Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.068456649780273	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
70.19338297843933	10	334.6241616911661	2.274398961635795	339.2290775132715	327.67092706565745	1000000	3.077625691307524	2.0270225695231714
127.12362265586853	20	353.9688177675575	2.7473528667541594	359.43718829611316	345.78114428796107	2000000	2.8414027954438805	2.149475854194554
184.69539427757263	30	354.69603826300147	2.5812096375699185	359.5708625919651	348.6221800686908	3000000	2.652002876260892	2.149475854194554
238.86974215507507	40	356.544361003565	2.349386069841521	361.68584265129175	350.0000260632951	4000000	2.6133641943627635	2.149475854194554
292.69833874702454	50	354.9347115595518	2.494200022662697	360.81955984060187	348.8403156517488	5000000	2.5421806926685284	2.149475854194554
350.67564725875854	60	354.64189592430165	2.074567789901867	359.80711208921275	348.51804582821205	6000000	2.481994523067908	2.149475854194554
404.6089472770691	70	355.60801861431537	2.3652204378466535	360.8209122242115	347.94800693876095	7000000	2.4298556103665105	2.149475854194554
458.8288142681122	80	355.5314958762763	3.2596444393636284	361.0314548162278	343.242235118174	8000000	2.413793549633678	2.149475854194554
514.3788752555847	90	354.2324777595974	2.2957361703569816	358.9321004357189	347.8693345283391	9000000	2.393760960583716	2.149475854194554
568.3237309455872	100	354.39509671364823	2.167813817596483	358.25787212792784	345.7057891803561	10000000	2.3902330116478474	2.149475854194554
