Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.9492506980896	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
53.50185585021973	10	11.012591193043411	11.361760274644995	58.36942602441559	0.8929418939806055	1000000	3.6363636363636362	1.0
96.04398012161255	20	238.74104272522106	3.987653181949791	254.42148653860204	233.2159177371068	2000000	3.8095238095238093	1.0
138.57415747642517	30	285.1644072391536	6.049510605449928	296.88211515890725	271.77710442524403	3000000	3.870967741935484	1.0
181.1982238292694	40	261.00072210939175	5.223289617264586	272.6785773691954	252.2177103550639	4000000	3.902439024390244	1.0
223.5889596939087	50	267.15754165777685	3.1409370235449736	280.15293008019216	259.236111230799	5000000	3.9215686274509802	1.0
265.8096749782562	60	245.20248767732954	1.698395846457933	250.15014161606086	241.1610465683043	6000000	3.9344262295081966	1.0
307.54617404937744	70	278.0360749942974	2.8470067132884065	284.89822006126633	271.9625448652805	7000000	3.943661971830986	1.0
348.7454242706299	80	268.757624050578	2.1666734550761033	274.2518014763482	263.24795409757644	8000000	3.950617283950617	1.0
389.89832735061646	90	274.4715527092735	2.127858017643112	279.7181173916906	269.6388367116451	9000000	3.956043956043956	1.0
430.9727716445923	100	283.6714371266054	3.136612758580082	289.9938547111233	271.3787280044053	10000000	3.9603960396039604	1.0
