Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.276246547698975	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
35.40299081802368	50	44.7217607321116	6.42988149806429	62.66522984119001	32.898850670142565	100000	0.9803921568627451	0.25
61.47916078567505	100	157.65275969508426	6.337018877319573	170.36598177510314	138.47445219607107	200000	0.9900990099009901	0.25
87.76009559631348	150	183.08809826031342	8.142425515969661	201.6210844393354	169.67077009458444	300000	0.9933774834437086	0.25
113.82364416122437	200	226.06589282534685	3.407361755987065	233.8274476226618	220.33080087776762	400000	0.9950248756218906	0.25
139.55476903915405	250	282.82376795063146	4.277544849728246	292.4059143772174	275.4064670925727	500000	0.9960159362549801	0.25
165.0895926952362	300	299.70411550111646	2.3694033272651573	306.0387793404516	294.6197085389431	600000	0.9966777408637874	0.25
191.6957471370697	350	313.452114453328	1.436449148393753	317.4055423612008	310.0981991526205	700000	0.9971509971509972	0.25
217.90956902503967	400	330.4941978011637	1.483190903850815	333.74647602404	326.80617422227806	800000	0.9975062344139651	0.25
243.18142175674438	450	340.9296315363501	1.620893254283737	345.6367349277716	336.37972249633276	900000	0.9977827050997783	0.25
268.6203758716583	500	341.42535533572925	1.6160107131827492	344.2470308531774	337.9356937426346	1000000	0.998003992015968	0.25
272.16970586776733	501	344.4350035802143	1.5788828796942624	347.6199858034961	340.142968601489	1002000	0.99800796812749	0.25
