Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.97848892211914	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
86.85623455047607	10	182.37554812000178	3.6236142938131155	189.491273367541	170.49379767128266	1000000	0.9090909090909091	0.6208458616758145
155.24170899391174	20	255.2526271959344	2.765228864350017	264.08669499757525	250.26514370186487	2000000	0.9523809523809523	0.6208458616758145
224.31725549697876	30	313.84255888261845	2.4635632259160407	318.0481881168671	305.4880667566904	3000000	0.967741935483871	0.6208458616758145
292.6515791416168	40	332.53320820142403	1.8250167976015892	336.2352950622735	327.66100514819846	4000000	0.975609756097561	0.6208458616758145
361.3971748352051	50	340.9315898240068	1.6731482543838758	344.2756647602655	337.9646037449711	5000000	0.9803921568627451	0.7136229781167348
429.16632103919983	60	349.2750687124095	1.7375675618680424	352.3852134217741	343.8187467030657	6000000	0.9836065573770492	0.7136229781167348
498.4485778808594	70	349.7007651226522	1.527012262970968	353.41550222446676	346.360946662724	7000000	0.9859154929577465	0.7136229781167348
565.522501707077	80	350.9146651052326	1.9168916972805112	355.84383754676674	347.35132620082004	8000000	0.9876543209876543	0.7136229781167348
634.8563044071198	90	353.19079883984045	2.046466257301208	357.1236519347294	347.8602246479131	9000000	0.989010989010989	0.7136229781167348
702.816930770874	100	351.7845740784113	1.5514860315207568	355.3447600788495	348.416622252611	10000000	0.9900990099009901	0.7136229781167348
