Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.018507480621338	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
35.68776774406433	50	24.350731903908706	7.124806987894723	36.29736936292488	12.249999890067556	100000	0.9803921568627451	0.7154173901801465
65.28228759765625	100	28.6723779227683	5.068971377847946	36.02003772590149	19.73541285097599	200000	0.9900990099009901	0.7154173901801465
95.88185524940491	150	29.395865863515663	3.3748159348062527	35.86131383110933	24.462425399862695	300000	0.9933774834437086	0.7480676937347109
125.74295806884766	200	29.844709061716884	2.2769004331526346	33.89562103088247	25.574318832717836	400000	0.9950248756218906	0.7480676937347109
154.5127091407776	250	42.3646581759615	7.744974517683901	63.46472304992312	31.61396313354635	500000	0.9960159362549801	0.8313389235496507
181.23377442359924	300	91.89982225999164	3.73839378663592	99.57827191508841	81.23091211447172	600000	0.9966777408637874	0.8313389235496507
207.32063364982605	350	152.52960892629855	10.672869822100166	173.20161759351322	134.2489174157381	700000	0.9971509971509972	0.8313389235496507
233.2420310974121	400	252.55366364058918	2.154049513847387	257.50228559003153	248.26530708617065	800000	0.9975062344139651	0.8313389235496507
258.7059347629547	450	280.54362943470267	2.974333659003949	290.10455997256213	273.5337055272421	900000	0.9977827050997783	0.8313389235496507
285.0927255153656	500	303.26994050790364	2.8991370552700957	309.8808871828951	297.3761032793118	1000000	0.998003992015968	0.8313389235496507
288.4205439090729	501	306.2027764187611	3.5879859918189996	313.4167308419128	299.39131433703005	1002000	0.99800796812749	0.8313389235496507
