Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.939521312713623	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
71.11053848266602	10	329.37640567233075	2.82784707463939	337.3986028714571	322.00156153342687	1000000	3.0447777989693985	2.448675260676079
130.06946897506714	20	352.88159084976303	2.541295533351192	358.0707110705407	347.7650296314532	2000000	2.9757159851110764	2.448675260676079
182.8467779159546	30	353.5660565237024	2.2560880380207236	358.23744160484057	347.5773130323796	3000000	2.738821262062119	2.448675260676079
240.0635585784912	40	356.5104557522745	2.40001526947633	360.69515226455405	350.14701079277984	4000000	2.643087299227552	2.448675260676079
296.85489869117737	50	356.83060491742935	2.746937451601747	361.73217192015727	347.2285376639047	5000000	2.612319037318466	2.448675260676079
352.32282280921936	60	354.6499526141165	2.2953679132046734	359.53677278058603	346.068462519499	6000000	2.5631730249377145	2.448675260676079
407.2103786468506	70	357.0560437755307	2.3365800746322147	361.36082003696356	349.9506594205741	7000000	2.565144216532151	2.448675260676079
463.437148809433	80	357.7569263977865	2.244109664074575	361.8269621350337	349.60470075233025	8000000	2.509354153965455	2.448675260676079
515.1788096427917	90	354.5536719752691	2.079533448165725	359.8063226423692	348.9086696404265	9000000	2.4506101692939146	2.448675260676079
572.779586315155	100	354.3570052629708	2.2123375834329653	359.22762498119846	347.0211191168055	10000000	2.430829586394336	2.448675260676079
