Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.197592735290527	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
53.73851919174194	10	36.491387031028474	4.580304066113631	42.11435922514647	5.121566818667418	1000000	1.4020636843343706	1.306558269244457
96.1369354724884	20	253.91122760389678	3.1377596434050723	260.59960772446357	244.83599100698484	2000000	1.7907112453257539	1.485962320319854
138.6689817905426	30	334.22503987535174	2.352430166326089	339.1228518979624	328.87427828344516	3000000	1.9763730487781404	1.54645989255455
180.5836362838745	40	349.63773948244926	1.9215505797682373	353.6427857114468	345.22431455604965	4000000	1.896743538865658	1.54645989255455
222.0979654788971	50	351.96535577565476	2.397976723421012	356.61386584778666	347.5748551908837	5000000	1.7849127733169707	1.54645989255455
263.88829159736633	60	353.48598530883277	2.5764883921156128	358.2913680015481	347.1823340485571	6000000	1.6974877511342619	1.54645989255455
305.5693168640137	70	353.40951584770164	1.9058895206840756	357.1868843571283	348.9322635193821	7000000	1.6429365652381074	1.54645989255455
346.2874433994293	80	353.8805014286126	1.8870102572672298	357.4489964940585	349.5995009895414	8000000	1.593330396486931	1.54645989255455
388.83012557029724	90	353.29970559586343	1.5856790798330573	356.66736392324674	349.8464978832053	9000000	1.549771042749025	1.54645989255455
430.50582909584045	100	355.69383074747674	2.042317059113215	359.79417195683345	350.73738483712077	10000000	1.5267573571102626	1.54645989255455
