Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.685457468032837	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
73.2784276008606	10	259.9406404903246	3.1903637690611277	266.1132958839298	250.86502941104845	1000000	1.7865307660809897	1.2412357400144678
129.26564121246338	20	353.7040338406707	2.4846884879999895	359.40850639902055	348.52924763644114	2000000	1.9153246664502894	1.431080576887886
185.18301701545715	30	353.5917250191506	2.307567923381116	358.1724818855291	346.47619345600833	3000000	1.708500436353271	1.431080576887886
243.0220708847046	40	355.20117619237396	2.257511653308938	360.27100040065125	348.48616112695163	4000000	1.58886149110283	1.431080576887886
300.115207195282	50	356.0094311342834	3.1250565471556477	361.70655773661565	341.5920363262994	5000000	1.557496662613591	1.431080576887886
357.8528573513031	60	355.2080775855991	2.168726176346796	360.67504141980316	348.552794893767	6000000	1.5009690395962483	1.431080576887886
415.2593262195587	70	357.2101128676488	2.568782563507313	361.3332443960244	349.4290177975854	7000000	1.4645039392169241	1.431080576887886
468.83036398887634	80	354.6288957231588	2.0896621131688873	359.37449246353935	349.70178569923155	8000000	1.435445420378476	1.431080576887886
524.3841750621796	90	355.2640032590215	2.029198707406882	359.90920063853264	349.30868521297816	9000000	1.4180609067085261	1.431080576887886
580.3937397003174	100	354.66218275615046	2.3913507599468917	360.91215152223594	344.95670382143	10000000	1.3883683657413561	1.431080576887886
