Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.011679410934448	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
36.11174035072327	50	28.437499568451038	20.118671970330958	79.89311210697633	4.682908028131351	100000	1.8224481875398229	0.5
63.271554470062256	100	83.23069786880325	9.207315981971012	111.45124944997951	67.93926421389915	200000	1.8389749983382693	0.5
90.07958126068115	150	136.34172366962437	9.409451599269163	156.2283385276096	112.4923439186532	300000	1.8447225778001188	0.5
116.67430353164673	200	186.86251096156388	7.745298035494156	202.59759689956263	170.43874421236978	400000	1.848710227447018	0.5
143.40944814682007	250	223.2476114830316	2.6978913842358017	229.78832094051177	217.41028688062215	500000	1.8486372099645916	0.5
170.24246072769165	300	261.9401129231397	3.133913404017957	269.97346542356536	255.28372100043634	600000	1.853298418196664	0.5
196.69646763801575	350	281.7475683069977	2.5173453299614525	285.78955479103024	271.9275111735333	700000	1.855345722707094	0.5
223.52421283721924	400	312.14737796873453	2.3078464177572706	316.86836815439165	305.7936801384785	800000	1.8572875590170084	0.5
250.0050084590912	450	328.6868242165277	2.2019811831640266	333.0828213203931	323.41755384006683	900000	1.8599517027491819	0.5
277.3938021659851	500	332.9401537981959	3.3051750656538332	340.57684010503	326.3955140701728	1000000	1.8589356529636014	0.5
280.69582891464233	501	333.4707100721004	3.1172642875331213	339.8653362117475	325.2404013648629	1002000	1.8590958766967167	0.5
