Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.305119514465332	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
72.99735283851624	10	145.99924681139018	4.946250628388525	154.99517300206935	136.76674975595597	1000000	0.9090909090909091	0.6579107564153065
129.90440320968628	20	297.04238638044063	2.988522288606263	302.7511181413429	289.5339671741385	2000000	0.9523809523809523	0.6579107564153065
180.66564655303955	30	345.96846531546726	2.200748709087323	351.23329402692616	340.4245385581162	3000000	0.967741935483871	0.694057289834142
234.71583724021912	40	352.3591969454212	2.3852462784588933	357.8975596484961	346.26051296666265	4000000	0.975609756097561	0.7578431203811067
290.69367957115173	50	353.84520893854716	2.611355566160713	358.87924565922003	345.9827382732183	5000000	0.9803921568627451	0.7578431203811067
345.0489706993103	60	355.47286819806743	2.906119473195976	361.11069153482094	345.6317223389633	6000000	0.9836065573770492	0.7578431203811067
400.73519706726074	70	354.52678926691345	1.9251161477241512	358.87138439434057	349.03407820896246	7000000	0.9859154929577465	0.7578431203811067
457.2537307739258	80	354.1683644605941	2.0543600025798754	359.5745616987115	348.2953830647748	8000000	0.9876543209876543	0.7578431203811067
514.8178141117096	90	353.9863384088442	2.156794812182952	357.41930703428807	346.4576913419296	9000000	0.989010989010989	0.7578431203811067
566.392019033432	100	355.511610324335	2.227527343015872	360.7438307006378	349.9368771784066	10000000	0.9900990099009901	0.7578431203811067
