Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
10.717232704162598	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
43.09900259971619	50	10.462526218283529	10.123417048432007	49.86210641195066	-7.146924384258455	100000	0.9803921568627451	0.25
72.8167610168457	100	104.71605074278374	5.460996706682584	117.0612026884919	92.16720739370794	200000	0.9900990099009901	0.25
101.18451428413391	150	173.2018437420072	4.858289518439875	182.1369376371731	160.72181903084856	300000	0.9933774834437086	0.25
129.4725363254547	200	252.00509622016344	3.7285959693116677	260.0052617825568	242.34729622403393	400000	0.9950248756218906	0.25
157.79704475402832	250	299.0128054136956	2.3573106422339225	303.91600034659496	293.70130926672573	500000	0.9960159362549801	0.25
186.05392694473267	300	322.82994173751126	3.4262327355124604	330.12142501061317	314.8445207492623	600000	0.9966777408637874	0.25
214.39385342597961	350	336.3758865808248	2.115260073619183	340.1703241395153	331.5005668895028	700000	0.9971509971509972	0.25
243.38631391525269	400	348.53358519180017	2.0983229550377613	352.4361214863602	341.54361001476354	800000	0.9975062344139651	0.25
272.7554588317871	450	351.08280339438556	2.0562985562158493	355.332100262749	344.3362409945403	900000	0.9977827050997783	0.25
302.2891790866852	500	350.90780530466566	2.4199592060955974	355.3789975941763	341.86170289479196	1000000	0.998003992015968	0.25
309.4943277835846	501	351.1882780948542	2.3557057018146628	355.9324770711828	344.4202160741006	1002000	0.99800796812749	0.25
