Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.17796778678894	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
85.42732310295105	10	133.36094167630824	5.041406169452088	143.14952007788816	120.21623217404704	1000000	0.9090909090909091	0.6300856502306599
151.22252655029297	20	237.8675368191632	3.4812785174610945	245.8159454432316	229.10511755087646	2000000	0.9523809523809523	0.6300856502306599
218.56673860549927	30	295.4400518951376	3.5684269812323914	303.33733569631295	287.63944953665487	3000000	0.967741935483871	0.7176636599262911
286.53234934806824	40	326.4990223235483	2.4598332457468466	332.00267466827427	321.3631586480187	4000000	0.975609756097561	0.7176636599262911
351.7517020702362	50	340.2550177221991	2.32021389059619	346.01146469826926	333.8593136863783	5000000	0.9803921568627451	0.7176636599262911
413.204398393631	60	343.26695662606966	2.495405527585509	349.1128332624212	334.8758252987318	6000000	0.9836065573770492	0.7176636599262911
479.47556948661804	70	347.85713985561074	2.453356365347126	352.9052627988858	342.7806664314703	7000000	0.9859154929577465	0.7176636599262911
545.5394084453583	80	350.00769604688173	2.347076131637719	354.4970182836114	344.74206516868435	8000000	0.9876543209876543	0.7510557775315536
613.3338205814362	90	351.7868739987108	2.300360566323569	355.7566296356963	343.91400727664586	9000000	0.989010989010989	0.7510557775315536
679.8433239459991	100	352.3696988194084	1.743906088627426	356.18744249641895	347.5050752585885	10000000	0.9900990099009901	0.7510557775315536
