Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
10.542272806167603	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
44.13253927230835	50	28.3092647060548	3.2856062286620635	34.00490393038797	21.390212412865367	100000	0.9803921568627451	0.25
77.26878643035889	100	51.93249510057105	5.667479189637218	62.73349739573314	39.19061702254112	200000	0.9900990099009901	0.25
106.78952622413635	150	113.9254170957149	7.406443540254807	125.81880489144532	96.97692159365397	300000	0.9933774834437086	0.25
135.60689496994019	200	125.13454434416066	11.923385869329765	148.50032873358577	101.14960376918316	400000	0.9950248756218906	0.25
165.8116569519043	250	197.8558415678569	4.757898088932835	206.5768507711473	185.52418701373972	500000	0.9960159362549801	0.25
194.21489477157593	300	214.54157379281654	3.782981206791361	222.7663449438778	206.5785797490389	600000	0.9966777408637874	0.25
223.78499007225037	350	237.86664372486382	4.200440466171795	246.6486998582841	225.66274540976156	700000	0.9971509971509972	0.25
254.33752298355103	400	290.91958212985924	4.011391666136554	301.39864353311714	284.0348586176988	800000	0.9975062344139651	0.25
282.56860995292664	450	303.1402510457257	2.1134304591517163	309.52218252245325	298.78197198873386	900000	0.9977827050997783	0.25
310.56957626342773	500	323.2439423429209	3.02927601509125	328.49199487162696	316.98091316362843	1000000	0.998003992015968	0.25
315.62660932540894	501	317.9247759632706	1.9542205199392406	324.1635857945439	313.68452019046526	1002000	0.99800796812749	0.25
