Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.92992091178894	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
85.42357802391052	10	109.18378594018328	6.846396205987874	124.88988138086279	96.12485296026716	1000000	1.0063450381093897	0.5
151.10943865776062	20	237.8005829732521	2.8658340818603714	244.7802712682751	231.13081916843657	2000000	1.0398121575432877	0.5
217.5777268409729	30	316.42907100477686	3.1158609958442764	322.6241996678291	308.36247149402334	3000000	1.1201546449878004	0.5
284.1061987876892	40	342.8614063942465	2.6429622119364278	348.2284361391794	336.61279868963175	4000000	1.1526037998790366	0.5
349.24091958999634	50	349.21964540892225	2.2602746121609747	354.08429481403437	344.5119618056342	5000000	1.146155963093983	0.5
414.1691598892212	60	351.25789653485066	2.1028934209459913	356.29175807721913	346.37186821457	6000000	1.0993288577165867	0.5
479.0681583881378	70	353.9034277436804	2.451469059875917	358.33474163216306	347.5832908655284	7000000	1.0723184445283382	0.5
545.0758867263794	80	355.02064357152017	2.392438224132997	359.2038218413072	348.0840843465412	8000000	1.0467008680734358	0.5
614.7642941474915	90	354.39983574147413	2.125046868119427	358.57581894323084	348.8001157612307	9000000	1.0204353250070224	0.5
681.9982721805573	100	353.3992122377143	1.8025757401512055	359.05808887968305	349.72903827636037	10000000	0.9962492334256239	0.5
