Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.851481199264526	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
37.34815549850464	50	189.66679399909307	3.381560534698428	198.66103221231606	181.63653297696146	100000	7.795207859557164	7.244088726287992
65.78321671485901	100	333.2156524014719	2.7790106551347997	338.52962427504826	327.07047127650003	200000	7.806290361284664	7.244088726287992
93.94409847259521	150	347.3300772439761	2.5834158577575717	354.52649072918575	341.1031880368828	300000	7.873252527983758	8.260889465720847
121.62562656402588	200	353.49547000293825	2.178554542117164	358.0222038151114	348.2299251265358	400000	7.922712870164038	8.260889465720847
149.51819014549255	250	354.85517306893854	1.4882817694034494	358.31973473366816	350.6744839765015	500000	7.917004198106848	8.260889465720847
183.99739480018616	300	355.83007945629373	2.0375204870875785	359.0336326495162	349.7603846199345	600000	7.976883862298002	8.260889465720847
219.4096236228943	350	354.2083780568119	2.13266015020752	358.2118213031208	347.8725435640663	700000	8.014823322224014	8.260889465720847
254.38837933540344	400	352.48836950879615	1.9713632214418944	359.1339038959122	348.95286998231313	800000	8.002709765920699	8.260889465720847
291.78304266929626	450	354.19327290448877	1.3859796313049106	357.1903230092721	351.33145071798936	900000	8.005599677931956	8.260889465720847
326.49253392219543	500	357.80589419170474	1.0933285905821777	359.8223212055891	353.977294231765	1000000	7.990724194292266	8.260889465720847
330.28853726387024	501	354.1814555012526	1.1401596434590031	356.0278806928545	351.45517854217906	1002000	7.987060766950517	8.260889465720847
