Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.040472030639648	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
83.92609882354736	10	330.7231033436139	2.342010672276501	336.88340525177773	323.9779513286776	1000000	3.2375373563435343	2.5551736669055205
151.3840036392212	20	353.38671228777474	2.087963387016672	357.3432780594849	348.0630759114283	2000000	3.0917702435916503	2.5551736669055205
218.86448097229004	30	352.1740815211762	1.5697258728185361	357.01772053696914	348.3887622782495	3000000	2.8838675783969325	2.5551736669055205
285.87987327575684	40	355.00186390702316	2.0488999525689295	358.84790817735484	347.90720073034754	4000000	2.681590893855419	2.5551736669055205
352.80065393447876	50	354.4952627023129	2.392671611743268	360.29279683122877	348.8742528888979	5000000	2.6110295625037634	2.5551736669055205
421.7951543331146	60	354.9437086110785	1.9508654970779018	359.63154508918524	351.17254086447065	6000000	2.584056579438305	2.5551736669055205
489.54713106155396	70	354.7542258461191	1.575898603797509	359.7936698945705	351.6829756142106	7000000	2.5866137322982237	2.5551736669055205
556.7426981925964	80	358.3285522672429	1.7609137013760197	360.96926129842177	351.2125679984456	8000000	2.5787087576384766	2.5551736669055205
622.8963935375214	90	358.4195761663212	1.3891391030505562	361.04089162684977	354.1173837936076	9000000	2.560462419165961	2.5551736669055205
691.3316118717194	100	355.4923038171411	1.263122816776681	358.2462063317507	352.58173917175736	10000000	2.541057272041283	2.5551736669055205
