Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.145443677902222	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
35.22934865951538	50	242.91351638714244	3.787002700754819	249.69177910767212	234.7578285218915	100000	7.7952078595571646	7.244088726287992
61.69798445701599	100	337.82668189066425	2.6657639698857274	343.02607510308735	331.7454459005967	200000	7.806290361284666	7.244088726287992
87.85864663124084	150	339.67223203853194	1.7126315886135952	342.6244304869033	335.54784958064556	300000	7.87325252798376	8.260889465720847
114.3527421951294	200	347.67443854670813	2.0102277223673943	351.90772627852857	343.75241413875483	400000	7.922712870164038	8.260889465720847
140.3062539100647	250	337.9846423705359	7.988867265646299	348.8762668315612	308.6660419246182	500000	7.917004198106848	8.260889465720847
166.76352167129517	300	343.39236122901406	5.487015755706917	353.4167641310196	325.3324993250426	600000	7.976883862298002	8.260889465720847
193.0419545173645	350	336.2359149735377	4.1969754737717455	344.5590013664332	326.94809935950616	700000	8.014823322224014	8.260889465720847
219.31876754760742	400	346.0595603706672	3.2240503047760285	351.6524700880982	339.35052791796625	800000	8.002709765920699	8.260889465720847
245.89018273353577	450	346.51773926599594	2.8640042121981106	350.9388907891698	340.8590204448701	900000	8.005599677931956	8.260889465720847
272.35367369651794	500	352.8263970774191	4.241214433056209	359.8574822912924	339.40832817030605	1000000	7.990724194292266	8.260889465720847
275.4503254890442	501	352.3729008994688	4.1768316066908175	358.3343934668519	340.5719274528965	1002000	7.987060766950517	8.260889465720847
