Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.510305881500244	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
36.258440256118774	50	34.73272077905186	7.6328565611399615	52.06373713738867	13.63762659454369	100000	0.9803921568627451	0.7282365327608291
63.58867645263672	100	68.33151936839211	6.568488737351129	85.27788275180501	57.82222907904361	200000	0.9900990099009901	0.7282365327608291
90.38600373268127	150	131.62629667780485	5.121423411672865	140.94859849954082	119.34614718603552	300000	0.9933774834437086	0.7479759653981487
117.1734447479248	200	162.09443391689726	4.317209620833805	171.51170183543582	154.26816925071034	400000	0.9950248756218906	0.7817129955552287
143.64974427223206	250	188.10772068159363	3.582647484433363	197.21110625955043	179.32612307777163	500000	0.9960159362549801	0.7817129955552287
170.94326210021973	300	208.89868077361825	3.4010133655903765	215.51786126897787	201.5200027957908	600000	0.9966777408637874	0.7817129955552287
197.48729586601257	350	233.16548759798115	3.433806923544086	239.66681909852196	225.58839526828524	700000	0.9971509971509972	0.7937241636825247
223.71460223197937	400	259.3158074064502	3.1290923588856447	266.33822389447596	251.22431381500792	800000	0.9975062344139651	0.7937241636825247
249.91437125205994	450	278.6079230185879	3.1479830466103693	285.1437159948109	271.13880064571276	900000	0.9977827050997783	0.7937241636825247
277.4502627849579	500	300.20751208331745	2.5791790174943237	305.3471356846858	293.24216999008786	1000000	0.998003992015968	0.7937241636825247
280.51121520996094	501	299.57734885889823	2.843732030477109	306.5394371104194	291.80574238154804	1002000	0.99800796812749	0.7937241636825247
