Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.057878732681274	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
36.179161071777344	50	32.40776168263184	4.2671112301988146	39.685270916408626	23.922458584554988	100000	0.9803921568627451	0.25
63.80162024497986	100	53.64511626352319	10.527289462646902	71.48267905586545	19.615941825562913	200000	0.9900990099009901	0.25
90.86781716346741	150	70.19666083873527	6.033043028932762	101.52527520735748	61.355485527659766	300000	0.9933774834437086	0.25
117.18479585647583	200	150.54733184338914	4.535144109202071	159.6720843958101	136.75385866634315	400000	0.9950248756218906	0.25
143.9307508468628	250	157.67525356666917	4.5434012066018195	165.9094555633692	148.84595526686462	500000	0.9960159362549801	0.25
170.4268217086792	300	201.07152989195671	5.144318483648326	210.57109835647861	188.6540292937425	600000	0.9966777408637874	0.25
199.47391939163208	350	237.41676058135323	3.6360151282690154	243.53475637234078	225.85971762309782	700000	0.9971509971509972	0.25
226.23586249351501	400	265.53381784971515	3.150653476712833	271.0671772011556	256.1884000810787	800000	0.9975062344139651	0.25
252.74608540534973	450	291.748379383025	2.283014204645351	295.7500904831668	284.58842402952723	900000	0.9977827050997783	0.25
278.7809205055237	500	313.2452099665036	2.9099204565266237	319.95591588446405	306.55022186250426	1000000	0.998003992015968	0.25
281.96783995628357	501	312.34765386990347	2.433994114578282	320.64325952436775	307.5594149676617	1002000	0.99800796812749	0.25
