Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
10.083001375198364	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
55.36539101600647	10	150.9762422970191	4.969131451663173	162.86820187105332	138.5657925944197	1000000	1.4838963358063646	0.5
100.14054727554321	20	295.8657820992184	2.9703698002988674	301.14264165522764	286.86120223466423	2000000	1.5858602755391673	0.5
143.63463187217712	30	335.0127933672819	2.837746869872274	341.0529084075242	327.13989387046604	3000000	1.6185257272216957	0.5
187.03910851478577	40	345.509165255098	3.030990608658969	351.65325080045295	337.92309135198593	4000000	1.6044659023524996	0.5
229.6734311580658	50	348.0747468153521	2.928979947793274	354.2794533194974	336.8938646330498	5000000	1.6000275814277858	0.5
273.6204626560211	60	350.39035294522284	2.6607420340585195	356.5233109823603	342.977741362527	6000000	1.5900258278564194	0.5
317.32279324531555	70	351.3158060044214	2.445242870376483	358.25745378865395	345.94769983470906	7000000	1.5700983412746763	0.5
362.1868555545807	80	351.0284964276659	2.238917766034116	357.187795114005	346.2390739901457	8000000	1.5622623859999714	0.5
406.39418601989746	90	351.06540768028077	1.7835674605164549	356.3305003621208	346.93637714500073	9000000	1.5581726184336213	0.5
451.33868408203125	100	351.59650415897056	3.2260589858065654	359.0243848578539	343.39528690627776	10000000	1.5556209803678882	0.5
