Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
10.664777278900146	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
40.692938804626465	50	96.4270975095814	5.223602008344359	106.29229261062574	83.66935414727777	100000	7.7952078595571646	7.244088726287992
71.37985038757324	100	124.90533345303365	4.369313537594598	132.89688182645477	116.80306881875731	200000	7.806290361284666	7.244088726287992
100.23706769943237	150	332.6828102818338	2.794931266864835	336.7816283227876	323.3842374468222	300000	7.87325252798376	8.260889465720844
128.8767318725586	200	351.429300067375	1.665609955192258	354.84041034337133	345.2456283720967	400000	7.922712870164038	8.260889465720844
157.4665744304657	250	341.47515993682913	1.7250514744043342	345.41276972333435	336.2482967257092	500000	7.917004198106848	8.260889465720844
190.2192633152008	300	341.0203786123786	3.3367469424228644	346.8134469416691	328.25313085946254	600000	7.976883862298002	8.260889465720844
219.66085958480835	350	349.3176576330815	3.870215204593168	356.99816983373603	339.18439681536984	700000	8.014823322224014	8.260889465720844
249.81611275672913	400	337.50560039299074	3.904620206248206	343.5159368159948	325.6396844840492	800000	8.002709765920699	8.260889465720844
279.7055847644806	450	351.2642478403997	2.5505089240700456	357.3448038044735	343.9091944398824	900000	8.005599677931956	8.260889465720844
309.36331510543823	500	343.1024743695847	5.134738649948079	349.29514059871144	328.0623091944726	1000000	7.990724194292266	8.260889465720844
312.5568685531616	501	348.5521883825492	4.976527083767699	356.12149647651495	335.7662243556697	1002000	7.987060766950517	8.260889465720844
