Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.20753002166748	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
82.8535373210907	10	234.49852115954135	4.684863859898114	245.23173676495207	224.30723450827645	1000000	2.0865917490520434	1.6461821608091116
151.3818724155426	20	327.70182469142014	1.4989306081740805	331.1038450706983	324.6555552762002	2000000	2.208248055542236	1.6461821608091116
218.3290832042694	30	347.2303980483846	1.348440091131061	350.96928352865507	344.1144257619162	3000000	2.049895214713596	1.6461821608091116
286.728684425354	40	349.88833582899065	1.7032947199302662	353.55016747545596	345.5302846072591	4000000	1.883741774003072	1.6461821608091116
353.9484758377075	50	351.9474733283976	2.0382167959416053	356.0177355382249	347.28587340330705	5000000	1.7549093841406844	1.6461821608091116
421.5419132709503	60	354.9049583718316	1.8144138074730292	358.64362816514404	350.5085380068922	6000000	1.684507913803873	1.6461821608091116
490.39047288894653	70	352.7758632303096	1.5651416029687213	356.4618267849437	348.5980937676504	7000000	1.6425930963266777	1.6461821608091116
557.4584286212921	80	353.76773806307983	1.57428878860922	357.8844373510219	350.6644284197828	8000000	1.595979577490024	1.6461821608091116
625.4874641895294	90	355.1340993136905	1.8527523717268186	359.2457669924479	350.5703802869248	9000000	1.5564354371875413	1.6461821608091116
693.1901121139526	100	353.18560559695425	1.5622119397354344	356.60899107076693	350.18718161046854	10000000	1.5234862423041915	1.6461821608091116
