Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.875066995620728	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
82.48912119865417	10	156.66432117525702	3.67074970470412	165.5530721474206	148.08677910684492	1000000	0.9090909090909091	0.6205876957535306
148.0685851573944	20	237.78951012887038	3.0694401096387662	244.66396643826738	228.06109435328108	2000000	0.9523809523809523	0.6350733458107091
212.33551621437073	30	299.8562177070517	2.5177318916466587	305.36312829732196	293.5546319084242	3000000	0.967741935483871	0.6350733458107091
279.31963992118835	40	329.6880618009963	2.614514738994988	335.5016504380619	323.8145523237763	4000000	0.975609756097561	0.6350733458107091
344.0127465724945	50	340.39362382521426	1.884253843285509	345.33948412479367	336.75440895045176	5000000	0.9803921568627451	0.6350733458107091
410.20444917678833	60	348.0815603727386	2.304598975265583	352.49122743844055	341.50902986736037	6000000	0.9836065573770492	0.6798844106402313
475.77097272872925	70	348.74411603707864	1.6470694778109527	353.1081957423012	344.31584783957805	7000000	0.9859154929577465	0.6934550615137148
542.4846196174622	80	351.66466314038587	2.1865429572420814	356.0595912882127	346.7855905821343	8000000	0.9876543209876543	0.7965651400183352
611.2010056972504	90	352.2750698130226	2.527954783406921	358.26927888431237	346.44636850911775	9000000	0.989010989010989	0.7965651400183352
681.2045769691467	100	350.91046498070887	1.9662013738273647	356.18127851118334	346.46093621401815	10000000	0.9900990099009901	0.7965651400183352
