Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
13.292217254638672	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
68.74418807029724	10	349.14813068633407	2.91650655323987	356.2678884493653	344.0569800180383	1000000	2.9033809584851187	2.5486692859200537
124.05753874778748	20	350.2634252498293	3.8863412637130366	357.2394910151488	334.86872537096497	2000000	2.6976052023775563	2.5486692859200537
178.70257019996643	30	354.4259683162861	2.4924840192953446	361.3475085988175	347.37009199679596	3000000	2.595398674813002	2.5486692859200537
231.17598628997803	40	354.57533319361255	2.6490958508174995	360.8201500510331	347.2840868651401	4000000	2.5026205479903423	2.5486692859200537
284.9912223815918	50	353.7686609546839	2.6635625458410677	359.31256032490637	345.6027986393892	5000000	2.50336816133394	2.5486692859200537
335.01851081848145	60	353.5821346546643	2.2374237329310507	358.90603489006753	347.59444756370067	6000000	2.45343431983987	2.5486692859200537
391.01528573036194	70	355.4767571320019	2.8818185424295137	362.1818613044452	346.88188903121045	7000000	2.432189098801885	2.5486692859200537
447.65630865097046	80	355.05816314586167	2.797587425922427	360.8436603980317	347.44278058116834	8000000	2.421690922005649	2.5486692859200537
504.5137801170349	90	356.154103899273	3.043738105260721	362.09632178070024	349.8160907473357	9000000	2.409314424973673	2.5486692859200537
558.8619084358215	100	356.88451975884806	2.992583566951961	361.93757002893835	344.3667931680102	10000000	2.3787302327096502	2.5486692859200537
