Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
12.627487897872925	0	-0.30404523389316856	0.7831634747396644	2.251814016645012	-1.870696566842263	0	0.0	0
41.925384521484375	50	563.3742463623796	124.12839565406011	858.5180659484613	205.69912170490716	100000	19.733735458322382	8.240323501043736
69.14313459396362	100	866.450287334421	119.25262111437617	1167.4642439467134	612.91228648182	200000	20.034140482937627	8.49237141956883
95.46924066543579	150	1091.4000563357854	118.98989366453283	1393.1491093519144	756.6615679823444	300000	20.03169310418538	8.49237141956883
122.2161111831665	200	1081.3338818133564	168.7581430122547	1464.7269028148148	676.6984580416756	400000	20.069889561525248	8.49237141956883
148.70159316062927	250	1466.5739611009794	213.77252481673852	1842.822838024702	501.5751377250999	500000	20.10107757862734	8.49237141956883
175.32421469688416	300	1595.8431374281035	142.3131630960797	1849.5956660378724	1051.0337969402317	600000	20.09778362961003	8.49237141956883
200.9688844680786	350	1029.4918502801945	294.1775410940771	1562.678441486787	-901.0709938411601	700000	20.10324519285234	8.49237141956883
229.26784944534302	400	1600.2996771835803	484.45269898636127	2067.091487209196	-445.7171263792552	800000	20.109119423080116	8.49237141956883
256.23978209495544	450	1179.465550965773	749.6249931781819	2177.4369937619194	-1109.5586498859338	900000	20.120334905598675	8.49237141956883
283.92308139801025	500	1601.6795909090297	889.3906598956908	2373.128888273961	-1136.4108222601935	1000000	20.112496356542795	8.49237141956883
287.29864621162415	501	1739.4194289844204	475.37750184634996	2394.72667031514	-1178.1443613674492	1002000	20.115073931574077	8.49237141956883
