Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.485809564590454	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
35.835787534713745	50	0.3731284068980862	0.8524737765288152	2.3842550478715907	-1.9686986080077418	100000	0.9803921568627451	0.3569446790629347
64.12562894821167	100	1.9921581128903532	1.5459013515572253	5.126258090012731	-0.9813384554128319	200000	0.9900990099009901	0.3689897741828182
92.01862812042236	150	18.053125642791098	3.6735233661710565	24.076684550222126	8.523405196887325	300000	0.9933774834437086	0.3689897741828182
122.63471579551697	200	39.252718251477184	5.880605028853314	59.01877015066566	29.91595659061568	400000	0.9950248756218906	0.4265439525996158
150.50986576080322	250	650.92552256004	14.523173554262296	665.5323990582983	600.296252284199	500000	0.9960159362549801	0.4265439525996158
179.22293043136597	300	780.9527833949131	28.724984861771148	811.5444910058286	714.1553408361506	600000	0.9966777408637874	0.4265439525996158
207.88218069076538	350	826.0806712330223	24.199685344338015	850.345208093524	730.4615396219306	700000	0.9971509971509972	0.4265439525996158
235.62897157669067	400	1054.628476364702	6.981451323428321	1064.5767481382936	1013.9812124036252	800000	0.9975062344139651	0.4265439525996158
262.8236892223358	450	1040.099544545064	7.6130093552081375	1051.0042355526239	1008.5946449986659	900000	0.9977827050997783	0.4265439525996158
292.1188254356384	500	913.0780405527455	8.920671872549061	928.4942340236157	860.7415500443894	1000000	0.998003992015968	0.4265439525996158
297.14664244651794	501	931.1904451714141	9.158247570163992	943.1763706933707	877.7271914570592	1002000	0.99800796812749	0.4265439525996158
