Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.98863959312439	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
85.24322700500488	10	22.94495694501778	13.165123306482746	46.56628969569283	-3.362914754077792	1000000	2.1113169126947864	1.8132627041974065
154.86163330078125	20	22.711841880560343	16.25473707811818	46.02740309899673	-21.11401176918298	2000000	2.2189919678564154	1.8132627041974065
224.4967610836029	30	25.076024638388827	13.260366909648088	44.414331913460046	-10.21833753845931	3000000	2.1739883470948236	1.8132627041974065
293.5140678882599	40	35.76648051790118	35.24032921524013	86.05362253636122	-23.66444633001811	4000000	2.220986374285558	1.8132627041974065
362.2228808403015	50	172.71773112559038	46.749436246040624	271.69243681887747	100.98982444114517	5000000	2.3439749859383707	2.2938590598181974
427.6501679420471	60	336.9734568187502	2.70752751281263	342.14917070878437	327.06638327543624	6000000	2.5301670042910014	2.7713189453838054
494.60781812667847	70	347.1344709807374	2.349713182744159	352.81482668220997	341.6189891853137	7000000	2.613990860194289	2.7713189453838054
561.0610592365265	80	352.2308092888688	2.5586607686832394	358.06601718228194	346.1389180650003	8000000	2.5992170646184056	2.7713189453838054
625.6711633205414	90	352.37255979584586	2.314633741158491	358.6967523525818	345.6088687889278	9000000	2.577563041665753	2.7713189453838054
692.6026046276093	100	353.8444084924587	2.425896930547245	359.57670665581827	347.0260779664968	10000000	2.5771033176766913	2.7713189453838054
