Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.161444187164307	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
88.139728307724	10	141.03590828697264	6.165337970762966	150.5281809681328	124.23980809461136	1000000	1.181702930825947	1.2724600174194522
157.2890441417694	20	279.9056609543417	3.694499205399185	287.83982560696313	271.7608416285657	2000000	1.2741641694431503	1.2724600174194522
226.49386763572693	30	335.12150456996443	2.9451941206334946	339.95610273629427	327.9046123305161	3000000	1.364492750873586	1.2724600174194522
295.1087028980255	40	346.6339650820462	2.5308134071830595	352.559980759921	338.8574273783015	4000000	1.3284772335907948	1.2724600174194522
365.127738237381	50	350.8699915276565	1.873271642865083	354.75274382397765	346.16684707283275	5000000	1.267604481637468	1.2724600174194522
433.7250678539276	60	352.9024911795603	2.7793436830669234	358.682446732535	347.1751348252874	6000000	1.1967321712853076	1.2724600174194522
506.54799151420593	70	353.1447908484747	2.1581882381250312	358.83018984866794	349.0453272446757	7000000	1.1454573875361311	1.2724600174194522
576.3982603549957	80	355.5115390914964	2.5781632005706436	359.5727800821187	345.31796074821614	8000000	1.0950781955882822	1.2724600174194522
645.839940071106	90	355.11821688151	2.0940582810816366	359.1818836358725	350.10784102546904	9000000	1.0660538644206363	1.2724600174194522
713.6109418869019	100	355.9942980225114	2.1615329041141766	360.1130153088452	347.65998097514967	10000000	1.0403327239436342	1.2724600174194522
