Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.912083864212036	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
87.31847310066223	10	82.13066542223595	18.156311553217602	104.97240905149374	48.72171226888895	1000000	0.8865356583928684	0.6053406027915993
156.03878951072693	20	228.6601809392679	3.2705766455083634	235.67230644449592	219.99400461587356	2000000	0.9364271871806102	0.6873221589536201
224.86425495147705	30	296.90645458894556	3.2634304642651775	302.42103209882043	287.1195575784659	3000000	0.9569345461546069	0.6873221589536201
293.34462809562683	40	331.08236978218173	2.9815300194531384	338.2802387246047	320.8336574762943	4000000	0.9674383153851908	0.6873221589536201
361.3869559764862	50	345.33200560491355	2.8840150132034013	350.9094807217916	338.0574700164143	5000000	0.9727389968201902	0.6873221589536201
429.8239188194275	60	349.3949671764416	2.1137218456841587	354.05791548476554	343.8274434445775	6000000	0.9679538661285255	0.6890594031236089
496.852756023407	70	352.5945064769901	2.625455224993386	357.2652743877843	344.6866455414565	7000000	0.9650463547568419	0.881058421306713
563.4314382076263	80	352.35579451580094	2.05820455036572	357.8513774478124	348.4102928573848	8000000	0.9577374350205097	0.881058421306713
631.345822095871	90	353.45099411137716	2.332591587661981	359.2184603344358	347.9215391125708	9000000	0.9374007993486757	0.881058421306713
696.8937773704529	100	354.50622824238695	2.0979205228088156	358.7088524288265	348.7372975793842	10000000	0.9254043680964946	0.881058421306713
