Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.097240686416626	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
45.036887407302856	10	336.31376830261814	3.0181490949936403	341.98103984468617	328.2824181257747	1000000	3.0060273292204296	2.3118641091758008
79.55134725570679	20	354.08077627200794	2.4462038167800864	359.98454390931875	346.959560173098	2000000	2.7763544025692446	2.3118641091758008
114.38364315032959	30	352.1408341309727	3.5518447801009074	358.8284177792084	339.1434734114446	3000000	2.633264503847564	2.3118641091758008
149.01462531089783	40	353.93862267471565	2.663214858533001	358.93609367070894	342.32217343407683	4000000	2.5299084934562286	2.3118641091758008
183.3636577129364	50	353.4981772271635	3.4870071308707815	359.25407986238133	340.73023596720304	5000000	2.515648457220568	2.3118641091758008
217.47555685043335	60	354.13985353628857	2.1017680217956376	359.0564543615328	349.02085822989466	6000000	2.5020216756777374	2.3118641091758008
251.07627177238464	70	355.63336684090655	3.2880471933070514	361.6723519357183	348.75811817415524	7000000	2.469671800355463	2.3118641091758008
286.3445589542389	80	354.0401211064951	2.315104449795664	359.0520342774689	346.0188312388491	8000000	2.4411259750540175	2.3118641091758008
321.39500284194946	90	354.6189567306364	1.9306338907690865	360.5163953790907	346.6816655229777	9000000	2.422444314255251	2.3118641091758008
355.9497661590576	100	355.4476716249285	2.6799071963106824	361.4351422875261	346.2840945662465	10000000	2.4062600660938425	2.3118641091758008
