Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.324379444122314	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
75.1419734954834	10	30.8976313511306	5.545884474594043	44.25840273220092	21.892850301926956	1000000	1.516340543018638	0.5
135.7157905101776	20	34.89372047760578	7.228209900467739	49.66656109597534	20.34938013914507	2000000	1.496111341448231	0.5
196.5935513973236	30	38.128251277310355	3.993032540717444	47.218388855457306	29.16105889203027	3000000	1.4932004858479384	0.5
256.9458041191101	40	40.330970003257896	5.353959716178232	50.21734686428681	27.752357940888032	4000000	1.4983299327802926	0.5
317.64776372909546	50	38.49063229683805	6.612605601558439	49.43460015486926	24.8445017743652	5000000	1.5135374338729337	0.5
378.14112877845764	60	39.173428222316964	6.349118371503418	50.22381885908544	29.026166079333052	6000000	1.5139235079969364	0.5
439.0274040699005	70	39.80484921709263	6.900842029178349	51.402391562704	24.589380845427513	7000000	1.5150931270393442	0.5
498.54985094070435	80	38.59397141844001	7.159188629338715	52.25765711022541	24.68656211589405	8000000	1.518011049900958	0.5
559.1194183826447	90	39.85917982880217	5.237523795334041	48.75438127400594	30.133187925443053	9000000	1.5141161426191232	0.5
619.3183863162994	100	42.41065880044238	3.6517110098504597	49.88432374969125	34.54653304244857	10000000	1.5174993061318471	0.5
