Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.807078123092651	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
85.12625408172607	10	207.0345061856386	12.221781915931585	227.24452898965683	188.92117981531192	1000000	2.94659241495504	2.580578405498791
153.17643547058105	20	236.9372578952822	5.501007824058592	252.1087256608298	222.45850528171286	2000000	3.0220484319953482	2.580578405498791
221.63655400276184	30	249.68641709219474	5.606421057642957	266.3971868499648	241.67426335054915	3000000	2.915146412785158	2.580578405498791
289.0487849712372	40	257.3309019604927	7.310786614122981	283.9952863729559	250.46511492476566	4000000	2.8182673528024575	2.580578405498791
357.93634057044983	50	287.3490512212778	9.743949617677552	297.52605310454965	266.45800903474446	5000000	2.7851977696838373	2.580578405498791
428.232449054718	60	279.82201041604077	3.4160325961443174	287.2498876650061	271.9556066481164	6000000	2.763079691485363	2.580578405498791
496.71734642982483	70	287.46305052125376	7.274527376288547	298.013604064472	271.4522181341308	7000000	2.7451965801212337	2.580578405498791
565.6303489208221	80	276.8787184488151	6.932529920097385	289.61520624521654	262.96442581061274	8000000	2.7652355223369516	2.580578405498791
632.3209023475647	90	276.4387253901579	5.396053401165669	285.51718599314336	265.7215570413973	9000000	2.7517661404691247	2.580578405498791
700.4274566173553	100	288.1176066868279	2.5102586069992068	294.9461223020335	281.94389185955515	10000000	2.804999375851779	2.580578405498791
