Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.495314836502075	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
45.27931094169617	10	32.37904843763923	4.113152822468371	40.929073947365396	24.970850785495713	1000000	1.0102980551767684	0.8993085544923166
82.7777464389801	20	40.43641570843182	2.8852456848375763	45.77218744158745	33.64732471713796	2000000	1.0751173693165144	1.0590585578305935
118.9003701210022	30	42.11329469095333	2.4452102487539755	46.845207212958485	36.11083698668517	3000000	1.0203168122585178	1.0590585578305935
156.08878374099731	40	43.405468223576754	1.9227729394263184	47.045608101878315	38.972307843505405	4000000	1.032159083222978	1.0590585578305935
192.04292821884155	50	47.58324885611185	9.068880532745856	72.60169717599638	38.02921919687651	5000000	1.0750982858100706	1.1865732537517955
227.6734414100647	60	82.78830522731077	2.894105936986345	89.80259792697325	75.46560585073894	6000000	1.1660326853897744	1.296374132319408
261.2528603076935	70	106.34351230641546	2.6329204468191305	115.92904456611723	101.91371652536327	7000000	1.2447835680877595	1.6155652730099461
295.6694300174713	80	164.31592938086723	12.472374149918828	183.98673839494586	131.63931700773537	8000000	1.2532917744977567	1.6155652730099461
329.3466832637787	90	245.07400908464572	3.3635118814528027	249.9539128546603	226.4614312143458	9000000	1.2776910973383528	1.6155652730099461
361.16570711135864	100	247.6025338029971	3.6711797485698052	253.79672483797185	233.12835785374045	10000000	1.2670609476523618	1.6155652730099461
