Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.849859237670898	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
40.662919998168945	50	27.670398576227377	5.6551136319143085	37.49263920304392	14.617957235546783	100000	0.9803921568627451	0.25
70.63157510757446	100	27.186183433091756	3.3240754467058222	33.60097091729358	18.882022688689176	200000	0.9900990099009901	0.25
102.12834405899048	150	27.697278191174586	2.787338325573573	32.47637643561893	22.501613147447642	300000	0.9933774834437086	0.25
133.58010053634644	200	35.4308711409137	6.317074288871045	58.81410126997798	23.620449863749855	400000	0.9950248756218906	0.25
164.95579934120178	250	53.34682835333686	12.114938473653465	72.20772921090247	17.345698426361196	500000	0.9960159362549801	0.25
194.6252977848053	300	115.04239518781425	16.238745194946805	138.7209109197138	69.23639336499036	600000	0.9966777408637874	0.25
223.8102240562439	350	142.06620940767039	7.422307449092894	159.11634412557214	102.022390105878	700000	0.9971509971509972	0.25
252.50971722602844	400	157.55692945190498	9.412649221313817	177.16213573492132	122.9086279713083	800000	0.9975062344139651	0.25
280.96095180511475	450	183.97226444851378	4.746937595693239	193.68752578730346	171.67678822297603	900000	0.9977827050997783	0.25
309.07313561439514	500	205.98764954184014	4.065013464102137	214.64768989589356	194.85636554955272	1000000	0.998003992015968	0.25
314.2231729030609	501	206.7083195189732	4.439481112368089	213.99399424271542	193.95880601991666	1002000	0.99800796812749	0.25
