Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.240028619766235	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
35.44852161407471	50	58.58562176908045	8.217765090026143	75.09832089790143	42.04904926160816	100000	0.9803921568627451	0.25
62.64447784423828	100	107.91361059417854	4.855221881654685	122.73432374441472	99.6140584355744	200000	0.9900990099009901	0.25
91.00116229057312	150	197.05219453829065	4.257871460620647	205.60178059426835	185.68263010121882	300000	0.9933774834437086	0.25
118.36546158790588	200	244.85810799012805	4.122411774241204	251.2774599306722	236.53914626152255	400000	0.9950248756218906	0.25
144.34348678588867	250	259.8605057081743	3.0072054546382545	268.75213407189585	252.58855083514936	500000	0.9960159362549801	0.25
170.5353434085846	300	288.1548663777978	2.986500708871972	294.4445525580086	280.389695782098	600000	0.9966777408637874	0.25
196.52943634986877	350	296.4925379409488	2.84611746817631	302.1497815901821	288.13033737102523	700000	0.9971509971509972	0.25
223.92283511161804	400	321.1142714044463	2.416982486675535	325.95913045463385	314.53542408738576	800000	0.9975062344139651	0.25
250.89461278915405	450	333.63931193823623	2.9653364009805188	339.2367014687625	325.98533788044006	900000	0.9977827050997783	0.25
277.590913772583	500	342.36318550382117	3.135267958587002	347.99006812707376	333.92591589980293	1000000	0.998003992015968	0.25
281.047815322876	501	341.5408393240086	2.5227346800153563	346.39626669464633	333.64600491989404	1002000	0.99800796812749	0.25
