Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.650159358978271	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
36.432512044906616	50	0.004610667130944326	0.6410608711074369	1.77691992820656	-1.4201970671279085	100000	0.980392156862745	0.09901475429766744
65.53800010681152	100	0.16169255523986653	0.7460229927447205	2.3991094862485483	-1.9526693716931156	200000	0.99009900990099	0.09901475429766744
93.98169326782227	150	0.8100443591570542	1.0327354759254077	3.2194999587609914	-1.2890147530489884	300000	0.9933774834437085	0.09901475429766744
122.55065655708313	200	1.205290699689686	1.2371558702829333	4.034147810269346	-1.345430191139279	400000	0.9950248756218905	0.09901475429766744
151.1578986644745	250	2.3131432776019114	1.7034919575955116	6.05548785941032	-1.5015943987474571	500000	0.99601593625498	0.09901475429766744
180.25738143920898	300	5.6500552193450435	3.9156201466156486	14.028206812434938	-0.8058115050940273	600000	0.9966777408637871	0.09901475429766744
209.86366176605225	350	6.437618733593389	3.2316428315219334	13.129453988425357	-1.0478562927887918	700000	0.997150997150997	0.09901475429766744
238.44297814369202	400	11.965980818497885	6.855648378795929	22.874357544154265	-0.3487951204099886	800000	0.9975062344139649	0.09901475429766744
266.85791778564453	450	538.865580043806	215.68352984556466	632.300649904646	0.8067099420167949	900000	0.9977827050997782	0.09901475429766744
295.25779247283936	500	632.8543240499722	128.83550869974493	666.0592093624873	1.02162019492755	1000000	0.9980039920159679	0.09901475429766744
298.43220233917236	501	576.5613751470114	221.38535934592616	670.6468974724412	0.667332328059274	1002000	0.9980079681274899	0.09901475429766744
