Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.22088098526001	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
35.9693386554718	50	61.00276936711021	20.12419552511736	86.76639112795237	34.48536481732299	100000	1.8224481875398229	0.5
62.26023745536804	100	251.81889633969615	2.6602195504501105	259.6746098201256	246.39989537188376	200000	1.8389749983382693	0.5
87.99792218208313	150	333.7917616326944	2.239500178981398	338.1352698667906	328.4035372604849	300000	1.8447225778001188	0.5
114.18705940246582	200	343.4554259938847	2.0827551491406058	348.77073525650485	339.293879697565	400000	1.848710227447018	0.5
140.2589385509491	250	344.4816962804681	2.7198411758474297	350.9052916021319	339.1045151809103	500000	1.8486372099645916	0.5
166.2526879310608	300	346.52126754638715	2.942996061041249	353.23666004725965	339.56498597818427	600000	1.853298418196664	0.5
192.1597592830658	350	347.3680457015853	1.9893331541262513	351.4028849918395	342.47656949308293	700000	1.855345722707094	0.5
218.33931398391724	400	351.6394175385956	1.733301922338529	355.4760114190867	348.07184923008026	800000	1.8572875590170084	0.5
244.24106860160828	450	353.1154419446313	2.0058552703704113	357.1865520142019	346.588170062867	900000	1.8599517027491819	0.5
270.43467807769775	500	355.6782450522594	1.8364213745392846	358.95106719766045	351.2197570169519	1000000	1.8589356529636014	0.5
273.4300181865692	501	354.5456845541006	1.8795288331649769	358.43467876309296	347.7560619750875	1002000	1.8590958766967167	0.5
