Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
10.554796695709229	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
39.11437797546387	50	523.2610309968356	131.8151202931564	570.6805716140661	-0.568801883641413	100000	19.701657556597414	7.244088726287992
67.45670890808105	100	1194.0816615399544	93.4264914423112	1337.1918542456988	950.8876072349667	200000	19.87884253101578	7.244088726287992
93.4528295993805	150	850.2265286506195	403.6583222578706	1213.4909177272348	-760.9097145982087	300000	19.954895762383956	8.260889465720847
120.77997064590454	200	2152.434141498745	96.8614164524737	2333.456314029405	1797.1608555428684	400000	20.015627620743704	8.260889465720847
147.93279147148132	250	690.9125682106678	706.1812031659754	1544.9615736426786	-707.4810195306782	500000	20.01492705222536	8.260889465720847
175.51435828208923	300	1253.441819535058	757.786848388363	1723.8194202726008	-539.679950973019	600000	20.014072233156234	8.260889465720847
206.81001567840576	350	1042.730864927016	982.5257055513742	2096.6107481196523	-497.649976067245	700000	20.05019069044214	8.260889465720847
234.7907874584198	400	1554.650811508746	642.4906500813806	1906.7118147611618	-464.13915457576513	800000	20.05557736633416	9.20903683874918
260.98224401474	450	1925.0636362302089	246.57670636067908	2038.1319100661203	-109.20608900487423	900000	20.06910195635873	9.20903683874918
288.13763093948364	500	1751.2217817988712	337.91262363190265	1932.7923525664955	92.30766384792514	1000000	20.070257860686592	9.20903683874918
291.7700443267822	501	1671.0765728330966	510.4033764981049	1962.008412240073	-413.2616813853383	1002000	20.06856445146601	9.20903683874918
