Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
13.073330879211426	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
72.33916568756104	10	73.92868529804885	7.466252644962466	88.85734083820716	54.84261020156555	1000000	0.9090909090909091	0.570879957847765
128.63466000556946	20	223.97719956734184	4.382968514897419	231.76606260464177	214.19167563413794	2000000	0.9523809523809523	0.692060350643975
183.04299926757812	30	333.09261205103473	2.476662108566978	339.0976512618363	328.0830686886038	3000000	0.967741935483871	0.692060350643975
240.93614315986633	40	351.8876884492835	2.3913559163348594	357.13582109549316	346.61775000428315	4000000	0.975609756097561	0.7014843095056245
298.4170207977295	50	354.0225128743958	2.304892984581652	358.5130215501413	347.97610596427694	5000000	0.9778064209798233	0.7014843095056245
353.6221013069153	60	354.246884265802	2.4728163840711623	359.9185506923168	349.9881283143768	6000000	0.9814447126224752	0.7586870447016626
411.5063660144806	70	355.03044279486244	2.41937963533083	360.85484128119424	348.1950811841525	7000000	0.9816242835572626	0.7586870447016626
466.7198054790497	80	354.37828993871733	2.19290409912077	359.7980888938764	348.8264892352745	8000000	0.9829609365148979	0.7586870447016626
519.3544290065765	90	355.9749884010481	2.4346690514324636	361.74404994398355	350.79272562032565	9000000	0.9808898541888473	0.7586870447016626
574.2023408412933	100	354.4251572167021	2.238008367204867	359.34649992897175	347.22540177234623	10000000	0.9809577698673189	0.7586870447016626
