Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.565762519836426	0	-0.30404523389316856	0.7831634747396644	2.251814016645012	-1.870696566842263	0	0.0	0
36.36208891868591	50	2.178933477953954	2.001573106154215	5.98689733598394	-1.552529247220022	100000	4.601464632134131	0.5
67.11135768890381	100	6.628322616792709	4.671206683501913	15.514957087501898	-0.7993017296457765	200000	4.646345710132935	0.5
95.64460492134094	150	894.3995512078083	16.715495134164087	911.0253103785217	798.656574403296	300000	4.667544207091623	0.5
123.43842506408691	200	747.4308885833254	7.028791621839421	762.7392978966236	720.6535683581606	400000	4.67830083346032	0.5
150.96965169906616	250	938.5321601527708	8.808361215513504	961.493801439181	917.8685613265261	500000	4.683113861235732	0.5
178.94964170455933	300	1196.3951443044568	16.029451780155608	1225.4002781328745	1153.6072887075134	600000	4.684742291695828	0.5
207.73421120643616	350	1536.2115444623796	12.895347412679621	1559.8785181958228	1495.0136419981718	700000	4.686085195024968	0.5
236.11822390556335	400	1716.3192995013853	15.71840776755796	1736.7013053894043	1653.900485399703	800000	4.689393900542693	0.5
263.7403326034546	450	1996.2084978439539	28.263691462402587	2034.3524959450588	1909.0843716412783	900000	4.6919209604959535	0.5
290.5626287460327	500	2062.989870260965	20.993422165966997	2100.0044649913907	1991.0296921646222	1000000	4.692440002618602	0.5
293.7959394454956	501	2102.228623384527	28.276620830072325	2151.074228583835	1976.09648240963	1002000	4.692488396238485	0.5
