Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.419374704360962	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
37.886523485183716	50	25.67703285466654	7.161537451551943	34.87748954910785	5.873368632572237	100000	0.9803921568627451	0.25
67.68184733390808	100	25.817951843388954	2.7875702057035117	30.009983124951077	20.742027551165847	200000	0.9900990099009901	0.25
100.23441624641418	150	27.523463086457276	4.882204936701533	35.95857156896	18.261059625132475	300000	0.9933774834437086	0.25
131.25863981246948	200	27.179738563973878	8.022160890318322	43.510793775566526	12.939439098379808	400000	0.9950248756218906	0.25
161.37465047836304	250	29.57509044814149	6.903668379898938	42.491046691313386	19.308473012642935	500000	0.9960159362549801	0.25
194.55148696899414	300	44.17512173360635	2.709128809949257	49.16376464813948	36.2355772992596	600000	0.9966777408637874	0.25
226.3948473930359	350	39.98288019457774	4.606000756504619	48.52549599763006	26.811708585359156	700000	0.9971509971509972	0.25
256.77312564849854	400	68.69158972366515	9.60229813142884	83.87915466789127	40.18182224733755	800000	0.9975062344139651	0.25
285.5549464225769	450	180.27204245095098	3.041213622454425	188.4498439359013	175.19024967227597	900000	0.9977827050997783	0.25
314.71638345718384	500	225.22345020586752	6.038320752056793	237.18880355166038	211.0303230341524	1000000	0.998003992015968	0.25
317.9473376274109	501	215.02441166913258	4.736070050009909	225.29368697362952	202.49356730631553	1002000	0.99800796812749	0.25
