Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.571775913238525	0	-0.30404523389316856	0.7831634747396644	2.251814016645012	-1.870696566842263	0	0.0	0
36.485636949539185	50	-0.25422087415419214	0.7449188576355585	1.7552144639415594	-1.7699652162298563	100000	0.9803921568627451	0.4015660982424437
64.77429747581482	100	8.731984722677366	1.0482658071641202	11.833827816186385	6.621254053461598	200000	0.9900990099009901	0.4015660982424437
92.57658314704895	150	70.96164965146505	6.5673450727606175	86.44790270582598	62.459758492419496	300000	0.9933774834437086	0.4015660982424437
120.29855155944824	200	510.80347477841264	9.766538435991315	530.4359928143676	483.1010645004626	400000	0.9950248756218906	0.4015660982424437
153.14300298690796	250	421.6372421098048	7.720751844031618	438.6128910309635	396.9009381235119	500000	0.9960159362549801	0.4015660982424437
180.70000529289246	300	590.1364464989097	6.9827552409206515	603.0940189075191	564.8534987086896	600000	0.9966777408637874	0.4015660982424437
208.97335815429688	350	642.3259052937217	7.44252225184511	656.9652233244851	619.5805597805884	700000	0.9971509971509972	0.4015660982424437
236.7102756500244	400	672.6938369338291	8.438239852950918	686.5195941327838	638.6881569993202	800000	0.9975062344139651	0.4015660982424437
265.301162481308	450	746.30358897035	9.602522460200435	771.8257175995095	722.4517659092671	900000	0.9977827050997783	0.4015660982424437
292.89248037338257	500	691.005101601872	6.943959074712037	704.5454470387049	669.4653843249544	1000000	0.998003992015968	0.4015660982424437
296.72688913345337	501	663.8633635841422	7.3330518688433335	681.0512231979956	637.0002753386943	1002000	0.99800796812749	0.4015660982424437
