Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.150504350662231	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
37.40400528907776	50	98.98106904868513	10.52514437961373	128.45793522446183	58.05346801993437	100000	1.8224481875398229	0.5
65.87189221382141	100	213.6119051370694	3.423425959580701	221.18383630322933	205.7947271243902	200000	1.8389749983382695	0.5
95.70872688293457	150	304.38781302407074	2.8443353121097137	309.54276190075325	298.13398028723896	300000	1.844722577800119	0.5
123.30569911003113	200	326.11985290572477	2.9303742392432905	331.75935131986625	319.81876164709684	400000	1.8487102274470184	0.5
151.96383237838745	250	333.44265182402074	2.7111038007495356	339.92652680858737	327.6573326677244	500000	1.848637209964592	0.5
180.59581661224365	300	340.02614452687345	2.542859155445637	344.5081295106211	334.3607573671907	600000	1.8532984181966645	0.5
213.4643692970276	350	343.5247260131618	3.509918857812313	349.4681225763543	333.2030584496679	700000	1.8553457227070942	0.5
243.44190979003906	400	347.0964264621085	2.910384702772747	353.73314713756554	339.55320113037305	800000	1.8572875590170088	0.5
274.13804817199707	450	348.17782925954486	2.625103552909706	354.2280248858733	341.50697600730564	900000	1.859951702749182	0.5
303.3275547027588	500	351.31173622743705	2.8055462919353187	356.82943341648206	343.0163272494683	1000000	1.8589356529636016	0.5
306.8422586917877	501	349.6948432542047	3.6609762473003307	356.9138545881724	340.77041981124785	1002000	1.859095876696717	0.5
