Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.0638689994812	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
79.41758966445923	10	182.59999314987633	7.466827785966616	199.38452635880094	167.6367894935538	1000000	2.8600347471681182	2.029529652970772
142.76865482330322	20	339.1390048716505	1.999268924275374	343.67878139251843	334.8669131492861	2000000	3.289876762405173	2.514693668877119
207.06231784820557	30	353.40331839479984	1.4936808766766465	356.9842425332754	349.3904310500657	3000000	3.0169885306799467	2.514693668877119
271.5298218727112	40	351.72359036958983	1.7321595929952895	355.1264295168803	347.425670237164	4000000	2.87864590517621	2.514693668877119
337.17197847366333	50	354.8758234524666	2.025585456424295	359.1190051289741	350.4204543795204	5000000	2.8058631721971774	2.514693668877119
401.7591361999512	60	353.5209335554942	2.3414230647901926	360.4545135593071	349.1889767659013	6000000	2.7101262513797	2.514693668877119
468.573215007782	70	353.6711740475919	1.7247718401204755	357.7479848000221	349.64372413873207	7000000	2.6670993125460773	2.514693668877119
537.3333716392517	80	356.44184995444937	1.8707781321178447	359.5336126666516	350.8163057996426	8000000	2.6392847727824686	2.514693668877119
605.130508184433	90	356.07641509782593	1.286824218402984	358.9512488823966	352.52455229892803	9000000	2.597256333996786	2.514693668877119
673.2256107330322	100	356.20492416997536	1.9424698427974774	359.84101095370715	351.39242741315684	10000000	2.5665126171289847	2.514693668877119
