Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.068171501159668	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
75.49467635154724	10	101.2146529587705	5.682630848233511	112.6165812718682	89.20432778353279	1000000	0.9022397701834056	0.7110426538948396
134.67016696929932	20	260.63834303843504	3.248219538228926	266.5255131069698	251.61610022862442	2000000	0.9469739132336882	0.7110426538948396
192.59865164756775	30	342.1892370972126	2.8050405529689333	347.34322650944523	335.23027479770826	3000000	0.9640791025131435	0.7110426538948396
248.24596786499023	40	353.3825076673273	2.4499392288773856	357.9881046108203	347.5010650604381	4000000	0.9662611794720335	0.7110426538948396
306.1296274662018	50	354.4444796981254	2.912684631670302	360.5262493157061	343.8155023086001	5000000	0.9439861182056372	0.7110426538948396
362.8589999675751	60	353.6150394696446	2.086757143706749	359.9554404860028	347.98700372019084	6000000	0.8937860422805107	0.7110426538948396
421.32047033309937	70	355.77996588199164	2.4329307216767835	360.8204174344428	349.0449687934015	7000000	0.8592430028794205	0.7110426538948396
478.9588587284088	80	353.98900323047417	2.0449767008230646	357.97648921837396	346.71405618917197	8000000	0.8459186260598471	0.7110426538948396
534.5291390419006	90	354.6387493564423	2.0473786183647484	360.54926721926313	348.6435103851254	9000000	0.8331751738979085	0.7110426538948396
593.3572890758514	100	355.97549497505025	2.6416948224039136	361.3987070962321	346.7368849737686	10000000	0.8192895497086379	0.7110426538948396
