Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
12.733670949935913	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
42.75656771659851	50	145.08144408350248	3.86392982048939	154.72802859847434	138.77148324988957	100000	8.136891099643073	6.88414960492412
71.25757765769958	100	314.7489723412425	2.2058315071271237	319.65140546689145	306.3486150711542	200000	8.016408221695082	7.156567048617384
99.70428252220154	150	348.58293965958825	2.2397697239973664	352.2594524027081	337.0386991283158	300000	7.9470488165577535	7.156567048617384
128.21745014190674	200	349.2381458244454	2.167811934331937	354.8334231715562	344.54725132972817	400000	8.027269242576464	7.156567048617384
156.69661378860474	250	354.5651830018313	2.132955642984663	357.7901716772467	344.8494961017859	500000	8.039354559592175	7.156567048617384
184.9986445903778	300	350.61157650089643	1.8702609043229461	353.57017104141414	343.47375209178426	600000	8.009141322508443	7.156567048617384
213.38331508636475	350	350.2473254552875	1.3955939983888075	353.1703321917703	347.05237140133977	700000	7.970251946737752	7.156567048617384
241.55158519744873	400	353.506748680371	3.6251156798676267	356.9059645514935	337.7337451018393	800000	7.9792926626237906	7.156567048617384
270.22998094558716	450	356.7193086491572	1.0247013613029679	358.72741535509704	354.2605856861337	900000	7.997499275858568	7.156567048617384
298.4028482437134	500	356.396175749494	1.1943667865987837	358.83352763100993	353.77749964781106	1000000	7.983113504433291	7.176210975120038
301.6081340312958	501	353.3066670085193	1.220574248175932	355.66634362982586	350.19828599051107	1002000	7.985504192200526	7.176210975120038
