Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
7.868857145309448	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
35.79948544502258	50	26.151876622227952	4.804689704498572	34.34215707210751	18.348256739322096	100000	0.9803921568627451	0.7154173901801465
63.7956223487854	100	22.142421073914257	7.990048748496018	37.06148349988507	3.1085419731025468	200000	0.9900990099009901	0.7154173901801465
91.19015526771545	150	66.29813151690125	8.159550319803627	94.06909975034068	51.41431992629077	300000	0.9933774834437086	0.748067693734711
117.1994194984436	200	120.79560449521436	5.304550955632987	131.93290581856854	109.94375779590337	400000	0.9950248756218906	0.748067693734711
143.12992763519287	250	140.25536919916647	5.5785860221926615	153.01834196527489	127.44136940961471	500000	0.9960159362549801	0.8313389235496507
169.0083909034729	300	165.91246678729098	5.347414651109499	174.83137850411003	151.08663268267992	600000	0.9966777408637874	0.8313389235496507
195.36824822425842	350	203.14690497698976	3.984930300995045	210.85168033311493	191.93480940285372	700000	0.9971509971509972	0.8313389235496507
222.16602611541748	400	235.95827688721295	3.5081837084649545	245.01881157560274	226.58510994364042	800000	0.9975062344139651	0.8313389235496507
249.90135598182678	450	262.0166182564496	3.8427872180114333	269.66008216846967	250.71965334783272	900000	0.9977827050997783	0.8313389235496507
276.50937056541443	500	278.12412786833374	4.044104710215693	287.62081962340744	268.9613183651818	1000000	0.998003992015968	0.8313389235496507
279.8640456199646	501	280.18401992224375	3.6471490973348657	286.81443961756304	271.7348943949328	1002000	0.99800796812749	0.8313389235496507
