Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.552016973495483	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
36.88142991065979	50	0.5073956443004204	1.0129842191590972	3.197292271722084	-1.9951592831292988	100000	0.9803921568627451	0.3569446790629347
65.26183414459229	100	5.260019807198078	3.224567816036622	11.160735834615421	-0.8899700063034288	200000	0.9900990099009901	0.3689897741828182
93.013840675354	150	631.504004608409	201.85907383831156	854.8719363142736	22.512733670242596	300000	0.9933774834437086	0.3689897741828182
121.08554124832153	200	892.6793183989809	28.716604907642495	903.3863128200173	620.748949713452	400000	0.9950248756218906	0.4265439525996158
150.00672030448914	250	892.0025888974013	7.973888054796227	900.6116435992008	842.8237610198557	500000	0.9960159362549801	0.4265439525996158
179.16720938682556	300	1301.7672639105833	10.162903563790163	1320.4596481919289	1254.0469283033162	600000	0.9966777408637874	0.4265439525996158
208.68857669830322	350	1445.9150348462094	8.404826189981234	1462.9230446051806	1411.3807595223188	700000	0.9971509971509972	0.4265439525996158
236.63245248794556	400	1424.9586740983184	8.753973967794858	1440.8911568075418	1399.1565439623082	800000	0.9975062344139651	0.4265439525996158
264.688595533371	450	1554.02334873043	8.970389299180683	1572.8479024991393	1526.7711449656636	900000	0.9977827050997783	0.4265439525996158
292.66879630088806	500	1544.7995157714818	8.562116691397506	1558.7427871190012	1510.1731572337449	1000000	0.998003992015968	0.4265439525996158
295.90710377693176	501	1559.2720432486406	8.067486856846477	1577.6936691328883	1529.2438567026984	1002000	0.99800796812749	0.4265439525996158
