Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
12.910929918289185	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
73.56865000724792	10	159.82091537706793	4.472193679243503	169.17111863807077	150.60638640613251	1000000	1.2553319534716378	0.8892391993132691
129.87381744384766	20	331.4410306838646	2.927506728948739	338.18253665370867	323.3930879336549	2000000	1.3453639252027147	1.0881903445577275
183.3873074054718	30	353.60617646098285	2.695830618219578	358.9831958655268	345.9271301996341	3000000	1.3192911469888857	1.0881903445577275
241.66506934165955	40	354.9449169479922	2.5534166795710695	359.44337152977823	346.77977213426493	4000000	1.191030754935572	1.0881903445577275
296.3462972640991	50	353.37145473970645	2.320035718994231	358.17876770321163	345.5244289281254	5000000	1.1044513301951864	1.0881903445577275
354.12636828422546	60	355.62524041736253	2.3114511479419453	360.7366956711048	349.1177558696363	6000000	1.0422855019719288	1.0881903445577275
411.3106083869934	70	354.66874795911417	2.0983146632822742	358.84467583122023	348.33952291203605	7000000	0.9938513795330698	1.0881903445577275
465.9917254447937	80	355.4606587199536	2.412195581011277	360.10348486172734	346.5176931977039	8000000	0.9631238826136186	1.0881903445577275
523.636700630188	90	354.870113119654	2.2571468448069623	360.6387104149908	348.50629027266405	9000000	0.9451584499735421	1.0881903445577275
576.3217446804047	100	356.3087592577201	2.5155198718963887	360.7557100488775	349.19435193180107	10000000	0.929277982175731	1.0881903445577275
