Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.893494844436646	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
87.20015335083008	10	103.31551827339327	7.43075798071517	123.16646795687848	84.4572203618809	1000000	0.9090909090909091	0.8154158978289189
154.566077709198	20	242.28783966610226	4.540911425078704	250.77218746843573	231.59452244045679	2000000	0.9523809523809523	0.8154158978289189
223.53333640098572	30	307.70087024487634	2.643923217541787	313.5800782191727	301.8251646752469	3000000	0.967741935483871	0.8154158978289189
292.27184295654297	40	334.56295875722344	2.7488191233532726	339.5415997649543	326.2147480644344	4000000	0.975609756097561	0.8154158978289189
360.8607006072998	50	346.7262829714019	2.923214375228128	352.74858883954585	340.145903557539	5000000	0.9803921568627451	0.8154158978289189
429.74422907829285	60	351.1299305289779	2.4581280579303275	356.2661264737544	343.3921114289551	6000000	0.9836065573770492	0.8154158978289189
498.1593019962311	70	352.65684186810364	2.59444999127605	357.3931087930396	346.4367493825266	7000000	0.9834435984453168	0.8154158978289189
567.2872281074524	80	352.1878775324309	1.9951615530247557	356.171873230589	348.185899308417	8000000	0.9819583074133882	0.8154158978289189
633.7659640312195	90	354.2090446919018	2.356591958619216	359.15653175121406	347.6885011862323	9000000	0.9839409109943346	0.8154158978289189
702.4016003608704	100	354.13792568376596	1.9983627256266165	358.9872655219806	350.20391200541053	10000000	0.983549479793493	0.8154158978289189
