Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.261228561401367	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
37.103718519210815	50	0.18310046767161595	0.7481786848327826	1.8563132065756367	-1.930053115155756	100000	0.980392156862745	0.09901475429766744
65.65331029891968	100	1.1264022178434079	1.1873935796393658	3.8875643530620945	-1.59839683570209	200000	0.99009900990099	0.09901475429766744
96.76161408424377	150	2.6113793910225462	1.820557801144486	6.9280932935630375	-0.9448056016740622	300000	0.9933774834437085	0.09901475429766744
124.65449500083923	200	13.973184838344263	6.32628975271181	34.828888435382396	4.24568979414471	400000	0.9950248756218905	0.09901475429766744
153.04063487052917	250	536.5112403267216	109.91573914890101	577.7713692103862	53.942288406862644	500000	0.99601593625498	0.09901475429766744
181.75888061523438	300	579.6108384195921	19.19033640264234	598.2844084360986	486.22504319628933	600000	0.9966777408637871	0.09901475429766744
210.2336184978485	350	969.3357159105476	10.287968194268625	992.3078562300652	944.0986976628774	700000	0.997150997150997	0.09901475429766744
241.36350679397583	400	1142.988107581374	7.528630146014985	1166.7138975039124	1123.3359888127088	800000	0.9975062344139649	0.09901475429766744
270.0047354698181	450	974.6668508243549	4.343861846012306	983.6599687226117	958.6154125351459	900000	0.9977827050997782	0.09901475429766744
298.87948513031006	500	1114.7745727267275	10.268628599512517	1132.7123612090945	1070.672709301114	1000000	0.9980039920159679	0.09901475429766744
302.95969319343567	501	1166.2168091023875	11.12161575132311	1193.5497300885618	1133.7687183385715	1002000	0.9980079681274899	0.09901475429766744
