Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.432217359542847	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
34.714051485061646	50	270.33143846417937	2.9575224618535976	278.6241557620815	264.75124300958123	100000	7.7952078595571646	7.244088726287992
60.87525463104248	100	351.86780634081833	1.9221374314907498	355.64164486627124	347.96978119947016	200000	7.806290361284666	7.244088726287992
86.90817308425903	150	354.4263614207607	2.052784028210391	359.4790794957662	348.46136902108265	300000	7.87325252798376	8.260889465720847
113.3611855506897	200	354.411586296889	1.7328242010615422	359.2214087731554	350.8656270655338	400000	7.922712870164038	8.260889465720847
139.53961277008057	250	348.30880834822693	1.0237065629074782	350.388385383063	345.7481846192386	500000	7.917004198106848	8.260889465720847
165.25435328483582	300	353.99617467812465	1.5871165561194231	356.79664435470477	350.24788334965706	600000	7.976883862298002	8.260889465720847
191.0101499557495	350	358.41369850278164	0.8885274754591189	360.28695419899304	356.13691433682106	700000	8.014823322224014	8.260889465720847
217.07674312591553	400	354.30810589108063	1.410128336179444	357.1920325658284	351.10169856244465	800000	8.002709765920699	8.260889465720847
243.2033634185791	450	357.3600350436749	1.3460513882720762	359.7325533704534	352.0417111240531	900000	8.005599677931956	8.260889465720847
270.16286873817444	500	358.583530769321	1.2986747469834263	360.9633419321617	355.68462847103365	1000000	7.990724194292266	8.260889465720847
273.1663906574249	501	354.31851188766194	1.2694205827589256	356.6922570593888	352.1133302450762	1002000	7.987060766950517	8.260889465720847
