['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'brac', '--traj', 'medium', '--seed', '1', '--data', '100000']
2531.7149286595472
episode: 0 training return: tensor(-1.1805e+10, device='cuda:0')
episode: 1 training return: tensor(-8.6479e+08, device='cuda:0')
episode: 2 training return: tensor(-4.4313e+11, device='cuda:0')
episode: 3 training return: tensor(-4.1652e+11, device='cuda:0')
epoch: 1 test_true_pfm: -83.4824689893545
episode: 4 training return: tensor(-2.6240e+11, device='cuda:0')
episode: 5 training return: tensor(-1.1067e+10, device='cuda:0')
episode: 6 training return: tensor(-4.9095e+09, device='cuda:0')
episode: 7 training return: tensor(-2.7222e+11, device='cuda:0')
epoch: 2 test_true_pfm: -84.52719948491342
episode: 8 training return: tensor(-7.5485e+10, device='cuda:0')
episode: 9 training return: tensor(-542003.4375, device='cuda:0')
episode: 10 training return: tensor(-421476.7500, device='cuda:0')
episode: 11 training return: tensor(-1615067.3750, device='cuda:0')
epoch: 3 test_true_pfm: -144.42570936269138
episode: 12 training return: tensor(-1619282.2500, device='cuda:0')
episode: 13 training return: tensor(-1611088.7500, device='cuda:0')
episode: 14 training return: tensor(-1617539.7500, device='cuda:0')
episode: 15 training return: tensor(-1616941.3750, device='cuda:0')
epoch: 4 test_true_pfm: -144.4694338367682
episode: 16 training return: tensor(-1620207.2500, device='cuda:0')
episode: 17 training return: tensor(-1606016.5000, device='cuda:0')
episode: 18 training return: tensor(-1614752.7500, device='cuda:0')
episode: 19 training return: tensor(-1618349.8750, device='cuda:0')
epoch: 5 test_true_pfm: -144.04442673742736
episode: 20 training return: tensor(-1617233.5000, device='cuda:0')
episode: 21 training return: tensor(-1613364.6250, device='cuda:0')
episode: 22 training return: tensor(-1610557.5000, device='cuda:0')
episode: 23 training return: tensor(-1623866.7500, device='cuda:0')
epoch: 6 test_true_pfm: -144.39384142145713
episode: 24 training return: tensor(-23487354., device='cuda:0')
episode: 25 training return: tensor(-159962.3594, device='cuda:0')
episode: 26 training return: tensor(-160523.9688, device='cuda:0')
episode: 27 training return: tensor(-160107.2969, device='cuda:0')
epoch: 7 test_true_pfm: -25.95443671516423
episode: 28 training return: tensor(-160061.6719, device='cuda:0')
episode: 29 training return: tensor(-160104.2656, device='cuda:0')
episode: 30 training return: tensor(-160435.8594, device='cuda:0')
episode: 31 training return: tensor(-160373., device='cuda:0')
epoch: 8 test_true_pfm: -22.526815836335192
episode: 32 training return: tensor(-160316.4688, device='cuda:0')
episode: 33 training return: tensor(-159781.3281, device='cuda:0')
episode: 34 training return: tensor(-160158.3594, device='cuda:0')
episode: 35 training return: tensor(-160191.7031, device='cuda:0')
epoch: 9 test_true_pfm: -22.53163104462499
episode: 36 training return: tensor(-159809.9531, device='cuda:0')
episode: 37 training return: tensor(-159760.7656, device='cuda:0')
episode: 38 training return: tensor(-159808.7031, device='cuda:0')
episode: 39 training return: tensor(-103097.2578, device='cuda:0')
epoch: 10 test_true_pfm: 87.24016181155677
episode: 40 training return: tensor(-62568784., device='cuda:0')
episode: 41 training return: tensor(-62523012., device='cuda:0')
episode: 42 training return: tensor(-61885068., device='cuda:0')
episode: 43 training return: tensor(-62676940., device='cuda:0')
epoch: 11 test_true_pfm: 79.2157672884848
episode: 44 training return: tensor(-61785932., device='cuda:0')
episode: 45 training return: tensor(-62249324., device='cuda:0')
episode: 46 training return: tensor(-61482084., device='cuda:0')
episode: 47 training return: tensor(-61491000., device='cuda:0')
epoch: 12 test_true_pfm: 86.0721645746952
episode: 48 training return: tensor(-62474044., device='cuda:0')
episode: 49 training return: tensor(-62672348., device='cuda:0')
episode: 50 training return: tensor(-62629584., device='cuda:0')
episode: 51 training return: tensor(-58396308., device='cuda:0')
epoch: 13 test_true_pfm: 82.65275094661449
episode: 52 training return: tensor(-62009820., device='cuda:0')
episode: 53 training return: tensor(-62292836., device='cuda:0')
episode: 54 training return: tensor(-62309004., device='cuda:0')
episode: 55 training return: tensor(-61893060., device='cuda:0')
epoch: 14 test_true_pfm: 94.61886192159902
episode: 56 training return: tensor(-62583656., device='cuda:0')
episode: 57 training return: tensor(-59014940., device='cuda:0')
episode: 58 training return: tensor(-61836692., device='cuda:0')
episode: 59 training return: tensor(-178815.4062, device='cuda:0')
epoch: 15 test_true_pfm: 88.94632056704569
episode: 60 training return: tensor(-62295992., device='cuda:0')
episode: 61 training return: tensor(-71331696., device='cuda:0')
episode: 62 training return: tensor(-62616748., device='cuda:0')
episode: 63 training return: tensor(-62041396., device='cuda:0')
epoch: 16 test_true_pfm: 105.27273931790073
episode: 64 training return: tensor(-61502112., device='cuda:0')
episode: 65 training return: tensor(-62319376., device='cuda:0')
episode: 66 training return: tensor(-61652856., device='cuda:0')
episode: 67 training return: tensor(-71859.7812, device='cuda:0')
epoch: 17 test_true_pfm: 376.75131822702497
episode: 68 training return: tensor(-3.4872e+10, device='cuda:0')
episode: 69 training return: tensor(-87136168., device='cuda:0')
episode: 70 training return: tensor(-27384258., device='cuda:0')
episode: 71 training return: tensor(-63176604., device='cuda:0')
epoch: 18 test_true_pfm: 140.8954476491376
episode: 72 training return: tensor(-2.3130e+11, device='cuda:0')
episode: 73 training return: tensor(-58766392., device='cuda:0')
episode: 74 training return: tensor(-3.6061e+10, device='cuda:0')
episode: 75 training return: tensor(-1.2880e+10, device='cuda:0')
epoch: 19 test_true_pfm: -50.27869365440946
episode: 76 training return: tensor(-66927740., device='cuda:0')
episode: 77 training return: tensor(-98145.1641, device='cuda:0')
episode: 78 training return: tensor(-33129.8555, device='cuda:0')
episode: 79 training return: tensor(-28167.8379, device='cuda:0')
epoch: 20 test_true_pfm: 84.52244783083248
episode: 80 training return: tensor(-62688452., device='cuda:0')
episode: 81 training return: tensor(-61864864., device='cuda:0')
episode: 82 training return: tensor(-62624044., device='cuda:0')
episode: 83 training return: tensor(-62273340., device='cuda:0')
epoch: 21 test_true_pfm: 118.06364291720261
episode: 84 training return: tensor(-120795., device='cuda:0')
episode: 85 training return: tensor(-56262732., device='cuda:0')
episode: 86 training return: tensor(-1083619.8750, device='cuda:0')
episode: 87 training return: tensor(-5.1835e+10, device='cuda:0')
epoch: 22 test_true_pfm: 53.19629824659956
episode: 88 training return: tensor(-5.5795e+10, device='cuda:0')
episode: 89 training return: tensor(-57595480., device='cuda:0')
episode: 90 training return: tensor(-51443684., device='cuda:0')
episode: 91 training return: tensor(-62583344., device='cuda:0')
epoch: 23 test_true_pfm: 55.847776918608226
episode: 92 training return: tensor(-45939.8242, device='cuda:0')
episode: 93 training return: tensor(-58998008., device='cuda:0')
episode: 94 training return: tensor(-1.4488e+08, device='cuda:0')
episode: 95 training return: tensor(-91238968., device='cuda:0')
epoch: 24 test_true_pfm: 5.886176672386353
episode: 96 training return: tensor(-83316032., device='cuda:0')
episode: 97 training return: tensor(-51245892., device='cuda:0')
episode: 98 training return: tensor(-95955640., device='cuda:0')
episode: 99 training return: tensor(-1.0888e+08, device='cuda:0')
epoch: 25 test_true_pfm: -13.35534855891229
episode: 100 training return: tensor(-1248203.7500, device='cuda:0')
episode: 101 training return: tensor(-79071392., device='cuda:0')
episode: 102 training return: tensor(-48730376., device='cuda:0')
episode: 103 training return: tensor(-76714720., device='cuda:0')
epoch: 26 test_true_pfm: -24.72488233318403
episode: 104 training return: tensor(-76365864., device='cuda:0')
episode: 105 training return: tensor(-78262152., device='cuda:0')
episode: 106 training return: tensor(-83530296., device='cuda:0')
episode: 107 training return: tensor(-4422598.5000, device='cuda:0')
epoch: 27 test_true_pfm: 2.319735379682861
episode: 108 training return: tensor(-3428806.5000, device='cuda:0')
episode: 109 training return: tensor(-1.1572e+08, device='cuda:0')
episode: 110 training return: tensor(-95328488., device='cuda:0')
episode: 111 training return: tensor(-1.8259e+08, device='cuda:0')
epoch: 28 test_true_pfm: -118.37280614046377
episode: 112 training return: tensor(-1.1321e+08, device='cuda:0')
episode: 113 training return: tensor(-85540.7812, device='cuda:0')
episode: 114 training return: tensor(-86607.5234, device='cuda:0')
episode: 115 training return: tensor(-87235.5469, device='cuda:0')
epoch: 29 test_true_pfm: 10.552442042627199
episode: 116 training return: tensor(-84958.6094, device='cuda:0')
episode: 117 training return: tensor(-102242.5625, device='cuda:0')
episode: 118 training return: tensor(-1.1284e+08, device='cuda:0')
episode: 119 training return: tensor(-96661872., device='cuda:0')
epoch: 30 test_true_pfm: -81.4709503533848
episode: 120 training return: tensor(-87105.4219, device='cuda:0')
episode: 121 training return: tensor(-86860.1719, device='cuda:0')
episode: 122 training return: tensor(-86527.9844, device='cuda:0')
episode: 123 training return: tensor(-1.0931e+08, device='cuda:0')
epoch: 31 test_true_pfm: 66.46234933221973
episode: 124 training return: tensor(-1.0700e+08, device='cuda:0')
episode: 125 training return: tensor(-105071.4141, device='cuda:0')
episode: 126 training return: tensor(-1.0356e+08, device='cuda:0')
episode: 127 training return: tensor(-1.0984e+08, device='cuda:0')
epoch: 32 test_true_pfm: 149.26635703530698
episode: 128 training return: tensor(-46439300., device='cuda:0')
episode: 129 training return: tensor(-94577.1250, device='cuda:0')
episode: 130 training return: tensor(-81473.2500, device='cuda:0')
episode: 131 training return: tensor(-1.1409e+08, device='cuda:0')
epoch: 33 test_true_pfm: -61.836148949404325
episode: 132 training return: tensor(-1.0267e+08, device='cuda:0')
episode: 133 training return: tensor(-1.0032e+08, device='cuda:0')
episode: 134 training return: tensor(-1.1698e+08, device='cuda:0')
episode: 135 training return: tensor(-86917.1328, device='cuda:0')
epoch: 34 test_true_pfm: 10.891891442943892
episode: 136 training return: tensor(-86432.5234, device='cuda:0')
episode: 137 training return: tensor(-1.1677e+08, device='cuda:0')
episode: 138 training return: tensor(-1.2032e+08, device='cuda:0')
episode: 139 training return: tensor(-82135.5938, device='cuda:0')
epoch: 35 test_true_pfm: -25.75909511642273
episode: 140 training return: tensor(-60896.8164, device='cuda:0')
episode: 141 training return: tensor(-68168.6250, device='cuda:0')
episode: 142 training return: tensor(-55410.8984, device='cuda:0')
episode: 143 training return: tensor(-40567.4453, device='cuda:0')
epoch: 36 test_true_pfm: -12.18979755177704
episode: 144 training return: tensor(-110243.5781, device='cuda:0')
episode: 145 training return: tensor(-1.4976e+08, device='cuda:0')
episode: 146 training return: tensor(-1.6609e+08, device='cuda:0')
episode: 147 training return: tensor(-90236.7812, device='cuda:0')
epoch: 37 test_true_pfm: -1.4005989253847124
episode: 148 training return: tensor(-39362668., device='cuda:0')
episode: 149 training return: tensor(-1559244.2500, device='cuda:0')
episode: 150 training return: tensor(-97595016., device='cuda:0')
episode: 151 training return: tensor(-1.2134e+08, device='cuda:0')
epoch: 38 test_true_pfm: -83.13841722458842
episode: 152 training return: tensor(-60144536., device='cuda:0')
episode: 153 training return: tensor(-102806.5000, device='cuda:0')
episode: 154 training return: tensor(-1.1486e+08, device='cuda:0')
episode: 155 training return: tensor(-1.2467e+08, device='cuda:0')
epoch: 39 test_true_pfm: 55.91456342726301
episode: 156 training return: tensor(-132333.3906, device='cuda:0')
episode: 157 training return: tensor(-38967376., device='cuda:0')
episode: 158 training return: tensor(-1.0239e+08, device='cuda:0')
episode: 159 training return: tensor(-64198.8320, device='cuda:0')
epoch: 40 test_true_pfm: 34.34649995138168
episode: 160 training return: tensor(-75063.7422, device='cuda:0')
episode: 161 training return: tensor(-1075789.3750, device='cuda:0')
episode: 162 training return: tensor(-1.1042e+08, device='cuda:0')
episode: 163 training return: tensor(-85442.1953, device='cuda:0')
epoch: 41 test_true_pfm: 28.830197244735654
episode: 164 training return: tensor(-190671.8750, device='cuda:0')
episode: 165 training return: tensor(-114983.1172, device='cuda:0')
episode: 166 training return: tensor(-30957.3320, device='cuda:0')
episode: 167 training return: tensor(-1240476.2500, device='cuda:0')
epoch: 42 test_true_pfm: -12.308058937839784
episode: 168 training return: tensor(-3520.3994, device='cuda:0')
episode: 169 training return: tensor(-2226088., device='cuda:0')
episode: 170 training return: tensor(-1.1293e+08, device='cuda:0')
episode: 171 training return: tensor(-1.1588e+08, device='cuda:0')
epoch: 43 test_true_pfm: 41.549618026078754
episode: 172 training return: tensor(-107827.3281, device='cuda:0')
episode: 173 training return: tensor(-171845.1250, device='cuda:0')
episode: 174 training return: tensor(-90800512., device='cuda:0')
episode: 175 training return: tensor(-110098.3203, device='cuda:0')
epoch: 44 test_true_pfm: -36.14637336016984
episode: 176 training return: tensor(-123303.6875, device='cuda:0')
episode: 177 training return: tensor(-1.5625e+08, device='cuda:0')
episode: 178 training return: tensor(-1.1362e+08, device='cuda:0')
episode: 179 training return: tensor(-1.0308e+08, device='cuda:0')
epoch: 45 test_true_pfm: -61.91238807268123
episode: 180 training return: tensor(-1.0072e+08, device='cuda:0')
episode: 181 training return: tensor(-86426.2266, device='cuda:0')
episode: 182 training return: tensor(-85706.2656, device='cuda:0')
episode: 183 training return: tensor(-87492.8672, device='cuda:0')
epoch: 46 test_true_pfm: -0.43442799669062043
episode: 184 training return: tensor(-1.0440e+08, device='cuda:0')
episode: 185 training return: tensor(-1625736.5000, device='cuda:0')
episode: 186 training return: tensor(-86065.1328, device='cuda:0')
episode: 187 training return: tensor(-72338.7812, device='cuda:0')
epoch: 47 test_true_pfm: 126.03236410502068
episode: 188 training return: tensor(-301440.3750, device='cuda:0')
episode: 189 training return: tensor(-73069.2422, device='cuda:0')
episode: 190 training return: tensor(-92181472., device='cuda:0')
episode: 191 training return: tensor(-1.1418e+08, device='cuda:0')
epoch: 48 test_true_pfm: 19.668892076945784
episode: 192 training return: tensor(-101522.4688, device='cuda:0')
episode: 193 training return: tensor(-1.0435e+08, device='cuda:0')
episode: 194 training return: tensor(-1.2239e+08, device='cuda:0')
episode: 195 training return: tensor(-108614.9219, device='cuda:0')
epoch: 49 test_true_pfm: -6.494258172482646
episode: 196 training return: tensor(-1.1875e+08, device='cuda:0')
episode: 197 training return: tensor(-29557130., device='cuda:0')
episode: 198 training return: tensor(-102459.4453, device='cuda:0')
episode: 199 training return: tensor(-1687201., device='cuda:0')
epoch: 50 test_true_pfm: 39.93942516058568
episode: 200 training return: tensor(-19964338., device='cuda:0')
episode: 201 training return: tensor(-1.2154e+08, device='cuda:0')
episode: 202 training return: tensor(-87599.6172, device='cuda:0')
episode: 203 training return: tensor(-84491.9219, device='cuda:0')
epoch: 51 test_true_pfm: -3.3240997412832605
episode: 204 training return: tensor(-89741.5547, device='cuda:0')
episode: 205 training return: tensor(-93076.4141, device='cuda:0')
episode: 206 training return: tensor(-1.2169e+08, device='cuda:0')
episode: 207 training return: tensor(-117240.2578, device='cuda:0')
epoch: 52 test_true_pfm: -8.019071349259137
episode: 208 training return: tensor(-97998408., device='cuda:0')
episode: 209 training return: tensor(-1.2423e+08, device='cuda:0')
episode: 210 training return: tensor(-1.5461e+08, device='cuda:0')
episode: 211 training return: tensor(-8.6291e+10, device='cuda:0')
epoch: 53 test_true_pfm: 3.232577128330894
episode: 212 training return: tensor(-3058.4856, device='cuda:0')
episode: 213 training return: tensor(-21364.4727, device='cuda:0')
episode: 214 training return: tensor(-3066.2505, device='cuda:0')
episode: 215 training return: tensor(-16396876., device='cuda:0')
epoch: 54 test_true_pfm: 78.26128915920017
episode: 216 training return: tensor(-1.2308e+08, device='cuda:0')
episode: 217 training return: tensor(-59487112., device='cuda:0')
episode: 218 training return: tensor(-60710212., device='cuda:0')
episode: 219 training return: tensor(-1.0864e+08, device='cuda:0')
epoch: 55 test_true_pfm: 44.984194739740076
episode: 220 training return: tensor(-73338400., device='cuda:0')
episode: 221 training return: tensor(-1.1391e+08, device='cuda:0')
episode: 222 training return: tensor(-1.2311e+08, device='cuda:0')
episode: 223 training return: tensor(-1.1724e+08, device='cuda:0')
epoch: 56 test_true_pfm: 134.40512452532607
episode: 224 training return: tensor(-70136.4375, device='cuda:0')
episode: 225 training return: tensor(-843472.1875, device='cuda:0')
episode: 226 training return: tensor(-2735663.7500, device='cuda:0')
episode: 227 training return: tensor(-86806.5156, device='cuda:0')
epoch: 57 test_true_pfm: -1.9438916688784396
episode: 228 training return: tensor(-1.2225e+08, device='cuda:0')
episode: 229 training return: tensor(-1.1751e+08, device='cuda:0')
episode: 230 training return: tensor(-36322.3086, device='cuda:0')
episode: 231 training return: tensor(-3.5566e+14, device='cuda:0')
epoch: 58 test_true_pfm: -32.99068759502199
episode: 232 training return: tensor(-88850.0156, device='cuda:0')
episode: 233 training return: tensor(-57790.2695, device='cuda:0')
episode: 234 training return: tensor(-797905.5000, device='cuda:0')
episode: 235 training return: tensor(-26551.4492, device='cuda:0')
epoch: 59 test_true_pfm: -51.776716441662586
episode: 236 training return: tensor(-25455.6387, device='cuda:0')
episode: 237 training return: tensor(-27323924., device='cuda:0')
episode: 238 training return: tensor(-27370836., device='cuda:0')
episode: 239 training return: tensor(-27491384., device='cuda:0')
epoch: 60 test_true_pfm: 173.53793885338348
episode: 240 training return: tensor(-27440632., device='cuda:0')
episode: 241 training return: tensor(-27491388., device='cuda:0')
episode: 242 training return: tensor(-27424938., device='cuda:0')
episode: 243 training return: tensor(-27678866., device='cuda:0')
epoch: 61 test_true_pfm: 170.93651919875492
episode: 244 training return: tensor(-26119038., device='cuda:0')
episode: 245 training return: tensor(-25919.2109, device='cuda:0')
episode: 246 training return: tensor(-25558.2715, device='cuda:0')
episode: 247 training return: tensor(-25593.7812, device='cuda:0')
epoch: 62 test_true_pfm: -51.4010299624591
episode: 248 training return: tensor(-551383.5000, device='cuda:0')
episode: 249 training return: tensor(-33425444., device='cuda:0')
episode: 250 training return: tensor(-33522.2695, device='cuda:0')
episode: 251 training return: tensor(-25500.3281, device='cuda:0')
epoch: 63 test_true_pfm: -51.39607762065409
episode: 252 training return: tensor(-25533.3438, device='cuda:0')
episode: 253 training return: tensor(-122853.2656, device='cuda:0')
episode: 254 training return: tensor(-519123.3125, device='cuda:0')
episode: 255 training return: tensor(-50743.0391, device='cuda:0')
epoch: 64 test_true_pfm: -4.276902371224966
episode: 256 training return: tensor(-500091.4688, device='cuda:0')
episode: 257 training return: tensor(-10392.6514, device='cuda:0')
episode: 258 training return: tensor(-33812.2266, device='cuda:0')
episode: 259 training return: tensor(-61486.0898, device='cuda:0')
epoch: 65 test_true_pfm: -19.272026213321173
episode: 260 training return: tensor(-33496.6484, device='cuda:0')
episode: 261 training return: tensor(-24242.4609, device='cuda:0')
episode: 262 training return: tensor(-31808.0938, device='cuda:0')
episode: 263 training return: tensor(-524552.7500, device='cuda:0')
epoch: 66 test_true_pfm: 29.361819757864613
episode: 264 training return: tensor(-15145.1924, device='cuda:0')
episode: 265 training return: tensor(-512200.6562, device='cuda:0')
episode: 266 training return: tensor(-11098.8174, device='cuda:0')
episode: 267 training return: tensor(-42719088., device='cuda:0')
epoch: 67 test_true_pfm: -44.718130941159984
episode: 268 training return: tensor(-58591192., device='cuda:0')
episode: 269 training return: tensor(-61952848., device='cuda:0')
episode: 270 training return: tensor(-62319748., device='cuda:0')
episode: 271 training return: tensor(-62308760., device='cuda:0')
epoch: 68 test_true_pfm: 85.42956259128681
episode: 272 training return: tensor(-62642196., device='cuda:0')
episode: 273 training return: tensor(-62430396., device='cuda:0')
episode: 274 training return: tensor(-62638740., device='cuda:0')
episode: 275 training return: tensor(-61463436., device='cuda:0')
epoch: 69 test_true_pfm: 102.63961257600437
episode: 276 training return: tensor(-62333912., device='cuda:0')
episode: 277 training return: tensor(-112307.2500, device='cuda:0')
episode: 278 training return: tensor(-268106.0625, device='cuda:0')
episode: 279 training return: tensor(-59447388., device='cuda:0')
epoch: 70 test_true_pfm: 255.06666956687204
episode: 280 training return: tensor(-83144.6406, device='cuda:0')
episode: 281 training return: tensor(-58337396., device='cuda:0')
episode: 282 training return: tensor(-58155260., device='cuda:0')
episode: 283 training return: tensor(-67825976., device='cuda:0')
epoch: 71 test_true_pfm: 34.374268268152214
episode: 284 training return: tensor(-58902160., device='cuda:0')
episode: 285 training return: tensor(-61175612., device='cuda:0')
episode: 286 training return: tensor(-61087292., device='cuda:0')
episode: 287 training return: tensor(-60707732., device='cuda:0')
epoch: 72 test_true_pfm: 83.23267737579648
episode: 288 training return: tensor(-62576404., device='cuda:0')
episode: 289 training return: tensor(-62406296., device='cuda:0')
episode: 290 training return: tensor(-34338.9766, device='cuda:0')
episode: 291 training return: tensor(-62343616., device='cuda:0')
epoch: 73 test_true_pfm: 58.96352025330032
episode: 292 training return: tensor(-32912.3711, device='cuda:0')
episode: 293 training return: tensor(-78775792., device='cuda:0')
episode: 294 training return: tensor(-38917.3711, device='cuda:0')
episode: 295 training return: tensor(-62177992., device='cuda:0')
epoch: 74 test_true_pfm: 85.60867671589968
episode: 296 training return: tensor(-62615228., device='cuda:0')
episode: 297 training return: tensor(-61786052., device='cuda:0')
episode: 298 training return: tensor(-60384840., device='cuda:0')
episode: 299 training return: tensor(-59172780., device='cuda:0')
epoch: 75 test_true_pfm: -69.6055801211392
episode: 300 training return: tensor(-57164100., device='cuda:0')
episode: 301 training return: tensor(-61214024., device='cuda:0')
episode: 302 training return: tensor(-62530696., device='cuda:0')
episode: 303 training return: tensor(-68498744., device='cuda:0')
epoch: 76 test_true_pfm: 73.40675070019891
episode: 304 training return: tensor(-35308.4844, device='cuda:0')
episode: 305 training return: tensor(-846988.5625, device='cuda:0')
episode: 306 training return: tensor(-56602568., device='cuda:0')
episode: 307 training return: tensor(-62046104., device='cuda:0')
epoch: 77 test_true_pfm: 85.06331971049914
episode: 308 training return: tensor(-62584684., device='cuda:0')
episode: 309 training return: tensor(-62471176., device='cuda:0')
episode: 310 training return: tensor(-68123248., device='cuda:0')
episode: 311 training return: tensor(-3717843.7500, device='cuda:0')
epoch: 78 test_true_pfm: -199.21880577678454
episode: 312 training return: tensor(-70392.6172, device='cuda:0')
episode: 313 training return: tensor(-77244832., device='cuda:0')
episode: 314 training return: tensor(-78702312., device='cuda:0')
episode: 315 training return: tensor(-78815192., device='cuda:0')
epoch: 79 test_true_pfm: 14.19068412693733
episode: 316 training return: tensor(-1.0643e+08, device='cuda:0')
episode: 317 training return: tensor(-1.0735e+08, device='cuda:0')
episode: 318 training return: tensor(-64548060., device='cuda:0')
episode: 319 training return: tensor(-14588.0850, device='cuda:0')
epoch: 80 test_true_pfm: -238.52743604331963
episode: 320 training return: tensor(-68519168., device='cuda:0')
episode: 321 training return: tensor(-73470216., device='cuda:0')
episode: 322 training return: tensor(-111609.9922, device='cuda:0')
episode: 323 training return: tensor(-61460584., device='cuda:0')
epoch: 81 test_true_pfm: -10.52673732672467
episode: 324 training return: tensor(-70776704., device='cuda:0')
episode: 325 training return: tensor(-51812816., device='cuda:0')
episode: 326 training return: tensor(-1.3050e+08, device='cuda:0')
episode: 327 training return: tensor(-1085328.8750, device='cuda:0')
epoch: 82 test_true_pfm: 51.956297001633146
episode: 328 training return: tensor(-4.7557e+09, device='cuda:0')
episode: 329 training return: tensor(-6.2235e+09, device='cuda:0')
episode: 330 training return: tensor(-5.7996e+09, device='cuda:0')
episode: 331 training return: tensor(-14611037., device='cuda:0')
epoch: 83 test_true_pfm: 437.56782148163825
episode: 332 training return: tensor(-19382.1230, device='cuda:0')
episode: 333 training return: tensor(-264429.2188, device='cuda:0')
episode: 334 training return: tensor(-534914.6250, device='cuda:0')
episode: 335 training return: tensor(-72714872., device='cuda:0')
epoch: 84 test_true_pfm: -6.451660313624384
episode: 336 training return: tensor(-74048760., device='cuda:0')
episode: 337 training return: tensor(-73848760., device='cuda:0')
episode: 338 training return: tensor(-4.5545e+09, device='cuda:0')
episode: 339 training return: tensor(-87246.6484, device='cuda:0')
epoch: 85 test_true_pfm: -1.4778106174037688
episode: 340 training return: tensor(-2176504.2500, device='cuda:0')
episode: 341 training return: tensor(-35482812., device='cuda:0')
episode: 342 training return: tensor(-4.8113e+10, device='cuda:0')
episode: 343 training return: tensor(-78991656., device='cuda:0')
epoch: 86 test_true_pfm: 40.873716862348864
episode: 344 training return: tensor(-21986206., device='cuda:0')
episode: 345 training return: tensor(-8.1298e+08, device='cuda:0')
episode: 346 training return: tensor(-79819048., device='cuda:0')
episode: 347 training return: tensor(-79706672., device='cuda:0')
epoch: 87 test_true_pfm: 51.03362146887062
episode: 348 training return: tensor(-81909136., device='cuda:0')
episode: 349 training return: tensor(-79933544., device='cuda:0')
episode: 350 training return: tensor(-2.3930e+08, device='cuda:0')
episode: 351 training return: tensor(-5.4955e+14, device='cuda:0')
epoch: 88 test_true_pfm: 140.5068376690015
episode: 352 training return: tensor(-1.2685e+10, device='cuda:0')
episode: 353 training return: tensor(-1.7155e+09, device='cuda:0')
episode: 354 training return: tensor(-3.5507e+10, device='cuda:0')
episode: 355 training return: tensor(-82178648., device='cuda:0')
epoch: 89 test_true_pfm: 43.606828649070984
episode: 356 training return: tensor(-4.1759e+10, device='cuda:0')
episode: 357 training return: tensor(-1.9702e+09, device='cuda:0')
episode: 358 training return: tensor(-9028086., device='cuda:0')
episode: 359 training return: tensor(-6424294., device='cuda:0')
epoch: 90 test_true_pfm: -20.745611018915167
episode: 360 training return: tensor(-44532136., device='cuda:0')
episode: 361 training return: tensor(-72289576., device='cuda:0')
episode: 362 training return: tensor(-8829236., device='cuda:0')
episode: 363 training return: tensor(-11281.6064, device='cuda:0')
epoch: 91 test_true_pfm: 46.730932128656924
episode: 364 training return: tensor(-39205.3164, device='cuda:0')
episode: 365 training return: tensor(-37323.6719, device='cuda:0')
episode: 366 training return: tensor(-32108.4922, device='cuda:0')
episode: 367 training return: tensor(-17701282., device='cuda:0')
epoch: 92 test_true_pfm: -303.46872912526015
episode: 368 training return: tensor(-7838.8833, device='cuda:0')
episode: 369 training return: tensor(-2238020.7500, device='cuda:0')
episode: 370 training return: tensor(-2.4897e+08, device='cuda:0')
episode: 371 training return: tensor(-3.3447e+10, device='cuda:0')
epoch: 93 test_true_pfm: -67.80082347759395
episode: 372 training return: tensor(-43408.0078, device='cuda:0')
episode: 373 training return: tensor(-25342.9883, device='cuda:0')
episode: 374 training return: tensor(-25288.3848, device='cuda:0')
episode: 375 training return: tensor(-25376.7090, device='cuda:0')
epoch: 94 test_true_pfm: -82.78989248666748
episode: 376 training return: tensor(-25324.2637, device='cuda:0')
episode: 377 training return: tensor(-25222.4727, device='cuda:0')
episode: 378 training return: tensor(-25242.4980, device='cuda:0')
episode: 379 training return: tensor(-26315.3301, device='cuda:0')
epoch: 95 test_true_pfm: -83.57897839010413
episode: 380 training return: tensor(-25201.6328, device='cuda:0')
episode: 381 training return: tensor(-25355.1211, device='cuda:0')
episode: 382 training return: tensor(-25545.7773, device='cuda:0')
episode: 383 training return: tensor(-25512.5645, device='cuda:0')
epoch: 96 test_true_pfm: -52.30729349054274
episode: 384 training return: tensor(-25568.1953, device='cuda:0')
episode: 385 training return: tensor(-25587.5469, device='cuda:0')
episode: 386 training return: tensor(-25519.9180, device='cuda:0')
episode: 387 training return: tensor(-25456.6934, device='cuda:0')
epoch: 97 test_true_pfm: -53.1907345095074
episode: 388 training return: tensor(-25591.4531, device='cuda:0')
episode: 389 training return: tensor(-25449.4316, device='cuda:0')
episode: 390 training return: tensor(-25607.9180, device='cuda:0')
episode: 391 training return: tensor(-25485.2871, device='cuda:0')
epoch: 98 test_true_pfm: -54.53037950664554
episode: 392 training return: tensor(-24964.7012, device='cuda:0')
episode: 393 training return: tensor(-15324.8936, device='cuda:0')
episode: 394 training return: tensor(-38145.9453, device='cuda:0')
episode: 395 training return: tensor(-50237.8867, device='cuda:0')
epoch: 99 test_true_pfm: -59.08001083807061
episode: 396 training return: tensor(-40467.3750, device='cuda:0')
episode: 397 training return: tensor(-63579.5586, device='cuda:0')
episode: 398 training return: tensor(-46276.8906, device='cuda:0')
episode: 399 training return: tensor(-1065369.7500, device='cuda:0')
epoch: 100 test_true_pfm: -37.69313555919664
episode: 400 training return: tensor(-60303608., device='cuda:0')
episode: 401 training return: tensor(-11094.7598, device='cuda:0')
episode: 402 training return: tensor(-8.3509e+10, device='cuda:0')
episode: 403 training return: tensor(-1045685.1875, device='cuda:0')
epoch: 101 test_true_pfm: -7.923119489517262
episode: 404 training return: tensor(-1286734.5000, device='cuda:0')
episode: 405 training return: tensor(-64988.0117, device='cuda:0')
episode: 406 training return: tensor(-3.7727e+08, device='cuda:0')
episode: 407 training return: tensor(-21450546., device='cuda:0')
epoch: 102 test_true_pfm: -93.47028614816004
episode: 408 training return: tensor(-64481492., device='cuda:0')
episode: 409 training return: tensor(-11550.5186, device='cuda:0')
episode: 410 training return: tensor(-15895937., device='cuda:0')
episode: 411 training return: tensor(-605601.1250, device='cuda:0')
epoch: 103 test_true_pfm: -35.79982051373964
episode: 412 training return: tensor(-41084648., device='cuda:0')
episode: 413 training return: tensor(-24414.5000, device='cuda:0')
episode: 414 training return: tensor(-98992136., device='cuda:0')
episode: 415 training return: tensor(-42245.6367, device='cuda:0')
epoch: 104 test_true_pfm: 33.48239639407782
episode: 416 training return: tensor(-10841.4141, device='cuda:0')
episode: 417 training return: tensor(-28478.2402, device='cuda:0')
episode: 418 training return: tensor(-9063.5352, device='cuda:0')
episode: 419 training return: tensor(-10488.5195, device='cuda:0')
epoch: 105 test_true_pfm: 12.64591506036877
episode: 420 training return: tensor(-14182.9131, device='cuda:0')
episode: 421 training return: tensor(-15572.7012, device='cuda:0')
episode: 422 training return: tensor(-316978.0312, device='cuda:0')
episode: 423 training return: tensor(-15682.8398, device='cuda:0')
epoch: 106 test_true_pfm: 5.722250138087894
episode: 424 training return: tensor(-12378.6953, device='cuda:0')
episode: 425 training return: tensor(-6582.6309, device='cuda:0')
episode: 426 training return: tensor(-8184.6509, device='cuda:0')
episode: 427 training return: tensor(-8369.5293, device='cuda:0')
epoch: 107 test_true_pfm: 127.90764932649937
episode: 428 training return: tensor(-10559.8027, device='cuda:0')
episode: 429 training return: tensor(-8740.9707, device='cuda:0')
episode: 430 training return: tensor(-7297.3911, device='cuda:0')
episode: 431 training return: tensor(-8205.1309, device='cuda:0')
epoch: 108 test_true_pfm: 77.02943646544362
episode: 432 training return: tensor(-11309.3047, device='cuda:0')
episode: 433 training return: tensor(-5880.7178, device='cuda:0')
episode: 434 training return: tensor(-5208.5220, device='cuda:0')
episode: 435 training return: tensor(-5132.9697, device='cuda:0')
epoch: 109 test_true_pfm: 43.13869471209085
episode: 436 training return: tensor(-5229.3511, device='cuda:0')
episode: 437 training return: tensor(-5469.4009, device='cuda:0')
episode: 438 training return: tensor(-5307.2373, device='cuda:0')
episode: 439 training return: tensor(-5440.0967, device='cuda:0')
epoch: 110 test_true_pfm: 42.2226557885027
episode: 440 training return: tensor(-5464.8394, device='cuda:0')
episode: 441 training return: tensor(-5401.9092, device='cuda:0')
episode: 442 training return: tensor(-6519.4751, device='cuda:0')
episode: 443 training return: tensor(-13800.6250, device='cuda:0')
epoch: 111 test_true_pfm: 89.61463997992887
episode: 444 training return: tensor(-13870.6748, device='cuda:0')
episode: 445 training return: tensor(-21929.2637, device='cuda:0')
episode: 446 training return: tensor(-16757.1680, device='cuda:0')
episode: 447 training return: tensor(-15799.6602, device='cuda:0')
epoch: 112 test_true_pfm: 79.96004523651798
episode: 448 training return: tensor(-16406.1855, device='cuda:0')
episode: 449 training return: tensor(-1618378.1250, device='cuda:0')
episode: 450 training return: tensor(-1616499.7500, device='cuda:0')
episode: 451 training return: tensor(-1620558.5000, device='cuda:0')
epoch: 113 test_true_pfm: 87.10669302028727
episode: 452 training return: tensor(-13661.1504, device='cuda:0')
episode: 453 training return: tensor(-16902.5625, device='cuda:0')
episode: 454 training return: tensor(-30887.5625, device='cuda:0')
episode: 455 training return: tensor(-558305.1250, device='cuda:0')
epoch: 114 test_true_pfm: -131.51407425919209
episode: 456 training return: tensor(-460377.6562, device='cuda:0')
episode: 457 training return: tensor(-372256.3438, device='cuda:0')
episode: 458 training return: tensor(-9.1117e+08, device='cuda:0')
episode: 459 training return: tensor(-326080.0625, device='cuda:0')
epoch: 115 test_true_pfm: 395.96310600544234
episode: 460 training return: tensor(-218236., device='cuda:0')
episode: 461 training return: tensor(-39375.6094, device='cuda:0')
episode: 462 training return: tensor(-628052.1875, device='cuda:0')
episode: 463 training return: tensor(-286622.1562, device='cuda:0')
epoch: 116 test_true_pfm: 141.0499526975004
episode: 464 training return: tensor(-20101.8691, device='cuda:0')
episode: 465 training return: tensor(-68284.7266, device='cuda:0')
episode: 466 training return: tensor(-3209350.7500, device='cuda:0')
episode: 467 training return: tensor(-1892680.1250, device='cuda:0')
epoch: 117 test_true_pfm: 19.436852539752255
episode: 468 training return: tensor(-349269.2188, device='cuda:0')
episode: 469 training return: tensor(-18476.7441, device='cuda:0')
episode: 470 training return: tensor(-96989.3828, device='cuda:0')
episode: 471 training return: tensor(-109353.0156, device='cuda:0')
epoch: 118 test_true_pfm: 198.20504810591356
episode: 472 training return: tensor(-109194.0391, device='cuda:0')
episode: 473 training return: tensor(-158052.9062, device='cuda:0')
episode: 474 training return: tensor(-146502.1094, device='cuda:0')
episode: 475 training return: tensor(-447353.6250, device='cuda:0')
epoch: 119 test_true_pfm: -40.61795438140115
episode: 476 training return: tensor(-188305.2500, device='cuda:0')
episode: 477 training return: tensor(-399464.3438, device='cuda:0')
episode: 478 training return: tensor(-263770.3750, device='cuda:0')
episode: 479 training return: tensor(-226469.2969, device='cuda:0')
epoch: 120 test_true_pfm: 10.207571204000027
episode: 480 training return: tensor(-249957.5000, device='cuda:0')
episode: 481 training return: tensor(-115943.9844, device='cuda:0')
episode: 482 training return: tensor(-114929.7109, device='cuda:0')
episode: 483 training return: tensor(-1617533.7500, device='cuda:0')
epoch: 121 test_true_pfm: -124.25064090357266
episode: 484 training return: tensor(-48421.1289, device='cuda:0')
episode: 485 training return: tensor(-1724869.7500, device='cuda:0')
episode: 486 training return: tensor(-1595819., device='cuda:0')
episode: 487 training return: tensor(-1687695.5000, device='cuda:0')
epoch: 122 test_true_pfm: 301.91682998666926
episode: 488 training return: tensor(-1581290., device='cuda:0')
episode: 489 training return: tensor(-1609548.1250, device='cuda:0')
episode: 490 training return: tensor(-52809.0352, device='cuda:0')
episode: 491 training return: tensor(-56975.1016, device='cuda:0')
epoch: 123 test_true_pfm: 226.2259831450532
episode: 492 training return: tensor(-61440.7578, device='cuda:0')
episode: 493 training return: tensor(-2345425.7500, device='cuda:0')
episode: 494 training return: tensor(-1561110.6250, device='cuda:0')
episode: 495 training return: tensor(-1616828.7500, device='cuda:0')
epoch: 124 test_true_pfm: -144.9822368624267
episode: 496 training return: tensor(-1613422.8750, device='cuda:0')
episode: 497 training return: tensor(-1617233.7500, device='cuda:0')
episode: 498 training return: tensor(-3.7405e+09, device='cuda:0')
episode: 499 training return: tensor(-3.8952e+09, device='cuda:0')
epoch: 125 test_true_pfm: -149.60645048636223
episode: 500 training return: tensor(-1740059.7500, device='cuda:0')
episode: 501 training return: tensor(-8137133., device='cuda:0')
episode: 502 training return: tensor(-150406.4844, device='cuda:0')
episode: 503 training return: tensor(-18244.7988, device='cuda:0')
epoch: 126 test_true_pfm: 72.79307473384759
episode: 504 training return: tensor(-19586.1387, device='cuda:0')
episode: 505 training return: tensor(-14740.0518, device='cuda:0')
episode: 506 training return: tensor(-16697.7539, device='cuda:0')
episode: 507 training return: tensor(-16638.2109, device='cuda:0')
epoch: 127 test_true_pfm: 139.99028581905876
episode: 508 training return: tensor(-15162.3467, device='cuda:0')
episode: 509 training return: tensor(-16902.1777, device='cuda:0')
episode: 510 training return: tensor(-18112.5137, device='cuda:0')
episode: 511 training return: tensor(-15749.4521, device='cuda:0')
epoch: 128 test_true_pfm: 203.8434943949269
episode: 512 training return: tensor(-1650302.7500, device='cuda:0')
episode: 513 training return: tensor(-7.0953e+09, device='cuda:0')
episode: 514 training return: tensor(-1318801.6250, device='cuda:0')
episode: 515 training return: tensor(-34037.1523, device='cuda:0')
epoch: 129 test_true_pfm: -42.685207846154434
episode: 516 training return: tensor(-1621283.3750, device='cuda:0')
episode: 517 training return: tensor(-1.6342e+10, device='cuda:0')
episode: 518 training return: tensor(-1215243.7500, device='cuda:0')
episode: 519 training return: tensor(-6.6128e+12, device='cuda:0')
epoch: 130 test_true_pfm: -12.620138680723414
episode: 520 training return: tensor(-10485483., device='cuda:0')
episode: 521 training return: tensor(-11261866., device='cuda:0')
episode: 522 training return: tensor(-416624.7500, device='cuda:0')
episode: 523 training return: tensor(-1739211.7500, device='cuda:0')
epoch: 131 test_true_pfm: 42.60898646759894
episode: 524 training return: tensor(-1.0183e+15, device='cuda:0')
episode: 525 training return: tensor(-144765.6406, device='cuda:0')
episode: 526 training return: tensor(-1.4180e+09, device='cuda:0')
episode: 527 training return: tensor(-1.0958e+08, device='cuda:0')
epoch: 132 test_true_pfm: -21.808901608173567
episode: 528 training return: tensor(-2.4760e+08, device='cuda:0')
episode: 529 training return: tensor(-80247232., device='cuda:0')
episode: 530 training return: tensor(-1.9596e+08, device='cuda:0')
episode: 531 training return: tensor(-2452946.7500, device='cuda:0')
epoch: 133 test_true_pfm: -187.2596142636891
episode: 532 training return: tensor(-7.7700e+08, device='cuda:0')
episode: 533 training return: tensor(-5.0252e+08, device='cuda:0')
episode: 534 training return: tensor(-1473069.1250, device='cuda:0')
episode: 535 training return: tensor(-2465304.7500, device='cuda:0')
epoch: 134 test_true_pfm: 216.75989632082556
episode: 536 training return: tensor(-1442996.5000, device='cuda:0')
episode: 537 training return: tensor(-1844785.3750, device='cuda:0')
episode: 538 training return: tensor(-305030.2812, device='cuda:0')
episode: 539 training return: tensor(-144026., device='cuda:0')
epoch: 135 test_true_pfm: -122.44012294257207
episode: 540 training return: tensor(-978546.3125, device='cuda:0')
episode: 541 training return: tensor(-984425.8750, device='cuda:0')
episode: 542 training return: tensor(-942769.2500, device='cuda:0')
episode: 543 training return: tensor(-213843.7812, device='cuda:0')
epoch: 136 test_true_pfm: -101.59639120234665
episode: 544 training return: tensor(-148237.4375, device='cuda:0')
episode: 545 training return: tensor(-940373.6875, device='cuda:0')
episode: 546 training return: tensor(-12099996., device='cuda:0')
episode: 547 training return: tensor(-6174187.5000, device='cuda:0')
epoch: 137 test_true_pfm: 7.711247085113977
episode: 548 training return: tensor(-119356.4766, device='cuda:0')
episode: 549 training return: tensor(-7.6356e+08, device='cuda:0')
episode: 550 training return: tensor(-862508.4375, device='cuda:0')
episode: 551 training return: tensor(-119530.0938, device='cuda:0')
epoch: 138 test_true_pfm: 52.88525681853321
episode: 552 training return: tensor(-64215.2539, device='cuda:0')
episode: 553 training return: tensor(-333280.3750, device='cuda:0')
episode: 554 training return: tensor(-4.4895e+08, device='cuda:0')
episode: 555 training return: tensor(-62963.9492, device='cuda:0')
epoch: 139 test_true_pfm: -218.17706667440567
episode: 556 training return: tensor(-204496.3281, device='cuda:0')
episode: 557 training return: tensor(-746022.1875, device='cuda:0')
episode: 558 training return: tensor(-373800.9375, device='cuda:0')
episode: 559 training return: tensor(-241153.2812, device='cuda:0')
epoch: 140 test_true_pfm: 24.58789163358307
episode: 560 training return: tensor(-1.9432e+11, device='cuda:0')
episode: 561 training return: tensor(-1.8840e+09, device='cuda:0')
episode: 562 training return: tensor(-704024.0625, device='cuda:0')
episode: 563 training return: tensor(-4684506.5000, device='cuda:0')
epoch: 141 test_true_pfm: 383.13422091096
episode: 564 training return: tensor(-5.1888e+08, device='cuda:0')
episode: 565 training return: tensor(-92698936., device='cuda:0')
episode: 566 training return: tensor(-63816516., device='cuda:0')
episode: 567 training return: tensor(-48075524., device='cuda:0')
epoch: 142 test_true_pfm: 61.77352200920884
episode: 568 training return: tensor(-49407608., device='cuda:0')
episode: 569 training return: tensor(-57138396., device='cuda:0')
episode: 570 training return: tensor(-328416.6250, device='cuda:0')
episode: 571 training return: tensor(-47643388., device='cuda:0')
epoch: 143 test_true_pfm: -66.84886246262293
episode: 572 training return: tensor(-48138596., device='cuda:0')
episode: 573 training return: tensor(-144913.6406, device='cuda:0')
episode: 574 training return: tensor(-109157.7656, device='cuda:0')
episode: 575 training return: tensor(-158237.9531, device='cuda:0')
epoch: 144 test_true_pfm: 101.8667965419469
episode: 576 training return: tensor(-148279.9062, device='cuda:0')
episode: 577 training return: tensor(-227448.4688, device='cuda:0')
episode: 578 training return: tensor(-165662.9844, device='cuda:0')
episode: 579 training return: tensor(-59851.0039, device='cuda:0')
epoch: 145 test_true_pfm: 455.5081674098307
episode: 580 training return: tensor(-86845.7969, device='cuda:0')
episode: 581 training return: tensor(-296712.3125, device='cuda:0')
episode: 582 training return: tensor(-251272.6719, device='cuda:0')
episode: 583 training return: tensor(-233779.6562, device='cuda:0')
epoch: 146 test_true_pfm: 120.55761895696678
episode: 584 training return: tensor(-203522.5781, device='cuda:0')
episode: 585 training return: tensor(-222388.9375, device='cuda:0')
episode: 586 training return: tensor(-240585.1094, device='cuda:0')
episode: 587 training return: tensor(-244735.2344, device='cuda:0')
epoch: 147 test_true_pfm: 202.47493787616847
episode: 588 training return: tensor(-197461.8906, device='cuda:0')
episode: 589 training return: tensor(-240380.3594, device='cuda:0')
episode: 590 training return: tensor(-174413.3281, device='cuda:0')
episode: 591 training return: tensor(-189702.8281, device='cuda:0')
epoch: 148 test_true_pfm: 195.0708274790422
episode: 592 training return: tensor(-167477.9062, device='cuda:0')
episode: 593 training return: tensor(-235385.2188, device='cuda:0')
episode: 594 training return: tensor(-227252.8125, device='cuda:0')
episode: 595 training return: tensor(-218488.9688, device='cuda:0')
epoch: 149 test_true_pfm: 196.58521485183164
episode: 596 training return: tensor(-178518.2188, device='cuda:0')
episode: 597 training return: tensor(-178108.3594, device='cuda:0')
episode: 598 training return: tensor(-263064.3125, device='cuda:0')
episode: 599 training return: tensor(-176481.1094, device='cuda:0')
epoch: 150 test_true_pfm: 246.83681726826612
