Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.048589944839478	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
39.16723012924194	50	27.804288417038816	4.793150873641857	37.58940807942008	18.190822739852592	100000	1.8287196216634354	0.5
69.50038933753967	100	28.706338806657786	2.691572609493308	34.700793720625484	22.592211346840486	200000	1.8559943367649339	0.5
103.44847297668457	150	31.194693711562795	2.61432723691675	36.72026383539196	25.27744549768977	300000	1.862781364413194	0.5
134.13575768470764	200	33.847569588012924	2.6970016118889006	40.36193224624731	28.775567677104846	400000	1.867454476295365	0.5
165.02101826667786	250	36.277630607350766	3.3162307700580254	43.96958422078751	28.519148495513946	500000	1.8725317301787296	0.5
196.4097547531128	300	43.57215356793604	3.545095404576287	51.60114348819479	36.340623354539275	600000	1.8695275068587118	0.5
225.85929608345032	350	122.1253960718137	11.942545535282157	136.11099777487107	104.20175156983896	700000	1.8680911725551956	0.5
255.44492268562317	400	171.83220024926496	4.424978579792074	181.91861802375206	160.27785237075295	800000	1.8682045054007987	0.5
284.07474064826965	450	269.96246104643546	3.612873207761781	278.1800810744171	260.9148560138128	900000	1.8682299252293924	0.5
311.6159682273865	500	283.93077128926905	2.7270396198013427	289.4450518040103	277.04644125769846	1000000	1.8675519300746202	0.5
315.0559914112091	501	281.74467758078356	2.4057757557530266	287.1720641046122	276.6742828258866	1002000	1.8673619584885637	0.5
