['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'baseline', '--traj', 'expert', '--seed', '1']
episode: 0 training return: tensor(-942.6162, device='cuda:0')
episode: 1 training return: tensor(-914.0199, device='cuda:0')
episode: 2 training return: tensor(-863.9133, device='cuda:0')
episode: 3 training return: tensor(-941.4103, device='cuda:0')
epoch: 1 test_true_pfm: -41.42201101553521 sim_pfm: -847.4250080982844
episode: 4 training return: tensor(-955.2045, device='cuda:0')
episode: 5 training return: tensor(-936.2978, device='cuda:0')
episode: 6 training return: tensor(-957.1954, device='cuda:0')
episode: 7 training return: tensor(-894.1089, device='cuda:0')
epoch: 2 test_true_pfm: 15.41412581256492 sim_pfm: -778.5270701404661
episode: 8 training return: tensor(-929.9689, device='cuda:0')
episode: 9 training return: tensor(-899.4479, device='cuda:0')
episode: 10 training return: tensor(-608.5485, device='cuda:0')
episode: 11 training return: tensor(-811.9297, device='cuda:0')
epoch: 3 test_true_pfm: 97.58680978557305 sim_pfm: -774.9576795772106
episode: 12 training return: tensor(-792.2089, device='cuda:0')
episode: 13 training return: tensor(-876.2208, device='cuda:0')
episode: 14 training return: tensor(-951.0305, device='cuda:0')
episode: 15 training return: tensor(-942.1642, device='cuda:0')
epoch: 4 test_true_pfm: -875.8760135956946 sim_pfm: -954.460410396258
episode: 16 training return: tensor(-942.2933, device='cuda:0')
episode: 17 training return: tensor(-833.7940, device='cuda:0')
episode: 18 training return: tensor(-942.6969, device='cuda:0')
episode: 19 training return: tensor(-928.5289, device='cuda:0')
epoch: 5 test_true_pfm: -15.120019026212395 sim_pfm: -904.017243458579
episode: 20 training return: tensor(-913.2885, device='cuda:0')
episode: 21 training return: tensor(-919.4131, device='cuda:0')
episode: 22 training return: tensor(-885.0688, device='cuda:0')
episode: 23 training return: tensor(-920.5922, device='cuda:0')
epoch: 6 test_true_pfm: -244.2414628567685 sim_pfm: -817.8773809646567
episode: 24 training return: tensor(-968.2264, device='cuda:0')
episode: 25 training return: tensor(-978.4344, device='cuda:0')
episode: 26 training return: tensor(-932.5129, device='cuda:0')
episode: 27 training return: tensor(-866.7421, device='cuda:0')
epoch: 7 test_true_pfm: 214.30478285359675 sim_pfm: -880.0730932108903
episode: 28 training return: tensor(-939.4823, device='cuda:0')
episode: 29 training return: tensor(-818.9340, device='cuda:0')
episode: 30 training return: tensor(-937.2887, device='cuda:0')
episode: 31 training return: tensor(-824.4159, device='cuda:0')
epoch: 8 test_true_pfm: -46.02786374519309 sim_pfm: -964.4351094936331
episode: 32 training return: tensor(-895.5551, device='cuda:0')
episode: 33 training return: tensor(-950.6252, device='cuda:0')
episode: 34 training return: tensor(-952.0706, device='cuda:0')
episode: 35 training return: tensor(-857.4214, device='cuda:0')
epoch: 9 test_true_pfm: 115.45402903948047 sim_pfm: -939.5196420773864
episode: 36 training return: tensor(-968.2154, device='cuda:0')
episode: 37 training return: tensor(-942.7744, device='cuda:0')
episode: 38 training return: tensor(-940.3714, device='cuda:0')
episode: 39 training return: tensor(-963.8215, device='cuda:0')
epoch: 10 test_true_pfm: 95.01687741528308 sim_pfm: -915.3648807952801
episode: 40 training return: tensor(-948.0959, device='cuda:0')
episode: 41 training return: tensor(-851.1597, device='cuda:0')
episode: 42 training return: tensor(-946.9217, device='cuda:0')
episode: 43 training return: tensor(-947.8593, device='cuda:0')
epoch: 11 test_true_pfm: 144.61069303512986 sim_pfm: -965.5334496721625
episode: 44 training return: tensor(-944.4326, device='cuda:0')
episode: 45 training return: tensor(-935.1957, device='cuda:0')
episode: 46 training return: tensor(-936.3102, device='cuda:0')
episode: 47 training return: tensor(-948.9153, device='cuda:0')
epoch: 12 test_true_pfm: 107.35892892199466 sim_pfm: -968.4829675510604
episode: 48 training return: tensor(-944.7701, device='cuda:0')
episode: 49 training return: tensor(-946.9773, device='cuda:0')
episode: 50 training return: tensor(-950.9966, device='cuda:0')
episode: 51 training return: tensor(-951.6390, device='cuda:0')
epoch: 13 test_true_pfm: 128.30421837147847 sim_pfm: -955.3397499819597
episode: 52 training return: tensor(-946.3957, device='cuda:0')
episode: 53 training return: tensor(-960.0231, device='cuda:0')
episode: 54 training return: tensor(-943.7980, device='cuda:0')
episode: 55 training return: tensor(-937.4483, device='cuda:0')
epoch: 14 test_true_pfm: 134.5077256187092 sim_pfm: -949.467339416345
episode: 56 training return: tensor(-935.2037, device='cuda:0')
episode: 57 training return: tensor(-943.9854, device='cuda:0')
episode: 58 training return: tensor(-949.1948, device='cuda:0')
episode: 59 training return: tensor(-943.3461, device='cuda:0')
epoch: 15 test_true_pfm: 131.83292893896584 sim_pfm: -951.2849981371934
episode: 60 training return: tensor(-942.8079, device='cuda:0')
episode: 61 training return: tensor(-935.2529, device='cuda:0')
episode: 62 training return: tensor(-948.1569, device='cuda:0')
episode: 63 training return: tensor(-942.0092, device='cuda:0')
epoch: 16 test_true_pfm: 128.17030506562037 sim_pfm: -960.1082734627029
episode: 64 training return: tensor(-950.8345, device='cuda:0')
episode: 65 training return: tensor(-948.5786, device='cuda:0')
episode: 66 training return: tensor(-929.6284, device='cuda:0')
episode: 67 training return: tensor(-952.5047, device='cuda:0')
epoch: 17 test_true_pfm: 132.8055251220842 sim_pfm: -961.8361060696383
episode: 68 training return: tensor(-947.6182, device='cuda:0')
episode: 69 training return: tensor(-954.0211, device='cuda:0')
episode: 70 training return: tensor(-932.1636, device='cuda:0')
episode: 71 training return: tensor(-951.0283, device='cuda:0')
epoch: 18 test_true_pfm: 119.72714857987943 sim_pfm: -960.927297608306
episode: 72 training return: tensor(-932.5680, device='cuda:0')
episode: 73 training return: tensor(-935.1992, device='cuda:0')
episode: 74 training return: tensor(-929.9003, device='cuda:0')
episode: 75 training return: tensor(-941.4650, device='cuda:0')
epoch: 19 test_true_pfm: 145.72839757584867 sim_pfm: -931.0842273974171
episode: 76 training return: tensor(-918.7529, device='cuda:0')
episode: 77 training return: tensor(-935.8194, device='cuda:0')
episode: 78 training return: tensor(-930.3159, device='cuda:0')
episode: 79 training return: tensor(-929.6143, device='cuda:0')
epoch: 20 test_true_pfm: 142.17280752121144 sim_pfm: -920.4967051176354
episode: 80 training return: tensor(-955.3638, device='cuda:0')
episode: 81 training return: tensor(-926.9933, device='cuda:0')
episode: 82 training return: tensor(-938.8086, device='cuda:0')
episode: 83 training return: tensor(-925.1978, device='cuda:0')
epoch: 21 test_true_pfm: 144.1270275995311 sim_pfm: -953.6665545168022
episode: 84 training return: tensor(-904.4391, device='cuda:0')
episode: 85 training return: tensor(-934.6260, device='cuda:0')
episode: 86 training return: tensor(-936.9885, device='cuda:0')
episode: 87 training return: tensor(-919.5355, device='cuda:0')
epoch: 22 test_true_pfm: 149.58758264724224 sim_pfm: -911.1290327211221
episode: 88 training return: tensor(-905.0352, device='cuda:0')
episode: 89 training return: tensor(-933.4393, device='cuda:0')
episode: 90 training return: tensor(-928.4905, device='cuda:0')
episode: 91 training return: tensor(-922.9500, device='cuda:0')
epoch: 23 test_true_pfm: 150.31767526068975 sim_pfm: -905.6995966586595
episode: 92 training return: tensor(-932.5905, device='cuda:0')
episode: 93 training return: tensor(-933.9146, device='cuda:0')
episode: 94 training return: tensor(-927.0463, device='cuda:0')
episode: 95 training return: tensor(-924.1284, device='cuda:0')
epoch: 24 test_true_pfm: 160.76478353465978 sim_pfm: -903.0354314694802
episode: 96 training return: tensor(-931.2416, device='cuda:0')
episode: 97 training return: tensor(-923.7632, device='cuda:0')
episode: 98 training return: tensor(-911.4894, device='cuda:0')
episode: 99 training return: tensor(-936.6559, device='cuda:0')
epoch: 25 test_true_pfm: 139.25699608112222 sim_pfm: -900.5392703140775
episode: 100 training return: tensor(-906.9117, device='cuda:0')
episode: 101 training return: tensor(-933.9959, device='cuda:0')
episode: 102 training return: tensor(-924.4185, device='cuda:0')
episode: 103 training return: tensor(-921.5911, device='cuda:0')
epoch: 26 test_true_pfm: 150.60381933212668 sim_pfm: -903.230567013224
episode: 104 training return: tensor(-918.0838, device='cuda:0')
episode: 105 training return: tensor(-922.6028, device='cuda:0')
episode: 106 training return: tensor(-922.1490, device='cuda:0')
episode: 107 training return: tensor(-926.0939, device='cuda:0')
epoch: 27 test_true_pfm: 166.97640041818974 sim_pfm: -909.3016445326308
episode: 108 training return: tensor(-927.5867, device='cuda:0')
episode: 109 training return: tensor(-903.1128, device='cuda:0')
episode: 110 training return: tensor(-920.4001, device='cuda:0')
episode: 111 training return: tensor(-923.2296, device='cuda:0')
epoch: 28 test_true_pfm: 150.50876766092003 sim_pfm: -899.0199083673457
episode: 112 training return: tensor(-920.6127, device='cuda:0')
episode: 113 training return: tensor(-919.6750, device='cuda:0')
episode: 114 training return: tensor(-922.1700, device='cuda:0')
episode: 115 training return: tensor(-917.7390, device='cuda:0')
epoch: 29 test_true_pfm: 136.76694324069888 sim_pfm: -919.4901405417671
episode: 116 training return: tensor(-934.4924, device='cuda:0')
episode: 117 training return: tensor(-935.7181, device='cuda:0')
episode: 118 training return: tensor(-925.4185, device='cuda:0')
episode: 119 training return: tensor(-925.6359, device='cuda:0')
epoch: 30 test_true_pfm: 123.27193906552412 sim_pfm: -904.9647848904133
episode: 120 training return: tensor(-921.6763, device='cuda:0')
episode: 121 training return: tensor(-916.6459, device='cuda:0')
episode: 122 training return: tensor(-917.0886, device='cuda:0')
episode: 123 training return: tensor(-921.4225, device='cuda:0')
epoch: 31 test_true_pfm: 148.6519258207127 sim_pfm: -899.1594301412503
episode: 124 training return: tensor(-930.0762, device='cuda:0')
episode: 125 training return: tensor(-924.3045, device='cuda:0')
episode: 126 training return: tensor(-927.7917, device='cuda:0')
episode: 127 training return: tensor(-915.4689, device='cuda:0')
epoch: 32 test_true_pfm: 148.16897105927163 sim_pfm: -900.7358067035675
episode: 128 training return: tensor(-929.1691, device='cuda:0')
episode: 129 training return: tensor(-925.6663, device='cuda:0')
episode: 130 training return: tensor(-937.0739, device='cuda:0')
episode: 131 training return: tensor(-879.2549, device='cuda:0')
epoch: 33 test_true_pfm: 127.38563939232908 sim_pfm: -900.6206424856404
episode: 132 training return: tensor(-930.3394, device='cuda:0')
episode: 133 training return: tensor(-926.0717, device='cuda:0')
episode: 134 training return: tensor(-933.3926, device='cuda:0')
episode: 135 training return: tensor(-919.1853, device='cuda:0')
epoch: 34 test_true_pfm: 148.05947181647775 sim_pfm: -902.404950649788
episode: 136 training return: tensor(-900.8812, device='cuda:0')
episode: 137 training return: tensor(-926.8860, device='cuda:0')
episode: 138 training return: tensor(-920.3354, device='cuda:0')
episode: 139 training return: tensor(-912.4293, device='cuda:0')
epoch: 35 test_true_pfm: 110.4735714391112 sim_pfm: -911.0917301860949
episode: 140 training return: tensor(-930.4030, device='cuda:0')
episode: 141 training return: tensor(-912.7944, device='cuda:0')
episode: 142 training return: tensor(-903.6020, device='cuda:0')
episode: 143 training return: tensor(-926.6430, device='cuda:0')
epoch: 36 test_true_pfm: 154.22949809004 sim_pfm: -913.6851762980223
episode: 144 training return: tensor(-919.0410, device='cuda:0')
episode: 145 training return: tensor(-923.2408, device='cuda:0')
episode: 146 training return: tensor(-923.7101, device='cuda:0')
episode: 147 training return: tensor(-912.0178, device='cuda:0')
epoch: 37 test_true_pfm: 149.6588065333975 sim_pfm: -907.1838838557402
episode: 148 training return: tensor(-918.3672, device='cuda:0')
episode: 149 training return: tensor(-911.6242, device='cuda:0')
episode: 150 training return: tensor(-913.6656, device='cuda:0')
episode: 151 training return: tensor(-913.2626, device='cuda:0')
epoch: 38 test_true_pfm: 152.14824713445765 sim_pfm: -906.6487533406665
episode: 152 training return: tensor(-935.8597, device='cuda:0')
episode: 153 training return: tensor(-924.7170, device='cuda:0')
episode: 154 training return: tensor(-914.1549, device='cuda:0')
episode: 155 training return: tensor(-916.6628, device='cuda:0')
epoch: 39 test_true_pfm: 115.5952744159246 sim_pfm: -914.5903848856688
episode: 156 training return: tensor(-926.4594, device='cuda:0')
episode: 157 training return: tensor(-925.5507, device='cuda:0')
episode: 158 training return: tensor(-915.6726, device='cuda:0')
episode: 159 training return: tensor(-913.8538, device='cuda:0')
epoch: 40 test_true_pfm: 149.81768158278777 sim_pfm: -907.0089222912987
episode: 160 training return: tensor(-934.0681, device='cuda:0')
episode: 161 training return: tensor(-922.3125, device='cuda:0')
episode: 162 training return: tensor(-930.5118, device='cuda:0')
episode: 163 training return: tensor(-928.9415, device='cuda:0')
epoch: 41 test_true_pfm: 157.501259257642 sim_pfm: -898.9461077898741
episode: 164 training return: tensor(-919.3682, device='cuda:0')
episode: 165 training return: tensor(-919.8788, device='cuda:0')
episode: 166 training return: tensor(-924.4461, device='cuda:0')
episode: 167 training return: tensor(-913.4376, device='cuda:0')
epoch: 42 test_true_pfm: 149.61990186758973 sim_pfm: -910.4298710599542
episode: 168 training return: tensor(-923.1501, device='cuda:0')
episode: 169 training return: tensor(-922.8450, device='cuda:0')
episode: 170 training return: tensor(-923.8502, device='cuda:0')
episode: 171 training return: tensor(-895.2895, device='cuda:0')
epoch: 43 test_true_pfm: 126.49476616299039 sim_pfm: -911.7860400661206
episode: 172 training return: tensor(-919.2871, device='cuda:0')
episode: 173 training return: tensor(-927.7164, device='cuda:0')
episode: 174 training return: tensor(-920.5391, device='cuda:0')
episode: 175 training return: tensor(-914.6221, device='cuda:0')
epoch: 44 test_true_pfm: 147.18534460928188 sim_pfm: -903.6304934223493
episode: 176 training return: tensor(-917.3384, device='cuda:0')
episode: 177 training return: tensor(-903.8062, device='cuda:0')
episode: 178 training return: tensor(-928.5755, device='cuda:0')
episode: 179 training return: tensor(-917.4070, device='cuda:0')
epoch: 45 test_true_pfm: 158.19202403540507 sim_pfm: -897.2342293759187
episode: 180 training return: tensor(-922.1470, device='cuda:0')
episode: 181 training return: tensor(-920.9970, device='cuda:0')
episode: 182 training return: tensor(-918.5058, device='cuda:0')
episode: 183 training return: tensor(-912.8579, device='cuda:0')
epoch: 46 test_true_pfm: 140.91850354735013 sim_pfm: -903.517003039519
episode: 184 training return: tensor(-928.9948, device='cuda:0')
episode: 185 training return: tensor(-917.4050, device='cuda:0')
episode: 186 training return: tensor(-934.3618, device='cuda:0')
episode: 187 training return: tensor(-910.1494, device='cuda:0')
epoch: 47 test_true_pfm: 136.61451232554643 sim_pfm: -911.9821364209056
episode: 188 training return: tensor(-924.8484, device='cuda:0')
episode: 189 training return: tensor(-925.3797, device='cuda:0')
episode: 190 training return: tensor(-930.4911, device='cuda:0')
episode: 191 training return: tensor(-926.5306, device='cuda:0')
epoch: 48 test_true_pfm: 147.72778406863816 sim_pfm: -901.4456182867289
episode: 192 training return: tensor(-918.5518, device='cuda:0')
episode: 193 training return: tensor(-924.7930, device='cuda:0')
episode: 194 training return: tensor(-915.4359, device='cuda:0')
episode: 195 training return: tensor(-931.1403, device='cuda:0')
epoch: 49 test_true_pfm: 167.915438406118 sim_pfm: -911.7750469918052
episode: 196 training return: tensor(-918.8129, device='cuda:0')
episode: 197 training return: tensor(-910.2391, device='cuda:0')
episode: 198 training return: tensor(-917.0599, device='cuda:0')
episode: 199 training return: tensor(-923.6724, device='cuda:0')
epoch: 50 test_true_pfm: 157.40878073330853 sim_pfm: -902.5017130623261
episode: 200 training return: tensor(-917.8326, device='cuda:0')
episode: 201 training return: tensor(-926.7974, device='cuda:0')
episode: 202 training return: tensor(-923.1252, device='cuda:0')
episode: 203 training return: tensor(-919.3448, device='cuda:0')
epoch: 51 test_true_pfm: 151.90009901450932 sim_pfm: -908.5888992018687
episode: 204 training return: tensor(-927.7964, device='cuda:0')
episode: 205 training return: tensor(-906.9675, device='cuda:0')
episode: 206 training return: tensor(-925.1722, device='cuda:0')
episode: 207 training return: tensor(-918.4234, device='cuda:0')
epoch: 52 test_true_pfm: 107.94729208499983 sim_pfm: -910.7425970559319
episode: 208 training return: tensor(-921.4743, device='cuda:0')
episode: 209 training return: tensor(-929.2339, device='cuda:0')
episode: 210 training return: tensor(-923.8232, device='cuda:0')
episode: 211 training return: tensor(-937.9003, device='cuda:0')
epoch: 53 test_true_pfm: 169.30261146714022 sim_pfm: -910.1672899561623
episode: 212 training return: tensor(-909.4916, device='cuda:0')
episode: 213 training return: tensor(-934.0403, device='cuda:0')
episode: 214 training return: tensor(-920.4285, device='cuda:0')
episode: 215 training return: tensor(-928.9506, device='cuda:0')
epoch: 54 test_true_pfm: 126.82519724372209 sim_pfm: -913.5792347341776
episode: 216 training return: tensor(-916.7679, device='cuda:0')
episode: 217 training return: tensor(-922.9509, device='cuda:0')
episode: 218 training return: tensor(-918.1409, device='cuda:0')
episode: 219 training return: tensor(-905.3317, device='cuda:0')
epoch: 55 test_true_pfm: 152.22893376460578 sim_pfm: -911.9084747073551
episode: 220 training return: tensor(-923.7029, device='cuda:0')
episode: 221 training return: tensor(-927.3366, device='cuda:0')
episode: 222 training return: tensor(-929.2416, device='cuda:0')
episode: 223 training return: tensor(-932.0309, device='cuda:0')
epoch: 56 test_true_pfm: 132.07019392043324 sim_pfm: -959.6053839797775
episode: 224 training return: tensor(-926.8582, device='cuda:0')
episode: 225 training return: tensor(-911.8344, device='cuda:0')
episode: 226 training return: tensor(-906.8067, device='cuda:0')
episode: 227 training return: tensor(-927.0173, device='cuda:0')
epoch: 57 test_true_pfm: 145.48237660285136 sim_pfm: -915.0519307255745
episode: 228 training return: tensor(-919.3752, device='cuda:0')
episode: 229 training return: tensor(-920.3946, device='cuda:0')
episode: 230 training return: tensor(-916.3805, device='cuda:0')
episode: 231 training return: tensor(-919.2682, device='cuda:0')
epoch: 58 test_true_pfm: 116.38450349464604 sim_pfm: -916.6403009568652
episode: 232 training return: tensor(-921.4736, device='cuda:0')
episode: 233 training return: tensor(-881.4492, device='cuda:0')
episode: 234 training return: tensor(-907.9706, device='cuda:0')
episode: 235 training return: tensor(-910.1379, device='cuda:0')
epoch: 59 test_true_pfm: 139.96848250146118 sim_pfm: -910.1664369876186
episode: 236 training return: tensor(-922.9879, device='cuda:0')
episode: 237 training return: tensor(-921.5110, device='cuda:0')
episode: 238 training return: tensor(-908.6019, device='cuda:0')
episode: 239 training return: tensor(-867.5945, device='cuda:0')
epoch: 60 test_true_pfm: 146.9223721263811 sim_pfm: -910.614195095996
episode: 240 training return: tensor(-924.2551, device='cuda:0')
episode: 241 training return: tensor(-916.9076, device='cuda:0')
episode: 242 training return: tensor(-936.5280, device='cuda:0')
episode: 243 training return: tensor(-907.0183, device='cuda:0')
epoch: 61 test_true_pfm: 138.31219821875456 sim_pfm: -922.1567397514979
episode: 244 training return: tensor(-923.0829, device='cuda:0')
episode: 245 training return: tensor(-918.4058, device='cuda:0')
episode: 246 training return: tensor(-913.0594, device='cuda:0')
episode: 247 training return: tensor(-929.7553, device='cuda:0')
epoch: 62 test_true_pfm: 150.52028520837402 sim_pfm: -912.95585672309
episode: 248 training return: tensor(-927.1636, device='cuda:0')
episode: 249 training return: tensor(-920.2800, device='cuda:0')
episode: 250 training return: tensor(-922.4748, device='cuda:0')
episode: 251 training return: tensor(-918.0836, device='cuda:0')
epoch: 63 test_true_pfm: 148.7445546928391 sim_pfm: -915.8123048320413
episode: 252 training return: tensor(-925.7140, device='cuda:0')
episode: 253 training return: tensor(-908.6699, device='cuda:0')
episode: 254 training return: tensor(-917.7114, device='cuda:0')
episode: 255 training return: tensor(-906.1932, device='cuda:0')
epoch: 64 test_true_pfm: 149.4277883881301 sim_pfm: -907.2139056399465
episode: 256 training return: tensor(-930.3650, device='cuda:0')
episode: 257 training return: tensor(-907.1146, device='cuda:0')
episode: 258 training return: tensor(-919.2076, device='cuda:0')
episode: 259 training return: tensor(-908.2032, device='cuda:0')
epoch: 65 test_true_pfm: 155.20155823961562 sim_pfm: -907.0273781915506
episode: 260 training return: tensor(-919.0842, device='cuda:0')
episode: 261 training return: tensor(-923.3625, device='cuda:0')
episode: 262 training return: tensor(-909.7269, device='cuda:0')
episode: 263 training return: tensor(-913.7280, device='cuda:0')
epoch: 66 test_true_pfm: 146.08525237177216 sim_pfm: -910.1880096122622
episode: 264 training return: tensor(-923.7570, device='cuda:0')
episode: 265 training return: tensor(-915.4196, device='cuda:0')
episode: 266 training return: tensor(-917.4874, device='cuda:0')
episode: 267 training return: tensor(-893.3687, device='cuda:0')
epoch: 67 test_true_pfm: 161.18718102563008 sim_pfm: -909.3274822632471
episode: 268 training return: tensor(-939.3593, device='cuda:0')
episode: 269 training return: tensor(-922.1147, device='cuda:0')
episode: 270 training return: tensor(-924.1240, device='cuda:0')
episode: 271 training return: tensor(-904.9221, device='cuda:0')
epoch: 68 test_true_pfm: 152.90040835742604 sim_pfm: -908.1310582396885
episode: 272 training return: tensor(-938.3560, device='cuda:0')
episode: 273 training return: tensor(-919.8152, device='cuda:0')
episode: 274 training return: tensor(-921.7075, device='cuda:0')
episode: 275 training return: tensor(-923.0610, device='cuda:0')
epoch: 69 test_true_pfm: 152.09779089148358 sim_pfm: -908.3292157997688
episode: 276 training return: tensor(-922.4092, device='cuda:0')
episode: 277 training return: tensor(-912.2678, device='cuda:0')
episode: 278 training return: tensor(-929.6741, device='cuda:0')
episode: 279 training return: tensor(-922.9850, device='cuda:0')
epoch: 70 test_true_pfm: 157.00693658591058 sim_pfm: -906.7935139536858
episode: 280 training return: tensor(-930.9963, device='cuda:0')
episode: 281 training return: tensor(-926.7689, device='cuda:0')
episode: 282 training return: tensor(-933.1593, device='cuda:0')
episode: 283 training return: tensor(-921.0540, device='cuda:0')
epoch: 71 test_true_pfm: 133.10992227909546 sim_pfm: -920.4055654058853
episode: 284 training return: tensor(-923.9547, device='cuda:0')
episode: 285 training return: tensor(-927.8775, device='cuda:0')
episode: 286 training return: tensor(-891.8401, device='cuda:0')
episode: 287 training return: tensor(-929.0124, device='cuda:0')
epoch: 72 test_true_pfm: 150.81069487135437 sim_pfm: -908.2477734036123
episode: 288 training return: tensor(-922.1209, device='cuda:0')
episode: 289 training return: tensor(-916.2629, device='cuda:0')
episode: 290 training return: tensor(-912.3876, device='cuda:0')
episode: 291 training return: tensor(-912.7791, device='cuda:0')
epoch: 73 test_true_pfm: 145.06634207284537 sim_pfm: -929.870340163509
episode: 292 training return: tensor(-923.5399, device='cuda:0')
episode: 293 training return: tensor(-911.4509, device='cuda:0')
episode: 294 training return: tensor(-902.2657, device='cuda:0')
episode: 295 training return: tensor(-924.2375, device='cuda:0')
epoch: 74 test_true_pfm: 103.35642888047836 sim_pfm: -917.5315528810024
episode: 296 training return: tensor(-902.3134, device='cuda:0')
episode: 297 training return: tensor(-923.8030, device='cuda:0')
episode: 298 training return: tensor(-927.6718, device='cuda:0')
episode: 299 training return: tensor(-898.0149, device='cuda:0')
epoch: 75 test_true_pfm: 165.66910307006552 sim_pfm: -907.2501988460621
episode: 300 training return: tensor(-920.7888, device='cuda:0')
episode: 301 training return: tensor(-927.1551, device='cuda:0')
episode: 302 training return: tensor(-918.1635, device='cuda:0')
episode: 303 training return: tensor(-927.0872, device='cuda:0')
epoch: 76 test_true_pfm: 170.28895240635913 sim_pfm: -908.9855759702623
episode: 304 training return: tensor(-923.4266, device='cuda:0')
episode: 305 training return: tensor(-924.9597, device='cuda:0')
episode: 306 training return: tensor(-923.0850, device='cuda:0')
episode: 307 training return: tensor(-925.0840, device='cuda:0')
epoch: 77 test_true_pfm: 148.18457372064975 sim_pfm: -909.06487159885
episode: 308 training return: tensor(-925.1103, device='cuda:0')
episode: 309 training return: tensor(-939.3882, device='cuda:0')
episode: 310 training return: tensor(-907.2047, device='cuda:0')
episode: 311 training return: tensor(-923.3204, device='cuda:0')
epoch: 78 test_true_pfm: 158.5030690387355 sim_pfm: -909.0202814272294
episode: 312 training return: tensor(-902.5276, device='cuda:0')
episode: 313 training return: tensor(-916.0154, device='cuda:0')
episode: 314 training return: tensor(-921.6841, device='cuda:0')
episode: 315 training return: tensor(-920.9700, device='cuda:0')
epoch: 79 test_true_pfm: 161.61038609342862 sim_pfm: -930.3119460095962
episode: 316 training return: tensor(-912.9888, device='cuda:0')
episode: 317 training return: tensor(-936.2744, device='cuda:0')
episode: 318 training return: tensor(-920.4166, device='cuda:0')
episode: 319 training return: tensor(-909.6131, device='cuda:0')
epoch: 80 test_true_pfm: 149.89124726380746 sim_pfm: -927.1542260455899
episode: 320 training return: tensor(-920.0986, device='cuda:0')
episode: 321 training return: tensor(-894.6332, device='cuda:0')
episode: 322 training return: tensor(-926.5859, device='cuda:0')
episode: 323 training return: tensor(-905.1388, device='cuda:0')
epoch: 81 test_true_pfm: 148.49249705395727 sim_pfm: -909.1447047367692
episode: 324 training return: tensor(-927.3513, device='cuda:0')
episode: 325 training return: tensor(-912.5060, device='cuda:0')
episode: 326 training return: tensor(-905.4333, device='cuda:0')
episode: 327 training return: tensor(-922.1589, device='cuda:0')
epoch: 82 test_true_pfm: 159.47232898567043 sim_pfm: -908.8736347729961
episode: 328 training return: tensor(-910.9095, device='cuda:0')
episode: 329 training return: tensor(-914.7228, device='cuda:0')
episode: 330 training return: tensor(-935.9276, device='cuda:0')
episode: 331 training return: tensor(-916.0136, device='cuda:0')
epoch: 83 test_true_pfm: 125.86929620110733 sim_pfm: -923.787226508061
episode: 332 training return: tensor(-920.6915, device='cuda:0')
episode: 333 training return: tensor(-914.8773, device='cuda:0')
episode: 334 training return: tensor(-918.3048, device='cuda:0')
episode: 335 training return: tensor(-919.2152, device='cuda:0')
epoch: 84 test_true_pfm: 129.93610416677237 sim_pfm: -908.5671350744864
episode: 336 training return: tensor(-917.4332, device='cuda:0')
episode: 337 training return: tensor(-922.0614, device='cuda:0')
episode: 338 training return: tensor(-919.6100, device='cuda:0')
episode: 339 training return: tensor(-930.7924, device='cuda:0')
epoch: 85 test_true_pfm: 152.91917504753312 sim_pfm: -906.5186388703684
episode: 340 training return: tensor(-932.5068, device='cuda:0')
episode: 341 training return: tensor(-927.2448, device='cuda:0')
episode: 342 training return: tensor(-922.8541, device='cuda:0')
episode: 343 training return: tensor(-927.6904, device='cuda:0')
epoch: 86 test_true_pfm: 157.0896197142209 sim_pfm: -925.1226154758284
episode: 344 training return: tensor(-927.5741, device='cuda:0')
episode: 345 training return: tensor(-916.9228, device='cuda:0')
episode: 346 training return: tensor(-915.8650, device='cuda:0')
episode: 347 training return: tensor(-923.0309, device='cuda:0')
epoch: 87 test_true_pfm: 113.79117348390184 sim_pfm: -911.3348666969687
episode: 348 training return: tensor(-925.3771, device='cuda:0')
episode: 349 training return: tensor(-925.9780, device='cuda:0')
episode: 350 training return: tensor(-914.6312, device='cuda:0')
episode: 351 training return: tensor(-920.3592, device='cuda:0')
epoch: 88 test_true_pfm: 131.9426024937417 sim_pfm: -907.7371588945389
episode: 352 training return: tensor(-921.7294, device='cuda:0')
episode: 353 training return: tensor(-914.0856, device='cuda:0')
episode: 354 training return: tensor(-933.8123, device='cuda:0')
episode: 355 training return: tensor(-921.3750, device='cuda:0')
epoch: 89 test_true_pfm: 136.41459265205768 sim_pfm: -910.6662801642864
episode: 356 training return: tensor(-930.7097, device='cuda:0')
episode: 357 training return: tensor(-912.4797, device='cuda:0')
episode: 358 training return: tensor(-915.8882, device='cuda:0')
episode: 359 training return: tensor(-923.9153, device='cuda:0')
epoch: 90 test_true_pfm: 149.612601098315 sim_pfm: -911.4723110819856
episode: 360 training return: tensor(-908.6056, device='cuda:0')
episode: 361 training return: tensor(-918.0065, device='cuda:0')
episode: 362 training return: tensor(-918.8307, device='cuda:0')
episode: 363 training return: tensor(-899.4377, device='cuda:0')
epoch: 91 test_true_pfm: 149.6338110828266 sim_pfm: -909.6155566945672
episode: 364 training return: tensor(-929.2056, device='cuda:0')
episode: 365 training return: tensor(-923.0666, device='cuda:0')
episode: 366 training return: tensor(-916.6569, device='cuda:0')
episode: 367 training return: tensor(-920.6718, device='cuda:0')
epoch: 92 test_true_pfm: 137.199012747946 sim_pfm: -909.3968346516291
episode: 368 training return: tensor(-911.8262, device='cuda:0')
episode: 369 training return: tensor(-907.4906, device='cuda:0')
episode: 370 training return: tensor(-920.6722, device='cuda:0')
episode: 371 training return: tensor(-898.3119, device='cuda:0')
epoch: 93 test_true_pfm: 150.8201078267476 sim_pfm: -910.0578305342545
episode: 372 training return: tensor(-921.4250, device='cuda:0')
episode: 373 training return: tensor(-921.0191, device='cuda:0')
episode: 374 training return: tensor(-932.3220, device='cuda:0')
episode: 375 training return: tensor(-912.9949, device='cuda:0')
epoch: 94 test_true_pfm: 134.74683539101372 sim_pfm: -915.300111832718
episode: 376 training return: tensor(-912.9016, device='cuda:0')
episode: 377 training return: tensor(-907.3831, device='cuda:0')
episode: 378 training return: tensor(-911.7551, device='cuda:0')
episode: 379 training return: tensor(-903.2833, device='cuda:0')
epoch: 95 test_true_pfm: 157.0929968673073 sim_pfm: -909.7452651411295
episode: 380 training return: tensor(-921.5938, device='cuda:0')
episode: 381 training return: tensor(-908.6401, device='cuda:0')
episode: 382 training return: tensor(-920.3425, device='cuda:0')
episode: 383 training return: tensor(-924.4719, device='cuda:0')
epoch: 96 test_true_pfm: 151.52819414519692 sim_pfm: -909.7947863253454
episode: 384 training return: tensor(-913.7493, device='cuda:0')
episode: 385 training return: tensor(-912.0210, device='cuda:0')
episode: 386 training return: tensor(-920.9597, device='cuda:0')
episode: 387 training return: tensor(-929.2147, device='cuda:0')
epoch: 97 test_true_pfm: 133.8158262746821 sim_pfm: -909.9011899717152
episode: 388 training return: tensor(-937.4022, device='cuda:0')
episode: 389 training return: tensor(-925.4982, device='cuda:0')
episode: 390 training return: tensor(-922.2355, device='cuda:0')
episode: 391 training return: tensor(-913.5969, device='cuda:0')
epoch: 98 test_true_pfm: 122.38617829814666 sim_pfm: -927.3955122294525
episode: 392 training return: tensor(-915.0900, device='cuda:0')
episode: 393 training return: tensor(-920.3414, device='cuda:0')
episode: 394 training return: tensor(-913.2889, device='cuda:0')
episode: 395 training return: tensor(-919.0093, device='cuda:0')
epoch: 99 test_true_pfm: 160.65971767820153 sim_pfm: -914.2324954755604
episode: 396 training return: tensor(-923.9980, device='cuda:0')
episode: 397 training return: tensor(-923.5923, device='cuda:0')
episode: 398 training return: tensor(-902.7618, device='cuda:0')
episode: 399 training return: tensor(-921.7030, device='cuda:0')
epoch: 100 test_true_pfm: 137.7659725336725 sim_pfm: -927.2421965748072
episode: 400 training return: tensor(-924.4567, device='cuda:0')
episode: 401 training return: tensor(-922.9005, device='cuda:0')
episode: 402 training return: tensor(-930.0505, device='cuda:0')
episode: 403 training return: tensor(-893.2618, device='cuda:0')
epoch: 101 test_true_pfm: 149.65192514654402 sim_pfm: -909.954719464799
episode: 404 training return: tensor(-924.1868, device='cuda:0')
episode: 405 training return: tensor(-916.7488, device='cuda:0')
episode: 406 training return: tensor(-921.3331, device='cuda:0')
episode: 407 training return: tensor(-911.7751, device='cuda:0')
epoch: 102 test_true_pfm: 146.9649533475807 sim_pfm: -909.8618098944426
episode: 408 training return: tensor(-906.6580, device='cuda:0')
episode: 409 training return: tensor(-928.6304, device='cuda:0')
episode: 410 training return: tensor(-924.3387, device='cuda:0')
episode: 411 training return: tensor(-909.6685, device='cuda:0')
epoch: 103 test_true_pfm: 158.03688372254263 sim_pfm: -909.0983015745878
episode: 412 training return: tensor(-938.1429, device='cuda:0')
episode: 413 training return: tensor(-928.1593, device='cuda:0')
episode: 414 training return: tensor(-925.1741, device='cuda:0')
episode: 415 training return: tensor(-910.6664, device='cuda:0')
epoch: 104 test_true_pfm: 129.11151872626095 sim_pfm: -914.7040797024965
episode: 416 training return: tensor(-927.9411, device='cuda:0')
episode: 417 training return: tensor(-895.6483, device='cuda:0')
episode: 418 training return: tensor(-926.6478, device='cuda:0')
episode: 419 training return: tensor(-907.8381, device='cuda:0')
epoch: 105 test_true_pfm: 146.91169280402693 sim_pfm: -909.5732086375356
episode: 420 training return: tensor(-911.3604, device='cuda:0')
episode: 421 training return: tensor(-905.8497, device='cuda:0')
episode: 422 training return: tensor(-929.7871, device='cuda:0')
episode: 423 training return: tensor(-917.6213, device='cuda:0')
epoch: 106 test_true_pfm: 154.11583560699412 sim_pfm: -909.1839285170039
episode: 424 training return: tensor(-930.5110, device='cuda:0')
episode: 425 training return: tensor(-925.6981, device='cuda:0')
episode: 426 training return: tensor(-921.0698, device='cuda:0')
episode: 427 training return: tensor(-925.6144, device='cuda:0')
epoch: 107 test_true_pfm: 149.3125406974697 sim_pfm: -913.4862182761232
episode: 428 training return: tensor(-936.2260, device='cuda:0')
episode: 429 training return: tensor(-930.7767, device='cuda:0')
episode: 430 training return: tensor(-913.4651, device='cuda:0')
episode: 431 training return: tensor(-894.3323, device='cuda:0')
epoch: 108 test_true_pfm: 140.07199331221892 sim_pfm: -908.5869435394803
episode: 432 training return: tensor(-919.3690, device='cuda:0')
episode: 433 training return: tensor(-913.8257, device='cuda:0')
episode: 434 training return: tensor(-927.1763, device='cuda:0')
episode: 435 training return: tensor(-921.3783, device='cuda:0')
epoch: 109 test_true_pfm: 151.00178677119342 sim_pfm: -903.4795747343451
episode: 436 training return: tensor(-922.0306, device='cuda:0')
episode: 437 training return: tensor(-909.4106, device='cuda:0')
episode: 438 training return: tensor(-916.9609, device='cuda:0')
episode: 439 training return: tensor(-895.5142, device='cuda:0')
epoch: 110 test_true_pfm: 139.018434425503 sim_pfm: -911.67695071653
episode: 440 training return: tensor(-921.4149, device='cuda:0')
episode: 441 training return: tensor(-916.1653, device='cuda:0')
episode: 442 training return: tensor(-913.3234, device='cuda:0')
episode: 443 training return: tensor(-910.5461, device='cuda:0')
epoch: 111 test_true_pfm: 148.87827730654763 sim_pfm: -908.7132260203362
episode: 444 training return: tensor(-913.3964, device='cuda:0')
episode: 445 training return: tensor(-932.5301, device='cuda:0')
episode: 446 training return: tensor(-915.6604, device='cuda:0')
episode: 447 training return: tensor(-889.1600, device='cuda:0')
epoch: 112 test_true_pfm: 157.16772765026664 sim_pfm: -904.0607952872912
episode: 448 training return: tensor(-915.5806, device='cuda:0')
episode: 449 training return: tensor(-895.5916, device='cuda:0')
episode: 450 training return: tensor(-931.3054, device='cuda:0')
episode: 451 training return: tensor(-919.7626, device='cuda:0')
epoch: 113 test_true_pfm: 163.94150070849983 sim_pfm: -908.980697552363
episode: 452 training return: tensor(-912.3981, device='cuda:0')
episode: 453 training return: tensor(-917.7223, device='cuda:0')
episode: 454 training return: tensor(-923.5731, device='cuda:0')
episode: 455 training return: tensor(-867.8743, device='cuda:0')
epoch: 114 test_true_pfm: 147.60409070651528 sim_pfm: -908.7217743135989
episode: 456 training return: tensor(-914.4322, device='cuda:0')
episode: 457 training return: tensor(-899.9038, device='cuda:0')
episode: 458 training return: tensor(-905.6914, device='cuda:0')
episode: 459 training return: tensor(-915.6196, device='cuda:0')
epoch: 115 test_true_pfm: 156.85289615180884 sim_pfm: -907.9948986371359
episode: 460 training return: tensor(-917.5773, device='cuda:0')
episode: 461 training return: tensor(-912.0923, device='cuda:0')
episode: 462 training return: tensor(-913.1304, device='cuda:0')
episode: 463 training return: tensor(-918.8307, device='cuda:0')
epoch: 116 test_true_pfm: 119.16211285294565 sim_pfm: -922.7889639635881
episode: 464 training return: tensor(-902.1243, device='cuda:0')
episode: 465 training return: tensor(-918.2882, device='cuda:0')
episode: 466 training return: tensor(-900.1758, device='cuda:0')
episode: 467 training return: tensor(-934.4454, device='cuda:0')
epoch: 117 test_true_pfm: 120.92706013616208 sim_pfm: -933.762023533384
episode: 468 training return: tensor(-890.5073, device='cuda:0')
episode: 469 training return: tensor(-929.8284, device='cuda:0')
episode: 470 training return: tensor(-918.9542, device='cuda:0')
episode: 471 training return: tensor(-925.8753, device='cuda:0')
epoch: 118 test_true_pfm: 142.41405030092545 sim_pfm: -908.5985542585453
episode: 472 training return: tensor(-911.0736, device='cuda:0')
episode: 473 training return: tensor(-923.7515, device='cuda:0')
episode: 474 training return: tensor(-918.1759, device='cuda:0')
episode: 475 training return: tensor(-894.9974, device='cuda:0')
epoch: 119 test_true_pfm: 149.06066661246697 sim_pfm: -907.1976416309675
episode: 476 training return: tensor(-924.0887, device='cuda:0')
episode: 477 training return: tensor(-910.8727, device='cuda:0')
episode: 478 training return: tensor(-897.6652, device='cuda:0')
episode: 479 training return: tensor(-918.7078, device='cuda:0')
epoch: 120 test_true_pfm: 148.4146906513541 sim_pfm: -922.4604871521393
episode: 480 training return: tensor(-911.9876, device='cuda:0')
episode: 481 training return: tensor(-916.5433, device='cuda:0')
episode: 482 training return: tensor(-897.0341, device='cuda:0')
episode: 483 training return: tensor(-912.3921, device='cuda:0')
epoch: 121 test_true_pfm: 154.45839280840667 sim_pfm: -930.7543952216705
episode: 484 training return: tensor(-924.1263, device='cuda:0')
episode: 485 training return: tensor(-912.0156, device='cuda:0')
episode: 486 training return: tensor(-901.7106, device='cuda:0')
episode: 487 training return: tensor(-919.5165, device='cuda:0')
epoch: 122 test_true_pfm: 133.1074170641463 sim_pfm: -919.0967631315192
episode: 488 training return: tensor(-903.8363, device='cuda:0')
episode: 489 training return: tensor(-914.2404, device='cuda:0')
episode: 490 training return: tensor(-922.9385, device='cuda:0')
episode: 491 training return: tensor(-902.3555, device='cuda:0')
epoch: 123 test_true_pfm: 132.29528069262716 sim_pfm: -908.4791568011666
episode: 492 training return: tensor(-919.4451, device='cuda:0')
episode: 493 training return: tensor(-913.3253, device='cuda:0')
episode: 494 training return: tensor(-896.2184, device='cuda:0')
episode: 495 training return: tensor(-917.9868, device='cuda:0')
epoch: 124 test_true_pfm: 147.82885185283564 sim_pfm: -905.7536026028296
episode: 496 training return: tensor(-904.9960, device='cuda:0')
episode: 497 training return: tensor(-927.8626, device='cuda:0')
episode: 498 training return: tensor(-918.9707, device='cuda:0')
episode: 499 training return: tensor(-881.4950, device='cuda:0')
epoch: 125 test_true_pfm: 151.13578163215018 sim_pfm: -909.1762284748256
episode: 500 training return: tensor(-921.4875, device='cuda:0')
episode: 501 training return: tensor(-921.6063, device='cuda:0')
episode: 502 training return: tensor(-923.8893, device='cuda:0')
episode: 503 training return: tensor(-917.3566, device='cuda:0')
epoch: 126 test_true_pfm: 108.23286015170521 sim_pfm: -915.6385095529258
episode: 504 training return: tensor(-922.7301, device='cuda:0')
episode: 505 training return: tensor(-912.2631, device='cuda:0')
episode: 506 training return: tensor(-928.6736, device='cuda:0')
episode: 507 training return: tensor(-916.7780, device='cuda:0')
epoch: 127 test_true_pfm: 127.28729883811654 sim_pfm: -922.0610382457575
episode: 508 training return: tensor(-916.8646, device='cuda:0')
episode: 509 training return: tensor(-907.9990, device='cuda:0')
episode: 510 training return: tensor(-918.6174, device='cuda:0')
episode: 511 training return: tensor(-911.2103, device='cuda:0')
epoch: 128 test_true_pfm: 149.02137216108903 sim_pfm: -910.1867603907982
episode: 512 training return: tensor(-917.0247, device='cuda:0')
episode: 513 training return: tensor(-914.1981, device='cuda:0')
episode: 514 training return: tensor(-929.0327, device='cuda:0')
episode: 515 training return: tensor(-918.1613, device='cuda:0')
epoch: 129 test_true_pfm: 141.530235919937 sim_pfm: -912.9197188162556
episode: 516 training return: tensor(-928.7347, device='cuda:0')
episode: 517 training return: tensor(-907.3206, device='cuda:0')
episode: 518 training return: tensor(-905.4462, device='cuda:0')
episode: 519 training return: tensor(-923.8436, device='cuda:0')
epoch: 130 test_true_pfm: 156.5366878154383 sim_pfm: -907.1856503883997
episode: 520 training return: tensor(-901.7458, device='cuda:0')
episode: 521 training return: tensor(-910.9204, device='cuda:0')
episode: 522 training return: tensor(-919.5534, device='cuda:0')
episode: 523 training return: tensor(-907.6426, device='cuda:0')
epoch: 131 test_true_pfm: 140.61025475726524 sim_pfm: -907.8599556560317
episode: 524 training return: tensor(-917.8212, device='cuda:0')
episode: 525 training return: tensor(-917.3292, device='cuda:0')
episode: 526 training return: tensor(-916.3554, device='cuda:0')
episode: 527 training return: tensor(-911.7284, device='cuda:0')
epoch: 132 test_true_pfm: 168.70317687395618 sim_pfm: -914.0108208383123
episode: 528 training return: tensor(-916.0870, device='cuda:0')
episode: 529 training return: tensor(-926.7043, device='cuda:0')
episode: 530 training return: tensor(-937.6641, device='cuda:0')
episode: 531 training return: tensor(-909.8838, device='cuda:0')
epoch: 133 test_true_pfm: 115.7209940590012 sim_pfm: -925.5850559522709
episode: 532 training return: tensor(-895.3208, device='cuda:0')
episode: 533 training return: tensor(-919.6425, device='cuda:0')
episode: 534 training return: tensor(-898.4120, device='cuda:0')
episode: 535 training return: tensor(-918.8738, device='cuda:0')
epoch: 134 test_true_pfm: 120.62338528645557 sim_pfm: -915.0502959315976
episode: 536 training return: tensor(-920.8726, device='cuda:0')
episode: 537 training return: tensor(-897.3148, device='cuda:0')
episode: 538 training return: tensor(-890.9723, device='cuda:0')
episode: 539 training return: tensor(-918.5034, device='cuda:0')
epoch: 135 test_true_pfm: 142.29424159532178 sim_pfm: -906.1285241413862
episode: 540 training return: tensor(-902.7286, device='cuda:0')
episode: 541 training return: tensor(-907.3035, device='cuda:0')
episode: 542 training return: tensor(-910.1026, device='cuda:0')
episode: 543 training return: tensor(-919.8718, device='cuda:0')
epoch: 136 test_true_pfm: 109.00318330233635 sim_pfm: -920.567621226112
episode: 544 training return: tensor(-904.9623, device='cuda:0')
episode: 545 training return: tensor(-913.5288, device='cuda:0')
episode: 546 training return: tensor(-927.4890, device='cuda:0')
episode: 547 training return: tensor(-913.8728, device='cuda:0')
epoch: 137 test_true_pfm: 145.7184406553259 sim_pfm: -908.590856825312
episode: 548 training return: tensor(-925.4867, device='cuda:0')
episode: 549 training return: tensor(-895.0020, device='cuda:0')
episode: 550 training return: tensor(-904.6075, device='cuda:0')
episode: 551 training return: tensor(-919.9554, device='cuda:0')
epoch: 138 test_true_pfm: 150.67365629498465 sim_pfm: -907.3874938558243
episode: 552 training return: tensor(-906.7899, device='cuda:0')
episode: 553 training return: tensor(-909.4839, device='cuda:0')
episode: 554 training return: tensor(-914.5869, device='cuda:0')
episode: 555 training return: tensor(-911.4721, device='cuda:0')
epoch: 139 test_true_pfm: 143.85361029952114 sim_pfm: -909.5242319218814
episode: 556 training return: tensor(-911.6445, device='cuda:0')
episode: 557 training return: tensor(-922.0370, device='cuda:0')
episode: 558 training return: tensor(-910.7589, device='cuda:0')
episode: 559 training return: tensor(-899.7557, device='cuda:0')
epoch: 140 test_true_pfm: 142.9396275923956 sim_pfm: -905.561909010013
episode: 560 training return: tensor(-922.3944, device='cuda:0')
episode: 561 training return: tensor(-918.1489, device='cuda:0')
episode: 562 training return: tensor(-911.6296, device='cuda:0')
episode: 563 training return: tensor(-909.4801, device='cuda:0')
epoch: 141 test_true_pfm: 148.3592057035709 sim_pfm: -909.9494859166443
episode: 564 training return: tensor(-913.6147, device='cuda:0')
episode: 565 training return: tensor(-892.6851, device='cuda:0')
episode: 566 training return: tensor(-913.0740, device='cuda:0')
episode: 567 training return: tensor(-925.2594, device='cuda:0')
epoch: 142 test_true_pfm: 163.1087284815657 sim_pfm: -916.8154414625218
episode: 568 training return: tensor(-917.5656, device='cuda:0')
episode: 569 training return: tensor(-916.5311, device='cuda:0')
episode: 570 training return: tensor(-899.8091, device='cuda:0')
episode: 571 training return: tensor(-914.7793, device='cuda:0')
epoch: 143 test_true_pfm: 142.18088880692827 sim_pfm: -909.0590949331721
episode: 572 training return: tensor(-911.9081, device='cuda:0')
episode: 573 training return: tensor(-908.4062, device='cuda:0')
episode: 574 training return: tensor(-894.9025, device='cuda:0')
episode: 575 training return: tensor(-911.9307, device='cuda:0')
epoch: 144 test_true_pfm: 139.28097812618117 sim_pfm: -909.4390258180598
episode: 576 training return: tensor(-880.6891, device='cuda:0')
episode: 577 training return: tensor(-902.6989, device='cuda:0')
episode: 578 training return: tensor(-933.9680, device='cuda:0')
episode: 579 training return: tensor(-917.6563, device='cuda:0')
epoch: 145 test_true_pfm: 157.20690046181775 sim_pfm: -910.7932812459767
episode: 580 training return: tensor(-898.2677, device='cuda:0')
episode: 581 training return: tensor(-912.8137, device='cuda:0')
episode: 582 training return: tensor(-909.8733, device='cuda:0')
episode: 583 training return: tensor(-903.9923, device='cuda:0')
epoch: 146 test_true_pfm: 150.05760140203088 sim_pfm: -906.5081868891915
episode: 584 training return: tensor(-907.6251, device='cuda:0')
episode: 585 training return: tensor(-910.4685, device='cuda:0')
episode: 586 training return: tensor(-921.6457, device='cuda:0')
episode: 587 training return: tensor(-910.8768, device='cuda:0')
epoch: 147 test_true_pfm: 154.21220099812305 sim_pfm: -905.0560742105978
episode: 588 training return: tensor(-918.4276, device='cuda:0')
episode: 589 training return: tensor(-910.3997, device='cuda:0')
episode: 590 training return: tensor(-904.0258, device='cuda:0')
episode: 591 training return: tensor(-902.8077, device='cuda:0')
epoch: 148 test_true_pfm: 151.63262870006056 sim_pfm: -910.5088341633478
episode: 592 training return: tensor(-895.8846, device='cuda:0')
episode: 593 training return: tensor(-916.1603, device='cuda:0')
episode: 594 training return: tensor(-910.3785, device='cuda:0')
episode: 595 training return: tensor(-904.4398, device='cuda:0')
epoch: 149 test_true_pfm: 159.4999662069564 sim_pfm: -922.7470834595151
episode: 596 training return: tensor(-913.0535, device='cuda:0')
episode: 597 training return: tensor(-924.4726, device='cuda:0')
episode: 598 training return: tensor(-923.2303, device='cuda:0')
episode: 599 training return: tensor(-922.8037, device='cuda:0')
epoch: 150 test_true_pfm: 159.6000747096617 sim_pfm: -931.7629737246704
