Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
19.02950668334961	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
49.25808310508728	50	181.41297701515023	4.750399946186021	195.98662470683666	158.5922215388855	100000	7.835201017186473	6.051690688497223
77.48114919662476	100	321.1582506154451	2.867695678019281	326.9057635155041	310.75100166804623	200000	7.829581580172183	6.595539547152909
105.4331784248352	150	348.56073015107313	1.8694744287445169	353.06241691939067	343.7732164058034	300000	8.028121073164728	7.768367627135068
133.64065146446228	200	348.08525996277274	3.1505714865215557	354.25355917261913	338.1881369277835	400000	7.976096973231652	7.768367627135068
161.88926887512207	250	350.63700258746206	1.7762428768842458	354.27256999937526	343.5138950238179	500000	7.951998589445975	7.768367627135068
190.55702376365662	300	347.49260720330244	6.527539432082244	352.6494730541017	310.6723184141738	600000	7.983674733801796	7.768367627135068
219.75604128837585	350	342.72769752702953	26.842659000646684	349.8811402107531	84.07685348967789	700000	7.978058148178507	7.768367627135068
248.48304557800293	400	352.6302591696955	2.6376704944307185	356.51633855805267	342.32448610151187	800000	7.948499571930375	7.768367627135068
276.5096094608307	450	349.08603575974723	2.162491799270415	354.63362265218166	339.9766917369561	900000	7.937383750596726	7.768367627135068
307.7562851905823	500	353.53634607399755	2.9616287952021128	357.29752688242297	340.53546194506634	1000000	7.897944917091889	7.768367627135068
310.8792636394501	501	354.79888668626586	3.1024794293058204	359.5706054037437	341.9346437113709	1002000	7.896380491492584	7.768367627135068
