Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.67512559890747	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
45.70427441596985	10	32.13101689279	8.183619268644708	48.22365447785705	14.556245951243909	1000000	0.9090909090909091	0.7296114372541436
80.49282050132751	20	151.39493366270636	4.826673986860617	161.98861016519368	140.25527232745662	2000000	0.9523809523809523	0.8169093215141159
115.1059205532074	30	285.2578234973602	2.923144067173891	291.4232164566056	278.2998125455779	3000000	0.967741935483871	0.8169093215141159
148.7547206878662	40	344.6377517591761	2.4472257478016926	349.3984534875199	336.2657894808799	4000000	0.975609756097561	0.8169093215141159
183.30182790756226	50	350.87433572987464	2.2639673582042987	356.79967829080124	346.0520361458475	5000000	0.9803921568627451	0.8169093215141159
216.75337314605713	60	352.87199880267605	2.574660905484082	359.0502830093319	346.8124316002577	6000000	0.9836065573770492	0.8169093215141159
251.1471939086914	70	354.7644649557974	3.0976110948424713	360.2401463080896	346.87869687590864	7000000	0.9859154929577465	0.8169093215141159
285.7595171928406	80	353.2915503312516	2.138360945149109	357.8257615456823	347.68206109432504	8000000	0.9876543209876543	0.8169093215141159
319.5523109436035	90	353.54456548676853	2.5728493937227053	358.7993962986511	348.5488315834082	9000000	0.989010989010989	0.8169093215141159
353.4379246234894	100	353.6026260026094	2.3997163474098624	359.36649952526204	345.6503192472155	10000000	0.9900990099009901	0.8169093215141159
