Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.777295351028442	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
74.2539312839508	10	176.84931891765984	4.760568488294929	186.37567958928412	165.1925425484078	1000000	1.7135709664976753	1.7851207434414396
130.83368730545044	20	348.80469807007137	2.597878660082643	355.20433256053366	342.860101074446	2000000	1.9573222740827323	1.7851207434414396
189.38563537597656	30	353.17199653538313	2.332359067576127	358.0620722385647	347.1039350624196	3000000	1.7879741411681713	1.7851207434414396
246.8061444759369	40	353.8587168273147	2.104958154035672	359.42182123771636	349.2798473460134	4000000	1.7193864836547916	1.7851207434414396
304.6217966079712	50	355.0931240959046	2.0275698067352543	360.0805181375399	349.3218562206457	5000000	1.6153359366746167	1.7851207434414396
363.70866227149963	60	355.1356479821584	2.3313822680961547	360.4795009251102	349.489488311443	6000000	1.5515384100981522	1.7851207434414396
421.80864787101746	70	355.33661291519405	2.519030298712909	360.45218980812933	345.4680346660316	7000000	1.5371458236227689	1.7851207434414396
479.03471851348877	80	356.82129115803195	2.528831029598206	361.16124736960046	350.324834629253	8000000	1.4977714831763411	1.7851207434414396
538.727968454361	90	356.7744849396024	2.545627567357959	361.4085915865144	349.7456543373992	9000000	1.4649702927010098	1.7851207434414396
595.5219178199768	100	356.4852063072187	2.444395552866962	361.6339012742974	349.8555699958233	10000000	1.4339445526940473	1.7851207434414396
