Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.194297075271606	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
37.22888207435608	50	27.90377462901906	5.547439529348845	36.70432412511833	11.695377873373218	100000	0.9803921568627451	0.25
66.9341950416565	100	27.849954327366515	4.06575213581219	35.12054230111971	10.116567329379905	200000	0.9900990099009901	0.25
96.27750825881958	150	29.72824724845673	3.0942793790962178	36.00459554261761	21.88801948283799	300000	0.9933774834437086	0.25
124.43542432785034	200	96.1655811352087	4.086551066705253	106.87004948727554	83.2162401569658	400000	0.9950248756218906	0.25
151.55278491973877	250	154.18599050455236	11.454220036881615	178.0090304063633	129.73314487899188	500000	0.9960159362549801	0.25
178.82069396972656	300	198.72714414456468	3.3979773374434643	207.15533189516282	190.57559252271312	600000	0.9966777408637874	0.25
205.40247225761414	350	217.01693738991256	3.46419276022639	224.1483990863635	209.2763935443072	700000	0.9971509971509972	0.25
231.91397309303284	400	263.77816165816427	4.714088904512986	274.0966818612069	256.6615324886516	800000	0.9975062344139651	0.25
258.3488268852234	450	272.36375096627967	4.903282691886409	282.5074278586544	261.25111964461394	900000	0.9977827050997783	0.25
285.0848546028137	500	287.7198147282906	4.577012391330121	297.60025853291154	272.9589710595028	1000000	0.998003992015968	0.25
288.1168441772461	501	283.6469191965413	16.49152046046605	294.3010392077267	126.14731407893123	1002000	0.99800796812749	0.25
