Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.507794618606567	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
38.568344593048096	50	2.1335986692661617	1.7043253884380154	6.443289920927668	-2.033898511804182	100000	4.610406805065743	0.5
66.87800335884094	100	719.1732444344672	14.651770751553055	757.8504862327827	681.853617696921	200000	4.653935880017789	0.5
94.50330543518066	150	1031.942375795155	165.02523008675198	1113.5571534356568	-10.664540604688227	300000	4.6749685865362824	0.5
121.97156429290771	200	1331.1726080142048	22.296842372839983	1375.2720103892498	1265.8301401787903	400000	4.68526352105535	0.5
149.58078837394714	250	1603.4160052744066	46.3536531474849	1713.1520100025227	1490.4503651626874	500000	4.687991889179126	0.5
176.8245370388031	300	2210.862120060691	179.08585846247053	2331.6729164058343	481.75938889209647	600000	4.6917071581443714	0.5
204.32555675506592	350	2236.0280441637046	25.243236454534813	2291.0418639555573	2171.563318324741	700000	4.694911840223483	0.5
232.0493094921112	400	2151.712338945144	68.39067355698866	2261.438180302852	1651.919959777384	800000	4.69612267145681	0.5
260.3869535923004	450	1866.2209909585663	861.2746549687115	2467.615757866297	-681.9905895311385	900000	4.697316876105876	0.5
289.59709072113037	500	1145.9572137018617	926.7261362124447	2023.5710016526282	-14.14375274188933	1000000	4.696991953493721	0.5
297.0691180229187	501	1134.577242060959	881.2779973054761	1912.1677714511752	-18.223700972259394	1002000	4.697146672553556	0.5
