Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.869050979614258	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
55.99132752418518	10	70.63950261650483	4.554494283708736	82.41269948581976	58.613396513828775	1000000	1.0899514146888405	0.8875688776803335
99.70111608505249	20	250.86617836202552	3.0958276140138365	256.37551426878053	242.54756041546352	2000000	1.177825907506909	0.8875688776803335
143.79356026649475	30	324.9431980578095	2.5343240358866375	330.88987631635973	317.2615566169916	3000000	1.3390291630955673	1.153072452757421
186.87665271759033	40	347.21343849664134	2.568075875340518	351.5936331086559	340.91311676218174	4000000	1.3551917037609313	1.153072452757421
230.07759189605713	50	350.5330215449589	2.5790180703334795	356.0836925471667	345.167813413922	5000000	1.2906365620621163	1.153072452757421
274.1448142528534	60	351.1883936458521	2.212071181349157	357.1461155062934	347.0348136248067	6000000	1.225255160596506	1.153072452757421
314.0822551250458	70	353.1910403890825	2.290856215975729	358.67774534769705	345.1468526624376	7000000	1.1745045558859943	1.153072452757421
357.2360773086548	80	355.7653128093219	2.278476870545373	359.88944648792676	348.90784526019706	8000000	1.1397087562780062	1.153072452757421
400.48803973197937	90	353.82633028940324	1.938166755238208	358.5300457770936	348.22675271109983	9000000	1.128907924511542	1.153072452757421
443.06810688972473	100	356.1674736491457	1.7114460058263408	359.4109367216006	351.88252494484186	10000000	1.1013556555489337	1.153072452757421
