Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.269560813903809	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
39.00712013244629	50	28.771498736472967	4.035692665395293	35.778076918957595	19.13664763001725	100000	0.9803921568627451	0.7208555729067712
70.43261504173279	100	27.703027806608006	3.2124908316058143	33.816862668531144	20.668141427566297	200000	0.9900990099009901	0.7208555729067712
103.25385355949402	150	35.26318511947224	16.91944687295826	62.20009528636001	3.2353473275688884	300000	0.9933774834437086	0.7208555729067712
132.9873833656311	200	70.39295061450034	9.229590348183727	81.1203260521288	40.84693399735261	400000	0.9950248756218906	0.7381868324700197
162.02149271965027	250	77.12386279111111	15.76161030990096	107.97799505054718	48.706269520684145	500000	0.9960159362549801	0.7381868324700197
190.53481769561768	300	147.95214663037993	5.87219233890301	159.52189984335564	130.00147342039418	600000	0.9966777408637874	0.7381868324700197
218.83959078788757	350	173.47412143382505	4.787146073060463	185.6552062241244	163.68351286552206	700000	0.9971509971509972	0.7406704270115955
247.63151955604553	400	203.21577245375673	4.33678504456234	212.49359703420487	193.99708793242462	800000	0.9975062344139651	0.7406704270115955
276.0190496444702	450	231.55674549726183	3.5547294776925185	239.80285152525175	224.59602174060774	900000	0.9977827050997783	0.7406704270115955
305.52693367004395	500	254.58209890581128	3.5836477069202353	262.42830384738045	247.32498168124948	1000000	0.998003992015968	0.7406704270115955
309.58104252815247	501	253.6073127879261	3.104422910897368	260.2532017084304	247.58146157255396	1002000	0.99800796812749	0.7406704270115955
