Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.840437412261963	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
44.895620584487915	10	58.31279995548246	11.220820524393048	81.21951351454481	38.19591489323648	1000000	1.4233005581284255	0.5
78.38030242919922	20	252.06433750443728	3.3759745691574374	258.8940576040477	242.3471990787948	2000000	1.5374895517597809	0.5
112.1475760936737	30	343.85014208770286	2.0547193818368292	348.93370543955825	340.11409484082833	3000000	1.5820172965737884	0.5
146.06058549880981	40	354.51753748512124	2.310255271813038	359.4286741607357	348.30693100660574	4000000	1.5660298649179514	0.5
178.85380053520203	50	354.96680477350293	2.622223815056568	359.9660995627055	348.9924435268622	5000000	1.5492085712918149	0.5
212.75002431869507	60	354.6494556067951	2.2782452793529706	359.20249263755977	348.934436341282	6000000	1.5463508126080927	0.5
246.40581631660461	70	354.1520255281903	2.2094401548469937	361.91596888925415	348.59310384173295	7000000	1.5346285409868428	0.5
280.320307970047	80	355.44761997799367	2.5608006808492685	360.09171681429143	348.0457526034661	8000000	1.5294779240453202	0.5
314.37580847740173	90	353.8657742806419	2.3977598104769955	358.1570995275688	347.7676517617365	9000000	1.5297270160781415	0.5
347.75299739837646	100	355.06338388273	2.4911353225497574	360.04087082348997	347.4303054633201	10000000	1.522539185154619	0.5
