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:[514.8692596569028, 518.4588705091538, 508.219191229776, 645.0076516253636, 451.46962587735305, 410.7519936393801, 371.3078882587838, 723.034297505443, 343.1703014191802, 646.9958163315362, 543.9199403362474, 314.50444935435803, 589.0765744038273, 825.0541339657501, 687.1709591388363, 491.4125527432908, 915.6100843969987, 418.08469260202287, 481.9465849281579, 480.4245513546478, 449.6902999145618, 348.0821037814183, 425.5050379743765, 393.93660988158416, 433.9173884019692, 826.3479910346483, 383.29810835062653, 447.9598028841856, 432.84770920622327, 433.31827829037996, 478.5866675477366, 578.0876426270017, 363.6950974555349, 407.43080888736336, 383.41529382239025, 873.4091923211572, 748.4945130855201, 271.8927749578716, 350.9845405321536, 556.4924907190236, 486.0468697628007, 442.8329998106467, 244.1699781646648, 613.6735524280334, 562.6470904237684, 417.27763808893815, 422.2223537209761, 519.7498260540193, 366.48200363961007, 582.6152825459362, 496.45629887818154, 572.866103546422, 364.1771453774403, 373.75641530600944, 530.4950540764248, 557.8082073185778, 546.1144616965481, 742.9001600124906, 486.28880981693055, 481.2739755951602, 539.4322566654541, 502.6924429714146, 503.18977815398216, 731.9477124979069, 594.8101859128842, 278.14558700430536, 333.58376610588664, 520.7959524387509, 456.68995651918345, 680.9856368253811, 466.5759147299735, 345.71597925471406, 365.741611707423, 612.4597800526692, 361.2426392499084, 251.02158742094744, 545.3246311392758, 345.79239587066263, 408.2929038986107, 447.61163443182375, 444.11987676063245, 417.47569301015153, 535.5108249637715, 617.1669326567667, 555.365694577124, 322.0088764623513, 462.1020754061038, 159.0453251730839, 316.3983026147247, 486.6261966330611, 771.9776459331647, 400.5067549005299, 516.1511985872967, 267.63292272808303, 219.9257868741317, 481.5183747304305, 613.7280178605683, 622.8590027896813, 384.77470286327764, 520.9500442412922] 
average_reward:486.85632599833696 
check_reward:[916.7734439622537, 1153.3434153703831, 432.98437878026914, 1208.851967267753, 881.9399098578937, 812.5201049140597, 528.9017043868175, 1072.6576976309368, 1285.5373230215591, 1695.5158062825612, 772.87305502598, 819.8449934590283, 736.6874684650109, 973.3336342587576, 1101.6660806723219, 1107.42036016038, 1467.935780642628, 1070.678343091053, 272.451178506383, 765.194027093323, 1435.711165996771, 880.0047940957586, 1276.1240293771411, 751.1846054842589, 1207.4409155498129, 236.49215841702895, 1250.488102243366, 1167.7300491117294, 466.3121875021513, 516.4013179599979, 1304.1266468320218, 905.251760485617, 715.8168906132331, 770.2256230683452, 831.8654064324525, 1062.5523870377365, 1163.5930997973269, 1592.4262903695285, 1750.3095266399803, 476.04999546935625, 358.7382618244012, 866.6123132871198, 999.8949150815777, 895.2445053282083, 700.0324352278841, 1181.005145644326, 572.9198154675075, 1296.5413461668036, 1232.3753733820274, 1341.498621907175, 1093.5719917347785, 1531.6946782626721, 1063.0068188839955, 1070.875736468757, 1947.3839744461982, 435.34150332468346, 1121.1170971796696, 214.47162748025477, 1255.6127160373583, 1988.767706077847, 1155.1290644229864, 1244.980130616345, 1103.1593722074658, 1056.9461531665756, 1124.8081996244782, 939.05327059153, 2008.0896929074554, 759.4976174669142, 747.1945429804821, 423.5076997438138, 1261.636758138832, 790.5392311438777, 1237.8524054095599, 316.67469278701486, 916.6053185077833, 1087.6083014528497, 1458.872905922969, 731.7946539787844, 494.64521164789727, 478.96742881671213, 453.43266339004975, 736.2612447437914, 1015.0307583729401, 1216.200104726854, 895.1820171530366, 1097.6152932343302, 767.5822300109562, 1229.985075904867, 1143.0520089254383, 1099.2472506840372, 874.4540354188458, 1017.592016430652, 1292.5203103213134, 1142.301003572065, 950.1216873380208, 1194.4471437522627, 1046.6974147475598, 1196.797070211581, 1195.8104500613258, 1123.8849522638247] 
average_reward:1000.2970159134429 
check_reward:[873.9498993704831, 510.3769381569335, 777.0356994781589, 1202.5950955146852, 976.1134120419213, 1280.6276388406598, 940.7894796948573, 1191.955282036697, 892.4400087904177, 831.3416957546813, 484.5884661623992, 932.4677490435064, 735.1798384394089, 796.9910238746627, 475.52417733743084, 495.04015423081455, 856.1024227749265, 905.8669351775932, 981.3881805299169, 780.238051464788, 737.507785634115, 989.7485470818812, 647.241608674341, 835.8993779931354, 1349.9736888241916, 689.4165822152526, 837.200670958126, 832.694245751836, 995.8781110522665, 895.9316014103025, 946.558330115693, 1155.4374991314432, 838.7042323376013, 812.8222885319966, 838.3250605039548, 494.4664894391914, 477.40741363181957, 487.1029063734903, 789.9909975577126, 877.2979421579485, 813.5960188262717, 716.7536783212822, 518.4421344004722, 821.9333363140161, 873.2190165441795, 777.8816387411935, 1053.9362881000975, 752.7658352815608, 1224.3866364316775, 767.4775227443034, 805.7307781854876, 1336.114165078356, 844.3790139948525, 930.4872656374087, 920.7290959247389, 927.9352507226229, 755.815708006659, 736.1138531654941, 480.2325743687403, 944.5408860110881, 928.6267939758208, 475.6931759839792, 805.0623999159131, 778.1233490994671, 501.23999308860357, 828.0451704938404, 484.6800685921462, 831.4561492035484, 745.7222540598924, 649.5835372812348, 645.5566182808044, 494.0526619838388, 772.9480173038451, 766.3115843854715, 825.0308869192927, 1143.8163489533695, 845.5278824689597, 829.9289851152954, 775.3190298735473, 1336.5738670451742, 765.8216799209406, 742.3333110921799, 707.2018778879767, 818.8316758586174, 952.0110800417613, 648.7349459524023, 510.16405025541775, 803.5795121957779, 632.9921426063327, 881.4137603431234, 846.7699059720129, 855.802071784418, 508.1732539673158, 991.4227119043323, 1158.6246804883842, 1156.385745446075, 486.7430627132563, 488.75683965315113, 859.1748806319652, 851.0655847341129] 
average_reward:815.8198977236535 
check_reward:[562.4621577626148, 576.3845023455923, 355.81461016306264, 416.04450745526816, 742.9144666060424, 403.69191332817525, 510.82090634215814, 469.76207380381555, 359.2105391784272, 345.3844511087679, 359.9516639804941, 849.7162377741804, 425.1471571513531, 509.2830965662252, 354.66168991319853, 667.8288520260348, 470.56636406859377, 1126.9716975492202, 1557.1504516291138, 683.5941249173475, 468.7421995011779, 954.8243297490621, 473.9491611567196, 646.4674357825863, 641.9369428903713, 506.21414048759624, 487.02081333338685, 792.6261055364475, 372.09857000130165, 657.5554738821069, 351.1415992695112, 771.7563250703727, 347.96916291428033, 861.1542395249119, 607.2170969057609, 470.68660747470904, 881.1500605054451, 675.9566069866306, 675.630848301508, 350.08910503996754, 370.86753689059424, 696.2486993942817, 368.66003404293906, 766.2110108113918, 465.8512560563433, 477.3561087143594, 385.48437952165574, 454.6465912098594, 700.9252722343934, 347.9751085416717, 394.08550178366085, 617.3185573558428, 383.05869937841805, 679.9215572761632, 458.0436687717146, 403.66297888169686, 450.9179674724056, 1113.4968357516805, 687.0079330838961, 368.3179750664793, 626.0466479293495, 1525.3967067755782, 389.48870098552055, 362.71343173083307, 346.5572642682206, 599.6671848098916, 1080.3091528774944, 607.428514094097, 665.0496154724018, 487.80686380691486, 390.1286401879596, 345.11395623220733, 757.9331472029872, 473.4488064804344, 373.1531819564709, 729.6967825223293, 977.1887114726775, 586.035800211354, 370.8368379734131, 456.3683374585945, 532.0215015989993, 598.5237363402138, 373.36466167165634, 346.38234137478537, 878.6917300372313, 468.39087073000456, 591.201150868568, 733.2984633180502, 368.0982994680701, 1183.9969015560223, 765.0958933897035, 515.152774303398, 577.9737021908817, 709.6566610654663, 447.00602042946235, 356.11866217669166, 377.6313601122275, 368.50084391076393, 644.3110819871289, 367.4770342731039] 
average_reward:576.8486793547414 
check_reward:[1358.212311503332, 2161.1149737657256, 1008.7178506225162, 1006.3432725099111, 1364.5574840856896, 2182.161473329026, 1164.876038469609, 390.52107261184005, 1215.2679500080092, 388.3545198322364, 596.2350768245599, 1225.6322071562474, 653.1843352368129, 654.2774287241173, 807.5135234419236, 1318.690632959294, 617.2756529044325, 2369.650315124586, 370.74216451975406, 1335.9017080558247, 1211.1089712066087, 1301.082305322191, 889.3527731593836, 1339.9004201672265, 1913.2926409774802, 1079.2766190590628, 1009.800370108119, 1256.9118049509016, 1529.3937393643478, 854.3796605075563, 493.63016632335234, 1206.361755962451, 1683.0502259313448, 986.519164794441, 996.0576427307553, 1147.4857426153499, 1216.6442136581675, 1235.5733171218453, 1864.7017195311637, 976.3794535409527, 625.5936032433931, 582.611288196566, 1007.7403597904301, 1636.850706725902, 397.9701621273904, 953.8397449955797, 1700.8676321384762, 1091.5642527435443, 394.5344016064679, 831.1526006829913, 850.7652490579336, 1211.9822052047546, 1188.4805277489113, 1459.6301869144236, 705.8598889313653, 1365.9492190937012, 1187.7219647361887, 2794.4649378674285, 2086.54817503934, 1463.066484749292, 986.7267618367134, 738.0480792119627, 947.4144599002842, 1040.9014729521343, 485.86216867206645, 1218.8859908164454, 1821.2369141690076, 920.1940627634345, 592.9636212044509, 1536.7946086513812, 1246.2493092315967, 711.14419356534, 778.535111996616, 684.1659045356183, 1964.562143452701, 711.5038448444288, 1303.5308688641376, 1203.5632533870685, 1517.2658081397924, 1178.6625355809397, 1375.4526433659476, 1200.4493972036867, 1032.204461100947, 609.4254885860723, 591.3940010430935, 598.5793279486886, 571.7941700713056, 1236.1087531133114, 635.331166704213, 755.2995029523311, 799.221216645539, 670.0793897955525, 411.55522978188526, 630.1574405072838, 394.771951811196, 616.4154369805678, 820.0438632080437, 567.7375326460924, 1206.115827068312, 807.7687092181636] 
average_reward:1070.3544291384057 
