Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.052964687347412	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
82.27685189247131	10	159.61905447562714	4.844005539222417	168.52489478305506	145.86280966328923	1000000	1.8323934080823334	1.31140950640227
147.48554039001465	20	272.7583321131825	4.121511986953139	281.3274410712984	263.4375678387005	2000000	2.1715513167202554	1.75640799071561
212.51959085464478	30	339.18978547263083	2.356675819739909	345.6537785596447	332.2204836400342	3000000	2.1809090512892357	1.7663174342696057
278.5347111225128	40	347.9494365356928	2.6178430058080244	354.71644016646314	340.26791816414334	4000000	2.0124787849104275	1.7663174342696057
344.02602553367615	50	350.49175135400225	2.078536014495785	356.73076458188007	345.59940550959436	5000000	1.915923384197601	1.7663174342696057
408.8432869911194	60	353.61553054963156	2.7473847765287163	358.72661226894706	345.74671776988544	6000000	1.8111439938586253	1.7663174342696057
474.55518531799316	70	351.5589656069326	1.8451337878665655	356.747448902388	347.41728523606434	7000000	1.7348119001780438	1.7663174342696057
540.5492124557495	80	352.92787915842143	1.880013058269359	357.6555417574418	349.2349850826431	8000000	1.6857858520196922	1.7663174342696057
605.2111446857452	90	354.6091742454901	2.4681333251970425	358.9287635420915	345.6129634339595	9000000	1.6412659824494746	1.7663174342696057
671.4301912784576	100	355.3000221355505	1.9190756819724557	358.6241569094127	350.2234863381891	10000000	1.6083749062948616	1.7663174342696057
