Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.11312508583069	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
83.02882623672485	10	234.39899824566652	2.6729886202556132	241.5040158382617	229.2088268804364	1000000	1.5974418961900272	0.5
148.86945581436157	20	312.82472061747507	2.6883279518450354	319.96118282328825	307.08858652296476	2000000	1.6289945143624736	0.5
216.3237488269806	30	343.3598281936317	1.702237067324993	348.30624897556845	338.93471209311974	3000000	1.648640147104303	0.5
283.7070860862732	40	348.87581167467744	2.149646826374651	354.7147409841418	345.28759971569525	4000000	1.6266305361795566	0.5
345.32024216651917	50	350.8002862304292	2.267013668424591	356.5118837716291	345.27548310765997	5000000	1.6154648678885373	0.5
409.9847674369812	60	353.9948485776694	2.3977912806889123	358.53134284297994	344.9037557080155	6000000	1.5980532303245427	0.5
475.20584774017334	70	352.5633686640765	2.221022097908738	358.5686236495094	347.898299819557	7000000	1.5861548178362066	0.5
541.9184105396271	80	355.52467613956725	2.126650087853385	359.142438959796	349.25440851673557	8000000	1.5786629842616327	0.5
609.1272759437561	90	355.8950871790558	2.012802894289152	359.55595026756055	349.26150902948575	9000000	1.5641043744130751	0.5
676.2743082046509	100	354.90314921744016	1.8308422702301255	359.78575017140247	350.26409733947366	10000000	1.5577432591360298	0.5
