trian_config 
gae_lambda:0.95 
 gamma:0.99 
 clip_coef:0.2 
 max_clip_coef:4 
 vf_coef:1 
 ent_coef:0.0 
 learning_rate:0.00025 
 ratio_coef:0.5 
 grad_norm:0.5 
 max_version:1000000 
 pg_loss_type:1 
 enable_clip_max:True 
 use_noise:True 
 enable_ratio_decay:False 
 enable_entropy_decay:False 
 enable_lr_decay:False 
 enable_grad_norm:False 
 enable_adv_norm:True 
 enable_mini_batch:True 
 gae_length:512 
 num_envs:8 
 num_steps:512 
 use_gpu:False 
 mini_batch_size:512 
 tensorboard_comment:gae_length_512_num_steps_512 
 check_reward:[405.15576098707163, 644.6244511947484, 450.4776826617383, 575.6167042026266, 561.5981359841658, 508.99524124935465, 422.29004686096965, 651.8848996078281, 483.6423823941501, 526.6240398671941, 438.9705043279428, 558.8161895267964, 589.0277723930078, 481.8714601763023, 654.074367930456, 655.0796193724082, 574.239967718856, 593.2914349689961, 381.20088400320986, 623.1405720054331, 509.0968754966581, 344.0825261272904, 646.8305137276501, 653.9978456091039, 648.8057055675924, 553.8202144809578, 643.1628286843986, 351.58847067726435, 481.0427422759602, 642.8243748821454, 502.4200107557532, 648.8012433725589, 379.7872521505514, 593.3679709020621, 646.6080779302108, 459.74756494573546, 648.6577448519947, 527.6472592682428, 649.5926026533824, 476.0919160233324, 344.3333593834653, 644.3617772575244, 639.8989578034709, 528.5113020909798, 614.516435275797, 342.78017170851274, 339.0368706517591, 658.5146947697715, 573.7717584134693, 584.9694223358806, 612.8649791116768, 622.6557701269026, 635.9513243489167, 652.8987020864747, 609.1349347709436, 519.56784330958, 612.7296502000954, 550.1441002465731, 641.314151978611, 464.6504625542967, 652.4971494575618, 574.8886725425025, 585.6415304138491, 613.7322233205425, 613.1254383490899, 651.415607150456, 376.33019681166775, 648.117403033173, 653.7023582141624, 646.5053268656383, 475.7114514896502, 552.562926137017, 644.0762226862047, 645.0446930038472, 645.5064639978075, 493.00193484855174, 356.7749512815627, 579.6990815165434, 511.61468324939995, 504.5466250017523, 630.4670427373494, 649.3092310136456, 649.600417813474, 519.7867071287225, 580.7083649736678, 343.4571523502273, 648.4710738975964, 487.9907987777337, 643.8893514969146, 639.1073315644435, 438.10708923884584, 642.8503493758126, 596.8032118839353, 447.7260627125277, 647.6897621864903, 559.4586589803441, 503.5750283005466, 459.1971024769573, 528.2687485967565, 649.1731461737623] 
average_reward:556.7133409729154 
check_reward:[736.7538827232264, 697.7886175794555, 738.9373567933935, 744.8828349694841, 717.1583021360245, 741.0991118976262, 736.8680956453131, 712.6846182303053, 734.6645812322832, 737.9559807294603, 737.3294117693256, 743.3345087670764, 791.3547915122593, 737.6755291911427, 739.5764616054786, 742.7099824285051, 738.4481712845472, 748.0634395239624, 727.7694629794539, 734.5682246665385, 739.6805587129356, 743.2565921036554, 738.1599271803879, 809.699372046192, 725.2172244147304, 696.9419259553829, 739.6327580419608, 735.7485748664192, 741.4439639357918, 728.5311322815173, 737.5545447235413, 743.6691575048703, 743.2159893656169, 738.6366640623397, 743.2330428278842, 735.2597903626923, 739.6586571527729, 743.6755216531701, 736.9688682482749, 733.6479598903188, 789.6332929564942, 734.6008914436657, 742.2088531876379, 742.5315387768975, 728.1317902435965, 795.3306878433543, 740.8025923434537, 734.2272510416759, 744.0567167821278, 744.1804805433501, 733.5232479706522, 782.3441303962934, 736.0020147345369, 740.4435985907173, 741.668165540895, 744.8025986375733, 729.2323504213007, 743.325595205328, 742.5904100788875, 787.6544078483018, 737.5448889323781, 742.4124241336813, 799.6879849249084, 782.1570637308134, 721.3577358840674, 743.9588349762827, 745.5746041990908, 733.0775992835914, 735.8353739597808, 739.4675735041512, 734.053206697547, 739.9095016794165, 739.8844874390396, 736.7454971054002, 740.0063663731282, 736.3461054314051, 751.1156861749866, 746.1256136071528, 733.1317818012724, 743.3016990489002, 732.1748104112114, 716.7494652203006, 736.4314684214576, 743.0077068141269, 736.041945021302, 754.5919383923026, 734.8080634665433, 738.9742680677311, 742.8567301914159, 743.2582088970911, 723.6781169176656, 740.015954718257, 743.8488869727821, 735.6904319900239, 638.6472521619169, 736.663934171519, 740.6415036174242, 740.8437319091668, 742.8850175338857, 744.3097148411447] 
average_reward:740.5855938420632 
check_reward:[173.5106680381872, 173.0175915712685, 173.23123291908047, 174.86628731838078, 174.82802797619792, 173.95445137263252, 174.32689692018255, 174.60432225371838, 170.68234469564914, 176.0244998559975, 161.60310625643436, 177.18728082297082, 162.70726432320288, 171.7298719643426, 176.98694597249096, 175.64875990082575, 171.68795201833163, 173.64811780843615, 176.99630655966192, 174.23873675069984, 176.44544172933854, 173.39366378293195, 176.81185248811616, 169.2393809559806, 176.81107245490279, 171.77233008319655, 174.7474534864004, 173.748933914753, 173.5598246337016, 174.54266756551448, 173.57103783585742, 174.04794411180063, 176.76498791798858, 177.7570741901122, 174.99743682956884, 173.76413396620623, 174.10677251262177, 170.7258796415772, 176.0632004651273, 172.30236074576666, 173.50012066842234, 172.09165192338327, 173.94898916909113, 161.70832151809708, 172.50321600371367, 176.65038843814798, 177.87124121148435, 173.8911345371212, 173.12934358298403, 173.602329871645, 177.9167440450984, 173.80668114301355, 164.46871047117745, 176.4707580973761, 176.4559706896332, 169.85299902095437, 174.17386656917708, 172.0605868797787, 175.7567917915624, 174.32931962487922, 173.55259094672343, 173.8051753366753, 174.0624580202013, 178.53076730399485, 174.4193995734771, 164.51882834447633, 174.13348588839278, 175.60293107796846, 173.82443584291818, 167.26600315210186, 171.88977144524534, 177.216865977634, 178.9415977966697, 174.1038914105647, 177.38736020069194, 176.00438403520224, 173.6806856079009, 171.8927053539804, 175.6021941450829, 177.7810481023199, 174.196655441183, 161.7256271359425, 173.40549341775161, 163.46783134308987, 175.96368524595366, 175.75018108634475, 177.51264503853875, 174.07631510329585, 169.39275740754667, 174.57697406964274, 174.15142743147115, 176.8321012827131, 176.95250362082788, 176.39202282096383, 177.23821601182027, 164.55994682129543, 175.33734297197708, 174.02380843683602, 174.00684675169282, 174.02561538627592] 
average_reward:173.5864785625428 
check_reward:[1043.2607455908612, 1054.6998181284102, 942.2839390173988, 890.0585856344245, 1051.2749074093558, 1004.7722565714228, 1020.8963215096719, 1025.8580585888221, 1053.2367226540755, 1011.1893835127738, 1036.0027271805855, 1040.0771402253376, 1032.3620831498317, 869.9570531259997, 995.4750085223741, 1045.444508798931, 910.7829942680556, 776.2949810747241, 1038.9475330606847, 742.8658955187111, 847.6442522236878, 1057.5775711625574, 972.7113681312375, 770.9322969310264, 1209.685145622024, 1246.2133641493592, 37.00037106887219, 865.4085935358528, 964.0355610573769, 622.4252577500456, 1014.8617784646649, 741.0146605641644, 1056.756021204617, 1033.5045274018667, 616.8126362398167, 1149.1117789806933, 1053.433318728588, 1055.8045386231177, 1046.1814750763538, 1325.756132192139, 1347.9755606295028, 1071.0664088500844, 1022.3633403005069, 887.0632612562163, 1073.2526839982577, 1039.7498139994618, 1010.8488244514776, 842.0916777264445, 812.4128212731445, 894.6829892637289, 827.2849991456699, 823.0489737754724, 1087.879756923026, 932.2244434299405, 739.9080456833021, 1016.2071828333937, 814.0679635130565, 1015.1022658678698, 613.018917583991, 1059.9001320104817, 1001.9438534995045, 1061.8554462435945, 925.0188955993938, 1159.5916186810111, 1015.3592356010489, 1004.1491811081169, 1015.033325731366, 895.6084753139796, 1218.7911914988545, 1030.20646696155, 836.616509772069, 627.0069526344565, 1034.5981830396747, 847.4419295207324, 767.6534148256176, 608.0153764166508, 961.2726644931515, 826.4428836731369, 1067.5593293382517, 1030.7848652856208, 1062.696167722686, 928.8189300157826, 1248.809672373744, 702.5622018451586, 622.379828738276, 802.2506357329025, 1081.6610264834055, 1306.9950431502277, 744.2501701516055, 794.2134890490188, 1185.4648214677838, 1039.6045673511994, 847.4638079152271, 625.7909238001099, 933.8147606727929, 1005.4473919559513, 1037.023533404166, 39.29536974853428, 1115.1023590442874, 1011.127869875658] 
average_reward:942.7248374490185 
check_reward:[1038.3913719149878, 977.3265118818309, 914.8761132697217, 1100.5167525450206, 915.9192574061221, 1156.0601589011153, 732.5238039241724, 1070.3567455157386, 1086.2107653544065, 1007.6764886516423, 911.8792776407229, 1039.7811242652854, 1118.55497937786, 1021.9025917437532, 913.7655478394781, 975.8150930481472, 842.752236640145, 1007.8867013778406, 990.2220482621806, 1150.735502381871, 1058.21337610897, 834.3291051280765, 936.0652007621068, 909.6041711305024, 1142.4576886838713, 1050.930129330768, 1012.4390521357916, 1081.0594133314357, 1016.3929068992891, 799.4415102606214, 986.0273474325372, 1144.2660543765255, 932.3846106455226, 929.8106688805207, 1099.108076020007, 1154.8227508912391, 1029.6265267376612, 1152.4934198426286, 928.6166882579599, 1150.956090639227, 1020.0570735325622, 1035.16147388228, 987.3569323325701, 906.5847813888026, 1067.856220835257, 995.0262667784923, 1063.0665722553504, 1007.6613074954141, 1079.436770293027, 1149.8366671328881, 905.3219364893289, 913.953617035115, 1088.5840209918363, 909.9247186524947, 1144.4988147886017, 959.5656346105256, 913.0038110936774, 912.4557636351035, 1010.7347262431601, 953.3706799956309, 1069.8410251128084, 987.7702963153307, 914.6284858380159, 991.3923934090799, 1034.3474646266473, 924.2277132184721, 1049.5167688973872, 1034.7612951958456, 1019.2405867190225, 1148.7727678999172, 1013.7391509467485, 1061.6824908532822, 1005.119432855518, 1094.5324489729119, 1065.8163720822279, 1051.8302132272775, 970.2132912593775, 938.7473942976987, 912.3460622792218, 934.5843229986295, 1037.0174857436298, 909.6965074220675, 931.6404547518524, 918.9243920290296, 1001.9211277577622, 949.095832128223, 963.7424226516656, 989.5753375466944, 940.2689257905391, 1052.036838950985, 984.1475889864339, 985.6088621980376, 1003.5630210368885, 1017.4388604750552, 1154.6346270249496, 1177.9329181684832, 1082.7982582369204, 1128.4638228318438, 1171.9315208986327, 1158.982363902845] 
average_reward:1011.2818679443739 
