Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.119769096374512	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
36.26874780654907	50	27.83477650284958	3.7724560172224937	35.01678655121941	20.40780828165589	100000	0.9803921568627451	0.7208555729067712
64.6683759689331	100	27.163891447937168	3.7753362771628254	37.31620140903965	19.404859499976737	200000	0.9900990099009901	0.7208555729067712
93.38137102127075	150	35.84377737298244	2.3306404961791882	40.2586030352395	28.086742977964605	300000	0.9933774834437086	0.7208555729067712
120.73251676559448	200	110.49356303314471	20.03526959781286	137.40491817425936	77.88601493812166	400000	0.9950248756218906	0.7381868324700196
147.48504996299744	250	179.52285846060394	29.82939644036973	207.54504570970312	117.31158813543152	500000	0.9960159362549801	0.7381868324700196
174.26677417755127	300	223.17118917050203	4.873597373008593	235.20258506271057	210.71015882695065	600000	0.9966777408637874	0.7381868324700196
200.9976406097412	350	243.85989672007935	2.1809872889941917	248.8895388278179	238.28128186421236	700000	0.9971509971509972	0.7406704270115955
227.65383386611938	400	295.9693048126712	3.368765079113483	303.5850428320118	289.05035933101317	800000	0.9975062344139651	0.7406704270115955
254.31646752357483	450	315.35567328414726	2.6439734921937306	324.11424910172354	309.6867089821317	900000	0.9977827050997783	0.7406704270115955
280.93695521354675	500	326.46863119501563	2.802186653809273	333.2560627120547	320.6410918866022	1000000	0.998003992015968	0.7406704270115955
283.94260478019714	501	326.5514430132122	2.598363606402514	332.142284123227	320.48161303496454	1002000	0.99800796812749	0.7406704270115955
