Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.057069301605225	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
45.6920702457428	10	29.122384230129953	4.37169620385933	37.97466420498256	21.234113110229373	1000000	0.9090909090909091	0.6740290676495668
82.52775025367737	20	39.21311018849155	4.0565052265498815	46.346540787722915	29.852611634647474	2000000	0.9301917564177425	0.6740290676495668
119.28742837905884	30	40.389587245125384	3.494678736257894	47.37824507988989	33.09383429796435	3000000	0.9499676085028462	0.6922775524445358
156.16315269470215	40	41.93394734316666	2.517594923690295	46.886312820483	36.59020932065323	4000000	0.9619263947149969	0.7691597192355137
193.6319613456726	50	41.437816027391385	2.6959998480655005	46.68050408177078	34.94520290987566	5000000	0.9691002921038168	0.7743315043425387
230.3445224761963	60	43.52575832091719	2.2593473862382423	47.36769150674809	38.054772863164544	6000000	0.974165817988437	0.7743315043425387
267.04505681991577	70	44.298672416290735	2.2347374493707584	47.93138338578865	38.688211457338184	7000000	0.9762199814088556	0.7743315043425387
303.65489387512207	80	44.853180522690465	1.9905532352993427	48.43864600267261	40.40776914684102	8000000	0.9791557861731943	0.7743315043425387
338.9975209236145	90	45.20382568612491	1.8279171115489132	48.75536440126598	41.61958939302713	9000000	0.9778123643790395	0.7743315043425387
375.99614334106445	100	45.68641391085039	1.645445111390755	48.86207160865888	42.00677943089977	10000000	0.9776433159360158	0.7743315043425387
