episode: 0 training return: -499.99966368281787
episode: 1 training return: -499.999803061417
episode: 2 training return: -499.99959118750786
episode: 3 training return: -499.9998162518869
epoch: 1 test_true_pfm: -1.0775847881388214
episode: 4 training return: -499.9996435960445
episode: 5 training return: -499.99968125956235
episode: 6 training return: -499.9996591054392
episode: 7 training return: -499.9996364499277
epoch: 2 test_true_pfm: 0.19252163037232087
episode: 8 training return: -499.9997307920299
episode: 9 training return: -499.99966549472106
episode: 10 training return: -499.9996735351352
episode: 11 training return: -499.9996700723339
epoch: 3 test_true_pfm: -0.9760704798835064
episode: 12 training return: -499.9997303261603
episode: 13 training return: -499.9997023478506
episode: 14 training return: -499.99963956098406
episode: 15 training return: -499.99961620359613
epoch: 4 test_true_pfm: -0.3204912615578151
episode: 16 training return: -499.99912191968014
episode: 17 training return: -499.9987838374292
episode: 18 training return: -499.9998145590572
episode: 19 training return: -499.9996095986042
epoch: 5 test_true_pfm: 0.041260778460952253
episode: 20 training return: -499.9995665225633
episode: 21 training return: -499.9996634739136
episode: 22 training return: -499.99961947471866
episode: 23 training return: -499.9997040344768
epoch: 6 test_true_pfm: -0.8900824322590984
episode: 24 training return: -499.9997541742123
episode: 25 training return: -499.99962994871925
episode: 26 training return: -499.999659111578
episode: 27 training return: -499.9997750658239
epoch: 7 test_true_pfm: -0.264177370005193
episode: 28 training return: -499.99975867428043
episode: 29 training return: -499.99977870688457
episode: 30 training return: -499.99974314162193
episode: 31 training return: -499.9996898909928
epoch: 8 test_true_pfm: -0.8148887916065334
episode: 32 training return: -499.9996622103788
episode: 33 training return: -499.99964734507734
episode: 34 training return: -499.99968852626057
episode: 35 training return: -499.9996727374846
epoch: 9 test_true_pfm: -0.5095561001259848
episode: 36 training return: -499.999644156877
episode: 37 training return: -499.9996060339929
episode: 38 training return: -499.9996951589758
episode: 39 training return: -499.99968793522123
epoch: 10 test_true_pfm: 0.5769427563732541
episode: 40 training return: -499.99959583112764
episode: 41 training return: -499.9996932822969
episode: 42 training return: -499.9996368128995
episode: 43 training return: -499.99980797277055
epoch: 11 test_true_pfm: -0.23942013811399868
episode: 44 training return: -499.9996767179665
episode: 45 training return: -499.99969855742734
episode: 46 training return: -499.9998074065185
episode: 47 training return: -499.9997497637044
epoch: 12 test_true_pfm: -0.41808795385864966
episode: 48 training return: -499.99781838761584
episode: 49 training return: -499.99971886483365
episode: 50 training return: -499.99970160905826
episode: 51 training return: -499.9996331998343
epoch: 13 test_true_pfm: 0.36693497710549733
episode: 52 training return: -499.99969594627055
episode: 53 training return: -499.99978290914765
episode: 54 training return: -499.999776519824
episode: 55 training return: -499.9996284336941
epoch: 14 test_true_pfm: -0.6779490477679762
episode: 56 training return: -499.9996258293188
episode: 57 training return: -499.9997125346977
episode: 58 training return: -499.99969073738566
episode: 59 training return: -499.99968544400855
epoch: 15 test_true_pfm: -0.2489119282164052
episode: 60 training return: -499.9997843693464
episode: 61 training return: -499.9997237336712
episode: 62 training return: -499.99968463936676
episode: 63 training return: -499.99977094058585
epoch: 16 test_true_pfm: -0.6717881895842283
episode: 64 training return: -499.9996747514544
episode: 65 training return: -499.99969328235676
episode: 66 training return: -499.99964165349775
episode: 67 training return: -499.9998234994796
epoch: 17 test_true_pfm: -0.13094362258079442
episode: 68 training return: -499.9996884122953
episode: 69 training return: -499.99985130493747
episode: 70 training return: -499.99959153423595
episode: 71 training return: -499.9998376199621
epoch: 18 test_true_pfm: -0.005685935217102367
episode: 72 training return: -499.99965369304897
episode: 73 training return: -499.9996408603472
episode: 74 training return: -499.99966120907004
episode: 75 training return: -499.9996809323453
epoch: 19 test_true_pfm: -0.4284151081888939
episode: 76 training return: -499.9996801222405
episode: 77 training return: -499.99981327168297
episode: 78 training return: -499.9996493182171
episode: 79 training return: -499.9996960957438
epoch: 20 test_true_pfm: 0.0476874786743984
episode: 80 training return: -499.9997406079772
episode: 81 training return: -499.9996144680142
episode: 82 training return: -499.9996236828171
episode: 83 training return: -499.99966004364256
epoch: 21 test_true_pfm: -0.14959868655249273
episode: 84 training return: -499.9996874109619
episode: 85 training return: -499.9996747810991
episode: 86 training return: -499.9996638207236
episode: 87 training return: -499.9998128840621
epoch: 22 test_true_pfm: -0.22970555727221798
episode: 88 training return: -499.9997090472956
episode: 89 training return: -499.99965023640465
episode: 90 training return: -499.999629471041
episode: 91 training return: -499.99963155063676
epoch: 23 test_true_pfm: -0.4381555989060879
episode: 92 training return: -499.9997938055631
episode: 93 training return: -499.99970175170085
episode: 94 training return: -499.99962323005474
episode: 95 training return: -499.99968368594284
epoch: 24 test_true_pfm: 0.626551087753037
episode: 96 training return: -499.99972936680524
episode: 97 training return: -499.9997438133455
episode: 98 training return: -499.99965250677366
episode: 99 training return: -499.99968135711623
epoch: 25 test_true_pfm: -0.4193048306231543
episode: 100 training return: -499.99980907012997
episode: 101 training return: -499.99962288375485
episode: 102 training return: -499.9997143169393
episode: 103 training return: -499.99983531933447
epoch: 26 test_true_pfm: -0.9072954833129735
episode: 104 training return: -499.9996071319682
episode: 105 training return: -499.999819005494
episode: 106 training return: -499.999668893132
episode: 107 training return: -499.99967085894576
epoch: 27 test_true_pfm: -0.9796977644698428
episode: 108 training return: -499.9996355855485
episode: 109 training return: -499.99966241317674
episode: 110 training return: -499.9995880563956
episode: 111 training return: -499.99961671660674
epoch: 28 test_true_pfm: 0.3236092076956188
episode: 112 training return: -499.99965043285744
episode: 113 training return: -499.9996190510357
episode: 114 training return: -499.99963655731335
episode: 115 training return: -499.9996841207802
epoch: 29 test_true_pfm: -0.34699804444730353
episode: 116 training return: -499.9996946827224
episode: 117 training return: -499.99979637369586
episode: 118 training return: -499.9996159248058
episode: 119 training return: -499.99962657945815
epoch: 30 test_true_pfm: -0.12736632524083205
episode: 120 training return: -499.9996533001167
episode: 121 training return: -499.9996670981998
episode: 122 training return: -499.99967262327516
episode: 123 training return: -499.99813278201935
epoch: 31 test_true_pfm: -0.24711662270024592
episode: 124 training return: -499.99971506719635
episode: 125 training return: -499.9998395041665
episode: 126 training return: -499.9996797639893
episode: 127 training return: -499.99971199180516
epoch: 32 test_true_pfm: -0.08455257961894798
episode: 128 training return: -499.9998074365316
episode: 129 training return: -499.99961556727095
episode: 130 training return: -499.99966315819347
episode: 131 training return: -499.9996955177739
epoch: 33 test_true_pfm: -0.06711876046112064
episode: 132 training return: -499.99967572307867
episode: 133 training return: -499.99964342349597
episode: 134 training return: -499.999610564368
episode: 135 training return: -499.99983213637205
epoch: 34 test_true_pfm: -0.45171597422025195
episode: 136 training return: -499.99968505641624
episode: 137 training return: -499.99984173829574
episode: 138 training return: -499.9996142964358
episode: 139 training return: -499.99974691547374
epoch: 35 test_true_pfm: -0.03160979072897263
episode: 140 training return: -499.99968434873534
episode: 141 training return: -499.999673434516
episode: 142 training return: -499.99965055793047
episode: 143 training return: -499.99967317144416
epoch: 36 test_true_pfm: 0.5641086694359305
episode: 144 training return: -499.9996817917664
episode: 145 training return: -499.9996372381049
episode: 146 training return: -499.9997824204202
episode: 147 training return: -499.9996275901579
epoch: 37 test_true_pfm: -0.7477184628188072
episode: 148 training return: -499.99963419119337
episode: 149 training return: -499.99968983670004
episode: 150 training return: -499.9996684211832
episode: 151 training return: -499.9996168638096
epoch: 38 test_true_pfm: 0.06076247713714833
episode: 152 training return: -499.99971423324956
episode: 153 training return: -499.99971144964866
episode: 154 training return: -499.999670239353
episode: 155 training return: -499.9981856537615
epoch: 39 test_true_pfm: -0.5886605394586092
episode: 156 training return: -499.99976748361894
episode: 157 training return: -499.99973696144
episode: 158 training return: -499.99965321688245
episode: 159 training return: -499.9998195071137
epoch: 40 test_true_pfm: 0.2707447775385732
episode: 160 training return: -499.9996892588321
episode: 161 training return: -499.9996397477083
episode: 162 training return: -499.9996913568301
episode: 163 training return: -499.99985251529915
epoch: 41 test_true_pfm: 0.39175592188893305
episode: 164 training return: -499.9996616858791
episode: 165 training return: -499.99566712279625
episode: 166 training return: -499.9996288814068
episode: 167 training return: -499.99978599722766
epoch: 42 test_true_pfm: -0.37940463601447755
episode: 168 training return: -499.9996781958411
episode: 169 training return: -499.99965378938435
episode: 170 training return: -499.999669387698
episode: 171 training return: -499.9996740424665
epoch: 43 test_true_pfm: -0.49332857347698145
episode: 172 training return: -499.99960244659377
episode: 173 training return: -499.9997221600649
episode: 174 training return: -499.9997133569997
episode: 175 training return: -499.9997434927841
epoch: 44 test_true_pfm: -0.046622432659929526
episode: 176 training return: -499.99972453238905
episode: 177 training return: -499.9996774217206
episode: 178 training return: -499.9996099495331
episode: 179 training return: -499.9996970611199
epoch: 45 test_true_pfm: -0.5990655197226759
episode: 180 training return: -499.99961915377696
episode: 181 training return: -499.9996316932717
episode: 182 training return: -499.99970575743833
episode: 183 training return: -499.9997655651505
epoch: 46 test_true_pfm: -1.2024732632283144
episode: 184 training return: -499.99966193097475
episode: 185 training return: -499.9996963278872
episode: 186 training return: -499.99964497299317
episode: 187 training return: -499.9996778565564
epoch: 47 test_true_pfm: -0.48077308379006944
episode: 188 training return: -499.99968149249725
episode: 189 training return: -499.9996884899735
episode: 190 training return: -499.9996618594429
episode: 191 training return: -499.9997273346025
epoch: 48 test_true_pfm: -0.4746742738774592
episode: 192 training return: -499.99972014595284
episode: 193 training return: -499.99977050574734
episode: 194 training return: -499.99964345890703
episode: 195 training return: -499.9996725874204
epoch: 49 test_true_pfm: 0.40232392766354375
episode: 196 training return: -499.99981833198717
episode: 197 training return: -499.9996558689702
episode: 198 training return: -499.99969270370724
episode: 199 training return: -499.9996137715802
epoch: 50 test_true_pfm: -0.44133081840466487
episode: 200 training return: -499.999734361843
episode: 201 training return: -499.9996927819524
episode: 202 training return: -499.99883747305495
episode: 203 training return: -499.9996826019172
epoch: 51 test_true_pfm: -0.4060471804020211
episode: 204 training return: -499.99970445781537
episode: 205 training return: -499.99983782306754
episode: 206 training return: -499.9996498017278
episode: 207 training return: -499.9996774401441
epoch: 52 test_true_pfm: 0.19266895587148014
episode: 208 training return: -499.99971141953085
episode: 209 training return: -499.9996711630471
episode: 210 training return: -499.9996730223992
episode: 211 training return: -499.9996553809469
epoch: 53 test_true_pfm: -0.6379335839836672
episode: 212 training return: -499.999690391578
episode: 213 training return: -499.99972585589376
episode: 214 training return: -499.999723590706
episode: 215 training return: -499.99968365647567
epoch: 54 test_true_pfm: 0.1592740666731102
episode: 216 training return: -499.9996183489088
episode: 217 training return: -499.99964049654125
episode: 218 training return: -499.99977447602936
episode: 219 training return: -499.9996943617101
epoch: 55 test_true_pfm: -0.2823385060495442
episode: 220 training return: -499.9997823610003
episode: 221 training return: -499.9996384887213
episode: 222 training return: -499.99965784777453
episode: 223 training return: -499.999851441997
epoch: 56 test_true_pfm: -0.0757585555326152
episode: 224 training return: -499.9996341015908
episode: 225 training return: -499.9996854142335
episode: 226 training return: -499.9997389571712
episode: 227 training return: -499.99969701937766
epoch: 57 test_true_pfm: -0.2922286920611155
episode: 228 training return: -499.99965240117047
episode: 229 training return: -499.9998367318059
episode: 230 training return: -499.99963089501307
episode: 231 training return: -499.9997860859401
epoch: 58 test_true_pfm: -0.6929196175306376
episode: 232 training return: -499.9997203182712
episode: 233 training return: -499.99967708222766
episode: 234 training return: -499.99968450217483
episode: 235 training return: -499.99802264246665
epoch: 59 test_true_pfm: -0.5754467549253792
episode: 236 training return: -499.99969446237367
episode: 237 training return: -499.99965139887655
episode: 238 training return: -499.999611779851
episode: 239 training return: -499.99971310048716
epoch: 60 test_true_pfm: 0.051462296417709885
episode: 240 training return: -499.99963063393045
episode: 241 training return: -499.99974217008423
episode: 242 training return: -499.9996645116965
episode: 243 training return: -499.99975485929735
epoch: 61 test_true_pfm: -0.28193050185918617
episode: 244 training return: -499.9997154370043
episode: 245 training return: -499.999740888243
episode: 246 training return: -499.9996440908619
episode: 247 training return: -499.9996665259901
epoch: 62 test_true_pfm: -0.001253317639841563
episode: 248 training return: -499.99965604355185
episode: 249 training return: -499.9996270800806
episode: 250 training return: -499.9996905349433
episode: 251 training return: -499.99969817541154
epoch: 63 test_true_pfm: -0.6202472487409453
episode: 252 training return: -499.9996646659999
episode: 253 training return: -499.9997205390567
episode: 254 training return: -499.99969213788654
episode: 255 training return: -499.99973839231876
epoch: 64 test_true_pfm: -0.5022467053785616
episode: 256 training return: -499.99966222822195
episode: 257 training return: -499.9996803417883
episode: 258 training return: -499.99977386728847
episode: 259 training return: -499.99975824449035
epoch: 65 test_true_pfm: -0.0952992002868193
episode: 260 training return: -499.9997920114624
episode: 261 training return: -499.99970397485225
episode: 262 training return: -499.9996011538207
episode: 263 training return: -499.9996625980178
epoch: 66 test_true_pfm: -0.08692824374242226
episode: 264 training return: -499.99963591768693
episode: 265 training return: -499.9996890741822
episode: 266 training return: -499.999714465454
episode: 267 training return: -499.9996540991613
epoch: 67 test_true_pfm: 0.13507625237510937
episode: 268 training return: -499.9996227144343
episode: 269 training return: -499.9997238588256
episode: 270 training return: -499.99961149956835
episode: 271 training return: -499.99973846056605
epoch: 68 test_true_pfm: -0.6873802170617768
episode: 272 training return: -499.9996609347757
episode: 273 training return: -499.99968634471617
episode: 274 training return: -499.99980267485984
episode: 275 training return: -499.99973220417684
epoch: 69 test_true_pfm: -0.021702878774196868
episode: 276 training return: -499.99972484212
episode: 277 training return: -499.9997841195679
episode: 278 training return: -499.9996852297952
episode: 279 training return: -499.99964036541814
epoch: 70 test_true_pfm: 0.0016927132489932644
episode: 280 training return: -499.9997335926825
episode: 281 training return: -499.9997597348004
episode: 282 training return: -499.99789728280115
episode: 283 training return: -499.9996314583466
epoch: 71 test_true_pfm: -0.37724415992257215
episode: 284 training return: -499.9997173384248
episode: 285 training return: -499.99963010214327
episode: 286 training return: -499.99601321598
episode: 287 training return: -499.9996836271286
epoch: 72 test_true_pfm: 0.15320677814991013
episode: 288 training return: -499.9996996119663
episode: 289 training return: -499.9996766466213
episode: 290 training return: -499.99970814772985
episode: 291 training return: -499.99968217783675
epoch: 73 test_true_pfm: -0.3612349080350697
episode: 292 training return: -499.99964373924485
episode: 293 training return: -499.9996459207021
episode: 294 training return: -499.99971369076246
episode: 295 training return: -499.99964868016895
epoch: 74 test_true_pfm: -0.46180438693105613
episode: 296 training return: -499.9996887520097
episode: 297 training return: -499.99966973004916
episode: 298 training return: -499.9996918037543
episode: 299 training return: -499.9996238016041
epoch: 75 test_true_pfm: 0.3467886737959744
episode: 300 training return: -499.99965414636625
episode: 301 training return: -499.99966262189713
episode: 302 training return: -499.9996565978396
episode: 303 training return: -499.99965851487366
epoch: 76 test_true_pfm: 0.2253204078829176
episode: 304 training return: -499.9995956093144
episode: 305 training return: -499.9996262645696
episode: 306 training return: -499.9996699604033
episode: 307 training return: -499.9998204180746
epoch: 77 test_true_pfm: 0.3528472236908022
episode: 308 training return: -499.99970882707663
episode: 309 training return: -499.999607690831
episode: 310 training return: -499.9996493615152
episode: 311 training return: -499.9996844663616
epoch: 78 test_true_pfm: -0.4235933358905162
episode: 312 training return: -499.9996961608932
episode: 313 training return: -499.9996651791581
episode: 314 training return: -499.9997017288366
episode: 315 training return: -499.9997144833827
epoch: 79 test_true_pfm: 0.2389830188823695
episode: 316 training return: -499.9997016204217
episode: 317 training return: -499.99965547513233
episode: 318 training return: -499.99967802369
episode: 319 training return: -499.99969917091175
epoch: 80 test_true_pfm: 0.05006090846343921
episode: 320 training return: -499.9996457240397
episode: 321 training return: -499.9996369456845
episode: 322 training return: -499.9996567446377
episode: 323 training return: -499.9996359075861
epoch: 81 test_true_pfm: -0.02773292445348141
episode: 324 training return: -499.9996489906843
episode: 325 training return: -499.9996842163536
episode: 326 training return: -499.99979185549546
episode: 327 training return: -499.99978131178216
epoch: 82 test_true_pfm: -0.3470276244249666
episode: 328 training return: -499.99964108702574
episode: 329 training return: -499.9997102576682
episode: 330 training return: -499.99972030644875
episode: 331 training return: -499.9996577587101
epoch: 83 test_true_pfm: -0.7518884204297214
episode: 332 training return: -499.99973979708625
episode: 333 training return: -499.99964971258163
episode: 334 training return: -499.9996637481973
episode: 335 training return: -499.99972548644394
epoch: 84 test_true_pfm: -0.743160829367178
episode: 336 training return: -499.9996035309575
episode: 337 training return: -499.9996994451016
episode: 338 training return: -499.9996498812216
episode: 339 training return: -499.9997550081528
epoch: 85 test_true_pfm: -0.33605118381067395
episode: 340 training return: -499.9997031825295
episode: 341 training return: -499.99982003664155
episode: 342 training return: -499.99967249381103
episode: 343 training return: -499.9996808191809
epoch: 86 test_true_pfm: -0.041554697429808295
episode: 344 training return: -499.99969700730264
episode: 345 training return: -499.9996636946693
episode: 346 training return: -499.9997127427536
episode: 347 training return: -499.99967153325184
epoch: 87 test_true_pfm: -0.5406293201907024
episode: 348 training return: -499.9995925354444
episode: 349 training return: -499.99967013818554
episode: 350 training return: -499.9996571975743
episode: 351 training return: -499.9997718952615
epoch: 88 test_true_pfm: -0.7536587597626383
episode: 352 training return: -499.99965703698933
episode: 353 training return: -499.9996766530579
episode: 354 training return: -499.9996756630234
episode: 355 training return: -499.99969054003026
epoch: 89 test_true_pfm: -0.4486098874056596
episode: 356 training return: -499.99982587234894
episode: 357 training return: -499.9996713121406
episode: 358 training return: -499.9996526978927
episode: 359 training return: -499.99978499597637
