Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.880558013916016	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
73.13617038726807	10	167.66120832950293	4.626628135880017	177.05719200184103	153.66628863321966	1000000	1.4866663134587796	0.5
128.11636447906494	20	333.60839272459356	2.2832503407431832	339.54058588232147	329.08093787537655	2000000	1.6077755816994426	0.5
182.6588213443756	30	350.7679517967346	2.522890315021384	356.24644569316297	344.0479257203406	3000000	1.5862859379797036	0.5
237.96707248687744	40	354.50042280473235	2.8426910126998357	360.00453923956957	348.12670515920036	4000000	1.5838110225223012	0.5
294.1830720901489	50	354.5051421763237	2.841730236543404	360.2496139915893	345.73630946909543	5000000	1.5499625879752605	0.5
349.9999077320099	60	353.35593078449847	2.5212956130975033	357.8032828348805	346.083938671276	6000000	1.5498723830496313	0.5
406.6671345233917	70	354.33699602221844	2.244241661115575	360.0997481896775	346.337798354798	7000000	1.5435129802956042	0.5
461.30152010917664	80	352.88613975956537	2.7691995729281857	359.01729656546377	346.17196552141104	8000000	1.5479030803660463	0.5
516.4099614620209	90	352.6981310104909	3.416128915368548	358.0693101132347	339.98363400099333	9000000	1.544316181057126	0.5
571.2562811374664	100	352.5914304405785	2.815710793690754	358.36385273296037	344.65180713999143	10000000	1.5337184911341584	0.5
