Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.494390964508057	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
85.90881085395813	10	193.6303856083594	4.0549225065171095	201.4231109621178	183.89318808339885	1000000	1.2733710147849022	0.5
152.72033715248108	20	301.69011141485515	2.5185836915504303	307.79162276769057	297.01646985874686	2000000	1.3800017638998103	0.5
217.18543195724487	30	339.85638549199956	2.1571261196311764	345.2522408745135	333.31278254900826	3000000	1.4339377904204538	0.5
282.1567733287811	40	350.66106864815947	2.249334826777289	355.26491913897917	344.5886324000894	4000000	1.4309515085741753	0.5
347.22098302841187	50	351.34710000580134	2.191783614630506	357.18134117516456	345.8183824402804	5000000	1.381097571971312	0.5
413.6445369720459	60	352.5949114883781	2.326776757321035	358.2194407163188	347.7626302514691	6000000	1.3464202071265479	0.5
480.35666394233704	70	355.2150366750946	2.724704541016883	360.22502686898224	346.95736528151974	7000000	1.3124037262714983	0.5
546.8445584774017	80	353.32088224573187	2.0029322527498477	358.2260026356962	348.52150948374765	8000000	1.301519002567679	0.5
613.9272756576538	90	355.04980520273244	2.2372663560720603	359.81182600345346	350.59224107058253	9000000	1.2950968605260293	0.5
680.8412160873413	100	356.62769235030095	2.242166405049139	360.4405290100258	349.73098887914966	10000000	1.2821548242469851	0.5
