Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.240374088287354	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
84.9198637008667	10	287.74601657651607	2.608818390293374	292.84984328766586	279.86121468030615	1000000	2.9326452765292927	2.1187555740658124
150.26982021331787	20	345.9453095317782	2.432253806820137	351.5027164540952	340.3248704514699	2000000	3.074624513428072	2.5047504735633135
216.2421691417694	30	349.8958326878825	2.2880715700426633	353.8649780843407	344.55791641894393	3000000	2.9511614544524565	2.5047504735633135
285.13010931015015	40	354.5704221181867	2.2007924245860186	358.72598782915156	349.106541866553	4000000	2.8052476583960164	2.5047504735633135
354.10566449165344	50	351.94944805171747	1.9532677955442537	358.98087142023724	347.656654846156	5000000	2.693205819942585	2.5047504735633135
422.8321301937103	60	354.6600559442496	2.7669388827814565	360.12884723744355	348.78056457513594	6000000	2.6350573876851486	2.5047504735633135
488.4769401550293	70	353.9700363379361	2.068022285661376	359.24718715040945	348.743072679732	7000000	2.6195172337384407	2.5047504735633135
555.9351096153259	80	354.0686501374788	1.7332231467489152	358.80347812059335	350.70941913849674	8000000	2.5883013502113412	2.5047504735633135
625.5316934585571	90	354.13547930417207	1.8503796039549796	358.28063912154175	349.87543407981866	9000000	2.5540885073026742	2.5047504735633135
693.4551260471344	100	356.3118970642993	1.8948220973661654	360.57433836418204	349.95697310956893	10000000	2.5146322778606036	2.5047504735633135
