Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.543645143508911	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
37.07405138015747	50	219.1829126821774	5.184604129372486	225.9821170043142	201.57025253411848	100000	8.136891099643073	6.88414960492412
69.61917471885681	100	225.28069168041074	2.938828561347074	236.1198220285587	220.6768341846764	200000	8.016408221695082	7.156567048617384
98.72524237632751	150	259.4845600473528	1.1449952702076895	261.9157843698049	256.444013774395	300000	7.9470488165577535	7.156567048617384
126.92653441429138	200	276.8275399882952	1.763292527579677	281.86053633876145	271.8012515641749	400000	8.027269242576464	7.156567048617384
156.48209238052368	250	300.31411732461794	1.6782789956576065	303.3226548653911	296.64286261587404	500000	8.039354559592175	7.156567048617384
184.84119653701782	300	338.8492982072019	1.5962249677482965	342.3093271808757	335.1888155915076	600000	8.009141322508443	7.156567048617384
212.94642400741577	350	351.96449548139367	2.035783144124723	355.58245742441795	345.1515188230551	700000	7.970251946737752	7.156567048617384
241.36175751686096	400	348.9226321324856	1.4253560392383402	351.74369958846364	346.08225257054437	800000	7.9792926626237906	7.156567048617384
269.93297696113586	450	352.3738512170992	1.735089259989649	356.1987568809418	348.1619251141674	900000	7.997499275858568	7.156567048617384
298.53459644317627	500	352.4941118438475	1.5629907464123591	358.89179878216237	350.0278396558715	1000000	7.983113504433291	7.176210975120038
301.7332875728607	501	354.11610324466574	2.83447302571833	359.47328965662746	346.6791543061845	1002000	7.985504192200526	7.176210975120038
