Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.2662034034729	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
50.962883710861206	10	213.16561765929598	3.6145516188547915	221.73112957074773	203.99880061295698	1000000	1.7100633324506982	1.3168584415658402
91.40008807182312	20	332.02702376586683	3.1467184668849932	338.38549140281975	323.40566312125884	2000000	2.004900896828082	1.3168584415658402
132.09784364700317	30	347.26109216589316	2.17559081237848	353.6953625588503	342.739210274769	3000000	1.9634191762205342	1.337510554048637
173.35723996162415	40	352.27212279487327	2.499223173799888	357.23229159461334	347.06329559045844	4000000	1.8170123487272778	1.337510554048637
214.37368273735046	50	353.20067988553194	2.685868102761422	358.89274223256507	346.45740035688505	5000000	1.7385330367972776	1.337510554048637
256.01604175567627	60	353.0219153529173	2.1213892097346227	357.08159267599694	348.56372103389003	6000000	1.6570925429880201	1.337510554048637
297.38574624061584	70	354.40875552114426	2.4262363422798456	359.8308010697365	348.5209327074699	7000000	1.600215765773125	1.337510554048637
338.1708915233612	80	355.0829433198425	2.038539272247426	359.8931123461007	351.00299295189325	8000000	1.5520305499634037	1.337510554048637
380.5007572174072	90	354.4820961284346	2.1151400686715194	360.4873597160913	350.24045480170753	9000000	1.513280239836475	1.337510554048637
422.3313190937042	100	355.30000758695724	1.7105120006220653	359.2282750448212	350.5578571522492	10000000	1.4991196612479458	1.337510554048637
