Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.875420093536377	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
36.53415298461914	50	0.0005594677986307417	0.6654999919500063	1.837360298147459	-1.5874531227271085	100000	0.9803921568627451	0.3551215412473305
64.87190866470337	100	0.1695452396702429	0.7323685813316415	2.382824064223186	-1.9143576775816271	200000	0.9900990099009901	0.3551215412473305
92.81758117675781	150	0.9955852995313949	1.1439616329343893	3.684368024787304	-1.2477501507566853	300000	0.9933774834437086	0.3984649513187947
121.07337665557861	200	1.9880162739934268	1.747908384318083	5.831660147481266	-1.2084837112633977	400000	0.9950248756218906	0.3984649513187947
149.46197843551636	250	5.897583849325133	3.809963830945277	13.622387211460158	-0.7402708335651198	500000	0.9960159362549801	0.3984649513187947
178.19804048538208	300	11.060969414078675	5.431051185574651	18.34064699970761	0.11108788735631947	600000	0.9966777408637874	0.40746124001391876
206.02814173698425	350	17.657258882079393	6.441869972659315	25.424976818765572	0.8335500615794444	700000	0.9971509971509972	0.40746124001391876
234.59027647972107	400	526.9210598769356	160.31918251619982	587.0262489931192	12.288568466785364	800000	0.9975062344139651	0.45084528314621886
264.3372640609741	450	674.8054463005262	92.66025002031739	693.9208833205048	23.931645409902558	900000	0.9977827050997783	0.45084528314621886
291.95068407058716	500	805.2398814432622	77.76712093048138	820.0251151537523	32.793336684117094	1000000	0.998003992015968	0.45084528314621886
295.3880250453949	501	807.1718411653396	111.72383423760017	832.7785122469068	35.43462527409429	1002000	0.99800796812749	0.45084528314621886
