Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.41389274597168	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
85.18414759635925	10	147.85456364911045	4.462063429447552	156.94341370707843	131.67547401519187	1000000	0.9090909090909091	0.6166531079731842
153.67108607292175	20	241.84481857532774	3.1103183183786154	250.11673222857644	235.34887301712297	2000000	0.9523809523809523	0.6968690831645171
221.31350445747375	30	306.41451985230185	3.237595292466845	313.106348673944	296.62250244343886	3000000	0.967741935483871	0.6968690831645171
289.43796944618225	40	335.4718676133882	2.715521955913681	340.84488095040433	327.4568620416976	4000000	0.975609756097561	0.6968690831645171
357.35838556289673	50	345.0245055197502	2.1592876321568006	350.64587081060745	340.4795466774376	5000000	0.9803921568627451	0.6968690831645171
425.02664017677307	60	350.99042744140667	1.9411250619869365	355.1479778534267	346.86644867810537	6000000	0.9836065573770492	0.6968690831645171
493.19236183166504	70	353.6704418860788	2.360219186762868	357.7116533447406	345.9530558295228	7000000	0.9859154929577465	0.6968690831645171
560.0656049251556	80	353.8855657855419	1.9776898725420802	358.2441322132945	350.28152172395494	8000000	0.9858106520882715	0.6968690831645171
627.0737662315369	90	355.2138483292341	2.485158494536972	359.7357340976305	347.8790536944289	9000000	0.9867915225689315	0.6968690831645171
693.6408014297485	100	353.63009606562116	1.8170134519020522	358.46874116017716	349.70019907678943	10000000	0.9874151351547775	0.6968690831645171
