Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.229031324386597	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
36.481619119644165	50	26.59774697938349	3.1788974950206694	31.900454257667775	19.65682061103871	100000	0.9803921568627451	0.25
64.17617702484131	100	148.87753969263127	7.154869499492621	164.58238942193566	131.89066651510075	200000	0.9900990099009901	0.25
93.11732459068298	150	211.0611753723742	3.9067528032201886	218.08758438692894	203.1367625145358	300000	0.9933774834437086	0.25
119.33292961120605	200	265.65263495129796	2.490905335074459	272.630240793922	261.33547830595853	400000	0.9950248756218906	0.25
146.13873720169067	250	276.5159570836154	2.0215667521480682	281.42432729324355	272.97113779420033	500000	0.9960159362549801	0.25
172.85166788101196	300	297.2102726592052	3.59041546724854	303.92357635777444	289.9788862974965	600000	0.9966777408637874	0.25
199.62476897239685	350	306.9008946425204	1.6775012187115916	312.3623043674743	303.86928120220546	700000	0.9971509971509972	0.25
226.07160305976868	400	333.35709743085835	3.2205362692480084	340.1369224502123	327.07184509770013	800000	0.9975062344139651	0.25
252.7045648097992	450	344.84824333491895	2.8802245178375823	349.23582512140274	337.32950405869633	900000	0.9977827050997783	0.25
278.87993907928467	500	347.15652818942146	2.1267479233199373	351.4477444450604	342.73209832189605	1000000	0.998003992015968	0.25
282.35590410232544	501	346.5449143381445	2.0597723613528895	351.30397646012716	342.66242554597557	1002000	0.99800796812749	0.25
