Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.587509632110596	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
37.895790576934814	50	17.55423647568217	15.36727151694424	43.285641912181745	-11.767443385485535	100000	0.9803921568627451	0.7282365327608291
67.08744192123413	100	51.22908281927657	6.029552294323253	70.4288221183233	42.058669517107774	200000	0.9900990099009901	0.7282365327608291
95.84181261062622	150	130.9380850435035	5.50898878606788	141.14214827353135	118.94687430863996	300000	0.9933774834437086	0.7479759653981487
123.65604758262634	200	172.3024116465341	4.1948820974262	181.63416633708403	162.19231130799744	400000	0.9950248756218906	0.7817129955552287
153.12833380699158	250	197.59857307145444	3.95974057255797	205.34328188642394	188.43946614174638	500000	0.9960159362549801	0.7817129955552287
181.39145731925964	300	219.9120910327412	3.0653970092697027	226.8422652737063	212.19187238742597	600000	0.9966777408637874	0.7817129955552287
209.613698720932	350	240.57674821303027	3.729953455399483	247.5247836428116	231.8162618651404	700000	0.9971509971509972	0.7937241636825247
240.4803376197815	400	265.9373908783951	3.0362848610732818	271.62524515076075	258.6961447302019	800000	0.9975062344139651	0.7937241636825247
268.7486455440521	450	283.01904966436524	3.209436619755536	288.712837385945	274.5034939525649	900000	0.9977827050997783	0.7937241636825247
296.9449338912964	500	303.36134681011646	2.7908434944917087	308.59228950331453	296.2759885673877	1000000	0.998003992015968	0.7937241636825247
300.35952401161194	501	303.1944633952163	3.0271237037138237	308.68278262368403	295.79150266147917	1002000	0.99800796812749	0.7937241636825247
