Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.704105854034424	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
75.23221063613892	10	42.94201114038634	5.609759229037862	60.112917939637555	33.08445673476672	1000000	1.0702573714719725	0.911454557662519
130.80029296875	20	220.57395010871565	3.598673217538175	230.24062711425358	209.29013350815512	2000000	1.2389685411116371	0.9679888845120962
185.64326190948486	30	340.18542561879906	2.192239034081161	345.70853502544924	334.9850598308258	3000000	1.3142814287422913	1.0748467219510072
241.834730386734	40	352.5300883550657	2.053533216122011	357.9816712444881	348.0975158647634	4000000	1.2621120788850162	1.0748467219510072
296.6260359287262	50	355.01837105398073	2.3089082790270674	359.8840780928731	349.28157528932206	5000000	1.1954968971933733	1.0748467219510072
351.64840722084045	60	354.8319527634126	2.107619326624387	360.0988705018535	349.48641166090965	6000000	1.120287043750537	1.0748467219510072
406.9811165332794	70	355.8645369512295	2.532707615189247	361.02284878341015	349.2994360931334	7000000	1.1046235454947457	1.0748467219510072
462.6789336204529	80	355.4000747377654	2.6135543035713393	360.6699167464103	347.6904608462937	8000000	1.0557115581531946	1.0748467219510072
517.5457458496094	90	354.8939535726579	1.7823628426707765	359.63385930506047	350.52239220420597	9000000	1.0231211602137344	1.0748467219510072
573.8233866691589	100	356.2841769501496	2.8284144708477017	361.801229381701	348.89255858701654	10000000	1.0026673813417746	1.0748467219510072
