Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.93113088607788	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
73.87718462944031	10	58.63758583157359	6.057689827616379	70.1780719170929	45.23887952091172	1000000	0.9075419998993101	0.6589803120143087
130.17959117889404	20	215.3597753410421	4.787921679027532	223.72432687735636	202.4564347909502	2000000	0.9515696189948767	0.6589803120143087
185.4561891555786	30	326.31697112697316	2.380959052659569	331.23636308836285	320.56668159144465	3000000	0.9671923225449165	0.6589803120143087
239.9240448474884	40	351.63689415274655	2.739585643421109	357.16860262246337	345.01950744341593	4000000	0.9690292109089347	0.6589803120143087
292.51579332351685	50	354.03267836685524	2.2651503280193523	359.28201800666284	349.1100091582339	5000000	0.9460571040881363	0.6951881803332297
346.08443689346313	60	355.38202990136693	2.797059972103233	361.0160947913537	347.6582333483384	6000000	0.9068461917452637	0.6951881803332297
401.3398196697235	70	356.42307850645096	2.453207874179352	360.99270732922014	351.0365120333154	7000000	0.8842972238921482	0.6951881803332297
456.37632513046265	80	356.0427028435528	2.7484449097502943	361.4254376660101	348.3134989338578	8000000	0.8668979930106929	0.6951881803332297
511.581095457077	90	354.9689931140892	2.1576884899662327	359.09972769449814	350.8052614440094	9000000	0.8445308378823541	0.6951881803332297
566.6302924156189	100	355.98116858334475	2.6305365619722756	361.3184317911364	347.6387545700418	10000000	0.8464672541259706	0.6951881803332297
