Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.88675332069397	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
71.25501561164856	10	114.73715800193142	5.618456304922549	127.19002407509834	103.5892585383699	1000000	1.3788710570455665	0.5
124.75542545318604	20	313.2847275481576	2.810542423015847	318.7041783775203	306.5766492676921	2000000	1.5376407821428368	0.5
179.09084153175354	30	351.4866093639497	2.749620480479006	356.70828521298245	342.726429334376	3000000	1.5613310319237648	0.5
234.84018206596375	40	354.2117137258116	2.757914275081108	359.7602796193678	348.02549812721554	4000000	1.5588694834199843	0.5
290.9156928062439	50	354.91253025175433	2.7663268102679828	360.75077741220593	347.82695969236374	5000000	1.546157135117543	0.5
345.12563967704773	60	353.5074924021031	2.267543703568165	357.6895889239386	344.0984649997845	6000000	1.539809301506389	0.5
399.22613048553467	70	355.1139537399844	2.654632509788754	360.6571183722117	346.6441602297127	7000000	1.534107353439817	0.5
456.3891324996948	80	356.6024763978281	2.896909792577545	361.0770877668692	346.75414120413916	8000000	1.5354751457325926	0.5
510.2125771045685	90	354.60045275840145	2.051361792060605	358.7620587476995	350.12565541407093	9000000	1.5267020867658108	0.5
563.3862693309784	100	355.7725047150669	2.4640145336464836	361.0205832514912	346.7229005250265	10000000	1.5178779518289631	0.5
