Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.490844488143921	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
37.12539982795715	50	0.07053998464967894	0.9872026031865672	2.782585210405159	-2.2382637346281626	100000	4.624611302837594	0.5
65.59621739387512	100	0.6715867920969057	1.3338343138309812	4.26113746126066	-1.6241234900662675	200000	4.669427545929823	0.5
95.74138069152832	150	547.8122471464162	15.269218083627644	592.5281317457557	509.6772033055531	300000	4.682484625777486	0.5
125.02495861053467	200	1138.117346569504	23.03284982138373	1196.6136735063046	1083.2496163919568	400000	4.691610273875494	0.5
152.97232127189636	250	675.4047737484867	8.246054164769975	695.7839299906045	651.0228031333536	500000	4.697621315501485	0.5
180.83167624473572	300	1449.299377968958	17.69529077576437	1492.6609260495752	1405.9420032948256	600000	4.6977996345431485	0.5
208.47622561454773	350	2123.4929301620014	230.8162530052643	2222.3503264416067	-144.91060797742102	700000	4.6996142083326635	0.5
235.73958492279053	400	2467.8511790834423	30.22058808802462	2535.325606249273	2356.9659835426137	800000	4.700372880863578	0.5
263.1827175617218	450	2701.709185958993	41.82536075536065	2780.6033622091636	2543.144844725728	900000	4.701441920473869	0.5
290.4165003299713	500	3201.022074020022	30.817102958000177	3264.1406023893505	3138.671871729195	1000000	4.702470745123317	0.5
293.4116520881653	501	3346.142711419641	35.77879659153686	3418.756798543036	3250.038118790835	1002000	4.702377347567211	0.5
