Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.022992849349976	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
35.69427275657654	50	49.67302556606971	16.992424148996875	101.29681249900023	-12.28615211660508	100000	8.136891099643073	6.88414960492412
62.37334895133972	100	320.5786643227508	3.515021217826243	327.2736840440193	310.43808687268756	200000	8.016408221695082	7.156567048617384
90.00136470794678	150	349.2529254938816	1.5159757139228076	352.5603518760763	345.6613101546973	300000	7.9470488165577535	7.156567048617384
116.60362434387207	200	336.6903758483547	5.407405725726314	347.25477343215607	294.438986940484	400000	8.027269242576464	7.156567048617384
143.79879188537598	250	323.3666894337421	6.41964345056325	332.58369772322476	289.49969654361485	500000	8.039354559592173	7.156567048617384
170.5040307044983	300	348.68678638504684	3.782910323351238	353.9648613879108	340.60356823704205	600000	8.009141322508443	7.156567048617384
197.32768440246582	350	347.6959909634346	1.6319345519410953	351.1895698211156	343.1733527954202	700000	7.970251946737752	7.156567048617384
224.47948288917542	400	358.17810146193625	1.9778597662720592	361.0092428205535	351.88215016768663	800000	7.9792926626237906	7.156567048617384
250.91688108444214	450	355.2663298493411	1.8545688402104998	359.10232091508806	349.7860419808603	900000	7.997499275858568	7.156567048617384
277.49635004997253	500	354.4302528150544	1.6925393486577909	358.09890225110576	349.6485473374778	1000000	7.983113504433291	7.176210975120038
280.95206332206726	501	356.2085893333287	1.6943232648198339	361.3161663268693	350.11034234263934	1002000	7.985504192200526	7.176210975120038
