Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
7.6073830127716064	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
35.1805100440979	50	114.19926697297859	21.53727313618644	153.02277431646507	49.59782325740525	100000	7.835201017186473	6.051690688497223
63.59159827232361	100	-18.591844783312627	6.368704424611172	-5.864750552738656	-30.15817658836022	200000	7.829581580172183	6.595539547152909
90.36760354042053	150	16.671244434266665	13.969336876129512	40.34074028057512	-19.84566905567044	300000	8.028121073164728	7.768367627135068
116.96748852729797	200	94.70480256992875	14.6096694196927	120.58599469589535	46.07884119016171	400000	7.976096973231651	7.768367627135068
143.0473837852478	250	220.3951979693485	76.82484351947643	266.0420381324366	-23.814264834392816	500000	7.951998589445975	7.768367627135068
169.03966069221497	300	307.82212854410346	39.656748006543005	330.6939174402796	47.35553339053877	600000	7.983674733801796	7.768367627135068
194.87301397323608	350	333.1218032954905	5.494828328352252	340.33247537794523	301.63692251397515	700000	7.978058148178507	7.768367627135068
223.38117218017578	400	353.752796725212	3.58663875968111	360.5830188804248	344.5314826637041	800000	7.948499571930375	7.768367627135068
249.62389993667603	450	351.30363789488575	4.427138022577575	358.4112013007398	340.91114440337697	900000	7.937383750596726	7.768367627135068
276.0039870738983	500	351.35926684897566	3.3604906012530464	359.13641689337965	342.81622782550403	1000000	7.897944917091889	7.768367627135068
279.2537212371826	501	323.8123890788886	4.898484920367387	333.3571228007786	316.21435789973475	1002000	7.896380491492584	7.768367627135068
