Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.32541823387146	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
52.12674355506897	10	207.076353102754	3.4929752461675947	218.3660465983703	201.2312883080449	1000000	1.496054436352874	0.5
90.5212881565094	20	294.39809007670027	2.99827049189104	302.636678097595	289.0521650110604	2000000	1.5822045713598087	0.5
130.3652925491333	30	335.56258066757056	1.7301814841693504	339.6979326067958	332.2770521938364	3000000	1.6014536594045414	0.5
171.47765731811523	40	348.9241098721369	1.5392551007808735	352.29341239552014	345.2239421189297	4000000	1.622619842639578	0.5
214.09676265716553	50	354.10150563862567	1.9328507443377054	358.1245435872115	349.5920587897999	5000000	1.6259955801344081	0.5
255.0999116897583	60	352.958942474397	1.7004359261069804	356.6838848498883	349.7191003478365	6000000	1.6140427887217754	0.5
296.64180850982666	70	355.10636549527754	2.119414520054236	358.9224855643697	349.4930204685661	7000000	1.6036019893984064	0.5
336.8410527706146	80	355.0574676999451	1.9374864056049348	359.7163391605718	350.1951677305624	8000000	1.584430211047131	0.5
378.41602993011475	90	355.02568371445204	1.9539197314751269	360.15280186664313	351.7293596333766	9000000	1.5739085544308002	0.5
420.231160402298	100	356.1434161392765	1.948727011824769	360.75694280164316	351.93273761560704	10000000	1.5684524958351727	0.5
