Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.617365598678589	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
36.668909788131714	50	0.24420188955339428	81.15238688074439	133.1785697145533	-221.75901485723443	100000	19.701657556597414	7.244088726287992
64.05891442298889	100	645.5424780435119	378.367041634612	1025.8733253013343	-465.8929021945223	200000	19.87884253101578	7.244088726287992
91.59671449661255	150	380.24626862896577	308.0712052740769	834.8198398163076	-1638.1723033268936	300000	19.95489576238396	8.260889465720847
118.42125272750854	200	-337.6929203135203	510.355725935507	121.98599594086409	-2312.6615319028497	400000	20.015627620743704	8.260889465720847
146.38616633415222	250	-1605.6493936311372	587.1402437706096	-827.1318408043007	-4846.410932905972	500000	20.014927052225364	8.260889465720847
174.52223920822144	300	-1815.9908526434133	363.6449850255005	-1391.1234581377357	-3197.4757603462785	600000	20.014072233156234	8.260889465720847
203.10552263259888	350	-1607.0492263247534	439.87917577547876	-994.202650080435	-2620.169723074883	700000	20.05019069044214	8.260889465720847
231.9944932460785	400	-2456.996779577079	1057.875775703244	-1547.2463391013443	-7669.712975274771	800000	20.055577366334163	9.20903683874918
260.5400116443634	450	-2469.0712279102586	206.62607458492138	-2041.9415671573952	-2893.6116634979844	900000	20.069101956358733	9.20903683874918
288.94964575767517	500	-3195.390782366883	730.0529915349532	-1960.8615299761295	-5823.992147380486	1000000	20.070257860686596	9.20903683874918
293.9638705253601	501	-3075.4290588061435	800.2919974309328	-1907.5374057777226	-6405.149916425347	1002000	20.068564451466013	9.20903683874918
