Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.84915566444397	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
85.59572291374207	10	162.0458404806292	4.10144181029601	170.86156568367733	152.53597550996346	1000000	0.9082421222968633	0.6325167870538918
154.50004506111145	20	255.68803380900223	3.3397348156350377	262.26482202112675	247.37336743774358	2000000	0.9493436699106113	0.6325167870538918
223.97358393669128	30	315.24961316335845	2.7991594610999506	321.0046568669495	308.34795113583095	3000000	0.9656844215523496	0.6325167870538918
292.31162214279175	40	338.77267072110254	2.585894752884331	343.45904006587807	331.27839743276127	4000000	0.9740540748322642	0.6496015257432787
359.1624846458435	50	347.29206623256715	2.712485185474549	353.4292903551832	340.97331407963065	5000000	0.9780067005614496	0.6496015257432787
427.9695928096771	60	350.74698531961104	2.2835773130561257	356.56525035892264	344.90855199989164	6000000	0.9604502223116194	0.6496015257432787
496.19158840179443	70	353.9236146861097	2.305501709678522	358.3481490663253	348.5205099939776	7000000	0.9443124004802088	0.6496015257432787
563.7371034622192	80	353.7308305146913	2.346830402928115	359.0490513595869	348.86536622123094	8000000	0.9321270916146139	0.6496015257432787
633.360104560852	90	355.69928773365274	2.0535449665284617	359.7743691718206	349.94399984163465	9000000	0.9226213719256712	0.6496015257432787
702.7859170436859	100	353.74902767964335	2.316048535903597	359.6894643845444	346.0636642567697	10000000	0.9098477090745402	0.6496015257432787
