Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.63554859161377	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
74.49562931060791	10	126.85992692982876	6.138348185804433	139.16771807006444	110.38578066108312	1000000	1.4913039080545738	0.5
131.15386033058167	20	319.91689557859127	3.071219036731235	326.9060504527297	309.2675676152576	2000000	1.6020366791053486	0.5
189.31520080566406	30	352.494912531857	2.7088202411451783	357.81840590283537	345.1995453890413	3000000	1.6143880182342287	0.5
246.62288856506348	40	354.79613933825806	2.464909286257659	360.3566616292228	349.91559268150013	4000000	1.596641613282493	0.5
294.2228465080261	50	353.6686037775502	2.2962015659572446	357.83951983152656	345.38987053366145	5000000	1.5632549203869932	0.5
349.23051023483276	60	353.58934326745987	2.17266687139762	358.5690640856046	346.89858877903316	6000000	1.5719920209853924	0.5
400.3635129928589	70	353.61750113164874	2.8734935158120343	359.5932516527828	344.196226791144	7000000	1.5592201060914694	0.5
456.4498827457428	80	353.8775079840687	2.3340974052249064	358.4688297195826	347.3707290466409	8000000	1.549785963950247	0.5
510.6078906059265	90	355.84892048577126	2.8008720703836096	360.541096794419	344.97169595393643	9000000	1.5483161846022542	0.5
563.7991254329681	100	356.0732479262586	3.322870987182141	361.2418318192649	347.35650102982254	10000000	1.5419174764900225	0.5
