Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.62083888053894	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
87.72289681434631	10	166.38249504193035	4.637893131332936	174.00031415643025	157.29498886867077	1000000	1.2228994274381797	0.898186948607286
156.06697416305542	20	282.78867853488896	2.9707917799321546	288.7895260815858	275.46818048153364	2000000	1.2622789249141786	0.898186948607286
224.31167221069336	30	337.85055418486036	2.6803527449704405	343.65671111037955	331.50377716252115	3000000	1.3644353387252701	1.1664386113540495
293.1991949081421	40	349.4910329783	2.2728852532387003	353.9982997501502	343.82408784894506	4000000	1.3388894052716127	1.1664386113540495
362.710955619812	50	351.9734717531566	2.274253167078581	357.10022666519944	344.5957894512394	5000000	1.27157095101109	1.1664386113540495
430.2079212665558	60	352.89894353841703	2.4574102881604976	359.5223314226896	348.5023999318946	6000000	1.2003445039943939	1.1664386113540495
498.63025403022766	70	353.87845993271645	2.2570969181220515	358.8366880592657	349.123194713713	7000000	1.1482886524940352	1.1664386113540495
568.4533092975616	80	353.86330436094534	2.200521305955927	359.2082837698981	348.2856407108484	8000000	1.1116209519343472	1.1664386113540495
637.4736976623535	90	353.4141059782733	1.6197788525478123	358.1210980336182	349.8484548170236	9000000	1.0750940381114382	1.1664386113540495
707.8060970306396	100	354.1293294997762	1.9131323171213017	360.32390599377686	349.1727804392576	10000000	1.052936740641117	1.1664386113540495
