Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.014583349227905	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
51.755197048187256	10	64.35504776151829	8.292953626575947	84.2451217591879	42.92887345107738	1000000	0.8871969459894817	0.6099965296166429
91.09766364097595	20	186.63090993695434	3.888843803575743	194.6057715859497	177.15043328770844	2000000	0.9409126859944905	0.6208891418746135
131.53655815124512	30	270.3709959046514	2.920604189515984	277.63538003130816	262.13091911328956	3000000	0.9599731098672355	0.6766691425023278
171.42159271240234	40	319.5253503636065	2.570478102019391	327.20950510526745	314.0124011359453	4000000	0.969735765997178	0.6766691425023278
210.92691445350647	50	339.4398308754742	2.5285682497666304	345.463794918498	333.3821276727249	5000000	0.9738579371289923	0.734595599618344
250.92676973342896	60	346.82738221366145	3.108606826718622	352.9678352633491	338.76249365799595	6000000	0.9691351103009958	0.734595599618344
290.8177673816681	70	349.91257048115995	2.851016879269136	355.2304552970454	342.87338506348897	7000000	0.959800529110239	0.734595599618344
330.6782248020172	80	351.13202983379955	2.241130641017876	355.9985730908811	346.21246788301505	8000000	0.948405729367628	0.734595599618344
372.03748297691345	90	352.3779020311496	2.524227561431278	357.66838965017814	345.4537268001586	9000000	0.9245610293945518	0.734595599618344
412.19238471984863	100	351.3666836574103	2.389666114482015	357.1704154975014	345.04428936738987	10000000	0.9243827447873484	0.734595599618344
