Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
13.52819299697876	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
41.536595582962036	50	0.21087533703263875	0.778525736937764	2.6900224154859558	-1.8182217951313007	100000	0.9803921568627451	0.3551215412473305
70.26646971702576	100	1.203665275173431	1.1256020212743103	3.735536058190519	-1.494302283258918	200000	0.9900990099009901	0.3551215412473305
98.84534692764282	150	5.666415689076152	3.0963091896159822	10.671174388697946	-0.04573955779562766	300000	0.9933774834437086	0.3984649513187947
127.73325562477112	200	605.8995651079825	7.648239664293221	620.0824254262843	565.0371671402827	400000	0.9950248756218906	0.3984649513187947
156.8831250667572	250	725.8356475790341	4.995301705703962	734.8989263468247	704.9017728572944	500000	0.9960159362549801	0.3984649513187947
185.07262897491455	300	1030.9848138793038	5.637601043086528	1043.605400864035	1015.5735707916319	600000	0.9966777408637874	0.40746124001391865
212.7166929244995	350	1032.9723678877758	8.023550006824378	1065.0091358693317	1018.6448784768581	700000	0.9971509971509972	0.40746124001391865
240.1682186126709	400	1289.373532955331	4.806821345235694	1301.89797485061	1275.3107740115374	800000	0.9975062344139651	0.45084528314621886
267.4214837551117	450	1378.8015922100342	5.434110704175063	1388.5055398792028	1364.4006802318618	900000	0.9977827050997783	0.45084528314621886
297.91164112091064	500	1381.7843911434816	4.774505987643432	1392.989468915388	1368.3209461718798	1000000	0.998003992015968	0.45084528314621886
301.3819205760956	501	1390.2864608890213	7.9924256998890515	1417.0033880770206	1357.4960977791343	1002000	0.99800796812749	0.45084528314621886
