Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.573803663253784	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
46.64565348625183	10	34.09358290566857	2.2737185159517157	38.947554008685984	30.13350741042018	1000000	3.6363636363636362	1.0
84.0728268623352	20	42.418709062351994	2.1823881199532957	47.32339827902615	38.464316182304174	2000000	3.8095238095238093	1.0
121.25389552116394	30	45.63581398352559	1.643456145919399	48.742534012533724	42.23135608877055	3000000	3.870967741935484	1.0
158.5920536518097	40	45.49578325990849	1.204121914683075	47.63841657387093	42.869134744629264	4000000	3.902439024390244	1.0
195.10338044166565	50	52.789941831973834	5.03578197339113	71.36283391114557	41.52233969111694	5000000	3.9215686274509802	1.0
228.98871684074402	60	255.876834284955	3.3339875203124243	263.8196809164947	248.4969756952487	6000000	3.9344262295081966	1.0
262.3688750267029	70	284.4336422954002	11.288420747075115	295.4642277985695	234.72484333865577	7000000	3.943661971830986	1.0
296.6934678554535	80	272.5277570756905	28.799371099655797	297.9526021828642	148.55116825341247	8000000	3.950617283950617	1.0
328.1029040813446	90	280.7979748611185	5.210548435605699	293.37679962225957	274.53277419199003	9000000	3.956043956043956	1.0
361.13930201530457	100	280.93678683702956	1.7172855197248027	287.6951010803459	277.4205810592248	10000000	3.9603960396039604	1.0
