Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.718711614608765	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
83.39468216896057	10	300.1532514590372	2.5050828243475913	305.7794206428807	295.5502304276888	1000000	2.917854059772574	2.4688393882200868
149.00640606880188	20	347.74116782674724	2.580542441529974	353.59814442662173	340.8332022622635	2000000	2.91312476293233	2.9776286958127858
215.80304646492004	30	353.4125334270136	2.386754970416029	358.9175662638154	348.0298397798906	3000000	2.8220955691928187	2.9776286958127858
282.6718032360077	40	354.0201272034563	2.1264844144429946	358.74948454633704	348.3058571331203	4000000	2.676493112304718	2.9776286958127858
350.4157507419586	50	356.8424187644404	1.9931010664911484	360.1831628808286	349.3197235307889	5000000	2.5846662596402785	2.9776286958127858
413.82589626312256	60	355.06254907708274	1.6408650098538975	358.78034978709184	350.45370555168483	6000000	2.521250286917339	2.9776286958127858
479.15793538093567	70	355.21139949767087	1.6998842309728521	359.3853173465468	349.8919013921113	7000000	2.4672251088445205	2.9776286958127858
547.4976880550385	80	354.98663551442934	1.6630693416379143	360.28076874034014	352.1049884034437	8000000	2.4831191930956424	2.9776286958127858
615.6697597503662	90	354.93532876951656	1.1452136763794187	358.09791162671763	352.84802272427623	9000000	2.4563749324653403	2.9776286958127858
682.8663802146912	100	359.1484985959102	1.2566926364653643	361.2291012480855	354.21630714833736	10000000	2.4664480618996345	2.9776286958127858
