Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.354387998580933	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
73.54759168624878	10	33.477778899701754	8.022354941502524	47.20312854787335	16.82977717812173	1000000	0.9090909090909091	0.6771441541940593
134.88001585006714	20	36.98206699771738	5.446675989258102	47.01816049730405	24.262759034187184	2000000	0.9523809523809523	0.6825680022946569
195.07203078269958	30	39.94444254870015	3.8780919787182935	46.08200157992542	31.72232574201189	3000000	0.967741935483871	0.6825680022946569
253.71372199058533	40	40.455436309773546	3.737381612374539	47.59030367387459	31.44962142710574	4000000	0.975609756097561	0.6825680022946569
311.91267561912537	50	54.06318337866862	10.049108313441005	74.50716887286399	29.59750741533935	5000000	0.9803921568627451	0.6825680022946569
369.13320755958557	60	56.55492113788316	14.782045562614188	81.84310028361506	33.39379787644884	6000000	0.9836065573770492	0.6825680022946569
425.24573969841003	70	68.19379592946109	13.004750400462928	90.64468680764548	33.46633190658031	7000000	0.9859154929577465	0.6825680022946569
481.99523091316223	80	71.88254370805646	14.7872042410144	94.23004573135404	48.11703546883291	8000000	0.9876543209876543	0.7004492145251046
535.6377475261688	90	62.878645185879705	22.851545988159245	95.08249467279529	32.12138085864353	9000000	0.989010989010989	0.7004492145251046
590.7880973815918	100	64.84563660499246	27.0792047671291	105.61980117787607	31.732960847504728	10000000	0.9900990099009901	0.7004492145251046
