Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.16036033630371	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
71.20682334899902	10	125.1434555096598	5.357384343683334	136.15013607710716	110.4064402517979	1000000	0.9090909090909091	0.6478533053437041
127.77017855644226	20	277.3013919968369	3.0672494958345635	283.4403777177213	269.97106653422816	2000000	0.9523809523809523	0.6494894888670476
185.5780999660492	30	344.47960716903816	2.7090804468822465	350.3314776585321	337.51956416585017	3000000	0.967741935483871	0.6494894888670476
242.67853307724	40	353.88724599653585	2.2676471467325205	358.15779525926337	349.00132406072225	4000000	0.9723693714642282	0.6494894888670476
298.9635889530182	50	353.1636120465709	2.4842762704900103	359.0082039658446	342.1458197765751	5000000	0.9704974886866451	0.7127635851394188
355.338595867157	60	355.81426654740267	2.524502076119725	361.0435977523448	349.2210080914665	6000000	0.9700276825281218	0.7127635851394188
412.99049639701843	70	354.1542508602644	2.1245381402697725	359.16260119458457	346.722116578836	7000000	0.9711309430674238	0.7127635851394188
471.2315731048584	80	354.7726976818014	2.3322658799271827	359.52312123199226	346.7709364264738	8000000	0.9721102455855286	0.7127635851394188
527.0515947341919	90	356.64870491941093	2.5721987460105407	361.83960779914923	350.42487362375505	9000000	0.9736918678463296	0.7127635851394188
583.7925043106079	100	355.0583803662001	2.2625116629858586	360.49830910470337	346.689813887584	10000000	0.9738802913832348	0.7127635851394188
