Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.749097108840942	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
39.82041621208191	50	0.9935332953483211	1.3021408084998805	4.581470842082709	-1.9112830667228593	100000	4.624611302837594	0.5
67.94550395011902	100	7.783643205676607	4.360584521268416	16.026478056192172	-1.0665640196799018	200000	4.669427545929823	0.5
96.19033908843994	150	389.6218047849008	187.70079061338086	513.157754251064	-0.979947298824527	300000	4.682484625777486	0.5
124.19386887550354	200	1070.1817189766846	28.094256988633123	1110.7304053525731	829.8726693041608	400000	4.691610273875494	0.5
151.50517082214355	250	1017.6024651361658	22.55345169288598	1029.4573729154072	864.3907511257567	500000	4.697621315501486	0.5
179.56133246421814	300	1462.4136085121263	13.309521627385946	1497.5644533485174	1395.8767345895758	600000	4.697799634543149	0.5
206.66239953041077	350	1371.5288734538422	21.868092404089865	1481.2373068854213	1327.2649830132723	700000	4.6996142083326635	0.5
234.5626311302185	400	1610.639360522998	29.55861114245358	1641.774529851973	1498.6577758416533	800000	4.700372880863579	0.5
260.8436851501465	450	1533.0458696491685	8.425990136460243	1550.5315463244915	1515.1687317304313	900000	4.7014419204738696	0.5
288.52264499664307	500	1520.9977990259306	16.548618728450492	1576.055482391268	1464.3645952339284	1000000	4.702470745123318	0.5
291.9832594394684	501	1586.6964466422912	78.01067723178154	1671.9457855857909	1447.9955397676677	1002000	4.702377347567212	0.5
