Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.792480230331421	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
38.41167688369751	50	27.58133539262668	6.111250253010952	38.24158440675819	12.634546800749376	100000	0.9803921568627451	0.7154173901801465
68.95494031906128	100	28.48645876494372	3.4014832366944328	35.05369811161654	21.109097735995533	200000	0.9900990099009901	0.7154173901801465
97.91971039772034	150	62.07276734694679	4.237464572296518	70.29988625395345	52.041597716801334	300000	0.9933774834437086	0.748067693734711
125.99951195716858	200	122.30624389700688	6.001933844806597	134.16400318476371	109.4908578202303	400000	0.9950248756218906	0.748067693734711
154.41944694519043	250	140.7617808754508	6.544352400996329	156.33243297773151	123.61214979691431	500000	0.9960159362549801	0.8313389235496507
183.70085549354553	300	167.60979649979294	5.025539152533429	175.66549314763688	154.5735309983138	600000	0.9966777408637874	0.8313389235496507
212.7953975200653	350	207.87693960816912	4.938675663411111	216.492771006946	197.6250610977877	700000	0.9971509971509972	0.8313389235496507
245.49053645133972	400	245.8140260542241	3.3931947521627914	252.3224446606473	237.92165502574062	800000	0.9975062344139651	0.8313389235496507
274.38982033729553	450	267.00648446894445	3.3946312596503905	272.5689353758935	255.6424947492851	900000	0.9977827050997783	0.8313389235496507
303.43227553367615	500	283.1407553600508	3.3161356130940036	289.331755991152	273.76227399497293	1000000	0.998003992015968	0.8313389235496507
306.6798014640808	501	284.86970582820163	2.917320143702735	291.3940782475984	278.1115862102106	1002000	0.99800796812749	0.8313389235496507
