Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.980502128601074	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
37.550750970840454	50	323.33051708164095	197.05143126444588	452.1755530303344	-2.2707880066554935	100000	4.624611302837594	0.5
65.69958257675171	100	878.7008650835353	14.843048770646954	909.5178479228052	826.6668767738156	200000	4.669427545929823	0.5
93.58292293548584	150	1096.6362304286233	394.2846486531295	1312.272156703868	-437.53258660284337	300000	4.682484625777486	0.5
121.80208539962769	200	1231.0688509749648	13.091659349009317	1259.3177144983783	1191.9055281409528	400000	4.691610273875494	0.5
153.1032223701477	250	1204.578222210129	20.041942917816428	1250.73577226029	1160.799263710156	500000	4.697621315501486	0.5
179.81635069847107	300	1465.7223470370084	277.2583090743764	1555.7671336382627	-108.60077071584601	600000	4.697799634543149	0.5
207.770272731781	350	646.2194815770063	459.95429771626823	1404.372403413523	-78.77906560199335	700000	4.6996142083326635	0.5
236.34468793869019	400	571.1669895586206	26.423183543819572	632.8062901429366	513.9671998124686	800000	4.700372880863579	0.5
264.5553734302521	450	724.0205616350412	35.76180624454643	804.9191026088852	610.1582448453992	900000	4.7014419204738696	0.5
293.104478597641	500	520.0774377061664	31.085358856366252	583.5352259440115	432.4542822795338	1000000	4.702470745123318	0.5
296.3516387939453	501	624.3669288019212	28.13481463843324	687.201737066498	545.2316800321348	1002000	4.702377347567212	0.5
