Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.239755153656006	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
85.51666688919067	10	264.213545311505	2.5796902706662483	270.09289736271603	258.58081952726934	1000000	1.8811731599410195	1.487075252854534
154.36595273017883	20	343.91805317780614	2.8093616307999234	349.50241815613117	336.93889803171623	2000000	2.1310134902017013	1.5001767558683323
222.02314376831055	30	351.83957050741736	2.5150720417268264	357.2969358073242	346.0720297531225	3000000	1.9635803763800348	1.5001767558683323
289.89693093299866	40	354.3450075344709	2.648087782191979	358.86547625612	346.68613272625953	4000000	1.80192524334646	1.5001767558683323
357.75658917427063	50	353.15592931052356	2.301630923256219	359.7348339444725	349.0613278115634	5000000	1.7018625803659633	1.5001767558683323
426.5066204071045	60	353.50006796631203	2.1858108017871976	359.2907867271715	349.5984399514855	6000000	1.6243305206215095	1.5001767558683323
494.7491250038147	70	356.1083217879698	2.3673755048390195	360.4719224225846	349.19957674568286	7000000	1.556491088511951	1.5001767558683323
562.6778185367584	80	354.1451638888398	1.6183802160557086	359.1414529713802	350.5304668067256	8000000	1.5058314537133473	1.5001767558683323
630.6161112785339	90	357.1982101277796	1.8931317413932278	361.2251450617332	352.3354179373273	9000000	1.4878502176243287	1.5001767558683323
698.9606354236603	100	355.7051393848371	1.9327688748203415	360.15402953820376	350.92111548560206	10000000	1.462988000335079	1.5001767558683323
