Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.220062732696533	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
44.53211236000061	50	45.704719264811466	9.825598793217958	58.379742968649225	10.121842434906284	100000	1.8287196216634354	0.5
73.05191111564636	100	91.24385482190272	10.330734644765798	111.77447659694008	70.12590306269703	200000	1.8559943367649339	0.5
101.16506743431091	150	202.01828911510228	6.167598187481081	213.2623098458862	185.6006182936544	300000	1.862781364413194	0.5
129.8701455593109	200	289.5409436836182	4.808995864859149	296.7190643635113	274.68469790462404	400000	1.867454476295365	0.5
158.43786215782166	250	330.58192571164926	2.3447150235520136	339.0869394284091	326.5780261142645	500000	1.8725317301787296	0.5
187.18008852005005	300	344.32149053126136	2.5974367692553755	350.2406128398143	338.5461389530683	600000	1.8695275068587118	0.5
215.33732557296753	350	347.52035579220967	1.9962365214599413	351.35138189641293	342.0540698216064	700000	1.8680911725551956	0.5
243.3463532924652	400	351.18449146698845	1.8555482600934585	355.0779552690219	346.6427252906433	800000	1.8682045054007987	0.5
272.57507586479187	450	352.24460105794674	1.7434559725854957	357.4819039031863	348.7006236772286	900000	1.8682299252293924	0.5
301.73786091804504	500	353.9168079784452	2.144751325944897	359.512406445574	350.29843045107555	1000000	1.8675519300746202	0.5
304.99677538871765	501	356.26145419088016	2.1601562425814604	360.921498183161	351.00804701360175	1002000	1.8673619584885637	0.5
