Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.176645278930664	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
73.31928300857544	10	204.5245256298316	3.571750058980693	211.95971361006377	196.09051695093513	1000000	1.8228458291830059	1.7780479688408066
128.62356543540955	20	349.9995403672765	2.5081988433955353	355.7351814174326	344.77272362075746	2000000	1.9492036960450119	1.9597516076786825
183.5217216014862	30	354.2533947736336	2.7959895025159125	359.38323734281585	347.9628409211655	3000000	1.7853556188779958	1.9597516076786825
240.22314596176147	40	353.7086315728595	2.0623461434066455	357.6142215417931	348.65245738683734	4000000	1.6425275187216104	1.9597516076786825
293.0544800758362	50	355.91744782080013	2.483450770603642	360.1332896652166	349.2103172370116	5000000	1.6098580360339276	1.9597516076786825
347.9477279186249	60	355.4349275747988	2.479286836342245	360.18450700014364	350.18174976510636	6000000	1.5632189417082285	1.9597516076786825
405.6804344654083	70	355.1554602921575	2.2601998058436803	360.26392071534065	347.9428022291977	7000000	1.5310423073642125	1.9597516076786825
459.1200122833252	80	354.4515387106804	2.1041038061395643	358.88020403039263	347.24016021352145	8000000	1.5025690431586658	1.9597516076786825
512.0838689804077	90	355.8742095925881	2.5333940318250336	361.0242447631317	347.88988912588684	9000000	1.464950653668045	1.9597516076786825
564.8921973705292	100	354.716521363505	2.0783021386979486	359.44038024242036	348.7430706231389	10000000	1.4474814842749049	1.9597516076786825
