Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.007404804229736	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
80.86544680595398	10	308.23283677597516	2.1494806777036937	312.79770802427083	303.7580587483244	1000000	3.133233926258394	2.824421406694417
147.10863137245178	20	345.9049166601757	1.64915806658526	350.2461404437199	341.95107546960935	2000000	3.089707550365002	2.824421406694417
213.71299290657043	30	354.36366714635915	2.2617105211285264	357.93893571652006	347.32041417917935	3000000	2.905800579261311	2.824421406694417
280.30617809295654	40	354.31481940225575	1.6423188852455302	359.79238493042067	350.58885357355757	4000000	2.7479435815080464	2.824421406694417
347.57436442375183	50	353.60613175402017	2.001966361316097	358.7266827725689	347.9596334290691	5000000	2.667472841052476	2.824421406694417
413.40560603141785	60	355.89259703060236	1.9571165413925449	359.64512412052136	350.0155896889919	6000000	2.6214654038030645	2.824421406694417
480.6955819129944	70	355.8891909169535	1.7380038224820311	359.71368833649467	351.7742704465054	7000000	2.5528439819010265	2.824421406694417
547.8258023262024	80	355.5599873088373	1.724908094462537	359.9493707938236	351.8262521697907	8000000	2.5199967862740613	2.824421406694417
614.6504576206207	90	354.9946316991225	1.935780045693839	361.2483718546573	351.24230530066416	9000000	2.4799453545056314	2.824421406694417
681.3861949443817	100	357.3763928980494	2.2067927221967887	361.4331849269802	351.8680452358676	10000000	2.433780076345962	2.824421406694417
