Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.58508563041687	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
59.69228529930115	10	30.51089912924899	3.3493602248314702	38.08922776368854	22.213603779673576	600000	0.9090909090909091	0.25
107.0715823173523	20	119.60665564521358	6.273849222472265	132.38974061218323	107.88186140661128	1200000	0.9523809523809523	0.25
148.99411368370056	30	163.13093983461667	2.759692703608243	174.24161675192045	157.83832872874336	1800000	0.967741935483871	0.25
193.01198983192444	40	234.685741123407	4.067432021492845	243.99321682727896	220.3215320041636	2400000	0.975609756097561	0.25
233.85055446624756	50	306.6900170237024	3.095649223241717	312.1985965799722	295.8951391799492	3000000	0.9803921568627451	0.25
276.81561970710754	60	330.7753230308002	3.05052703681108	337.3464867254952	323.582036437896	3600000	0.9836065573770492	0.25
316.90017533302307	70	338.5482361976286	3.474602453082538	345.73839786087046	330.596545049455	4200000	0.9859154929577465	0.25
360.0328965187073	80	344.94811570065235	3.0055940655807856	350.34232077305205	338.32818572362885	4800000	0.9876543209876543	0.25
398.6573977470398	90	347.33247101713334	2.221349927697409	352.6140901336912	342.7684343561996	5400000	0.989010989010989	0.25
439.9634108543396	100	348.7817915444159	2.6361131198775247	353.48291583452374	341.3757397774607	6000000	0.9900990099009901	0.25
479.55677366256714	110	349.35590061848075	2.2489853293285362	355.1170742235845	342.7789873147267	6600000	0.990990990990991	0.25
522.094696521759	120	351.70909642266423	2.957884187611981	357.40752251353115	342.81357912672684	7200000	0.9917355371900827	0.25
561.360945224762	130	350.6422469846907	2.310345710143825	356.4276148114586	346.29989255516557	7800000	0.9923664122137404	0.25
604.758718252182	140	351.8956686391555	2.053744111725784	357.0319888285012	346.88790738987154	8400000	0.9929078014184397	0.25
644.5692546367645	150	352.29135146833045	1.8667645066731744	358.07642088644207	347.28228672905243	9000000	0.9933774834437086	0.25
687.4625203609467	160	354.53684557983894	2.324281847370386	359.74073501979	347.7020993961487	9600000	0.9937888198757764	0.25
