Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.290048122406006	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
71.3871123790741	10	25.038763764815517	9.519378607791605	44.452426781877875	3.345898037761799	1000000	2.4647876334528953	2.121939768320991
130.48139452934265	20	30.057618632906287	6.912930966514313	45.89060059003532	15.552427439717576	2000000	2.5209111603910164	2.121939768320991
189.415668964386	30	37.18710259858636	4.882759527995867	48.03975125402212	26.68674996489426	3000000	2.50505078117197	2.121939768320991
246.67723774909973	40	40.630893247026826	5.867154674419371	51.050903687253594	26.601077194849495	4000000	2.504886166878556	2.121939768320991
304.70102763175964	50	40.320523819221904	6.344218102569103	49.95468472968787	24.890581012296025	5000000	2.4939651870247177	2.121939768320991
362.1544494628906	60	40.09985470353975	7.206893271986828	53.07193208485842	26.446728021866875	6000000	2.4436189525405094	2.121939768320991
419.75220346450806	70	40.06454748170848	7.008335031484709	51.53953626938164	26.348410534788854	7000000	2.422356452972317	2.121939768320991
478.2599034309387	80	36.04166146808465	8.985533636954909	51.70337371015921	15.637954034187715	8000000	2.4048890635466558	2.121939768320991
538.2418601512909	90	38.086102446136685	7.5656969650981925	50.42023730836809	20.70837817050051	9000000	2.3777645665347205	2.121939768320991
597.5410137176514	100	41.45314281670391	6.053412117955462	51.67161642876454	21.144372395647224	10000000	2.3608035828968426	2.121939768320991
