Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.224115371704102	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
51.38707447052002	10	299.55322414680563	2.6168804017058456	306.4630112760642	293.5834038979374	1000000	2.8043339973421566	2.306261328939449
93.33736085891724	20	346.95475706834753	2.3148597164066245	354.1391239129007	342.1298638774897	2000000	3.02249625776224	2.306261328939449
133.82264709472656	30	351.81423929460055	2.541741511844687	358.74249501153827	345.3297810126096	3000000	2.854630558858042	2.306261328939449
174.90946578979492	40	353.95749856944224	2.273363186085326	359.92283175489865	347.534004252404	4000000	2.716061148374231	2.306261328939449
216.72585916519165	50	352.9657695302069	2.0173167045424765	358.53699766274076	348.58133548195474	5000000	2.6453487107036957	2.306261328939449
257.9590702056885	60	353.60364357525464	1.9831043586588848	357.9830603110604	347.8137335692736	6000000	2.580115315526566	2.306261328939449
300.5913622379303	70	356.23650852900266	2.2508477881587288	360.8303149922576	349.1860292974452	7000000	2.5562565656925416	2.306261328939449
343.7204191684723	80	355.0512492887615	1.9555531434220925	360.40545314666815	350.78182462998666	8000000	2.549998809259208	2.306261328939449
384.62447595596313	90	354.41714893609446	2.1626168322040953	358.7952366946265	347.334311098326	9000000	2.481182359895028	2.306261328939449
427.5539107322693	100	356.7666013951036	1.9762742134614604	360.68698624388344	351.80877772253007	10000000	2.475900017902953	2.306261328939449
