Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.718271493911743	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
39.561612606048584	50	29.730936873239926	3.694572556152385	38.88554922299227	21.462202628477826	100000	0.9803921568627451	0.7154173901801465
71.05943250656128	100	34.69803486419259	4.197759972100039	44.763966280501336	18.6038592151599	200000	0.9900990099009901	0.7154173901801465
101.66096830368042	150	40.298600164579305	3.4085438360814706	47.87264915648848	32.18529769103043	300000	0.9933774834437086	0.748067693734711
132.20597386360168	200	41.27887247309413	2.8298893971430275	46.64933709427714	33.54947405052371	400000	0.9950248756218906	0.748067693734711
165.59623217582703	250	44.787757521588354	3.000392789054154	50.69939339580014	35.01157911028713	500000	0.9960159362549801	0.8313389235496507
196.45948934555054	300	45.656643693085464	2.2680397251308344	50.785323350690305	40.00496111018583	600000	0.9966777408637874	0.8313389235496507
228.43937849998474	350	45.26382821520616	2.864861495474117	52.64559609815478	39.38340593269095	700000	0.9971509971509972	0.8313389235496507
259.91771960258484	400	45.58522912482991	2.5562048364855197	50.92132959049195	38.7992925690487	800000	0.9975062344139651	0.8313389235496507
291.33946108818054	450	44.37015719827909	3.2702060322831183	51.75821070279926	35.77040454489179	900000	0.9977827050997783	0.8313389235496507
322.6575536727905	500	46.0182813143218	2.681518253180919	51.560204402543604	38.4583409819752	1000000	0.998003992015968	0.8313389235496507
326.2758867740631	501	46.7991857431901	2.81969035109281	52.77119411760941	40.29395295493305	1002000	0.99800796812749	0.8313389235496507
