Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.430889129638672	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
36.53008437156677	50	18.723488258032525	8.2346101899702	32.1018462816719	-1.2084021773480345	100000	0.9803921568627451	0.25
64.0350730419159	100	29.280620670524502	4.260159257858773	36.43190543015953	20.20095518301241	200000	0.9900990099009901	0.25
92.08465123176575	150	29.011514858615143	3.1851607891242253	35.073526400219635	23.001920043257996	300000	0.9933774834437086	0.25
120.01091575622559	200	30.162078052612948	2.7716717059132048	35.01086152023299	24.75870959693566	400000	0.9950248756218906	0.25
148.62394309043884	250	30.2739862630295	2.8572597304834852	36.533347595107216	24.08139551267959	500000	0.9960159362549801	0.25
177.50982236862183	300	44.09018772327258	14.041607127256494	83.86179053183878	22.456775999255115	600000	0.9966777408637874	0.25
204.33177042007446	350	98.78125353586901	6.041919941673479	112.19834720194922	85.84203893179074	700000	0.9971509971509972	0.25
230.53127336502075	400	112.13541458909759	4.8311623258283936	122.76692139809893	101.82427847043436	800000	0.9975062344139651	0.25
257.7751669883728	450	126.77684709824177	4.453770483498642	134.93415210810872	117.07870631798869	900000	0.9977827050997783	0.25
285.5553295612335	500	163.8881748845861	3.7629206358723737	171.83145696489373	156.29009943367055	1000000	0.998003992015968	0.25
288.7802562713623	501	171.48444602719587	3.941803325915246	177.86525358250947	161.71562005829765	1002000	0.99800796812749	0.25
