Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.241008043289185	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
37.114726066589355	50	33.30904802170833	4.922753827275413	43.409825895447284	24.941478956025094	100000	7.835201017186473	6.051690688497224
66.05716252326965	100	19.547164783810693	2.864219148357567	24.204599303993746	8.143367591666902	200000	7.829581580172183	6.595539547152909
95.49482131004333	150	80.02639799765872	21.851029759007396	115.18062389799161	-1.8013074632035568	300000	8.028121073164728	7.768367627135075
121.72723126411438	200	224.09852814523228	7.790849424601429	234.13714200566756	168.76687183091417	400000	7.976096973231651	7.768367627135075
147.71665573120117	250	308.25747093037063	8.645211457180359	322.35787380766124	282.8684436423937	500000	7.951998589445975	7.768367627135075
173.50381588935852	300	338.32847592854046	2.353203507287603	342.72619652881986	328.179951469996	600000	7.983674733801796	7.768367627135075
199.5588254928589	350	350.933912867575	1.9409987445985548	355.7796240171883	346.008485598024	700000	7.978058148178507	7.768367627135075
225.31350421905518	400	355.1808657054121	1.32721939149766	358.0765921421116	352.0279260655516	800000	7.948499571930375	7.768367627135075
251.4260802268982	450	353.35492284371094	1.8822469118450045	357.89406084372604	348.15159392997157	900000	7.937383750596726	7.768367627135075
277.156564950943	500	352.82681247271154	2.381518973964944	358.36028501484543	349.7321450415184	1000000	7.897944917091889	7.768367627135075
280.3493347167969	501	354.4403468713061	2.264052807267903	360.38929585163714	350.48471573204733	1002000	7.896380491492584	7.768367627135075
