Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.149671077728271	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
73.9632716178894	10	127.75604630611252	5.062557485191356	139.68010466641863	115.98004885064438	1000000	1.247394650575551	1.2726140966636337
129.58258938789368	20	304.77476091215425	3.268140119679465	311.155087947016	294.49336557352217	2000000	1.36370421983958	1.2726140966636337
186.4515461921692	30	350.49474890214884	2.790891816186468	355.28540250405786	343.1326286866097	3000000	1.3896820967772172	1.2726140966636337
243.57618355751038	40	354.12502715739123	2.1090188091914452	359.2069012039574	348.2792550536542	4000000	1.2862069512180274	1.2726140966636337
300.63519978523254	50	354.1760338438598	2.09006800369075	358.4620174788288	349.5323308549123	5000000	1.1800223049149396	1.2726140966636337
357.8773031234741	60	355.63414637082053	2.5344042412689367	361.0135339011904	348.94787742503104	6000000	1.1126681776079577	1.2726140966636337
414.7932457923889	70	354.08637224124186	1.880826950198417	358.68185290609836	349.5386768495373	7000000	1.1012461356907763	1.2726140966636337
472.06895780563354	80	354.6840449503179	1.9392535776284763	359.7214357407065	349.6726007371908	8000000	1.0532291605532056	1.2726140966636337
528.6402311325073	90	355.21975103053467	2.372570842057259	361.2154267579317	348.53479874203913	9000000	1.0303031703061099	1.2726140966636337
585.6759626865387	100	356.15423235714775	2.3862876708798084	361.0075807484682	349.29623614100274	10000000	0.9967488419424988	1.2726140966636337
