Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.896942853927612	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
90.67164254188538	10	36.61971356768248	3.5054602466845424	45.17299860995263	30.132298469077796	1000000	2.456195890112202	1.7674199520680964
164.10799407958984	20	198.22095445140644	7.037563848202446	212.15625035591074	180.61912041832693	2000000	2.701455974681403	2.7736176147857297
233.21015882492065	30	238.11509300493498	11.084796036026788	268.32590760674793	218.93304166058078	3000000	2.7507923427268497	2.7736176147857297
301.50097727775574	40	269.89987316421923	6.108187061347109	282.4248759057373	258.31479934742674	4000000	2.7472017586810193	2.7736176147857297
370.1724410057068	50	268.9876061541514	8.197901942332248	290.05966829234967	260.3491983526037	5000000	2.676081191254199	2.7736176147857297
438.1593813896179	60	268.93677316061564	2.026367387634093	273.67074005136965	264.69190313963554	6000000	2.628519352069751	2.7736176147857297
507.6097831726074	70	279.8574601706428	8.713759265114392	293.5900102391606	267.60824167798273	7000000	2.5966113926429664	2.7736176147857297
575.3773326873779	80	280.5812867012747	6.653040679449113	291.773344971356	268.97724737157114	8000000	2.5822349906916613	2.7736176147857297
643.9770848751068	90	279.5390961746758	5.646789343991358	289.82436321489513	269.5472452577669	9000000	2.5901859173844723	2.7736176147857297
714.2505400180817	100	276.9849786002749	4.921545655181428	291.7248175111017	270.583917331649	10000000	2.6089602096020585	2.7736176147857297
