Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
12.345067262649536	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
42.073158979415894	50	5.16206994887394	8.060848790020998	32.91429391066049	-8.526543452695478	100000	0.9803921568627451	0.25
71.55475616455078	100	31.572375542622567	4.886958041818016	42.83954675355926	20.79463165445486	200000	0.9900990099009901	0.25
100.43068861961365	150	68.1375904711015	4.38540928314724	81.44986113964114	58.01440119962808	300000	0.9933774834437086	0.25
128.83514142036438	200	92.8650795618611	7.6331435080046255	108.93601557682268	75.11507483519381	400000	0.9950248756218906	0.25
156.668363571167	250	128.9396556843166	6.853491910859239	141.04458046457148	86.40787875489332	500000	0.9960159362549801	0.25
184.8546347618103	300	160.0019472252001	5.1317410165890065	169.9594985851436	147.60367195357685	600000	0.9966777408637874	0.25
214.3999307155609	350	197.14310225423702	4.158158739438653	206.93656292601372	187.02353396872059	700000	0.9971509971509972	0.25
242.51074314117432	400	215.78239222301585	3.398428837423888	225.0894694829767	208.57029840839095	800000	0.9975062344139651	0.25
271.7877821922302	450	232.65365281833766	3.6498608883089747	239.46805164730176	224.38767642958555	900000	0.9977827050997783	0.25
302.4766800403595	500	227.5787613138915	3.589779944145586	235.2853089480559	219.91133916535182	1000000	0.998003992015968	0.25
305.76692152023315	501	233.71212073224143	3.494365361962966	240.5916253758478	226.1327574555762	1002000	0.99800796812749	0.25
