Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.41240668296814	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
87.9779782295227	10	189.13144371921086	3.800193023770237	197.12663658568636	181.741732552764	1000000	1.1130700780557992	0.5
157.12525987625122	20	294.69576906224495	2.7816047875919403	300.49109830360976	287.6869561537169	2000000	1.1953433433146017	0.5
225.49266815185547	30	337.70312552248424	2.878198050005557	343.8266354353691	331.5723582613591	3000000	1.2637168544769828	0.5
295.5880708694458	40	347.9796561008921	2.4428800241365067	352.1979716963833	341.28979267840623	4000000	1.2265434571889335	0.5
362.95121932029724	50	350.26257233591116	2.4712525810562216	357.02690642746165	344.8322964896797	5000000	1.1733257712090182	0.5
430.6224434375763	60	353.6158148608275	2.431093810619032	358.5104738448281	346.96476214332506	6000000	1.1178745580219294	0.5
498.544447183609	70	352.78207775016404	1.8824827757874216	357.44616985542234	348.4826237085508	7000000	1.0883570261494426	0.5
566.5104172229767	80	355.4669974210776	2.0049691549425455	359.3292547923629	349.90421250116196	8000000	1.0569038142444276	0.5
634.7216374874115	90	354.75618417637924	1.9576546883593846	359.44855572027154	351.39089069515467	9000000	1.0288829672854996	0.5
703.6027631759644	100	354.53694759266523	2.016029023292713	359.1322480252129	349.27996579534374	10000000	0.9993667672653228	0.5
