Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.87622356414795	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
36.54499101638794	50	0.15020866050446088	0.7743892228083811	2.162186711730058	-2.0627991842682434	100000	0.980392156862745	0.09901475429766744
66.08231830596924	100	1.4535253561521744	1.192600893763855	4.258241274643524	-1.111756998355176	200000	0.99009900990099	0.09901475429766744
93.91852569580078	150	10.097867928215766	6.628922779167421	22.913112707193463	-0.2929923021831371	300000	0.9933774834437085	0.09901475429766744
124.5514988899231	200	249.28207288441968	228.33698883989533	557.0839886181056	21.96741047227988	400000	0.9950248756218905	0.09901475429766744
152.83727598190308	250	803.0913960851285	11.460779271578076	818.1229874528944	764.0904315188527	500000	0.99601593625498	0.09901475429766744
180.78082132339478	300	821.1712460897476	425.00999696802273	1065.372726842761	37.927731028350536	600000	0.9966777408637871	0.09901475429766744
208.77553415298462	350	984.7725186191523	162.3725863730285	1077.8148854654282	446.2090925636585	700000	0.997150997150997	0.09901475429766744
236.2761697769165	400	1176.57037578827	12.024433236173069	1195.9603525698185	1114.6750680324621	800000	0.9975062344139649	0.09901475429766744
263.73497223854065	450	1275.3811108167693	6.837995308381159	1283.0542315393686	1228.6415440929122	900000	0.9977827050997782	0.09901475429766744
291.2071387767792	500	1344.563189264395	9.162796820542628	1355.542052924633	1272.3258445806568	1000000	0.9980039920159679	0.09901475429766744
295.8665943145752	501	1339.4244425141683	10.919970080089616	1354.4673252552748	1256.18116367943	1002000	0.9980079681274899	0.09901475429766744
