Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.609959840774536	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
38.6983003616333	50	60.74971710030059	6.3811435637201965	80.22857718386695	51.20924143399316	100000	0.9803921568627451	0.7282365327608291
68.01605439186096	100	132.31178321626328	5.786539385003033	140.745005429686	109.4692946379073	200000	0.9900990099009901	0.7282365327608291
96.088627576828	150	203.250841487088	3.761965654042207	213.08395678261877	193.06778708056663	300000	0.9933774834437086	0.7479759653981487
124.02023983001709	200	253.64723143816525	3.037226659526505	264.27499605427147	247.929010617303	400000	0.9950248756218906	0.7817129955552287
152.96466255187988	250	284.7636410036919	2.216940370073534	289.93804084602743	279.1954256318277	500000	0.9960159362549801	0.7817129955552287
181.89306020736694	300	305.6469814016323	3.2158004802332774	312.6028444800759	299.3881574727129	600000	0.9966777408637874	0.7817129955552287
213.20376014709473	350	326.1079284919204	2.4226725652888064	329.93955902173184	318.47322987468215	700000	0.9971509971509972	0.7937241636825247
242.12158846855164	400	336.83345717077304	2.0294595103508777	341.8894252696191	332.9492871304974	800000	0.9975062344139651	0.7937241636825247
272.7349991798401	450	341.9638289265016	2.649542950028962	347.5499611493119	337.3239126247354	900000	0.9977827050997783	0.7937241636825247
301.82172179222107	500	344.2077447541977	2.619335802384178	350.57556346280035	338.72698168698116	1000000	0.998003992015968	0.7937241636825247
305.24738478660583	501	344.2838867601703	2.4641479027927335	349.2485936302983	337.53541295189643	1002000	0.99800796812749	0.7937241636825247
