Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.55619764328003	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
47.555724143981934	10	34.80746873801858	3.7411458090013885	42.22302340972237	25.76008571578859	1000000	1.0892431325946006	0.884538750985813
82.64936590194702	20	197.90650788049345	4.189129313053158	207.5684035945451	187.30210240813904	2000000	1.2149523130744122	0.9704382235080738
117.14256238937378	30	339.3605320118287	2.7434025757403235	344.603283551347	333.59241338429274	3000000	1.3592238062304434	1.3006088994814966
152.3897602558136	40	353.31116607259537	2.3837815803322444	358.11810681479983	347.09503302506346	4000000	1.2822934942187523	1.3006088994814966
188.96910452842712	50	355.2591220917433	2.502399330896565	359.9537849298358	347.5888999287854	5000000	1.1956568946755526	1.3006088994814966
224.97716069221497	60	354.64765110774636	2.5068087323174355	360.4043083714205	348.0134993172396	6000000	1.1184673019714582	1.3006088994814966
260.3400626182556	70	355.4333053617073	2.0158556459323065	359.2580211579334	350.2025244194083	7000000	1.0704635428285252	1.3006088994814966
296.30795907974243	80	355.4332091330214	2.2361308666118873	360.4203110440867	346.80242677076603	8000000	1.0236614676520166	1.3006088994814966
332.23048520088196	90	353.86072678373245	1.9033734926820876	359.87478537006245	349.49999496736564	9000000	0.9966928690231264	1.3006088994814966
367.8319923877716	100	355.7476751697668	2.4201190566815085	360.104930595262	349.23669182835147	10000000	0.9812138162715722	1.3006088994814966
