Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
10.709390878677368	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
40.346675634384155	50	39.147371314605806	13.4080625535361	75.10801888816059	13.263745945194387	100000	0.9803921568627451	0.25
68.90226411819458	100	99.91583046168067	4.6576828617595645	110.44884532942888	89.7613948144135	200000	0.9900990099009901	0.25
97.64290189743042	150	181.83882625413895	3.982305822163142	191.27261982654454	171.51331868948182	300000	0.9933774834437086	0.25
126.69183230400085	200	219.76342729431582	4.441573518848582	227.8925556309987	209.75476234825328	400000	0.9950248756218906	0.25
155.7159662246704	250	251.86548107183003	3.6363443474501973	259.03738095000153	241.33271944505395	500000	0.9960159362549801	0.25
183.99842739105225	300	279.9441955301104	3.3889941424218626	284.96135803032666	269.8481716514798	600000	0.9966777408637874	0.25
215.60724186897278	350	291.253255983856	2.814696144424594	297.5597980531893	283.32841938119964	700000	0.9971509971509972	0.25
242.59594416618347	400	316.65637409533605	2.0419995724521174	320.86834825971164	312.14081720203467	800000	0.9975062344139651	0.25
275.00360584259033	450	331.1380229138628	2.1643665424744203	335.2358529550838	325.3551690399181	900000	0.9977827050997783	0.25
305.17525696754456	500	339.5330778380661	2.1064956599296565	343.9391189168673	333.98546899692155	1000000	0.998003992015968	0.25
308.9897632598877	501	338.4908744987502	1.9621322396573484	342.7886018209392	333.22836625162745	1002000	0.99800796812749	0.25
