Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.283228874206543	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
37.973350048065186	50	1.0474901810310968	0.9461419030318297	3.581597064765191	-1.0900133949391781	100000	4.610406805065743	0.5
66.3427517414093	100	9.103252060039635	4.204049038537368	15.447777524105618	0.500742276070639	200000	4.653935880017789	0.5
94.95391058921814	150	656.5758142780672	7.315903100816906	666.8792876582593	625.5065733906813	300000	4.6749685865362824	0.5
123.37197518348694	200	759.4335408459549	18.364804242355177	789.8190332744562	671.7861477454426	400000	4.68526352105535	0.5
151.6141655445099	250	995.5146021515945	4.731669468212783	1005.6157424375415	983.3085433356464	500000	4.687991889179126	0.5
179.53055787086487	300	1043.7074429345207	4.5641123820835645	1052.110071728006	1031.5421391576529	600000	4.691707158144372	0.5
208.4219810962677	350	1199.3808525161842	3.776172183421776	1208.4677774747834	1191.635711275041	700000	4.694911840223484	0.5
237.67600011825562	400	1161.4929450727732	6.647252828117284	1175.9509409852326	1142.7517067724839	800000	4.696122671456811	0.5
265.1550931930542	450	1378.4151172537743	10.162191505113308	1394.6374883241951	1338.7880983054638	900000	4.697316876105876	0.5
292.7877130508423	500	1405.9856043915972	8.71977013674322	1431.4318685634062	1373.7619598712772	1000000	4.696991953493721	0.5
295.9081950187683	501	1312.924878581076	12.584611741908352	1343.1503026872233	1282.6885140687227	1002000	4.697146672553556	0.5
