Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.497794389724731	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
51.88960409164429	10	35.98386901946665	3.3146850608551395	42.28859908692539	28.773405155166984	1000000	1.0234961889832397	0.8298901831644957
93.3372962474823	20	120.41578248759491	7.260486290247655	139.06734512280673	106.71031792811118	2000000	1.1082621202491352	1.3011164380599676
133.7468123435974	30	276.6606795000328	2.9745487613072266	283.77944426829345	268.1851371253724	3000000	1.3852304502398547	1.5809690588094736
173.3335576057434	40	337.159979023333	2.8401745720745355	343.6276084301062	329.565812388435	4000000	1.4824225408040839	1.5809690588094736
214.21422028541565	50	344.0421419960349	2.645925172423799	350.3610067709815	339.13771765341517	5000000	1.4126172282638094	1.5809690588094736
255.16361594200134	60	347.9758822528859	2.795854828023323	352.7879394621559	340.3314940482378	6000000	1.3232575940381623	1.5809690588094736
295.6613116264343	70	349.5699938643367	2.2521057558730626	355.9005623672274	344.26325417810585	7000000	1.2620726297705502	1.5809690588094736
336.3946342468262	80	351.98999508736046	2.3173088027178275	356.9876885759295	346.5794600447116	8000000	1.2181763789037898	1.5809690588094736
376.6795470714569	90	352.971169389661	2.059612092966047	357.30377970222617	347.5357388382545	9000000	1.1764700078064712	1.5809690588094736
416.39208459854126	100	352.11415452013375	1.9504864239495747	357.15707907025353	348.5165783489356	10000000	1.1506201568216947	1.5809690588094736
