Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
7.373249769210815	0	-0.30404523389316856	0.7831634747396644	2.251814016645012	-1.870696566842263	0	0.0	0
34.981045961380005	10	6.741429652676823	5.0253304265755405	16.301748511931294	-0.7663127551824509	800000	2.1299584448315634	0.5
62.599220275878906	20	886.0041935449133	9.57707020109578	903.5641817780343	857.004746002669	1600000	2.2254769490461945	0.5
89.99651670455933	30	1545.3617354215855	10.678087367293436	1571.5709478985518	1493.0813274206594	2400000	2.162083464045513	0.5
117.18190622329712	40	1882.6106196423777	37.36076957976807	1954.0043642923702	1747.0603024433367	3200000	2.1672620793203383	0.5
144.24061584472656	50	1698.7898360879526	10.13357101266159	1724.603958427906	1664.0133321024477	4000000	2.1213337356504827	0.5
171.4051022529602	60	1703.5595612070733	9.938930644592158	1718.4153464213014	1654.96315109008	4800000	2.106895696083403	0.5
198.8321270942688	70	1973.9727073839913	24.44106233474406	2028.3295802026987	1918.1497072293423	5600000	2.11362882150548	0.5
226.48794794082642	80	1741.1624729398568	10.980315294283395	1762.1216592090204	1693.3215778218582	6400000	2.119456228102187	0.5
254.0113627910614	90	1870.105121520846	8.885087966990845	1888.6221372932196	1845.2275664135814	7200000	2.1162074644533058	0.5
281.6153748035431	100	1956.8676796689026	21.38104576769523	2010.2150482659054	1893.7112623283174	8000000	2.1019428635702138	0.5
309.345755815506	110	2058.904732019177	20.291178036509944	2095.0007757991552	1997.596027251333	8800000	2.0962858654219927	0.5
