Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.939091920852661	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
45.4713716506958	10	22.51190645890332	12.539165500555509	45.34536668565124	-2.248489559322479	1000000	2.315795652954842	1.5705252465301827
82.84828090667725	20	40.6588302442464	4.342325415870607	48.52922317478806	32.47498907032423	2000000	2.4710461414152425	2.801650086991962
119.98881769180298	30	41.353087967581615	3.4992336141662332	48.32354948669672	33.21826757886447	3000000	2.3711594033489827	2.801650086991962
156.8546326160431	40	42.25163517968097	3.551844398995174	49.96025422634557	34.28267486765981	4000000	2.3712320001172436	2.801650086991962
194.39413952827454	50	38.62773065723559	5.917110059164563	50.64214977156371	28.207655407721177	5000000	2.3456977627988578	2.801650086991962
232.6266233921051	60	42.14722913349353	4.672845668728884	53.08322370424867	31.973505929578096	6000000	2.350258730548645	2.801650086991962
269.6134853363037	70	41.946920402661675	4.795112072503966	51.61130714369938	30.47301035700366	7000000	2.327238154469901	2.801650086991962
306.1261999607086	80	43.27226179649384	3.606008558084331	50.88372377259657	35.771808105520904	8000000	2.3169753388187653	2.801650086991962
343.2967116832733	90	44.173781269577304	2.7097287526100318	50.415045481175184	37.85969873087015	9000000	2.3170453305992793	2.801650086991962
381.0191345214844	100	44.06006444583734	3.338798694503342	49.65997625910677	36.6373460101895	10000000	2.3120510631013764	2.801650086991962
