 115 test_true_pfm: 109.2188224101152 sim_pfm: -580.8749139959691
episode: 460 training return: tensor(-812.0261, device='cuda:0')
episode: 461 training return: tensor(-662.0899, device='cuda:0')
episode: 462 training return: tensor(-696.9039, device='cuda:0')
episode: 463 training return: tensor(-646.2365, device='cuda:0')
epoch: 116 test_true_pfm: 5.499903391718727 sim_pfm: -572.3187979230037
episode: 464 training return: tensor(-662.5745, device='cuda:0')
episode: 465 training return: tensor(-911.4460, device='cuda:0')
episode: 466 training return: tensor(-676.6913, device='cuda:0')
episode: 467 training return: tensor(-667.2401, device='cuda:0')
epoch: 117 test_true_pfm: 103.57335789494773 sim_pfm: -610.7032652121658
episode: 468 training return: tensor(-648.4827, device='cuda:0')
episode: 469 training return: tensor(-753.1719, device='cuda:0')
episode: 470 training return: tensor(-638.3850, device='cuda:0')
episode: 471 training return: tensor(-656.0117, device='cuda:0')
epoch: 118 test_true_pfm: 57.93694925237519 sim_pfm: -584.3056490021991
episode: 472 training return: tensor(-680.6187, device='cuda:0')
episode: 473 training return: tensor(-813.2951, device='cuda:0')
episode: 474 training return: tensor(-701.2463, device='cuda:0')
episode: 475 training return: tensor(-660.5971, device='cuda:0')
epoch: 119 test_true_pfm: 59.36814477716365 sim_pfm: -617.3089648106446
episode: 476 training return: tensor(-696.7156, device='cuda:0')
episode: 477 training return: tensor(-744.4583, device='cuda:0')
episode: 478 training return: tensor(-619.2878, device='cuda:0')
episode: 479 training return: tensor(-664.5508, device='cuda:0')
epoch: 120 test_true_pfm: 100.25189840729497 sim_pfm: -689.8893089874182
episode: 480 training return: tensor(-701.9005, device='cuda:0')
episode: 481 training return: tensor(-673.2059, device='cuda:0')
episode: 482 training return: tensor(-671.4606, device='cuda:0')
episode: 483 training return: tensor(-624.7047, device='cuda:0')
epoch: 121 test_true_pfm: -83.58797957755158 sim_pfm: -604.4234560352439
episode: 484 training return: tensor(-677.0920, device='cuda:0')
episode: 485 training return: tensor(-655.4623, device='cuda:0')
episode: 486 training return: tensor(-633.6670, device='cuda:0')
episode: 487 training return: tensor(-664.1946, device='cuda:0')
epoch: 122 test_true_pfm: 160.42210856188515 sim_pfm: -576.2460840729376
episode: 488 training return: tensor(-733.4135, device='cuda:0')
episode: 489 training return: tensor(-659.0690, device='cuda:0')
episode: 490 training return: tensor(-642.0535, device='cuda:0')
episode: 491 training return: tensor(-633.8127, device='cuda:0')
epoch: 123 test_true_pfm: 124.78214686970398 sim_pfm: -618.9974053458427
episode: 492 training return: tensor(-688.6603, device='cuda:0')
episode: 493 training return: tensor(-774.4392, device='cuda:0')
episode: 494 training return: tensor(-798.0384, device='cuda:0')
episode: 495 training return: tensor(-721.5993, device='cuda:0')
epoch: 124 test_true_pfm: 40.0408523684647 sim_pfm: -648.3374148862591
episode: 496 training return: tensor(-669.0196, device='cuda:0')
episode: 497 training return: tensor(-642.0886, device='cuda:0')
episode: 498 training return: tensor(-679.3879, device='cuda:0')
episode: 499 training return: tensor(-750.1827, device='cuda:0')
epoch: 125 test_true_pfm: 132.61303693966613 sim_pfm: -561.7169101651137
episode: 500 training return: tensor(-638.4188, device='cuda:0')
episode: 501 training return: tensor(-673.1437, device='cuda:0')
episode: 502 training return: tensor(-644.5462, device='cuda:0')
episode: 503 training return: tensor(-714.1652, device='cuda:0')
epoch: 126 test_true_pfm: 40.467495055507754 sim_pfm: -601.3251643106341
episode: 504 training return: tensor(-661.6730, device='cuda:0')
episode: 505 training return: tensor(-724.1539, device='cuda:0')
episode: 506 training return: tensor(-669.0461, device='cuda:0')
episode: 507 training return: tensor(-650.4528, device='cuda:0')
epoch: 127 test_true_pfm: 52.97987693479163 sim_pfm: -630.7288354017364
episode: 508 training return: tensor(-588.8762, device='cuda:0')
episode: 509 training return: tensor(-750.5060, device='cuda:0')
episode: 510 training return: tensor(-696.8592, device='cuda:0')
episode: 511 training return: tensor(-645.9309, device='cuda:0')
epoch: 128 test_true_pfm: 99.61808000616959 sim_pfm: -630.9316495114375
episode: 512 training return: tensor(-683.6761, device='cuda:0')
episode: 513 training return: tensor(-640.0008, device='cuda:0')
episode: 514 training return: tensor(-662.6835, device='cuda:0')
episode: 515 training return: tensor(-799.2393, device='cuda:0')
epoch: 129 test_true_pfm: -0.5711771989946755 sim_pfm: -673.1397205368461
episode: 516 training return: tensor(-680.8339, device='cuda:0')
episode: 517 training return: tensor(-656.0089, device='cuda:0')
episode: 518 training return: tensor(-722.6778, device='cuda:0')
episode: 519 training return: tensor(-659.0613, device='cuda:0')
epoch: 130 test_true_pfm: -152.52996294903608 sim_pfm: -607.3887492090774
episode: 520 training return: tensor(-739.7072, device='cuda:0')
episode: 521 training return: tensor(-689.7282, device='cuda:0')
episode: 522 training return: tensor(-660.2408, device='cuda:0')
episode: 523 training return: tensor(-686.0589, device='cuda:0')
epoch: 131 test_true_pfm: -32.18866221409886 sim_pfm: -594.6186719108373
episode: 524 training return: tensor(-690.2155, device='cuda:0')
episode: 525 training return: tensor(-649.8721, device='cuda:0')
episode: 526 training return: tensor(-640.2884, device='cuda:0')
episode: 527 training return: tensor(-663.4956, device='cuda:0')
epoch: 132 test_true_pfm: -20.469390717231178 sim_pfm: -581.6736991467575
episode: 528 training return: tensor(-680.9240, device='cuda:0')
episode: 529 training return: tensor(-651.2756, device='cuda:0')
episode: 530 training return: tensor(-626.4360, device='cuda:0')
episode: 531 training return: tensor(-634.0846, device='cuda:0')
epoch: 133 test_true_pfm: 167.9237556417818 sim_pfm: -599.4262620064352
episode: 532 training return: tensor(-686.5416, device='cuda:0')
episode: 533 training return: tensor(-678.6148, device='cuda:0')
episode: 534 training return: tensor(-789.9207, device='cuda:0')
episode: 535 training return: tensor(-732.0483, device='cuda:0')
epoch: 134 test_true_pfm: 111.4582030573634 sim_pfm: -634.8280962272547
episode: 536 training return: tensor(-709.7859, device='cuda:0')
episode: 537 training return: tensor(-687.0339, device='cuda:0')
episode: 538 training return: tensor(-690.8865, device='cuda:0')
episode: 539 training return: tensor(-658.7233, device='cuda:0')
epoch: 135 test_true_pfm: 181.47694613034437 sim_pfm: -666.2270734111468
episode: 540 training return: tensor(-631.3113, device='cuda:0')
episode: 541 training return: tensor(-659.3724, device='cuda:0')
episode: 542 training return: tensor(-672.4421, device='cuda:0')
episode: 543 training return: tensor(-675.0987, device='cuda:0')
epoch: 136 test_true_pfm: 146.60100390078534 sim_pfm: -687.8797708887918
episode: 544 training return: tensor(-672.2571, device='cuda:0')
episode: 545 training return: tensor(-667.7792, device='cuda:0')
episode: 546 training return: tensor(-753.1287, device='cuda:0')
episode: 547 training return: tensor(-634.6627, device='cuda:0')
epoch: 137 test_true_pfm: 27.386852938257338 sim_pfm: -625.1123857724791
episode: 548 training return: tensor(-648.6631, device='cuda:0')
episode: 549 training return: tensor(-881.8978, device='cuda:0')
episode: 550 training return: tensor(-710.3843, device='cuda:0')
episode: 551 training return: tensor(-760.4725, device='cuda:0')
epoch: 138 test_true_pfm: 60.13662594182548 sim_pfm: -693.5818988736719
episode: 552 training return: tensor(-609.8777, device='cuda:0')
episode: 553 training return: tensor(-698.4694, device='cuda:0')
episode: 554 training return: tensor(-775.8305, device='cuda:0')
episode: 555 training return: tensor(-681.7821, device='cuda:0')
epoch: 139 test_true_pfm: -6.165726278799549 sim_pfm: -599.9628665031438
episode: 556 training return: tensor(-663.9676, device='cuda:0')
episode: 557 training return: tensor(-661.2869, device='cuda:0')
episode: 558 training return: tensor(-632.5451, device='cuda:0')
episode: 559 training return: tensor(-656.4922, device='cuda:0')
epoch: 140 test_true_pfm: 171.98889853256432 sim_pfm: -680.6242041071722
episode: 560 training return: tensor(-869.0509, device='cuda:0')
episode: 561 training return: tensor(-660.8052, device='cuda:0')
episode: 562 training return: tensor(-697.5145, device='cuda:0')
episode: 563 training return: tensor(-655.0197, device='cuda:0')
epoch: 141 test_true_pfm: 190.20133609338868 sim_pfm: -595.404700470157
episode: 564 training return: tensor(-653.8539, device='cuda:0')
episode: 565 training return: tensor(-670.9318, device='cuda:0')
episode: 566 training return: tensor(-714.4410, device='cuda:0')
episode: 567 training return: tensor(-681.2266, device='cuda:0')
epoch: 142 test_true_pfm: 114.72692458780455 sim_pfm: -675.1541423756474
episode: 568 training return: tensor(-779.2238, device='cuda:0')
episode: 569 training return: tensor(-693.9033, device='cuda:0')
episode: 570 training return: tensor(-722.2637, device='cuda:0')
episode: 571 training return: tensor(-643.6227, device='cuda:0')
epoch: 143 test_true_pfm: 50.5325083365704 sim_pfm: -792.9018008643761
episode: 572 training return: tensor(-652.2459, device='cuda:0')
episode: 573 training return: tensor(-626.4045, device='cuda:0')
episode: 574 training return: tensor(-684.5422, device='cuda:0')
episode: 575 training return: tensor(-652.1943, device='cuda:0')
epoch: 144 test_true_pfm: 170.99300619335213 sim_pfm: -626.044725053478
episode: 576 training return: tensor(-716.3578, device='cuda:0')
episode: 577 training return: tensor(-661.0559, device='cuda:0')
episode: 578 training return: tensor(-698.8807, device='cuda:0')
episode: 579 training return: tensor(-629.6818, device='cuda:0')
epoch: 145 test_true_pfm: 99.53470899042232 sim_pfm: -582.0732071541715
episode: 580 training return: tensor(-772.5448, device='cuda:0')
episode: 581 training return: tensor(-649.4021, device='cuda:0')
episode: 582 training return: tensor(-672.0718, device='cuda:0')
episode: 583 training return: tensor(-678.4115, device='cuda:0')
epoch: 146 test_true_pfm: 61.042653401862886 sim_pfm: -636.8797477271874
episode: 584 training return: tensor(-674.1114, device='cuda:0')
episode: 585 training return: tensor(-632.5535, device='cuda:0')
episode: 586 training return: tensor(-726.4038, device='cuda:0')
episode: 587 training return: tensor(-662.7507, device='cuda:0')
epoch: 147 test_true_pfm: 58.14133954219574 sim_pfm: -612.2879961873308
episode: 588 training return: tensor(-606.1276, device='cuda:0')
episode: 589 training return: tensor(-641.2007, device='cuda:0')
episode: 590 training return: tensor(-680.1522, device='cuda:0')
episode: 591 training return: tensor(-688.3080, device='cuda:0')
epoch: 148 test_true_pfm: 89.61377431380886 sim_pfm: -597.9874439232517
episode: 592 training return: tensor(-704.9221, device='cuda:0')
episode: 593 training return: tensor(-632.9277, device='cuda:0')
episode: 594 training return: tensor(-660.4509, device='cuda:0')
episode: 595 training return: tensor(-704.4052, device='cuda:0')
epoch: 149 test_true_pfm: 19.892401325549816 sim_pfm: -625.1467217366832
episode: 596 training return: tensor(-639.3369, device='cuda:0')
episode: 597 training return: tensor(-689.9669, device='cuda:0')
episode: 598 training return: tensor(-636.5568, device='cuda:0')
episode: 599 training return: tensor(-656.1708, device='cuda:0')
epoch: 150 test_true_pfm: 32.61643100943511 sim_pfm: -753.2704226979986
