Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.362271070480347	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
86.89462041854858	10	203.95131364531144	3.536081901346791	210.6406018465641	193.93573805788765	1000000	1.2681733085583262	1.0156734405925258
158.7610216140747	20	310.50257971563815	3.11920879539337	317.5009341989644	303.6378190520918	2000000	1.3743996186438328	1.1723945543567913
227.7521779537201	30	345.82434921907713	2.4181777135738445	351.22592041114694	337.70732522165054	3000000	1.4592721926159713	1.1723945543567913
296.84996914863586	40	348.6302199826509	1.8494950865757114	354.0524914878988	344.99231290607713	4000000	1.3784347000624124	1.1723945543567913
368.7494604587555	50	350.89842614531847	2.09468993665407	355.2396197501803	345.14373404718935	5000000	1.2962999814856795	1.1723945543567913
438.57383489608765	60	354.26304282344995	2.403601576947908	358.51978273838176	346.2245623739436	6000000	1.227439770132913	1.1723945543567913
507.6171205043793	70	354.2744683477343	2.075139213294914	358.91354808263713	349.3277124594606	7000000	1.1785515288064403	1.1723945543567913
573.0276122093201	80	353.241136628008	2.1642848600075206	358.5052649699064	348.5082122669555	8000000	1.1355043503904898	1.1723945543567913
640.6339066028595	90	355.90565777225834	2.4258577207062513	360.83352044425556	349.8513789391436	9000000	1.1022316829841567	1.1723945543567913
709.4274380207062	100	355.43209640874636	2.2831005210611943	360.04682033811696	350.1860836431151	10000000	1.073377285299404	1.1723945543567913
