Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.28647494316101	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
85.06751418113708	10	227.6063238913949	3.0354827570729936	233.4323261185782	218.08753023974714	1000000	1.5327710234951253	0.5
153.7932994365692	20	307.3643819286972	2.479841460196501	312.43268482148414	301.1156425661902	2000000	1.6291639158899485	0.5
222.06427645683289	30	341.7337978281334	2.653524948497157	346.4696790454909	333.4434491498396	3000000	1.6202793424375466	0.5
291.2866475582123	40	345.667194244903	2.4180641768535156	350.8092942391522	339.16025695292046	4000000	1.5969756097057184	0.5
360.1034207344055	50	348.19382380377067	2.6984669931723024	354.74639364972245	341.6163205130724	5000000	1.5925170200320915	0.5
428.66463899612427	60	349.70739802586496	2.1466761588436323	355.52521439641714	343.9669430865324	6000000	1.5752165141972991	0.5
498.34458899497986	70	351.9839649736605	1.9619054909740121	356.32043301372323	346.46372312051244	7000000	1.5597617100400456	0.5
568.3515555858612	80	355.39861119698634	1.8910462662897196	358.53068909421563	347.0935105179087	8000000	1.5619917369866463	0.5
636.7924792766571	90	353.90163397105135	1.8008044814261561	357.97764478146564	349.8066842831904	9000000	1.554930854856349	0.5
704.6606290340424	100	352.9821138131887	1.9990607007359666	358.7626510229893	348.83010948472656	10000000	1.5490047178877029	0.5
