Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
12.892586469650269	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
41.153892278671265	50	0.23841921803044716	0.7834492576833909	2.9005062929987524	-1.7650056680098771	100000	0.980392156862745	0.09901475429766744
69.47856426239014	100	0.9098687745884706	0.9523795351338836	3.41113635025026	-1.5771672520360198	200000	0.99009900990099	0.09901475429766744
97.51319313049316	150	4.541957629487334	2.595170916654987	8.707768006620668	-0.5327187825825064	300000	0.9933774834437085	0.09901475429766744
125.5960476398468	200	364.3215562266461	285.27958456061947	600.1551510947756	-1.0076462799898422	400000	0.9950248756218905	0.09901475429766744
153.50961899757385	250	564.6117246014106	216.5195505500107	653.1216157395393	-0.5808703354473437	500000	0.99601593625498	0.09901475429766744
181.99945449829102	300	879.6768953265051	5.191939087580829	891.7938073221594	856.0080025778152	600000	0.9966777408637871	0.09901475429766744
210.21134114265442	350	985.9019758146153	98.53448672549165	1022.2059101238847	6.746424648401444	700000	0.997150997150997	0.09901475429766744
239.6255238056183	400	1278.6256838510383	6.8576716300977285	1292.8758725244552	1246.3265153423417	800000	0.9975062344139649	0.09901475429766744
269.24600315093994	450	1269.109149928351	7.640029454188606	1289.7888873293996	1255.4599938932806	900000	0.9977827050997782	0.09901475429766744
297.1242859363556	500	1349.2480425508297	6.605469796806346	1367.4702984392643	1335.3185105025768	1000000	0.9980039920159679	0.09901475429766744
300.57072830200195	501	1377.253472721347	13.031765371902562	1411.1494868919253	1323.295036130352	1002000	0.9980079681274899	0.09901475429766744
