Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.062757968902588	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
73.89188480377197	10	168.5763553811791	5.770073167472766	180.5849361087894	155.4371618377627	1000000	2.656619530535302	2.145600806295144
132.9846007823944	20	351.6639930016847	2.2387531150401947	357.59650472167414	346.8816471901082	2000000	2.926106450606894	2.145600806295144
185.65360283851624	30	352.88679170676374	2.4806423659649157	358.39146558672655	345.00483219754824	3000000	2.761322409177142	2.145600806295144
242.55877161026	40	353.989890183884	2.4680679903215896	359.0212456268491	342.29857456864556	4000000	2.6372584777340107	2.145600806295144
299.4565088748932	50	355.9594121452093	2.800910771706525	361.46334447007393	348.5437894517672	5000000	2.5610861725937504	2.145600806295144
349.0971350669861	60	354.1246392955512	2.2580915313939154	359.8611892205954	348.4076060372172	6000000	2.498557137329339	2.145600806295144
408.0898230075836	70	355.590495325468	2.6589786019998884	360.7320085158717	345.9811175621144	7000000	2.4707425523119975	2.145600806295144
462.42704796791077	80	352.96471213809747	2.4051293787335424	357.40850773193233	346.55551364531857	8000000	2.4590576188724254	2.145600806295144
513.6996245384216	90	354.5983527497691	1.9131350083189322	359.00321116995474	349.240140527545	9000000	2.4366384981439944	2.145600806295144
571.3078336715698	100	357.2559583571749	2.6380926501939403	361.89600582409184	349.3103121306631	10000000	2.4167887486107884	2.145600806295144
