Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
7.598754644393921	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
35.995689868927	50	29.175318874908662	3.8145794622795224	36.03667629316317	17.927752477116883	100000	0.9803921568627451	0.7208555729067712
63.72265362739563	100	101.25594041016079	9.62527203941909	114.21169241453754	58.698950395861175	200000	0.9900990099009901	0.7208555729067712
89.77803659439087	150	219.4832603756436	2.4477215504915897	224.8010190014029	213.14867664972553	300000	0.9933774834437086	0.7208555729067712
115.71624803543091	200	261.0022460480404	2.5792748499526024	267.2830021355767	255.8924757540226	400000	0.9950248756218906	0.7381868324700196
143.50948071479797	250	305.24581801644894	2.4872469339775773	309.523526809091	300.0455696298741	500000	0.9960159362549801	0.7381868324700196
169.09956192970276	300	329.3926581751409	2.7071749799088525	333.9221164478804	323.25748324803135	600000	0.9966777408637874	0.7381868324700196
196.22401881217957	350	341.94174231843385	2.2949547446889285	346.2873664959334	335.08484607120045	700000	0.9971509971509972	0.7406704270115955
223.47064113616943	400	349.2588552349503	2.3521853891168374	353.55478405649774	342.70199765166035	800000	0.9975062344139651	0.7406704270115955
249.60270929336548	450	350.86345824831494	1.8203929806031647	354.4985099287005	346.78131518757436	900000	0.9977827050997783	0.7406704270115955
275.16322445869446	500	351.914367039438	1.495972484848709	354.65066161028517	348.3262407507282	1000000	0.998003992015968	0.7406704270115955
278.91193103790283	501	349.54243003361876	1.3161849216663986	352.1436632204568	346.0398917356506	1002000	0.99800796812749	0.7406704270115955
