Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.115248680114746	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
35.976792335510254	50	86.54493732081268	9.566512838649944	112.92115057760384	62.388921126876085	100000	1.8224481875398229	0.5
62.33009195327759	100	166.99396102654916	5.586045597289958	178.51446324342396	157.6416229037859	200000	1.8389749983382693	0.5
88.19880962371826	150	242.5052567798135	2.8879518269940467	249.37998135772068	236.72167689326307	300000	1.8447225778001188	0.5
114.55649209022522	200	303.9122072915996	2.512091973618662	311.22206547809765	299.54874597187154	400000	1.848710227447018	0.5
140.83603191375732	250	323.7508151165044	1.6905140684906268	327.3849347445648	320.63152840326075	500000	1.8486372099645916	0.5
166.7809648513794	300	340.6911562840575	1.765461217728339	343.9066801663721	335.7515091350069	600000	1.853298418196664	0.5
192.778235912323	350	345.4596577691467	2.378935410489761	350.0995815169299	339.45694221783197	700000	1.8553457227070935	0.5
218.4369924068451	400	350.41636945480394	1.7892417649534762	353.71005002234597	344.41792618774343	800000	1.8572875590170081	0.5
245.0264537334442	450	352.5889228647668	2.1892380827030817	355.9041832569492	347.33792209008243	900000	1.8599517027491816	0.5
275.33502650260925	500	353.9833403386132	1.609497059761455	357.2505731503261	350.0421545301797	1000000	1.8589356529636012	0.5
278.8621199131012	501	352.0202824092035	1.4377210788066876	355.45571367430966	349.4400045395596	1002000	1.8590958766967165	0.5
