Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
13.717118740081787	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
85.84416103363037	10	33.63436911782115	8.831978319263738	48.713283421937376	6.059683126746677	1000000	0.9090909090909091	0.7300600003783609
156.51222324371338	20	154.31543095195838	6.521138071813216	165.78855143790133	137.12019539064568	2000000	0.9523809523809523	0.7300600003783609
224.28661179542542	30	264.3404469542062	3.698823753385139	272.21611733926693	253.65400551605853	3000000	0.967741935483871	0.7565396393880289
291.0397210121155	40	315.868726811577	2.534483195202421	320.1860302957648	308.72600314067677	4000000	0.975609756097561	0.7565396393880289
356.0359833240509	50	337.4238659141792	2.704760778658967	343.13401748929755	331.7942753963507	5000000	0.9803921568627451	0.7565396393880289
417.91381072998047	60	346.62732463003516	2.6501574436247934	353.02496719283226	340.06300686020404	6000000	0.9836065573770492	0.7565396393880289
484.2756350040436	70	348.9644458631831	2.416017766246689	353.4425345577765	342.2192647244665	7000000	0.9859154929577465	0.7565396393880289
549.0497181415558	80	352.0884938046956	2.4569407935131946	357.2848672911932	344.94629275938496	8000000	0.9876543209876543	0.7565396393880289
613.4875800609589	90	353.2136399888636	2.426116060771934	358.0696181516396	346.0051962304424	9000000	0.989010989010989	0.7565396393880289
679.3961219787598	100	354.12353744191523	2.181309893384229	359.30317171951174	348.27313434775715	10000000	0.9900990099009901	0.7565396393880289
